﻿<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" dtd-version="1.1" specific-use="sps-1.9" article-type="review-article" xml:lang="en">
<front>
<journal-meta>
<journal-id journal-id-type="publisher-id">abcic</journal-id>
<journal-title-group>
<journal-title>ABC Imagem Cardiovascular</journal-title>
<abbrev-journal-title abbrev-type="publisher">ABC Imagem Cardiovasc.</abbrev-journal-title>
</journal-title-group>
<issn pub-type="epub">2675-312X</issn>
<issn pub-type="ppub">2318-8219</issn>
<publisher>
<publisher-name>Departamento de Imagem Cardiovascular da Sociedade Brasileira de Cardiolodia (DIC/SBC)</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="doi">10.36660/abcimg.20250058i</article-id>
<article-id pub-id-type="publisher-id">abcimg.20250058i</article-id>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Review Article</subject>
</subj-group>
</article-categories>
<title-group>
<article-title>Convolutional Neural Network Applications In Cardiac Imaging</article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0002-4178-0651</contrib-id>
<name><surname>Fernandes</surname><given-names>Luiz Henrique Cartaxo</given-names></name>
<role>Acquisition of data</role>
<role>Analysis and interpretation of the data</role>
<role>Writing of the manuscript</role>
<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
<xref ref-type="corresp" rid="c1"/>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0003-0129-391X</contrib-id>
<name><surname>Dantas</surname><given-names>José Lucas Formiga</given-names></name>
<role>Acquisition of data</role>
<role>Analysis and interpretation of the data</role>
<role>Writing of the manuscript</role>
<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0009-0004-8820-8515</contrib-id>
<name><surname>Lima</surname><given-names>Marilia Graziela Vieira de Macena</given-names></name>
<role>Acquisition of data</role>
<role>Analysis and interpretation of the data</role>
<role>Writing of the manuscript</role>
<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0001-8081-9734</contrib-id>
<name><surname>Donato</surname><given-names>Glaudir</given-names></name>
<role>Analysis and interpretation of the data</role>
<role>Critical revision of the manuscript for intellectual content</role>
<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0001-8809-8783</contrib-id>
<name><surname>Melo</surname><given-names>Marcelo Dantas Tavares de</given-names></name>
<role>Conception and design of the research</role>
<role>Critical revision of the manuscript for intellectual content</role>
<xref ref-type="aff" rid="aff2"><sup>2</sup></xref>
</contrib>
<aff id="aff1">
<label>1</label>
<institution content-type="orgname">Universidade Federal da Paraíba</institution>
<institution content-type="orgdiv1">Centro de Ciências Médicas</institution>
<addr-line>
<named-content content-type="city">João Pessoa</named-content>
<named-content content-type="state">PB</named-content>
</addr-line>
<country country="BR">Brasil</country>
<institution content-type="original">Centro de Ciências Médicas, Universidade Federal da Paraíba, João Pessoa, PB – Brasil</institution>
</aff>
<aff id="aff2">
<label>2</label>
<institution content-type="orgname">Universidade Federal da Paraíba</institution>
<institution content-type="orgdiv1">Departamento de Medicina Interna</institution>
<addr-line>
<named-content content-type="city">João Pessoa</named-content>
<named-content content-type="state">PB</named-content>
</addr-line>
<country country="BR">Brasil</country>
<institution content-type="original">Departamento de Medicina Interna, Universidade Federal da Paraíba, João Pessoa, PB – Brasil</institution>
</aff>
</contrib-group>
<author-notes>
<corresp id="c1"><label>Mailing Address:</label> <bold>Luiz Henrique Cartaxo Fernandes</bold> • Universidade Federal da Paraíba – Centro de Ciências Médicas. Cidade Universitária, s/n – Conj. Pres. Castelo Branco III. Postal Code: <postal-code>58051-900</postal-code>. João Pessoa, PB – Brazil E-mail: <email>luiz.cartaxo@academico.ufpb.br</email></corresp>
<fn fn-type="coi-statement"><label>Potential conflict of interest</label>
<p>No potential conflict of interest relevant to this article was reported.</p></fn>
<fn fn-type="edited-by"><label>Editor responsible for the review:</label> <p>Marcelo Tavares</p></fn>
</author-notes>
<pub-date publication-format="electronic" date-type="pub">
<day>17</day>
<month>11</month>
<year>2025</year>
</pub-date>
<pub-date publication-format="electronic" date-type="collection">
<year>2025</year>
</pub-date>
<volume>38</volume>
<issue>3</issue>
<elocation-id>e20250058</elocation-id>
<history>
<date date-type="received">
<day>13</day>
<month>08</month>
<year>2025</year>
</date>
<date date-type="rev-recd">
<day>29</day>
<month>08</month>
<year>2025</year>
</date>
<date date-type="accepted">
<day>29</day>
<month>08</month>
<year>2025</year>
</date>
</history>
<permissions>
<license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by/4.0/" xml:lang="en">
<license-p>This is an open-access article distributed under the terms of the Creative Commons Attribution License</license-p>
</license>
</permissions>
<abstract>
<title>Abstract</title>
<p>Neural networks are computer models that mimic the workings of the human brain, learning from large volumes of data to perform increasingly complex tasks. This is done by means of interconnected artificial neurons that propagate information from raw layers to refined layers, sometimes of a weighted nature, weaving in the classification or identification of non-linear patterns. The Convolutional Neural Network (CNN) is a specialized deep learning architecture designed to extract and analyze spatial patterns within images, enabling applications in diagnostic decision-making and longitudinal clinical monitoring. Its use in Computed Tomography and Magnetic Resonance Imaging through cardiac image segmentation makes it possible to quickly and efficiently define cardiac structures, playing an important role in the reconstruction of three-dimensional images and in supporting preoperative procedures. In addition, compared to other forms of conventional analysis, it guarantees objective interpretations and superior image quality, based on the removal of artifacts from the studied segment. Echocardiograms have shown good results in identifying pathologies such as pulmonary hypertension, amyloidosis, hypertrophic cardiomyopathy and congenital diseases, and studies on the automation of these exams have shown an opening for what could be a dissemination framework in more remote areas where manual operators are not available. Consequently, CNN-based approaches have the potential to streamline cardiovascular imaging workflows, minimize inter-observer variability, and expand diagnostic capabilities to underserved and remote regions with limited access to specialized care.</p>
</abstract>
<kwd-group xml:lang="en">
<title>Keywords</title>
<kwd>Computer Neural Networks</kwd>
<kwd>Artificial Intelligence</kwd>
<kwd>Cardiac Imaging Techniques</kwd>
</kwd-group>
<funding-group>
<funding-statement>There were no external funding sources for this study</funding-statement>
</funding-group>
<counts>
<fig-count count="2"/>
<table-count count="0"/>
<equation-count count="0"/>
<ref-count count="62"/>
</counts>
</article-meta>
</front>
<body>
<fig id="f1">
<caption>
<title>Applications of Convolutional Neural Networks in different types of diagnostic imaging methods in cardiology.</title>
<p>AF: Atrial Fibrilation; CAD: Coronary artery disease; CT: Computed Tomography; ECO: Echocardiography; HCM: Hypertrophic Cardiomyopathy; IAC: Interatrial Communication; MRI: Magnetic Imaging Resonance; OCT: Optical Coherence Tomography; PAH: Pulmonary Arterial Hypertension; PDA: Patent Ductus Arteriosus; SPECT-MPI: Single Photon Emission Computed Tomography – Myocardial Perfusion Imaging.</p></caption>
<graphic xlink:href="2675-312X-abcic-38-03-e20250058-gf01.tif"/>
</fig>
<sec sec-type="intro">
<title>Introduction</title>
<p>The human nervous system is one of the most efficient ways of capturing and interpreting data, reflecting the stimuli and experiences to which the body is subjected throughout life.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> According to the phenomenon of neuroplasticity, all these interactions dictate brain modifications, being adapted for decision-making and allowing pre-existing knowledge to be learned and act as a basis for the creation of new information circuits.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
<p>Neural networks have emerged as artificial models that try to recover this processing quickly and effectively in order to solve the problems raised, becoming important tools in the dynamic field of artificial intelligence (AI).<sup><xref ref-type="bibr" rid="B3">3</xref></sup> In order to overcome this challenge, networks are trained to identify recognition patterns from thousands or millions of examples, making it possible to build the system&apos;s own learning.<sup><xref ref-type="bibr" rid="B4">4</xref></sup> This happens through what is called &quot;input&quot;, i.e. any new concept that is inserted into the ordering. The set of inputs generates a response, the &quot;output&quot;, which can be influenced in a weighted way, always taking a reference standard as its essence.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
<p>This can be exemplified simply: in the assessment of a patient with suspected atrial fibrillation (AF), when an electrocardiogram is requested for investigation, each voltage in the tracing can take on the role of an input neuron, which can continue to influence the cascade and serve as a new input for the next neuron, solidifying the final response.<sup><xref ref-type="bibr" rid="B6">6</xref></sup> Thus, if the diagnosis is AF when there is no corresponding tracing, the weights that led to that result are reduced. On the other hand, if there is a match, they are strengthened and reused in subsequent analyses.<sup><xref ref-type="bibr" rid="B7">7</xref></sup> In addition, extra notions can be added, such as the patient&apos;s age, gender and comorbidities.</p>
<p>The application of AI in the medical field has been widely explored and, in recent years, has become a disruptive technology for interpreting images.<sup><xref ref-type="bibr" rid="B8">8</xref></sup> Within this context, the Convolutional Neural Network (CNN) has emerged as a version of this processing aimed at recognizing and classifying images, reducing the computational effort and improving its robustness.<sup><xref ref-type="bibr" rid="B8">8</xref></sup> The hierarchical arrangement of multiple convolutional layers allows CNNs to progressively transform low-level features – such as pixel intensity gradientes – into increasingly abstract and clinically relevant representations.<sup><xref ref-type="bibr" rid="B9">9</xref></sup> During the training period, the CNN exercises and individualizes its filters according to the task to be performed. In a way, image classification starts by detecting the edges of coarser pixels in the initial layer, using this to detect simple shapes in the second layer and so on, allowing more complex features to be distinguished. Finally, the last layer is responsible for advanced image reading, based on the filters built.<sup><xref ref-type="bibr" rid="B10">10</xref></sup></p>
<p>The advantages of CNN over other neural networks is that it establishes the vital resources for successful prediction, reducing the dimensionality of the resources in the previous layer.<sup><xref ref-type="bibr" rid="B11">11</xref></sup></p>
<p>Accurate segmentation of cardiac images is essential for clinical decision making, and Deep Learning techniques and the use of CNN have shown remarkable results in this area, although their quantification and analysis remains an ongoing challenge due to the complexity of cardiac substructures and existing anatomical variability. The individualization of this analysis is essential to solidify objective evidence of the most varied pathologies investigated, facilitating diagnosis, monitoring and clinical follow-up of the patient.<sup><xref ref-type="bibr" rid="B12">12</xref></sup></p>
<p>In this approach, through the image segmentation method, the convolutional neural network enables fast and efficient responses. This is because in certain situations, the presence of certain features is more important than others. Sometimes recognizing the location of an alteration in the heart chamber is the only essential objective, and it is not necessary to see these structures with high pixel definition.<sup><xref ref-type="bibr" rid="B13">13</xref></sup></p>
<p>The application scenario covers a wide range of imaging exams, from use in echocardiography to calculate end-systolic and end-diastolic volume, through to the ability to assess the ventricular or atrial space in multiple slices, as well as the observation of coronary calcification plaques through CT-guided coronary angiography (CCTA). The range of applications of CNNs in cardiac imaging is highlighted in the Central Illustration. For the most part, these aspects are supported by figures and engravings from atlases or other documents that are included in the model&apos;s database. Another interesting point is that there are already studies using the system itself to weave in and ensure the quality of ultrasounds and other tests made available.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
<sec>
<title>Applications of CNN in CT</title>
<p>The use of convolutional neural networks has excelled in automating the segmentation of cardiac and vascular structures in computed tomography (CT) images, a process by which cardiac structures or pathological lesions are delimited.<sup><xref ref-type="bibr" rid="B5">5</xref>,<xref ref-type="bibr" rid="B12">12</xref>,<xref ref-type="bibr" rid="B13">13</xref></sup> The segmentation of cardiac images by CT has clinical relevance in the identification of valvular heart disease, evaluation of coronary artery disease, diagnosis of congenital heart disease, preoperative planning and in extracardiac indications.<sup><xref ref-type="bibr" rid="B12">12</xref></sup> The application of CNNs has brought speed and efficiency to the cardiac segmentation process, since it was previously carried out manually and subjectively by radiologists. In a study of the segmentation of cardiac chambers and great vessels, Sharkey et al. presented results indicating that the variability of analysis between observers is similar to the variability between the observer and the CNN.<sup><xref ref-type="bibr" rid="B14">14</xref></sup> These findings support the premise that CNN-based segmentation can deliver reproducible, objective, and diagnostically accurate results, comparable to expert manual assessment.</p>
<p>With regard to the identification of anatomical structures, Chen, et al. showed that the convolutional neural network proved to be an accurate and efficient tool for assessing the volume and three-dimensional reconstruction of the left atrium.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> The calculation of volume by CNN proved to be capable of predicting the risk of recurrence of atrial fibrillation in patients after catheter ablation. Astudillo, et al. used a CNN technique to identify the coronary cusps and the right and left coronary ostia on multi-detector row computed tomography.<sup><xref ref-type="bibr" rid="B16">16</xref></sup> These structures are important reference points for defining the perimeter and area of the aortic annulus and, consequently, the aortic valve prostheses to be implanted by transcatheter means. The method proved to be reproducible and reliable, and could be applied in routine preoperative planning in order to reduce time spent and accuracy in defining reference points.</p>
<p>CNNs have also proved to be excellent tools for identifying pathological images in coronary angiography. Coronary computed tomography angiography is an important method for assessing the severity of arterial stenosis, as well as being highly accurate in quantifying atherosclerosis when compared to intravascular ultrasound. In a multicenter study, a neural network was trained to segment coronary plaques.<sup><xref ref-type="bibr" rid="B17">17</xref></sup> The study showed excellent agreement between the Deep Learning tool and the measurements of experienced readers regarding the volume of the atheroma plaque and the degree of arterial stenosis. There was also agreement with vascular ultrasound measurements, as well as prognostic value in terms of the risk of future acute myocardial infarction.</p>
<p>Quantification of epicardial adipose tissue can also be optimized through the use of CNNs. Epicardial adipose tissue is a metabolically active depot of visceral fat and may be related to visceral obesity and metabolic syndrome.<sup><xref ref-type="bibr" rid="B18">18</xref></sup> Coronary angiography is the gold standard for identifying epicardial adipose tissue, but its manual quantification is laborious and challenging. In this scenario, West et al. developed a CNN to automatically quantify epicardial adipose tissue and identify its clinical association with cardiac and non-cardiac diseases.<sup><xref ref-type="bibr" rid="B19">19</xref></sup> The method proved to be accurate, fast and reproducible for quantifying epicardial adiposity using coronary angiography. The tool was also able to show good prognostic value for mortality in general and for cardiovascular events.</p>
</sec>
<sec>
<title>Applications of CNN in MRI</title>
<p>In recent years, magnetic resonance imaging has become an excellent tool for investigating cardiovascular diseases, with a high capacity to provide complex diagnoses.<sup><xref ref-type="bibr" rid="B20">20</xref>,<xref ref-type="bibr" rid="B21">21</xref></sup> It is a non-invasive, versatile method free of ionizing radiation, capable of identifying structure, function, flow and characterization of cardiac tissue. Late gadolinium enhancement and T1/T2 mapping have added important information about cardiac viability and pathologies such as tissue infarction and diffuse myocardial fibrosis. The development of flow MRI has also brought major advances by providing blood flow information in several planes, which allows the identification of intracardiac shunts.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> However, the lengthy scanning process and slow image production are disadvantages of MRI. MRI images must take cardiac and respiratory movement into account to avoid artifacts, which must be suppressed by reconstruction algorithms. In this scenario, Deep learning–based reconstruction methods have demonstrated superior performance compared with conventional algorithms, yielding higher-fidelity images, enhanced artifact suppression, and substantially reduced processing times.</p>
<p>Hauptmann, et al. trained a three-dimensional residual CNN in U-Net to remove spatio-temporal artifacts in subsampling real-time MRI data from images of patients with congenital heart disease.<sup><xref ref-type="bibr" rid="B22">22</xref></sup> Artifact removal by the CNN was compared with the conventional compression sensing technique, a tool that requires intense and time-consuming computational reconstruction. The CNN-based method achieved artifact suppression over five times faster than the compressed sensing approach, while delivering superior image quality and more accurate ventricular volumetric measurements. El-Rewaidy et al. also presented important results on the reconstruction of MRI images with delayed gadolinium enhancement using a convolutional neural network.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> Compared to the compression sensing technique, image reconstruction using CNN was 300 times faster.</p>
<p>CNNs have influenced multiple stages of the MRI workflow, from image acquisition planning and real-time reconstruction to post-processing tasks such as quantitative analysis and prognostic modeling. Like CT, MRI also plays an important role in the segmentation and consequent identification of cardiac structures.<sup><xref ref-type="bibr" rid="B24">24</xref></sup> In this process using MRI, the use of CNNs has also been related to greater efficiency.<sup><xref ref-type="bibr" rid="B25">25</xref></sup> Sander et al. used a CNN to perform the segmentation of cardiac structures and another auxiliary CNN to automatically identify areas of segmentation failure.<sup><xref ref-type="bibr" rid="B26">26</xref></sup> The study showed that cardiac image segmentation using CNNs associated with the manual correction of detected segmentation failures resulted in increased performance.</p>
<p>In terms of disease identification, many studies have used conventional image indices as input data for neural networks to diagnose heart disease. For example, cardiac scarring identified on magnetic resonance imaging is associated with unfavorable cardiovascular outcomes. Bekheet, et al., developed a CNN called FibrosisNet to diagnose cardiac fibrosis on MRI, showing high diagnostic accuracy and precision.<sup><xref ref-type="bibr" rid="B27">27</xref></sup> Sharifrazi et al., obtained important results by combining a deep convolutional neural network with the K-means clustering technique, forming CNN-KCL, to diagnose and classify myocarditis based on MRI image data.<sup><xref ref-type="bibr" rid="B28">28</xref></sup> The technique using CNN outperformed other traditional Machine Learning algorithms in classifying myocarditis in terms of accuracy and precision.</p>
</sec>
<sec>
<title>Applications of CNN in echocardiography</title>
<p>Echocardiography is the most easily accessible and widely used imaging method for assessing cardiac structure and function. Its advantages include rapid image acquisition and the absence of ionizing radiation, which make it an efficient and democratic method. Echocardiography can be used both to screen asymptomatic patients and to diagnose and follow up cardiac conditions.<sup><xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B30">30</xref></sup> As it is an operator-dependent test, it requires a certain degree of experience on the part of the professional, and there can be variations in interpretation.<sup><xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B31">31</xref></sup></p>
<p>When it comes to applying automated image interpretation to echocardiography, there are some intrinsic challenges to this method. The echocardiogram consists of generating both static images, as well as videos and Doppler recordings collected from different points of view to obtain the desired parameters. In addition, the values obtained in the measurements can vary greatly due to the intrinsic variability of heartbeats. There is also the variation that already exists when extrapolating measurements from two-dimensional images to measurements of the three-dimensional object.<sup><xref ref-type="bibr" rid="B32">32</xref>,<xref ref-type="bibr" rid="B33">33</xref></sup></p>
<p>Despite these impasses and given the complexity of the diagnostic method in question, an automated learning approach would bring many benefits and assist human interpretation, as it would allow automatic identification and classification of views. In fact, the use of Deep Learning (DL), and more specifically Convolutional Neural Networks (CNNs), to train artificial intelligence in the interpretation of echocardiograms would make it possible to reduce costs and, consequently, democratize this test. This technological integration could enable echocardiographic acquisition by operators with limited specialized training, thereby facilitating access to cardiac imaging in geographically remote or resource-limited settings.<sup><xref ref-type="bibr" rid="B32">32</xref></sup></p>
<p>Several studies have shown the effectiveness of using CNNs in echocardiography. Among the applications observed, the majority are for quantifying the structure and function of the heart and for cardiac segmentation.<sup><xref ref-type="bibr" rid="B10">10</xref>,<xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B34">34</xref>–<xref ref-type="bibr" rid="B38">38</xref></sup> It has also been used in the detection of left ventricular hypertrophy,<sup><xref ref-type="bibr" rid="B39">39</xref>–<xref ref-type="bibr" rid="B41">41</xref></sup> aortic stenosis,<sup><xref ref-type="bibr" rid="B42">42</xref>,<xref ref-type="bibr" rid="B43">43</xref></sup> identification of cardiac phases,<sup><xref ref-type="bibr" rid="B44">44</xref></sup> early detection of acute myocardial infarction<sup><xref ref-type="bibr" rid="B45">45</xref></sup> and classification of cardiac visualizations.<sup><xref ref-type="bibr" rid="B46">46</xref>,<xref ref-type="bibr" rid="B47">47</xref></sup> The model used by Ghorbani et al, in addition to accurately identifying elements of cardiac structure and function, trained a CNN to predict systemic phenotypes that modify cardiovascular risk, such as age, gender, height and weight, from echocardiogram images.<sup><xref ref-type="bibr" rid="B29">29</xref></sup></p>
<p>Zhang et al went further and trained a convolutional neural network for fully automated interpretation of echocardiograms, including visualization identification, image segmentation, quantification of heart structure and function, and disease detection. This study demonstrated success in the automated analysis of view type and image segmentation. With regard to the structure and function of the heart, there was some discrepancy between manual and automated measurements, especially of the structure, with a tendency to overestimate the values. Finally, the model was successful in identifying pulmonary arterial hypertension (PAH), amyloidosis and hypertrophic cardiomyopathy, based on analysis of the masses, structure and function of the heart chambers.<sup><xref ref-type="bibr" rid="B32">32</xref></sup></p>
<p>Recent studies have also evaluated the capacity for automatic diagnosis of pulmonary arterial hypertension and,<sup><xref ref-type="bibr" rid="B48">48</xref></sup> according to the results obtained by DuBrock et al,<sup><xref ref-type="bibr" rid="B49">49</xref></sup> the algorithm used is capable of speeding up the diagnosis of PAH by 6 to 18 months, an extremely relevant aspect in a disease where early diagnosis is crucial for effective control of the condition.<sup><xref ref-type="bibr" rid="B48">48</xref>,<xref ref-type="bibr" rid="B49">49</xref></sup></p>
<p>Another described pathology that can be identified by echocardiography using CNNs is occult atrial fibrillation (AF). Yuan et al developed a model that was able to distinguish between sinus rhythm and AF, as well as predicting the concomitant presence of paroxysmal AF in those with sinus rhythm. The model performed better than using clinical risk factors, transthoracic echocardiogram measurements, left atrial size or CHA<sub>2</sub>DS<sub>2</sub>VASc score.<sup><xref ref-type="bibr" rid="B50">50</xref></sup> Research using DL has also been carried out and obtained favorable results in the area of fetal and neonatal echocardiography, such as for the prenatal diagnosis of atrial septal defect<sup><xref ref-type="bibr" rid="B51">51</xref></sup> and for the identification of patent ductus arteriosus in neonates.<sup><xref ref-type="bibr" rid="B52">52</xref></sup></p>
</sec>
<sec sec-type="methods">
<title>Application of CNN in other methods</title>
<p>Single Photon Emission Computed Tomography (SPECT) of myocardial perfusion is a test that can identify the presence of myocardial ischemia and therefore coronary artery disease. Betancur et al analyzed the application of deep learning to this diagnostic method, aiming to verify the ability to automatically predict coronary disease through CNNs trained with myocardial perfusion images, compared to the usual method currently used. The result was greater efficacy and better detection sensitivity with the deep learning method.<sup><xref ref-type="bibr" rid="B53">53</xref></sup> Other studies have also evaluated the ability to automatically classify myocardial perfusion images. Papadrianos et al trained CNNs to identify three possible outputs - infarction, ischemia and normal perfusion - and all models evaluated presented positive and reliable results.<sup><xref ref-type="bibr" rid="B54">54</xref></sup> Su et al demonstrated the feasibility and accuracy of CNN-based diagnosis for CAD, with a system that is already used in practice and is capable of considerably reducing the time needed to interpret images.<sup><xref ref-type="bibr" rid="B55">55</xref></sup></p>
<p>X-ray fluoroscopy allows real-time visualization of the cardiac structure, which makes it an indispensable method for performing image-guided procedures, such as cardiac resynchronization therapy, angiography and endovascular aortic repair. Deep learning has also been successfully tested to aid these procedures, either by reducing video noise or by fusing preoperative data with intraoperative x-ray images in order to guide the intervention and reduce contrast exposure.<sup><xref ref-type="bibr" rid="B56">56</xref>–<xref ref-type="bibr" rid="B59">59</xref></sup> Studies have also shown better sensitivity and specificity in characterizing coronary lesions using optical coherence tomography when deep learning is applied.<sup><xref ref-type="bibr" rid="B60">60</xref>–<xref ref-type="bibr" rid="B62">62</xref></sup></p>
</sec>
<sec sec-type="conclusions">
<title>Conclusion</title>
<p>The application of CNN in cardiac image analysis has emerged as a versatile tool, contributing to accurate and rapid diagnoses. Its incorporation into cardiovascular imaging makes it possible to remove the bias of inter-observer variability, reduce image artifacts, improve the automation of measurements and, finally, overcome geographical barriers by allowing the evaluation of images acquired remotely and thus democratizing care. Future perspectives should focus on large-scale validation studies to confirm the generalizability and clinical robustness of CNN-based approaches across diverse patient populations and imaging protocols. Furthermore, integrating these algorithms into routine workflows will require addressing regulatory and interoperability challenges to ensure safe and effective adoption in real-world cardiovascular practice.</p>
</sec>
</sec>
</body>
<back>
<fn-group>
<fn fn-type="financial-disclosure" id="fn1"><label>Sources of funding</label>
<p>There were no external funding sources for this study.</p></fn>
<fn fn-type="other" id="fn2"><label>Study association</label>
<p>This study is not associated with any thesis or dissertation work.</p></fn>
<fn fn-type="other" id="fn3"><label>Ethics approval and consent to participate</label>
<p>This article does not contain any studies with human participants or animals performed by any of the authors.</p></fn>
<fn fn-type="other" id="fn4"><label>Use of Artificial Intelligence</label>
<p>The authors did not use any artificial intelligence tools in the development of this work.</p></fn>
</fn-group>
<sec sec-type="data-availability" specific-use="data-in-article">
<label>Data Availability</label>
<p>The underlying content of the research text is contained within the manuscript.</p>
</sec>
<ref-list>
<title>References</title>
<ref id="B1">
<label>1</label>
<element-citation publication-type="book">
<person-group person-group-type="author">
<name><surname>Rotta</surname><given-names>NT</given-names></name>
<name><surname>Ohlweiler</surname><given-names>L</given-names></name>
<name><surname>Riesgo</surname><given-names>RS</given-names></name>
</person-group>
<source>Transtornos da Aprendizagem</source>
<publisher-loc>Porto Alegre</publisher-loc>
<publisher-name>Artmed</publisher-name>
<year>2015</year>
</element-citation>
<mixed-citation>Rotta NT, Ohlweiler L, Riesgo RS. Transtornos da Aprendizagem. Porto Alegre: Artmed; 2015.</mixed-citation>
</ref>
<ref id="B2">
<label>2</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Costa</surname><given-names>RLS</given-names></name>
</person-group>
<article-title>Neuroscience and Learning</article-title>
<source>Rev Bras Educ</source>
<year>2023</year>
<volume>28</volume>
<elocation-id>e280010</elocation-id>
<pub-id pub-id-type="doi">10.1590/S1413-24782023280010</pub-id>
</element-citation>
<mixed-citation>Costa RLS. Neuroscience and Learning. Rev Bras Educ. 2023;28:e280010. doi: 10.1590/S1413-24782023280010.</mixed-citation>
</ref>
<ref id="B3">
<label>3</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Kriegeskorte</surname><given-names>N</given-names></name>
<name><surname>Golan</surname><given-names>T</given-names></name>
</person-group>
<article-title>Neural Network Models and Deep Learning</article-title>
<source>Curr Biol</source>
<year>2019</year>
<volume>29</volume>
<issue>7</issue>
<fpage>R231</fpage>
<lpage>R236</lpage>
<pub-id pub-id-type="doi">10.1016/j.cub.2019.02.034</pub-id>
</element-citation>
<mixed-citation>Kriegeskorte N, Golan T. Neural Network Models and Deep Learning. Curr Biol. 2019;29(7):R231-6. doi: 10.1016/j.cub.2019.02.034.</mixed-citation>
</ref>
<ref id="B4">
<label>4</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Krittanawong</surname><given-names>C</given-names></name>
<name><surname>Zhang</surname><given-names>H</given-names></name>
<name><surname>Wang</surname><given-names>Z</given-names></name>
<name><surname>Aydar</surname><given-names>M</given-names></name>
<name><surname>Kitai</surname><given-names>T</given-names></name>
</person-group>
<article-title>Artificial Intelligence in Precision Cardiovascular Medicine</article-title>
<source>J Am Coll Cardiol</source>
<year>2017</year>
<volume>69</volume>
<issue>21</issue>
<fpage>2657</fpage>
<lpage>2664</lpage>
<pub-id pub-id-type="doi">10.1016/j.jacc.2017.03.571</pub-id>
</element-citation>
<mixed-citation>Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial Intelligence in Precision Cardiovascular Medicine. J Am Coll Cardiol. 2017;69(21):2657-64. doi: 10.1016/j.jacc.2017.03.571.</mixed-citation>
</ref>
<ref id="B5">
<label>5</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Litjens</surname><given-names>G</given-names></name>
<name><surname>Ciompi</surname><given-names>F</given-names></name>
<name><surname>Wolterink</surname><given-names>JM</given-names></name>
<name><surname>de Vos</surname><given-names>BD</given-names></name>
<name><surname>Leiner</surname><given-names>T</given-names></name>
<name><surname>Teuwen</surname><given-names>J</given-names></name>
<etal/>
</person-group>
<article-title>State-of-the-Art Deep Learning in Cardiovascular Image Analysis</article-title>
<source>JACC Cardiovasc Imaging</source>
<year>2019</year>
<volume>12</volume>
<issue>8 Pt 1</issue>
<fpage>1549</fpage>
<lpage>1565</lpage>
<pub-id pub-id-type="doi">10.1016/j.jcmg.2019.06.009</pub-id>
</element-citation>
<mixed-citation>Litjens G, Ciompi F, Wolterink JM, de Vos BD, Leiner T, Teuwen J, et al. State-of-the-Art Deep Learning in Cardiovascular Image Analysis. JACC Cardiovasc Imaging. 2019;12(8 Pt 1):1549-65. doi: 10.1016/j.jcmg.2019.06.009.</mixed-citation>
</ref>
<ref id="B6">
<label>6</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Krittanawong</surname><given-names>C</given-names></name>
<name><surname>Johnson</surname><given-names>KW</given-names></name>
<name><surname>Rosenson</surname><given-names>RS</given-names></name>
<name><surname>Wang</surname><given-names>Z</given-names></name>
<name><surname>Aydar</surname><given-names>M</given-names></name>
<name><surname>Baber</surname><given-names>U</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning for Cardiovascular Medicine: A Practical Primer</article-title>
<source>Eur Heart J</source>
<year>2019</year>
<volume>40</volume>
<issue>25</issue>
<fpage>2058</fpage>
<lpage>2073</lpage>
<pub-id pub-id-type="doi">10.1093/eurheartj/ehz056</pub-id>
</element-citation>
<mixed-citation>Krittanawong C, Johnson KW, Rosenson RS, Wang Z, Aydar M, Baber U, et al. Deep Learning for Cardiovascular Medicine: A Practical Primer. Eur Heart J. 2019;40(25):2058-73. doi: 10.1093/eurheartj/ehz056.</mixed-citation>
</ref>
<ref id="B7">
<label>7</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>El-Taraboulsi</surname><given-names>J</given-names></name>
<name><surname>Cabrera</surname><given-names>CP</given-names></name>
<name><surname>Roney</surname><given-names>C</given-names></name>
<name><surname>Aung</surname><given-names>N</given-names></name>
</person-group>
<article-title>Deep Neural Network Architectures for Cardiac Image Segmentation</article-title>
<source>Artif Intell Life Sci</source>
<year>2023</year>
<volume>4</volume>
<fpage>100083</fpage>
<lpage>100083</lpage>
<pub-id pub-id-type="doi">10.1016/j.ailsci.2023.100083</pub-id>
</element-citation>
<mixed-citation>El-Taraboulsi J, Cabrera CP, Roney C, Aung N. Deep Neural Network Architectures for Cardiac Image Segmentation. Artif Intell Life Sci. 2023;4:100083. doi: 10.1016/j.ailsci.2023.100083.</mixed-citation>
</ref>
<ref id="B8">
<label>8</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Johnson</surname><given-names>KW</given-names></name>
<name><surname>Soto</surname><given-names>JT</given-names></name>
<name><surname>Glicksberg</surname><given-names>BS</given-names></name>
<name><surname>Shameer</surname><given-names>K</given-names></name>
<name><surname>Miotto</surname><given-names>R</given-names></name>
<name><surname>Ali</surname><given-names>M</given-names></name>
<etal/>
</person-group>
<article-title>Artificial Intelligence in Cardiology</article-title>
<source>J Am Coll Cardiol</source>
<year>2018</year>
<volume>71</volume>
<issue>23</issue>
<fpage>2668</fpage>
<lpage>2679</lpage>
<pub-id pub-id-type="doi">10.1016/j.jacc.2018.03.521</pub-id>
</element-citation>
<mixed-citation>Johnson KW, Soto JT, Glicksberg BS, Shameer K, Miotto R, Ali M, et al. Artificial Intelligence in Cardiology. J Am Coll Cardiol. 2018;71(23):2668-79. doi: 10.1016/j.jacc.2018.03.521.</mixed-citation>
</ref>
<ref id="B9">
<label>9</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Bizopoulos</surname><given-names>P</given-names></name>
<name><surname>Koutsouris</surname><given-names>D</given-names></name>
</person-group>
<article-title>Deep Learning in Cardiology</article-title>
<source>IEEE Rev Biomed Eng</source>
<year>2019</year>
<volume>12</volume>
<fpage>168</fpage>
<lpage>193</lpage>
<pub-id pub-id-type="doi">10.1109/RBME.2018.2885714</pub-id>
</element-citation>
<mixed-citation>Bizopoulos P, Koutsouris D. Deep Learning in Cardiology. IEEE Rev Biomed Eng. 2019;12:168-93. doi: 10.1109/RBME.2018.2885714.</mixed-citation>
</ref>
<ref id="B10">
<label>10</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Lau</surname><given-names>ES</given-names></name>
<name><surname>Di Achille</surname><given-names>P</given-names></name>
<name><surname>Kopparapu</surname><given-names>K</given-names></name>
<name><surname>Andrews</surname><given-names>CT</given-names></name>
<name><surname>Singh</surname><given-names>P</given-names></name>
<name><surname>Reeder</surname><given-names>C</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning-Enabled Assessment of Left Heart Structure and Function Predicts Cardiovascular Outcomes</article-title>
<source>J Am Coll Cardiol</source>
<year>2023</year>
<volume>82</volume>
<issue>20</issue>
<fpage>1936</fpage>
<lpage>1948</lpage>
<pub-id pub-id-type="doi">10.1016/j.jacc.2023.09.800</pub-id>
</element-citation>
<mixed-citation>Lau ES, Di Achille P, Kopparapu K, Andrews CT, Singh P, Reeder C, et al. Deep Learning-Enabled Assessment of Left Heart Structure and Function Predicts Cardiovascular Outcomes. J Am Coll Cardiol. 2023;82(20):1936-48. doi: 10.1016/j.jacc.2023.09.800.</mixed-citation>
</ref>
<ref id="B11">
<label>11</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Wang</surname><given-names>P</given-names></name>
<name><surname>Qiao</surname><given-names>J</given-names></name>
<name><surname>Liu</surname><given-names>N</given-names></name>
</person-group>
<article-title>An Improved Convolutional Neural Network-Based Scene Image Recognition Method</article-title>
<source>Comput Intell Neurosci</source>
<year>2022</year>
<volume>2022</volume>
<fpage>3464984</fpage>
<lpage>3464984</lpage>
<pub-id pub-id-type="doi">10.1155/2022/3464984</pub-id>
</element-citation>
<mixed-citation>Wang P, Qiao J, Liu N. An Improved Convolutional Neural Network-Based Scene Image Recognition Method. Comput Intell Neurosci. 2022;2022:3464984. doi: 10.1155/2022/3464984.</mixed-citation>
</ref>
<ref id="B12">
<label>12</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Alnasser</surname><given-names>TN</given-names></name>
<name><surname>Abdulaal</surname><given-names>L</given-names></name>
<name><surname>Maiter</surname><given-names>A</given-names></name>
<name><surname>Sharkey</surname><given-names>M</given-names></name>
<name><surname>Dwivedi</surname><given-names>K</given-names></name>
<name><surname>Salehi</surname><given-names>M</given-names></name>
<etal/>
</person-group>
<article-title>Advancements in Cardiac Structures Segmentation: A Comprehensive Systematic Review of Deep Learning in CT Imaging</article-title>
<source>Front Cardiovasc Med</source>
<year>2024</year>
<volume>11</volume>
<fpage>1323461</fpage>
<lpage>1323461</lpage>
<pub-id pub-id-type="doi">10.3389/fcvm.2024.1323461</pub-id>
</element-citation>
<mixed-citation>Alnasser TN, Abdulaal L, Maiter A, Sharkey M, Dwivedi K, Salehi M, et al. Advancements in Cardiac Structures Segmentation: A Comprehensive Systematic Review of Deep Learning in CT Imaging. Front Cardiovasc Med. 2024;11:1323461. doi: 10.3389/fcvm.2024.1323461.</mixed-citation>
</ref>
<ref id="B13">
<label>13</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Lüscher</surname><given-names>TF</given-names></name>
<name><surname>Wenzl</surname><given-names>FA</given-names></name>
<name><surname>D’Ascenzo</surname><given-names>F</given-names></name>
<name><surname>Friedman</surname><given-names>PA</given-names></name>
<name><surname>Antoniades</surname><given-names>C</given-names></name>
</person-group>
<article-title>Artificial Intelligence in Cardiovascular Medicine: Clinical Applications</article-title>
<source>Eur Heart J</source>
<year>2024</year>
<volume>45</volume>
<issue>40</issue>
<fpage>4291</fpage>
<lpage>4304</lpage>
<pub-id pub-id-type="doi">10.1093/eurheartj/ehae465</pub-id>
</element-citation>
<mixed-citation>Lüscher TF, Wenzl FA, D’Ascenzo F, Friedman PA, Antoniades C. Artificial Intelligence in Cardiovascular Medicine: Clinical Applications. Eur Heart J. 2024;45(40):4291-304. doi: 10.1093/eurheartj/ehae465.</mixed-citation>
</ref>
<ref id="B14">
<label>14</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Sharkey</surname><given-names>MJ</given-names></name>
<name><surname>Taylor</surname><given-names>JC</given-names></name>
<name><surname>Alabed</surname><given-names>S</given-names></name>
<name><surname>Dwivedi</surname><given-names>K</given-names></name>
<name><surname>Karunasaagarar</surname><given-names>K</given-names></name>
<name><surname>Johns</surname><given-names>CS</given-names></name>
<etal/>
</person-group>
<article-title>Fully Automatic Cardiac Four Chamber and Great Vessel Segmentation on CT Pulmonary Angiography Using Deep Learning</article-title>
<source>Front Cardiovasc Med</source>
<year>2022</year>
<volume>9</volume>
<fpage>983859</fpage>
<lpage>983859</lpage>
<pub-id pub-id-type="doi">10.3389/fcvm.2022.983859</pub-id>
</element-citation>
<mixed-citation>Sharkey MJ, Taylor JC, Alabed S, Dwivedi K, Karunasaagarar K, Johns CS, et al. Fully Automatic Cardiac Four Chamber and Great Vessel Segmentation on CT Pulmonary Angiography Using Deep Learning. Front Cardiovasc Med. 2022;9:983859. doi: 10.3389/fcvm.2022.983859.</mixed-citation>
</ref>
<ref id="B15">
<label>15</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Chen</surname><given-names>HH</given-names></name>
<name><surname>Liu</surname><given-names>CM</given-names></name>
<name><surname>Chang</surname><given-names>SL</given-names></name>
<name><surname>Chang</surname><given-names>PY</given-names></name>
<name><surname>Chen</surname><given-names>WS</given-names></name>
<name><surname>Pan</surname><given-names>YM</given-names></name>
<etal/>
</person-group>
<article-title>Automated Extraction of Left Atrial Volumes from Two-Dimensional Computer Tomography Images Using a Deep Learning Technique</article-title>
<source>Int J Cardiol</source>
<year>2020</year>
<volume>316</volume>
<fpage>272</fpage>
<lpage>278</lpage>
<pub-id pub-id-type="doi">10.1016/j.ijcard.2020.03.075</pub-id>
</element-citation>
<mixed-citation>Chen HH, Liu CM, Chang SL, Chang PY, Chen WS, Pan YM, et al. Automated Extraction of Left Atrial Volumes from Two-Dimensional Computer Tomography Images Using a Deep Learning Technique. Int J Cardiol. 2020;316:272-8. doi: 10.1016/j.ijcard.2020.03.075.</mixed-citation>
</ref>
<ref id="B16">
<label>16</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Astudillo</surname><given-names>P</given-names></name>
<name><surname>Mortier</surname><given-names>P</given-names></name>
<name><surname>Bosmans</surname><given-names>J</given-names></name>
<name><surname>De Backer</surname><given-names>O</given-names></name>
<name><surname>Jaegere</surname><given-names>P</given-names></name>
<name><surname>Iannaccone</surname><given-names>F</given-names></name>
<etal/>
</person-group>
<article-title>Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography</article-title>
<source>J Interv Cardiol</source>
<year>2020</year>
<volume>2020</volume>
<fpage>9843275</fpage>
<lpage>9843275</lpage>
<pub-id pub-id-type="doi">10.1155/2020/9843275</pub-id>
</element-citation>
<mixed-citation>Astudillo P, Mortier P, Bosmans J, De Backer O, Jaegere P, Iannaccone F, et al. Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography. J Interv Cardiol. 2020;2020:9843275. doi: 10.1155/2020/9843275.</mixed-citation>
</ref>
<ref id="B17">
<label>17</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Lin</surname><given-names>A</given-names></name>
<name><surname>Park</surname><given-names>C</given-names></name>
</person-group>
<source>HHS Public Access international multicentre study</source>
<year>2022</year>
<volume>4</volume>
<issue>4</issue>
<fpage>10</fpage>
<lpage>11</lpage>
</element-citation>
<mixed-citation>Lin A, Park C. HHS Public Access international multicentre study. 2022;4(4):10–1.</mixed-citation>
</ref>
<ref id="B18">
<label>18</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Oikonomou</surname><given-names>EK</given-names></name>
<name><surname>Antoniades</surname><given-names>C</given-names></name>
</person-group>
<article-title>The Role of Adipose Tissue in Cardiovascular Health and Disease</article-title>
<source>Nat Rev Cardiol</source>
<year>2019</year>
<volume>16</volume>
<issue>2</issue>
<fpage>83</fpage>
<lpage>99</lpage>
<pub-id pub-id-type="doi">10.1038/s41569-018-0097-6</pub-id>
</element-citation>
<mixed-citation>Oikonomou EK, Antoniades C. The Role of Adipose Tissue in Cardiovascular Health and Disease. Nat Rev Cardiol. 2019;16(2):83-99. doi: 10.1038/s41569-018-0097-6.</mixed-citation>
</ref>
<ref id="B19">
<label>19</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>West</surname><given-names>HW</given-names></name>
<name><surname>Siddique</surname><given-names>M</given-names></name>
<name><surname>Williams</surname><given-names>MC</given-names></name>
<name><surname>Volpe</surname><given-names>L</given-names></name>
<name><surname>Desai</surname><given-names>R</given-names></name>
<name><surname>Lyasheva</surname><given-names>M</given-names></name>
<etal/>
</person-group>
<article-title>Deep-Learning for Epicardial Adipose Tissue Assessment with Computed Tomography: Implications for Cardiovascular Risk Prediction</article-title>
<source>JACC Cardiovasc Imaging</source>
<year>2023</year>
<volume>16</volume>
<issue>6</issue>
<fpage>800</fpage>
<lpage>816</lpage>
<pub-id pub-id-type="doi">10.1016/j.jcmg.2022.11.018</pub-id>
</element-citation>
<mixed-citation>West HW, Siddique M, Williams MC, Volpe L, Desai R, Lyasheva M, et al. Deep-Learning for Epicardial Adipose Tissue Assessment with Computed Tomography: Implications for Cardiovascular Risk Prediction. JACC Cardiovasc Imaging. 2023;16(6):800-16. doi: 10.1016/j.jcmg.2022.11.018.</mixed-citation>
</ref>
<ref id="B20">
<label>20</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Oscanoa</surname><given-names>JA</given-names></name>
<name><surname>Middione</surname><given-names>MJ</given-names></name>
<name><surname>Alkan</surname><given-names>C</given-names></name>
<name><surname>Yurt</surname><given-names>M</given-names></name>
<name><surname>Loecher</surname><given-names>M</given-names></name>
<name><surname>Vasanawala</surname><given-names>SS</given-names></name>
 <etal/>
</person-group>
<article-title>Deep Learning-Based Reconstruction for Cardiac MRI: A Review</article-title>
<source>Bioengineering</source>
<year>2023</year>
<volume>10</volume>
<issue>3</issue>
<fpage>334</fpage>
<lpage>334</lpage>
<pub-id pub-id-type="doi">10.3390/bioengineering10030334</pub-id>
</element-citation>
<mixed-citation>Oscanoa JA, Middione MJ, Alkan C, Yurt M, Loecher M, Vasanawala SS, et al. Deep Learning-Based Reconstruction for Cardiac MRI: A Review. Bioengineering. 2023;10(3):334. doi: 10.3390/bioengineering10030334.</mixed-citation>
</ref>
<ref id="B21">
<label>21</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Argentiero</surname><given-names>A</given-names></name>
<name><surname>Muscogiuri</surname><given-names>G</given-names></name>
<name><surname>Rabbat</surname><given-names>MG</given-names></name>
<name><surname>Martini</surname><given-names>C</given-names></name>
<name><surname>Soldato</surname><given-names>N</given-names></name>
<name><surname>Basile</surname><given-names>P</given-names></name>
<etal/>
</person-group>
<article-title>The Applications of Artificial Intelligence in Cardiovascular Magnetic Resonance-A Comprehensive Review</article-title>
<source>J Clin Med</source>
<year>2022</year>
<volume>11</volume>
<issue>10</issue>
<fpage>2866</fpage>
<lpage>2866</lpage>
<pub-id pub-id-type="doi">10.3390/jcm11102866</pub-id>
</element-citation>
<mixed-citation>Argentiero A, Muscogiuri G, Rabbat MG, Martini C, Soldato N, Basile P, et al. The Applications of Artificial Intelligence in Cardiovascular Magnetic Resonance-A Comprehensive Review. J Clin Med. 2022;11(10):2866. doi: 10.3390/jcm11102866.</mixed-citation>
</ref>
<ref id="B22">
<label>22</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Hauptmann</surname><given-names>A</given-names></name>
<name><surname>Arridge</surname><given-names>S</given-names></name>
<name><surname>Lucka</surname><given-names>F</given-names></name>
<name><surname>Muthurangu</surname><given-names>V</given-names></name>
<name><surname>Steeden</surname><given-names>JA</given-names></name>
</person-group>
<article-title>Real-Time Cardiovascular MR with Spatio-Temporal Artifact Suppression Using Deep Learning-Proof of Concept in Congenital Heart Disease</article-title>
<source>Magn Reson Med</source>
<year>2019</year>
<volume>81</volume>
<issue>2</issue>
<fpage>1143</fpage>
<lpage>1156</lpage>
<pub-id pub-id-type="doi">10.1002/mrm.27480</pub-id>
</element-citation>
<mixed-citation>Hauptmann A, Arridge S, Lucka F, Muthurangu V, Steeden JA. Real-Time Cardiovascular MR with Spatio-Temporal Artifact Suppression Using Deep Learning-Proof of Concept in Congenital Heart Disease. Magn Reson Med. 2019;81(2):1143-56. doi: 10.1002/mrm.27480.</mixed-citation>
</ref>
<ref id="B23">
<label>23</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>El-Rewaidy</surname><given-names>H</given-names></name>
<name><surname>Neisius</surname><given-names>U</given-names></name>
<name><surname>Mancio</surname><given-names>J</given-names></name>
<name><surname>Kucukseymen</surname><given-names>S</given-names></name>
<name><surname>Rodriguez</surname><given-names>J</given-names></name>
<name><surname>Paskavitz</surname><given-names>A</given-names></name>
<etal/>
</person-group>
<article-title>Deep Complex Convolutional Network for Fast Reconstruction of 3D Late Gadolinium Enhancement Cardiac MRI</article-title>
<source>NMR Biomed</source>
<year>2020</year>
<volume>33</volume>
<issue>7</issue>
<elocation-id>e4312</elocation-id>
<pub-id pub-id-type="doi">10.1002/nbm.4312</pub-id>
</element-citation>
<mixed-citation>El-Rewaidy H, Neisius U, Mancio J, Kucukseymen S, Rodriguez J, Paskavitz A, et al. Deep Complex Convolutional Network for Fast Reconstruction of 3D Late Gadolinium Enhancement Cardiac MRI. NMR Biomed. 2020;33(7):e4312. doi: 10.1002/nbm.4312.</mixed-citation>
</ref>
<ref id="B24">
<label>24</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Peng</surname><given-names>P</given-names></name>
<name><surname>Lekadir</surname><given-names>K</given-names></name>
<name><surname>Gooya</surname><given-names>A</given-names></name>
<name><surname>Shao</surname><given-names>L</given-names></name>
<name><surname>Petersen</surname><given-names>SE</given-names></name>
<name><surname>Frangi</surname><given-names>AF</given-names></name>
</person-group>
<article-title>A Review of Heart Chamber Segmentation for Structural and Functional Analysis Using Cardiac Magnetic Resonance Imaging</article-title>
<source>MAGMA</source>
<year>2016</year>
<volume>29</volume>
<issue>2</issue>
<fpage>155</fpage>
<lpage>195</lpage>
<pub-id pub-id-type="doi">10.1007/s10334-015-0521-4</pub-id>
</element-citation>
<mixed-citation>Peng P, Lekadir K, Gooya A, Shao L, Petersen SE, Frangi AF. A Review of Heart Chamber Segmentation for Structural and Functional Analysis Using Cardiac Magnetic Resonance Imaging. MAGMA. 2016;29(2):155-95. doi: 10.1007/s10334-015-0521-4.</mixed-citation>
</ref>
<ref id="B25">
<label>25</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Xiong</surname><given-names>Z</given-names></name>
<name><surname>Fedorov</surname><given-names>VV</given-names></name>
<name><surname>Fu</surname><given-names>X</given-names></name>
<name><surname>Cheng</surname><given-names>E</given-names></name>
<name><surname>Macleod</surname><given-names>R</given-names></name>
<name><surname>Zhao</surname><given-names>J</given-names></name>
</person-group>
<article-title>Fully Automatic Left Atrium Segmentation from Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network</article-title>
<source>IEEE Trans Med Imaging</source>
<year>2019</year>
<volume>38</volume>
<issue>2</issue>
<fpage>515</fpage>
<lpage>524</lpage>
<pub-id pub-id-type="doi">10.1109/TMI.2018.2866845</pub-id>
</element-citation>
<mixed-citation>Xiong Z, Fedorov VV, Fu X, Cheng E, Macleod R, Zhao J. Fully Automatic Left Atrium Segmentation from Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network. IEEE Trans Med Imaging. 2019;38(2):515-24. doi: 10.1109/TMI.2018.2866845.</mixed-citation>
</ref>
<ref id="B26">
<label>26</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Sander</surname><given-names>J</given-names></name>
<name><surname>de Vos</surname><given-names>BD</given-names></name>
<name><surname>Išgum</surname><given-names>I</given-names></name>
</person-group>
<article-title>Automatic Segmentation with Detection of Local Segmentation Failures in Cardiac MRI</article-title>
<source>Sci Rep</source>
<year>2020</year>
<volume>10</volume>
<issue>1</issue>
<fpage>21769</fpage>
<lpage>21769</lpage>
<pub-id pub-id-type="doi">10.1038/s41598-020-77733-4</pub-id>
</element-citation>
<mixed-citation>Sander J, de Vos BD, Išgum I. Automatic Segmentation with Detection of Local Segmentation Failures in Cardiac MRI. Sci Rep. 2020;10(1):21769. doi: 10.1038/s41598-020-77733-4.</mixed-citation>
</ref>
<ref id="B27">
<label>27</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Bekheet</surname><given-names>M</given-names></name>
<name><surname>Sallah</surname><given-names>M</given-names></name>
<name><surname>Alghamdi</surname><given-names>NS</given-names></name>
<name><surname>Rusu-Both</surname><given-names>R</given-names></name>
<name><surname>Elgarayhi</surname><given-names>A</given-names></name>
<name><surname>Elmogy</surname><given-names>M</given-names></name>
</person-group>
<article-title>Cardiac Fibrosis Automated Diagnosis Based on FibrosisNet Network Using CMR Ischemic Cardiomyopathy</article-title>
<source>Diagnostics</source>
<year>2024</year>
<volume>14</volume>
<issue>3</issue>
<fpage>255</fpage>
<lpage>255</lpage>
<pub-id pub-id-type="doi">10.3390/diagnostics14030255</pub-id>
</element-citation>
<mixed-citation>Bekheet M, Sallah M, Alghamdi NS, Rusu-Both R, Elgarayhi A, Elmogy M. Cardiac Fibrosis Automated Diagnosis Based on FibrosisNet Network Using CMR Ischemic Cardiomyopathy. Diagnostics. 2024;14(3):255. doi: 10.3390/diagnostics14030255.</mixed-citation>
</ref>
<ref id="B28">
<label>28</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Sharifrazi</surname><given-names>D</given-names></name>
<name><surname>Alizadehsani</surname><given-names>R</given-names></name>
<name><surname>Joloudari</surname><given-names>JH</given-names></name>
<name><surname>Band</surname><given-names>SS</given-names></name>
<name><surname>Hussain</surname><given-names>S</given-names></name>
<name><surname>Sani</surname><given-names>ZA</given-names></name>
<etal/>
</person-group>
<article-title>CNN-KCL: Automatic Myocarditis Diagnosis Using Convolutional Neural Network Combined with K-Means Clustering</article-title>
<source>Math Biosci Eng</source>
<year>2022</year>
<volume>19</volume>
<issue>3</issue>
<fpage>2381</fpage>
<lpage>2402</lpage>
<pub-id pub-id-type="doi">10.3934/mbe.2022110</pub-id>
</element-citation>
<mixed-citation>Sharifrazi D, Alizadehsani R, Joloudari JH, Band SS, Hussain S, Sani ZA, et al. CNN-KCL: Automatic Myocarditis Diagnosis Using Convolutional Neural Network Combined with K-Means Clustering. Math Biosci Eng. 2022;19(3):2381-402. doi: 10.3934/mbe.2022110.</mixed-citation>
</ref>
<ref id="B29">
<label>29</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Ghorbani</surname><given-names>A</given-names></name>
<name><surname>Ouyang</surname><given-names>D</given-names></name>
<name><surname>Abid</surname><given-names>A</given-names></name>
<name><surname>He</surname><given-names>B</given-names></name>
<name><surname>Chen</surname><given-names>JH</given-names></name>
<name><surname>Harrington</surname><given-names>RA</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning Interpretation of Echocardiograms</article-title>
<source>NPJ Digit Med</source>
<year>2020</year>
<volume>3</volume>
<fpage>10</fpage>
<lpage>10</lpage>
<pub-id pub-id-type="doi">10.1038/s41746-019-0216-8</pub-id>
</element-citation>
<mixed-citation>Ghorbani A, Ouyang D, Abid A, He B, Chen JH, Harrington RA, et al. Deep Learning Interpretation of Echocardiograms. NPJ Digit Med. 2020;3:10. doi: 10.1038/s41746-019-0216-8.</mixed-citation>
</ref>
<ref id="B30">
<label>30</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<collab>American College of Cardiology Foundation Appropriate Use Criteria Task Force; American Society of Echocardiography; American Heart Association; American Society of Nuclear Cardiology; Heart Failure Society of America; Heart Rhythm Society</collab>
<etal/>
</person-group>
<article-title>ACCF/ASE/AHA/ASNC/HFSA/HRS/SCAI/SCCM/SCCT/SCMR 2011 Appropriate Use Criteria for Echocardiography. A Report of the American College of Cardiology Foundation Appropriate Use Criteria Task Force, American Society of Echocardiography, American Heart Association, American Society of Nuclear Cardiology, Heart Failure Society of America, Heart Rhythm Society, Society for Cardiovascular Angiography and Interventions, Society of Critical Care Medicine, Society of Cardiovascular Computed Tomography, Society for Cardiovascular Magnetic Resonance American College of Chest Physicians</article-title>
<source>J Am Soc Echocardiogr</source>
<year>2011</year>
<volume>24</volume>
<issue>3</issue>
<fpage>229</fpage>
<lpage>267</lpage>
<pub-id pub-id-type="doi">10.1016/j.echo.2010.12.008</pub-id>
</element-citation>
<mixed-citation>American College of Cardiology Foundation Appropriate Use Criteria Task Force; American Society of Echocardiography; American Heart Association; American Society of Nuclear Cardiology; Heart Failure Society of America; Heart Rhythm Society; et al. ACCF/ASE/AHA/ASNC/HFSA/HRS/SCAI/SCCM/SCCT/SCMR 2011 Appropriate Use Criteria for Echocardiography. A Report of the American College of Cardiology Foundation Appropriate Use Criteria Task Force, American Society of Echocardiography, American Heart Association, American Society of Nuclear Cardiology, Heart Failure Society of America, Heart Rhythm Society, Society for Cardiovascular Angiography and Interventions, Society of Critical Care Medicine, Society of Cardiovascular Computed Tomography, Society for Cardiovascular Magnetic Resonance American College of Chest Physicians. J Am Soc Echocardiogr. 2011;24(3):229-67. doi: 10.1016/j.echo.2010.12.008.</mixed-citation>
</ref>
<ref id="B31">
<label>31</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>De Geer</surname><given-names>L</given-names></name>
<name><surname>Oscarsson</surname><given-names>A</given-names></name>
<name><surname>Engvall</surname><given-names>J</given-names></name>
</person-group>
<article-title>Variability in Echocardiographic Measurements of Left Ventricular Function in Septic Shock Patients</article-title>
<source>Cardiovasc Ultrasound</source>
<year>2015</year>
<volume>13</volume>
<fpage>19</fpage>
<lpage>19</lpage>
<pub-id pub-id-type="doi">10.1186/s12947-015-0015-6</pub-id>
</element-citation>
<mixed-citation>De Geer L, Oscarsson A, Engvall J. Variability in Echocardiographic Measurements of Left Ventricular Function in Septic Shock Patients. Cardiovasc Ultrasound. 2015;13:19. doi: 10.1186/s12947-015-0015-6.</mixed-citation>
</ref>
<ref id="B32">
<label>32</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Zhang</surname><given-names>J</given-names></name>
<name><surname>Gajjala</surname><given-names>S</given-names></name>
<name><surname>Agrawal</surname><given-names>P</given-names></name>
<name><surname>Tison</surname><given-names>GH</given-names></name>
<name><surname>Hallock</surname><given-names>LA</given-names></name>
<name><surname>Beussink-Nelson</surname><given-names>L</given-names></name>
<etal/>
</person-group>
<article-title>Fully Automated Echocardiogram Interpretation in Clinical Practice</article-title>
<source>Circulation</source>
<year>2018</year>
<volume>138</volume>
<issue>16</issue>
<fpage>1623</fpage>
<lpage>1635</lpage>
<pub-id pub-id-type="doi">10.1161/CIRCULATIONAHA.118.034338</pub-id>
</element-citation>
<mixed-citation>Zhang J, Gajjala S, Agrawal P, Tison GH, Hallock LA, Beussink-Nelson L, et al. Fully Automated Echocardiogram Interpretation in Clinical Practice. Circulation. 2018;138(16):1623-35. doi: 10.1161/CIRCULATIONAHA.118.034338.</mixed-citation>
</ref>
<ref id="B33">
<label>33</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Madani</surname><given-names>A</given-names></name>
<name><surname>Arnaout</surname><given-names>R</given-names></name>
<name><surname>Mofrad</surname><given-names>M</given-names></name>
<name><surname>Arnaout</surname><given-names>R</given-names></name>
</person-group>
<article-title>Fast and Accurate View Classification of Echocardiograms Using Deep Learning</article-title>
<source>NPJ Digit Med</source>
<year>2018</year>
<volume>1</volume>
<fpage>6</fpage>
<lpage>6</lpage>
<pub-id pub-id-type="doi">10.1038/s41746-017-0013-1</pub-id>
</element-citation>
<mixed-citation>Madani A, Arnaout R, Mofrad M, Arnaout R. Fast and Accurate View Classification of Echocardiograms Using Deep Learning. NPJ Digit Med. 2018;1:6. doi: 10.1038/s41746-017-0013-1.</mixed-citation>
</ref>
<ref id="B34">
<label>34</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Shi</surname><given-names>S</given-names></name>
<name><surname>Alimu</surname><given-names>P</given-names></name>
<name><surname>Mahemut</surname><given-names>P</given-names></name>
</person-group>
<article-title>The Study of Echocardiography of Left Ventricle Segmentation Combining Transformer and Convolutional Neural Networks</article-title>
<source>Int Heart J</source>
<year>2024</year>
<volume>65</volume>
<issue>5</issue>
<fpage>889</fpage>
<lpage>897</lpage>
<pub-id pub-id-type="doi">10.1536/ihj.23-638</pub-id>
</element-citation>
<mixed-citation>Shi S, Alimu P, Mahemut P. The Study of Echocardiography of Left Ventricle Segmentation Combining Transformer and Convolutional Neural Networks. Int Heart J. 2024;65(5):889-97. doi: 10.1536/ihj.23-638.</mixed-citation>
</ref>
<ref id="B35">
<label>35</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Jiang</surname><given-names>J</given-names></name>
<name><surname>Deng</surname><given-names>H</given-names></name>
<name><surname>Xue</surname><given-names>Y</given-names></name>
<name><surname>Liao</surname><given-names>H</given-names></name>
<name><surname>Wu</surname><given-names>S</given-names></name>
</person-group>
<article-title>Detection of Left Atrial Enlargement Using a Convolutional Neural Network-Enabled Electrocardiogram</article-title>
<source>Front Cardiovasc Med</source>
<year>2020</year>
<volume>7</volume>
<fpage>609976</fpage>
<lpage>609976</lpage>
<pub-id pub-id-type="doi">10.3389/fcvm.2020.609976</pub-id>
</element-citation>
<mixed-citation>Jiang J, Deng H, Xue Y, Liao H, Wu S. Detection of Left Atrial Enlargement Using a Convolutional Neural Network-Enabled Electrocardiogram. Front Cardiovasc Med. 2020;7:609976. doi: 10.3389/fcvm.2020.609976.</mixed-citation>
</ref>
<ref id="B36">
<label>36</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Painchaud</surname><given-names>N</given-names></name>
<name><surname>Duchateau</surname><given-names>N</given-names></name>
<name><surname>Bernard</surname><given-names>O</given-names></name>
<name><surname>Jodoin</surname><given-names>PM</given-names></name>
</person-group>
<article-title>Echocardiography Segmentation with Enforced Temporal Consistency</article-title>
<source>IEEE Trans Med Imaging</source>
<year>2022</year>
<volume>41</volume>
<issue>10</issue>
<fpage>2867</fpage>
<lpage>2878</lpage>
<pub-id pub-id-type="doi">10.1109/TMI.2022.3173669</pub-id>
</element-citation>
<mixed-citation>Painchaud N, Duchateau N, Bernard O, Jodoin PM. Echocardiography Segmentation with Enforced Temporal Consistency. IEEE Trans Med Imaging. 2022;41(10):2867-78. doi: 10.1109/TMI.2022.3173669.</mixed-citation>
</ref>
<ref id="B37">
<label>37</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Lei</surname><given-names>Y</given-names></name>
<name><surname>Fu</surname><given-names>Y</given-names></name>
<name><surname>Roper</surname><given-names>J</given-names></name>
<name><surname>Higgins</surname><given-names>K</given-names></name>
<name><surname>Bradley</surname><given-names>JD</given-names></name>
<name><surname>Curran</surname><given-names>WJ</given-names></name>
<etal/>
</person-group>
<article-title>Echocardiographic Image Multi-Structure Segmentation Using Cardiac-SegNet</article-title>
<source>Med Phys</source>
<year>2021</year>
<volume>48</volume>
<issue>5</issue>
<fpage>2426</fpage>
<lpage>2437</lpage>
<pub-id pub-id-type="doi">10.1002/mp.14818</pub-id>
</element-citation>
<mixed-citation>Lei Y, Fu Y, Roper J, Higgins K, Bradley JD, Curran WJ, et al. Echocardiographic Image Multi-Structure Segmentation Using Cardiac-SegNet. Med Phys. 2021;48(5):2426-37. doi: 10.1002/mp.14818.</mixed-citation>
</ref>
<ref id="B38">
<label>38</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Wehbe</surname><given-names>RM</given-names></name>
<name><surname>Katsaggelos</surname><given-names>AK</given-names></name>
<name><surname>Hammond</surname><given-names>KJ</given-names></name>
<name><surname>Hong</surname><given-names>H</given-names></name>
<name><surname>Ahmad</surname><given-names>FS</given-names></name>
<name><surname>Ouyang</surname><given-names>D</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning for Cardiovascular Imaging: A Review</article-title>
<source>JAMA Cardiol</source>
<year>2023</year>
<volume>8</volume>
<issue>11</issue>
<fpage>1089</fpage>
<lpage>1098</lpage>
<pub-id pub-id-type="doi">10.1001/jamacardio.2023.3142</pub-id>
</element-citation>
<mixed-citation>Wehbe RM, Katsaggelos AK, Hammond KJ, Hong H, Ahmad FS, Ouyang D, et al. Deep Learning for Cardiovascular Imaging: A Review. JAMA Cardiol. 2023;8(11):1089-98. doi: 10.1001/jamacardio.2023.3142.</mixed-citation>
</ref>
<ref id="B39">
<label>39</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Jian</surname><given-names>Z</given-names></name>
<name><surname>Wang</surname><given-names>X</given-names></name>
<name><surname>Zhang</surname><given-names>J</given-names></name>
<name><surname>Wang</surname><given-names>X</given-names></name>
<name><surname>Deng</surname><given-names>Y</given-names></name>
</person-group>
<article-title>Diagnosis of Left Ventricular Hypertrophy Using Convolutional Neural Network</article-title>
<source>BMC Med Inform Decis Mak</source>
<year>2020</year>
<volume>20</volume>
<issue>1</issue>
<fpage>243</fpage>
<lpage>243</lpage>
<pub-id pub-id-type="doi">10.1186/s12911-020-01255-2</pub-id>
</element-citation>
<mixed-citation>Jian Z, Wang X, Zhang J, Wang X, Deng Y. Diagnosis of Left Ventricular Hypertrophy Using Convolutional Neural Network. BMC Med Inform Decis Mak. 2020;20(1):243. doi: 10.1186/s12911-020-01255-2.</mixed-citation>
</ref>
<ref id="B40">
<label>40</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Nazar</surname><given-names>W</given-names></name>
<name><surname>Nazar</surname><given-names>K</given-names></name>
<name><surname>Daniłowicz-Szymanowicz</surname><given-names>L</given-names></name>
</person-group>
<article-title>Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality</article-title>
<source>Life</source>
<year>2024</year>
<volume>14</volume>
<issue>6</issue>
<fpage>761</fpage>
<lpage>761</lpage>
<pub-id pub-id-type="doi">10.3390/life14060761</pub-id>
</element-citation>
<mixed-citation>Nazar W, Nazar K, Daniłowicz-Szymanowicz L. Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality. Life. 2024;14(6):761. doi: 10.3390/life14060761.</mixed-citation>
</ref>
<ref id="B41">
<label>41</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Duffy</surname><given-names>G</given-names></name>
<name><surname>Cheng</surname><given-names>PP</given-names></name>
<name><surname>Yuan</surname><given-names>N</given-names></name>
<name><surname>He</surname><given-names>B</given-names></name>
<name><surname>Kwan</surname><given-names>AC</given-names></name>
<name><surname>Shun-Shin</surname><given-names>MJ</given-names></name>
<etal/>
</person-group>
<article-title>High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning</article-title>
<source>JAMA Cardiol</source>
<year>2022</year>
<volume>7</volume>
<issue>4</issue>
<fpage>386</fpage>
<lpage>395</lpage>
<pub-id pub-id-type="doi">10.1001/jamacardio.2021.6059</pub-id>
</element-citation>
<mixed-citation>Duffy G, Cheng PP, Yuan N, He B, Kwan AC, Shun-Shin MJ, et al. High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning. JAMA Cardiol. 2022;7(4):386-95. doi: 10.1001/jamacardio.2021.6059.</mixed-citation>
</ref>
<ref id="B42">
<label>42</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Holste</surname><given-names>G</given-names></name>
<name><surname>Oikonomou</surname><given-names>EK</given-names></name>
<name><surname>Mortazavi</surname><given-names>BJ</given-names></name>
<name><surname>Coppi</surname><given-names>A</given-names></name>
<name><surname>Faridi</surname><given-names>KF</given-names></name>
<name><surname>Miller</surname><given-names>EJ</given-names></name>
<etal/>
</person-group>
<article-title>Severe Aortic Stenosis Detection by Deep Learning Applied to Echocardiography</article-title>
<source>Eur Heart J</source>
<year>2023</year>
<volume>44</volume>
<issue>43</issue>
<fpage>4592</fpage>
<lpage>4604</lpage>
<pub-id pub-id-type="doi">10.1093/eurheartj/ehad456</pub-id>
</element-citation>
<mixed-citation>Holste G, Oikonomou EK, Mortazavi BJ, Coppi A, Faridi KF, Miller EJ, et al. Severe Aortic Stenosis Detection by Deep Learning Applied to Echocardiography. Eur Heart J. 2023;44(43):4592-604. doi: 10.1093/eurheartj/ehad456.</mixed-citation>
</ref>
<ref id="B43">
<label>43</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Wessler</surname><given-names>BS</given-names></name>
<name><surname>Huang</surname><given-names>Z</given-names></name>
<name><surname>Long</surname><given-names>GM</given-names><suffix>Jr</suffix></name>
<name><surname>Pacifici</surname><given-names>S</given-names></name>
<name><surname>Prashar</surname><given-names>N</given-names></name>
<name><surname>Karmiy</surname><given-names>S</given-names></name>
<etal/>
</person-group>
<article-title>Automated Detection of Aortic Stenosis Using Machine Learning</article-title>
<source>J Am Soc Echocardiogr</source>
<year>2023</year>
<volume>36</volume>
<issue>4</issue>
<fpage>411</fpage>
<lpage>420</lpage>
<pub-id pub-id-type="doi">10.1016/j.echo.2023.01.006</pub-id>
</element-citation>
<mixed-citation>Wessler BS, Huang Z, Long GM Jr, Pacifici S, Prashar N, Karmiy S, et al. Automated Detection of Aortic Stenosis Using Machine Learning. J Am Soc Echocardiogr. 2023;36(4):411-20. doi: 10.1016/j.echo.2023.01.006.</mixed-citation>
</ref>
<ref id="B44">
<label>44</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Farhad</surname><given-names>M</given-names></name>
<name><surname>Masud</surname><given-names>MM</given-names></name>
<name><surname>Beg</surname><given-names>A</given-names></name>
<name><surname>Ahmad</surname><given-names>A</given-names></name>
<name><surname>Ahmed</surname><given-names>LA</given-names></name>
<name><surname>Memon</surname><given-names>S</given-names></name>
</person-group>
<article-title>Cardiac Phase Detection in Echocardiography Using Convolutional Neural Networks</article-title>
<source>Sci Rep</source>
<year>2023</year>
<volume>13</volume>
<issue>1</issue>
<fpage>8908</fpage>
<lpage>8908</lpage>
<pub-id pub-id-type="doi">10.1038/s41598-023-36047-x</pub-id>
</element-citation>
<mixed-citation>Farhad M, Masud MM, Beg A, Ahmad A, Ahmed LA, Memon S. Cardiac Phase Detection in Echocardiography Using Convolutional Neural Networks. Sci Rep. 2023;13(1):8908. doi: 10.1038/s41598-023-36047-x.</mixed-citation>
</ref>
<ref id="B45">
<label>45</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Muraki</surname><given-names>R</given-names></name>
<name><surname>Teramoto</surname><given-names>A</given-names></name>
<name><surname>Sugimoto</surname><given-names>K</given-names></name>
<name><surname>Sugimoto</surname><given-names>K</given-names></name>
<name><surname>Yamada</surname><given-names>A</given-names></name>
<name><surname>Watanabe</surname><given-names>E</given-names></name>
</person-group>
<article-title>Automated Detection Scheme for Acute Myocardial Infarction Using Convolutional Neural Network and Long Short-Term Memory</article-title>
<source>PLoS One</source>
<year>2022</year>
<volume>17</volume>
<issue>2</issue>
<elocation-id>e0264002</elocation-id>
<pub-id pub-id-type="doi">10.1371/journal.pone.0264002</pub-id>
</element-citation>
<mixed-citation>Muraki R, Teramoto A, Sugimoto K, Sugimoto K, Yamada A, Watanabe E. Automated Detection Scheme for Acute Myocardial Infarction Using Convolutional Neural Network and Long Short-Term Memory. PLoS One. 2022;17(2):e0264002. doi: 10.1371/journal.pone.0264002.</mixed-citation>
</ref>
<ref id="B46">
<label>46</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Naser</surname><given-names>JA</given-names></name>
<name><surname>Lee</surname><given-names>E</given-names></name>
<name><surname>Pislaru</surname><given-names>SV</given-names></name>
<name><surname>Tsaban</surname><given-names>G</given-names></name>
<name><surname>Malins</surname><given-names>JG</given-names></name>
<name><surname>Jackson</surname><given-names>JI</given-names></name>
<etal/>
</person-group>
<article-title>Artificial Intelligence-Based Classification of Echocardiographic Views</article-title>
<source>Eur Heart J Digit Health</source>
<year>2024</year>
<volume>5</volume>
<issue>3</issue>
<fpage>260</fpage>
<lpage>269</lpage>
<pub-id pub-id-type="doi">10.1093/ehjdh/ztae015</pub-id>
</element-citation>
<mixed-citation>Naser JA, Lee E, Pislaru SV, Tsaban G, Malins JG, Jackson JI, et al. Artificial Intelligence-Based Classification of Echocardiographic Views. Eur Heart J Digit Health. 2024;5(3):260-9. doi: 10.1093/ehjdh/ztae015.</mixed-citation>
</ref>
<ref id="B47">
<label>47</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Østvik</surname><given-names>A</given-names></name>
<name><surname>Smistad</surname><given-names>E</given-names></name>
<name><surname>Aase</surname><given-names>SA</given-names></name>
<name><surname>Haugen</surname><given-names>BO</given-names></name>
<name><surname>Lovstakken</surname><given-names>L</given-names></name>
</person-group>
<article-title>Real-Time Standard View Classification in Transthoracic Echocardiography Using Convolutional Neural Networks</article-title>
<source>Ultrasound Med Biol</source>
<year>2019</year>
<volume>45</volume>
<issue>2</issue>
<fpage>374</fpage>
<lpage>384</lpage>
<pub-id pub-id-type="doi">10.1016/j.ultrasmedbio.2018.07.024</pub-id>
</element-citation>
<mixed-citation>Østvik A, Smistad E, Aase SA, Haugen BO, Lovstakken L. Real-Time Standard View Classification in Transthoracic Echocardiography Using Convolutional Neural Networks. Ultrasound Med Biol. 2019;45(2):374-84. doi: 10.1016/j.ultrasmedbio.2018.07.024.</mixed-citation>
</ref>
<ref id="B48">
<label>48</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Sun</surname><given-names>D</given-names></name>
<name><surname>Hu</surname><given-names>Y</given-names></name>
<name><surname>Li</surname><given-names>Y</given-names></name>
<name><surname>Yu</surname><given-names>X</given-names></name>
<name><surname>Chen</surname><given-names>X</given-names></name>
<name><surname>Shen</surname><given-names>P</given-names></name>
<etal/>
</person-group>
<article-title>Chamber Attention Network (CAN): Towards Interpretable Diagnosis of Pulmonary Artery Hypertension Using Echocardiography</article-title>
<source>J Adv Res</source>
<year>2024</year>
<volume>63</volume>
<fpage>103</fpage>
<lpage>115</lpage>
<pub-id pub-id-type="doi">10.1016/j.jare.2023.10.013</pub-id>
</element-citation>
<mixed-citation>Sun D, Hu Y, Li Y, Yu X, Chen X, Shen P, et al. Chamber Attention Network (CAN): Towards Interpretable Diagnosis of Pulmonary Artery Hypertension Using Echocardiography. J Adv Res. 2024;63:103-15. doi: 10.1016/j.jare.2023.10.013.</mixed-citation>
</ref>
<ref id="B49">
<label>49</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>DuBrock</surname><given-names>HM</given-names></name>
<name><surname>Wagner</surname><given-names>TE</given-names></name>
<name><surname>Carlson</surname><given-names>K</given-names></name>
<name><surname>Carpenter</surname><given-names>CL</given-names></name>
<name><surname>Awasthi</surname><given-names>S</given-names></name>
<name><surname>Attia</surname><given-names>ZI</given-names></name>
<etal/>
</person-group>
<article-title>An Electrocardiogram-Based AI Algorithm for Early Detection of Pulmonary Hypertension</article-title>
<source>Eur Respir J</source>
<year>2024</year>
<volume>64</volume>
<issue>1</issue>
<fpage>2400192</fpage>
<lpage>2400192</lpage>
<pub-id pub-id-type="doi">10.1183/13993003.00192-2024</pub-id>
</element-citation>
<mixed-citation>DuBrock HM, Wagner TE, Carlson K, Carpenter CL, Awasthi S, Attia ZI, et al. An Electrocardiogram-Based AI Algorithm for Early Detection of Pulmonary Hypertension. Eur Respir J. 2024;64(1):2400192. doi: 10.1183/13993003.00192-2024.</mixed-citation>
</ref>
<ref id="B50">
<label>50</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Yuan</surname><given-names>N</given-names></name>
<name><surname>Stein</surname><given-names>NR</given-names></name>
<name><surname>Duffy</surname><given-names>G</given-names></name>
<name><surname>Sandhu</surname><given-names>RK</given-names></name>
<name><surname>Chugh</surname><given-names>SS</given-names></name>
<name><surname>Chen</surname><given-names>PS</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning Evaluation of Echocardiograms to Identify Occult Atrial Fibrillation</article-title>
<source>NPJ Digit Med</source>
<year>2024</year>
<volume>7</volume>
<issue>1</issue>
<fpage>96</fpage>
<lpage>96</lpage>
<pub-id pub-id-type="doi">10.1038/s41746-024-01090-z</pub-id>
</element-citation>
<mixed-citation>Yuan N, Stein NR, Duffy G, Sandhu RK, Chugh SS, Chen PS, et al. Deep Learning Evaluation of Echocardiograms to Identify Occult Atrial Fibrillation. NPJ Digit Med. 2024;7(1):96. doi: 10.1038/s41746-024-01090-z.</mixed-citation>
</ref>
<ref id="B51">
<label>51</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Zhou</surname><given-names>X</given-names></name>
<name><surname>Yang</surname><given-names>T</given-names></name>
<name><surname>Ruan</surname><given-names>Y</given-names></name>
<name><surname>Zhang</surname><given-names>Y</given-names></name>
<name><surname>Liu</surname><given-names>X</given-names></name>
<name><surname>Zhao</surname><given-names>Y</given-names></name>
<etal/>
</person-group>
<article-title>Application of Neural Networks in Prenatal Diagnosis of Atrioventricular Septal Defect</article-title>
<source>Transl Pediatr</source>
<year>2024</year>
<volume>13</volume>
<issue>1</issue>
<fpage>26</fpage>
<lpage>37</lpage>
<pub-id pub-id-type="doi">10.21037/tp-23-394</pub-id>
</element-citation>
<mixed-citation>Zhou X, Yang T, Ruan Y, Zhang Y, Liu X, Zhao Y, et al. Application of Neural Networks in Prenatal Diagnosis of Atrioventricular Septal Defect. Transl Pediatr. 2024;13(1):26-37. doi: 10.21037/tp-23-394.</mixed-citation>
</ref>
<ref id="B52">
<label>52</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Erno</surname><given-names>J</given-names></name>
<name><surname>Gomes</surname><given-names>T</given-names></name>
<name><surname>Baltimore</surname><given-names>C</given-names></name>
<name><surname>Lineberger</surname><given-names>JP</given-names></name>
<name><surname>Smith</surname><given-names>DH</given-names></name>
<name><surname>Baker</surname><given-names>GH</given-names></name>
</person-group>
<article-title>Automated Identification of Patent Ductus Arteriosus Using a Computer Vision Model</article-title>
<source>J Ultrasound Med</source>
<year>2023</year>
<volume>42</volume>
<issue>12</issue>
<fpage>2707</fpage>
<lpage>2713</lpage>
<pub-id pub-id-type="doi">10.1002/jum.16305</pub-id>
</element-citation>
<mixed-citation>Erno J, Gomes T, Baltimore C, Lineberger JP, Smith DH, Baker GH. Automated Identification of Patent Ductus Arteriosus Using a Computer Vision Model. J Ultrasound Med. 2023;42(12):2707-13. doi: 10.1002/jum.16305.</mixed-citation>
</ref>
<ref id="B53">
<label>53</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Betancur</surname><given-names>J</given-names></name>
<name><surname>Commandeur</surname><given-names>F</given-names></name>
<name><surname>Motlagh</surname><given-names>M</given-names></name>
<name><surname>Sharir</surname><given-names>T</given-names></name>
<name><surname>Einstein</surname><given-names>AJ</given-names></name>
<name><surname>Bokhari</surname><given-names>S</given-names></name>
<etal/>
</person-group>
<article-title>Deep Learning for Prediction of Obstructive Disease from Fast Myocardial Perfusion SPECT: A Multicenter Study</article-title>
<source>JACC Cardiovasc Imaging</source>
<year>2018</year>
<volume>11</volume>
<issue>11</issue>
<fpage>1654</fpage>
<lpage>1663</lpage>
<pub-id pub-id-type="doi">10.1016/j.jcmg.2018.01.020</pub-id>
</element-citation>
<mixed-citation>Betancur J, Commandeur F, Motlagh M, Sharir T, Einstein AJ, Bokhari S, et al. Deep Learning for Prediction of Obstructive Disease from Fast Myocardial Perfusion SPECT: A Multicenter Study. JACC Cardiovasc Imaging. 2018;11(11):1654-63. doi: 10.1016/j.jcmg.2018.01.020.</mixed-citation>
</ref>
<ref id="B54">
<label>54</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Papandrianos</surname><given-names>NI</given-names></name>
<name><surname>Feleki</surname><given-names>A</given-names></name>
<name><surname>Papageorgiou</surname><given-names>EI</given-names></name>
<name><surname>Martini</surname><given-names>C</given-names></name>
</person-group>
<article-title>Deep Learning-Based Automated Diagnosis for Coronary Artery Disease Using SPECT-MPI Images</article-title>
<source>J Clin Med</source>
<year>2022</year>
<volume>11</volume>
<issue>13</issue>
<fpage>3918</fpage>
<lpage>3918</lpage>
<pub-id pub-id-type="doi">10.3390/jcm11133918</pub-id>
</element-citation>
<mixed-citation>Papandrianos NI, Feleki A, Papageorgiou EI, Martini C. Deep Learning-Based Automated Diagnosis for Coronary Artery Disease Using SPECT-MPI Images. J Clin Med. 2022;11(13):3918. doi: 10.3390/jcm11133918.</mixed-citation>
</ref>
<ref id="B55">
<label>55</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Su</surname><given-names>TY</given-names></name>
<name><surname>Chen</surname><given-names>JJ</given-names></name>
<name><surname>Chen</surname><given-names>WS</given-names></name>
<name><surname>Chang</surname><given-names>YH</given-names></name>
<name><surname>Lu</surname><given-names>HH</given-names></name>
</person-group>
<article-title>Deep Learning for Myocardial Ischemia Auxiliary Diagnosis Using CZT SPECT Myocardial Perfusion Imaging</article-title>
<source>J Chin Med Assoc</source>
<year>2023</year>
<volume>86</volume>
<issue>1</issue>
<fpage>122</fpage>
<lpage>130</lpage>
<pub-id pub-id-type="doi">10.1097/JCMA.0000000000000833</pub-id>
</element-citation>
<mixed-citation>Su TY, Chen JJ, Chen WS, Chang YH, Lu HH. Deep Learning for Myocardial Ischemia Auxiliary Diagnosis Using CZT SPECT Myocardial Perfusion Imaging. J Chin Med Assoc. 2023;86(1):122-30. doi: 10.1097/JCMA.0000000000000833.</mixed-citation>
</ref>
<ref id="B56">
<label>56</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Toth</surname><given-names>D</given-names></name>
<name><surname>Miao</surname><given-names>S</given-names></name>
<name><surname>Kurzendorfer</surname><given-names>T</given-names></name>
<name><surname>Rinaldi</surname><given-names>CA</given-names></name>
<name><surname>Liao</surname><given-names>R</given-names></name>
<name><surname>Mansi</surname><given-names>T</given-names></name>
<etal/>
</person-group>
<article-title>3D/2D Model-to-Image Registration by Imitation Learning for Cardiac Procedures</article-title>
<source>Int J Comput Assist Radiol Surg</source>
<year>2018</year>
<volume>13</volume>
<issue>8</issue>
<fpage>1141</fpage>
<lpage>1149</lpage>
<pub-id pub-id-type="doi">10.1007/s11548-018-1774-y</pub-id>
</element-citation>
<mixed-citation>Toth D, Miao S, Kurzendorfer T, Rinaldi CA, Liao R, Mansi T, et al. 3D/2D Model-to-Image Registration by Imitation Learning for Cardiac Procedures. Int J Comput Assist Radiol Surg. 2018;13(8):1141-9. doi: 10.1007/s11548-018-1774-y.</mixed-citation>
</ref>
<ref id="B57">
<label>57</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Breininger</surname><given-names>K</given-names></name>
<name><surname>Albarqouni</surname><given-names>S</given-names></name>
<name><surname>Kurzendorfer</surname><given-names>T</given-names></name>
<name><surname>Pfister</surname><given-names>M</given-names></name>
<name><surname>Kowarschik</surname><given-names>M</given-names></name>
<name><surname>Maier</surname><given-names>A</given-names></name>
</person-group>
<article-title>Intraoperative Stent Segmentation in X-Ray Fluoroscopy for Endovascular Aortic Repair</article-title>
<source>Int J Comput Assist Radiol Surg</source>
<year>2018</year>
<volume>13</volume>
<issue>8</issue>
<fpage>1221</fpage>
<lpage>1231</lpage>
<pub-id pub-id-type="doi">10.1007/s11548-018-1779-6</pub-id>
</element-citation>
<mixed-citation>Breininger K, Albarqouni S, Kurzendorfer T, Pfister M, Kowarschik M, Maier A. Intraoperative Stent Segmentation in X-Ray Fluoroscopy for Endovascular Aortic Repair. Int J Comput Assist Radiol Surg. 2018;13(8):1221-31. doi: 10.1007/s11548-018-1779-6.</mixed-citation>
</ref>
<ref id="B58">
<label>58</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Sadda</surname><given-names>P</given-names></name>
<name><surname>Qarni</surname><given-names>T</given-names></name>
</person-group>
<article-title>Real-Time Medical Video Denoising with Deep Learning: Application to Angiography</article-title>
<source>Int J Appl Inf Syst</source>
<year>2018</year>
<volume>12</volume>
<issue>13</issue>
<fpage>22</fpage>
<lpage>28</lpage>
<pub-id pub-id-type="doi">10.5120/ijais2018451755</pub-id>
</element-citation>
<mixed-citation>Sadda P, Qarni T. Real-Time Medical Video Denoising with Deep Learning: Application to Angiography. Int J Appl Inf Syst. 2018;12(13):22-8. doi: 10.5120/ijais2018451755.</mixed-citation>
</ref>
<ref id="B59">
<label>59</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Luo</surname><given-names>Y</given-names></name>
<name><surname>Ma</surname><given-names>Y</given-names></name>
<name><surname>O’ Brien</surname><given-names>H</given-names></name>
<name><surname>Jiang</surname><given-names>K</given-names></name>
<name><surname>Kohli</surname><given-names>V</given-names></name>
<name><surname>Maidelin</surname><given-names>S</given-names></name>
<etal/>
</person-group>
<article-title>Edge-Enhancement Densenet for X-Ray Fluoroscopy Image Denoising in Cardiac Electrophysiology Procedures</article-title>
<source>Med Phys</source>
<year>2022</year>
<volume>49</volume>
<issue>2</issue>
<fpage>1262</fpage>
<lpage>1275</lpage>
<pub-id pub-id-type="doi">10.1002/mp.15426</pub-id>
</element-citation>
<mixed-citation>Luo Y, Ma Y, O’ Brien H, Jiang K, Kohli V, Maidelin S, et al. Edge-Enhancement Densenet for X-Ray Fluoroscopy Image Denoising in Cardiac Electrophysiology Procedures. Med Phys. 2022;49(2):1262-75. doi: 10.1002/mp.15426.</mixed-citation>
</ref>
<ref id="B60">
<label>60</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Abdolmanafi</surname><given-names>A</given-names></name>
<name><surname>Duong</surname><given-names>L</given-names></name>
<name><surname>Dahdah</surname><given-names>N</given-names></name>
<name><surname>Adib</surname><given-names>IR</given-names></name>
<name><surname>Cheriet</surname><given-names>F</given-names></name>
</person-group>
<article-title>Characterization of Coronary Artery Pathological Formations from OCT Imaging Using Deep Learning</article-title>
<source>Biomed Opt Express</source>
<year>2018</year>
<volume>9</volume>
<issue>10</issue>
<fpage>4936</fpage>
<lpage>4960</lpage>
<pub-id pub-id-type="doi">10.1364/BOE.9.004936</pub-id>
</element-citation>
<mixed-citation>Abdolmanafi A, Duong L, Dahdah N, Adib IR, Cheriet F. Characterization of Coronary Artery Pathological Formations from OCT Imaging Using Deep Learning. Biomed Opt Express. 2018;9(10):4936-60. doi: 10.1364/BOE.9.004936.</mixed-citation>
</ref>
<ref id="B61">
<label>61</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Abdolmanafi</surname><given-names>A</given-names></name>
<name><surname>Cheriet</surname><given-names>F</given-names></name>
<name><surname>Duong</surname><given-names>L</given-names></name>
<name><surname>Ibrahim</surname><given-names>R</given-names></name>
<name><surname>Dahdah</surname><given-names>N</given-names></name>
</person-group>
<article-title>An Automatic Diagnostic System of Coronary Artery Lesions in Kawasaki Disease Using Intravascular Optical Coherence Tomography Imaging</article-title>
<source>J Biophotonics</source>
<year>2020</year>
<volume>13</volume>
<issue>1</issue>
<elocation-id>e201900112</elocation-id>
<pub-id pub-id-type="doi">10.1002/jbio.201900112</pub-id>
</element-citation>
<mixed-citation>Abdolmanafi A, Cheriet F, Duong L, Ibrahim R, Dahdah N. An Automatic Diagnostic System of Coronary Artery Lesions in Kawasaki Disease Using Intravascular Optical Coherence Tomography Imaging. J Biophotonics. 2020;13(1):e201900112. doi: 10.1002/jbio.201900112.</mixed-citation>
</ref>
<ref id="B62">
<label>62</label>
<element-citation publication-type="journal">
<person-group person-group-type="author">
<name><surname>Gessert</surname><given-names>N</given-names></name>
<name><surname>Lutz</surname><given-names>M</given-names></name>
<name><surname>Heyder</surname><given-names>M</given-names></name>
<name><surname>Latus</surname><given-names>S</given-names></name>
<name><surname>Leistner</surname><given-names>DM</given-names></name>
<name><surname>Abdelwahed</surname><given-names>YS</given-names></name>
<etal/>
</person-group>
<article-title>Automatic Plaque Detection in IVOCT Pullbacks Using Convolutional Neural Networks</article-title>
<source>IEEE Trans Med Imaging</source>
<year>2019</year>
<volume>38</volume>
<issue>2</issue>
<fpage>426</fpage>
<lpage>434</lpage>
<pub-id pub-id-type="doi">10.1109/TMI.2018.2865659</pub-id>
</element-citation>
<mixed-citation>Gessert N, Lutz M, Heyder M, Latus S, Leistner DM, Abdelwahed YS, et al. Automatic Plaque Detection in IVOCT Pullbacks Using Convolutional Neural Networks. IEEE Trans Med Imaging. 2019;38(2):426-34. doi: 10.1109/TMI.2018.2865659.</mixed-citation>
</ref>
</ref-list>
</back>
<sub-article article-type="translation" id="S1" xml:lang="pt">
<front-stub>
<article-id pub-id-type="doi">10.36660/abcimg.20250058</article-id>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Artigo de Revisão</subject>
</subj-group>
</article-categories>
<title-group>
<article-title>As Aplicações das Redes Neurais Convolucionais na Imagem Cardíaca</article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0002-4178-0651</contrib-id>
<name><surname>Fernandes</surname><given-names>Luiz Henrique Cartaxo</given-names></name>
<role>Obtenção de dados</role>
<role>Análise e interpretação dos dados</role>
<role>Redação do manuscrito</role>
<xref ref-type="aff" rid="aff3"><sup>1</sup></xref>
<xref ref-type="corresp" rid="c2"/>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0003-0129-391X</contrib-id>
<name><surname>Dantas</surname><given-names>José Lucas Formiga</given-names></name>
<role>Obtenção de dados</role>
<role>Análise e interpretação dos dados</role>
<role>Redação do manuscrito</role>
<xref ref-type="aff" rid="aff3"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0009-0004-8820-8515</contrib-id>
<name><surname>Lima</surname><given-names>Marilia Graziela Vieira de Macena</given-names></name>
<role>Obtenção de dados</role>
<role>Análise e interpretação dos dados</role>
<role>Redação do manuscrito</role>
<xref ref-type="aff" rid="aff3"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0001-8081-9734</contrib-id>
<name><surname>Donato</surname><given-names>Glaudir</given-names></name>
<role>Análise e interpretação dos dados</role>
<role>Revisão crítica do manuscrito quanto ao conteúdo intelectual importante</role>
<xref ref-type="aff" rid="aff3"><sup>1</sup></xref>
</contrib>
<contrib contrib-type="author">
<contrib-id contrib-id-type="orcid">0000-0001-8809-8783</contrib-id>
<name><surname>Melo</surname><given-names>Marcelo Dantas Tavares de</given-names></name>
<role>Concepção e desenho da pesquisa</role>
<role>Revisão crítica do manuscrito quanto ao conteúdo intelectual importante</role>
<xref ref-type="aff" rid="aff4"><sup>2</sup></xref>
</contrib>
<aff id="aff3">
<label>1</label>
<addr-line>
<named-content content-type="city">João Pessoa</named-content>
<named-content content-type="state">PB</named-content>
</addr-line>
<country country="BR">Brasil</country>
<institution content-type="original">Centro de Ciências Médicas, Universidade Federal da Paraíba, João Pessoa, PB – Brasil</institution>
</aff>
<aff id="aff4">
<label>2</label>
<addr-line>
<named-content content-type="city">João Pessoa</named-content>
<named-content content-type="state">PB</named-content>
</addr-line>
<country country="BR">Brasil</country>
<institution content-type="original">Departamento de Medicina Interna, Universidade Federal da Paraíba, João Pessoa, PB – Brasil</institution>
</aff>
</contrib-group>
<author-notes>
<corresp id="c2"><label>Correspondência:</label> <bold>Luiz Henrique Cartaxo Fernandes</bold> • Universidade Federal da Paraíba – Centro de Ciências Médicas. Cidade Universitária, s/n – Conj. Pres. Castelo Branco III. CEP: <postal-code>58051-900</postal-code>. João Pessoa, PB – Brasil E-mail: <email>luiz.cartaxo@academico.ufpb.br</email></corresp>
<fn fn-type="coi-statement"><label>Potencial conflito de interesse</label>
<p>Declaro não haver conflito de interesses pertinentes.</p></fn>
<fn fn-type="edited-by"><label>Editor responsável pela revisão:</label> <p>Marcelo Tavares</p></fn>
</author-notes>
<abstract>
<title>Resumo</title>
<p>Redes neurais são modelos computacionais que imitam o funcionamento do cérebro humano, aprendendo a partir de grandes volumes de dados para realizar tarefas cada vez mais complexas. Isso é feito por meio de neurônios artificiais interconectados que propagam informações de camadas brutas para camadas refinadas, às vezes com pesos atribuídos, permitindo a classificação ou identificação de padrões não lineares. A Rede Neural Convolucional (CNN, do inglês <italic>Convolutional Neural Network</italic>) é uma arquitetura especializada de aprendizado profundo (<italic>deep learning</italic>) projetada para extrair e analisar padrões espaciais em imagens, possibilitando aplicações em decisões diagnósticas e monitoramento clínico longitudinal. Seu uso em tomografia computadorizada e ressonância magnética, por meio da segmentação de imagens cardíacas, permite definir estruturas cardíacas de forma rápida e eficiente, desempenhando um papel importante na reconstrução de imagens tridimensionais e no suporte a procedimentos pré-operatórios. Além disso, em comparação com outras formas de análise convencional, a CNN garante interpretações objetivas e qualidade superior de imagem, com base na remoção de artefatos do segmento estudado. Ecocardiogramas têm mostrado bons resultados na identificação de patologias como hipertensão pulmonar, amiloidose, cardiomiopatia hipertrófica e doenças congênitas, e estudos sobre a automação desses exames apontam para uma possível ampliação do acesso em áreas remotas onde operadores manuais não estão disponíveis. Consequentemente, abordagens baseadas em CNN têm o potencial de otimizar os fluxos de trabalho em imagem cardiovascular, minimizar a variabilidade entre observadores e expandir as capacidades diagnósticas para regiões carentes e remotas com acesso limitado a cuidados especializados.</p>
</abstract>
<kwd-group xml:lang="pt">
<title>Palavras-chave</title>
<kwd>Redes neurais de computação</kwd>
<kwd>inteligência artificial</kwd>
<kwd>técnicas de imagem cardíaca</kwd>
</kwd-group>
<funding-group>
<funding-statement>O presente estudo não teve fontes de financiamento externas</funding-statement>
</funding-group>
</front-stub>
<body>
<fig id="f2">
<caption>
<title>Aplicações de Redes Neurais Convolucionais em diferentes tipos de métodos de imagem diagnóstica em cardiologia.</title>
<p>TC: Tomografia Computadorizada; RM: Ressonância Magnética; ECO: Ecocardiografia; HAP: Hipertensão Arterial Pulmonar; CMH: Cardiomiopatia Hipertrófica; FA: Fibrilação Atrial; CIA: Comunicação Interatrial; PCA: Persistência do Canal Arterial; DAC: Doença Arterial Coronariana.</p></caption>
<graphic xlink:href="2675-312X-abcic-38-03-e20250058-gf01-pt.tif"/>
</fig>
<sec sec-type="intro">
<title>Introdução</title>
<p>O sistema nervoso humano é uma das formas mais eficientes de captar e interpretar dados, refletindo os estímulos e experiências aos quais o corpo é submetido ao longo da vida.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Segundo o fenômeno da neuroplasticidade, todas essas interações provocam modificações no cérebro, permitindo sua adaptação para a tomada de decisões e possibilitando que conhecimentos pré-existentes sejam assimilados e sirvam de base para a formação de novos circuitos de informação.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
<p>As redes neurais surgiram como modelos artificiais que buscam reproduzir esse processamento de forma rápida e eficaz, com o objetivo de solucionar os problemas propostos, tornando-se ferramentas importantes no dinâmico campo da Inteligência Artificial (IA).<sup><xref ref-type="bibr" rid="B3">3</xref></sup> Para enfrentar esse desafio, as redes são treinadas para reconhecer padrões a partir de milhares ou até milhões de exemplos, permitindo que o sistema desenvolva sua própria capacidade de aprendizado.<sup><xref ref-type="bibr" rid="B4">4</xref></sup> Isso ocorre por meio do que se chama de &quot;<italic>input</italic>&quot;, ou seja, qualquer novo conceito inserido na ordenação. O conjunto de entradas gera uma resposta, o &quot;<italic>output</italic>&quot;, que pode ser influenciado de maneira ponderada, sempre guiado por um padrão de referência que serve como base.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
<p>Isso pode ser exemplificado de forma simples: na avaliação de um paciente com suspeita de Fibrilação Atrial (FA), quando um eletrocardiograma é solicitado para investigação, cada voltagem no traçado pode assumir o papel de um neurônio de entrada, que continua influenciando a cascata e serve como nova entrada para o próximo neurônio, solidificando a resposta final.<sup><xref ref-type="bibr" rid="B6">6</xref></sup> Assim, se o diagnóstico for FA sem que haja traçado correspondente, os pesos que levaram a esse resultado são reduzidos. Por outro lado, se houver correspondência, eles são reforçados e reutilizados em análises subsequentes.<sup><xref ref-type="bibr" rid="B7">7</xref></sup> Além disso, podem ser adicionadas informações extras, como idade, sexo e comorbidades do paciente.</p>
<p>A aplicação da IA na área médica tem sido amplamente explorada e, nos últimos anos, tornou-se uma tecnologia disruptiva na interpretação de imagens.<sup><xref ref-type="bibr" rid="B8">8</xref></sup> Nesse contexto, a Rede Neural Convolucional (CNN, do inglês <italic>Convolutional Neural Network</italic>) surgiu como uma versão desse processamento voltada para o reconhecimento e a classificação de imagens, reduzindo o esforço computacional e aumentando sua robustez.<sup><xref ref-type="bibr" rid="B8">8</xref></sup> A disposição hierárquica de múltiplas camadas convolucionais permite que as CNNs transformem progressivamente características de baixo nível – como gradientes de intensidade de pixels – em representações cada vez mais abstratas e clinicamente relevantes.<sup><xref ref-type="bibr" rid="B9">9</xref></sup> Durante o período de treinamento, a CNN ajusta e individualiza seus filtros de acordo com a tarefa a ser executada. De certa forma, a classificação de imagens começa pela detecção das bordas de pixels mais grosseiros na camada inicial, utilizando essas informações para identificar formas simples na segunda camada e assim por diante, permitindo a distinção de características mais complexas. Por fim, a última camada é responsável pela leitura avançada da imagem, com base nos filtros construídos.<sup><xref ref-type="bibr" rid="B10">10</xref></sup></p>
<p>A vantagem das CNNs em relação a outras redes neurais é que elas estabelecem os recursos essenciais para uma previsão bem-sucedida, reduzindo a dimensionalidade dos dados na camada anterior.<sup><xref ref-type="bibr" rid="B11">11</xref></sup></p>
<p>A segmentação precisa de imagens cardíacas é essencial para a tomada de decisões clínicas, e as técnicas de Deep Learning e o uso da CNN têm demonstrado resultados notáveis nessa área. No entanto, a quantificação e análise dessas imagens ainda representam um desafio contínuo, devido à complexidade das subestruturas cardíacas e à variabilidade anatômica existente. A individualização dessa análise é fundamental para consolidar evidências objetivas das mais variadas patologias investigadas, facilitando o diagnóstico, o monitoramento e o acompanhamento clínico do paciente.<sup><xref ref-type="bibr" rid="B12">12</xref></sup></p>
<p>Nessa abordagem, o uso da segmentação de imagens por meio de CNNs permite respostas rápidas e eficientes. Isso ocorre porque, em determinadas situações, a presença de certas características é mais relevante do que outras. Às vezes, identificar a localização de uma alteração na câmara cardíaca é o único objetivo essencial, não sendo necessário visualizar essas estruturas com alta definição de pixels.<sup><xref ref-type="bibr" rid="B13">13</xref></sup></p>
<p>O cenário de aplicação abrange uma ampla variedade de exames de imagem, desde a ecocardiografia – utilizada para calcular os volumes sistólico final e diastólico final – até a avaliação dos espaços ventriculares e atriais em múltiplos cortes, além da detecção de placas de calcificação coronariana por meio da angiotomografia coronária guiada por tomografia computadorizada (CCTA). A versatilidade das CNNs na imagem cardíaca é ilustrada na Figura Central. Na maioria dos casos, esses aspectos são apoiados por figuras e diagramas provenientes de atlas ou outros documentos incluídos no banco de dados do modelo. Outro ponto interessante é que já existem estudos que exploram o uso desses sistemas para avaliar e garantir a qualidade de ultrassonografias e outros exames diagnósticos.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
<sec>
<title>Aplicações de CNN na Tomografia Computadorizada (TC)</title>
<p>O uso de CNNs tem se destacado na automatização da segmentação de estruturas cardíacas e vasculares em imagens de Tomografia Computadorizada (TC), processo pelo qual estruturas cardíacas ou lesões patológicas são delimitadas.<sup><xref ref-type="bibr" rid="B5">5</xref>,<xref ref-type="bibr" rid="B12">12</xref>,<xref ref-type="bibr" rid="B13">13</xref></sup> A segmentação de imagens cardíacas por TC possui relevância clínica na identificação de doenças valvulares, avaliação de doença arterial coronariana, diagnóstico de cardiopatias congênitas, planejamento pré-operatório e em indicações extracardíacas.<sup><xref ref-type="bibr" rid="B12">12</xref></sup> A aplicação de CNNs trouxe rapidez e eficiência ao processo de segmentação cardíaca, que anteriormente era realizado de forma manual e subjetiva por radiologistas. Em um estudo sobre a segmentação de câmaras cardíacas e grandes vasos, Sharkey et al.<sup><xref ref-type="bibr" rid="B14">14</xref></sup> apresentaram resultados indicando que a variabilidade da análise entre observadores é semelhante à variabilidade entre o observador e a CNN.<sup><xref ref-type="bibr" rid="B14">14</xref></sup> Esses achados sustentam a premissa de que a segmentação baseada em CNN pode fornecer resultados reprodutíveis, objetivos e com precisão diagnóstica comparável à avaliação manual realizada por especialistas.</p>
<p>Com relação à identificação de estruturas anatômicas, Chen et al.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> demonstraram que a CNN se mostrou uma ferramenta precisa e eficiente para avaliar o volume e a reconstrução tridimensional do átrio esquerdo. O cálculo de volume por meio da CNN revelou-se capaz de prever o risco de recorrência de FA em pacientes após ablação por cateter. Astudillo et al.<sup><xref ref-type="bibr" rid="B16">16</xref></sup> utilizaram uma técnica de CNN para identificar as cúspides coronarianas e os óstios coronarianos direito e esquerdo em tomografia computadorizada com múltiplos detectores. Essas estruturas são pontos de referência importantes para definir o perímetro e a área do anel aórtico e, consequentemente, as próteses valvares a serem implantadas por via transcateter. O método mostrou-se reprodutível e confiável, podendo ser aplicado no planejamento pré-operatório de rotina, com o objetivo de reduzir o tempo gasto e aumentar a precisão na definição dos pontos de referência.</p>
<p>As CNNs também se mostraram excelentes ferramentas para a identificação de imagens patológicas na angiografia coronariana. A angiotomografia coronária por tomografia computadorizada é um método importante para avaliar a gravidade da estenose arterial, além de apresentar alta precisão na quantificação da aterosclerose quando comparada ao ultrassom intravascular. Em um estudo multicêntrico, uma rede neural foi treinada para segmentar placas coronarianas.<sup><xref ref-type="bibr" rid="B17">17</xref></sup> O estudo demonstrou excelente concordância entre a ferramenta de <italic>Deep Learning</italic> e as medições realizadas por leitores experientes quanto ao volume da placa ateromatosa e ao grau de estenose arterial. Também houve concordância com as medições por ultrassom vascular, além de valor prognóstico em relação ao risco de infarto agudo do miocárdio futuro.</p>
<p>A quantificação do tecido adiposo epicárdico também pode ser otimizada com o uso de CNNs. O tecido adiposo epicárdico é um depósito metabolicamente ativo de gordura visceral e pode estar relacionado à obesidade visceral e à síndrome metabólica.<sup><xref ref-type="bibr" rid="B18">18</xref></sup> A angiografia coronária é o padrão-ouro para identificar esse tecido, mas sua quantificação manual é trabalhosa e desafiadora. Nesse cenário, West et al.<sup><xref ref-type="bibr" rid="B19">19</xref></sup> desenvolveram uma CNN para quantificar automaticamente o tecido adiposo epicárdico e identificar sua associação clínica com doenças cardíacas e não cardíacas. O método mostrou-se preciso, rápido e reprodutível para a quantificação da adiposidade epicárdica por meio da angiografia coronária. A ferramenta também demonstrou bom valor prognóstico para mortalidade geral e para eventos cardiovasculares.</p>
</sec>
<sec>
<title>Aplicações de CNN na Ressonância Magnética</title>
<p>Nos últimos anos, a Ressonância Magnética (RM) tornou-se uma excelente ferramenta para a investigação de doenças cardiovasculares, com alta capacidade para fornecer diagnósticos complexos.<sup><xref ref-type="bibr" rid="B20">20</xref>,<xref ref-type="bibr" rid="B21">21</xref></sup> Trata-se de um método não invasivo, versátil e livre de radiação ionizante, capaz de identificar estrutura, função, fluxo e caracterização do tecido cardíaco. O realce tardio com gadolínio e os mapeamentos T1/T2 adicionaram informações importantes sobre a viabilidade cardíaca e patologias como infarto tecidual e fibrose miocárdica difusa.</p>
<p>O desenvolvimento da RM de fluxo também trouxe avanços significativos ao fornecer informações sobre o fluxo sanguíneo em diversos planos, permitindo a identificação de <italic>shunts</italic> intracardíacos.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> No entanto, o longo tempo de escaneamento e a produção lenta de imagens são desvantagens da RM. As imagens de RM devem considerar os movimentos cardíacos e respiratórios para evitar artefatos, que precisam ser suprimidos por algoritmos de reconstrução. Nesse cenário, os métodos de reconstrução baseados em Deep Learning têm demonstrado desempenho superior em comparação com algoritmos convencionais, oferecendo imagens de maior fidelidade, melhor supressão de artefatos e tempos de processamento substancialmente reduzidos.</p>
<p>Hauptmann et al.<sup><xref ref-type="bibr" rid="B22">22</xref></sup> treinaram uma CNN residual tridimensional em arquitetura U-Net para remover artefatos espaço-temporais em dados de ressonância magnética (RM) em tempo real com subamostragem (<italic>subsampling</italic>), a partir de imagens de pacientes com cardiopatias congênitas. A remoção de artefatos pela CNN foi comparada à técnica convencional de compressão sensorial, uma ferramenta que exige reconstrução computacional intensa e demorada. O método baseado em CNN alcançou supressão de artefatos mais de cinco vezes mais rápida que a abordagem de compressão sensorial, além de oferecer qualidade de imagem superior e medições volumétricas ventriculares mais precisas. El-Rewaidy et al.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> também apresentaram resultados importantes na reconstrução de imagens de RM com realce tardio por gadolínio utilizando uma rede neural convolucional.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> Em comparação com a técnica de compressão sensorial, a reconstrução de imagens por meio da CNN foi 300 vezes mais rápida.</p>
<p>As CNNs influenciaram múltiplas etapas do fluxo de trabalho da RM, desde o planejamento da aquisição de imagens e reconstrução em tempo real até tarefas de pós-processamento, como análise quantitativa e modelagem prognóstica. Assim como a TC, a RM também desempenha um papel importante na segmentação e consequente identificação de estruturas cardíacas.<sup><xref ref-type="bibr" rid="B24">24</xref></sup> Nesse processo com RM, o uso de CNNs também tem sido associado à maior eficiência.<sup><xref ref-type="bibr" rid="B25">25</xref></sup> Sander et al.<sup><xref ref-type="bibr" rid="B26">26</xref></sup> utilizaram uma CNN para realizar a segmentação de estruturas cardíacas e outra CNN auxiliar para identificar automaticamente áreas com falhas de segmentação. O estudo mostrou que a segmentação de imagens cardíacas com CNNs, associada à correção manual das falhas detectadas, resultou em melhor desempenho.</p>
<p>No que diz respeito à identificação de doenças, muitos estudos têm utilizado índices convencionais de imagem como dados de entrada para redes neurais na tentativa de diagnosticar doenças cardíacas. Por exemplo, a presença de cicatrizes cardíacas identificadas por RM está associada a desfechos cardiovasculares desfavoráveis. Bekheet et al.<sup><xref ref-type="bibr" rid="B27">27</xref></sup> desenvolveram uma CNN chamada FibrosisNet para diagnosticar fibrose cardíaca por RM, demonstrando alta precisão e acurácia diagnóstica. Sharifrazi et al.<sup><xref ref-type="bibr" rid="B28">28</xref></sup> obtiveram resultados importantes ao combinar uma rede neural convolucional profunda com a técnica de agrupamento K-means, formando a CNN-KCL, para diagnosticar e classificar miocardite com base em dados de imagem por RM. A técnica baseada em CNN superou outros algoritmos tradicionais de <italic>machine learning</italic> na classificação da miocardite em termos de precisão e acurácia.</p>
</sec>
<sec>
<title>Aplicações de CNN na ecocardiografia</title>
<p>A ecocardiografia é o método de imagem mais acessível e amplamente utilizado para avaliar a estrutura e a função cardíaca. Suas vantagens incluem aquisição rápida de imagens e ausência de radiação ionizante, o que a torna um método eficiente e democrático. A ecocardiografia pode ser utilizada tanto para rastrear pacientes assintomáticos quanto para diagnosticar e acompanhar condições cardíacas.<sup><xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B30">30</xref></sup> Por ser um exame dependente do operador, exige certo grau de experiência por parte do profissional, podendo haver variações na interpretação.<sup><xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B31">31</xref></sup></p>
<p>Quando se trata da aplicação de interpretação automatizada de imagens na ecocardiografia, existem alguns desafios intrínsecos a esse método. O ecocardiograma consiste na geração de imagens estáticas, bem como vídeos e registros Doppler coletados de diferentes pontos de vista para obtenção dos parâmetros desejados. Além disso, os valores obtidos nas medições podem variar significativamente devido à variabilidade intrínseca dos batimentos cardíacos. Há também a variação existente ao extrapolar medições de imagens bidimensionais para medições de um objeto tridimensional.<sup><xref ref-type="bibr" rid="B32">32</xref>,<xref ref-type="bibr" rid="B33">33</xref></sup></p>
<p>Apesar desses impasses e considerando a complexidade do método diagnóstico em questão, uma abordagem de aprendizado automatizado traria muitos benefícios e auxiliaria na interpretação humana, ao permitir a identificação e classificação automática das imagens. De fato, o uso de <italic>Deep Learning</italic> (DL), e mais especificamente de CNNs, para treinar a IA na interpretação de ecocardiogramas poderia reduzir custos e, consequentemente, democratizar esse exame. Essa integração tecnológica permitiria a aquisição de ecocardiogramas por operadores com treinamento especializado limitado, facilitando assim o acesso à imagem cardíaca em regiões geograficamente remotas ou com poucos recursos.<sup><xref ref-type="bibr" rid="B32">32</xref></sup></p>
<p>Diversos estudos demonstraram a eficácia do uso de CNNs na ecocardiografia. Entre as aplicações observadas, a maioria está relacionada à quantificação da estrutura e função cardíaca, bem como à segmentação cardíaca.<sup><xref ref-type="bibr" rid="B10">10</xref>,<xref ref-type="bibr" rid="B29">29</xref>,<xref ref-type="bibr" rid="B34">34</xref>–<xref ref-type="bibr" rid="B38">38</xref></sup> As CNNs também têm sido utilizadas na detecção de hipertrofia ventricular esquerda,<sup><xref ref-type="bibr" rid="B39">39</xref>–<xref ref-type="bibr" rid="B41">41</xref></sup> na estenose aórtica,<sup><xref ref-type="bibr" rid="B42">42</xref>,<xref ref-type="bibr" rid="B43">43</xref></sup> na identificação de fases cardíacas,<sup><xref ref-type="bibr" rid="B44">44</xref></sup> na detecção precoce de infarto agudo do miocárdio,<sup><xref ref-type="bibr" rid="B45">45</xref></sup> e na classificação de visualizações cardíacas.<sup><xref ref-type="bibr" rid="B46">46</xref>,<xref ref-type="bibr" rid="B47">47</xref></sup> O modelo utilizado por Ghorbani et al.,<sup><xref ref-type="bibr" rid="B29">29</xref></sup> além de identificar com precisão elementos da estrutura e função cardíaca, treinou uma CNN para prever fenótipos sistêmicos que modificam o risco cardiovascular, como idade, sexo, altura e peso, a partir de imagens de ecocardiograma.<sup><xref ref-type="bibr" rid="B29">29</xref></sup></p>
<p>Zhang et al.<sup><xref ref-type="bibr" rid="B32">32</xref></sup> foram além e treinaram uma CNN para a interpretação totalmente automatizada de ecocardiogramas, incluindo identificação de visualizações, segmentação de imagens, quantificação da estrutura e função cardíaca e detecção de doenças. Esse estudo demonstrou sucesso na análise automatizada do tipo de visualização e na segmentação de imagens. Em relação à estrutura e função do coração, houve alguma discrepância entre as medições manuais e automatizadas, especialmente na estrutura, com tendência à superestimação dos valores. Por fim, o modelo foi bem-sucedido na identificação de Hipertensão Arterial Pulmonar (HAP), amiloidose e cardiomiopatia hipertrófica, com base na análise das massas, estrutura e função das câmaras cardíacas.<sup><xref ref-type="bibr" rid="B32">32</xref></sup></p>
<p>Estudos recentes também avaliaram o potencial para o diagnóstico automático da HAP.<sup><xref ref-type="bibr" rid="B48">48</xref></sup> Segundo os achados de DuBrock et al.,<sup><xref ref-type="bibr" rid="B49">49</xref></sup> o algoritmo utilizado foi capaz de antecipar o diagnóstico de HAP em um período de seis a dezoito meses – um avanço extremamente relevante em uma condição na qual o diagnóstico precoce é crucial para o manejo eficaz da doença.<sup><xref ref-type="bibr" rid="B48">48</xref>,<xref ref-type="bibr" rid="B49">49</xref></sup></p>
<p>Outra patologia que pode ser identificada por meio da ecocardiografia com o uso de CNNs é a FA oculta. Yuan et al.<sup><xref ref-type="bibr" rid="B50">50</xref></sup> desenvolveram um modelo capaz de distinguir entre ritmo sinusal e FA, além de prever a presença concomitante de FA paroxística em indivíduos com ritmo sinusal. O modelo superou métodos tradicionais baseados em fatores de risco clínicos, medições do ecocardiograma transtorácico, tamanho do átrio esquerdo ou escore CHA<sub>2</sub>DS<sub>2</sub>-VASc.<sup><xref ref-type="bibr" rid="B50">50</xref></sup> Pesquisas utilizando técnicas de DL também têm apresentado resultados promissores na ecocardiografia fetal e neonatal, incluindo o diagnóstico pré-natal de defeito do septo atrial<sup><xref ref-type="bibr" rid="B51">51</xref></sup> e a identificação de persistência do canal arterial em neonatos.<sup><xref ref-type="bibr" rid="B52">52</xref></sup></p>
</sec>
<sec sec-type="methods">
<title>Aplicação de CNN em outros métodos</title>
<p>A TC por emissão de fóton único (SPECT) de perfusão miocárdica é um exame capaz de identificar a presença de isquemia miocárdica e, portanto, de doença arterial coronariana. Betancur et al.<sup><xref ref-type="bibr" rid="B53">53</xref></sup> analisaram a aplicação de DL nesse método diagnóstico, com o objetivo de verificar a capacidade de prever automaticamente a doença coronariana por meio de CNNs treinadas com imagens de perfusão miocárdica, em comparação com o método convencional atualmente utilizado. O resultado foi uma maior eficácia e melhor sensibilidade de detecção com o método baseado em DL.<sup><xref ref-type="bibr" rid="B53">53</xref></sup> Outros estudos também avaliaram a capacidade de classificar automaticamente imagens de perfusão miocárdica. Papandrianos et al.<sup><xref ref-type="bibr" rid="B54">54</xref></sup> treinaram CNNs para identificar três possíveis resultados – infarto, isquemia e perfusão normal – e todos os modelos avaliados apresentaram resultados positivos e confiáveis.<sup><xref ref-type="bibr" rid="B54">54</xref></sup> Su et al.<sup><xref ref-type="bibr" rid="B55">55</xref></sup> demonstraram a viabilidade e precisão do diagnóstico de doença arterial coronariana baseado em CNN, com um sistema já utilizado na prática, e capaz de reduzir consideravelmente o tempo necessário para interpretar as imagens.</p>
<p>A fluoroscopia por raios X permite a visualização em tempo real da estrutura cardíaca, o que a torna um método indispensável para a realização de procedimentos guiados por imagem, como a terapia de ressincronização cardíaca, angiografia e reparo endovascular da aorta. O DL também tem sido testado com sucesso para auxiliar esses procedimentos, seja na redução de ruído em vídeos ou na fusão de dados pré-operatórios com imagens intraoperatórias de raios X, com o objetivo de guiar a intervenção e reduzir a exposição ao contraste.<sup><xref ref-type="bibr" rid="B56">56</xref>–<xref ref-type="bibr" rid="B59">59</xref></sup> Estudos também demonstraram melhor sensibilidade e especificidade na caracterização de lesões coronarianas utilizando tomografia de coerência óptica quando o DL é aplicado.<sup><xref ref-type="bibr" rid="B60">60</xref>–<xref ref-type="bibr" rid="B62">62</xref></sup></p>
</sec>
</sec>
<sec sec-type="conclusions">
<title>Conclusão</title>
<p>A aplicação de CNNs na análise de imagens cardíacas surgiu como uma ferramenta versátil, contribuindo para diagnósticos mais precisos e rápidos. Sua integração à imagem cardiovascular permite reduzir a variabilidade entre observadores, minimizar artefatos de imagem, aprimorar a automação de medições e superar barreiras geográficas ao possibilitar a avaliação remota de imagens adquiridas – democratizando, assim, o acesso ao cuidado. As direções futuras devem priorizar estudos de validação em larga escala para confirmar a generalização e a robustez clínica das abordagens baseadas em CNNs em diferentes populações de pacientes e protocolos de imagem. Além disso, a integração desses algoritmos aos fluxos de trabalho clínicos rotineiros exigirá a superação de desafios regulatórios e de interoperabilidade, a fim de garantir uma adoção segura e eficaz na prática cardiovascular real.</p>
</sec>
</body>
<back>
<fn-group>
<fn fn-type="financial-disclosure" id="fn5"><label>Fontes de financiamento</label>
<p>O presente estudo não teve fontes de financiamento externas.</p></fn>
<fn fn-type="other" id="fn6"><label>Vinculação acadêmica</label>
<p>Não há vinculação deste estudo a programas de pós-graduação.</p></fn>
<fn fn-type="other" id="fn7"><label>Aprovação ética e consentimento informado</label>
<p>Este artigo não contém estudos com humanos ou animais realizados por nenhum dos autores.</p></fn>
<fn fn-type="other" id="fn8"><label>Uso de Inteligência Artificial</label>
<p>Os autores não utilizaram ferramentas de inteligência artificial no desenvolvimento deste trabalho.</p></fn>
</fn-group>
<sec sec-type="data-availability" specific-use="data-in-article">
<label>Disponibilidade de Dados</label>
<p>Os conteúdos subjacentes ao texto da pesquisa estão contidos no manuscrito.</p>
</sec>
</back>
</sub-article>
</article>