<?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 article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="en" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">
	<front>
		<journal-meta>
			<journal-id journal-id-type="publisher-id">dic</journal-id>
			<journal-title-group>
				<journal-title>Arquivos Brasileiros de Cardiologia Imagem cardiovascular</journal-title>
				<abbrev-journal-title abbrev-type="publisher">Arq Bras Cardiol: Imagem cardiovasc</abbrev-journal-title>
			</journal-title-group>
			<issn pub-type="epub">2675-312X</issn>
			<publisher>
				<publisher-name>Sociedade Brasileira de Cardiologia</publisher-name>
			</publisher>
		</journal-meta>
		<article-meta>
			<article-id pub-id-type="doi">10.36660/abcimg.2023371i</article-id>
			<article-categories>
				<subj-group subj-group-type="heading">
					<subject>Original Article</subject>
				</subj-group>
			</article-categories>
			<title-group>
				<article-title>Automatic Measurement of the Mitral Valve Based on Echocardiography Using Digital Image Processing</article-title>
			</title-group>
			<contrib-group>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0001-8744-6600</contrib-id>
					<name>
						<surname>Barros</surname>
						<given-names>Genilton de França</given-names>
						<suffix>Filho</suffix>
					</name>
					<role>Conception and design of the research, analysis and interpretation of the data, statistical analysis</role>
					<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0009-0005-0569-7155</contrib-id>
					<name>
						<surname>Solha</surname>
						<given-names>Israel</given-names>
					</name>
					<role>Conception and design of the research, analysis and interpretation of the data, statistical analysis</role>
					<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0009-0005-5619-4080</contrib-id>
					<name>
						<surname>Medeiros</surname>
						<given-names>Ewerton Freitas de</given-names>
					</name>
					<role>Conception and design of the research,analysis and interpretation of the data, statistical analysis</role>
					<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0001-7046-8707</contrib-id>
					<name>
						<surname>Felix</surname>
						<given-names>Alex dos Santos</given-names>
					</name>
					<role>acquisition of data</role>
					<xref ref-type="aff" rid="aff2"><sup>2</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-1777-477X</contrib-id>
					<name>
						<surname>Almeida</surname>
						<given-names>André Luiz Cerqueira de</given-names>
					</name>
					<role>critical revision of the manuscript for intellectual conten</role>
					<xref ref-type="aff" rid="aff3"><sup>3</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-9083-7650</contrib-id>
					<name>
						<surname>Lima</surname>
						<given-names>José Carlos de</given-names>
						<suffix>Júnior</suffix>
					</name>
					<role>critical revision of the manuscript for intellectual conten</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, acquisition of data, analysis and interpretation of the data, critical revision of the manuscript for intellectual conten</role>
					<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-3663-5097</contrib-id>
					<name>
						<surname>Rodrigues</surname>
						<given-names>Marcelo Cavalcanti</given-names>
					</name>
					<role>Conception and design of the research, analysis and interpretation of the data, critical revision of the manuscript for intellectual content</role>
					<xref ref-type="aff" rid="aff1"><sup>1</sup></xref>
				</contrib>
			</contrib-group>
			<aff id="aff1">
				<label>1</label>
				<institution content-type="orgname">Universidade Federal da Paraíba</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">Brazil</country>
				<institution content-type="original">Universidade Federal da Paraíba, João Pessoa, PB – Brazil</institution>
			</aff>
			<aff id="aff2">
				<label>2</label>
				<institution content-type="orgname">Instituto Nacional de Cardiologia</institution>
				<addr-line>
					<named-content content-type="city">Rio de Janeiro</named-content>
					<named-content content-type="state">RJ</named-content>
				</addr-line>
				<country country="BR">Brazil</country>
				<institution content-type="original">Instituto Nacional de Cardiologia, Rio de Janeiro, RJ – Brazil</institution>
			</aff>
			<aff id="aff3">
				<label>3</label>
				<institution content-type="orgname">Departamento de Imagem Cardiovascular</institution>
				<addr-line>
					<named-content content-type="city">São Paulo</named-content>
					<named-content content-type="state">SP</named-content>
				</addr-line>
				<country country="BR">Brazil</country>
				<institution content-type="original">Departamento de Imagem Cardiovascular, São Paulo, SP – Brazil</institution>
			</aff>
			<author-notes>
				<corresp id="c01">
					<label>Correspondência</label>: Genilton de França Barros Filho • Rua Luiza Dantas de Medeiros, 261, apt. 103 G. Postal code: 58073-040. José Américo, João Pessoa, PB - Brazil E-mail: <email>gfbfilho@gmail.com</email>
				</corresp>
				<fn fn-type="conflict">
					<p>Potential Conflict of Interest</p>
					<p>No potential conflict of interest relevant to this article was reported.</p>
				</fn>
				<fn fn-type="edited-by">
					<p>Editor responsible for the review: Daniela do Carmo Rassi Frota</p>
				</fn>
			</author-notes>
			<pub-date date-type="pub" publication-format="electronic">
				<day>24</day>
				<month>03</month>
				<year>2023</year>
			</pub-date>
			<pub-date date-type="collection" publication-format="electronic">
				<year>2023</year>
			</pub-date>
			<volume>36</volume>
			<issue>1</issue>
			<elocation-id>e371</elocation-id>
			<history>
				<date date-type="received">
					<day>18</day>
					<month>12</month>
					<year>2022</year>
				</date>
				<date date-type="rev-recd">
					<day>27</day>
					<month>01</month>
					<year>2023</year>
				</date>
				<date date-type="accepted">
					<day>1</day>
					<month>01</month>
					<year>2023</year>
				</date>
			</history>
			<permissions>
				<license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by-nc/4.0/">
					<license-p> This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. </license-p>
				</license>
			</permissions>
			<abstract>
				<title>Abstract</title>
				<sec>
					<title>Background</title>
					<p> The evaluation of mitral valve area through multiplanar reconstruction in 3-dimensional echocardiography is restricted to specific software and to the experience of echocardiographers. They need to manually select the video frame that contains the maximum mitral valve opening area, as this dimension is fundamental to identification of mitral stenosis.</p>
				</sec>
				<sec>
					<title>Objective</title>
					<p> To automate the process of determining the maximum mitral valve opening area, through the application of digital image processing (DIP) in echocardiography tests, developing an open algorithm with video reading in avi format.</p>
				</sec>
				<sec>
					<title>Method</title>
					<p> This cross-sectional observational pilot study was conducted with 25 different echocardiography exams, 15 with normal aperture and 10 with rheumatic mitral stenosis. With the authorization of the Research Ethics Committee, all exams were performed and made available by 2 specialists who used 2 models of echocardiographic devices: Vivid E95 (GE Healthcare) and Epiq 7 (Philips), with multiplanar transesophageal probes. All videos in avi format were submitted to DIP using the image segmentation technique.</p>
				</sec>
				<sec>
					<title>Results</title>
					<p> The measurements obtained manually by experienced echocardiographers and the values calculated by the developed system were compared using a Bland-Altman diagram. There was greater agreement between values in the range from 0.4 to 2.7 cm<sup>2</sup>.</p>
				</sec>
				<sec>
					<title>Conclusion</title>
					<p> It was possible to automatically determine the maximum mitral valve opening area, for cases from both GE and Philips, using only 1 video as input data. The algorithm has been demonstrated to save time on measurements when compared to the usual method.</p>
				</sec>
			</abstract>
			<kwd-group xml:lang="en">
				<kwd>Mitral Valve</kwd>
				<kwd>Echocardiography</kwd>
				<kwd>Image Processing, Computer-Assisted</kwd>
			</kwd-group>
			<counts>
				<fig-count count="12"/>
				<table-count count="0"/>
				<equation-count count="0"/>
				<ref-count count="16"/>
			</counts>
		</article-meta>
	</front>
	<body>
		<sec sec-type="intro">
			<title>Introduction</title>
			<p>Valve diseases are important determinants of cardiovascular morbidity and mortality, with degenerative diseases of the mitral and aortic valves being the most prevalent, even though rheumatic disease still constitutes an important public health problem in Brazil. Echocardiography plays an important role in the diagnosis and severity assessment of valve diseases. It is able to determine anatomical and pathophysiological details that assist in planning the best intervention for each patient, and it has the advantages of being widely available and low cost, without requiring radiation or nephrotoxic contrast.<sup><xref ref-type="bibr" rid="B1">1</xref></sup></p>
			<p>Among the most common imaging tests, echocardiography is the most frequently used modality in the evaluation of mitral valve diseases. This is possible because it is a more readily available and widely used technique to assess function and structure. Echocardiography makes real-time imaging possible without the presence of ionizing radiation, serving today as a backbone in the field of cardiovascular imaging.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
			<p>The use of 3-dimensional echocardiography provides numerous advantages, such as the possibility of real-time navigation, image post-processing, and multiplanar reconstruction. It is especially important for the preoperative evaluation of patients who are candidates for valve repair or replacement surgery. It allows intraoperative monitoring of procedures, such as transcatheter aortic valve replacement<sup><xref ref-type="bibr" rid="B3">3</xref></sup> and implantation of clips for percutaneous mitral repair (Mitraclip). It also makes it possible to conduct procedures to treat rheumatic mitral stenosis, such as percutaneous mitral balloon valvuloplasty, or even percutaneous implantation of a biological mitral valve prosthesis by transcatheter mitral valve replacement, in patients with degenerative mitral disease and calcification of the valve annulus, or percutaneous prosthesis implantation inside a dysfunctional biological prosthesis (mitral valve-in-valve procedure). The procedures described have shown great evolution, with increasingly effective results due to the help of multimodal cardiac imaging in pre-procedure evaluation and during the intervention.<sup><xref ref-type="bibr" rid="B4">4</xref>,<xref ref-type="bibr" rid="B5">5</xref></sup></p>
			<p>During interventions, decisions must be be agile, and accurate information must be provided to the interventionist; therefore, the quality of communication between teams is essential. Through visual demonstration of structures, made possible by 3-dimensional reconstruction and rendering, with more accurate measurements that are less dependent on angulations, such as those obtained by multiplanar reconstruction, it is possible to obtain better results, with greater efficiency and lower rate of complications.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
			<p>There is significant variation in the human interpretation of echocardiographic data, in addition to errors in measurements, due to considerable inter-observer variability. The use of automated systems for the interpretation of cardiovascular images can be useful in improving the methods’ diagnostic and prognostic performance, and the application of machine learning to medical images, with the help of specialists’ interpretation, increases the reliability of the process due to the availability of various data structured by reports.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
			<p>The accurate evaluation of the mitral valve area by means of multiplanar reconstruction on 3-dimensional transesophageal echocardiography is totally dependent on the examiner’s experience and expertise in using specific software, which may not be available on some platforms or may not even be very practical to use, thus consuming exam time.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
			<p>Digital image processing (DIP) has been gaining recognition in 2 main areas of application, namely, improving visual information from imaging for human interpretation and processing imaging data for storage, transmission, and representation, considering automatic machine perception.<sup><xref ref-type="bibr" rid="B7">7</xref></sup></p>
			<p>It consists of manipulation of images by a computer, with different applications, such as contrast enhancement, noise reduction, tracking objects and/or people, edge detection, pattern identification, classification and counting of objects and/or people, and many others.<sup><xref ref-type="bibr" rid="B7">7</xref></sup> Among multiple existing DIP techniques, image segmentation has been applied. This technique produces a binary image, with pixels of value 1, indicating they are part of the object under study, and pixels of value 0, indicating they are not. Thus, it is possible to divide an image into regions, identifying borders and discontinuities, for example.<sup><xref ref-type="bibr" rid="B8">8</xref></sup></p>
			<p>Several studies have contributed to the evolution of echocardiography analysis using computerized tools. For example, Sakamiya et al. created a platform for online monitoring of the contractile behavior of the heart, which are the main functional characteristics of cardiac tissue, simultaneously employing an image processing and piezoelectric detection system. They also evaluated the influence of medications such as isoproterenol and doxorubicin on the contractile behavior of the heart. The medication reactivity results provided by these 2 measurement systems were consistent with the previous reports they had, demonstrating the reliability of the developed platform and its potential for use in medication-related screening applications.<sup><xref ref-type="bibr" rid="B9">9</xref></sup></p>
			<p>Nizar et al. used a convolutional neural network for real-time detection of the aortic valve in echocardiography exams, with the purpose of assisting medical examination, since an automated detection system in an echocardiogram can improve the accuracy of the medical diagnosis and provide additional medical analysis from the resulting detection. Therefore, they concluded that this tool can be of great help for medical purposes.<sup><xref ref-type="bibr" rid="B10">10</xref></sup></p>
			<p>Ostvik et al. verified the possibility of applying artificial neural networks in the classification of transthoracic images obtained by echocardiography. The conclusion was satisfactory for the implementation in 2-dimensional echocardiography, and, for analysis of 3-dimensional echocardiography, studies still need to make gains in performance, seeing that it is conducted based on frames obtained during the procedure.⁠<sup><xref ref-type="bibr" rid="B11">11</xref></sup></p>
			<p>Therefore, the objective of this project is to automate the determination of maximum mitral valve opening area, by applying DIP to echocardiography exams and developing an open algorithm with video reading in avi format.</p>
		</sec>
		<sec sec-type="methods">
			<title>Methods</title>
			<p>Retrospective analyses were conducted in different echocardiography studies by experienced echocardiographers. The exams included patients who had “normal” mitral valves, that is, mitral valve openings in normal conditions, and patients with mitral valves affected by rheumatic stenosis.</p>
			<p>For acquisition, the echocardiographers used 2 echocardiography device models, with multiplanar transesophageal probes: the Vivid E95 (GE Healthcare) and the Epiq 7 (Philips). Each has its particularities. The most considerable difference, in relation to this research, is the way in which the image scale is represented. The Philips echocardiograph draws green dots, and the distance between their centroids is indicated as a numerical value belonging to the metric scale. The General Electric (GE) brand echocardiograph represents the scale at the bottom right of the image.</p>
			<p>After acquiring the exams saved as videos, they were submitted to DIP using the image segmentation technique, considering that a video is composed of a set of sequential static images. As a result, DIP identifies the maximum valve opening area, highlights its outline, and calculates its value.</p>
			<p>An application was developed to facilitate the use of DIP. People unfamiliar with programming are able to use it, as it has an intuitive graphical interface. It was created with python language.</p>
			<p>Finally, the results obtained by the application were compared with the results obtained by the echocardiographers, who manually selected the maximum valve opening area using specific software. To verify the correlation between both measurements, the Bland-Altman method was used.</p>
		</sec>
		<sec sec-type="results">
			<title>Results</title>
			<p>All exams obtained were saved in avi video format. A total of 25 videos were acquired, 22 from the GE echocardiography device and 3 from the Philips device. The number of tests used in the present study was limited by the study time and influenced by the pandemic, which made it difficult to acquire more tests.</p>
			<p>The study model was retrospective, cross-sectional, and observational, acquired in accordance with the recommendations of the American Society of Echocardiography.<sup><xref ref-type="bibr" rid="B12">12</xref></sup> Planimetry was performed by multiplanar reconstruction with ventricular and atrial view, using EchoPac v.204 for GE devices and directly on the Epiq 7 device during the echocardiography for the Philips devices.</p>
			<p>
				<xref ref-type="fig" rid="f01">Figure 1</xref> illustrates the interfaces of the developed application and how it functions.</p>
			<p>
				<fig id="f01">
					<label>Figure 1</label>
					<caption>
						<title>– Screens of the developed application. a) Home screen; b) Screen for processing videos from Philips echocardiography devices; c) Screen for selecting options for video from GE echocardiography devices; d) Screen for processing videos with only the 3-dimensional view from GE echocardiography devices (Case 1); e) Screen for processing videos with 3-dimensional, lateral, superior, and frontal views from GE echocardiography devices (Case 2).</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf01.tif"/>
				</fig>
			</p>
			<p>When the application is opened, the home screen is displayed (<xref ref-type="fig" rid="f01">Figure 1a</xref>). It displays 2 options: “Philips” and “General Electric”. The user must select the button according to the source of the video to be used for analysis. If the video was saved from echocardiograms performed using Philips devices, the “Philips” button must be selected. If the exams were performed using General Electric devices, the “General Electric” button must be selected.</p>
			<p>When selecting the “Philips” option, the screen in <xref ref-type="fig" rid="f01">Figure 1b</xref> will be displayed. The user must click on the “Select Video” button to load the video to be analyzed and, subsequently, inform the numerical scale present in the video. For example, if the exam was performed and saved with a 5 mm scale in the grid, the user must enter a value of 0.5 in the “Scale [cm]” field. Finally, the “Play” button must be selected for the application to perform the entire DIP to identify and calculate the maximum valve opening area. Additionally, the screen displays some instructions to facilitate the use of the application and to optimize the results to be obtained.</p>
			<p>If the “General Electric” option is selected on the initial screen (<xref ref-type="fig" rid="f01">Figure 1a</xref>), the screen in <xref ref-type="fig" rid="f01">Figure 1c</xref> will be displayed. This screen allows the user to choose how the video was saved. If it was saved with only the 3-dimensional view, the “Case 1” button must be selected. If it was saved with the 3-dimensional view and the frontal, lateral, and superior views, the “Case 2” button must be selected. This distinction is necessary, because the mode and characteristics of saved videos influence digital processing.</p>
			<p>The “Case 1” and “Case 2” buttons will display the screens in <xref ref-type="fig" rid="f01">Figures 1d and 1e</xref>, respectively. They function in the same manner as the screen in <xref ref-type="fig" rid="f01">Figure 1b</xref>, previously described.</p>
			<p>After selecting the “Play” button in <xref ref-type="fig" rid="f01">Figure 1b, Figure 1d, or Figure 1e</xref>, DIP transforms the video into a set of images (as in the example illustrated in <xref ref-type="fig" rid="f02">Figure 2</xref>), also called frames, to analyze them separately and to identify the image that contains the maximum valve opening area. As all images are isolated, the frame rate (frames per second) of each video did not interfere with the results.</p>
			<p>
				<fig id="f02">
					<label>Figura 2</label>
					<caption>
						<title>– Example illustrating the transformation of a video into multiple images (frames).</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf02.tif"/>
				</fig>
			</p>
			<p>After digital processing, the application displays the result, as illustrated in <xref ref-type="fig" rid="f03">Figure 3</xref>.</p>
			<p>
				<fig id="f03">
					<label>Figure 3</label>
					<caption>
						<title>– Results displayed by the developed application. a) Home screen; b) Final screen, with the image of the maximum valve opening selected.</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf03.tif"/>
				</fig>
			</p>
			<p>
				<xref ref-type="fig" rid="f03">Figure 3a</xref> illustrates the first screen displayed after the application executes the DIP. The maximum valve opening area is identified and drawn (white outline). The value of the maximum area is also displayed. In the case shown in <xref ref-type="fig" rid="f03">Figure 3a</xref>, the area is 4.45 cm<sup>2</sup>.</p>
			<p>In order to make the results more accurate, the application allows the user to check the preceding and subsequent images, with the buttons “Previous image” and “Next image”, respectively. They make it possible to verify the outlines that best correspond to reality.</p>
			<p>In the result shown in <xref ref-type="fig" rid="f03">Figure 3</xref>, although the outline in <xref ref-type="fig" rid="f03">Figure 3a</xref> shows a satisfactory result, the outline in <xref ref-type="fig" rid="f03">Figure 3b</xref> is more accurate and more consistent with the shape of the maximum valve opening. In fact, the maximum valve opening area became 4.5 cm<sup>2</sup>.</p>
			<p>The “Home screen” button returns to the initial screen of the application (<xref ref-type="fig" rid="f01">Figure 1a</xref>) and the “Select image” button saves the results obtained.</p>
			<p>
				<xref ref-type="fig" rid="f04">Figures 4</xref> and <xref ref-type="fig" rid="f05">5</xref> represent comparisons between the results obtained by measuring the maximum valve opening area performed by the developed application and by an echocardiographer. <xref ref-type="fig" rid="f04">Figure 4</xref> characterizes a “normal” case, and <xref ref-type="fig" rid="f05">Figure 5</xref> displays a case with stenosis.</p>
			<p>
				<fig id="f04">
					<label>Figure 4</label>
					<caption>
						<title>– Comparison between the measurement of the developed application and the measurement of an echocardiographer, with manual selection by means of specific software. a) Analyzed video of a “normal” case; b) Result of the developed application: Area of 4.59 cm2; c) Result of the echocardiographer’s measurement: Area of 4.7 cm2.</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf04.tif"/>
				</fig>
			</p>
			<p>
				<fig id="f05">
					<label>Figure 5</label>
					<caption>
						<title>– Comparison between the measurement of the developed application and the measurement of an echocardiographer, with manual selection by means of specific software. a) Analyzed video of a case with stenosis; b) Result of the developed application: Area of 0.51 cm2; c) Result of the echocardiographer’s measurement: Area of 0.6 cm2.</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf05.tif"/>
				</fig>
			</p>
			<p>Analysis of <xref ref-type="fig" rid="f04">Figures 4</xref> and <xref ref-type="fig" rid="f05">5</xref> reveals that the results were very close. For the “normal” case, the application provided the value of 4.59 cm<sup>2</sup> (<xref ref-type="fig" rid="f04">Figure 4b</xref>), and the echocardiographer’s measurement provided the value of 4.7 cm <sup>2</sup> (<xref ref-type="fig" rid="f04">Figure 4c</xref>). In the case with stenosis, the application provided the value of 0.51 cm<sup>2</sup> (<xref ref-type="fig" rid="f05">Figure 5b</xref>), and the echocardiographer’s measurement provided the value of 0.6 cm<sup>2</sup> (<xref ref-type="fig" rid="f05">Figure 5c</xref>).</p>
			<p>Furthermore, it was observed that the adoption of some practices optimizes the results of the application, for example, saving videos highlighting the mitral valve region, applying zoom, and saving videos with few elements, preferably only the region of interest and the scale used. However, further tests would be needed to validate this finding.</p>
			<p>With the identification of the maximum valve opening and the calculation of its value, the developed application is also able to detect whether or not the patient in the referred exam has stenosis.</p>
			<p>Furthermore, the processing time of the application is relatively low, remaining under 3 minutes for the majority of analyses.</p>
			<p>In order to verify the concordance of the results obtained by the application and by the echocardiographers’ measurements, the Bland-Altman method was applied, as shown in <xref ref-type="fig" rid="f06">Figure 6</xref>.</p>
			<p>
				<fig id="f06">
					<label>Figure 6</label>
					<caption>
						<title>– Bland-Altman method. a) Applied only to cases without stenosis; b) Applied only to cases with stenosis; c) Applied to all 25 tests used in this study.</title>
					</caption>
					<graphic xlink:href="2675-312X-dic-36-01-e371-gf06.tif"/>
				</fig>
			</p>
			<p>Using the Bland-Altman method, evaluating the cases with and without stenosis separately, agreement was found between the DIP and echocardiographers’ measurements in obtaining the maximum valve opening area (<xref ref-type="fig" rid="f06">Figure 6a and Figure 6b</xref>). Combining all cases, only 2 were outside the acceptable range (<xref ref-type="fig" rid="f06">Figure 6c</xref>). These results contribute to the validation of both the DIP technique employed and the developed application.</p>
			<p>For cases without stenosis (<xref ref-type="fig" rid="f06">Figure 6a</xref>), the greatest difference between measurements was 0.7 cm<sup>2</sup>, while most remained within the range of −0.5 cm<sup>2</sup> to 0.5 cm<sup>2</sup>. For cases with stenosis (<xref ref-type="fig" rid="f06">Figure 6b</xref>), the greatest difference between measurements was 0.2 cm<sup>2</sup>, and all remained within the range of −0.2 cm<sup>2</sup> to 0.2 cm<sup>2</sup>. Analyzing all cases (<xref ref-type="fig" rid="f06">Figure 6c</xref>), those with stenosis (points further to the left in <xref ref-type="fig" rid="f06">Figure 6c</xref>) had smaller differences in measurements compared to those without stenoses (points further to the right in <xref ref-type="fig" rid="f06">Figure 6c</xref>).</p>
		</sec>
		<sec sec-type="discussion">
			<title>Discussion</title>
			<p>This study stands out because it employs DIP, based on the image segmentation technique, to detect the maximum mitral valve opening area automatically, based on echocardiogram videos in avi format. Therefore, it contributes to the detection of mitral stenosis. A major differential is the application developed with python language, which allows easy access and easy handling of the DIP tools. It needs only be installed on a computer. The application’s screens were developed to improve users’ experience, and they do not require prior knowledge of programming.</p>
			<p>The developed application is capable of analyzing more complex cases, such as patients with arrhythmias, because the automatic selection makes it possible to check each image in the video, highlighting the image with the maximum valve opening. Moreover, the more measurements that are performed with the developed application and compared with medical measurements, especially with different and atypical cases, the more it will be tested, allowing better assessment for its consolidation.</p>
			<p>This automatic measurement has some advantages when compared with manual selection performed by echocardiographers, because the result can be heavily influenced by the moment when they pause the video to perform the analysis. This manual selection requires a great deal of the specialist’s time, considering that they must be very careful to carry out a selection with as little error as possible and with maximum attention. Considering a full day of care, the accuracy of the selected regions will be greater for the first patients of the day, and they will decrease according to the echocardiographer’s physical and mental fatigue, in addition to other external factors that may influence the measurement.</p>
			<p>When conducting a survey of the literature, nothing similar was found. However, one of the great efforts of researchers is to ensure the automation of measurements in operator-dependent examinations for the investigation of various pathologies, with the aim of reducing or eliminating manual selection errors. Thus, Saine et al. presented a technique for automatic boundary detection of the left atrium and ventricle based on 2-dimensional echocardiograms, with the objective of determining the dilation area of these chambers in patients with mitral valve insufficiency.<sup><xref ref-type="bibr" rid="B13">13</xref></sup></p>
			<p>Melo et al. developed a semiautomated method that determines variation in ventricular area on dynamic 2-dimensional echocardiograms using DIP techniques such as time averaging, wavelet-based denoising, edge enhancement filtering, morphological operations, homotopy modification, and watershed segmentation. This method has become useful for analyzing global ventricular function by measurements of area.<sup><xref ref-type="bibr" rid="B14">14</xref></sup></p>
			<p>Mahadi et al. verified the use of DIP in 2-dimensional echocardiograms to transform scan slices into a set of pixels and thus determine the distance of points that could measure the diameter of a mitral valve in a given view.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> Aquila et al. presented the use of a tool called Siemens eSie Valves which made it possible to automatically determine a series of parameters of the mitral valve annulus such as area, anteroposterior and posterolateral diameters, and intertrigonal distance. Therefore, this study compares existing anatomical alterations between functional and organic mitral regurgitation processes based on the automatic acquisition of valve measurements.<sup><xref ref-type="bibr" rid="B16">16</xref></sup></p>
			<p>Accordingly, this study offers another tool to combat possible human errors in measuring valve areas and to contribute to automation.</p>
		</sec>
		<sec sec-type="conclusions">
			<title>Conclusions</title>
			<p>It was possible to automatically determine the maximum mitral valve opening area, for cases from both GE and Philips echocardiography devices, using only 1 video as input data.</p>
			<p>As the application chooses the appropriate frame and calculates the area almost instantly, it can be intuitively concluded that it is faster than manual measurement.</p>
			<p>This study shows interesting potential because it does not depend on specific software, and it has a good outlook for obtaining measurements remotely.</p>
		</sec>
	</body>
	<back>
		<ref-list>
			<title>References</title>
			<ref id="B1">
				<label>1</label>
				<mixed-citation>1. Tarasoutchi F, Montera MW, Grinberg M, Piñeiro DJ, Sánchez CR, Bacelar AC, et al. Brazilian Guidelines for Valve Disease - SBC 2011 / I Guideline Inter-American Valve Disease - 2011 SIAC. Arq Bras Cardiol. 2011;97(5 Suppl 1):1-67. doi: 10.1590/s0066-782x2011002000001.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Tarasoutchi</surname>
							<given-names>F</given-names>
						</name>
						<name>
							<surname>Montera</surname>
							<given-names>MW</given-names>
						</name>
						<name>
							<surname>Grinberg</surname>
							<given-names>M</given-names>
						</name>
						<name>
							<surname>Piñeiro</surname>
							<given-names>DJ</given-names>
						</name>
						<name>
							<surname>Sánchez</surname>
							<given-names>CR</given-names>
						</name>
						<name>
							<surname>Bacelar</surname>
							<given-names>AC</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Brazilian Guidelines for Valve Disease - SBC 2011 / I Guideline Inter-American Valve Disease - 2011 SIAC</article-title>
					<source>Arq Bras Cardiol</source>
					<year>2011</year>
					<volume>97</volume>
					<issue>5</issue>
					<supplement>Suppl 1</supplement>
					<fpage>1</fpage>
					<lpage>67</lpage>
					<issue-id pub-id-type="doi">10.1590/s0066-782x2011002000001</issue-id>
				</element-citation>
			</ref>
			<ref id="B2">
				<label>2</label>
				<mixed-citation>2. Andreassen BS, Veronesi F, Gerard O, Solberg AHS, Samset E. Mitral Annulus Segmentation Using Deep Learning in 3-D Transesophageal Echocardiography. IEEE J Biomed Health Inform. 2020;24(4):994-1003. doi: 10.1109/JBHI.2019.2959430.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Andreassen</surname>
							<given-names>BS</given-names>
						</name>
						<name>
							<surname>Veronesi</surname>
							<given-names>F</given-names>
						</name>
						<name>
							<surname>Gerard</surname>
							<given-names>O</given-names>
						</name>
						<name>
							<surname>Solberg</surname>
							<given-names>AHS</given-names>
						</name>
						<name>
							<surname>Samset</surname>
							<given-names>E</given-names>
						</name>
					</person-group>
					<article-title>Mitral Annulus Segmentation Using Deep Learning in 3-D Transesophageal Echocardiography</article-title>
					<source>IEEE J Biomed Health Inform</source>
					<year>2020</year>
					<volume>24</volume>
					<issue>4</issue>
					<fpage>994</fpage>
					<lpage>1003</lpage>
					<issue-id pub-id-type="doi">10.1109/JBHI.2019.2959430</issue-id>
				</element-citation>
			</ref>
			<ref id="B3">
				<label>3</label>
				<mixed-citation>3. Reardon MJ, van Mieghem NM, Popma JJ, Kleiman NS, Søndergaard L, Mumtaz M, et al. Surgical or Transcatheter Aortic-Valve Replacement in Intermediate-Risk Patients. N Engl J Med. 2017;376(14):1321-31. doi: 10.1056/NEJMoa1700456.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Reardon</surname>
							<given-names>MJ</given-names>
						</name>
						<name>
							<surname>van Mieghem</surname>
							<given-names>NM</given-names>
						</name>
						<name>
							<surname>Popma</surname>
							<given-names>JJ</given-names>
						</name>
						<name>
							<surname>Kleiman</surname>
							<given-names>NS</given-names>
						</name>
						<name>
							<surname>Søndergaard</surname>
							<given-names>L</given-names>
						</name>
						<name>
							<surname>Mumtaz</surname>
							<given-names>M</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Surgical or Transcatheter Aortic-Valve Replacement in Intermediate-Risk Patients</article-title>
					<source>N Engl J Med</source>
					<year>2017</year>
					<volume>376</volume>
					<issue>14</issue>
					<fpage>1321</fpage>
					<lpage>1331</lpage>
					<issue-id pub-id-type="doi">10.1056/NEJMoa1700456</issue-id>
				</element-citation>
			</ref>
			<ref id="B4">
				<label>4</label>
				<mixed-citation>4. El Sabbagh A, Eleid MF, Foley TA, Al-Hijji MA, Daly RC, Rihal CS, et al. Direct Transatrial Implantation of Balloon-Expandable Valve for Mitral Stenosis with Severe Annular Calcifications: Early Experience and Lessons Learned. Eur J Cardiothorac Surg. 2018;53(1):162-9. doi: 10.1093/ejcts/ezx262.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>El Sabbagh</surname>
							<given-names>A</given-names>
						</name>
						<name>
							<surname>Eleid</surname>
							<given-names>MF</given-names>
						</name>
						<name>
							<surname>Foley</surname>
							<given-names>TA</given-names>
						</name>
						<name>
							<surname>Al-Hijji</surname>
							<given-names>MA</given-names>
						</name>
						<name>
							<surname>Daly</surname>
							<given-names>RC</given-names>
						</name>
						<name>
							<surname>Rihal</surname>
							<given-names>CS</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Direct Transatrial Implantation of Balloon-Expandable Valve for Mitral Stenosis with Severe Annular Calcifications: Early Experience and Lessons Learned</article-title>
					<source>Eur J Cardiothorac Surg</source>
					<year>2018</year>
					<volume>53</volume>
					<issue>1</issue>
					<fpage>162</fpage>
					<lpage>169</lpage>
					<issue-id pub-id-type="doi">10.1093/ejcts/ezx262</issue-id>
				</element-citation>
			</ref>
			<ref id="B5">
				<label>5</label>
				<mixed-citation>5. Mackensen GB, Lee JC, Wang DD, Pearson PJ, Blanke P, Dvir D, et al. Role of Echocardiography in Transcatheter Mitral Valve Replacement in Native Mitral Valves and Mitral Rings. J Am Soc Echocardiogr. 2018;31(4):475-90. doi: 10.1016/j.echo.2018.01.011.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Mackensen</surname>
							<given-names>GB</given-names>
						</name>
						<name>
							<surname>Lee</surname>
							<given-names>JC</given-names>
						</name>
						<name>
							<surname>Wang</surname>
							<given-names>DD</given-names>
						</name>
						<name>
							<surname>Pearson</surname>
							<given-names>PJ</given-names>
						</name>
						<name>
							<surname>Blanke</surname>
							<given-names>P</given-names>
						</name>
						<name>
							<surname>Dvir</surname>
							<given-names>D</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Role of Echocardiography in Transcatheter Mitral Valve Replacement in Native Mitral Valves and Mitral Rings</article-title>
					<source>J Am Soc Echocardiogr</source>
					<year>2018</year>
					<volume>31</volume>
					<issue>4</issue>
					<fpage>475</fpage>
					<lpage>490</lpage>
					<issue-id pub-id-type="doi">10.1016/j.echo.2018.01.011</issue-id>
				</element-citation>
			</ref>
			<ref id="B6">
				<label>6</label>
				<mixed-citation>6. 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>
				<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>et al</etal>
					</person-group>
					<article-title>Deep Learning Interpretation of Echocardiograms</article-title>
					<source>NPJ Digit Med</source>
					<year>2020</year>
					<volume>3</volume>
					<size units="pages">10</size>
					<issue-id pub-id-type="doi">10.1038/s41746-019-0216-8</issue-id>
				</element-citation>
			</ref>
			<ref id="B7">
				<label>7</label>
				<mixed-citation>7. Gonzalez RC, Woods RE. Processamento Digital de Imagens. São Paulo: Pearson Prentice Hall; 2010.</mixed-citation>
				<element-citation publication-type="book">
					<person-group person-group-type="author">
						<name>
							<surname>Gonzalez</surname>
							<given-names>RC</given-names>
						</name>
						<name>
							<surname>Woods</surname>
							<given-names>RE</given-names>
						</name>
					</person-group>
					<source>Processamento Digital de Imagens</source>
					<publisher-loc>São Paulo</publisher-loc>
					<publisher-name>Pearson Prentice Hall</publisher-name>
					<year>2010</year>
				</element-citation>
			</ref>
			<ref id="B8">
				<label>8</label>
				<mixed-citation>8. Jähne B. Digital Image Processing. Heidelberg: Springer; 2005.</mixed-citation>
				<element-citation publication-type="book">
					<person-group person-group-type="author">
						<name>
							<surname>Jähne</surname>
							<given-names>B</given-names>
						</name>
					</person-group>
					<source>Digital Image Processing</source>
					<publisher-loc>Heidelberg</publisher-loc>
					<publisher-name>Springer</publisher-name>
					<year>2005</year>
				</element-citation>
			</ref>
			<ref id="B9">
				<label>9</label>
				<mixed-citation>9. Sakamiya M, Fang Y, Mo X, Shen J, Zhang T. A Heart-On-A-Chip Platform for Online Monitoring of Contractile Behavior via Digital Image Processing and Piezoelectric Sensing Technique. Med Eng Phys. 2020;75:36-44. doi: 10.1016/j.medengphy.2019.10.001.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Sakamiya</surname>
							<given-names>M</given-names>
						</name>
						<name>
							<surname>Fang</surname>
							<given-names>Y</given-names>
						</name>
						<name>
							<surname>Mo</surname>
							<given-names>X</given-names>
						</name>
						<name>
							<surname>Shen</surname>
							<given-names>J</given-names>
						</name>
						<name>
							<surname>Zhang</surname>
							<given-names>T</given-names>
						</name>
					</person-group>
					<article-title>A Heart-On-A-Chip Platform for Online Monitoring of Contractile Behavior via Digital Image Processing and Piezoelectric Sensing Technique</article-title>
					<source>Med Eng Phys</source>
					<year>2020</year>
					<volume>75</volume>
					<fpage>36</fpage>
					<lpage>44</lpage>
					<issue-id pub-id-type="doi">10.1016/j.medengphy.2019.10.001</issue-id>
				</element-citation>
			</ref>
			<ref id="B10">
				<label>10</label>
				<mixed-citation>10. Nizar MHA, Chan CK, Khalil A, Yusof AKM, Lai KW. Real-Time Detection of Aortic Valve in Echocardiography using Convolutional Neural Networks. Curr Med Imaging. 2020;16(5):584-91. doi: 10.2174/1573405615666190114151255.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Nizar</surname>
							<given-names>MHA</given-names>
						</name>
						<name>
							<surname>Chan</surname>
							<given-names>CK</given-names>
						</name>
						<name>
							<surname>Khalil</surname>
							<given-names>A</given-names>
						</name>
						<name>
							<surname>Yusof</surname>
							<given-names>AKM</given-names>
						</name>
						<name>
							<surname>Lai</surname>
							<given-names>KW</given-names>
						</name>
					</person-group>
					<article-title>Real-Time Detection of Aortic Valve in Echocardiography using Convolutional Neural Networks</article-title>
					<source>Curr Med Imaging</source>
					<year>2020</year>
					<volume>16</volume>
					<issue>5</issue>
					<fpage>584</fpage>
					<lpage>591</lpage>
					<issue-id pub-id-type="doi">10.2174/1573405615666190114151255</issue-id>
				</element-citation>
			</ref>
			<ref id="B11">
				<label>11</label>
				<mixed-citation>11. 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>
				<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>
					<issue-id pub-id-type="doi">10.1016/j.ultrasmedbio.2018.07.024</issue-id>
				</element-citation>
			</ref>
			<ref id="B12">
				<label>12</label>
				<mixed-citation>12. Hahn RT, Saric M, Faletra FF, Garg R, Gillam LD, Horton K, et al. Recommended Standards for the Performance of Transesophageal Echocardiographic Screening for Structural Heart Intervention: From the American Society of Echocardiography. J Am Soc Echocardiogr. 2022;35(1):1-76. doi: 10.1016/j.echo.2021.07.006.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Hahn</surname>
							<given-names>RT</given-names>
						</name>
						<name>
							<surname>Saric</surname>
							<given-names>M</given-names>
						</name>
						<name>
							<surname>Faletra</surname>
							<given-names>FF</given-names>
						</name>
						<name>
							<surname>Garg</surname>
							<given-names>R</given-names>
						</name>
						<name>
							<surname>Gillam</surname>
							<given-names>LD</given-names>
						</name>
						<name>
							<surname>Horton</surname>
							<given-names>K</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Recommended Standards for the Performance of Transesophageal Echocardiographic Screening for Structural Heart Intervention: From the American Society of Echocardiography</article-title>
					<source>J Am Soc Echocardiogr</source>
					<year>2022</year>
					<volume>35</volume>
					<issue>1</issue>
					<fpage>1</fpage>
					<lpage>76</lpage>
					<issue-id pub-id-type="doi">10.1016/j.echo.2021.07.006</issue-id>
				</element-citation>
			</ref>
			<ref id="B13">
				<label>13</label>
				<mixed-citation>13. Saini K, Dewal ML, Rohit M. A Fast Region-Based Active Contour Model for Boundary Detection of Echocardiographic Images. J Digit Imaging. 2012;25(2):271-8. doi: 10.1007/s10278-011-9408-8.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Saini</surname>
							<given-names>K</given-names>
						</name>
						<name>
							<surname>Dewal</surname>
							<given-names>ML</given-names>
						</name>
						<name>
							<surname>Rohit</surname>
							<given-names>M</given-names>
						</name>
					</person-group>
					<article-title>A Fast Region-Based Active Contour Model for Boundary Detection of Echocardiographic Images</article-title>
					<source>J Digit Imaging</source>
					<year>2012</year>
					<volume>25</volume>
					<issue>2</issue>
					<fpage>271</fpage>
					<lpage>278</lpage>
					<issue-id pub-id-type="doi">10.1007/s10278-011-9408-8</issue-id>
				</element-citation>
			</ref>
			<ref id="B14">
				<label>14</label>
				<mixed-citation>14. Melo SA Jr, Macchiavello B, Andrade MM, Carvalho JL, Carvalho HS, Vasconcelos DF, et al. Semi-Automatic Algorithm for Construction of the Left Ventricular Area Variation Curve Over a Complete Cardiac Cycle. Biomed Eng Online. 2010;9:5. doi: 10.1186/1475-925X-9-5.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Melo</surname>
							<given-names>SA</given-names>
							<suffix>Jr</suffix>
						</name>
						<name>
							<surname>Macchiavello</surname>
							<given-names>B</given-names>
						</name>
						<name>
							<surname>Andrade</surname>
							<given-names>MM</given-names>
						</name>
						<name>
							<surname>Carvalho</surname>
							<given-names>JL</given-names>
						</name>
						<name>
							<surname>Carvalho</surname>
							<given-names>HS</given-names>
						</name>
						<name>
							<surname>Vasconcelos</surname>
							<given-names>DF</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Semi-Automatic Algorithm for Construction of the Left Ventricular Area Variation Curve Over a Complete Cardiac Cycle</article-title>
					<source>Biomed Eng Online</source>
					<year>2010</year>
					<volume>9</volume>
					<size units="pages">5</size>
					<issue-id pub-id-type="doi">10.1186/1475-925X-9-5</issue-id>
				</element-citation>
			</ref>
			<ref id="B15">
				<label>15</label>
				<mixed-citation>15. Mahadi LF, Ibrahim N, Zaluwi MT, Johan MHSM. Feature Detection of Mitral Valve Based on Image Processing Technique: A Review. J Phy: Conf Ser. 2019;1372(1):12071. doi: 10.1088/1742-6596/1372/1/012071.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Mahadi</surname>
							<given-names>LF</given-names>
						</name>
						<name>
							<surname>Ibrahim</surname>
							<given-names>N</given-names>
						</name>
						<name>
							<surname>Zaluwi</surname>
							<given-names>MT</given-names>
						</name>
						<name>
							<surname>Johan</surname>
							<given-names>MHSM</given-names>
						</name>
					</person-group>
					<article-title>Feature Detection of Mitral Valve Based on Image Processing Technique: A Review</article-title>
					<source>J Phy: Conf Ser</source>
					<year>2019</year>
					<volume>1372</volume>
					<issue>1</issue>
					<size units="pages">12071</size>
					<issue-id pub-id-type="doi">10.1088/1742-6596/1372/1/012071</issue-id>
				</element-citation>
			</ref>
			<ref id="B16">
				<label>16</label>
				<mixed-citation>16. Aquila I, Fernández-Golfín C, Rincon LM, González A, García Martín A, Hinojar R, et al. Fully Automated Software for Mitral Annulus Evaluation in Chronic Mitral Regurgitation by 3-Dimensional Transesophageal Echocardiography. Medicine. 2016;95(49):e5387. doi: 10.1097/MD.0000000000005387.</mixed-citation>
				<element-citation publication-type="journal">
					<person-group person-group-type="author">
						<name>
							<surname>Aquila</surname>
							<given-names>I</given-names>
						</name>
						<name>
							<surname>Fernández-Golfín</surname>
							<given-names>C</given-names>
						</name>
						<name>
							<surname>Rincon</surname>
							<given-names>LM</given-names>
						</name>
						<name>
							<surname>González</surname>
							<given-names>A</given-names>
						</name>
						<name>
							<surname>García Martín</surname>
							<given-names>A</given-names>
						</name>
						<name>
							<surname>Hinojar</surname>
							<given-names>R</given-names>
						</name>
						<etal>et al</etal>
					</person-group>
					<article-title>Fully Automated Software for Mitral Annulus Evaluation in Chronic Mitral Regurgitation by 3-Dimensional Transesophageal Echocardiography</article-title>
					<source>Medicine</source>
					<year>2016</year>
					<volume>95</volume>
					<issue>49</issue>
					<fpage>e5387</fpage>
					<issue-id pub-id-type="doi">10.1097/MD.0000000000005387</issue-id>
				</element-citation>
			</ref>
		</ref-list>
		<fn-group>
			<fn fn-type="other">
				<label/>
				<p>Study Association</p>
				<p> This article is part of the thesis of Doctoral submitted by Genilton de França Barros Filho, from Universidade Federal da Paraíba, Programa de Pós-Graduação em Engenharia Mecânica.</p>
			</fn>
			<fn fn-type="other">
				<p> Ethics Approval and Consent to Participate</p>
				<p> This study was approved by the Ethics Committee on Animal Experiments of the Colegiado do Comitê de Ética em Pesquisa com Seres Humanos - CEP/CCM/UFPB under the protocol number 3.858.742.</p>
			</fn>
		</fn-group>
		<fn-group>
			<fn fn-type="supported-by">
				<p>Sources of Funding</p>
				<p>This study was partially funded by Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES).</p>
			</fn>
		</fn-group>
	</back>
	<sub-article article-type="translation" id="TRpt" xml:lang="pt">
		<front-stub>
			<article-id pub-id-type="doi">10.36660/abcimg.2023371</article-id>
			<article-categories>
				<subj-group subj-group-type="heading">
					<subject>Artigo Original</subject>
				</subj-group>
			</article-categories>
			<title-group>
				<article-title>Medição Automática de Valva Mitral a Partir de Ecocardiograma Utilizando Processamento Digital de Imagens</article-title>
			</title-group>
			<contrib-group>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0001-8744-6600</contrib-id>
					<name>
						<surname>Barros</surname>
						<given-names>Genilton de França</given-names>
						<suffix>Filho</suffix>
					</name>
					<role>Concepção e desenho da pesquisa, análise e interpretação dos dados, análise estatística</role>
					<xref ref-type="aff" rid="aff1002"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0009-0005-0569-7155</contrib-id>
					<name>
						<surname>Solha</surname>
						<given-names>Israel</given-names>
					</name>
					<role>Concepção e desenho da pesquisa, análise e interpretação dos dados, análise estatística</role>
					<xref ref-type="aff" rid="aff1002"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0009-0005-5619-4080</contrib-id>
					<name>
						<surname>Medeiros</surname>
						<given-names>Ewerton Freitas de</given-names>
					</name>
					<role>análise e interpretação dos dados, redação do manuscrito</role>
					<xref ref-type="aff" rid="aff1002"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0001-7046-8707</contrib-id>
					<name>
						<surname>Felix</surname>
						<given-names>Alex dos Santos</given-names>
					</name>
					<role>obtenção de dados, análise e interpretação dos dados</role>
					<xref ref-type="aff" rid="aff2002"><sup>2</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-1777-477X</contrib-id>
					<name>
						<surname>Almeida</surname>
						<given-names>André Luiz Cerqueira de</given-names>
					</name>
					<role>revisão crítica do manuscrito quanto ao conteúdo intelectual importante</role>
					<xref ref-type="aff" rid="aff3002"><sup>3</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-9083-7650</contrib-id>
					<name>
						<surname>Lima</surname>
						<given-names>José Carlos de</given-names>
						<suffix>Júnior</suffix>
					</name>
					<role>revisão crítica do manuscrito quanto ao conteúdo intelectual importante</role>
					<xref ref-type="aff" rid="aff1002"><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, obtenção de dados, análise e interpretação dos dados, revisão crítica do manuscrito quanto ao conteúdo intelectual importante</role>
					<xref ref-type="aff" rid="aff1002"><sup>1</sup></xref>
				</contrib>
				<contrib contrib-type="author">
					<contrib-id contrib-id-type="orcid">0000-0002-3663-5097</contrib-id>
					<name>
						<surname>Rodrigues</surname>
						<given-names>Marcelo Cavalcanti</given-names>
					</name>
					<role>Concepção e desenho da pesquisa, análise e interpretação dos dados, revisão crítica do manuscrito quanto ao conteúdo intelectual importante:</role>
					<xref ref-type="aff" rid="aff1002"><sup>1</sup></xref>
				</contrib>
			</contrib-group>
			<aff id="aff1002">
				<label>1</label>
				<country country="BR">Brasil</country>
				<institution content-type="original">Universidade Federal da Paraíba, João Pessoa, PB – Brasil</institution>
			</aff>
			<aff id="aff2002">
				<label>2</label>
				<country country="BR">Brasil</country>
				<institution content-type="original">Instituto Nacional de Cardiologia, Rio de Janeiro, RJ – Brasil</institution>
			</aff>
			<aff id="aff3002">
				<label>3</label>
				<country country="BR">Brasil</country>
				<institution content-type="original">Departamento de Imagem Cardiovascular, São Paulo, SP – Brasil</institution>
			</aff>
			<author-notes>
				<corresp id="c01002">
					<label>Correspondência</label>: Genilton de França Barros Filho Rua Luiza Dantas de Medeiros, 261, apt. 103 G. CEP: 58073-040. José Américo, João Pessoa, PB - Brasil E-mail: gfbfilho@gmail.com </corresp>
				<fn fn-type="conflict">
					<p>Potencial Conflito de Interesse</p>
					<p>Declaro não haver conflito de interesses pertinentes.</p>
				</fn>
				<fn fn-type="edited-by">
					<p>Editor responsável pela revisão: Daniela do Carmo Rassi Frota</p>
				</fn>
			</author-notes>
			<abstract>
				<title>Resumo</title>
				<sec>
					<title>Fundamento</title>
					<p> A avaliação da área valvar mitral por meio da reconstrução multiplano na ecocardiografia tridimensional é restrita a softwares específicos e à experiência dos ecocardiografistas. Eles precisam selecionar manualmente o frame do vídeo que contenha a área de abertura máxima da valva mitral, dimensão fundamental para a identificação de estenose mitral.</p>
				</sec>
				<sec>
					<title>Objetivo</title>
					<p> Automatizar o processo de determinação da área de abertura máxima da valva mitral, por meio da aplicação de Processamento Digital de Imagens (PDI) em exames de ecocardiograma, desenvolvendo um algoritmo aberto com leitura de vídeo no formato avi.</p>
				</sec>
				<sec>
					<title>Método</title>
					<p> Este estudo piloto observacional transversal foi realizado com vinte e cinco exames diferentes de ecocardiograma, sendo quinze com abertura normal e dez com estenose mitral reumática. Todos os exames foram realizados e disponibilizados por dois especialistas, com autorização do Comitê de Ética em Pesquisa, que utilizaram dois modelos de aparelhos ecocardiográficos: Vivid E95 (GE Healthcare) e Epiq 7 (Philips), com sondas multiplanares transesofágicas. Todos os vídeos em formato avi foram submetidos ao PDI através da técnica de segmentação de imagens.</p>
				</sec>
				<sec>
					<title>Resultados</title>
					<p> As medidas obtidas manualmente por ecocardiografistas experientes e os valores calculados pelo sistema desenvolvido foram comparados utilizando o diagrama de Bland-Altman. Observou-se maior concordância entre valores no intervalo de 0,4 a 2,7 cm<sup>2</sup>.</p>
				</sec>
				<sec>
					<title>Conclusão</title>
					<p> Foi possível determinar automaticamente a área de máxima abertura das valvas mitrais, tanto para os casos advindos da GE quanto da Philips, utilizando apenas um vídeo como dado de entrada. O algoritmo demonstrou economizar tempo nas medições quando comparado com a mensuração habitual.</p>
				</sec>
			</abstract>
			<kwd-group xml:lang="pt">
				<kwd>Valvar Mitral</kwd>
				<kwd>Ecocardiografia</kwd>
				<kwd>Processamento de Imagem Assistida por Computador</kwd>
			</kwd-group>
		</front-stub>
		<body>
			<sec sec-type="intro">
				<title>Introdução</title>
				<p>As doenças valvares são importantes determinantes de morbidade e mortalidade cardiovascular, sendo as doenças degenerativas das valvas mitral e aórtica as mais prevalentes, muito embora a doença reumática ainda constitua importante problema de saúde pública no Brasil. A ecocardiografia tem importante papel no diagnóstico e avaliação da gravidade das doenças valvares, podendo determinar detalhes anatômicos e fisiopatológicos que auxiliam no planejamento da melhor intervenção para cada paciente, além de possuir as vantagens de ser amplamente disponível, de baixo custo e sem necessidade de uso de radiação ou contraste nefrotóxico.<sup><xref ref-type="bibr" rid="B1">1</xref></sup></p>
				<p>Dentre os exames de imagem mais comuns, o ecocardiograma é a modalidade de exame mais utilizada na avaliação de doenças valvares mitrais. Isso é possível pois trata-se de uma técnica mais prontamente disponível e amplamente utilizada para avaliar função e estrutura. O ecocardiograma combina imagem em tempo real sem a presença de radiação ionizante, servindo hoje como espinha dorsal para a área de exames de imagem cardiovasculares.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
				<p>O uso de ecocardiografia 3D fornece inúmeras vantagens, como a possibilidade de navegação em tempo real, pós-processamento de imagens e reconstrução multiplanar. É especialmente importante para avaliação pré-operatória de pacientes candidatos a cirurgias de reparo ou troca valvar. Possibilita a monitorização intraoperatória dos procedimentos, como na substituição da valva aórtica transcateter (TAVR, sigla do inglês <italic>transcatheter aortic valve replacement</italic>)<sup><xref ref-type="bibr" rid="B3">3</xref></sup> e no implante de clipes para reparo percutâneo mitral (Mitraclip). Permite, também, a realização de procedimentos para o tratamento da estenose mitral reumática, como a valvoplastia mitral percutânea por cateter-balão (VMCB), ou mesmo o implante de prótese valvar biológica mitral, por via percutânea (TMVR, sigla do inglês <italic>transcatheter mitral valve replacement</italic>), em pacientes com doença degenerativa mitral e calcificação do anel valvar, ou o implante de prótese percutânea no interior de próteses biológicas disfuncionantes (<italic>valve-in-valve mitral</italic>). Os procedimentos descritos têm apresentado grande evolução, com resultados cada vez mais eficazes devido a ajuda da multimodalidade de imagem cardíaca na avaliação pré-procedimento e durante a intervenção.<sup><xref ref-type="bibr" rid="B4">4</xref>,<xref ref-type="bibr" rid="B5">5</xref></sup></p>
				<p>Na sala de intervenção, as decisões tem que ser ágeis, com o fornecimento de informações precisas para o intervencionista, sendo, portanto, fundamental a qualidade da comunicação entre as equipes. Através da demonstração visual das estruturas, possibilitada pela reconstrução e renderização pelo 3D, e com medidas mais acuradas e menos dependente de angulações, tais como as obtidas pela reconstrução multiplanar, é possível obter resultados melhores, com maior eficácia e menor taxa de complicações.<sup><xref ref-type="bibr" rid="B5">5</xref></sup></p>
				<p>Há significativa variação na interpretação humana de dados ecocardiográficos, além de erros na realização das medidas, por uma considerável variabilidade inter-observador. O uso de sistemas automatizados para a interpretação de imagens cardiovasculares pode ser útil em melhorar a performance diagnóstica e prognóstica dos métodos, e a aplicação do <italic>machine learning</italic> a imagens médicas, com o auxílio da interpretação de especialistas, aumenta a confiabilidade do processo pela disposição de vários dados estruturados por relatórios.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
				<p>A avaliação acurada da área valvar mitral por meio da reconstrução multiplanar pela ecocardiografia transesofágica tridimensional é totalmente dependente da experiência dos examinadores e da expertise no uso de softwares específicos, que podem não estar disponíveis em algumas plataformas ou mesmo serem de uso pouco prático, consumindo tempo de exame.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
				<p>O processamento digital de imagens (PDI) está adquirindo notoriedade em duas principais áreas de aplicação, que são: melhora das informações visuais de imagens para a interpretação humana e processamento de dados de imagens para armazenamento, transmissão e representação, considerando a percepção automática por máquinas.<sup><xref ref-type="bibr" rid="B7">7</xref></sup></p>
				<p>Ele consiste na manipulação da imagem por um computador, com diversas aplicações, como: realce de contraste, redução de ruído, perseguição de objetos e/ou pessoas, detecção de bordas, identificação de padrões, classificação e contagem de objetos e/ou pessoas, entre muitas outras.<sup><xref ref-type="bibr" rid="B7">7</xref></sup> Dentre várias técnicas existentes do PDI, foi aplicada a de segmentação de imagem. Essa técnica produz uma imagem binária, com pixels de valor um, indicando que fazem parte do objeto em estudo e com pixels de valor zero, caso contrário. Com isso, é possível parti-la em regiões, identificando fronteiras e descontinuidades, por exemplo.<sup><xref ref-type="bibr" rid="B8">8</xref></sup></p>
				<p>Vários estudos estão contribuindo para a evolução das análises de ecocardiograma por meio de ferramentas computadorizadas. Como exemplo, Sakamiya et al. criaram uma plataforma para o monitoramento online do comportamento contrátil do coração, que são as principais características funcionais do tecido cardíaco, empregando simultaneamente um sistema de processamento de imagem e de detecção piezoelétrica. Avaliaram também a influência de medicamentos como o isoproterenol e doxorrubicina no comportamento contrátil do coração. Os resultados da reatividade medicamentosa fornecida por esses dois sistemas de medição foram consistentes com os relatórios anteriores que eles possuíam, demonstrando a confiabilidade da plataforma desenvolvida e seu potencial para uso em aplicações de triagem relacionadas a medicamentos.<sup><xref ref-type="bibr" rid="B9">9</xref></sup></p>
				<p>Nizar e cols. usaram rede neural convolucional para a detecção, em tempo real, da valva aórtica do coração em exames de ecocardiograma, com a finalidade de auxiliar o exame médico, uma vez que um sistema de detecção automatizado em um ecocardiograma pode melhorar a precisão do diagnóstico médico e fornecer análises médicas adicionais a partir da detecção resultante. Concluíram, portanto, que essa ferramenta pode ser de grande ajuda para fins médicos.<sup><xref ref-type="bibr" rid="B10">10</xref></sup></p>
				<p>Ostvik et al. verificaram a possibilidade da aplicação de redes neurais artificiais na classificação de imagens transtorácicas obtidas por ecocardiografia. A conclusão foi satisfatória para a implementação em ecocardiografia 2D, e para análise da Ecocardiografia em 3D, os estudos ainda precisam ganhar mais empenho visto que é realizado a partir de quadros obtidos durante o procedimento.<sup><xref ref-type="bibr" rid="B11">11</xref></sup></p>
				<p>Portanto, o objetivo deste projeto é automatizar a determinação da área de máxima abertura da valva mitral, por meio da aplicação de PDI em exames de ecocardiograma, desenvolvendo um algoritmo aberto com leitura de vídeo no formato avi.</p>
			</sec>
			<sec sec-type="methods">
				<title>Metodologia</title>
				<p>As análises foram retrospectivas, realizadas em diferentes estudos de ecocardiograma por ecocardiografistas experientes. Os exames possuíam pacientes que apresentavam valvas mitrais “normais”, ou seja, com sua abertura em condições normais, e pacientes com valvas mitrais acometidas pela estenose reumática.</p>
				<p>Para a aquisição dos exames, os ecocardiografistas utilizaram 2 modelos de aparelhos ecocardiográficos, com sondas multiplanares transesofágicas: o Vivid E95 (GE Healthcare) e o Epiq 7 (Philips). Cada um apresenta suas particularidades. A diferença mais considerável, para o presente trabalho, é a maneira como a escala da imagem é representada. O ecocardiógrafo da marca Philips desenha pontos verdes, e a distância entre seus centroides é indicada em um valor numérico pertencente à escala métrica. O ecocardiógrafo da marca General Eletric (GE) representa a escala na parte inferior direita da imagem.</p>
				<p>Após a aquisição dos exames salvos em vídeos, eles foram submetidos ao PDI pela técnica de segmentação de imagens, tendo em vista que um vídeo é composto por um conjunto de imagens estáticas sequenciais. Como resultado, o PDI identifica a área de máxima abertura valvar, destaca seu contorno e calcula seu valor.</p>
				<p>Um aplicativo foi desenvolvido para facilitar a utilização do PDI. Leigos em programação podem utilizá-lo, pois apresenta uma interface gráfica intuitiva. Ele foi criado com linguagem python.</p>
				<p>Por fim, os resultados obtidos pelo aplicativo foram comparados com os resultados obtidos pelos ecocardiografistas, que selecionaram manualmente a área de máxima abertura valvar por meio de um software específico. Para verificar a correlação entre as duas medições, empregou-se o método Bland-Altman.</p>
			</sec>
			<sec sec-type="results">
				<title>Resultados</title>
				<p>Todos os exames obtidos foram salvos no formato de vídeos no formato avi. Ao total foram adquiridos 25 vídeos, sendo 22 do ecocardiógrafo da marca GE e 3 do ecocardiógrafo da marca Philips. A quantidade de exames utilizados no presente estudo foi limitada pelo tempo empregado no estudo e influenciada pela pandemia, que dificultou a aquisição de mais exames.</p>
				<p>O modelo do estudo utilizado foi o observacional transversal retrospectivo, adquirido de acordo com as recomendações da Sociedade Americana de Ecocardiografia.<sup><xref ref-type="bibr" rid="B12">12</xref></sup> As planimetrias foram realizadas pela reconstrução multiplanar com visão ventricular e atrial, utilizando o EchoPac v.204 para os aparelhos da GE e diretamente no aparelho Epiq 7 durante o exame para os da Philips.</p>
				<p>A <xref ref-type="fig" rid="f01002">Figura 1</xref> ilustra as interfaces do aplicativo desenvolvido e o seu funcionamento.</p>
				<p>
					<fig id="f01002">
						<label>Figura 1</label>
						<caption>
							<title>– Telas do aplicativo desenvolvido. a) Tela inicial; b) Tela para processamento dos vídeos advindos de ecocardiógrafos da marca Philips; c) Tela para seleção das opções de vídeos advindos de ecocardiógrafos da marca GE; d) Tela para processamento dos vídeos com apenas a vista 3D advindos de ecocardiógrafos da marca GE (Caso 1); e) Tela para processamento dos vídeos com vistas 3D, lateral, superior e frontal advindos de ecocardiógrafos da marca GE (Caso 2).</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf01-pt.tif"/>
					</fig>
				</p>
				<p>Ao abrir o aplicativo, a tela inicial é exibida (<xref ref-type="fig" rid="f01002">Figura 1a</xref>). Ela exibe duas opções: “Philips” e “General Eletric”. O usuário deve selecionar o botão de acordo com a origem do vídeo a ser utilizado para análise. Se o vídeo foi salvo a partir de exames de ecocardiogramas realizados com ecocardiógrafos da marca Philips, deve ser selecionado o botão “Philips”. Caso os exames tenham sido realizados com ecocardiógrafos da marca General Eletric, deve ser selecionado o botão “General Eletric”.</p>
				<p>Ao selecionar a opção “Philips”, a tela da <xref ref-type="fig" rid="f01002">Figura 1b</xref> será exibida. O usuário deverá clicar no botão “Selecionar Vídeo” para carregar o vídeo a ser analisado. Depois deve informar a escala numérica presente no vídeo. Por exemplo, se o exame foi realizado e salvo com escala 5 mm no grid, deve inserir no campo “Escala [cm]” o valor de 0,5. Por fim, o botão “Play” deve ser selecionado para o aplicativo realizar todo o PDI para identificar e calcular a área de máxima abertura valvar. Além disso, a tela exibe algumas instruções para facilitar a utilização do aplicativo e para otimizar os resultados a serem obtidos.</p>
				<p>Caso seja selecionada a opção de “General Eletric” na tela inicial (<xref ref-type="fig" rid="f01002">Figura 1a</xref>), a tela da <xref ref-type="fig" rid="f01002">Figura 1c</xref> será exibida. Ela permite escolher a forma como o vídeo foi salvo. Se foi salvo apenas com a vista 3D, deve ser selecionado o botão “Caso 1”. Se foi salvo com a vista 3D e as vistas frontal, lateral e superior, deve ser selecionado o botão “Caso 2”. Essa separação é necessária pois o modo e as características dos vídeos salvos influenciam o processamento digital.</p>
				<p>O botão “Caso 1” e o botão “Caso 2” exibirão as telas das <xref ref-type="fig" rid="f01002">Figuras 1d e 1e</xref>, respectivamente. Elas funcionam da mesma maneira que a tela da <xref ref-type="fig" rid="f01002">Figura 1b</xref>, descrita anteriormente.</p>
				<p>Após a seleção do botão “Play” da <xref ref-type="fig" rid="f01002">Figura 1b</xref>, <xref ref-type="fig" rid="f01002">Figura 1d</xref> ou da <xref ref-type="fig" rid="f01002">1e</xref>, o PDI transforma o vídeo em um conjunto de imagens (conforme exemplo ilustrado na <xref ref-type="fig" rid="f02002">Figura 2</xref>), também chamadas de <italic>frames</italic>, para analisa-las separadamente e para identificação da imagem que contém a área de máxima abertura valvar. Como todas as imagens são isoladas, o <italic>frame rate</italic> (<italic>frames</italic> por segundo) de cada vídeo não interferiu nos resultados.</p>
				<p>
					<fig id="f02002">
						<label>Figura 2</label>
						<caption>
							<title>– Exemplo da transformação de um vídeo em diversas imagens (frames).</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf02-pt.tif"/>
					</fig>
				</p>
				<p>Com isso, após o processamento digital, o aplicativo exibe o resultado conforme ilustra a <xref ref-type="fig" rid="f03002">Figura 3</xref>.</p>
				<p>
					<fig id="f03002">
						<label>Figura 3</label>
						<caption>
							<title>– Resultados exibidos pelo aplicativo desenvolvido. a) Tela inicialmente exibida; b) Tela final, com a imagem de máxima abertura valvar selecionada.</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf03-pt.tif"/>
					</fig>
				</p>
				<p>A <xref ref-type="fig" rid="f03002">Figura 3a</xref> ilustra a primeira tela exibida após o aplicativo executar o PDI. A área de máxima abertura valvar é identificada e desenhada (contorno de cor branca). Também é exibido o valor da área máxima. No caso da <xref ref-type="fig" rid="f03002">Figura 3a</xref>, a área é de 4,45 cm<sup>2</sup>.</p>
				<p>Com o intuito de tornar os resultados mais precisos, o aplicativo permite que o usuário verifique imagens anteriores e posteriores, com os botões “Imagem anterior” e “Imagem posterior”, respectivamente. Eles permitem a verificação de contornos mais condizentes com a realidade.</p>
				<p>No resultado da <xref ref-type="fig" rid="f03002">Figura 3</xref>, apesar do contorno da <xref ref-type="fig" rid="f03002">Figura 3a</xref> exibir um resultado satisfatório, o contorno da <xref ref-type="fig" rid="f03002">Figura 3b</xref> é mais preciso e mais condizente com o formato da abertura valvar máxima. Inclusive, o seu valor da área de máxima abertura valvar passou a ser 4,5 cm<sup>2</sup>.</p>
				<p>O botão “Tela Inicial” serve para retornar à tela inicial do aplicativo (<xref ref-type="fig" rid="f01002">Figura 1a</xref>) e o botão “Selecionar imagem” salva os resultados obtidos.</p>
				<p>As <xref ref-type="fig" rid="f04002">Figuras 4</xref> e <xref ref-type="fig" rid="f05002">5</xref> representam comparações entre os resultados obtidos pela medição da máxima área de abertura valvar realizada pelo aplicativo desenvolvido e por um médico ecocardiografista. A <xref ref-type="fig" rid="f04002">Figura 4</xref> caracteriza um caso “normal” e a <xref ref-type="fig" rid="f05002">Figura 5</xref> um caso com estenose.</p>
				<p>
					<fig id="f04002">
						<label>Figura 4</label>
						<caption>
							<title>– Comparação entre a medição do aplicativo desenvolvido e a medição, com seleção manual, de um ecocardiografista, por meio de um software específico. a) Vídeo analisado de um caso “normal”; b) Resultado do aplicativo desenvolvido: Área de 4,59 cm2; c) Resultado da medição do ecocardiografista: Área de 4,7 cm2.</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf04-pt.tif"/>
					</fig>
				</p>
				<p>
					<fig id="f05002">
						<label>Figura 5</label>
						<caption>
							<title>– Comparação entre a medição do aplicativo desenvolvido e a medição, com seleção manual, de um ecocardiografista, por meio de um software específico. a) Vídeo analisado de um caso com estenose; b) Resultado do aplicativo desenvolvido: Área de 0,51 cm2; c) Resultado da medição do ecocardiografista: Área de 0,6 cm2.</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf05-pt.tif"/>
					</fig>
				</p>
				<p>Pela análise das <xref ref-type="fig" rid="f04002">Figuras 4</xref> e <xref ref-type="fig" rid="f05002">5</xref>, percebe-se que os resultados foram bem próximos. Para o caso “normal” o aplicativo retornou o valor de 4,59 cm<sup>2</sup> (<xref ref-type="fig" rid="f04002">Figura 4b</xref>) e a medição médica retornou o valor de 4,7 cm<sup>2</sup> (<xref ref-type="fig" rid="f04002">Figura 4c</xref>). Para o caso com estenose, o aplicativo retornou o valor de 0,51 cm<sup>2</sup> (<xref ref-type="fig" rid="f05002">Figura 5b</xref>) e a medição médica retornou o valor de 0,6 cm<sup>2</sup> (<xref ref-type="fig" rid="f05002">Figura 5c</xref>).</p>
				<p>Além disso, percebeu-se que a adoção de algumas práticas otimiza os resultados do aplicativo, como a de salvar vídeos destacando a região da valva mitral, aplicando zoom, e a de salvar vídeos com poucos elementos, de preferência com apenas a região de interesse e a escala utilizada. Porém, seriam necessários mais exames para validar esta constatação.</p>
				<p>Com a identificação da máxima abertura valvar e do cálculo do seu valor, o aplicativo desenvolvido também consegue detectar se o paciente do referido exame possui ou não estenose.</p>
				<p>Além do mais, o tempo de processamento do aplicativo é relativamente baixo, não passando de 3 minutos, para a maioria das análises.</p>
				<p>Com a finalidade de verificar as concordâncias dos resultados obtidos pelo aplicativo e pelas medições dos ecocardiografistas, aplicou-se o método de Bland-Altman, como pode ser verificado na <xref ref-type="fig" rid="f06002">Figura 6</xref>.</p>
				<p>
					<fig id="f06002">
						<label>Figura 6</label>
						<caption>
							<title>– Método Bland-Altman: a) aplicado apenas para os casos sem estenose; b) aplicado apenas nos casos com estenose; c) aplicado em todos os 25 exames empregados no estudo.</title>
						</caption>
						<graphic xlink:href="2675-312X-dic-36-01-e371-gf06-pt.tif"/>
					</fig>
				</p>
				<p>Pelo método de Bland-Altman, avaliando os casos com e sem estenose separadamente, constatou-se concordância entre o PDI e a medição médica na obtenção da área de máxima abertura valvar (<xref ref-type="fig" rid="f06002">Figura 6a</xref> e <xref ref-type="fig" rid="f06002">Figura 6b</xref>). Juntando todos os casos, apenas dois ficaram fora do intervalo aceitável (<xref ref-type="fig" rid="f06002">Figura 6c</xref>). Esses resultados contribuem para a validação tanto da técnica de PDI empregada quanto do aplicativo desenvolvido.</p>
				<p>Para os casos sem estenose (<xref ref-type="fig" rid="f06002">Figura 6a</xref>), a maior diferença entre as medições foi de 0,7 cm<sup>2</sup>, enquanto a maioria permaneceu dentro do intervalo de −0,5 cm<sup>2</sup> a 0,5 cm<sup>2</sup>. Para os casos com estenose (<xref ref-type="fig" rid="f06002">Figura 6b</xref>), a maior diferença entre as medições foi de 0,2 cm<sup>2</sup>, e todas permaneceram dentro do intervalo de −0,2 cm<sup>2</sup> a 0,2 cm<sup>2</sup>. Analisando todos os casos (<xref ref-type="fig" rid="f06002">Figura 6c</xref>), percebe-se que os casos com estenose (pontos mais à esquerda da <xref ref-type="fig" rid="f06002">Figura 6c</xref>) apresentaram menores diferenças de medições comparadas com os casos sem estenoses (pontos mais à direita da <xref ref-type="fig" rid="f06002">Figura 6c</xref>).</p>
			</sec>
			<sec sec-type="discussion">
				<title>Discussão</title>
				<p>O presente trabalho se diferencia por empregar o PDI, a partir da técnica de segmentação de imagem, para detecção da área de máxima abertura de valvas mitrais, de modo automático, a partir de vídeos de ecocardiogramas no formato avi. Logo, contribui para a detecção de estenose mitral. Um grande diferencial é o aplicativo desenvolvido, com linguagem python, que permite o fácil acesso e o fácil manuseio das ferramentas do PDI. Basta instalá-lo no computador. As telas do aplicativo foram desenvolvidas para melhorar a experiência do seu usuário e não exige conhecimento prévio em programação.</p>
				<p>O aplicativo desenvolvido é capaz de analisar casos mais complexos, como pacientes com arritmias, pois a seleção automática permite verificar cada imagem do vídeo, destacando a imagem com a máxima abertura valvar. Além disso, quanto mais medições forem realizadas com o aplicativo desenvolvido e comparadas com medições médicas, principalmente com casos diferentes e atípicos, mais ele será testado, o que permite avaliá-lo melhor para sua consolidação.</p>
				<p>Essa medição automática possui algumas vantagens quando comparada com a seleção manual, realizada pelos ecocardiografistas, pois o resultado pode ser bastante influenciado pelo momento em que ele pausar o vídeo para a realização da análise. Essa seleção manual exige muito tempo do especialista, tendo em vista que ele deve ser bastante cuidadoso para realizar uma seleção com o mínimo de erro possível e com o máximo de atenção. Considerando um dia lotado de atendimento, a precisão das regiões selecionadas será maior para os primeiros pacientes do dia, diminuindo conforme o cansaço físico e mental do ecocardiografista, além de outros fatores externos que podem influenciar na medição.</p>
				<p>Após o levantamento realizado na literatura, não foi encontrado algo semelhante. Porém, um dos grandes esforços dos pesquisadores é garantir a automatização das medidas em exames dependentes do operador para investigação de diversas patologias, com a finalidade de reduzir ou eliminar o erro da seleção manual. Assim, Saine et al. apresentaram uma técnica de detecção automática dos contornos dos átrios e ventrículos esquerdos a partir de ecocardiogramas 2D com o objetivo de determinar a área de dilatações dessas câmaras em pacientes com insuficiência valvar mitral.<sup><xref ref-type="bibr" rid="B13">13</xref></sup></p>
				<p>Melo et al. desenvolveram um método semiautomático que determina a variação da área ventricular em ecocardiogramas 2D dinâmicos usando técnicas de PDI, como média de tempo, redução de ruído baseada em wavelets, filtragem de aprimoramento de borda, operações morfológicas, modificação de homotopia e segmentação de bacias hidrográficas. Tal método tornou-se útil para analisar a função ventricular global por medidas de área.<sup><xref ref-type="bibr" rid="B14">14</xref></sup></p>
				<p>Mahadi et al. verificaram o uso de PDI em ecocardiogramas 2D para transformar cortes de exames em um conjunto de pixels e assim determinar a distância de pontos que poderiam medir o diâmetro de uma valva mitral em uma determinada incidência.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> Aquila et al. apresentaram o uso de uma ferramenta chamada Siemens eSie Valves na qual foi possível determinar automaticamente uma série de parâmetros do anel valvar mitral como área, diâmetros anteroposteriores e posterolaterais, bem como distância intertrigonal. Logo, este estudo compara alterações anatômicas existentes entre os processos de regurgitação mitral funcional e orgânica a partir da aquisição automática das medidas valvares.<sup><xref ref-type="bibr" rid="B16">16</xref></sup></p>
				<p>Desse modo, o presente trabalho surge como mais uma ferramenta para combater possíveis erros humanos nas medições de áreas valvares e para contribuir com sua automatização.</p>
			</sec>
			<sec sec-type="conclusions">
				<title>Conclusões</title>
				<p>Foi possível determinar automaticamente a área de máxima abertura das valvas mitrais, tanto para os casos advindos de ecocardiógrafos da marca GE quanto de ecocardiógrafos da marca Philips, utilizando apenas um vídeo como dado de entrada.</p>
				<p>Como o aplicativo escolhe o frame adequado e calcula a área quase que instantaneamente, pode-se concluir, intuitivamente, que ele é mais rápido do que a mensuração manual.</p>
				<p>Este trabalho apresenta um potencial interessante por não depender de softwares específicos, tendo uma boa perspectiva na obtenção de medidas de uma forma remota.</p>
			</sec>
		</body>
		<back>
			<fn-group>
				<fn fn-type="other">
					<label/>
					<p>Vinculação Acadêmica</p>
					<p> Este artigo é parte de tese de Doutorado de Genilton de França Barros Filho pela Universidade Federal da Paraíba, Programa de Pós-Graduação em Engenharia Mecânica.</p>
				</fn>
				<fn fn-type="other">
					<p> Aprovação Ética e Consentimento Informado</p>
					<p> Este estudo foi aprovado pela Comissão de Ética em Experimentação Animal do Colegiado do Comitê de Ética em Pesquisa com Seres Humanos - CEP/CCM/UFPB sob o número de protocolo 3.858.742.</p>
				</fn>
			</fn-group>
			<fn-group>
				<fn fn-type="supported-by">
					<p>Fontes de Financiamento</p>
					<p>O presente estudo foi parcialmente financiado por Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES).</p>
				</fn>
			</fn-group>
		</back>
	</sub-article>
</article>