{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T16:27:22Z","timestamp":1787934442580,"version":"build-2784847793"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:00:00Z","timestamp":1726099200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science, Technology, and Innovation(MOSTl) under the Technology Development Fund","award":["TDF03211036"],"award-info":[{"award-number":["TDF03211036"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Regional Wall Motion Abnormality (RWMA) serves as an early indicator of myocardial infarction (MI), the global leader in mortality. Accurate and early detection of RWMA is vital for the successful treatment of MI. Current automated echocardiography analyses typically concentrate on peak values from left ventricular (LV) displacement curves, based on LV contour annotations or key frames during the heart\u2019s systolic or diastolic phases within a single echocardiographic cycle. This approach may overlook the rich motion field features available in multi-cycle cardiac data, which could enhance RWMA detection.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>In this research, we put forward an innovative approach to detect RWMA by harnessing motion information across multiple echocardiographic cycles and multi-views. Our methodology synergizes U-Net-based segmentation with optical flow algorithms for detailed cardiac structure delineation, and Temporal Convolutional Networks (ConvNet) to extract nuanced motion features. We utilize a variety of machine learning and deep learning classifiers on both A2C and A4C views echocardiograms to enhance detection accuracy. A three-phase algorithm\u2014originating from the HMC-QU dataset\u2014incorporates U-Net for segmentation, followed by optical flow for cardiac wall motion field features. Temporal ConvNet, inspired by the Temporal Segment Network (TSN), is then applied to interpret these motion field features, independent of traditional cardiac parameter curves or specific key phase frame inputs.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Employing five-fold cross-validation, our SVM classifier demonstrated high performance, with a sensitivity of 93.13%, specificity of 83.61%, precision of 88.52%, and an F1 score of 90.39%. When compared with other studies using the HMC-QU datasets, these Fig s stand out, underlining our method\u2019s effectiveness. The classifier also attained an overall accuracy of 89.25% and Area Under the Curve (AUC) of 95%, reinforcing its potential for reliable RWMA detection in echocardiographic analysis.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>This research not only demonstrates a novel technique but also contributes a more comprehensive and precise tool for early myocardial infarction diagnosis.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0310107","type":"journal-article","created":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T17:31:40Z","timestamp":1726162300000},"page":"e0310107","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Enhancing reginal wall abnormality detection accuracy: Integrating machine learning, optical flow algorithms, and temporal convolutional networks in multi-view echocardiography"],"prefix":"10.1371","volume":"19","author":[{"given":"Sazzli","family":"Kasim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-6404","authenticated-orcid":true,"given":"Sorayya","family":"Malek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khairul Shafiq","family":"Ibrahim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raja Ezman Raja","family":"Shariff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesvinna Kaur","family":"Chima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,9,12]]},"reference":[{"issue":"25","key":"pone.0310107.ref001","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.1016\/j.jacc.2023.11.007","article-title":"Global Burden of Cardiovascular Diseases and Risks, 1990\u20132022.","volume":"82","author":"G Mensah","year":"2023","journal-title":"J Am Coll Cardiol"},{"issue":"5","key":"pone.0310107.ref002","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1038\/s41591-023-02325-4","article-title":"Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations","volume":"29","author":"D Doudesis","year":"2023","journal-title":"Nat Med"},{"key":"pone.0310107.ref003","article-title":"Early Myocardial Infarction Detection with One-Class Classification over Multi-view Echocardiography. In: Computing in Cardiology","author":"A Degerli","year":"2022","journal-title":"IEEE Computer Society"},{"issue":"4","key":"pone.0310107.ref004","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1016\/0002-8703(85)90641-6","article-title":"The value of echocardiographic regional wall motion abnormalities in detecting coronary artery disease in subjects with or without a dilated left ventricle","volume":"109","author":"R Medina","year":"1985","journal-title":"Am Heart J"},{"key":"pone.0310107.ref005","doi-asserted-by":"crossref","first-page":"34442","DOI":"10.1109\/ACCESS.2021.3059595","article-title":"Early Detection of Myocardial Infarction in Low-Quality Echocardiography.","volume":"9","author":"A Degerli","year":"2021","journal-title":"IEEE Access."},{"key":"pone.0310107.ref006","first-page":"443","article-title":"Cardiac biomarkers and detection methods for myocardial infarction.","volume-title":"Molecular and Cellular Toxicology","author":"SY Kim","year":"2022"},{"issue":"16","key":"pone.0310107.ref007","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","article-title":"Fully automated echocardiogram interpretation in clinical practice: Feasibility and diagnostic accuracy","volume":"138","author":"J Zhang","year":"2018","journal-title":"Circulation"},{"issue":"26","key":"pone.0310107.ref008","doi-asserted-by":"crossref","first-page":"37417","DOI":"10.1007\/s11042-021-11579-4","article-title":"Fully automated 2D and 3D convolutional neural networks pipeline for video segmentation and myocardial infarction detection in echocardiography.","volume":"81","author":"O Hamila","year":"2022","journal-title":"Multimed Tools Appl."},{"issue":"2","key":"pone.0310107.ref009","first-page":"37","article-title":"Fully Automatic Heart Segmentation Model Analysis Using Residual Multi-Dilated Recurrent Convolutional U-Net.","volume":"9","author":"SH Lim","year":"2020","journal-title":"KIPS Transactions on Computer and Communication Systems [Internet]."},{"key":"pone.0310107.ref010","doi-asserted-by":"crossref","first-page":"210301","DOI":"10.1109\/ACCESS.2020.3038743","article-title":"Left Ventricular Wall Motion Estimation by Active Polynomials for Acute Myocardial Infarction Detection.","volume":"8","author":"S Kiranyaz","year":"2020","journal-title":"IEEE Access."},{"key":"pone.0310107.ref011","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1109\/TMI.2018.2811483","article-title":"A Dual Tissue-Doppler Optical-Flow Method for Speckle Tracking Echocardiography at High Frame Rate","volume":"37","author":"J Por\u00e9e","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0310107.ref012","doi-asserted-by":"crossref","first-page":"110878","DOI":"10.1016\/j.jbiomech.2021.110878","article-title":"Direct left-ventricular global longitudinal strain (GLS) computation with a fully convolutional network.","volume":"130","author":"J Kar","year":"2022","journal-title":"J Biomech"},{"issue":"1","key":"pone.0310107.ref013","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/TIP.2017.2753406","article-title":"Motion Estimation in Echocardiography Using Sparse Representation and Dictionary Learning","volume":"27","author":"N Ouzir","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"pone.0310107.ref014","first-page":"1","article-title":"Inter-frame Echocardiography Feature Matching for Analyzing the Cardiac Motion.","author":"Y Fahim","year":"2022","journal-title":"In: Proceedings of the 2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON);"},{"key":"pone.0310107.ref015","author":"S Thomas","year":"2022","journal-title":"Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound"},{"key":"pone.0310107.ref016","doi-asserted-by":"crossref","first-page":"105076","DOI":"10.1016\/j.bspc.2023.105076","article-title":"LVSnake: Accurate and robust left ventricle contour localization for myocardial infarction detection.","volume":"85","author":"Y Li","year":"2023","journal-title":"Biomed Signal Process Control."},{"key":"pone.0310107.ref017","author":"I Adalioglu","year":"2023","journal-title":"SAF-Net: Self-Attention Fusion Network for Myocardial Infarction Detection using Multi-View Echocardiography"},{"key":"pone.0310107.ref018","author":"O Ronneberger","year":"2015","journal-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation"},{"key":"pone.0310107.ref019","volume-title":"Simplifying Medical Ultrasound. ASMUS 2022. Lecture Notes in Computer Science","author":"M Saeed","year":"2022"},{"issue":"2","key":"pone.0310107.ref020","doi-asserted-by":"crossref","first-page":"e0264002","DOI":"10.1371\/journal.pone.0264002","article-title":"Automated detection scheme for acute myocardial infarction using convolutional neural network and long short-term memory","volume":"17","author":"R Muraki","year":"2022","journal-title":"PLoS ONE"},{"issue":"7802","key":"pone.0310107.ref021","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based AI for beat-to-beat assessment of cardiac function","volume":"580","author":"D Ouyang","year":"2020","journal-title":"Nature"},{"issue":"9","key":"pone.0310107.ref022","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","article-title":"Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography","volume":"38","author":"S Leclerc","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0310107.ref023","first-page":"308","author":"M S\u00fchling","year":"2004","journal-title":"Bimodal Myocardial Motion Analysis from B-Mode and Tissue Doppler UltrasoundIn: Proceedings of the Second IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI\u201904); 2004 Apr 15\u201318; Arlington VA, USA."},{"issue":"3","key":"pone.0310107.ref024","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1109\/TIP.2012.2226903","article-title":"Myocardial motion estimation from medical images using the monogenic signal","volume":"22","author":"M Alessandrini","year":"2013","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"pone.0310107.ref025","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1109\/TMI.2018.2870947","article-title":"Robust Optical Flow Estimation in Cardiac Ultrasound Images Using a Sparse Representation","volume":"38","author":"N Ouzir","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0310107.ref026","volume-title":"Computer Vision\u2013ECCV 2016. ECCV 2016. Lecture Notes in Computer Science","author":"L Wang","year":"2016"},{"key":"pone.0310107.ref027","first-page":"363","volume-title":"InImage Analysis: 13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, June 29\u2013July 2, 2003 Proceedings 13 2003","author":"G. Farneb\u00e4ck"},{"key":"pone.0310107.ref028","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"K Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"pone.0310107.ref029","first-page":"448","volume-title":"In: Proceedings of the 32nd International Conference on International Conference on Machine Learning\u2014Volume 37, ICML\u201915","author":"S Ioffe","year":"2015"},{"issue":"12","key":"pone.0310107.ref030","doi-asserted-by":"crossref","first-page":"6105","DOI":"10.1109\/JBHI.2022.3221429","article-title":"Improved Segmentation of Echocardiography With Orientation-Congruency of Optical Flow and Motion-Enhanced Segmentation","volume":"26","author":"W Xue","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0310107.ref031","article-title":"A Unified Framework Integrating Recurrent Fully-Convolutional Networks and Optical Flow for Segmentation of the Left Ventricle in Echocardiography Data.","author":"M Jafari","year":"2018","journal-title":"In: DLMIA\/ML-CDS@MICCAI"},{"key":"pone.0310107.ref032","doi-asserted-by":"crossref","first-page":"102686","DOI":"10.1016\/j.media.2022.102686","article-title":"Co-learning of appearance and shape for precise ejection fraction estimation from echocardiographic sequences","volume":"84","author":"H Wei","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0310107.ref033","first-page":"472","volume-title":"In International Conference on Medical Image Computing and Computer-Assisted Intervention: MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION\u2014MICCAI 2018, PT II.","author":"C Qin","year":"2018"},{"issue":"1","key":"pone.0310107.ref034","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s10916-023-01911-w","article-title":"Automatic Diagnostic Tool for Detection of Regional Wall Motion Abnormality from Echocardiogram.","volume":"47","author":"G Sanjeevi","year":"2023","journal-title":"J Med Syst."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0310107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T17:32:03Z","timestamp":1726162323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0310107"}},"subtitle":[],"editor":[{"given":"Hadeel K.","family":"Aljobouri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,9,12]]},"references-count":34,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0310107","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,12]]}}}