{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:25:38Z","timestamp":1792787138951,"version":"4.5.0"},"reference-count":57,"publisher":"SPIE-Intl Soc Optical Eng","issue":"02","license":[{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"American Heart Association","award":["AHA.24PRE1188140.pc.gr.190654"],"award-info":[{"award-number":["AHA.24PRE1188140.pc.gr.190654"]}],"id":[{"id":"https:\/\/ror.org\/013kjyp64","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Heart, Lung, and Blood Institute of the National Institutes of Health","award":["R15HL145576"],"award-info":[{"award-number":["R15HL145576"]}],"id":[{"id":"https:\/\/ror.org\/012pb6c26","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2025,3,26]]},"abstract":"<jats:p>PurposePrevious studies on echocardiogram segmentation are focused on the left ventricle in parasternal long-axis views. Deep-learning models were evaluated on the segmentation of the ventricles in parasternal short-axis echocardiograms (PSAX-echo). Segmentation of the ventricles in complementary echocardiogram views will allow the computation of important metrics with the potential to aid in diagnosing cardio-pulmonary diseases and other cardiomyopathies. Evaluating state-of-the-art models with small datasets can reveal if they improve performance on limited data.ApproachPSAX-echo was performed on 33 volunteer women. An experienced cardiologist identified end-diastole and end-systole frames from 387 scans, and expert observers manually traced the contours of the cardiac structures. Traced frames were pre-processed and used to create labels to train two domain-specific (Unet-Resnet101 and Unet-ResNet50), and four general-domain [three segment anything (SAM) variants, and the Detectron2] deep-learning models. The performance of the models was evaluated using the Dice similarity coefficient (DSC), Hausdorff distance (HD), and difference in cross-sectional area (DCSA).ResultsThe Unet-Resnet101 model provided superior performance in the segmentation of the ventricles with 0.83, 4.93\u00a0pixels, and 106 pixel2 on average for DSC, HD, and DCSA, respectively. A fine-tuned MedSAM model provided a performance of 0.82, 6.66\u00a0pixels, and 1252 pixel2, whereas the Detectron2 model provided 0.78, 2.12\u00a0pixels, and 116 pixel2 for the same metrics, respectively.ConclusionsDeep-learning models are suitable for the segmentation of the left and right ventricles in PSAX-echo. We demonstrated that domain-specific trained models such as Unet-ResNet provide higher accuracy for echo segmentation than general-domain segmentation models when working with small and locally acquired datasets.<\/jats:p>","DOI":"10.1117\/1.jmi.12.2.024002","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:00:56Z","timestamp":1743012056000},"page":"1-18","source":"Crossref","is-referenced-by-count":7,"title":["Evaluation of state-of-the-art deep learning models in the segmentation of the left and right ventricles in parasternal short-axis echocardiograms"],"prefix":"10.1117","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6373-6764","authenticated-orcid":false,"given":"Julian R.","family":"Cuellar","sequence":"first","affiliation":[{"name":"Southern Illinois University Edwardsville"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vu","family":"Dinh","sequence":"additional","affiliation":[{"name":"The Johns Hopkins University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjula","family":"Burri","sequence":"additional","affiliation":[{"name":"Columbus Regional Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julie","family":"Roelandts","sequence":"additional","affiliation":[{"name":"St. Louis Community College"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Wendling","sequence":"additional","affiliation":[{"name":"St. Louis Community College"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3770-2754","authenticated-orcid":false,"given":"Jon D.","family":"Klingensmith","sequence":"additional","affiliation":[{"name":"Southern Illinois University Edwardsville"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2020.00025"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.1117\/12.3004836"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3173669"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1117\/12.3027808"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2005.852057"},{"key":"r6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2002.806427"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.119"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.1117\/12.3028330"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2900516"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1109\/USBEREIT48449.2020.9117678"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2019.10.001"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103728"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_8"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-024-03255-0"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1002\/clc.4960040410"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2012.03.022"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1038\/nrrheum.2012.2"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.10.004"},{"key":"r20","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/58\/21\/7609"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcct.2015.07.011"},{"key":"r22","first-page":"74","article-title":"Medici\u00f3n autom\u00e1tica de grasa en im\u00e1genes MRI abdominales","author":"Polvorinos","year":"2013"},{"key":"r23","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1007\/s10554-021-02482-y"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.120.047530"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.034338"},{"key":"r27","article-title":"EchoONE: segmenting multiple echocardiography planes in one model","author":"Hu","year":"2024"},{"key":"r28","doi-asserted-by":"publisher","DOI":"10.1109\/IECBES48179.2021.9398738"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1109\/EHB55594.2022.9991538"},{"key":"r30","first-page":"549","article-title":"Parasternal short axis (PSAX) view","author":"Venkatram","year":"2024"},{"key":"r31","doi-asserted-by":"publisher","DOI":"10.1109\/IUS51837.2023.10306900"},{"key":"r32","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2021.02.008"},{"key":"r33","first-page":"53","article-title":"Correlation between heart mediastinal and epicardial fat volumes and coronary artery disease based on computed tomography images","author":"Kazemi","year":"2021"},{"key":"r34","doi-asserted-by":"publisher","DOI":"10.1080\/03091902.2022.2081736"},{"key":"r35","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"Long","year":"2015"},{"key":"r36","article-title":"Introduction to IQ-demodulation of RF-data","author":"Kirkhorn","year":"1999"},{"key":"r37","doi-asserted-by":"publisher","DOI":"10.5120\/1506-2024"},{"key":"r38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"r39","doi-asserted-by":"publisher","DOI":"10.1117\/12.3027916"},{"key":"r40","doi-asserted-by":"publisher","DOI":"10.1117\/12.2688269"},{"key":"r41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"r42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"r43","article-title":"Detectron2: a PyTorch-based modular object detection library"},{"key":"r44","doi-asserted-by":"publisher","DOI":"10.1117\/12.3028318"},{"key":"r45","article-title":"Mask R-CNN \u2013 meta research"},{"key":"r46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506485"},{"key":"r47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"r48","article-title":"An image is worth 16 \u00d7 16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"r49","doi-asserted-by":"publisher","DOI":"10.1016\/S1076-6332(03)00671-8"},{"key":"r50","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073"},{"key":"r51"},{"key":"r52","doi-asserted-by":"publisher","DOI":"10.1117\/12.2513089"},{"key":"r53","doi-asserted-by":"publisher","DOI":"10.1117\/12.2519112"},{"key":"r54","article-title":"Adversarial learning for semi-supervised semantic segmentation","author":"Hung","year":"2018"},{"key":"r55"},{"key":"r56","article-title":"EchoNet-Dynamic","year":"2020"},{"key":"r57","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.9.1.017001"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-12\/issue-02\/024002\/Evaluation-of-state-of-the-art-deep-learning-models-in\/10.1117\/1.JMI.12.2.024002.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T23:20:40Z","timestamp":1790205640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-12\/issue-02\/024002\/Evaluation-of-state-of-the-art-deep-learning-models-in\/10.1117\/1.JMI.12.2.024002.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,26]]},"references-count":57,"journal-issue":{"issue":"02","published-online":{"date-parts":[[2025,3,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.12.2.024002","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,26]]}}}