{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T06:28:41Z","timestamp":1790317721057,"version":"4.1.0"},"reference-count":31,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100015696","name":"Siemens Medical Solutions USA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Automated approaches may allow for fast, reproducible clinical assessment of cardiovascular diseases from MRI.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To develop an MRI\u2010based deep learning (DL) disease classification algorithm to distinguish among normal subjects (NORM), patients with dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM), and ischemic heart disease (IHD).<\/jats:p><\/jats:sec><jats:sec><jats:title>Study Type<\/jats:title><jats:p>Retrospective.<\/jats:p><\/jats:sec><jats:sec><jats:title>Population<\/jats:title><jats:p>A total of 1337 subjects (55% female), comprising normal subjects (<jats:italic>N<\/jats:italic>\u2009=\u2009568), and patients with DCM (<jats:italic>N<\/jats:italic>\u2009=\u2009151), HCM (<jats:italic>N<\/jats:italic>\u2009=\u2009177), and IHD (<jats:italic>N<\/jats:italic>\u2009=\u2009441).<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>Balanced steady\u2010state free precession cine sequence at 1.5\/3.0\u2009T.<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>Bi\u2010ventricular morphological and functional features and global and segmental left ventricular strain features were automatically extracted from short\u2010 and long\u2010axis cine images. Variational autoencoder models were trained on the extracted features and compared against consensus disease label provided by two expert readers (13 and 14\u2009years of experience). Adding unlabeled, normal data to the training was explored to increase specificity of NORM class.<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p>Tenfold cross\u2010validation for model development; mean, standard deviation (SD) for measurements; classification metrics: area under the curve (AUC), confusion matrix, accuracy, specificity, precision, recall; 95% confidence intervals; Mann\u2013Whitney <jats:italic>U<\/jats:italic> test for significance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>AUCs of 0.952 for NORM, 0.881 for DCM, 0.908 for HCM, and 0.856 for IHD and overall accuracy of 0.778 were obtained, with specificity of 0.908 for the NORM class using both SAX and LAX features. Longitudinal strain features slightly improved classification metrics by 0.001 to 0.03 points, except for HCM\u2010AUC. Differences in accuracy, metrics for NORM class and HCM\u2010AUC were statistically significant. Cotraining using unlabeled data increased the specificity for the NORM class to 0.961.<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusion<\/jats:title><jats:p>Cardiac function features automatically extracted from cine <jats:styled-content style=\"fixed-case\">MRI<\/jats:styled-content> have potential to be used for disease classification, especially for normal\u2010abnormal classification. Feature analyses showed that strain features were important for disease labeling. Cotraining using unlabeled data may help to increase specificity for normal\u2010abnormal classification.<\/jats:p><\/jats:sec><jats:sec><jats:title>Level of Evidence<\/jats:title><jats:p>3<\/jats:p><\/jats:sec><jats:sec><jats:title>Technical Efficacy<\/jats:title><jats:p>Stage 1<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.29619","type":"journal-article","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T01:59:52Z","timestamp":1727834392000},"page":"1635-1647","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep\u2010Learning\u2010Based Disease Classification in Patients Undergoing Cine Cardiac <scp>MRI<\/scp>"],"prefix":"10.1002","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5948-3655","authenticated-orcid":false,"given":"Athira J.","family":"Jacob","sequence":"first","affiliation":[{"name":"Digital Technology and Innovation Siemens Healthineers  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teodora","family":"Chitiboi","sequence":"additional","affiliation":[{"name":"Digital Technology and Innovation Siemens Healthineers  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6164-5641","authenticated-orcid":false,"given":"U. Joseph","family":"Schoepf","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[{"name":"Digital Technology and Innovation Siemens Healthineers  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Aldinger","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Baker","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carla","family":"Lautenschlager","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4156-7727","authenticated-orcid":false,"given":"Tilman","family":"Emrich","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"},{"name":"Department of Diagnostic and Interventional Radiology University Medical Center of the Johannes Gutenberg\u2010University Mainz  Mainz Germany"},{"name":"German Center for Cardiovascular Research (DZHK) Partner Site Rhine\u2010Main  Mainz Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2781-7462","authenticated-orcid":false,"given":"Akos","family":"Varga\u2010Szemes","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiological Science Medical University of South Carolina  Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,10]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjci\/jead124"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2020.00025"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09236-x"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.06.001"},{"key":"e_1_2_7_6_1","first-page":"82","volume-title":"Statistical atlases and computational models of the heart. ACDC and MMWHS challenges [Lecture Notes in Computer Science]","author":"Cetin I","year":"2018"},{"key":"e_1_2_7_7_1","first-page":"120","volume-title":"Statistical atlases and computational models of the heart. ACDC and MMWHS challenges [Lecture Notes in Computer Science]","author":"Isensee F","year":"2018"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779"},{"key":"e_1_2_7_9_1","first-page":"772","article-title":"Deep learning\u2010based strain quantification from CINE cardiac MRI","volume":"28","author":"Chitiboi T","year":"2020","journal-title":"Proc Intl Soc Magn Reson Med"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_7_11_1","unstructured":"NewtonA BuckeyeAJ AraiA et al.Second annual data science bowl.2015. Available from:https:\/\/www.kaggle.com\/c\/second-annual-data-science-bowl."},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehad655.164"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2011.5872476"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjci\/jead100"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehad655.211"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1161\/hc0402.102975"},{"key":"e_1_2_7_17_1","volume-title":"Auto\u2010encoding variational Bayes","author":"Kingma DP","year":"2022"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2021.103523"},{"key":"e_1_2_7_19_1","first-page":"448","volume-title":"Proceedings of the 32nd International Conference on international conference on machine learning","author":"Ioffe S","year":"2015"},{"key":"e_1_2_7_20_1","volume-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap AF","year":"2019"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15948-9"},{"key":"e_1_2_7_22_1","first-page":"2825","article-title":"Scikit\u2010learn: Machine learning in python","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_7_24_1","volume-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes L","year":"2020"},{"key":"e_1_2_7_25_1","first-page":"3319","volume-title":"Proceedings of the 34th International Conference on Machine Learning, PMLR","author":"Sundararajan M","year":"2017"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"e_1_2_7_27_1","volume-title":"Captum: A unified and generic model interpretability library for PyTorch","author":"Kokhlikyan N","year":"2020"},{"key":"e_1_2_7_28_1","first-page":"140","volume-title":"Statistical atlases and computational models of the heart. ACDC and MMWHS challenges [Lecture Notes in Computer Science]","author":"Khened M","year":"2018"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.0000078641.19365.4C"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968-018-0466-7"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.110.959817"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.1052"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.29619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T07:05:01Z","timestamp":1741763101000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.29619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1002\/jmri.29619"],"URL":"https:\/\/doi.org\/10.1002\/jmri.29619","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"2024-03-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}