{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T17:07:08Z","timestamp":1773335228407,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Pfizer Hellas","award":["070969\/2023"],"award-info":[{"award-number":["070969\/2023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Diagnosis of cardiomyopathies often depends on overt phenotypic manifestations, delaying patient management. This underscores the need for population-level opportunistic screening tools using clinically indicated CT scans to detect subclinical myocardial disease. This study developed an Ensemble Machine Learning (ML) model to automatically segment the left ventricular myocardium from CT data and estimate the probability of underlying myocardial disease using radiomic feature analysis. A total of 60 CT scans (~12,000 images) were used to train ML models for left ventricular myocardium segmentation, including scans from both healthy individuals and patients with myocardial disease. A novel Ensemble model was developed and externally validated on 10 independent CT scans. Subsequently, 100 unseen CT scans were segmented manually and automatically for radiomic feature analysis. After removing highly correlated features through intra-class variation and correlation filtering, the refined dataset was used for model training and testing. Key predictive features were identified, and model performance was evaluated. The four best-performing models (Unet++, ED w\/ASC, FPN, and TresUNET) were combined to form an Ensemble model, achieving a final DICE score of 0.882 after hyperparameter optimization. External validation yielded a DICE score of 0.907. Radiomic feature analysis identified 15 key predictors of myocardial disease in both manual and automatic segmentation datasets. The model demonstrated strong performance in detecting underlying myocardial disease, with AUCs of 0.85 and 0.8, respectively. This study presents a fully automated CT-based framework for LV myocardial segmentation and radiomic phenotyping that accurately estimates the probability of underlying myocardial disease. The model demonstrates strong generalizability across different CT protocols and highlights the potential role of AI-driven CT analysis for early, non-invasive cardiomyopathy screening at a population level.<\/jats:p>","DOI":"10.3390\/jimaging12030120","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:04:24Z","timestamp":1773162264000},"page":"120","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoding the Heart Through Computed Tomography: Early Cardiomyopathy Detection Using Ensemble-Based Segmentation and Radiomics"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0841-1688","authenticated-orcid":false,"given":"Theodoros","family":"Tsampras","sequence":"first","affiliation":[{"name":"Cardiogenetics and Sports Cardiology Unit, 1st Cardiology Department, Hippokration Hospital, National and Kapodistrian University of Athens, 11527 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexios","family":"Antonopoulos","sequence":"additional","affiliation":[{"name":"Cardiogenetics and Sports Cardiology Unit, 1st Cardiology Department, Hippokration Hospital, National and Kapodistrian University of Athens, 11527 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9766-983X","authenticated-orcid":false,"given":"Theodora","family":"Karamanidou","sequence":"additional","affiliation":[{"name":"Pfizer Center for Digital Innovation, 55535 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Kalykakis","sequence":"additional","affiliation":[{"name":"Cardiogenetics and Sports Cardiology Unit, 1st Cardiology Department, Hippokration Hospital, National and Kapodistrian University of Athens, 11527 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7636-6725","authenticated-orcid":false,"given":"Konstantinos","family":"Tsioufis","sequence":"additional","affiliation":[{"name":"Cardiogenetics and Sports Cardiology Unit, 1st Cardiology Department, Hippokration Hospital, National and Kapodistrian University of Athens, 11527 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9904-3558","authenticated-orcid":false,"given":"Charalambos","family":"Vlachopoulos","sequence":"additional","affiliation":[{"name":"Cardiogenetics and Sports Cardiology Unit, 1st Cardiology Department, Hippokration Hospital, National and Kapodistrian University of Athens, 11527 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1002\/ejhf.1461","article-title":"Heart failure in cardiomyopathies: A position paper from the Heart Failure Association of the European Society of Cardiology","volume":"21","author":"Polovina","year":"2019","journal-title":"Eur. J. Heart Fail."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1136\/heartjnl-2021-320181","article-title":"Epidemiology of cardiomyopathies and incident heart failure in a population-based cohort study","volume":"108","author":"Brownrigg","year":"2022","journal-title":"Heart"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1093\/eurjpc\/zwad058","article-title":"Diagnostic delay in arrhythmogenic cardiomyopathy","volume":"30","author":"Tini","year":"2023","journal-title":"Eur. J. Prev. Cardiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1080\/13696998.2023.2208966","article-title":"Frequency and clinicoeconomic impact of delays to definitive diagnosis of obstructive hypertrophic cardiomyopathy in the United States","volume":"26","author":"Naidu","year":"2023","journal-title":"J. Med. Econ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s40119-021-00219-5","article-title":"Impact of Delayed Diagnosis and Misdiagnosis for Patients with Transthyretin Amyloid Cardiomyopathy (ATTR-CM): A Targeted Literature Review","volume":"10","author":"Rozenbaum","year":"2021","journal-title":"Cardiol. Ther."},{"key":"ref_6","first-page":"25","article-title":"Transthyretin amyloidosis cardiomyopathy in Greece: Clinical insights from the National Referral Center","volume":"79","author":"Bampatsias","year":"2024","journal-title":"Hell. J. Cardiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1007\/s11547-023-01658-x","article-title":"Radiomics applications in cardiac imaging: A comprehensive review","volume":"128","author":"Polidori","year":"2023","journal-title":"Radiol. Medica"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"21769","DOI":"10.1038\/s41598-020-77733-4","article-title":"Automatic segmentation with detection of local segmentation failures in cardiac MRI","volume":"10","author":"Sander","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"101786","DOI":"10.1016\/j.compmedimag.2020.101786","article-title":"Fully automatic segmentation of right and left ventricle on short-axis cardiac MRI images","volume":"85","author":"Budai","year":"2020","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"660","DOI":"10.3348\/kjr.2019.0378","article-title":"Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning","volume":"21","author":"Koo","year":"2020","journal-title":"Korean J. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zreik, M., Leiner, T., Vos, B.D.d., Hamersvelt, R.W.v., Viergever, M.A., and I\u0161gum, I. (2016). Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic, 13\u201316 April 2016, IEEE.","DOI":"10.1109\/ISBI.2016.7493206"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"488","DOI":"10.2967\/jnumed.118.222893","article-title":"Introduction to Radiomics","volume":"61","author":"Mayerhoefer","year":"2020","journal-title":"J. Nucl. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105191","DOI":"10.1016\/j.compbiomed.2021.105191","article-title":"Deep learning-based whole-heart segmentation in 4D contrast-enhanced cardiac CT","volume":"142","author":"Bruns","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1002\/mp.14066","article-title":"Automated left ventricular myocardium segmentation using 3D deeply supervised attention U-net for coronary computed tomography angiography; CT myocardium segmentation","volume":"47","author":"He","year":"2020","journal-title":"Med. Phys."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Piccinelli, M., Dahiya, N., Folks, R.D., Yezzi, A., and Garcia, E.V. (2021). Validation of Automated Biventricular Myocardial Segmentation from Coronary Computed Tomographic Angiography for Multimodality Image Fusion. medRxiv, medRxiv:2021:2021.03.08.21252480.","DOI":"10.1101\/2021.03.08.21252480"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3436","DOI":"10.21037\/qims-21-1022","article-title":"Cardiac computed tomography radiomics: A narrative review of current status and future directions","volume":"12","author":"Shang","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ayx, I., Froelich, M.F., Baumann, S., Papavassiliu, T., and Schoenberg, S.O. (2023). Radiomics in Cardiac Computed Tomography. Diagnostics, 13.","DOI":"10.3390\/diagnostics13020307"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s12410-022-09563-z","article-title":"Radiomics in Cardiovascular Disease Imaging: From Pixels to the Heart of the Problem","volume":"15","author":"Spadarella","year":"2022","journal-title":"Curr. Cardiovasc. Imaging Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e230323","DOI":"10.1148\/ryct.230323","article-title":"Radiomics from Cardiovascular MR Cine Images for Identifying Patients with Hypertrophic Cardiomyopathy at High Risk for Heart Failure","volume":"6","author":"Zhang","year":"2024","journal-title":"Radiol. Cardiothorac. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1016\/j.jcmg.2018.11.024","article-title":"Radiomic Analysis of Myocardial Native T1 Imaging Discriminates Between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy","volume":"12","author":"Neisius","year":"2019","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"23596","DOI":"10.1038\/s41598-021-02971-z","article-title":"Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes","volume":"11","author":"Antonopoulos","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e008193","DOI":"10.1161\/CIRCHEARTFAILURE.120.008193","article-title":"Long-Term Survival with Tafamidis in Patients with Transthyretin Amyloid Cardiomyopathy","volume":"15","author":"Elliott","year":"2022","journal-title":"Circ. Heart Fail."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4475","DOI":"10.1002\/ehf2.70011","article-title":"Real-world effectiveness of targeted therapies in ATTR cardiomyopathy: A meta-analysis integrating population-based data","volume":"12","author":"Antonopoulos","year":"2025","journal-title":"ESC Heart Fail."},{"key":"ref_24","first-page":"25","article-title":"A complexity evaluation system for mitral valve repair based on preoperative echocardiographic and machine learning","volume":"81","author":"Zhu","year":"2025","journal-title":"Hell. J. Cardiol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"O\u2019Brien, H., Williams, M.C., Rajani, R., and Niederer, S. (2022). Radiomics and Machine Learning for Detecting Scar Tissue on CT Delayed Enhancement Imaging. Front. Cardiovasc. Med., 9.","DOI":"10.3389\/fcvm.2022.847825"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"101684","DOI":"10.1016\/j.jacadv.2025.101684","article-title":"Radiomic Cardiac MRI Signatures for Predicting Ventricular Arrhythmias in Patients with Nonischemic Dilated Cardiomyopathy","volume":"4","author":"Amyar","year":"2025","journal-title":"JACC Adv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ayx, I., Tharmaseelan, H., Hertel, A., N\u00f6renberg, D., Overhoff, D., Rotkopf, L.T., Riffel, P., Schoenberg, S.O., and Froelich, M.F. (2022). Comparison Study of Myocardial Radiomics Feature Properties on Energy-Integrating and Photon-Counting Detector CT. Diagnostics, 12.","DOI":"10.1038\/s41598-022-22877-8"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Angelaki, E., Kopidakis, I., Barmparis, G.D., Fragkiadakis, K., Maragkoudakis, S., Kalomoirakis, P., Kallergis, E., Zacharis, E., Kampanieris, E., and Alifragki, A. (2026). Single-Lead ECG-Based Machine Learning Model for Noninvasive Detection of Left Ventricular Hypertrophy in Hypertension. Hell. J. Cardiol., online ahead of print.","DOI":"10.1016\/j.hjc.2026.01.004"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Antonopoulos, A., Tsampras, T., Kalykakis, G., Karamanidou, T., Stavropoulos, T.G., and Stavropoulos, C. (2024, January 27\u201330). Automatic Segmentation of the Left Ventricular Myocardium in Cardiac CT Scans using AI. Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece.","DOI":"10.1109\/ISBI56570.2024.10635185"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e180026","DOI":"10.1148\/ryct.2019180026","article-title":"Radiomics for Distinguishing Myocardial Infarction from Myocarditis at Late Gadolinium Enhancement at MRI: Comparison with Subjective Visual Analysis","volume":"1","author":"Mannil","year":"2019","journal-title":"Radiol. Cardiothorac. Imaging"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.jcmg.2023.05.003","article-title":"Radiomics of Late Gadolinium Enhancement Reveals Prognostic Value of Myocardial Scar Heterogeneity in Hypertrophic Cardiomyopathy","volume":"17","author":"Fahmy","year":"2024","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1007\/s00330-022-09217-0","article-title":"Identification of fibrosis in hypertrophic cardiomyopathy: A radiomic study on cardiac magnetic resonance cine imaging","volume":"33","author":"Pu","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_33","first-page":"18","article-title":"Deep learning for cardiac imaging: Focus on myocardial diseases, a narrative review","volume":"81","author":"Tsampras","year":"2025","journal-title":"Hell. J. Cardiol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1080\/13506129.2025.2486072","article-title":"Computed tomography-derived myocardial radiomics for detection of transthyretin amyloidosis in patients with severe aortic stenosis","volume":"32","author":"Antonopoulos","year":"2025","journal-title":"Amyloid"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, Y., Zhang, G., Qiu, X., Tan, W., Yin, X., and Liao, L. (2022). Deep Learning with Radiomics for Disease Diagnosis and Treatment: Challenges and Potential. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.773840"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e250917","DOI":"10.1148\/radiol.250917","article-title":"Deep Learning\u2013based Opportunistic CT Osteoporosis Screening and the Establishment of Normative Values","volume":"317","author":"Westerhoff","year":"2025","journal-title":"Radiology"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.6009\/jjrt.26-1594","article-title":"Site-specific segmentation of skeletal muscles in body CT images via comprehensive muscular consideration","volume":"82","author":"Ashino","year":"2026","journal-title":"Nihon Hoshasen Gijutsu Gakkai Zasshi"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/120\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:29:52Z","timestamp":1773293392000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["jimaging12030120"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12030120","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]}}}