{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T17:11:44Z","timestamp":1784740304600,"version":"3.55.0"},"reference-count":35,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100015797","name":"Austrian Society of Cardiology","doi-asserted-by":"publisher","award":["Reducing costs of segmentation labeling in cardiac MRI using explainable AI"],"award-info":[{"award-number":["Reducing costs of segmentation labeling in cardiac MRI using explainable AI"]}],"id":[{"id":"10.13039\/501100015797","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JPM"],"abstract":"<jats:p>Aims: We tested the hypothesis that artificial intelligence (AI)-powered algorithms applied to cardiac magnetic resonance (CMR) images could be able to detect the potential patterns of cardiac amyloidosis (CA). Readers in CMR centers with a low volume of referrals for the detection of myocardial storage diseases or a low volume of CMRs, in general, may overlook CA. In light of the growing prevalence of the disease and emerging therapeutic options, there is an urgent need to avoid misdiagnoses. Methods and Results: Using CMR data from 502 patients (CA: n = 82), we trained convolutional neural networks (CNNs) to automatically diagnose patients with CA. We compared the diagnostic accuracy of different state-of-the-art deep learning techniques on common CMR imaging protocols in detecting imaging patterns associated with CA. As a result of a 10-fold cross-validated evaluation, the best-performing fine-tuned CNN achieved an average ROC AUC score of 0.96, resulting in a diagnostic accuracy of 94% sensitivity and 90% specificity. Conclusions: Applying AI to CMR to diagnose CA may set a remarkable milestone in an attempt to establish a fully computational diagnostic path for the diagnosis of CA, in order to support the complex diagnostic work-up requiring a profound knowledge of experts from different disciplines.<\/jats:p>","DOI":"10.3390\/jpm11121268","type":"journal-article","created":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T02:40:02Z","timestamp":1638412802000},"page":"1268","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Convolutional Neural Networks for Fully Automated Diagnosis of Cardiac Amyloidosis by Cardiac Magnetic Resonance Imaging"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0096-0143","authenticated-orcid":false,"given":"Asan","family":"Agibetov","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7632-9879","authenticated-orcid":false,"given":"Andreas","family":"Kammerlander","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7519-5274","authenticated-orcid":false,"given":"Franz","family":"Duca","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0141-7639","authenticated-orcid":false,"given":"Christian","family":"Nitsche","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Koschutnik","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina","family":"Don\u00e0","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theresa-Marie","family":"Dachs","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6409-5158","authenticated-orcid":false,"given":"Ren\u00e9","family":"Rettl","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0178-8867","authenticated-orcid":false,"given":"Alessa","family":"Stria","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lore","family":"Schrutka","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6060-7910","authenticated-orcid":false,"given":"Christina","family":"Binder","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Kastner","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hermine","family":"Agis","sequence":"additional","affiliation":[{"name":"Division of Oncology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2428-543X","authenticated-orcid":false,"given":"Renate","family":"Kain","sequence":"additional","affiliation":[{"name":"Department of Pathology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michaela","family":"Auer-Grumbach","sequence":"additional","affiliation":[{"name":"Division of Orthopedics and Traumatology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4855-2571","authenticated-orcid":false,"given":"Matthias","family":"Samwald","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8284-2994","authenticated-orcid":false,"given":"Christian","family":"Hengstenberg","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georg","family":"Dorffner","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Mascherbauer","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diana","family":"Bonderman","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Medical University of Vienna, 1090 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2440","DOI":"10.1161\/01.CIR.0000068314.02595.B2","article-title":"Serum N-Terminal Pro\u2013Brain Natriuretic Peptide Is a Sensitive Marker of Myocardial Dysfunction in AL Amyloidosis","volume":"107","author":"Palladini","year":"2003","journal-title":"Circulation"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1016\/j.jacc.2016.06.053","article-title":"AL (Light-Chain) Cardiac Amyloidosis: A Review of Diagnosis and Therapy","volume":"68","author":"Falk","year":"2016","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1080\/07853890701842988","article-title":"Senile systemic amyloidosis affects 25% of the very aged and associates with genetic variation in alpha2-macroglobulin and tau: A population-based autopsy study","volume":"40","author":"Tanskanen","year":"2008","journal-title":"Ann. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2585","DOI":"10.1093\/eurheartj\/ehv338","article-title":"Wild-type transthyretin amyloidosis as a cause of heart failure with preserved ejection fraction","volume":"36","author":"Moral","year":"2015","journal-title":"Eur. Heart J."},{"key":"ref_5","first-page":"A15","article-title":"1 A multi-centre study of cardiac amyloidosis in tavi patients","volume":"104","author":"Scully","year":"2018","journal-title":"Heart"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/s12968-017-0415-x","article-title":"Cardiac amyloidosis is prevalent in older patients with aortic stenosis and carries worse prognosis","volume":"19","author":"Cavalcante","year":"2017","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3420","DOI":"10.1182\/blood-2012-12-473066","article-title":"A European collaborative study of treatment outcomes in 346 patients with cardiac stage III AL amyloidosis","volume":"121","author":"Wechalekar","year":"2013","journal-title":"Blood"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2404","DOI":"10.1161\/CIRCULATIONAHA.116.021612","article-title":"Nonbiopsy Diagnosis of Cardiac Transthyretin Amyloidosis","volume":"133","author":"Gillmore","year":"2016","journal-title":"Circulation"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1093\/ehjci\/jew130","article-title":"Amyloid in the heart: An under-recognized threat at the interface of cardiology, haematology, and pathology","volume":"17","author":"Bonderman","year":"2016","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1007\/s00508-020-01781-z","article-title":"Diagnosis and treatment of cardiac amyloidosis: An interdisciplinary consensus statement","volume":"132","author":"Bonderman","year":"2020","journal-title":"Wien. Klin. Wochenschr."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/1532-429X-10-35","article-title":"Standardized cardiovascular magnetic resonance imaging (CMR) protocols, society for cardiovascular magnetic resonance: Board of trustees task force on standardized protocols","volume":"10","author":"Kramer","year":"2008","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_12","first-page":"63","article-title":"Extracellular volume fraction mapping in the myocardium, part 1: Evaluation of an automated method","volume":"14","author":"Kellman","year":"2012","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_15","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/bimj.200710415","article-title":"Youden Index and Optimal Cut-Point Estimated from Observations Affected by a Lower Limit of Detection","volume":"50","author":"Ruopp","year":"2008","journal-title":"Biom. J."},{"key":"ref_17","unstructured":"Sanjoy, D., and David, M. (2013). On the importance of initialization and momentum in deep learning. Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, Atlanta, GA, USA, 16\u201321 June 2013, PMLR."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s00365-006-0663-2","article-title":"On Early Stopping in Gradient Descent Learning","volume":"26","author":"Yao","year":"2007","journal-title":"Constr. Approx."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10741-014-9470-7","article-title":"Cardiovascular magnetic resonance for amyloidosis","volume":"20","author":"Fontana","year":"2014","journal-title":"Heart Fail. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1007\/s11886-019-1180-2","article-title":"Cardiac Amyloidosis: Updates in Imaging","volume":"21","author":"Chacko","year":"2019","journal-title":"Curr. Cardiol. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1016\/j.jcmg.2019.06.023","article-title":"Myocardial Amyloidosis: The Exemplar Interstitial Disease","volume":"12","author":"Fontana","year":"2019","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1161\/01.CIR.0000152819.97857.9D","article-title":"Cardiovascular Magnetic Resonance in Cardiac Amyloidosis","volume":"111","author":"Maceira","year":"2005","journal-title":"Circulation"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1093\/eurheartj\/ehu444","article-title":"T1 mapping and survival in systemic light-chain amyloidosis","volume":"36","author":"Banypersad","year":"2015","journal-title":"Eur. Heart J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1016\/j.jcmg.2009.08.008","article-title":"Delayed Hyper-Enhancement Magnetic Resonance Imaging Provides Incremental Diagnostic and Prognostic Utility in Suspected Cardiac Amyloidosis","volume":"2","author":"Austin","year":"2009","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1093\/ehjci\/jew101","article-title":"Clinical and prognostic utility of cardiovascular magnetic resonance imaging in myeloma patients with suspected cardiac amyloidosis","volume":"17","author":"Bhatti","year":"2016","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.tcm.2018.06.011","article-title":"Cardiovascular magnetic resonance imaging for amyloidosis: The state-of-the-art","volume":"29","author":"Tang","year":"2018","journal-title":"Trends Cardiovasc. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2726","DOI":"10.1038\/s41467-021-22877-8","article-title":"Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms","volume":"12","author":"Goto","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Agibetov, A., Seirer, B., Dachs, T.-M., Koschutnik, M., Dalos, D., Rettl, R., Duca, F., Schrutka, L., Agis, H., and Kain, R. (2020). Machine Learning Enables Prediction of Cardiac Amyloidosis by Routine Laboratory Parameters: A Proof-of-Concept Study. J. Clin. Med., 9.","DOI":"10.3390\/jcm9051334"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s12968-020-00690-4","article-title":"Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance","volume":"22","author":"Martini","year":"2020","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/17434440.2017.1300057","article-title":"Cardiac imaging: Working towards fully-automated machine analysis & interpretation","volume":"14","author":"Slomka","year":"2017","journal-title":"Expert Rev. Med. Devices"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Singh, A., Sengupta, S., and Lakshminarayanan, V. (2020). Explainable Deep Learning Models in Medical Image Analysis. J. Imaging, 6.","DOI":"10.3390\/jimaging6060052"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fcvm.2020.00001","article-title":"Image-Based Cardiac Diagnosis With Machine Learning: A Review","volume":"7","author":"Campello","year":"2020","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"van der Ploeg, T., Austin, P.C., and Steyerberg, E.W. (2014). Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints. BMC Med. Res. Methodol., 14.","DOI":"10.1186\/1471-2288-14-137"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1038\/nrcardio.2013.129-c1","article-title":"Troponins in cardiac amyloidosis: Multipurpose markers","volume":"11","author":"Perfetto","year":"2014","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_35","unstructured":"Rajpurkar, P., Irvin, J., and Bagul, A. (2021, September 28). MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs. Med. Imaging Deep. Learn., Available online: https:\/\/arxiv.org\/abs\/1712.06957."}],"container-title":["Journal of Personalized Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4426\/11\/12\/1268\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:38:25Z","timestamp":1760168305000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4426\/11\/12\/1268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,1]]},"references-count":35,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["jpm11121268"],"URL":"https:\/\/doi.org\/10.3390\/jpm11121268","relation":{},"ISSN":["2075-4426"],"issn-type":[{"value":"2075-4426","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,1]]}}}