{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T17:17:00Z","timestamp":1772126220570,"version":"3.50.1"},"reference-count":42,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UK International Development and the International Development Research Centre (IDRC)","award":["110473-001"],"award-info":[{"award-number":["110473-001"]}]},{"name":"Google Research Award, an NVIDIA hardware grant, Data Science Africa (DSAIL Affiliated Centre Program)","award":["110473-001"],"award-info":[{"award-number":["110473-001"]}]},{"name":"ARM","award":["110473-001"],"award-info":[{"award-number":["110473-001"]}]},{"name":"Google Cloud Research Credits program","award":["110473-001"],"award-info":[{"award-number":["110473-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Rheumatic heart disease (RHD) poses a significant global health challenge, necessitating improved diagnostic tools. This study investigated the use of self-supervised multi-task learning for automated echocardiographic analysis, aiming to predict echocardiographic views, diagnose RHD conditions, and determine severity. We compared two prominent self-supervised learning (SSL) methods: DINOv2, a vision-transformer-based approach known for capturing implicit features, and simple contrastive learning representation (SimCLR), a ResNet-based contrastive learning method recognised for its simplicity and effectiveness. Both models were pre-trained on a large, unlabelled echocardiogram dataset and fine-tuned on a smaller, labelled subset. DINOv2 achieved accuracies of 92% for view classification, 98% for condition detection, and 99% for severity assessment. SimCLR demonstrated good performance as well, achieving accuracies of 99% for view classification, 92% for condition detection, and 96% for severity assessment. Embedding visualisations, using both Uniform Manifold Approximation Projection (UMAP) and t-distributed Stochastic Neighbor Embedding (t-SNE), revealed distinct clusters for all tasks in both models, indicating the effective capture of the discriminative features of the echocardiograms. This study demonstrates the potential of using self-supervised multi-task learning for automated echocardiogram analysis, offering a scalable and efficient approach to improving RHD diagnosis, especially in resource-limited settings.<\/jats:p>","DOI":"10.3390\/jimaging11040097","type":"journal-article","created":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:54:48Z","timestamp":1743159288000},"page":"97","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Self-Supervised Multi-Task Learning for the Detection and Classification of RHD-Induced Valvular Pathology"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0824-5016","authenticated-orcid":false,"given":"Lorna","family":"Mugambi","sequence":"first","affiliation":[{"name":"Centre for Data Science and Artificial Intelligence, Dedan Kimathi University of Technology, Nyeri 10143, Kenya"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4203-3129","authenticated-orcid":false,"given":"Ciira","family":"wa Maina","sequence":"additional","affiliation":[{"name":"Centre for Data Science and Artificial Intelligence, Dedan Kimathi University of Technology, Nyeri 10143, Kenya"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liesl","family":"Z\u00fchlke","sequence":"additional","affiliation":[{"name":"South African Medical Research Council, Francie Van Zyl Drive, Cape Town 7505, South Africa"},{"name":"Division of Paediatric Cardiology, Department of Paediatrics and Child Health, Red Cross War Memorial Children\u2019s Hospital, Cape Town 7700, South Africa"},{"name":"Division of Cardiology, Department of Medicine, Groote Schuur Hospital, Cape Town 7925, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chillo, P., Mutagaywa, R., Nkya, D., Njelekela, M., Kwesigabo, G., Kahabuka, F., Kerry, V., and Kamuhabwa, A. (2023). Sub-clinical rheumatic heart disease (RHD) detected by hand-held echocardiogram in children participating in a school-based RHD prevention program in Tanzania. BMC Cardiovasc. Disord., 23.","DOI":"10.1186\/s12872-023-03186-y"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"113954","DOI":"10.1016\/j.jpeds.2024.113954","article-title":"Silent Acute Rheumatic Fever Unmasked by Using Handheld Echocardiography for Febrile Children Presenting in a Rheumatic Heart Disease\u2013Endemic Area","volume":"268","author":"Ali","year":"2024","journal-title":"J. Pediatr."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liang, Y., Yu, D., Lu, Q., Zheng, Y., and Yang, Y. (2023). The rise and fall of acute rheumatic fever and rheumatic heart disease: A mini review. Front. Cardiovasc. Med., 10.","DOI":"10.3389\/fcvm.2023.1183606"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"20503121231169389","DOI":"10.1177\/20503121231169389","article-title":"Prevalence of rheumatic heart disease in Ethiopia: A systematic review and meta-analysis","volume":"11","author":"Asfaw","year":"2023","journal-title":"SAGE Open Med."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Bennett, J., Moreland, N.J., Oliver, J., Crane, J., Williamson, D.A., Sika-Paotonu, D., Harwood, M., Upton, A., Smith, S., and Carapetis, J. (2019). Understanding group A streptococcal pharyngitis and skin infections as causes of rheumatic fever: Protocol for a prospective disease incidence study. BMC Infect. Dis., 19.","DOI":"10.1186\/s12879-019-4126-9"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8834443","DOI":"10.1155\/2023\/8834443","article-title":"Rheumatic Heart Disease in East Africa: A Systematic Review and Meta-Analysis","volume":"2023","author":"Mebrahtom","year":"2023","journal-title":"Int. J. Rheumatol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e012467","DOI":"10.1136\/bmjgh-2023-012467","article-title":"Research priorities for the primordial prevention of acute rheumatic fever and rheumatic heart disease by modifying the social determinants of health","volume":"8","author":"Baker","year":"2023","journal-title":"BMJ Glob. Health"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1038\/nrcardio.2012.7","article-title":"World Heart Federation criteria for echocardiographic diagnosis of rheumatic heart disease\u2014An evidence-based guideline","volume":"9","author":"Wilson","year":"2012","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1038\/s41569-023-00940-9","article-title":"2023 World Heart Federation guidelines for the echocardiographic diagnosis of rheumatic heart disease","volume":"21","author":"Rwebembera","year":"2024","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.5152\/TurkArchPediatr.2024.23162","article-title":"Echocardiographic Screening of Rheumatic Heart Disease: Current Concepts and Challenges","volume":"59","year":"2024","journal-title":"Turk. Arch. Pediatr."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.echo.2023.03.001","article-title":"The Use of Artificial Intelligence Guidance for Rheumatic Heart Disease Screening by Novices","volume":"36","author":"Peck","year":"2023","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.echo.2022.09.017","article-title":"Machine learning for pediatric echocardiographic mitral regurgitation detection","volume":"36","author":"Edwards","year":"2023","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e031257","DOI":"10.1161\/JAHA.123.031257","article-title":"Using Artificial Intelligence for Rheumatic Heart Disease Detection by Echocardiography: Focus on Mitral Regurgitation","volume":"13","author":"Brown","year":"2024","journal-title":"J. Am. Heart Assoc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/s41746-023-00811-0","article-title":"Self-supervised learning for medical image classification: A systematic review and implementation guidelines","volume":"6","author":"Huang","year":"2023","journal-title":"npj Digit. Med."},{"key":"ref_15","unstructured":"Ding, C., and Wu, C. (2024). Self-Supervised Learning for Biomedical Signal Processing: A Systematic Review on ECG and PPG Signals. medRxiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4592","DOI":"10.1093\/eurheartj\/ehad456","article-title":"Severe aortic stenosis detection by deep learning applied to echocardiography","volume":"44","author":"Holste","year":"2023","journal-title":"Eur. Heart J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, R., Agrawal, A., and Agarwal, P. (2024, January 29\u201330). Self-Supervised Representation Learning for Diagnosis of Cardiac Abnormalities on Echocardiograms. Proceedings of the 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC), Debre Tabor, Ethiopia.","DOI":"10.1109\/ICOCWC60930.2024.10470471"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/s43856-024-00538-3","article-title":"Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning","volume":"4","author":"Holste","year":"2024","journal-title":"Commun. Med."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, B., Bunting, K.V., Brind, D., Thorley, A., Karwath, A., Lu, W., Zhou, D., Wang, X., and Mobley, A.R. (2024). Development of Automated Neural Network Prediction for Echocardiographic Left ventricular Ejection Fraction. arXiv.","DOI":"10.3389\/fmed.2024.1354070"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Kainth, K., Zhou, A., Deyer, T.W., Fayad, Z.A., Greenspan, H., and Mei, X. (2024). A review of self-supervised, generative, and few-shot deep learning methods for data-limited magnetic resonance imaging segmentation. NMR Biomed., 37.","DOI":"10.1002\/nbm.5143"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Linguraru, M.G., Dou, Q., Feragen, A., Giannarou, S., Glocker, B., Lekadir, K., and Schnabel, J.A. (2024). EchoFM: A View-Independent Echocardiogram Model for the Detection of Pulmonary Hypertension. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2024, Proceedings of the 27th International Conference, Marrakesh, Morocco, 6\u201310 October 2024, Springer Nature.","DOI":"10.1007\/978-3-031-72111-3"},{"key":"ref_22","unstructured":"Jacob, A.J., Borgohain, I., Chitiboi, T., Sharma, P., Comaniciu, D., and Rueckert, D. (2024). Towards a vision foundation model for comprehensive assessment of Cardiac MRI. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, S., Ren, H., Charton, J., Hu, J., Gonzalez, C.A.M., Khambhati, J., Cheng, J., DeFrancesco, J., A Waheed, A., and Marciniak, S. (2024). Assessment of valve regurgitation severity via contrastive learning and multi-view video integration. Phys. Med. Biol., 69.","DOI":"10.1088\/1361-6560\/ad22a4"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Alavi, A., Li, M., and Zhang, X. (2023). Self-Supervised Contrastive Learning for Medical Time Series: A Systematic Review. Sensors, 23.","DOI":"10.3390\/s23094221"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hu, R., Chen, J., and Zhou, L. (2023). Spatiotemporal self-supervised representation learning from multi-lead ECG signals. Biomed. Signal Process. Control, 84.","DOI":"10.1016\/j.bspc.2023.104772"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1109\/JBHI.2023.3246241","article-title":"sCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification","volume":"27","author":"Le","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_27","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. arXiv."},{"key":"ref_28","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2024). DINOv2: Learning Robust Visual Features without Supervision. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6739","DOI":"10.1109\/TAI.2024.3485524","article-title":"MTECC: A Multitask Learning Framework for Esophageal Cancer Analysis","volume":"5","author":"An","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Azizi, S., Mustafa, B., Ryan, F., Beaver, Z., Freyberg, J., Deaton, J., Loh, A., Karthikesalingam, A., Kornblith, S., and Chen, T. (2021). Big Self-Supervised Models Advance Medical Image Classification. arXiv.","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zeng, D., Wang, Z., Shi, Y., and Hu, J. (2022). Distributed Contrastive Learning for Medical Image Segmentation. arXiv.","DOI":"10.1016\/j.media.2022.102564"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/s11633-022-1406-4","article-title":"A Review of Predictive and Contrastive Self-supervised Learning for Medical Images","volume":"20","author":"Wang","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Charton, J., Ren, H., Kim, S., Gonzalez, C.M., Khambhati, J., Cheng, J., DeFrancesco, J., Waheed, A., Marciniak, S., and Mour, F. (2023). Multi-task Learning for Hierarchically-Structured Images: Study on Echocardiogram View Classification. Simplifying Medical Ultrasound, Proceedings of the 4th International Workshop, ASMUS 2023, Vancouver, BC, Canada, 8 October 2023, Springer.","DOI":"10.1007\/978-3-031-44521-7_18"},{"key":"ref_34","unstructured":"Ahmadi Amiri, S.N. (2023). Detection and Severity Assessment of Aortic Stenosis Using Machine Learning. [Ph.D. Thesis, University of British Columbia]. Available online: https:\/\/open.library.ubc.ca\/soa\/cIRcle\/collections\/ubctheses\/24\/items\/1.0433730."},{"key":"ref_35","first-page":"1","article-title":"Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMap, and PaCMAP for Data Visualization","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","unstructured":"Damrich, S., B\u00f6hm, J.N., Hamprecht, F.A., and Kobak, D. (2023). From $t$-SNE to UMAP with contrastive learning. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Mittal, M., Praveen, G., Guru, P., Devadas, R.M., Ambreen, L., and Kumar, V. (2024, January 24\u201327). Dimensionality Reduction Using UMAP and TSNE Technique. Proceedings of the 2024 Second International Conference on Advances in Information Technology (ICAIT), Chikkamagaluru, India.","DOI":"10.1109\/ICAIT61638.2024.10690797"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Orlov, A., Akhmetshin, T., Horvath, D., Marcou, G., and Varnek, A. (2024). From High Dimensions to Human Comprehension: Exploring Dimensionality Reduction for Chemical Space Visualization. ChemRxiv.","DOI":"10.26434\/chemrxiv-2024-pxb4f"},{"key":"ref_39","unstructured":"Draganov, A., and Dohn, S. (2024). Relating tSNE and UMAP to Classical Dimensionality Reduction. arXiv."},{"key":"ref_40","first-page":"463","article-title":"A hybrid model for data visualization using linear algebra methods and machine learning algorithm","volume":"33","author":"Ali","year":"2024","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Holste, G., Oikonomou, E.K., Mortazavi, B.J., Coppi, A., Faridi, K.F., Miller, E.J., Forrest, J.K., McNamara, R.L., Ohno-Machado, L., and Yuan, N. (2022). Automated detection of severe aortic stenosis using single-view echocardiography: A self-supervised ensemble learning approach. medRxiv.","DOI":"10.1101\/2022.08.30.22279413"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sangha, V., Khunte, A., Holste, G., Mortazavi, B.J., Wang, Z., Oikonomou, E.K., and Khera, R. (2023). Biometric Contrastive Learning for Data-Efficient Deep Learning from Electrocardiographic Images. medRxiv.","DOI":"10.1101\/2023.09.13.23295494"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/4\/97\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:00:12Z","timestamp":1760029212000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/4\/97"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,25]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["jimaging11040097"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11040097","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,25]]}}}