{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T08:48:43Z","timestamp":1792226923755,"version":"4.4.0"},"reference-count":29,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Diagnosing Rotator Cuff Tears (RCTs) via Magnetic Resonance Imaging (MRI) is clinically challenging due to complex 3D anatomy and significant interobserver variability. Traditional slice-centric Convolutional Neural Networks (CNNs) often fail to capture the necessary volumetric context for accurate grading. This study aims to develop and validate the Patient-Aware Vision Transformer (Pa-ViT), an explainable deep-learning framework designed for the automated, patient-level classification of RCTs (Normal, Partial-Thickness, and Full-Thickness). Methods: A large-scale retrospective dataset comprising 2447 T2-weighted coronal shoulder MRI examinations was utilized. The proposed Pa-ViT framework employs a Vision Transformer (ViT-Base) backbone within a Weakly-Supervised Multiple Instance Learning (MIL) paradigm to aggregate slice-level semantic features into a unified patient diagnosis. The model was trained using a weighted cross-entropy loss to address class imbalance and was benchmarked against widely used CNN architectures and traditional machine-learning classifiers. Results: The Pa-ViT model achieved a high overall accuracy of 91% and a macro-averaged F1-score of 0.91, significantly outperforming the standard VGG-16 baseline (87%). Notably, the model demonstrated superior discriminative power for the challenging Partial-Thickness Tear class (ROC AUC: 0.903). Furthermore, Attention Rollout visualizations confirmed the model\u2019s reliance on genuine anatomical features, such as the supraspinatus footprint, rather than artifacts. Conclusions: By effectively modeling long-range dependencies, the Pa-ViT framework provides a robust alternative to traditional CNNs. It offers a clinically viable, explainable decision support tool that enhances diagnostic sensitivity, particularly for subtle partial-thickness tears.<\/jats:p>","DOI":"10.3390\/jcm15030928","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:21:40Z","timestamp":1769505700000},"page":"928","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Patient-Level Classification of Rotator Cuff Tears on Shoulder MRI Using an Explainable Vision Transformer Framework"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8495-3161","authenticated-orcid":false,"given":"Murat","family":"A\u015f\u00e7\u0131","sequence":"first","affiliation":[{"name":"Department of Orthopedics and Traumatology, Faculty of Medicine, Bilecik \u015eeyh Edebali University, Bilecik 11230, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3388-4047","authenticated-orcid":false,"given":"Sergen","family":"A\u015f\u0131k","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Faculty of Engineering and Architecture, Eski\u015fehir Osmangazi University, Eski\u015fehir 26040, T\u00fcrkiye"},{"name":"Center of Intelligent Systems Applications Research, Eski\u015fehir Osmangazi University, Eski\u015fehir 26040, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5589-2032","authenticated-orcid":false,"given":"Ahmet","family":"Yaz\u0131c\u0131","sequence":"additional","affiliation":[{"name":"Center of Intelligent Systems Applications Research, Eski\u015fehir Osmangazi University, Eski\u015fehir 26040, T\u00fcrkiye"},{"name":"Department of Computer Engineering, Faculty of Engineering and Architecture, Eski\u015fehir Osmangazi University, Eski\u015fehir 26040, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0547-4597","authenticated-orcid":false,"given":"\u0130rfan","family":"Okumu\u015fer","sequence":"additional","affiliation":[{"name":"Department of Radiology, Yunus Emre State Hospital, Ministry of Health, Eski\u015fehir 26190, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e220132","DOI":"10.1148\/ryai.220132","article-title":"A Deep Learning Algorithm for Automatic 3D Segmentation of Rotator. Cuff Muscle and Fat from Clinical MRI Scans","volume":"5","author":"Riem","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1097\/RLI.0000000000000951","article-title":"Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI","volume":"58","author":"Lin","year":"2023","journal-title":"Investig. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1016\/j.jse.2024.05.056","article-title":"Does Surgical Intervention Alter the Natural History of Degenerative Rotator Cuff Tears? Comparative Analysis from a Prospective Longitudinal Study","volume":"34","author":"Hill","year":"2025","journal-title":"J. Shoulder Elbow Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1016\/j.acra.2023.09.012","article-title":"Fully Automated Approach for Diagnosis of Supraspinatus Tendon Tear on Shoulder MRI by Using Deep Learning","volume":"31","author":"Cui","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lee, K.C., Cho, Y., Ahn, K.S., Park, H.J., Kang, Y.S., Lee, S., Kim, D., and Kang, C.H. (2023). Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI. Diagnostics, 13.","DOI":"10.3390\/diagnostics13203254"},{"key":"ref_6","first-page":"70","article-title":"Clinical and Biological Aspects of Rotator Cuff Tears","volume":"3","author":"Spoliti","year":"2013","journal-title":"Muscles Ligaments Tendons J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.pmr.2022.12.002","article-title":"Nonoperative Treatment of Rotator Cuff Tears","volume":"34","author":"Dickinson","year":"2023","journal-title":"Phys. Med. Rehabil. Clin. N. Am."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.jor.2023.11.011","article-title":"Advancements in the Diagnosis and Management of Rotator Cuff Tears. The Role of Artificial Intelligence","volume":"47","author":"Hsu","year":"2024","journal-title":"J. Orthop."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"15065","DOI":"10.1038\/s41598-021-93026-w","article-title":"Deep-Learning Framework and Computer Assisted Fatty Infiltration Analysis for the Supraspinatus Muscle in MRI","volume":"11","author":"Ro","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 Statement: An Updated Guideline for Reporting Systematic Reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103864","DOI":"10.1016\/j.medengphy.2022.103864","article-title":"ViVGG19: Novel Exemplar Deep Feature Extraction-Based Shoulder Rotator Cuff Tear and Biceps Tendinosis Detection Using Magnetic Resonance Images","volume":"110","author":"Key","year":"2022","journal-title":"Med. Eng. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"506","DOI":"10.2214\/AJR.21.26577","article-title":"Image Quality and Diagnostic Performance of Accelerated Shoulder MRI with Deep Learning\u2013Based Reconstruction","volume":"218","author":"Hahn","year":"2021","journal-title":"Am. J. Roentgenol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Saavedra, J.P., Droppelmann, G., Garc\u00eda, N., Jorquera, C., and Feijoo, F. (2023). High-Accuracy Detection of Supraspinatus Fatty Infiltration in Shoulder MRI Using Convolutional Neural Network Algorithms. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1070499"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5587","DOI":"10.1007\/s00330-023-09523-1","article-title":"Shoulder MRI-Based Radiomics for Diagnosis and Severity Staging Assessment of Surgically Treated Supraspinatus Tendon Tears","volume":"33","author":"Zhan","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1097\/JSA.0000000000000371","article-title":"Artificial Intelligence and Machine Learning in Rotator Cuff Tears","volume":"31","author":"Rodriguez","year":"2023","journal-title":"Sports Med. Arthrosc. Rev."},{"key":"ref_16","first-page":"e50103","article-title":"Role of Magnetic Resonance Imaging (MRI) in the Diagnosis of Rotator Cuff Injuries and Correlation with Arthroscopy Findings","volume":"15","author":"Jose","year":"2023","journal-title":"Cureus"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"685","DOI":"10.5312\/wjo.v12.i9.685","article-title":"Machine Learning in Orthopaedic Surgery","volume":"12","author":"Lalehzarian","year":"2021","journal-title":"World J. Orthop."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1302\/2046-3758.127.BJR-2023-0111.R1","article-title":"Artificial Intelligence in Orthopaedic Surgery Exploring Its Applications, Limitations, and Future Direction","volume":"12","author":"Powling","year":"2023","journal-title":"Bone Jt. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e15804","DOI":"10.1016\/j.heliyon.2023.e15804","article-title":"Detection of the Rotator Cuff Tears Using a Novel Convolutional Neural Network from Magnetic Resonance Image (MRI)","volume":"9","author":"Esfandiari","year":"2023","journal-title":"Heliyon"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1007\/s00256-022-04008-6","article-title":"Evaluation of a Deep Learning Method for the Automated Detection of Supraspinatus Tears on MRI","volume":"51","author":"Yao","year":"2022","journal-title":"Skelet. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3538","DOI":"10.1007\/s00330-023-10392-x","article-title":"MRI-Based Automated Multitask Deep Learning System to Evaluate Supraspinatus Tendon Injuries","volume":"34","author":"Ni","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"15632","DOI":"10.1038\/s41598-020-72357-0","article-title":"Automated Rotator Cuff Tear Classification Using 3D Convolutional Neural Network","volume":"10","author":"Shim","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Lee, J.H., Oh, K.S., Yoon, J.P., Seo, A., Jeong, Y.J., and Chung, S.W. (2023). Automated 3-Dimensional MRI Segmentation for the Posterosuperior Rotator Cuff Tear Lesion Using Deep Learning Algorithm. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0284111"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1093\/ehjdh\/ztaf029","article-title":"Multi-Instance Learning with Attention Mechanism for Coronary Artery Stenosis Detection on Coronary Computed Tomography Angiography","volume":"6","author":"Gupta","year":"2025","journal-title":"Eur. Heart J. Digit. Health"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5791","DOI":"10.1109\/TCSVT.2025.3528625","article-title":"Focus Your Attention: Multiple Instance Learning with Attention Modification for Whole Slide Pathological Image Classification","volume":"35","author":"Cheng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_26","first-page":"292","article-title":"MRI-Based Diagnosis of Rotator Cuff Tears Using Deep Learning and Weighted Linear Combinations","volume":"126","author":"Kim","year":"2020","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.arthro.2023.06.018","article-title":"Artificial Intelligence Aids Detection of Rotator Cuff Pathology: A Systematic Review","volume":"40","author":"Zhan","year":"2024","journal-title":"Arthrosc. J. Arthrosc. Relat. Surg."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kim, H., Shin, K., Kim, H., Lee, E.S., Chung, S.W., Koh, K.H., and Kim, N. (2022). Can Deep Learning Reduce the Time and Effort Required for Manual Segmentation in 3D Reconstruction of MRI in Rotator Cuff Tears?. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0274075"},{"key":"ref_29","unstructured":"Liu, H., Georgescu, B., Zhang, Y., Yoo, Y., Baumgartner, M., Gao, R., Wang, J., Zhao, G., Gibson, E., and Comaniciu, D. (2025). Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification. arXiv."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/3\/928\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:35:19Z","timestamp":1769506519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/3\/928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jcm15030928"],"URL":"https:\/\/doi.org\/10.3390\/jcm15030928","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]}}}