{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:07:50Z","timestamp":1789103270215,"version":"build-2803163510"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Ultrasonography (US) represents a practical and accessible imaging modality for rotator cuff tear (RCT) evaluation, yet diagnostic accuracy remains constrained by operator experience and the sonographic ambiguity of partial-thickness tears. Deep learning (DL) models applied to US imaging and machine learning models derived from clinical variables have each demonstrated independent promise, yet their integration within a unified diagnostic framework has not been systematically explored.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and validate a multimodal DL model integrating US imaging with structured clinical examination data for RCT detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort of 947 patients presenting with shoulder pain who underwent both shoulder US and MRI was partitioned into training and testing sets at a 7:3 ratio. Patients with MRI-confirmed supraspinatus RCT were designated RCT-positive, while those with supraspinatus tendinopathy or subacromial bursitis were designated RCT-negative. Four model configurations were developed: a clinical-only model, a single-view US model, a dual-view US model, and a full multimodal model (MM) combining dual-view US with clinical variables through feature-level fusion. All models were trained using five-fold cross-validation and evaluated on the testing set for discriminative performance, calibration, and clinical utility. Model interpretability was assessed using Gradient-weighted Class Activation Mapping (Grad-CAM) for the image encoder and SHapley Additive exPlanations (SHAP) for the clinical encoder.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 947 patients, 370 (39.1%) were RCT-positive and 577 (60.9%) were RCT-negative. MM achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.935, with sensitivity of 0.946, specificity of 0.786, and F1 score of 0.830, significantly outperforming all unimodal configurations. Decision curve analysis confirmed superior net benefit of MM across clinically relevant threshold probabilities. Grad-CAM heatmaps demonstrated anatomically coherent attention within the supraspinatus tendon, while SHAP analysis identified the drop arm test, external rotation lag sign, and empty can test as the dominant clinical predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed multimodal DL framework offers a validated and interpretable tool for MRI-independent RCT diagnosis, with potential applicability in resource-constrained clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1884047","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:33:26Z","timestamp":1789101206000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal deep learning integrating ultrasonographic and clinical data for enhanced rotator cuff tear identification"],"prefix":"10.3389","volume":"17","author":[{"given":"Ye","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huining","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyou","family":"Xin","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Wuxi Ninth People\u2019s Hospital Affiliated to Soochow University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1186\/s13244-023-01551-1","article-title":"Enhancing prediction of supraspinatus\/infraspinatus tendon complex injuries through integration of deep visual features and clinical information: a multicenter two-round assessment study","volume":"14","author":"Alike","year":"2023","journal-title":"Insights Imaging"},{"key":"B2","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s40477-024-00894-9","article-title":"Ultrasound definition of subacromial chronic \"fibro-adhesive\" bursitis and its treatment via ultrasound guided hydrodilation: a prospective pilot study","volume":"27","author":"Al Khayyat","year":"2024","journal-title":"J. Ultrasound"},{"key":"B3","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.jor.2019.08.027","article-title":"Partial thickness rotator cuff tears: Patient demographics and surgical trends within a large insurance database","volume":"17","author":"Ardeljan","year":"2020","journal-title":"J. Orthop."},{"key":"B4","doi-asserted-by":"publisher","first-page":"196","DOI":"10.4103\/jmu.jmu_182_21","article-title":"Deep learning for detecting supraspinatus calcific tendinopathy on ultrasound images","volume":"30","author":"Chiu","year":"2022","journal-title":"J. Med. Ultrasound"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1177\/23259671211035106","article-title":"Diagnostic accuracy of ultrasonography for rotator cuff tears: A systematic review and meta-analysis","volume":"9","author":"Farooqi","year":"2021","journal-title":"Orthop. J. Sports Med."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.2106\/jbjs.Oa.24.00097","article-title":"Disparities in rotator cuff tear progression definitions and rates: A systematic review","volume":"9","author":"Garcia","year":"2024","journal-title":"JB JS Open Access"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1751","DOI":"10.3390\/jcm15051751","article-title":"Artificial intelligence in orthopaedics: Clinical performance, limitations, and translational readiness-a review","volume":"15","author":"Glinkowski","year":"2026","journal-title":"J. Clin. Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/s0140-6736(11)61878-3","article-title":"Urbanisation and health in China","volume":"379","author":"Gong","year":"2012","journal-title":"Lancet"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.56065","article-title":"Rotator cuff tears: Correlation between clinical examination, magnetic resonance imaging and arthroscopy","volume":"16","author":"Gowda","year":"2024","journal-title":"Cureus"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-059175","article-title":"Prevalence of rotator cuff tendon tears and symptoms in a Chingford general population cohort, and the resultant impact on UK health services: a cross-sectional observational study","volume":"12","author":"Hinsley","year":"2022","journal-title":"BMJ Open"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.2106\/jbjs.D.02100","article-title":"Accuracy of office-based ultrasonography of the shoulder for the diagnosis of rotator cuff tears","volume":"87","author":"Iannotti","year":"2005","journal-title":"JBJS"},{"key":"B12","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1097\/phm.0000000000000566","article-title":"The diagnostic accuracy of special tests for rotator cuff tear: The ROW cohort study","volume":"96","author":"Jain","year":"2017","journal-title":"Am. J. Phys. Med. Rehabil."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1007\/s00167-022-07298-4","article-title":"Machine learning model successfully identifies important clinical features for predicting outpatients with rotator cuff tears","volume":"31","author":"Li","year":"2023","journal-title":"Knee Surg. Sports Traumatol. Arthrosc"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108635","article-title":"A review of deep learning-based information fusion techniques for multimodal medical image classification","volume":"177","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.jor.2013.01.008","article-title":"Prevalence of symptomatic and asymptomatic rotator cuff tears in the general population: From mass-screening in one village","volume":"10","author":"Minagawa","year":"2013","journal-title":"J. Orthop."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.4103\/njcp.njcp_325_23","article-title":"The efficiency of gray-level ultrasound histogram analysis in patients with supraspinatus tendinopathy","volume":"26","author":"Nalbant","year":"2023","journal-title":"Niger. J. Clin. Pract."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1007\/s00167-012-2105-4","article-title":"Learning curve of office-based ultrasonography for rotator cuff tendons tears","volume":"21","author":"Ok","year":"2013","journal-title":"Knee Surg. Sports Traumatol. Arthrosc"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.5435\/jaaos-d-20-01092","article-title":"Diagnosis and management of partial thickness rotator cuff tears: A comprehensive review","volume":"29","author":"Plancher","year":"2021","journal-title":"J. Am. Acad. Orthop. Surg."},{"key":"B19","doi-asserted-by":"publisher","first-page":"79","DOI":"10.5397\/cise.2022.01417","article-title":"Partial-thickness rotator cuff tears: a review of current literature on evaluation and management","volume":"27","author":"Radhakrishnan","year":"2024","journal-title":"Clin. Shoulder Elb"},{"key":"B20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vision"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2519\/jospt.2025.13611","article-title":"Rotator cuff imaging abnormalities in asymptomatic shoulders: A systematic review","volume":"55","author":"Sanders","year":"2025","journal-title":"J. Orthop. Sports Phys. Ther."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1016\/j.crad.2011.05.007","article-title":"Diagnostic accuracy of ultrasound for rotator cuff tears in adults: a systematic review and meta-analysis","volume":"66","author":"Smith","year":"2011","journal-title":"Clin. Radiol."},{"key":"B23","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B24","doi-asserted-by":"publisher","first-page":"498","DOI":"10.2106\/00004623-200004000-00005","article-title":"Ultrasonography of the rotator cuff : A comparison of ultrasonographic and arthroscopic findings in one hundred consecutive cases*","volume":"82","author":"Teefey","year":"2000","journal-title":"JBJS"},{"key":"B25","doi-asserted-by":"publisher","first-page":"59","DOI":"10.2147\/orr.S348726","article-title":"Optimal management of partial thickness rotator cuff tears: Clinical considerations and practical management","volume":"14","author":"Thangarajah","year":"2022","journal-title":"Orthop. Res. Rev."},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"Cbam: Convolutional block attention module","author":"Woo","year":"2018"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2708","DOI":"10.1016\/j.arthro.2024.12.024","article-title":"Diagnostic accuracy and interobserver reliability of rotator cuff tear detection with ultrasonography are improved with attentional deep learning","volume":"41","author":"Wu","year":"2025","journal-title":"Arthroscopy"},{"key":"B28","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.jse.2009.04.006","article-title":"Prevalence and risk factors of a rotator cuff tear in the general population","volume":"19","author":"Yamamoto","year":"2010","journal-title":"J. Shoulder Elbow Surg."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1016\/j.jse.2021.02.013","article-title":"Supraspinatus tears: predictability of magnetic resonance imaging findings based on clinical examination","volume":"30","author":"Yazigi Junior","year":"2021","journal-title":"J. Shoulder Elbow Surg."},{"key":"B30","doi-asserted-by":"publisher","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":"Arthroscopy"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1321939","article-title":"Risk factors for symptomatic rotator cuff tears: a retrospective case-control study","volume":"10","author":"Zhao","year":"2023","journal-title":"Front. Med. (Lausanne)"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.2214\/ajr.21.25606","article-title":"The evolving roles of MRI and ultrasound in first-line imaging of rotator cuff injuries","volume":"217","author":"Zoga","year":"2021","journal-title":"AJR Am. J. Roentgenol."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1884047\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:33:36Z","timestamp":1789101216000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1884047\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":32,"alternative-id":["10.3389\/fphys.2026.1884047"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1884047","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"1884047"}}