{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:32:16Z","timestamp":1784039536735,"version":"3.55.0"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Knee Ailments, such as meniscus injuries, bother millions globally, with research showing that more than 14% of the population above 40 years lives with meniscus-related conditions. Conventional diagnosis techniques, like manual MRI interpretation, are labour-intensive, error-prone, and dependent on skilled radiologists, making an automatic and more accurate alternative indispensable. Current deep-learning solutions heavily depend on CNNs, which perform poorly in long-range dependencies and global contextual info. We proposed MV2SwimNet, a hybrid of MobileNetV2 and Swin Transformer, integrating Window Multi-Head Self-Attention (W-MSA) and Multi-Stage Hierarchical Representation (MSHR), efficiently incorporating both local and global features towards enhanced diagnostic capability. Our strategy utilizes the efficiency of lightweight MobileNetV2 coupled with a hierarchical architecture and self-attention-based Swin Transformer, enabling better spatial representation and advanced feature extraction. W-MSA allows our model to process MRI scans effectively by attending to the corresponding regions of images. In contrast, MSHR adjusts feature representations across different levels in a way that allows for progressive and robust learning in stages. We tested MV2SwimNet on two sets using 3-fold cross-validation and achieved 99.94% and 96.04% accuracy on dataset1 and dataset2, which beats state-of-the-art techniques. These results confirm MV2SwimNet efficiency, robustness, and real-world application potential in medicine, providing a highly accurate, automated medical diagnosis tool for knee disease detection. The code of the proposed method can be accessed through the URL: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Visheshtanwar\/MV2SwimNet\" xlink:type=\"simple\">https:\/\/github.com\/Visheshtanwar\/MV2SwimNet<\/jats:ext-link><\/jats:p>","DOI":"10.1371\/journal.pone.0330444","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T17:26:46Z","timestamp":1756315606000},"page":"e0330444","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["MV2SwimNet: A lightweight transformer-based hybrid model for knee meniscus tears detection"],"prefix":"10.1371","volume":"20","author":[{"given":"Vishesh","family":"Tanwar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3400-3504","authenticated-orcid":true,"given":"Bhisham","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhirendra Prasad","family":"Yadav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian L.","family":"Webber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abolfazl","family":"Mehbodniya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"issue":"11","key":"pone.0330444.ref001","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.3390\/diagnostics14111090","article-title":"A comprehensive evaluation of deep learning models on knee MRIs for the diagnosis and classification of meniscal tears: a systematic review and meta-analysis","volume":"14","author":"A Botnari","year":"2024","journal-title":"Diagnostics (Basel)"},{"issue":"2","key":"pone.0330444.ref002","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/j.arthro.2020.09.012","article-title":"Diagnostic performance of artificial intelligence for detection of anterior cruciate ligament and meniscus tears: a systematic review","volume":"37","author":"KN Kunze","year":"2021","journal-title":"Arthroscopy"},{"issue":"2","key":"pone.0330444.ref003","doi-asserted-by":"crossref","first-page":"537","DOI":"10.3390\/diagnostics12020537","article-title":"Knee injury detection using deep learning on mri studies: a systematic review","volume":"12","author":"A Siouras","year":"2022","journal-title":"Diagnostics (Basel)"},{"issue":"2","key":"pone.0330444.ref004","first-page":"691","article-title":"Knee meniscus segmentation and tear detection based on magnitic resonacis images: a review of literature","volume":"13","author":"AA Mahdi","year":"2022","journal-title":"Int J Nonlinear Analysis Appl"},{"issue":"3","key":"pone.0330444.ref005","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/s00256-023-04416-2","article-title":"Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears","volume":"53","author":"SM Santomartino","year":"2024","journal-title":"Skeletal Radiol"},{"issue":"9","key":"pone.0330444.ref006","doi-asserted-by":"crossref","first-page":"5954","DOI":"10.1007\/s00330-024-10625-7","article-title":"Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis","volume":"34","author":"Y Zhao","year":"2024","journal-title":"Eur Radiol"},{"issue":"9","key":"pone.0330444.ref007","article-title":"A Comprehensive review on the diagnosis of knee injury by deep learning-based magnetic resonance imaging","volume":"15","author":"ND Shetty","year":"2023","journal-title":"Cureus"},{"key":"pone.0330444.ref008","doi-asserted-by":"crossref","DOI":"10.2196\/40504","article-title":"Digital health applications to establish a remote diagnosis of orthopedic knee disorders: scoping review","volume":"25","author":"SC van Eijck","year":"2023","journal-title":"J Med Internet Res"},{"issue":"8","key":"pone.0330444.ref009","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.3390\/tomography10080094","article-title":"Deep learning-assisted automatic diagnosis of anterior cruciate ligament tear in knee magnetic resonance images","volume":"10","author":"X Wang","year":"2024","journal-title":"Tomography"},{"key":"pone.0330444.ref010","article-title":"Meniscus injury prediction model based on metric learning","volume":"10","author":"Y Wang","year":"2024","journal-title":"PeerJ Comput Sci"},{"issue":"1","key":"pone.0330444.ref011","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1186\/s40001-022-00883-w","article-title":"Automated meniscus segmentation and tear detection of knee MRI with a 3D mask-RCNN","volume":"27","author":"Y-Z Li","year":"2022","journal-title":"Eur J Med Res"},{"key":"pone.0330444.ref012","doi-asserted-by":"crossref","first-page":"144349","DOI":"10.1109\/ACCESS.2023.3344456","article-title":"Deep learning-based meniscus tear detection from accelerated MRI","volume":"11","author":"F Harman","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0330444.ref013","doi-asserted-by":"crossref","first-page":"104523","DOI":"10.1016\/j.bspc.2022.104523","article-title":"Development of artificial intelligence-based clinical decision support system for diagnosis of meniscal injury using magnetic resonance images","volume":"82","author":"Y-T Chou","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"pone.0330444.ref014","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.jot.2022.05.006","article-title":"Identification and diagnosis of meniscus tear by magnetic resonance imaging using a deep learning model","volume":"34","author":"J Li","year":"2022","journal-title":"J Orthop Translat"},{"issue":"1","key":"pone.0330444.ref015","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1186\/s12891-022-05468-6","article-title":"Development of convolutional neural network model for diagnosing meniscus tear using magnetic resonance image","volume":"23","author":"H Shin","year":"2022","journal-title":"BMC Musculoskelet Disord"},{"key":"pone.0330444.ref016","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/978-3-031-16919-9_7","article-title":"Diagnosing knee injuries from MRI with transformer based deep learning","author":"G Sezen","year":"2022","journal-title":"Predictive Intelligence in Medicine. Cham: Springer"},{"issue":"4","key":"pone.0330444.ref017","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.3390\/make3040050","article-title":"Detection and classification of knee injuries from MR images using the MRNet dataset with progressively operating deep learning methods","volume":"3","author":"AC Kara","year":"2021","journal-title":"MAKE"},{"issue":"1","key":"pone.0330444.ref018","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s10278-024-01198-4","article-title":"Fully and weakly supervised deep learning for meniscal injury classification, and location based on MRI","volume":"38","author":"K Jiang","year":"2025","journal-title":"J Imaging Inform Med"},{"key":"pone.0330444.ref019","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ejmp.2021.02.010","article-title":"Meniscal lesion detection and characterization in adult knee MRI: A deep learning model approach with external validation","volume":"83","author":"B Rizk","year":"2021","journal-title":"Phys Med"},{"key":"pone.0330444.ref020","doi-asserted-by":"crossref","first-page":"102655","DOI":"10.1016\/j.bspc.2021.102655","article-title":"A deep learning approach for the quantification of lower tear meniscus height","volume":"68","author":"X Deng","year":"2021","journal-title":"Biomed Signal Process Control"},{"issue":"6","key":"pone.0330444.ref021","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1007\/s00417-021-05078-3","article-title":"Automatic screening of tear meniscus from lacrimal duct obstructions using anterior segment optical coherence tomography images by deep learning","volume":"259","author":"H Imamura","year":"2021","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"pone.0330444.ref022","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/978-981-15-8335-3_2","article-title":"Detection of anterior cruciate ligament tear using deep learning and machine learning techniques","author":"V Kapoor","year":"2021","journal-title":"Lecture notes on data engineering and communications technologies. Singapore: Springer"},{"issue":"3","key":"pone.0330444.ref023","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1007\/s00167-021-06838-8","article-title":"Artificial intelligence in orthopedics: three strategies for deep learning with orthopedic specific imaging","volume":"30","author":"S Ko","year":"2022","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"2","key":"pone.0330444.ref024","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1007\/s00167-022-07117-w","article-title":"Risk factors for secondary meniscus tears can be accurately predicted through machine learning, creating a resource for patient education and intervention","volume":"31","author":"K Jurgensmeier","year":"2023","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"pone.0330444.ref025","first-page":"1","article-title":"Med-SeAM: medical context aware self-supervised learning framework for anomaly classification in knee MRI.","author":"A Daydar","year":"2024","journal-title":"Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing"},{"issue":"11","key":"pone.0330444.ref026","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002699","article-title":"Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet","volume":"15","author":"N Bien","year":"2018","journal-title":"PLoS Med"},{"key":"pone.0330444.ref027","first-page":"784","article-title":"Knee injury detection using MRI with efficiently-layered network (ELNet).","author":"CH Tsai","year":"2020","journal-title":"Proceedings of the Third Conference on Medical Imaging with Deep Learning"},{"issue":"4","key":"pone.0330444.ref028","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1109\/TAI.2023.3299883","article-title":"Self-supervised representation learning for knee injury diagnosis from magnetic resonance data","volume":"5","author":"S Manna","year":"2024","journal-title":"IEEE Trans Artif Intell"},{"key":"pone.0330444.ref029","doi-asserted-by":"crossref","first-page":"106616","DOI":"10.1016\/j.bspc.2024.106616","article-title":"Anterior cruciate ligament tear detection using gated recurrent unit and flexible fitness dependent optimizer","volume":"96","author":"Y Zuo","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"pone.0330444.ref030","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/978-981-19-7041-2_16","article-title":"Deep learning approach for segmenting and classifying knee osteoarthritis using MR images.","author":"SA Revathi","year":"2023","journal-title":"Algorithms for Intelligent Systems. Singapore: Springer"},{"issue":"5","key":"pone.0330444.ref031","doi-asserted-by":"crossref","first-page":"2752","DOI":"10.3390\/app15052752","article-title":"Automatic meniscus segmentation using YOLO-based deep learning models with ensemble methods in knee MRI images","volume":"15","author":"MA \u015eim\u015fek","year":"2025","journal-title":"Appl Sci"},{"key":"pone.0330444.ref032","doi-asserted-by":"crossref","first-page":"0126","DOI":"10.34133\/cbsystems.0126","article-title":"New insights optimize landing strategies to reduce lower limb injury risk","volume":"5","author":"D Xu","year":"2024","journal-title":"Cyborg Bionic Syst"},{"key":"pone.0330444.ref033","doi-asserted-by":"crossref","first-page":"107761","DOI":"10.1016\/j.cmpb.2023.107761","article-title":"Accurately and effectively predict the ACL force: utilizing biomechanical landing pattern before and after-fatigue","volume":"241","author":"D Xu","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0330444.ref034","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition.","author":"K He","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T17:26:53Z","timestamp":1756315613000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330444"}},"subtitle":[],"editor":[{"given":"Yaodong","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0330444","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,27]]}}}