{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T14:08:37Z","timestamp":1790518117631,"version":"4.1.0"},"reference-count":32,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Knee cartilage injury (KCI) poses significant challenges in the early clinical diagnosis process, primarily due to its high incidence, the complexity of healing, and the limited sensitivity of initial imaging modalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to employ magnetic resonance imaging and machine learning methods to enhance the classification accuracy of the classifier for KCI, improve the existing network structure, and demonstrate important clinical application value.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed methodology is a multidimensional feature cross-level fusion classification network driven by the large separable kernel attention, which enables high-precision hierarchical diagnosis of KCI through deep learning. The network first fuses shallow high-resolution features with deep semantic features via the cross-level fusion module. Then, the large separable kernel attention module is embedded in the YOLOv8 network. This network utilizes the combined optimization of depth-separable and point-by-point convolutions to enhance features at multiple scales, thereby dramatically improving the hierarchical characterization of cartilage damage. Finally, five classifications of knee cartilage injuries are performed by classifiers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      To overcome the limitations of network models trained with single-plane images, this study presents the first hospital-based multidimensional magnetic resonance imaging real dataset for KCI, on which the classification accuracy is 99.7%, the Kappa statistic is 99.6%, the\n                      <jats:italic>F<\/jats:italic>\n                      -measure is 99.7%, the sensitivity is 99.7%, and the specificity is 99.9%. The experimental results validate the feasibility of the proposed method.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The experimental outcomes confirm that the proposed methodology not only achieves exceptional performance in classifying knee cartilage injuries but also offers substantial improvements over existing techniques. This underscores its potential for clinical deployment in enhancing diagnostic precision and efficiency.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/79748","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T21:13:07Z","timestamp":1766005987000},"page":"e79748-e79748","source":"Crossref","is-referenced-by-count":1,"title":["Large Separable Kernel Attention\u2013Driven Multidimensional Feature Cross-Level Fusion Classification Network of Knee Cartilage Injury: Algorithm Development and Validation"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9570-2029","authenticated-orcid":false,"given":"Lirong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8659-6205","authenticated-orcid":false,"given":"Hang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7492-5237","authenticated-orcid":false,"given":"Yating","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1016\/j.joca.2018.10.016","article-title":"Spatial distribution and temporal progression of T2 relaxation time values in knee cartilage prior to the onset of cartilage lesions \u2013 data from the Osteoarthritis Initiative (OAI)","volume":"27","author":"Kretzschmar","journal-title":"Osteoarthr Cartil"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2022.02.180","article-title":"Is there a relationship between knee biomechanics and pain in people with knee osteoarthritis? A systematic review and meta-analysis","volume":"30","author":"Hutchison","journal-title":"Osteoarthr Cartil"},{"issue":"Suppl 3","key":"R3","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/ar846","article-title":"Cell biology of synovial inflammation and secondary osteoporosis in rheumatoid arthritis","volume":"5","author":"Tanaka","journal-title":"Arthritis Res Ther"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1002\/jmri.28105","article-title":"Left-right intensity asymmetries vary depending on scanner model for FLAIR and T weighted MRI images","volume":"56","author":"Arani","journal-title":"J Magn Reson Imaging"},{"issue":"5","key":"R5","doi-asserted-by":"publisher","first-page":"E1662","DOI":"10.1002\/lary.29222","article-title":"Cholesteatoma localization using fused diffusion\u2010weighted images and thin\u2010slice T2 weighted images","volume":"131","author":"Benson","journal-title":"Laryngoscope"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1002\/jmri.27825","article-title":"Abdominal T2\u2010weighted imaging and T2 mapping using a variable Flip angle radial turbo spin\u2010Echo technique","volume":"55","author":"Keerthivasan","journal-title":"J Magn Reson Imaging"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1177\/0363546514559912","article-title":"Correlation of meniscal and articular cartilage injuries in children and adolescents with timing of anterior cruciate ligament reconstruction","volume":"43","author":"Anderson","journal-title":"Am J Sports Med"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1002\/jmri.28451","article-title":"Age\u2010dependent changes in knee cartilage T1, T2, and T1p simultaneously measured using MRI fingerprinting","volume":"57","author":"Kijowski","journal-title":"J Magn Reson Imaging"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bios.2024.116633","article-title":"Machine learning-assisted label-free colorectal cancer diagnosis using plasmonic needle-endoscopy system","volume":"264","author":"Jo","journal-title":"Biosens Bioelectron"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100399","article-title":"An improved SqueezeNet model for the diagnosis of lung cancer in CT scans","volume":"10","author":"Tsivgoulis","journal-title":"Mach Learn Appl"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1007\/s40031-025-01217-0","article-title":"Robust deep learning approach for colon cancer detection using MobileNet","author":"Jaware","journal-title":"J Inst Eng India Ser B"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105878","article-title":"Medical image segmentation and reconstruction of prostate tumor based on 3D AlexNet","volume":"200","author":"Chen","journal-title":"Comput Methods Programs Biomed"},{"issue":"12","key":"R13","doi-asserted-by":"publisher","first-page":"5349","DOI":"10.1109\/TNNLS.2020.2966319","article-title":"Why resnet works? Residuals generalize","volume":"31","author":"He","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103295","article-title":"Motor imagery EEG signal classification using image processing technique over GoogLeNet deep learning algorithm for controlling the robot manipulator","volume":"72","author":"Ak","journal-title":"Biomed Signal Process Control"},{"issue":"6","key":"R15","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1016\/j.knee.2020.09.014","article-title":"Clinical outcomes of primary anatomic all-inside Anterior Cruciate Ligament reconstruction using the TransLateral technique: a minimum one-year follow-up study","volume":"27","author":"Abdul","journal-title":"Knee"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103191","article-title":"Automated knee ligament injuries classification method based on exemplar pyramid local binary pattern feature extraction and hybrid iterative feature selection","volume":"71","author":"Demir","journal-title":"Biomed Signal Process Control"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103810","article-title":"Diabetic retinopathy classification using a novel DAG network based on multi-feature of fundus images","volume":"77","author":"Fang","journal-title":"Biomed Signal Process Control"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/62774","article-title":"Convolutional neural network models for visual classification of pressure ulcer stages: cross-sectional study","volume":"13","author":"Lei","journal-title":"JMIR Med Inform"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103343","article-title":"Interpretable breast cancer diagnosis using histopathology and lesion mask as domain concepts conditional simulation ultrasonography","volume":"123","author":"Dai","journal-title":"Inf Fusion"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103446","article-title":"Interpretable breast cancer identification by multi-view synergistic feature fusion interaction in dense breast tissue","volume":"125","author":"Dai","journal-title":"Inf Fusion"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","DOI":"10.2196\/34896","article-title":"Leveraging artificial intelligence to improve the diversity of dermatological skin color pathology: protocol for an algorithm development and validation study","volume":"11","author":"Rezk","journal-title":"JMIR Res Protoc"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104229","article-title":"Dual-stream parallel model of cartilage injury diagnosis based on local centroid optimization","volume":"80","author":"Fang","journal-title":"Biomed Signal Process Control"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104687","article-title":"Multi-level classification of knee cartilage lesion in multimodal MRI based on deep learning","volume":"83","author":"Zhang","journal-title":"Biomed Signal Process Control"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Ezhilin Freeda S Hariharan T Dinesh R Muthuaravind M . Classification of different stages of eczema disease using yolov8. Presented at: 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA); Nov 6-8, 2024:1575-1579; Coimbatore, India. 2024.[doi: 10.1109\/ICECA63461.2024.10801168]","DOI":"10.1109\/ICECA63461.2024.10801168"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Agulan RZ Magsumbol JAV Rosales MA . Detection of dental caries based on GV black classification utilizing YOLOv8 from X-ray images. Presented at: 2024 IEEE International Conference on Imaging Systems and Techniques (IST); Oct 14-16, 2024:1-6; Tokyo, Japan. 2024.[doi: 10.1109\/IST63414.2024.10759223]","DOI":"10.1109\/IST63414.2024.10759223"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.bonr.2024.101801","article-title":"Classification of AO\/OTA 31A\/B femur fractures in X-ray images using YOLOv8 and advanced data augmentation techniques","volume":"22","author":"Marullo","journal-title":"Bone Rep"},{"issue":"7","key":"R27","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1007\/s11517-024-03057-4","article-title":"A novel machine learning model for breast cancer detection using mammogram images","volume":"62","author":"Kalpana","journal-title":"Med Biol Eng Comput"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109182","article-title":"Aero-engine prognosis strategy based on multi-scale feature fusion and multi-task parallel learning","volume":"234","author":"Zhou","journal-title":"Reliab Eng Syst Safe"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121352","article-title":"Large separable kernel attention: rethinking the large kernel attention design in CNN","volume":"236","author":"Lau","journal-title":"Expert Syst Appl"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Islam J Furqon EN Farady I Rani Alex JS Kuo CC Lin CY . Integrating stable diffusion for improved alzheimer\u2019s disease classification: insights from MRI images and yolov8. Presented at: 2024 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan); Jul 9-11, 2024:303-304; Taichung, Taiwan. 2024.[doi: 10.1109\/ICCE-Taiwan62264.2024.10674478]","DOI":"10.1109\/ICCE-Taiwan62264.2024.10674478"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Palanivel N S D G LP B S M SM . The art of yolov8 algorithm in cancer diagnosis using medical imaging. Presented at: 2023 International Conference on System, Computation, Automation and Networking (ICSCAN); Nov 17-18, 2023:1-6; Puducherry, India. 2023.[doi: 10.1109\/ICSCAN58655.2023.10395046]","DOI":"10.1109\/ICSCAN58655.2023.10395046"},{"key":"R32","unstructured":"National Health Commission, Ministry of Education, Ministry of Science and Technology, State Administration of Traditional Chinese Medicine. Circular on issuing the ethical review measures for life sciences and medical research involving humans [guo wei ke jiao fa (2023) no. 4]. National Health Commission. 2023. URL: http:\/\/www.gov.cn\/zhengce\/zhengceku\/2023-02\/28\/content_5743658.htm [Accessed 20-06-2024]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e79748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:12:57Z","timestamp":1782843177000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e79748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":32,"URL":"https:\/\/doi.org\/10.2196\/79748","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]},"article-number":"v13i5e79748"}}