{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:25:54Z","timestamp":1793132754171,"version":"4.5.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Knee osteoarthritis (KOA) is a progressive musculoskeletal disorder and a leading cause of disability worldwide. Early and accurate diagnosis is crucial for timely intervention; however, conventional manual grading using radiographs is prone to variability. Artificial intelligence (AI)-based computer-aided diagnostic (CAD) systems offer potential to improve detection and grading accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and evaluate an AI-based diagnostic grading system for KOA using X-ray imaging and transfer learning techniques, with the goal of assisting clinicians and medical trainees in early and precise diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>An experimental cross-sectional study was conducted using 301 radiographs (602 knee images) collected from the Social Security Teaching Hospital, Lahore. The dataset included Kellgren\u2013Lawrence (KL) grades 0\u20134, with labeling based on pain observation and expert orthopedic assessment. Image preprocessing involved binary thresholding, morphological operations, knee isolation, normalization, and zero-padding. Transfer learning with DenseNet-121 served as the base network, augmented by convolutional and fully connected layers. Performance was evaluated against other deep learning architectures (DenseNet201, ResNet50, MobileNet) and classical machine learning algorithms (SVM, decision tree, random forest). Metrics included accuracy, area under the curve (AUC), precision, and recall.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>DenseNet-121 demonstrated the most robust performance among the tested models, achieving an accuracy of 68.85%, an AUC of 85.67%, a precision of 68.33%, and a recall of 67.21% on the independent test set. Comparative models, including DenseNet201 and MobileNet, exhibited lower accuracies (\u224860 to 61%) and AUCs (\u224880 to 83%). Machine learning approaches underperformed, with a maximum accuracy of 55.73%. The primary challenges included dataset imbalance and the difficulty in distinguishing between grade 0 and grade 1 due to overlapping radiographic features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed AI-based CAD system shows promise for supporting KOA diagnosis and grading in clinical practice, particularly for training junior clinicians and radiologists. Despite limitations of dataset imbalance and restricted single-center data, transfer learning with DenseNet-121 achieved reliable performance. Future work should focus on expanding datasets to encompass diverse populations, incorporating multimodal inputs, and validating generalizability across various clinical settings. This approach highlights the growing role of AI in musculoskeletal imaging and its potential to enhance early disease detection and patient care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1707588","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:21:50Z","timestamp":1761805310000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Potential of AI-based diagnostic grading system for knee osteoarthritis"],"prefix":"10.3389","volume":"12","author":[{"given":"Saman","family":"Shahid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aamir","family":"Wali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aatir","family":"Javaid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahid","family":"Zikria","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onur","family":"Osman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jawad","family":"Rasheed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,30]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.pmr.2022.08.019","article-title":"Evidence-based approach to orthobiologics for osteoarthritis and other joint disorders","volume":"34","author":"Herman","year":"2023","journal-title":"Phys Med Rehab Clin"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"6405","DOI":"10.3390\/ijms24076405","article-title":"Knee osteoarthritis: epidemiology, pathogenesis, and mesenchymal stem cells: what else is new? An update","volume":"24","author":"Giorgino","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.2147\/OARRR.S390778","article-title":"Assessing the burden of osteoarthritis in Africa and the Middle East: a rapid evidence assessment","volume":"15","author":"Al Saleh","year":"2023","journal-title":"Open Access Rheumatol"},{"key":"ref4","first-page":"677","article-title":"The effect of running on osteoarthrosis of the weight-bearing joints of","volume":"16","author":"G\u00e1likov\u00e1","year":"2023","journal-title":"reconstruction"},{"key":"ref5","first-page":"25","article-title":"Management of knee osteoarthritis through ayurveda: a case study","volume":"2","author":"Shukla","year":"2023","journal-title":"AYUSH: Int Res J Ayurveda Teach Assoc"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.4314\/ejhs.v33i1.19","article-title":"Explaining the concept of self-care competence and its dimensions in elderly women with knee osteoarthritis in Iran: a qualitative study","volume":"33","author":"Kooranian","year":"2023","journal-title":"Ethiop J Health Sci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1177\/03635465221143999","article-title":"Ankle pain after medial opening-wedge high Tibial osteotomy in patients with knee osteoarthritis and concurrent ankle osteoarthritis","volume":"51","author":"Kim","year":"2023","journal-title":"Am J Sports Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"101836","DOI":"10.1016\/j.berh.2023.101836","article-title":"The burden of osteoarthritis: is it a rising problem?","volume":"37","author":"Scheuing","year":"2023","journal-title":"Best Pract Res Clin Rheumatol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1002\/msc.1814","article-title":"Quality of life in individuals with knee osteoarthritis versus asymptomatic individuals","volume":"21","author":"Obara","year":"2023","journal-title":"Musculoskeletal Care"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1002\/acr.24886","article-title":"Loss of productivity-adjusted life-years in working-age Australians due to knee osteoarthritis: a life-table modeling approach","volume":"75","author":"Jin","year":"2023","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"335","DOI":"10.3389\/fpubh.2017.00335","article-title":"Age-related diseases and clinical and public health implications for the 85 years old and over population","volume":"5","author":"Jaul","year":"2017","journal-title":"Front Public Health"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"101549","DOI":"10.1016\/j.berh.2020.101549","article-title":"Global health policy in the 21st century: challenges and opportunities to arrest the global disability burden from musculoskeletal health conditions","volume":"34","author":"Briggs","year":"2020","journal-title":"Best Pract Res Clin Rheumatol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1759720X19893800","DOI":"10.1177\/1759720X19893800","article-title":"Treat-to-target strategy for knee osteoarthritis. International technical expert panel consensus and good clinical practice statements","volume":"11","author":"Migliore","year":"2019","journal-title":"Ther Adv Musculoskelet Dis"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1136\/annrheumdis-2013-204627","article-title":"The global burden of rheumatoid arthritis: estimates from the global burden of disease 2010 study","volume":"73","author":"Cross","year":"2014","journal-title":"Ann Rheum Dis"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IISA.2019.8900714","article-title":"Exploring deep learning capabilities in knee osteoarthritis case study for classification","volume-title":"2019 10th international conference on information, intelligence, systems and applications (IISA)","author":"Christodoulou","year":"2019"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological assessment of osteo-arthrosis","volume":"16","author":"Kellgren","year":"1957","journal-title":"Ann Rheum Dis"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/rheumatology\/39.suppl_2.3","article-title":"Epidemiology of rheumatic diseases","volume":"39","author":"Sangha","year":"2000","journal-title":"Rheumatology"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1136\/ard.2007.079020","article-title":"Differences in descriptions of Kellgren and Lawrence grades of knee osteoarthritis","volume":"67","author":"Schiphof","year":"2008","journal-title":"Ann Rheum Dis"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1759720X231158198","DOI":"10.1177\/1759720X231158198","article-title":"The application of machine learning in early diagnosis of osteoarthritis: a narrative review","volume":"15","author":"Xuan","year":"2023","journal-title":"Ther Adv Musculoskelet Dis"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13075-021-02634-4","article-title":"A deep learning method for predicting knee osteoarthritis radiographic progression from MRI","volume":"23","author":"Schiratti","year":"2021","journal-title":"Arthritis Res Ther"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00521-020-05459-5","article-title":"Dense neural networks in knee osteoarthritis classification: a study on accuracy and fairness","volume":"35","author":"Moustakidis","year":"2020","journal-title":"Neural Comput Appl"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"6189","DOI":"10.3390\/s21186189","article-title":"A novel hybrid approach based on deep cnn features to detect knee osteoarthritis","volume":"21","author":"Mahum","year":"2021","journal-title":"Sensors"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"3173","DOI":"10.1007\/s11831-023-09899-9","article-title":"On the analyses of medical images using traditional machine learning techniques and convolutional neural networks","volume":"30","author":"Iqbal","year":"2023","journal-title":"Arch Comput Methods Eng"},{"key":"ref24","article-title":"Application of machine learning in melanoma detection and the identification of \u2018ugly duckling\u2019 and suspicious naevi: a review","author":"Zegair","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e1490","DOI":"10.7717\/peerj-cs.1490","article-title":"Classification of Alzheimer\u2019s disease stages from magnetic resonance images using deep learning","volume":"9","author":"Mora-Rubio","year":"2023","journal-title":"PeerJ Comput Sci"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1694","DOI":"10.3390\/s23031694","article-title":"Convolution neural networks and self-attention learners for Alzheimer dementia diagnosis from brain MRI","volume":"23","author":"Carcagn\\`\\i","year":"2023","journal-title":"Sensors"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1148\/radiol.2020192091","article-title":"Prediction of total knee replacement and diagnosis of osteoarthritis by using deep learning on knee radiographs: data from the osteoarthritis initiative","volume":"296","author":"Leung","year":"2020","journal-title":"Radiology"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3094136\/v1","article-title":"Mind-body exercises for mild to moderate knee osteoarthritis: non-inferiority study protocol for a parallel, single-center randomized controlled trial","author":"Liu","year":"2023"},{"key":"ref29","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Huang","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/info8030091","article-title":"Deep transfer learning for modality classification of medical images","volume":"8","author":"Yu","year":"2017","journal-title":"Information"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-46805-6","article-title":"Object recognition with gradient-based learning","volume-title":"DA Forsyth, JL Mundy, V di Ges\u00f9 and R Cipolla, editors. Shape, contour and grouping in computer vision","author":"Forsyth","year":"1999"},{"key":"ref32","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","volume":"2","author":"LeCun","year":"1989","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"96930","DOI":"10.1109\/ACCESS.2022.3204395","article-title":"ADD-net: an effective deep learning model for early detection of Alzheimer disease in MRI scans","volume":"10","author":"Fareed","year":"2022","journal-title":"IEEE Access"},{"key":"ref34","first-page":"1","article-title":"Evaluating performance of software defect prediction models using area under precision-recall curve (AUC-PR)","volume-title":"2019 2nd international conference on advancements in computational sciences (ICACS)","author":"Khan","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"7085","DOI":"10.3390\/molecules27207085","article-title":"Dad-net: classification of Alzheimer\u2019s disease using adasyn oversampling technique and optimized neural network","volume":"27","author":"Ahmed","year":"2022","journal-title":"Molecules"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2195","DOI":"10.3390\/biomedicines10092195","article-title":"A robust deep model for classification of peptic ulcer and other digestive tract disorders using endoscopic images","volume":"10","author":"Mahmood","year":"2022","journal-title":"Biomedicine"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/ICoIAS61634.2023.00032","article-title":"Detection of Alzheimer\u2019s disease using deep learning: an optimized approach","volume-title":"2023 6th international conference on intelligent autonomous systems (ICoIAS)","author":"Ahmed","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"e37743","DOI":"10.1016\/j.heliyon.2024.e37743","article-title":"Computational imaging for rapid detection of grade-I cerebral small vessel disease (cSVD)","volume":"10","author":"Shahid","year":"2024","journal-title":"Heliyon"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/978-3-031-19818-2_12","article-title":"Adaptive spatial-BCE loss for weakly supervised semantic segmentation","volume-title":"Computer vision\u2013ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, proceedings, part XXIX","author":"Wu","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/s11547-022-01476-7","article-title":"Automatic detection and classification of knee osteoarthritis using deep learning approach","volume":"127","author":"Abdullah","year":"2022","journal-title":"Radiol Med"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"611","DOI":"10.3390\/diagnostics12030611","article-title":"A comprehensive survey on bone segmentation techniques in knee osteoarthritis research: from conventional methods to deep learning","volume":"12","author":"Ahmed","year":"2022","journal-title":"Diagnostics"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"2243","DOI":"10.1002\/jor.23519","article-title":"Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative","volume":"35","author":"Ashinsky","year":"2017","journal-title":"J Orthop Res"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/4931437","article-title":"Emergence of deep learning in knee osteoarthritis diagnosis","volume":"2021","author":"Yeoh","year":"2021","journal-title":"Comput Intell Neurosci"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12891-021-04722-7","article-title":"Automating classification of osteoarthritis according to Kellgren\u2013Lawrence in the knee using deep learning in an unfiltered adult population","volume":"22","author":"Olsson","year":"2021","journal-title":"BMC Musculoskelet Disord"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"e190065","DOI":"10.1148\/ryai.2020190065","article-title":"Automated classification of radiographic knee osteoarthritis severity using deep neural networks","volume":"2","author":"Thomas","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"e18636","DOI":"10.1097\/MD.0000000000018636","article-title":"Comprehensive application of high tibial osteotomy, chronic distraction tissue regeneration, and computer-assisted external fixation in the treatment of severe knee osteoarthritis: a case report","volume":"99","author":"Zhang","year":"2020","journal-title":"Medicine (Baltimore)"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1707588\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:21:53Z","timestamp":1761805313000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1707588\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,30]]},"references-count":46,"alternative-id":["10.3389\/fmed.2025.1707588"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1707588","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,30]]},"article-number":"1707588"}}