{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T07:05:10Z","timestamp":1779433510106,"version":"3.53.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>To evaluate whether routinely measured MRI-based patellofemoral joint morphometric parameters can support diagnostic modeling of selected adolescent knee pathologies and to compare a conventional multivariable logistic regression baseline with machine-learning approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective single-center pilot diganostic modeling study included 168 adolescents (97 girls, 71 boys, mean age 15.5\u202f\u00b1\u202f1.7\u202fyears) who underwent knee MRI between January 2018 and December 2024 because of anterior knee pain or suspected patellofemoral structural abnormality. Thirteen patellofemoral morphometric parameters were measured by two radiologists. Three binary MRI endpoints were modeled: composite chondromalacia, a composite endpoint of ACL injury or patellar bone bruise, and patellar retinacular lesion. Baseline multivariable logistic regression was compared with machine-learning approaches using chronological training, validation, and test splits. Additional gradient-boosting comparators were evaluated, and uncertainty was quantified using bootstrap confidence intervals on the independent test set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In multivariable logistic regression, no individual continuous morphometric predictor reached statistical significance for any endpoint. After correction of the model-selection procedure, predictive performance proved endpoint-specific rather than uniformly strong. For composite chondromalacia, discrimination remained weak. For the ACL injury\/patellar bone bruise composite, machine-learning models showed only modest improvement in point estimates over logistic regression, but confidence intervals for differences crossed zero. The strongest reproducible signal was observed for patellar retinacular lesions. After correction of model selection and bootstrap-based uncertainty estimation, a morphometric-only CatBoost model achieved an AUC of 0.85 (95% CI 0.68\u20130.97) and balanced accuracy of 0.79 (95% CI 0.61\u20130.94), while a morphometric-only LightGBM model achieved an AUC of 0.84 (95% CI 0.64\u20130.97) and balanced accuracy of 0.76 (95% CI 0.59\u20130.88).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>In adolescents, routine patellofemoral morphometrics do not provide uniformly strong diagnostic discrimination across all MRI-defined knee pathologies studied here. Their most convincing predictive value was observed for patellar retinacular lesions, whereas performance for composite chondromalacia and the ACL injury\/patellar bone bruise composite remained limited. These findings support a narrower interpretation of clinical utility and justify further validation in larger external cohorts.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1808422","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T06:09:54Z","timestamp":1779430194000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MRI-based morphometric analysis of the patellofemoral joint: diagnostic modeling of knee pathologies in adolescents"],"prefix":"10.3389","volume":"9","author":[{"given":"Dusan","family":"Spasic","sequence":"first","affiliation":[{"name":"Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]},{"name":"Department of Pharmacology, Clinical Pharmacology, and Toxicology, Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goran","family":"Djuricic","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]},{"name":"Department of Diagnostic Imaging, University Children's Hospital","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jelena Djokic","family":"Kovac","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]},{"name":"Clinic for Digestive Surgery, University Clinical Centre of Serbia","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bojan","family":"Bukva","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]},{"name":"Orthopedic Surgery and Traumatology Department, University Children's Hospital","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Radlovic","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Belgrade","place":["Belgrade, Serbia"]},{"name":"Orthopedic Surgery and Traumatology Department, University Children's Hospital","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milos","family":"Maletic","sequence":"additional","affiliation":[{"name":"Serbian Institute of Sports and Sports Medicine","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanislav","family":"Rajkovic","sequence":"additional","affiliation":[{"name":"Institute for Orthopaedics \u201cBanjica\u201d, Medical Faculty, University of Belgrade","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marko","family":"Radulovi\u0107","sequence":"additional","affiliation":[{"name":"Department of Experimental Oncology, Institute for Oncology & Radiology of Serbia","place":["Belgrade, Serbia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s00167-012-2274-1","article-title":"Patella instability: building bridges across the ocean a historic review","volume":"21","author":"Arendt","year":"2013","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"5736","DOI":"10.1007\/s00330-024-10596-9","article-title":"Knee landmarks detection via deep learning for automatic imaging evaluation of trochlear dysplasia and patellar height","volume":"34","author":"Barbosa","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1186\/s13018-023-03837-y","article-title":"Development of machine learning models aiming at knee osteoarthritis diagnosing: an MRI radiomics analysis","volume":"18","author":"Cui","year":"2023","journal-title":"J. Orthop. Surg. Res."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/BF01552649","article-title":"Factors of patellar instability: an anatomic radiographic study","volume":"2","author":"Dejour","year":"1994","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"ref5","first-page":"131","author":"Dunnhofer","year":"2021"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1201\/9780429246593","volume-title":"An Introduction to the Bootstrap","author":"Efron","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"186","DOI":"10.3928\/0090-4481-19910401-07","article-title":"Chronic anterior knee pain in the adolescent","volume":"20","author":"Goldberg","year":"1991","journal-title":"Pediatr. Ann."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3390\/medicina54020021","article-title":"The patello-femoral joint degeneration and the shape of the patella in the population needing an arthroscopic procedure","volume":"54","author":"Gudas","year":"2018","journal-title":"Medicina"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1148\/101.1.101","article-title":"Patella position in the normal knee joint","volume":"101","author":"Insall","year":"1971","journal-title":"Radiology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"23259671251358390","DOI":"10.1177\/23259671251358390","article-title":"Comparative analysis of 3 machine learning methods for identifying minimal predictors of patellofemoral instability risk factors","volume":"13","author":"Kwon","year":"2025","journal-title":"Orthop. J. Sports Med."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1177\/0363546511433028","article-title":"Observer agreement on the Dejour trochlear dysplasia classification","volume":"40","author":"Lippacher","year":"2012","journal-title":"Am. J. Sports Med."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"815","DOI":"10.3390\/bioengineering10070815","article-title":"Deep learning for automated measurement of patellofemoral anatomic landmarks","volume":"10","author":"Liu","year":"2023","journal-title":"Bioengineering"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1535519","DOI":"10.3389\/fspor.2025.1535519","article-title":"A machine learning-based radiomics approach for differentiating patellofemoral osteoarthritis from non-patellofemoral osteoarthritis using Q-Dixon MRI","volume":"7","author":"Lyu","year":"2025","journal-title":"Front. in Sports Active Liv."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"11390","DOI":"10.1038\/s41598-024-62143-7","article-title":"Three-dimensional magnetic resonance imaging-based statistical shape analysis and machine learning-based prediction of patellofemoral instability","volume":"14","author":"Nagawa","year":"2024","journal-title":"Sci. Rep."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1007\/s00167-017-4597-4","article-title":"Anatomic reconstruction of the medial patellofemoral ligament in children and adolescents using a pedicled quadriceps tendon graft shows favourable results at a minimum of 2-year follow-up","volume":"26","author":"Nelitz","year":"2017","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1148\/radiology.216.3.r00se38858","article-title":"Femoral trochlear dysplasia: MR findings","volume":"216","author":"Pfirrmann","year":"2000","journal-title":"Radiology"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"7637","DOI":"10.1038\/s41467-024-51888-4","article-title":"Learning co-plane attention across MRI sequences for diagnosing twelve types of knee abnormalities","volume":"15","author":"Qiu","year":"2024","journal-title":"Nat. Commun."},{"key":"ref19","article-title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","author":"Qu","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.knee.2005.06.003","article-title":"The tibial tuberosity\u2013trochlear groove distance; a comparative study between CT and MRI scanning","volume":"13","author":"Schoettle","year":"2006","journal-title":"Knee"},{"key":"ref21","author":"Song","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e0237587","DOI":"10.1371\/journal.pone.0237587","article-title":"FeAture explorer (FAE): a tool for developing and comparing radiomics models","volume":"15","author":"Song","year":"2020","journal-title":"PLoS One"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1136\/bjsports-2017-098418","article-title":"Relationship between growth, maturation and musculoskeletal conditions in adolescents: a systematic review","volume":"52","author":"Swain","year":"2018","journal-title":"Br. J. Sports Med."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1177\/02841851221092164","article-title":"Automatic diagnosis and grading of patellofemoral osteoarthritis from the axial radiographic view: a deep learning-based approach","volume":"64","author":"Tuya","year":"2023","journal-title":"Acta Radiol."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"319","DOI":"10.3109\/17453674108988818","article-title":"Roentgenographs and anatomic studies on the femoropatellar joint: with special reference to chondromalacia patellae","volume":"12","author":"Wibeeg","year":"1941","journal-title":"Acta Orthop. Scand."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1808422\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T06:09:55Z","timestamp":1779430195000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1808422\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":25,"alternative-id":["10.3389\/frai.2026.1808422"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1808422","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"article-number":"1808422"}}