[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126098-en":3,"doc-seo-126098-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126098,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","A machine learning-based radiomics approach for differentiating patellofemoral osteoarthritis from non-patellofemoral osteoarthritis using Q-Dixon MRI - Original Research","A prospective diagnostic study evaluated machine learning-based quadriceps fat pad (QFP) radiomics to distinguish patellofemoral osteoarthritis (PFOA) from non-PFOA in patients with anterior knee pain using Q-Dixon MRI. Three models were built: a proton density-weighted image model, a fat fraction model, and a merged model. After ANOVA-based feature selection and logistic regression classification, performance was compared across training, internal, and external test cohorts using AUC with DeLong testing. The merged model performed best, and fat fraction features showed stronger predictive value.","TYPE Original Research PUBLISHED 17 January 2025  \nDOI 10.3389/fspor.2025.1535519  \nEDITED BY  \nRong Lu,  \nFudan University, China  \nREVIEWED BY  \nXiao ’ao Xue,  \nFudan University, China Weijun Tang,  \nFudan University, China  \n*CORRESPONDENCE  \nYongliang Li  \n [1829@shtrhospital.com](1829@shtrhospital.com)[ ](1829@shtrhospital.com)Weiwu Yao  \n [YWW4142@shtrhospital.com](YWW4142@shtrhospital.com);  \n [yaoweiwuhuan@163.com](yaoweiwuhuan@163.com)  \n†These authors have contributed equally to this work  \nRECEIVED 27 November 2024  \nACCEPTED 06 January 2025  \nPUBLISHED 17 January 2025  \nCITATION  \nLyu L, Ren J, Lu W, Zhong J, Song Y, Li Y and  \nYao W (2025) A machine learning-based radiomics approach for differentiating patellofemoral osteoarthritis from non-patellofemoral osteoarthritis using Q-Dixon MRI.  \nFront. Sports Act. Living 7:1535519 .  \ndoi: 10.3389/fspor.2025.1535519  \nCOPYRIGHT  \n© 2025 Lyu, Ren, Lu, Zhong, Song, Li and Yao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nA machine learning-based radiomics approach for differentiating patellofemoral osteoarthritis from  \nnon-patellofemoral osteoarthritis using Q-Dixon MRI  \nLiangjing Lyu1, Jing Ren1, Wenjie Lu1, Jingyu Zhong1, Yang Song2, Yongliang Li1*† and Weiwu Yao1*†  \n1Department of Radiology, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China, 2MR Research Collaboration Team, Siemens Healthineers Ltd., Shanghai, China  \nThis prospective diagnostic study aimed to assess the utility of machine learningbased quadriceps fat pad (QFP) radiomics in distinguishing patellofemoral osteoarthritis (PFOA) from non-PFOA using Q-Dixon MRI in patients presenting with anterior knee pain. This diagnostic accuracy study retrospectively analyzed data from 215 patients (mean age: 54.2 ± 11.3 years; 113 women) . Three predictive models were evaluated: a proton densityweighted image model, a fat fraction model, and a merged model. Featureselection was conducted using analysis of variance, and logistic regression was applied for classification. Data were collected from training, internal, and external test cohorts. Radiomics features were extracted from Q-Dixon MRI sequences to distinguish PFOA from non-PFOA. The diagnostic performance of the three models was compared using the area under the curve (AUC) values analyzed with the Delong test. In the training set (109 patients) and internal test set (73 patients), the merged model exhibited optimal performance, with AUCs of 0.836 [95% confidence interval (CI): 0.762–0.910] and 0 . 826 (95% CI: 0 .722–0. 929), respectively. In the external test set (33 patients), the model achieved an AUC of 0.885 (95% CI: 0.768–1.000), with sensitivity and specificity values of 0 . 833 and 0 . 933, respectively (p \u003C 0 . 001) . Fat fraction features exhibited a stronger predictive value than shape-related features. Machine learning-based QFP radiomics using Q-Dixon MRI accurately distinguishes PFOA from non-PFOA, providing a non-invasive diagnostic approach for patients with anterior knee pain.  \nKEYWORDS  \nanterior knee pain, patellofemoral osteoarthritis, Q-Dixon MRI, radiomics, machine learning, fat fraction, quadriceps fat pad  \nAbbreviations  \nAKP, anterior knee pain; AKPS, anterior knee pain scale; AUC, area under the curve; BMI, body mass index; FF, fat fraction; ICC, intraclass correlation coefficient; IFP, infrapatellar fat pad; IPAQ, International Physical Activity Questionnaire; KOA, knee osteoarthritis; MOAKS, MRI osteoarthritis knee score; MRS, magnetic resonance spectroscopy; PDWI, proton density-weighted image; PFOA","cbCair0ZJPmR1jBl","https://ap.wps.com/l/cbCair0ZJPmR1jBl","pdf",15522230,5,1,10,"English","en",105,"# Introduction\n## Anterior knee pain and clinical context\n## Patellofemoral osteoarthritis and need for quantitative assessment\n# Radiomics and model development\n## Quadriceps fat pad radiomics concept\n## Feature selection and classification strategy\n# Diagnostic performance evaluation\n## Cohort design and model comparison\n## AUC-based results and sensitivity/specificity","[{\"question\":\"What imaging data and target region were used to build the radiomics models?\",\"answer\":\"The models used Q-Dixon MRI radiomics features extracted from the quadriceps fat pad (QFP) to differentiate PFOA from non-PFOA.\"},{\"question\":\"How were the predictive models constructed and classified?\",\"answer\":\"Feature selection was performed using analysis of variance, and logistic regression was used for classification. Three models were evaluated: PD-weighted, fat fraction, and a merged model.\"},{\"question\":\"Which model showed the best diagnostic performance across datasets?\",\"answer\":\"The merged model achieved the optimal performance in the training and internal test sets, and it also performed well in the external test set with an AUC of 0.885.\"}]","A machine learning-based radiomics approach for differentiating patellofemoral osteoarthritis from non-patellofemoral osteoarthritis using Q-Dixon MRI - Original Research | PDF",1785903089,25,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"a-machine-learning-based-radiomics-approach-for-differentiating-patellofemoral-osteoarthritis-from-non-patellofemoral-osteoarthritis-using-q-dixon-mri-original-research","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/a-machine-learning-based-radiomics-approach-for-differentiating-patellofemoral-osteoarthritis-from-non-patellofemoral-osteoarthritis-using-q-dixon-mri-original-research/126098/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What imaging data and target region were used to build the radiomics models?","Question",{"text":77,"@type":78},"The models used Q-Dixon MRI radiomics features extracted from the quadriceps fat pad (QFP) to differentiate PFOA from non-PFOA.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How were the predictive models constructed and classified?",{"text":82,"@type":78},"Feature selection was performed using analysis of variance, and logistic regression was used for classification. Three models were evaluated: PD-weighted, fat fraction, and a merged model.",{"name":84,"@type":75,"acceptedAnswer":85},"Which model showed the best diagnostic performance across datasets?",{"text":86,"@type":78},"The merged model achieved the optimal performance in the training and internal test sets, and it also performed well in the external test set with an AUC of 0.885.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":22,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]