[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123252-en":3,"doc-seo-123252-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123252,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Cross-Vendor Reproducibility of Radiomics-based Machine Learning Models for Computer-aided Diagnosis - Research report","Reproducibility of machine-learning models for prostate cancer detection across different MRI vendors remains a major barrier to clinical trust. The study trains support vector machines and random forest models on radiomic features from T2-weighted MRI using Pyradiomics and MRCradiomics, applying MRMR feature selection and pursuing feature fusion to strengthen multimodal decision support. Results show an AUC drop for vendor shifts: SVM decreases from 0.74 on the Multi-Improd Siemens dataset to 0.60 on the Philips test set. Overall, findings highlight the promise and remaining challenges of multimodal radiomics integration for generalizable AI diagnostic tools.","arXiv :2407 . 18060v 1 [ cs .LG] 25 Jul 2024  \nCross-Vendor Reproducibility of Radiomics-based Machine Learning Models for Computer-aided Diagnosis  \nJatin Chaudhary* 1 , Ivan Jambor2 , Hannu Aronen2 , Otto Ettala3 , Jani Saunavaara4 , Peter Boström3 , Jukka Heikkonen 1 , Rajeev Kanth5 , and Harri  \nMerisaari2  \n1 Department of Computing, University of Turku, Turku, Finland  \n2 Department of Diagnostic Radiology, University of Turku, Turku, Finland  \n3 Department of Urology, University of Turku, Turku, Finland  \n4 Department of Medical Physics, Turku University Hospital, Turku, Finland  \n5 Savonia University of Applied Sciences, Kuopio, Finland  \n*[jatin.chaudhary@utu.fi](jatin.chaudhary@utu.fi)  \nAbstract. Background: The reproducibility of machine-learning models in prostate cancer detection across different MRI vendors remains a significant challenge.  \nMethods: This study investigates Support Vector Machines (SVM) and Random Forest (RF) models trained on radiomic features extracted from T2-weighted MRI images using Pyradiomics and MRCradiomics libraries. Feature selection was performed using the maximum relevance minimum redundancy (MRMR) technique. We aimed to enhance clinical decision support through multimodal learning and feature fusion.  \nResults: Our SVM model, utilizing combined features from Pyradiomicsand MRCradiomics, achieved an AUC of 0.74 on the Multi-Improd dataset (Siemens scanner) but decreased to 0.60 on the Philips test set. The RF model showed similar trends, with notable robustness for models using Pyradiomics features alone (AUC of 0.78 on Philips) .  \nConclusions: These findings demonstrate the potential of multimodal feature integration to improve the robustness and generalizability of machine-learning models for clinical decision support in prostate cancer detection. This study marks a significant step towards developing reliable AI-driven diagnostic tools that maintain efficacy across various imaging platforms.  \nKeywords: Machine Learning · Inter-Vendor Reproducibility · Radiomics · Prostate Cancer · Diagnostic tools · Model Reproducibility  \n1 Introduction  \nThinking about the transformative era of medical diagnostics with the integration of machine learning (ML) into cancer detection opens up a new oil reserve of possibilities. The strategic application of ML in prostate cancer via Magnetic  \n2 J. Chaudhary et al.  \nResonance Imaging (MRI) stands at the crucial juncture of this revolution [27], insighting towards a pivotal intersection where innovation meets urgent healthcare demands. In the field of medical imaging, radiomic feature extraction and artificial intelligence (AI) in medical imaging has experienced significant progress over the past decade, with these methods increasingly being used in MRI of prostate [2][22], while reproducibility of these AI models is still not largely studied. Prostate cancer (PCa) continues to be the most common cancer among men in the western worlds and the second most common cause of death. While prostate cancer MRI is generally considered cost-effective [13], long acquisition times, high cost, and inter-center/reader variability of usual multi-parametric prostate MRI limit its wider adoption to clinical use.  \nReproducibility has recently gained more focus [20] . It is the bedrock that underpins the trustworthiness, effectiveness, and clinical acceptance of ML applications. The essence of reproducibility in this technological evolution is of paramount importance in the field of medical imaging, where number of variations hinder application and adoption of developed ML techniques to new environments. Among others, most prominent sources of these variations are differences in MR imaging devices and MR sequence acquisition settings. [1] have addressed several reproducibility dimensions and clinical ramifications of AI deployment in healthcare, emphasizing reproducibility as a critical component for safeguarding patient welfare and ensuring equitable treatment. T","cbCaijuhk2zVB7Jc","https://ap.wps.com/l/cbCaijuhk2zVB7Jc","pdf",436738,1,13,"English","en",105,"# Introduction\n## Clinical motivation and reproducibility challenge\n# Methods\n## Radiomic feature extraction and libraries\n## Models and feature selection\n## Feature fusion for multimodal learning\n# Results\n## SVM performance across vendors\n## Random forest robustness using radiomics features\n# Conclusions\n## Generalizability and clinical decision support","[{\"question\":\"What problem does the study address about radiomics-based ML models?\",\"answer\":\"It focuses on how reproducible machine-learning models are for prostate cancer detection when trained models are applied across MRI systems from different vendors.\"},{\"question\":\"Which models and radiomics pipelines are used in the experiments?\",\"answer\":\"Support Vector Machines and Random Forests are trained on radiomic features extracted from T2-weighted MRI using Pyradiomics and MRCradiomics, with MRMR feature selection.\"},{\"question\":\"How does vendor shift affect the reported model performance?\",\"answer\":\"For the SVM, AUC is 0.74 on the Multi-Improd dataset (Siemens) but decreases to 0.60 on the Philips test set; the RF model shows similar trends while being more robust when using Pyradiomics features alone.\"}]","Cross-Vendor Reproducibility of Radiomics-based Machine Learning Models for Computer-aided Diagnosis - Research report | PDF",1785815489,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"cross-vendor-reproducibility-of-radiomics-based-machine-learning-models-for-computer-aided-diagnosis-research-report","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/cross-vendor-reproducibility-of-radiomics-based-machine-learning-models-for-computer-aided-diagnosis-research-report/123252/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address about radiomics-based ML models?","Question",{"text":75,"@type":76},"It focuses on how reproducible machine-learning models are for prostate cancer detection when trained models are applied across MRI systems from different vendors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which models and radiomics pipelines are used in the experiments?",{"text":80,"@type":76},"Support Vector Machines and Random Forests are trained on radiomic features extracted from T2-weighted MRI using Pyradiomics and MRCradiomics, with MRMR feature selection.",{"name":82,"@type":73,"acceptedAnswer":83},"How does vendor shift affect the reported model performance?",{"text":84,"@type":76},"For the SVM, AUC is 0.74 on the Multi-Improd dataset (Siemens) but decreases to 0.60 on the Philips test set; the RF model shows similar trends while being more robust when using Pyradiomics features alone.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]