[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-364857-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-364857-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","feasibility-study-of-ai-assisted-multi-parameter-mri-diagnosis-of-prostate-cancer","Feasibility study of AI-assisted multi-parameter MRI diagnosis of prostate cancer","","A feasibility study evaluates an AI-assisted computer-aided diagnosis (CAD) approach for distinguishing benign versus malignant prostate lesions using multi-parametric MRI (mpMRI). A retrospective dataset of 106 patients (2021–2024) yielded 137 mpMRI images from T2W, DCE, and DWI sequences, producing 274 ROI sets for training/validation and testing. A pretrained ResNet50 with a multi-head attention feature fusion module performs classification. Results show strong performance with AUC around 0.89–0.91 and precision remaining high across most recall levels, suggesting improved risk assessment for clinically significant prostate cancer.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/feasibility-study-of-ai-assisted-multi-parameter-mri-diagnosis-of-prostate-cancer/364857/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/feasibility-study-of-ai-assisted-multi-parameter-mri-diagnosis-of-prostate-cancer/364857.png","ImageObject",300,407,{"name":42,"@type":43},"Rowan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-03","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the AI-assisted CAD system aim to address?","Question",{"text":63,"@type":64},"It targets the difficulty of distinguishing benign and malignant prostate lesions on multi-parametric MRI, which affects prostate cancer screening accuracy.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the dataset prepared for the feasibility study?",{"text":68,"@type":64},"The study retrospectively included 106 patients who underwent mp-MRI (2021–2024). Three MRI sequences (T2W, DCE, DWI) produced 137 images mapped to pathological sections, resulting in 274 ROI sets split into training/validation and testing.",{"name":70,"@type":61,"acceptedAnswer":71},"What model architecture was used and what is the attention mechanism for?",{"text":72,"@type":64},"A pretrained ResNet50 is combined with a multi-head attention mechanism to fuse modality-specific features and improve classification by emphasizing key details and reducing redundancy.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},364857,1790868569,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":112,"preview_page_count":33,"preview_urls":145},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nFeasibility study of AI-assisted multi-parameter MRI diagnosis of prostate cancer  \nYiboXu1,2, Rongjiang Wang1,2, Zhihai Fang1,2 & Jianer Tang1,2􀀍  \nDistinguishing between benign and malignant prostate lesions in magnetic resonance imaging (MRI) poses challenges that affect prostate cancer screening accuracy. We propose a novel computer-aided diagnosis (CAD) system to extract cancerous lesions from the prostate in multi-parametric MRI (mpMRI), assessing the feasibility of using artificial intelligence for detecting clinically significant prostate cancer (PCa). A retrospective study was conducted on 106 patients who underwent mp-MRI from 2021 to 2024 at a single center. We analyzed three sequences (T2W, DCE, and DWI) and collected 137 mpMRI images corresponding to pathological sections. From these, we obtained 274 sets of ROI data, using 206 for training and validation, and 68 for testing. A feature extractor was developed using a pretrained ResNet50 model combined with a multi-head attention mechanism to fuse modality-specific features and perform classification. The experimental results indicate that our model demonstrates high classification performance, achieving anAUC of 0.89. The PR curve shows high precision across most recall values, with anAUC of 0.91. We developed a novel CAD system based on deep learning ResNet50 models to assess the risk of prostate malignancy in mpMRI images. High classification ability is achieved, and combining the attention mechanism or optimization strategy can improve the performance of the model in medical imaging.  \nKeywords Prostate cancer, Multi-parameter MRI, Computer-aided diagnosis, Convolutional neural networks  \nProstate cancer (PCa) is the second most common malignancy in men globally, accounting for over one-fifth of male cancer diagnoses and posing significant challenges to healthcare systems1,2. Early treatment can reduce mortality, prompting widespread prostate cancer screening3. Consequently, prostate cancer screening has been widely promoted and implemented over the past decades2,4. Currently, prostate biopsy is the standard diagnostic method, but its invasive nature raises concerns about detecting small tumors, leading to overtreatment and psychological distress. Thus, optimizing biopsy protocols to improve detection while minimizing unnecessary procedures has become a critical research focus, aiming to alleviate patient burden and conserve resources.  \nOver the past decades, researchers have developed various computer-aided diagnosis (CAD) systems to classify malignant and benign prostate lesions5–8. However, their effectiveness depends on accurate segmentation and optimal image selection. Until these challenges are addressed, the performance of traditional CAD systems remains questionable. In recent years, rapid advancements in deep learning technology have led to the development of novel CAD systems for prostate cancer diagnosis7,9. Deep learning methods can simplify the classification of prostate lesion images and automatically learn complex patterns, reducing manual intervention, provided the dataset is sufficiently large7, 10, 11.  \nAmong various deep learning models, convolutional neural networks (CNNs) are the most widely used in medical imaging due to their simplicity and effectiveness9, 12. It has been applied to in other cancer diagnoses to classify benign and malignant cases9, 12, 13. Compared to the current popular algorithms such as U-Net or DenseNet, the ResNet50 architecture has better performance in alleviating the gradient disappearance problem and achieving deeper network training, which can better capture the detailed features in the image14. The U-Net model features a symmetric encoder-decoder structure with downsampling (contracting path) and upsampling (expansive path) parts15. It employs skip connection to combine the features of different layers and performs well on small s","cbCainI9IeJequhG","https://ap.wps.com/l/cbCainI9IeJequhG","pdf",2614303,12,"English","# Background\n## Challenges in prostate cancer imaging and screening\n## CAD and deep learning approaches\n# Methods\n## Study design and dataset\n## MRI sequences and ROI construction\n## ResNet50-based model with multi-head attention\n# Results\n## Classification performance metrics\n## Precision-recall behavior\n# Discussion\n## Role of attention/optimization in medical imaging","[{\"question\":\"What problem does the AI-assisted CAD system aim to address?\",\"answer\":\"It targets the difficulty of distinguishing benign and malignant prostate lesions on multi-parametric MRI, which affects prostate cancer screening accuracy.\"},{\"question\":\"How was the dataset prepared for the feasibility study?\",\"answer\":\"The study retrospectively included 106 patients who underwent mp-MRI (2021–2024). Three MRI sequences (T2W, DCE, DWI) produced 137 images mapped to pathological sections, resulting in 274 ROI sets split into training/validation and testing.\"},{\"question\":\"What model architecture was used and what is the attention mechanism for?\",\"answer\":\"A pretrained ResNet50 is combined with a multi-head attention mechanism to fuse modality-specific features and improve classification by emphasizing key details and reducing redundancy.\"}]","Feasibility study of AI-assisted multi-parameter MRI diagnosis of prostate cancer | PDF",1790159251,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e3ca5f23d1634e643a55509c6c5944bd.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/842d7fa2e6c2b501be19dbee8305d172.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/13e51721caadbe19be8cfb630a8b1e0d.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9033c23da8a414082a7690c9fc924089.webp",980,1287]