[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-376186-105":59,"doc-detail-376186-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","an-explainable-by-design-end-to-end-ai-framework-based-on-prototypical-part-learning-for-lesion-detection-and-classication-in-digital-breast-tomosynthesis-images","An explainable-by-design end-to-end AI framework based on prototypical part learning for lesion detection and classification in Digital Breast Tomosynthesis images","","Breast cancer is the leading cancer among women worldwide, and timely screening is essential for better outcomes. Digital Breast Tomosynthesis (DBT) improves over conventional mammography by reconstructing a 3D representation from multiple X-ray views, but its large data volume slows interpretation. This study introduces a transparent, explainable AI system that predicts and explains results to accelerate DBT scan analysis while preserving interpretability.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/an-explainable-by-design-end-to-end-ai-framework-based-on-prototypical-part-learning-for-lesion-detection-and-classication-in-digital-breast-tomosynthesis-images/376186/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/an-explainable-by-design-end-to-end-ai-framework-based-on-prototypical-part-learning-for-lesion-detection-and-classication-in-digital-breast-tomosynthesis-images/376186.png","ImageObject",300,407,{"name":92,"@type":93},"eBook King","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-24",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in Digital Breast Tomosynthesis (DBT)?","Question",{"text":112,"@type":113},"The study addresses the time-consuming manual review caused by the large volume of DBT images, and the need for AI systems that are both accurate and interpretable for medical diagnostics.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the proposed AI framework built?",{"text":117,"@type":113},"It uses a two-stage deep learning pipeline: YOLOv5/YOLOv8 (plus an ensemble) for lesion detection, followed by ProtoPNet for lesion classification using prototypical part learning.",{"name":119,"@type":110,"acceptedAnswer":120},"What explains the model’s decision-making in this work?",{"text":121,"@type":113},"The framework emphasizes explainable-by-design behavior, using ProtoPNet to provide transparent reasoning linked to prototypical parts, supporting interpretability required for clinical use.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},376186,1790242683,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":41},962088006270,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Computational and Structural Biotechnology Journal 27 (2025) 2649–2660  \nContents lists available at ScienceDirect  \nComputational and Structural Biotechnology Journal  \njournal [homepage:](homepage: www.elsevier.com/locate/csbj)[ www.elsevier.com/locate/csbj](homepage: www.elsevier.com/locate/csbj)  \n| Research Article\u003Cbr>An explainable-by-design end-to-end AI framework based on prototypical part learning for lesion detection and classification in Digital Breast Tomosynthesis images\u003Cbr>Andrea Berti a,b,c, ,∗ , Camilla Scapicchiob,d, , Chiara Iacconi e, ,\u003Cbr>\u003Cbr>Charlotte Marguerite Lucille Trombadori f , , Maria Evelina Fantaccib,d, ,\u003Cbr>\u003Cbr>Alessandra Retico b, , 1 , Sara Colantonio a, , 1\u003Cbr>|  |  | |\n| --- | --- | --- | --- |\n| a Institute of Information Science and Technologies (ISTI) -National Research Council of Italy (CNR), Via Giuseppe Moruzzi, 1, Pisa, 56127, Italy b National Institute for Nuclear Physics (INFN) section of Pisa, Largo Bruno Pontecorvo, 3/Edificio C, Pisa, 56127, Italy\u003Cbr>c Department of Information Engineering, University of Pisa, Via Girolamo Caruso, 16, Pisa, 56122, Italy d Department of Physics, University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, 56127, Italy e Department of Radiology, Breast Imaging UOSD, Piazza Monzoni 1, Carrara, 54033, Italy\u003Cbr>f Department of Diagnostic Imaging, Oncological Radiotherapy and Haematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Largo Agostino Gemelli, 8, Rome, 00168, Italy |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Ante-hoc explainability Deep learning ProtoPNet\u003Cbr>XAIDBT\u003Cbr>Lesion detection\u003Cbr>Lesion classification |  | Background and Objective: Breast cancer is the most common cancer among women worldwide, making early detection through breast screening crucial for improving patient outcomes. Digital Breast Tomosynthesis (DBT) isan advanced radiographic technique that enhances clarity over traditional mammography by compiling multiple X-ray images into a 3D reconstruction, thereby improving cancer detection rates. However, the large data volume of DBT poses a challenge for timely analysis. This study aims to introduce a transparent AI system that not only provides a prediction but also an explanation of that prediction, expediting the analysis of DBT scans while ensuring interpretability.\u003Cbr>Methods: The study employs a two-stage deep learning process. The first stage uses state-of-the-art Neural Network (NN) models, specifically YOLOv5 and YOLOv8, to detect lesions within the scans. An ensemble method is also explored to enhance detection capabilities. The second stage involves classifying the identified lesions using ProtoPNet, an inherently transparent NN that leverages prototypical part learning to distinguish between benign and cancerous lesions. The system facilitates clear interpretability in decision-making, which is crucial for medical diagnostics.\u003Cbr>Results: The performance of the AI system demonstrates competitive metric results for both detection and classification tasks (a recall of 0.76 and an accuracy of 0.70, respectively). The evaluation metrics, together with the validation by expert radiologists through clinical feedback, highlight the potential of the system for future clinical relevance. Despite challenges such as dataset limitations and the need for more accurate ground truth annotations, which limit the final values of the metrics, the approach shows significant advancement in applying AI to DBT scans.\u003Cbr>Conclusions: This study contributes to the growing field of AI in breast cancer screening by emphasizing the need for systems that are not only accurate but also transparent and interpretable. The proposed AI system marks a significant step forward in the timely and accurate analysis of DBT scans, with potential implications for improving early breast cancer detection and patient outcomes. |  |\n\n* Corresponding author at: Institute of Information Science and Technologies (ISTI) -National Research ","cbCaieOYJ4GCEtqt","https://ap.wps.com/l/cbCaieOYJ4GCEtqt","pdf",2767610,12,"English","# Abstract\n# Keywords\n# Background and Objective\n# Methods\n## Lesion detection\n## Lesion classification\n# Results\n# Conclusions\n# Introduction\n# Related Explainability Concepts","[{\"question\":\"What problem does the study address in Digital Breast Tomosynthesis (DBT)?\",\"answer\":\"The study addresses the time-consuming manual review caused by the large volume of DBT images, and the need for AI systems that are both accurate and interpretable for medical diagnostics.\"},{\"question\":\"How is the proposed AI framework built?\",\"answer\":\"It uses a two-stage deep learning pipeline: YOLOv5/YOLOv8 (plus an ensemble) for lesion detection, followed by ProtoPNet for lesion classification using prototypical part learning.\"},{\"question\":\"What explains the model’s decision-making in this work?\",\"answer\":\"The framework emphasizes explainable-by-design behavior, using ProtoPNet to provide transparent reasoning linked to prototypical parts, supporting interpretability required for clinical use.\"}]","An explainable-by-design end-to-end AI framework based on prototypical part learning for lesion detection and classification in Digital Breast Tomosynthesis images | PDF",1790217643]