[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-359758-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-359758-en":131},{"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","diagnostic-performance-of-a-deep-learning-based-tool-for-the-detection-and-staging-of-rectal-cancers-on-endoscopic-ultrasound-prospective-study","Diagnostic Performance of a Deep Learning-Based Tool for the Detection and Staging of Rectal Cancers on Endoscopic Ultrasound - Prospective Study","","Loco-regional staging of rectal cancer depends on MRI and rectal endoscopic ultrasound (R-EUS), yet MRI often fails to consistently differentiate early tumor categories (Tis, T1, T2). This prospective pilot study evaluates a deep learning (DL) tool using a convolutional neural network for image segmentation and classification on R-EUS. Lesion segmentation performance was measured with Dice similarity coefficient and F1-score, and tumor detection and T-stage discrimination were assessed across Tis/T1 versus T2/T3 and Tis versus T1–T3. Forty-eight?",{"@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/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/diagnostic-performance-of-a-deep-learning-based-tool-for-the-detection-and-staging-of-rectal-cancers-on-endoscopic-ultrasound-prospective-study/359758/",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/diagnostic-performance-of-a-deep-learning-based-tool-for-the-detection-and-staging-of-rectal-cancers-on-endoscopic-ultrasound-prospective-study/359758.png","ImageObject",300,407,{"name":42,"@type":43},"Taylor Morgan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",16,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address in rectal cancer staging?","Question",{"text":63,"@type":64},"It addresses limitations of loco-regional staging, where MRI and imaging assessment may not reliably distinguish early rectal cancer categories, motivating the use of R-EUS with a deep learning tool.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the deep learning tool work in this study?",{"text":68,"@type":64},"It uses a convolutional neural network to perform image segmentation and classification on rectal EUS images.",{"name":70,"@type":61,"acceptedAnswer":71},"What performance did the model achieve for tumor detection and staging?",{"text":72,"@type":64},"On lesion segmentation, the median DSC was reported as 0.65. Tumor detection accuracy was 0.77 with precision 0.85, recall 0.77, and F1-score 0.81, while Tis/T1 versus T2/T3 discrimination achieved accuracy 0.64 and F1-score 0.74.","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},359758,1790197995,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"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":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article  \nDiagnostic Performance of a Deep Learning-Based Tool for the Detection and Staging of Rectal Cancers on Endoscopic Ultrasound: Prospective Study  \nAmedeo Montale 1, Marco Valvano 1,*, Andrea Ghezzi 1, Marco Magliocco 2, Nicola Panvini 3, Mariangela Rutigliani 4, Massimo Oppezzi 1, Lucio Molini 3 and Francesco Paparo 3  \nAcademic Editor: Gwang HaKim  \nReceived: 27 February 2026  \nRevised: 22 March 2026  \nAccepted: 27 March 2026  \nPublished: 14 April 2026  \nCopyright: © 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \n1 Gastroenterology Unit, E.O. Ospedali Galliera, Mura delle Cappuccine 14, 16128 Genoa, Italy; [amedeo.montale@galliera.it](amedeo.montale@galliera.it) (A.M.); [andrea.ghezzi@galliera.it](andrea.ghezzi@galliera.it) (A.G.); [massimo.oppezzi@galliera.it](massimo.oppezzi@galliera.it) (M.O.)  \n2 Department of Experimental Medicine, University of Genoa, 16126 Genoa, Italy; [marco.magliocco@camelotbio.com](marco.magliocco@camelotbio.com)  \n3 Diagnostic Imaging Unit, E.O. Ospedali Galliera, Mura delle Cappuccine 14, 16128 Genoa, Italy; [nicola.panvini@galliera.it](nicola.panvini@galliera.it) (N.P.); [lucio.molini@galliera.it](lucio.molini@galliera.it) (L.M.); [francesco.paparo@galliera.it](francesco.paparo@galliera.it) (F.P.)  \n4 Pathology Unit, E.O. Ospedali Galliera, Mura delle Cappuccine 14, 16128 Genoa, Italy; [mariangela.rutigliani@galliera.it](mariangela.rutigliani@galliera.it)  \n* [Correspondence: marco.valvano@galliera.it](Correspondence: marco.valvano@galliera.it)  \nAbstract  \nBackground: Loco-regional staging of rectal cancer relies on MRI and rectal EUS (R-EUS) . In situ and T1 tumors may be candidates for endoscopic resection, and R-EUS enables reliable differentiation among early-stage tumors (Tis, T1, T2), a distinction that MRI cannot consistently provide. This prospective pilot study aimed to evaluate the predictive performance of a deep learning (DL) tool for detecting and staging rectal tumors on R-EUS. Methods: The DL tool uses a convolutional neural network for image segmentation and classification. Performance in lesion segmentation was assessed using the Dice Similarity Coefficient (DSC) and F1-score. The model was first evaluated for its ability to differentiate in situ and T1 tumors from T2/T3 lesions, and then for distinguishing Tis from other stages (T1, T2, T3) . Results: Fifty patients were enrolled. The median DSC for tumor segmentation was 0.65 (IQR 0.17) . Tumor detection showed an accuracy of 0.77, precision of 0.85, recall of 0.77, and F1-score of 0.81 . In distinguishing Tis/T1 from T2/T3 tumors, the model achieved an accuracy of 0.64, precision of 0.88, recall of 0.64, and F1-score of 0.74. For distinguishing Tis from T1, T2, and T3 lesions, the accuracy was 0.80, precision 0.83, recall 0.89, and F1-score 0.86 . Mesorectal lymph node segmentation showed a median DSC of 0.62 (IQR 0.17) . Conclusions: The DL tool shows promise for aiding operators in identifying rectal lesions suitable for endoscopic resection. The semi-supervised training approach reduces manual segmentation burden and achieves performance comparable to expert physicians.  \nKeywords: rectal endoscopic ultrasound; transrectal ultrasound; rectal cancer; deep learning; artificial intelligence; computer-aided detection  \n1. Introduction  \nColorectal cancer is the third most common malignancy worldwide. Loco-regional staging is primarily performed using magnetic resonance imaging (MRI) and ultrasound techniques with endocavitary transducers—mainly transrectal ultrasound (TRUS) and rectal EUS (R-EUS)—and is essential for therapeutic decision-making. It is based on the  \nassessment of tumor depth (T) and regional lymph node involvement (N) according to the TNM classification system [1,2] . Rectal MRI does not reliably distinguish early T categories (Tis, T1, T2), except in sele","cbCaigMgNcIOeEyv","https://ap.wps.com/l/cbCaigMgNcIOeEyv","pdf",1712640,14,"English","# Abstract\n# Introduction\n## Background and clinical need\n## Role and limitations of MRI and ultrasound\n## Prior AI/DL research for rectal cancer","[{\"question\":\"What problem does the study address in rectal cancer staging?\",\"answer\":\"It addresses limitations of loco-regional staging, where MRI and imaging assessment may not reliably distinguish early rectal cancer categories, motivating the use of R-EUS with a deep learning tool.\"},{\"question\":\"How does the deep learning tool work in this study?\",\"answer\":\"It uses a convolutional neural network to perform image segmentation and classification on rectal EUS images.\"},{\"question\":\"What performance did the model achieve for tumor detection and staging?\",\"answer\":\"On lesion segmentation, the median DSC was reported as 0.65. Tumor detection accuracy was 0.77 with precision 0.85, recall 0.77, and F1-score 0.81, while Tis/T1 versus T2/T3 discrimination achieved accuracy 0.64 and F1-score 0.74.\"}]","Diagnostic Performance of a Deep Learning-Based Tool for the Detection and Staging of Rectal Cancers on Endoscopic Ultrasound - Prospective Study | PDF",1790137724,35]