[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-351388-105":59,"doc-detail-351388-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","ai-powered-hierarchical-classification-of-ampullary-neoplasms-a-deep-learning-approach-using-white-light-and-narrow-band-imaging","AI-powered hierarchical classification of ampullary neoplasms: a deep learning approach using white-light and narrow-band imaging","","Endoscopic diagnosis of Ampulla of Vater (AoV) lesions remains difficult due to complex morphology and limited representative images, especially for high-risk dysplasia. This study develops a hierarchical deep learning framework for stepwise classification using white-light and narrow-band endoscopic images. Three sequential binary stages distinguish normal vs. abnormal, adenoma vs. cancer, and high-grade vs. low-grade dysplasia, with confidence-based fusion and synthetic augmentation to address imbalance and data scarcity.",{"@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/ai-powered-hierarchical-classification-of-ampullary-neoplasms-a-deep-learning-approach-using-white-light-and-narrow-band-imaging/351388/",{"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/ai-powered-hierarchical-classification-of-ampullary-neoplasms-a-deep-learning-approach-using-white-light-and-narrow-band-imaging/351388.png","ImageObject",300,407,{"name":92,"@type":93},"Maya Linwood","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-26","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What classification task does the hierarchical model perform for ampullary lesions?","Question",{"text":112,"@type":113},"It uses three sequential binary stages: normal vs. abnormal, adenoma vs. cancer, and high-grade dysplasia vs. low-grade dysplasia within adenomas.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are white-light and narrow-band images combined in the framework?",{"text":117,"@type":113},"Each stage is trained independently on white-light and narrow-band images, and predictions are integrated using confidence-based voting to leverage complementary diagnostic strengths.",{"name":119,"@type":110,"acceptedAnswer":120},"Why are synthetic images generated, and what was the effect?",{"text":121,"@type":113},"StyleGAN2-ADA is used for high-grade dysplasia and cancer to address data scarcity and class imbalance; sensitivity improved for cancer and high-grade dysplasia, and overall accuracy increased.","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},351388,1790452722,{"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":14,"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},962084928432,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Surgical Endoscopy (2026) 40:2902–2913  \n[https://doi.org/10.1007/s00464-025-12534-2](https://doi.org/10.1007/s00464-025-12534-2)  \nand Other Interventional Techniques  \nAI‑powered hierarchical classification of ampullary neoplasms: a deep learning approach using white‑light and narrow‑band imaging  \nDan Yoon1 · Sung Hoon Chang2 · Woo Hyun Paik2,3 · Chang Hyun Kim2 · Byeong Soo Kim4 · Young Gyun Kim4 · Hyunsoo Chung2,3 · Ji Kon Ryu2 · Sang Hyub Lee2 · In Rae Cho2 · Seong Ji Choi3,5 · Joo Seong Kim3,6 · Sungwan Kim1,4,7 · Jin Ho Choi2,3  \nReceived: 25 October 2025 / Accepted: 20 December 2025 / Published online: 14 January 2026 © The Author(s) 2026  \nAbstract  \nBackground Endoscopic diagnosis of Ampulla ofVater (AoV) lesions remains challenging owing to complex morphology and limited representative images, particularly for high-risk dysplastic lesions. This study aimed to develop a hierarchical deep learning framework for the stepwise classification of ampullary lesions using white-light (WL) and narrow-band endoscopic images (NBI) .  \nMethods The framework employs three sequential binary classifications: (1) normal vs. abnormal,(2) adenoma vs. cancer, and (3) high-grade dysplasia (HGD) vs. low-grade dysplasia (LGD) within adenomas. Each stage uses EfficientNet-B4 classifiers trained independently on WL and NBI. Predictions are integrated using confidence-based voting. To overcome data scarcity and class imbalance, for HGD and cancer, we used StyleGAN2-ADA to generate synthetic images. The hierarchical model was developed using 4244 endoscopic images from 464 patients collected at Seoul National University Hospital (2693/833/718 for train/validation/test) .  \nResults The hierarchical model achieved stage-specific accuracies of 95.6%(normal vs. abnormal), 94.4%(adenoma vs. cancer), and 92.7%(LGD vs. HGD), resulting in overall diagnostic accuracy of 92.2% . The model demonstrated excellent sensitivity of 83.3% for HGD and 87.5% for cancer, with specificities exceeding 98%. The confidence-based dual-modality approach (AUROC: 0.921) significantly outperformed single-modality approaches using WL alone (AUROC: 0.866) or NBI alone (AUROC: 0.895), by integrating their complementary diagnostic strengths. Generative adversarial network-based augmentation substantially improved sensitivity for cancer (from 87.5% to 91.7%) and HGD (from 83.3% to 86.5%), while overall accuracy increased from 94.5% to 95.1% .  \nConclusions A hierarchical deep learning approach integrating dual-modality imaging and synthetic data augmentation significantly improves diagnostic performance for ampullary lesions.  \nKeywords Ampulla of Vater neoplasm · Endoscopic images · Narrow-band imaging · Hierarchical classification · Deep learning  \nNeoplasms of the Ampulla of Vater (AoV) are rare tumors that are currently being diagnosed with increasing frequency owing to advances in imaging techniques and expanded use of diagnostic endoscopy for healthcare screening [1] . AoV adenomas represent precancerous lesions that progress  \n\n| Dan Yoon and Sung Hoon Chang have contributed equally to this work. |\n| --- |\n| Sungwan Kim and Jin Ho Choi have contributed equally to this work and are co-corresponding authors. |\n\nExtended author information available on the last page of the article  \nthrough the adenoma–carcinoma sequence [2–5] . Accurate classification into low-grade dysplasia (LGD), high-grade dysplasia (HGD), or carcinoma is essential for optimal clinical decision-making: small LGD adenomas can be managed conservatively or with endoscopic papillectomy (EP), whereas HGD and carcinoma require pancreaticoduodenectomy [6–9] . Although both HGD and carcinoma are typically managed surgically, distinguishing them remains clinically important for postoperative management and prognostication. However, this diagnostic process remains challenging given the subtle morphological features, interobserver variability, and inconsistent image quality [10–13] .  \nCurrent diagnosis relies","cbCaiks9XNnRWEAT","https://ap.wps.com/l/cbCaiks9XNnRWEAT","pdf",3159277,12,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n# Keywords","[{\"question\":\"What classification task does the hierarchical model perform for ampullary lesions?\",\"answer\":\"It uses three sequential binary stages: normal vs. abnormal, adenoma vs. cancer, and high-grade dysplasia vs. low-grade dysplasia within adenomas.\"},{\"question\":\"How are white-light and narrow-band images combined in the framework?\",\"answer\":\"Each stage is trained independently on white-light and narrow-band images, and predictions are integrated using confidence-based voting to leverage complementary diagnostic strengths.\"},{\"question\":\"Why are synthetic images generated, and what was the effect?\",\"answer\":\"StyleGAN2-ADA is used for high-grade dysplasia and cancer to address data scarcity and class imbalance; sensitivity improved for cancer and high-grade dysplasia, and overall accuracy increased.\"}]","AI-powered hierarchical classification of ampullary neoplasms: a deep learning approach using white-light and narrow-band imaging | PDF",1790093962]