[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-363613-105":59,"doc-detail-363613-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","differentiating-malignancy-from-liver-parenchyma-in-ex-vivo-oct-images-using-anomaly-detection","Differentiating malignancy from liver parenchyma in Ex-Vivo OCT images using anomaly detection","","Optical coherence tomography (OCT) with anomaly detection is evaluated for distinguishing hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (iCCA), and colorectal liver metastases (CRLM) from normal liver parenchyma in ex-vivo specimens. A dataset of 173 OCT images from 69 patients undergoing liver surgery is used, training an anomaly model only on non-cancer parenchyma scans via pre-trained neural networks with frozen weights and outlier modeling. Stratified cross-validation addresses dataset size and label uncertainty, yielding sensitivity 80%, specificity 78%, accuracy 79%, and ROC-AUC 81%, supporting fast intraoperative cancer screening.",{"@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":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/differentiating-malignancy-from-liver-parenchyma-in-ex-vivo-oct-images-using-anomaly-detection/363613/",{"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/differentiating-malignancy-from-liver-parenchyma-in-ex-vivo-oct-images-using-anomaly-detection/363613.png","ImageObject",300,407,{"name":92,"@type":93},"Franzy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does the study use anomaly detection with OCT data?","Question",{"text":112,"@type":113},"The anomaly detection model is trained only on non-cancer liver parenchyma scans, learning what normal tissue looks like and then flagging anomalies in aberrant (tumor) scans.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What dataset and validation method were used?",{"text":117,"@type":113},"The study uses 173 OCT images from 69 patients. Stratified cross-validation is applied to handle the small dataset size and label uncertainty while assessing how well OCT scans match histological diagnoses.",{"name":119,"@type":110,"acceptedAnswer":120},"What classification performance does the Vision Transformer achieve?",{"text":121,"@type":113},"Using a pre-trained Vision Transformer, the reported sensitivity is 80%, specificity 78%, accuracy 79%, and ROC-AUC 81% for differentiating malignancies from normal parenchyma.","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},363613,1790197981,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"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":145,"preview_page_count":19,"preview_urls":146},2336478945519,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDifferentiating malignancy from liver parenchyma in Ex-Vivo OCT images using anomaly detection  \nUlrich Krispel1, Alexander Pamler1, Caroline Girmen2, Niels König2, Robert Schmitt2,3, Eva Eggeling1, Sören Büsker4, Oliver Beetz5, Felix Oldhafer5, Daniel Truhn6,  \nFlorian W. R. Vondran5 & Iakovos Amygdalos5􀀍  \nPrimary liver cancer and colorectal liver metastases (CRLM) pose significant challenges, because of limited early diagnosis and the reliance on time-consuming frozen section analysis during surgery to confirm complete tumor resection (R0). This study investigates the potential of optical coherence tomography (OCT) combined with anomaly detection for differentiating hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (iCCA) and CRLM from normal liver parenchyma, ex-vivo. Our dataset comprises 173 OCT images sourced from 69 patients undergoing liver surgery. We leveraged pre-trained neural networks with frozen weights and statistical outlier modeling to train an anomaly detection model using only non-cancer parenchyma scans. Given the small-scale nature of the dataset and the presence of label uncertainty, a stratified cross-validation procedure was employed to robustly assess the model’s performance in accurately matching OCT scans with their corresponding histological diagnoses. This resulted in promising classification performance using a pre-trained Vision Transformer: sensitivity 80%, specificity 78%, accuracy 79%, and area under the receiving-operating-characteristiccurve (ROC-AUC) of 81%. While limited by a relatively small and noisy dataset, this study highlights the promising potential of OCT combined with anomaly detection for intraoperative liver cancer detection. This semi-supervised learning approach offers several advantages, including reduced training time and data requirements, as well as interpretable anomaly scores.  \nPrimary liver cancer is the sixth most common cancer worldwide, accounting for 4% of all cancer cases and causing the second highest number of cancer deaths (8%)1,2 after lung and colorectal cancer. It comprises hepatocellular carcinoma (HCC, up to 85% of cases), intrahepatic cholangiocarcinoma (iCCA, up to 15%), and other, rarer malignancies1,2. Moreover, colorectal cancer is the third most common cancer type worldwide, with the majority of these patients developing liver metastases, which are the primary cause of mortality2–4. As such, colorectal liver metastases (CRLM) are the most commonly diagnosed malignancy in the liver. Curative liver resection with complete tumor removal (R0) is the best option for all of these pathologies. However, only 12% - 40% of patients diagnosed with iCCA are eligible for surgical therapy and curative therapies such as surgical resection and liver transplantation are restricted to a minority of HCC patients with early disease1,5–8.  \nThis underlines the importance of improving diagnostics to detect liver cancer earlier and to accurately determine resection radicality intraoperatively. Additionally, the intraoperative detection of peritoneal metastases is crucial to the treatment plan, as these carry a difficult prognosis and often change a curative situation into a palliative one9, 10. Intraoperative tissue diagnostics rely on frozen section analysis, which is time-consuming, especially when multiple tissue samples are examined11–13. This leads to longer surgeries, particularly when frozen sections are positive, requiring further clearance of the resection margin. This, in turn, is associated with an increased risk of complications and costs14, 15.  \nTherefore, a technology with the potential to quickly conduct intraoperative tissue diagnostics would bean attractive solution to this problem. A non-invasive imaging technology with the potential to address these challenges is optical coherence tomography (OCT). Based on low-coherence interferometry, OCT produces realtime, ","cbCaidb2BJprRMUZ","https://ap.wps.com/l/cbCaidb2BJprRMUZ","pdf",3108301,13,"English","# Related work\n## OCT\n## Anomaly detection approach\n## Dataset and evaluation","[{\"question\":\"How does the study use anomaly detection with OCT data?\",\"answer\":\"The anomaly detection model is trained only on non-cancer liver parenchyma scans, learning what normal tissue looks like and then flagging anomalies in aberrant (tumor) scans.\"},{\"question\":\"What dataset and validation method were used?\",\"answer\":\"The study uses 173 OCT images from 69 patients. Stratified cross-validation is applied to handle the small dataset size and label uncertainty while assessing how well OCT scans match histological diagnoses.\"},{\"question\":\"What classification performance does the Vision Transformer achieve?\",\"answer\":\"Using a pre-trained Vision Transformer, the reported sensitivity is 80%, specificity 78%, accuracy 79%, and ROC-AUC 81% for differentiating malignancies from normal parenchyma.\"}]","Differentiating malignancy from liver parenchyma in Ex-Vivo OCT images using anomaly detection | PDF",1790152155,33,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b1e70e88c9199c2a079863bdeb92e4d9.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/31142f4661dfd5f79bc83b360dd4980b.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0eadc3a04eb8d1ffb87e6e544f2332d8.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cd93bd57c69cc6e363711f5792eef090.webp",980,1287]