[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-detail-365366-en":59,"doc-seo-365366-105":99},{"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":5,"data":60},{"doc_id":61,"user_id":62,"nickname":63,"user_avatar":64,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":66,"doc_content":67,"file_id":68,"file_url":69,"file_type":70,"file_size":71,"view_count":72,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":73,"language_code":74,"site_id":75,"html_lang":74,"table_of_contents":76,"faqs":77,"seo_title":78,"seo_description":66,"update_tm":79,"read_time":80,"preview_page_count":19,"preview_urls":81},365366,962084931830,"Jacob","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","A joint learning approach for automated diagnosis of keratinocyte carcinoma using optical attenuation coefficients","Keratinocyte carcinoma, including actinic keratosis and basal cell carcinoma, presents with similar clinical appearances yet differs strongly in prognosis and therapy, making effective screening critical. Optical coherence tomography enables diagnosis using signal intensity and layer thickness, but patient skin variability and system settings complicate standardization. The study proposes automated classification using optical attenuation coefficients (OAC) combined with a joint learning strategy and added probability distribution information, achieving accuracy above 80% and nearing 100% with 3D OAC data for robust early-stage non-melanoma skin cancer detection.","npj | digital medicine Article  \n\n| Published in partnership with Seoul National University Bundang Hospital |  | |\n| --- | --- | --- |\n| [https://doi.org/10.1038/s41746-025-01634-x](https://doi.org/10.1038/s41746-025-01634-x) |  |  |\n| A joint learning approach for automated diagnosis of keratinocyte carcinoma using optical attenuation coefﬁcients\u003Cbr> Check for updates |  |  |\n| Lei Zhang1, Xiaoran Li1, Wen Chen1, Yuanjie Gu1, Hao Wu2 , Zhong Lu2  & Biqin Dong1  |  |  |\n| Keratinocyte carcinoma, such as Actinic Keratosis (AK) and Basal Cell Carcinoma (BCC), share similar clinical presentations but differ signiﬁcantly in prognosis and treatment, highlighting the importance of effective screening. Optical coherence tomography(OCT) shows promise for diagnosing AKand BCC using signal intensity and skin layer thickness, but variability due to skin characteristics and system settings underscores the need for a standardized diagnostic method. Here, we propose an automated diagnostic method using the optical attenuation coefﬁcient (OAC) and a joint learning strategy to classify AK, BCC, and normal skin. OAC images extracted from OCT data revealed notable disparities between normal and cancerous tissues. By incorporating probability distribution function (PDF) information alongside OAC images, the model achieved an accuracy of over 80% and approaching 100%by utilizing 3DOAC data to enhance robustness. This approach highlights the potential of OACbased analysis for automated, intelligent diagnosis of early-stage non-melanoma skin cancers. |  |  |\n| Keratinocyte carcinoma (KC), which includes basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and actinic keratosis (AK), is the most common form of skin cancer, accounting for over 95% of all reported cases1. Among them, AK is considered to be a precursor of SCC, which may be transformed into SCC. The global incidence ofKC is estimated to be in the millions annually, with a noticeable rise in recent decades. One of traditional gold standard for in-clinic diagnosis is pathological examination. While histopathological biopsy provides valuable insights, it poses additional burdens on patients in terms of time, cost, and invasiveness. Patients with early-stage cancer often exhibit limited willingness to undergo biopsy procedures due to concerns about the invasive nature of the procedure or associated costs. Therefore, the development of non-invasive detection methods is essential for early skin cancer screening. Currently, dermoscopy and reﬂectance confocal microscopy (RCM), which provide superﬁcial imaging at depths of approximately 100–200 micrometers, optical coherence tomography (OCT), which offers medium-depth imaging ranging from 1 to 3 millimeters, and ultrasound imaging, which enables deep-depth imaging at 3 to 15 millimeters, are increasingly being used as supplementary diagnostic tools, allowing for preliminary diagnoses before biopsy2. Among these methods, OCT stands out due to its high speed, high resolution (3–15 μm), high signal sensitivity, and adequate imaging depth (1–3mm), making it particularly suitable for detecting KC.\u003Cbr>BCC and AK may exhibit certain similarities in their clinical manifestation, such as abnormal growths or rough patches on the skin, | particularly with prolonged sun exposure. However, due to substantial variations in prognosis and treatment strategies for these conditions, it is imperative to prioritize efﬁcient screening methods for patients3. Moreover, AK is a chronic precancerous lesion that typically does not metastasize and can be treated conservatively. In contrast, BCC is a malignant skin tumor that rarely metastasizes but exhibits locally invasive growth, often requiring surgical resection to prevent tissue destruction. Previous studies have deﬁned some morphological criteria for diagnosing BCCs and AKs using OCT4–6. As OCT technology has advanced, it has revealed more structural details of the skin, increasing diagnostic accuracy. These ","cbCairl7Lurq5sjg","https://ap.wps.com/l/cbCairl7Lurq5sjg","pdf",2675003,11,"English","en",105,"# Background\n## Clinical challenge and need for non-invasive screening\n## Current imaging modalities and why OCT is promising\n# Proposed method\n## OAC-based joint learning strategy\n## Role of probability distribution information\n# Results and impact\n## Accuracy performance and robustness\n## Potential for early-stage automated diagnosis","[{\"question\":\"Why are keratinocyte carcinoma subtypes challenging to diagnose?\",\"answer\":\"Actinic keratosis and basal cell carcinoma can look similar clinically, but they have different prognoses and treatment strategies. This makes reliable screening essential.\"},{\"question\":\"How does the proposed method use optical attenuation coefficients?\",\"answer\":\"It extracts optical attenuation coefficient (OAC) images from OCT data and feeds them into a joint learning classification approach, with probability distribution function information added to improve discrimination.\"},{\"question\":\"What performance does the method report for classifying skin tissues?\",\"answer\":\"The method reaches accuracy above 80% and approaches 100% when using 3D OAC data, indicating strong robustness for automated early-stage diagnosis.\"}]","A joint learning approach for automated diagnosis of keratinocyte carcinoma using optical attenuation coefficients | PDF",1790160741,25,[82,86,90,95],{"page_no":8,"url":83,"width":84,"height":85},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6d9d4e4a1d6036eff4ab11b5ccf5fcb2.webp",983,1305,{"page_no":14,"url":87,"width":88,"height":89},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7e91f98aeebe27bc8c2e5776583fc3be.webp",982,1304,{"page_no":91,"url":92,"width":93,"height":94},3,"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c2af4fb6fcb22a34a2f7fd0649fb9a7a.webp",981,1303,{"page_no":19,"url":96,"width":97,"height":98},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/40457adec6e9fbfe49a3663aab64b7a3.webp",980,1301,{"code":4,"msg":100,"data":101},"ok",{"site_id":75,"language":74,"slug":102,"title":65,"keywords":103,"description":66,"schema_data":104,"social_meta":157,"head_meta":159,"extra_data":161,"updated_unix":162},"a-joint-learning-approach-for-automated-diagnosis-of-keratinocyte-carcinoma-using-optical-attenuation-coefficients","",{"@graph":105,"@context":156},[106,119,139],{"@type":107,"itemListElement":108},"BreadcrumbList",[109,113,115,117],{"item":110,"name":111,"@type":112,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":114,"name":9,"@type":112,"position":14},"https://docshare.wps.com/document/",{"item":116,"name":40,"@type":112,"position":91},"https://docshare.wps.com/document/research-report/",{"item":118,"name":65,"@type":112,"position":19},"https://docshare.wps.com/document/a-joint-learning-approach-for-automated-diagnosis-of-keratinocyte-carcinoma-using-optical-attenuation-coefficients/365366/",{"url":118,"name":65,"@type":120,"image":121,"author":126,"headline":65,"publisher":128,"fileFormat":131,"inLanguage":74,"description":66,"dateModified":132,"datePublished":133,"encodingFormat":131,"isAccessibleForFree":134,"interactionStatistic":135},"DigitalDocument",{"url":122,"@type":123,"width":124,"height":125},"https://docshare.wps.com/thumbnails/a-joint-learning-approach-for-automated-diagnosis-of-keratinocyte-carcinoma-using-optical-attenuation-coefficients/365366.png","ImageObject",300,407,{"name":63,"@type":127},"Person",{"url":110,"name":129,"@type":130},"DocShare","Organization","application/pdf","2026-11-16","2026-09-23",true,{"@type":136,"interactionType":137,"userInteractionCount":72},"InteractionCounter",{"@type":138},"ViewAction",{"@type":140,"mainEntity":141},"FAQPage",[142,148,152],{"name":143,"@type":144,"acceptedAnswer":145},"Why are keratinocyte carcinoma subtypes challenging to diagnose?","Question",{"text":146,"@type":147},"Actinic keratosis and basal cell carcinoma can look similar clinically, but they have different prognoses and treatment strategies. This makes reliable screening essential.","Answer",{"name":149,"@type":144,"acceptedAnswer":150},"How does the proposed method use optical attenuation coefficients?",{"text":151,"@type":147},"It extracts optical attenuation coefficient (OAC) images from OCT data and feeds them into a joint learning classification approach, with probability distribution function information added to improve discrimination.",{"name":153,"@type":144,"acceptedAnswer":154},"What performance does the method report for classifying skin tissues?",{"text":155,"@type":147},"The method reaches accuracy above 80% and approaches 100% when using 3D OAC data, indicating strong robustness for automated early-stage diagnosis.","https://schema.org",{"og:url":118,"og:type":158,"og:title":65,"og:site_name":129,"og:description":66},"article",{"robots":160,"canonical":118},"index,follow",{"doc_id":61,"site_id":75},1790333077]