[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-367702-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-367702-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","aktransu-net-transformer-equipped-u-net-model-for-improved-actinic-keratosis-detection-in-clinical-photography","AKtransU-Net - Transformer-Equipped U-Net Model for Improved Actinic Keratosis Detection in Clinical Photography","","Integrating artificial intelligence into clinical photography enables more effective monitoring of skin conditions such as actinic keratosis (AK) and skin field cancerization. Precise AK assessment requires not only lesion morphology but also contextual cues, including surrounding photodamage, motivating models that merge fine local features with global understanding. AKTransU-net introduces a hybrid U-net architecture with Transformer blocks enhanced via ConvLSTM modules in skip connections. Evaluations using 569 annotated clinical photographs show improved whole-image lesion segmentation, reporting a median Dice score of 65.13%, supporting context-aware AK monitoring in clinical settings.",{"@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/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/aktransu-net-transformer-equipped-u-net-model-for-improved-actinic-keratosis-detection-in-clinical-photography/367702/",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/aktransu-net-transformer-equipped-u-net-model-for-improved-actinic-keratosis-detection-in-clinical-photography/367702.png","ImageObject",300,407,{"name":42,"@type":43},"McQueen","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-13","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",14,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does AKTransU-net address in actinic keratosis detection?","Question",{"text":63,"@type":64},"It targets the limitations of relying only on lesion morphology by combining local fine-grained features with global contextual cues from clinical photographs.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is AKTransU-net designed to capture both local and global context?",{"text":68,"@type":64},"It uses a hybrid U-net-based architecture that adds Transformer blocks for richer feature representations, with ConvLSTM modules included within skip connections to improve continuity and semantic coherence.",{"name":70,"@type":61,"acceptedAnswer":71},"How was the model evaluated and what performance metric was reported?",{"text":72,"@type":64},"A proprietary dataset of 569 clinical photographs from 115 patients was used for training and evaluation, with whole-image assessments producing a median Dice score of 65.13%.","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},367702,1790218147,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"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":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"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":112,"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":118,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":104,"preview_page_count":33,"preview_urls":145},5909890329169,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Article  \nAKtransU-Net: Transformer-Equipped U-Net Model for  \nImproved Actinic Keratosis Detection in Clinical Photography  \nPanagiotis Derekas 1, Charalampos Theodoridis 2, Aristidis Likas 2, Ioannis Bassukas 3, Georgios Gaitanis 3, Athanasia Zampeta 3, Despina Exadaktylou 4 and Panagiota Spyridonos 1, *  \nAcademic Editor: Choon ChiatOh  \nReceived: 3 June 2025  \nRevised: 8 July 2025  \nAccepted: 9 July 2025  \nPublished: 10 July 2025  \nCitation: Derekas, P.; Theodoridis, C.; Likas, A.; Bassukas, I.; Gaitanis, G.; Zampeta, A.; Exadaktylou, D.;  \nSpyridonos, P. AKtransU-Net: Transformer-Equipped U-Net Model for Improved Actinic Keratosis Detection in Clinical Photography. Diagnostics 2025, 15, 1752 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics15141752  \nCopyright: © 2025 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 ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Department of Medical Physics, Faculty of Medicine, School of Health Sciences, University of Ioannina, 45110 Ioannina, Greece; [p.derekas@uoi.gr](p.derekas@uoi.gr)  \n2 Department of Computer Science & Engineering, School of Engineering, University of Ioannina,  \n45110 Ioannina, Greece; [theodoridisxaris01@gmail.com](theodoridisxaris01@gmail.com) (C.T.); [arly@uoi.gr](arly@uoi.gr) (A.L.)  \n3 Department of Skin and Venereal Diseases, Faculty of Medicine, School of Health Sciences, University of Ioannina, 45110 Ioannina, Greece; [ibassuka@uoi.gr](ibassuka@uoi.gr) (I.B.); [ggaitan@uoi.gr](ggaitan@uoi.gr) (G.G.); [athanasiazampeta@gmail.com](athanasiazampeta@gmail.com) (A.Z.)  \n4 Department of Dermatology, General Hospital of Nikaia—Piraeus “Agios Panteleimon”, 18454 Nikaia, Greece; [deppie@gmail.com](deppie@gmail.com)  \n* [Correspondence: pspyrid@uoi.gr](Correspondence: pspyrid@uoi.gr)  \nAbstract  \nBackground: Integrating artificial intelligence into clinical photography offers great potential for monitoring skin conditions such as actinic keratosis (AK) and skin field cancerization. Identifying the extent of AK lesions often requires more than analyzing lesion morphology—it also depends on contextual cues, such as surrounding photodamage. This highlights the need for models that can combine fine-grained local features with a comprehensive global view. Methods: To address this challenge, we propose AKTransU-net, a hybrid U-net-based architecture. The model incorporates Transformer blocks to enrich feature representations, which are passed through ConvLSTM modules within the skip connections. This configuration allows the network to maintain semantic coherence and spatial continuity in AK detection. This global awareness is critical when applying the model to whole-image detection via tile-based processing, where continuity across tile boundaries is essential for accurate and reliable lesion segmentation. Results: The effectiveness of AKTransU-net was demonstrated through comparative evaluations with state-of-the-art segmentation models. A proprietary annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis was used to train and evaluate the models. From each photograph, crops of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions indifferent positions and captured different contexts. AKtransU-net exhibited a more robust context awareness and achieved a median Dice score of 65.13%, demonstrating significant progress in whole-image assessments. Conclusions: Transformer-driven context modeling offers a promising approach for robust AK lesion monitoring, supporting its application in real-world clinical settings where accurate, context-aware analysis is crucial for managing skin field cancerization.  \nKeywords: medical image segmentation; U","cbCaiqBKkuEOA4kY","https://ap.wps.com/l/cbCaiqBKkuEOA4kY","pdf",4035090,"English","# Abstract\n# Introduction\n## Actinic keratoses as precancerous lesions\n## Challenges of AK burden assessment\n## Need for objective, reproducible approaches\n## Role of clinical photography in dermatology","[{\"question\":\"What problem does AKTransU-net address in actinic keratosis detection?\",\"answer\":\"It targets the limitations of relying only on lesion morphology by combining local fine-grained features with global contextual cues from clinical photographs.\"},{\"question\":\"How is AKTransU-net designed to capture both local and global context?\",\"answer\":\"It uses a hybrid U-net-based architecture that adds Transformer blocks for richer feature representations, with ConvLSTM modules included within skip connections to improve continuity and semantic coherence.\"},{\"question\":\"How was the model evaluated and what performance metric was reported?\",\"answer\":\"A proprietary dataset of 569 clinical photographs from 115 patients was used for training and evaluation, with whole-image assessments producing a median Dice score of 65.13%.\"}]","AKtransU-Net - Transformer-Equipped U-Net Model for Improved Actinic Keratosis Detection in Clinical Photography | PDF",1790172147,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2c01a991364f07be07df7f8b037de9fa.webp",983,1390,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/60ace4e62470f6b533aca89ab2442907.webp",982,1388,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c38049626b011a2d7ee783d4264f5e06.webp",981,1387,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a4ed7fd2a9f4ef54a03957d41268abc3.webp",980,1385]