[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123076-en":3,"doc-seo-123076-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123076,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",7,"Healthcare","AI-Assisted Detection and Localization of Spinal Metastatic Lesions","Integration of machine learning and radiomics has advanced diagnostic and prognostic performance in medical imaging. This study develops and validates an AI model based on U-Net variants to detect and segment spinal metastases from computed tomography (CT), covering both osteolytic and osteoblastic lesions. The approach uses a vertebra dataset from 115 polytrauma patients and a metastasis dataset from 38 patients. Results show high vertebra segmentation (DSC 0.87–0.96) and metastasis segmentation (DSC 0.71; F-beta 0.68 for lytic), while sclerotic lesions remain more challenging (DSC 0.61; F-beta 0.57). The model can identify isolated metastatic lesions beyond the spine, supporting second-opinion workflows, with further refinement and diversified training data needed. An annotated CT dataset is provided for future research.","Technical Note  \nAI-Assisted Detection and Localization of Spinal Metastatic Lesions  \nEdgars Edelmers 1,2, *, Artrs N, ikuins 2, Klinta Lu¯ıze Sprdža 1, Patr¯ıcija Stapulone 1, Niks Saimons Pce 2, Elizabete Skrebele 3, Everita El¯ına Sin, icina 4, Viktorija C¯ırule 5, Ance Kazuša 1 and Katrina Boloˇcko 6  \nCitation: Edelmers, E.; N, ikuins, A.; Sprdža, K.L.; Stapulone, P.; Pce, N.S.; Skrebele, E.; Sin, icina, E.E.; Crule, V.; Kazuša, A.; Bolocko,ˇ K. AI-Assisted Detection and Localization of Spinal Metastatic Lesions. Diagnostics 2024, 14, 2458 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics14212458  \nAcademic Editor: Jae-Ho Han  \nReceived: 26 September 2024  \nRevised: 29 October 2024  \nAccepted: 2 November 2024  \nPublished: 3 November 2024  \nCopyright: © 2024 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://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Faculty of Medicine, Rga Stradin, š University, LV-1010 Riga, Latvia; [040214@rsu.edu.lv](040214@rsu.edu.lv) (K.L.S.); [040230@rsu.edu.lv](040230@rsu.edu.lv) (P.S.); [032155@rsu.edu.lv](032155@rsu.edu.lv) (A.K.)  \n2 Faculty of Computer Science, Information Technology and Energy, Riga Technical University, LV-1048 Riga, Latvia; [arturs.nikulins@edu.rtu.lv](arturs.nikulins@edu.rtu.lv) (A.N, .); [niks-saimons.puce@edu.rtu.lv](niks-saimons.puce@edu.rtu.lv) (N.S.P.)  \n3 Faculty of Civil and Mechanical Engineering, Riga Technical University, LV-1048 Riga, Latvia; [elizabete.skrebele@edu.rtu.lv](elizabete.skrebele@edu.rtu.lv)  \n4 Faculty of Biology, University of Latvia, LV-1004 Riga, Latvia; [everita.elina@biomed.lu.lv](everita.elina@biomed.lu.lv)  \n5 Department of Radiology, Faculty of Medicine, Rga Stradin, š University, LV-1010 Riga, Latvia; [vikdem@rsu.lv](vikdem@rsu.lv)  \n[6](6 Department of Computer Graphics and Computer Vision)[ Department of Computer Graphics and Computer Vision](6 Department of Computer Graphics and Computer Vision), [Riga Technical University](Riga Technical University), [LV-1048 Riga](LV-1048 Riga), [Latvia](Latvia); [katrina.bolocko@rtu.lv](katrina.bolocko@rtu.lv)  \n* Correspondence: [edgars.edelmers@rsu.lv](edgars.edelmers@rsu.lv)  \nAbstract: Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96 . For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particu","cbCaithyHHSc7cQt","https://ap.wps.com/l/cbCaithyHHSc7cQt","pdf",3802526,1,14,"English","en",105,"# Introduction\n## Machine Learning in Healthcare\n# Methods\n## Model architecture and datasets\n# Results\n## Vertebra segmentation performance\n## Metastasis segmentation performance\n# Discussion and Conclusions","[{\"question\":\"How does the AI model detect and localize spinal metastases?\",\"answer\":\"It uses U-Net architecture variants to perform segmentation on computed tomography (CT) images, targeting both vertebra regions and metastatic lesions.\"},{\"question\":\"What datasets were used to train and validate the model?\",\"answer\":\"Two datasets were used: 115 polytrauma patients for vertebra segmentation and 38 patients with documented spinal metastases for lesion detection.\"},{\"question\":\"How did the model perform on osteolytic versus osteoblastic (sclerotic) lesions?\",\"answer\":\"Lytic lesions achieved DSC 0.71 and F-beta 0.68, whereas sclerotic lesions were more difficult, with DSC 0.61 and F-beta 0.57 due to dense, subtle bone alterations.\"}]","AI-Assisted Detection and Localization of Spinal Metastatic Lesions | PDF",1785814526,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"ai-assisted-detection-and-localization-of-spinal-metastatic-lesions","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/ai-assisted-detection-and-localization-of-spinal-metastatic-lesions/123076/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the AI model detect and localize spinal metastases?","Question",{"text":75,"@type":76},"It uses U-Net architecture variants to perform segmentation on computed tomography (CT) images, targeting both vertebra regions and metastatic lesions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What datasets were used to train and validate the model?",{"text":80,"@type":76},"Two datasets were used: 115 polytrauma patients for vertebra segmentation and 38 patients with documented spinal metastases for lesion detection.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the model perform on osteolytic versus osteoblastic (sclerotic) lesions?",{"text":84,"@type":76},"Lytic lesions achieved DSC 0.71 and F-beta 0.68, whereas sclerotic lesions were more difficult, with DSC 0.61 and F-beta 0.57 due to dense, subtle bone alterations.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]