{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:25:04Z","timestamp":1758043504479,"version":"3.44.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Malignant melanoma is the deadliest skin cancer, yet its early dermoscopic presentation closely mimics benign melanocytic nevi. Conventional visual or dermoscopic screening therefore suffers from high miss rates and generates excessive biopsies. In this study we focus on Chinese East-Asian patients and introduce a reversed-exclusion strategy\u2014classifying \u201cbenign first, exclude malignancy\u201d: lesions that fully meet benign nevus criteria are deemed low-risk; all others are flagged as high-risk. Building on the real-time detector YOLOv10, we incorporate three medical-oriented upgrades: (i) a PP-LCNet backbone to preserve sub-3\u202fmm textures; (ii) a Multiscale Contextual Attention (MCA) neck to enhance cross-scale aggregation; and (iii) a Shape-IoU loss that jointly optimises position, scale, and curvature. The model was trained on a multi-centre dermoscopic dataset from three tertiary hospitals in mainland China (2,040 benign nevi) and independently tested on 365 biopsy-proven melanomas collected at the same medical institution but drawn from a demographically distinct patient cohort, achieving a detection mAP@0.5 of 97.69% for benign lesions and a melanoma false-negative rate (FNR) of only 0.27%. By delivering high-confidence benign identification followed by malignant exclusion, the proposed model offers a high-precision, low-risk pathway for early melanoma screening in Chinese clinical settings. It can markedly reduce unnecessary biopsies while keeping the miss rate below the clinical safety ceiling of 0.5%, thus preserving the life-saving window afforded by early detection.<\/jats:p>","DOI":"10.3389\/frai.2025.1637842","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T07:38:20Z","timestamp":1757662700000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["YOLOv10-based detection of melanocytic nevi: reverse exclusion optimization for melanoma screening"],"prefix":"10.3389","volume":"8","author":[{"given":"ShengJie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"ref1","author":"Akash","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3390\/info8030089","article-title":"Fuzzy color clustering for melanoma diagnosis in dermoscopy images","volume":"8","author":"Almubarak","year":"2017","journal-title":"Information"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"20240381","DOI":"10.1515\/jisys-2024-0381","article-title":"A comprehensive review of deep learning and machine learning techniques for early-stage skin cancer detection: challenges and research gaps","volume":"34","author":"Alzamili","year":"2025","journal-title":"J. Intell. Syst."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"20552076221109502","DOI":"10.1177\/20552076221109502","article-title":"Preparing infection detection technology for hospital-at-home after lower-limb external fixation","volume":"8","author":"Annadatha","year":"2022","journal-title":"Digit. Health."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1097\/01.MP.0000082394.91761.E5","article-title":"Grading of atypia in nevi: correlation with melanoma risk","volume":"16","author":"Arumi-Uria","year":"2003","journal-title":"Mod. Pathol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"W1","DOI":"10.7326\/0003-4819-138-1-200301070-00012-W1","article-title":"The STARD statement for reporting studies of diagnostic accuracy: explanation and elaboration","volume":"138","author":"Bossuyt","year":"2003","journal-title":"Ann. Intern. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"4961","DOI":"10.3390\/s23104961","article-title":"Corner-point and foreground-area IoU loss: better localization of small objects in bounding-box regression","volume":"23","author":"Cai","year":"2023","journal-title":"Sensors"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1001\/jamadermatol.2017.0129","article-title":"Dermoscopic clues for diagnosing melanomas that resemble seborrheic keratosis","volume":"153","author":"Carrera","year":"","journal-title":"JAMA Dermatol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1159\/000486851","article-title":"Dermoscopy improves the diagnostic accuracy of melanomas clinically resembling seborrheic keratosis: a cross-sectional study","volume":"233","author":"Carrera","year":"","journal-title":"Dermatology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.05006","article-title":"Skin lesion analysis toward melanoma detection: a challenge at ISBI 2017 (ISIC)","author":"Codella","year":"2017","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.15099","article-title":"PP-lcnet: a lightweight CPU convolutional neural network","author":"Cui","year":"2021","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"CD011902","DOI":"10.1002\/14651858.CD011902.pub2","article-title":"Dermoscopy, with and without visual inspection, for diagnosing melanoma in adults","volume":"12","author":"Dinnes","year":"2018","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref11","volume-title":"Evolution of YOLO algorithm and YOLOv5: The state-of-the-art object detection algorithm","author":"Do","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.det.2012.04.012","article-title":"New diagnostic aides for melanoma","volume":"30","author":"Ferris","year":"2012","journal-title":"Dermatol. Clin."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1111\/j.1468-3083.2006.01864.x","article-title":"Border sharpness of benign nevi in dermoscopic images","volume":"21","author":"Fikrle","year":"2007","journal-title":"J. Eur. Acad. Dermatol. Venereol."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.18554","article-title":"Skin Cancer detection utilizing deep learning: classification of skin lesion images using a vision transformer","author":"Flosdorf","year":"2024","journal-title":"arXiv"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/BF03000228","article-title":"Symmetry features of melanocytic nevi","volume":"5","author":"Flotte","year":"1992","journal-title":"Mod. Pathol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.jaad.2006.09.003","article-title":"The CASH algorithm for dermoscopy","volume":"56","author":"Henning","year":"2007","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.3390\/life13091907","article-title":"Exploring small-diameter melanomas: a retrospective study on clinical and Dermoscopic features","volume":"13","author":"Hunziker","year":"2023","journal-title":"Life"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2410.17725","DOI":"10.48550\/arXiv.2410.17725","article-title":"YOLOv11: an overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"820474","DOI":"10.1155\/2012\/820474","article-title":"New trends in dermoscopy to minimise the risk of missing melanoma","volume":"2012","author":"Lallas","year":"2012","journal-title":"J. Skin Cancer"},{"key":"ref23","first-page":"21","article-title":"SSD: Single shot MultiBox detector","volume-title":"Computer Vision \u2013 ECCV","author":"Liu","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.3390\/diagnostics13132139","article-title":"Accuracy of a smartphone-based YOLO application for classification of melanomas, melanocytic nevi, and seborrheic keratoses","volume":"13","author":"Liutkus","year":"2023","journal-title":"Diagnostics"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s12885-024-13423-y","article-title":"Diagnosis and prognosis of melanoma from Dermoscopy images using machine learning and deep learning: a systematic literature review","volume":"25","author":"Naseri","year":"2025","journal-title":"BMC Cancer"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1109\/TMI.2021.3122835","article-title":"Circle representation for medical object detection","volume":"41","author":"Nguyen","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/s41597-021-00815-z","article-title":"A patient-centric dataset of images and metadata for identifying melanomas using clinical context","volume":"8","author":"Rotemberg","year":"2021","journal-title":"Sci Data"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1111\/j.0909-725X.2005.00123.x","article-title":"Pigment distribution in melanocytic lesion images: a digital parameter to be employed for computer\u2010aided diagnosis","volume":"11","author":"Seidenari","year":"2005","journal-title":"Skin Res Technol."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.02353","article-title":"Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification","author":"Shen","year":"2021","journal-title":"arXiv"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1007\/978-981-99-7962-2_39","article-title":"A review on YOLOv8 and its advancements","volume-title":"Data intelligence and cognitive informatics","author":"Sohan","year":"2024"},{"key":"ref32","first-page":"56","article-title":"Aortic aneurysm detection in CT medical images based on YOLOv5","volume-title":"Acad. J. Comput. Inf. Sci.","author":"Song","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1245\/s10434-006-9240-4","article-title":"Method of biopsy and incidence of positive margins in primary melanoma","volume":"14","author":"Stell","year":"2007","journal-title":"Ann. Surg. Oncol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"19","DOI":"10.5826\/dpc.0304a05","article-title":"Systematic review of diagnostic accuracy of reflectance confocal microscopy for melanoma diagnosis in clinically equivocal lesions","volume":"3","author":"Stevenson","year":"2013","journal-title":"Dermatol. Pract. Concept."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1159\/000017969","article-title":"Semiological value of ABCDE criteria in the diagnosis of cutaneous pigmented tumors","volume":"197","author":"Thomas","year":"1998","journal-title":"Dermatology"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/j.jaad.2014.01.887","article-title":"Early detection of melanoma: reviewing the ABCDEs","volume":"72","author":"Tsao","year":"2015","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1038\/s41591-020-0942-0","article-title":"Human\u2013computer collaboration for skin cancer recognition","volume":"26","author":"Tschandl","year":"2020","journal-title":"Nat. Med."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"adv00343","DOI":"10.2340\/00015555-3696","article-title":"Cumulative-sum analysis for the learning curve of optical coherence tomography-assisted diagnosis of basal cell carcinoma","volume":"100","author":"Van Loo","year":"2020","journal-title":"Acta Derm. Venereol."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.14458","article-title":"YOLOv10: real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref40","first-page":"1","article-title":"YOLOv9: learning what you want to learn using programmable gradient information","volume-title":"Computer vision \u2013 ECCV 2024","author":"Wang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1001\/archinte.157.9.985","article-title":"Primary-care clinicians\u2019 performance for detecting actinic keratoses and skin cancer","volume":"157","author":"Whited","year":"1997","journal-title":"Arch. Intern. Med."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.3390\/s24092896","article-title":"YOLOv8-RMDA: lightweight YOLOv8 network for early detection of small target diseases in tea","volume":"24","author":"Ye","year":"2024","journal-title":"Sensors"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"107079","DOI":"10.1016\/j.engappai.2023.107079","article-title":"MCA: multidimensional collaborative attention in deep convolutional neural networks for image recognition","volume":"126","author":"Yu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.17663","article-title":"Shape-iou: more accurate metric considering bounding-box shape and scale","author":"Zhang","year":"2023","journal-title":"arXiv"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1637842\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T07:38:24Z","timestamp":1757662704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1637842\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":44,"alternative-id":["10.3389\/frai.2025.1637842"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1637842","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"article-number":"1637842"}}