{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T06:47:56Z","timestamp":1782197276882,"version":"3.54.5"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Dermoscopic skin lesion classification is challenged by class imbalance and the underutilization of clinical metadata, limiting the diagnostic reliability of existing deep learning systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Building upon a Vision Transformer baseline that fuses dermoscopic images with patient metadata via cross-modal attention, we introduce three complementary improvements: class-balanced focal loss with square-root effective-number sampling, a patch-level cross-attention metadata-guided attention module, and supervised contrastive regularization. The extended model is evaluated on the ISIC 2019 and BCN 20000 datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Ablation studies demonstrate consistent improvements. On the ISIC 2019 validation set, the full model achieves a Macro AUC of 0.9613 and a Macro balanced accuracy of 0.8426, with strong performance on rare categories such as dermatofibroma (AUC = 0.991) and vascular lesions (AUC = 0.999).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Principled loss design, spatially aware fusion, and representation-level regularization jointly improve the robustness of skin lesion classification under extreme class imbalance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1841617","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T06:12:11Z","timestamp":1782195131000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive class rebalancing and spatial-aware metadata fusion for long-tailed skin lesion classification"],"prefix":"10.3389","volume":"13","author":[{"given":"Tianming","family":"Ma","sequence":"first","affiliation":[{"name":"The Second Affiliated Hospital of Heilongjiang University of Chinese Medicine","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianwei","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Shenyang Seventh People's Hospital","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guijun","family":"Liu","sequence":"additional","affiliation":[{"name":"Heilongjiang University of Chinese Medicine","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-981-33-4638-3_1","article-title":"Dermoscopy: an overview of the principles, procedure and practice","author":"Adya","year":"2021","journal-title":"Dermoscopy"},{"key":"B3","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":"B4","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.ejca.2019.04.001","article-title":"Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task","volume":"113","author":"Brinker","year":"2019","journal-title":"Eur J Cancer"},{"key":"B5","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/ISBI.2018.8363547","article-title":"Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic)","volume-title":"2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018)","author":"Codella","year":"2018"},{"key":"B6","article-title":"Automated skin lesion classification using ensemble of deep neural networks in isic 2018: skin lesion analysis towards melanoma detection challenge","author":"Milton","year":"2019","journal-title":"arXiv Preprint arXiv:190110802"},{"key":"B7","doi-asserted-by":"publisher","first-page":"100864","DOI":"10.1016\/j.mex.2020.100864","article-title":"Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data","volume":"7","author":"Gessert","year":"2020","journal-title":"MethodsX"},{"key":"B8","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1109\/ISBI.2017.7950523","article-title":"Knowledge transfer for melanoma screening with deep learning","volume-title":"2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017)","author":"Menegola","year":"2017"},{"key":"B9","doi-asserted-by":"publisher","first-page":"102535","DOI":"10.1016\/j.media.2022.102535","article-title":"Adversarial multimodal fusion with attention mechanism for skin lesion classification using clinical and dermoscopic images","volume":"81","author":"Wang","year":"2022","journal-title":"Med Image Anal"},{"key":"B10","doi-asserted-by":"publisher","first-page":"106712","DOI":"10.1016\/j.compbiomed.2023.106712","article-title":"TFormer: a throughout fusion transformer for multi-modal skin lesion diagnosis","volume":"157","author":"Zhang","year":"2023","journal-title":"Comput Biol Med"},{"key":"B11","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Cui","year":"2019"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/ICCV.2017.324","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"B13","doi-asserted-by":"publisher","first-page":"18661","DOI":"10.5555\/3495724.3497291","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1093\/annonc\/mdy520","article-title":"Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists","volume":"29","author":"Haenssle","year":"2018","journal-title":"Ann Oncol"},{"key":"B15","first-page":"12626","article-title":"Day-night cross-domain vehicle re-identification","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Li","year":"2024"},{"key":"B16","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/978-3-030-57321-8_11","article-title":"A study on the fusion of pixels and patient metadata in CNN-based classification of skin lesion images","volume-title":"International cross-domain conference for machine learning and knowledge extraction","author":"Nunnari","year":"2020"},{"key":"B17","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv Preprint arXiv:201011929"},{"key":"B18","first-page":"268","article-title":"Skindistilvit: lightweight vision transformer for skin lesion classification","volume-title":"International conference on artificial neural networks","author":"Lungu-Stan","year":"2023"},{"key":"B19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv Preprint arXiv:14091556"},{"key":"B20","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He","year":"2016"},{"key":"B21","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Huang","year":"2017"},{"key":"B22","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"B23","first-page":"11976","article-title":"A convnet for the (2020s)","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Liu","year":"2022"},{"key":"B24","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1841617\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T06:12:14Z","timestamp":1782195134000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1841617\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":24,"alternative-id":["10.3389\/fmed.2026.1841617"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1841617","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"article-number":"1841617"}}