{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T09:56:53Z","timestamp":1792231013980,"version":"4.4.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Skin cancer is one of the most common malignancies worldwide, and early-stage diagnosis remains challenging due to its morphological similarity to benign lesions. Most existing computer-aided diagnostic systems rely on single static images, overlooking temporal information that is critical for distinguishing progressive malignancy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a novel multi-agent spatiotemporal fusion framework to enhance diagnostic accuracy. The framework consists of three key components: (1) a spatial agent based on a convolutional neural network for high-fidelity static feature extraction; (2) a temporal agent employing gated recurrent units to model longitudinal lesion evolution; and (3) a collaboration agent that dynamically fuses spatial and temporal representations via an attention-based weighting strategy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments on large-scale public dermoscopic datasets showed that our method achieved an accuracy of 94.5%, an F1-score of 93.8%, and an AUC of 0.97\u2014outperforming traditional machine learning models, CNN classifiers, and 3D-CNN baselines. Ablation studies further confirmed the critical contribution of temporal modeling and adaptive fusion, particularly in differentiating early melanoma from atypical nevi.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This work highlights the potential of spatiotemporal modeling to improve early skin cancer detection and provides a promising direction for AI-assisted diagnosis of other chronic diseases requiring longitudinal monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1759960","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T05:26:03Z","timestamp":1772688363000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A novel multi-agent spatiotemporal fusion framework for intelligent skin cancer diagnosis"],"prefix":"10.3389","volume":"16","author":[{"given":"Peiyao","family":"Zheng","sequence":"first","affiliation":[{"name":"College of Traditional Chinese Medicine, Hubei University of Chinese Medicine","place":["Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Yang","sequence":"additional","affiliation":[{"name":"Baotou Medical College, Inner Mongolia University of Science & Technology","place":["Inner Mongolia, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanru","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Inspection, Hebei University of Chinese Medicine","place":["Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqian","family":"Hu","sequence":"additional","affiliation":[{"name":"Hubei Provincial Hospital of Traditional Chinese Medicine","place":["Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41746-024-01031-w","article-title":"Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis","volume":"7","author":"Krakowski","year":"2024","journal-title":"NPJ digital Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/s13671-024-00440-0","article-title":"Skin type diversity in skin lesion datasets: a review","volume":"13","author":"Alipour","year":"2024","journal-title":"Curr Dermatol Rep"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"B4","first-page":"080006","article-title":"Classification of skin cancer images using local binary pattern and SVM classifier","author":"Adjed","year":"2016"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC.2012.6346942","article-title":"On the role of texture and color in the classification of dermoscopy images","author":"Marques","year":"2012"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2013.2271540","article-title":"Two systems for the detection of melanomas in dermoscopy images using texture and color features","volume":"8","author":"Barata","year":"2013","journal-title":"IEEE Syst J"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.011","article-title":"Clinically inspired analysis of dermoscopy images using a generative model","volume":"151","author":"Barata","year":"2016","journal-title":"Comput Vision Image Understanding"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e0274896","DOI":"10.1371\/journal.pone.0274896","article-title":"Skin lesion classification using multi-resolution empirical mode decomposition and local binary pattern","volume":"17","author":"Samsudin","year":"2022","journal-title":"PloS One"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"nature"},{"key":"B10","first-page":"1","article-title":"A review of machine learning and deep learning applications","author":"Shinde","year":"2018"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199","article-title":"review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput"},{"key":"B12","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"B14","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"B15","article-title":"An introduction to convolutional neural networks","author":"O\u2019shea","year":"2015","journal-title":"arXiv preprint arXiv:1511.08458"},{"key":"B16","doi-asserted-by":"publisher","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":"B17","doi-asserted-by":"publisher","first-page":"18134","DOI":"10.1038\/s41598-022-22644-9","article-title":"Skin lesion classification of dermoscopic images using machine learning and convolutional neural network","volume":"12","author":"Shetty","year":"2022","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"100659","DOI":"10.1016\/j.imu.2021.100659","article-title":"An approach for multiclass skin lesion classification based on ensemble learning","volume":"25","author":"Rahman","year":"2021","journal-title":"Inf Med Unlocked"},{"key":"B19","volume-title":"Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International conference on machine learning","author":"Tan","year":"2019"},{"key":"B20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B21","first-page":"1","article-title":"DermNet-CNN: A hyperparameter-tuned CNN model for accurate skin disease detection","volume-title":"Proceedings of the 2025 17th international conference on electronics, computers and artificial intelligence (ECAI)","author":"Das","year":"2025"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1111\/jdv.20479","article-title":"Effect of patient-contextual skin images in human-and artificial intelligence-based diagnosis of melanoma: results from the 2020 SIIM-ISIC melanoma classification challenge","volume":"39","author":"Kurtansky","year":"2025","journal-title":"J Eur Acad Dermatol Venereology"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2022.023178","article-title":"Hybridization of CNN with LBP for classification of melanoma images","volume":"71","author":"Iqbal","year":"2022","journal-title":"Computers Materials Continua"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3120091","article-title":"Early melanoma diagnosis with sequential dermoscopic images","volume":"41","author":"Yu","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW53098.2021.00201","article-title":"Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset","author":"Groh","year":"2021"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decision Making"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.893972","article-title":"Skin cancer classification with deep learning: a systematic review","volume":"12","author":"Wu","year":"2022","journal-title":"Front Oncol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/s41746-023-00872-1","article-title":"Prospective validation of dermoscopy-based open-source artificial intelligence for melanoma diagnosis (PROVE-AI study)","volume":"6","author":"Marchetti","year":"2023","journal-title":"NPJ Digit Med"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.27.10.106007","article-title":"Hyperspectral imaging for tumor segmentation on pigmented skin lesions","volume":"27","author":"Aloupogianni","year":"2022","journal-title":"J Biomed Optics"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109653","article-title":"Facilitating clinically relevant skin tumor diagnostics with spectroscopy-driven machine learning","volume":"27","author":"Andersson","year":"2024","journal-title":"Iscience"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ad.2024.09.030","article-title":"Melanoma diagnosis with 3D total-body photography","author":"Ferreirinha","year":"2025","journal-title":"Actas Dermo-Sifiliogr\u00e1ficas"},{"key":"B32","doi-asserted-by":"publisher","first-page":"112954","DOI":"10.1016\/j.ejca.2023.112954","article-title":"Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening","volume":"190","author":"Cerminara","year":"2023","journal-title":"Eur J Cancer"},{"key":"B33","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: A brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process magazine"},{"key":"B34","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"B36","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2019"},{"key":"B37","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B38","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020"},{"key":"B39","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"Wang","year":"2020"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1759960\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T05:26:05Z","timestamp":1772688365000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1759960\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":39,"alternative-id":["10.3389\/fonc.2026.1759960"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1759960","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]},"article-number":"1759960"}}