2026-04-14T06:57:29Zhttps://recercat.cat/oai/request

oai:recercat.cat:10256/258352024-12-12T04:56:50Zcom_2072_452955com_2072_2054col_2072_452957

Going Smaller: Attention-based models for automated melanoma diagnosis Nazari, Sana García Campos, Rafael European Commission Càncer -- Detecció precoç Cancer -- Early detection Visió per ordinador en medicina Computer vision in medicine Melanoma -- Diagnòstic Melanoma -- Diagnosis Melanoma -- Detecció precoç Melanoma -- Early detection Computational approaches offer a valuable tool to aid with the early diagnosis of melanoma by increasing both the speed and accuracy of doctors’ decisions. The latest and best-performing approaches often rely on large ensemble models, with the number of trained parameters exceeding 600 million. However, this large parameter count presents considerable challenges in terms of computational demands and practical application. Addressing this gap, our work introduces a suite of attention-based convolutional neural network (CNN) architectures tailored to the nuanced classification of melanoma. These innovative models, founded on the EfficientNet-B3 backbone, are characterized by their significantly reduced size. This study highlights the feasibility of deploying powerful, yet compact, diagnostic models in practical settings, such as smartphone-based dermoscopy, and in doing so revolutionizing point-of-care diagnostics and extending the reach of advanced medical technologies to remote and under-resourced areas. It presents a comparative analysis of these novel models with the top three prize winners of the International Skin Imaging Collaboration (ISIC) 2020 challenge using two independent test sets. The results for our architectures outperformed the second and third-placed winners and achieved comparable results to the first-placed winner. These models demonstrated a delicate balance between efficiency and accuracy, holding their ground against larger models in performance metrics while operating on up to 98% less number of parameters and showcasing their potential for real-time application in resource-limited environments This work was partially funded through the European Commission’s Horizon 2020 program through the iToBoS project (grant number SC1-BHC-06-2020-965221) and the IFUDG 2022 grant Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier 3 2025-02 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion peer-reviewed http://hdl.handle.net/10256/25835 39637458 http://hdl.handle.net/10256/25835 eng info:eu-repo/semantics/altIdentifier/doi/10.1016/j.compbiomed.2024.109492 info:eu-repo/semantics/altIdentifier/issn/0010-4825 info:eu-repo/semantics/altIdentifier/eissn/1879-0534 info:eu-repo/grantAgreement/EC/H2020/965221/EU/Intelligent Total Body Scanner for Early Detection of Melanoma/iToBoS Attribution-NonCommercial 4.0 International http://creativecommons.org/licenses/by-nc/4.0/ info:eu-repo/semantics/openAccess application/pdf Elsevier Computers in Biology and Medicine, 2025, vol. 185, art. núm. 109492 Articles publicats (D-ATC)