Identifying Malignant Skin Diseases Through Deep Learning
DOI:
https://doi.org/10.22456/2175-2745.143463Keywords:
Deep Learning, Skin Diseases, Medicine, Classification, Data AugmentationAbstract
Early and accurate identification of malignant skin diseases is critical to improving treatment outcomes and patient prognosis. Current diagnostic methods heavily rely on visual assessments by medical professionals, followed by biopsies for confirmation. These approaches can be subjective and require significant expertise, while access to specialized care remains limited, particularly in developing regions. Recent advancements in artificial intelligence, specifically deep learning, present an opportunity to improve dermatological diagnostics. This paper explores the application of two deep learning models, ResNet and Vision Transformer (ViT), for the automated detection of malignant skin conditions. Both models were trained on the PAD-UFES-20 dataset, which comprises clinical skin lesion images captured via smartphones. Our findings suggest that these models can offer real-time diagnostic support at reduced costs, with accuracy levels comparable to or exceeding human performance, with the best experiment achieving the F1 score of 79.89% and an accuracy of 80.63%.
Downloads
References
DEKONINCK, B.; CHRISTENBERY, T. Skin cancer screening in the medically underserved population: A unique opportunity for APNs to make a difference. Journal of the American Association of Nurse Practitioners, LWW, v. 27, n. 9, p. 501–506, 2015.
WILLEMINK, M.; ROTH, H.; SANDFORT, V. Toward foundational deep learning models for medical imaging in the new era of transformer networks. Radiology: Artificial Intelligence, Radiological Society of North America, v. 4, n. 5, p. e210284, 2022.
SAEED, M. et al. The power of generative AI to augment for enhanced skin cancer classification: A deep learning approach. IEEE Access, IEEE, 2023.
LECUN, Y. et al. Gradient-based learning applied to document recognition. Proceedings of the IEEE, IEEE, v. 86, n. 11, p. 2278–2324, 1998.
HAN, K. et al. A survey on vision transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, v. 45, n. 1, p. 87–110, 2022.
HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2016. p. 770–778.
DOSOVITSKIY, A. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
PACHECO, A. G. et al. PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data in Brief, v. 32, p. 106221, 2020. ISSN 2352-3409.
SHEHZAD, K. et al. A deep-ensemble-learning-based approach for skin cancer diagnosis. Electronics, v. 12, n. 6, 2023. ISSN 2079-9292.
FLOSDORF, C. et al. Skin Cancer Detection utilizing Deep Learning: Classification of Skin Lesion Images using a Vision Transformer. 2024. Disponível em: https://arxiv.org/abs/2407.18554.
SAKLI, M. et al. Deep learning-based multi-stage analysis for accurate skin cancer diagnosis using a lightweight CNN architecture. In: 2023 International Conference on Innovations in Intelligent Systems and Applications (INISTA). [S.l.: s.n.], 2023. p. 1–6.
TSCHANDL, P. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. [S.l.]: Harvard Dataverse, 2018.
CARMO, N.; MARI, J. A comparative study of convolutional neural networks for classification of pigmented skin lesions. In: Anais do XVII Workshop de Visão Computacional. Porto Alegre, RS, Brasil: SBC, 2021. p. 171–176. ISSN 0000-0000.
NANCY, V. A. O.; PRABHAVATHY, P.; ARYA, M. S. WEL-ODKC: Weighted extreme learning optimal diagonal-kernels convolution model for accurate classification of skin lesions. The Imaging Science Journal, Taylor & Francis, v. 71, n. 4, p. 362–377, 2023.
NIJHAWAN, R.; BHATNAGAR, D.; ROY, S. Diagnosing skin lesion using multi-modal analysis. In: 2022 5th International Conference on Computational Intelligence and Networks (CINE). [S.l.: s.n.], 2022. p. 1–5.
LIMA, L. M. de; KROHLING, R. A. Exploring advances in transformers and CNN for skin lesion diagnosis on small datasets. In: XAVIER-JUNIOR, J. C.; RIOS, R. A. (Ed.). Intelligent Systems. Cham: Springer International Publishing, 2022. p. 282–296. ISBN 978-3-031-21689-3.
HE, K. et al. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015. Disponível em: http://arxiv.org/abs/1512.03385.
DOSOVITSKIY, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. CoRR, abs/2010.11929, 2020. Disponível em: https://arxiv.org/abs/2010.11929.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Gabriel Mota, Matheus da Silva, João Mari, André Backes
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autorizo aos editores a publicação de meu artigo, caso seja aceito, em meio eletrônico de acordo com as regras do Public Knowledge Project.Accepted 2025-01-03
Published 2025-02-20
