Artificial intelligence for accessible diagnosis in the identification of melanoma and other skin lesions
DOI:
https://doi.org/10.20983/culcyt.2025.2.2e.6Keywords:
cancer, melanoma, diagnosis, deep learning, convolutional neural networksAbstract
The objective of this social innovation project is to generalize access to accurate diagnostic tools by promoting the implementation of early detection systems in clinical settings with limited resources. The aim is to develop deep learning systems to improve the accuracy of early melanoma detection, which is considered one of the most aggressive forms of skin cancer, emphasizing the need for precise diagnosis to reduce mortality. Through deep learning and transfer learning, the system identifies skin lesions using dermatoscopic images, leveraging pre-trained convolutional neural networks (CNNs) for feature extraction. Transfer learning is used to adapt the specific task of classifying pigmented skin lesions. This approach enables the use of pre-existing knowledge in CNN models to enhance the efficiency and accuracy of melanoma identification. Furthermore, by reducing the need for invasive medical procedures and optimizing resource use in healthcare systems with limited infrastructure, the project contributes to the sustainability of healthcare, promoting more accessible and accurate diagnoses. The development methodology is crucial and is presented in this work, with the expectation that improvements in melanoma detection capabilities will have a positive impact on public health and long-term sustainability.
Downloads
References
A. C. Geller et al., “Advancing Survivors Knowledge (ASK Study) of Skin Cancer Surveillance after Childhood Cancer: A Randomized Controlled Trial in the Childhood Cancer Survivor Study”, J Clin Oncol, vol. 41, n.º 12, pp. 2269-2280, abr. 2023, doi: 10.1200/JCO.22.00408.
H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries”, CA Cancer J Clin, vol. 71, n.º 3, pp. 209-249, may. 2021, doi: 10.3322/caac.21660.
WHO, The effect of occupational exposure to solar ultraviolet radiation on malignant skin melanoma and non-melanoma skin cancer: a systematic review and meta-analysis from the WHO/ILO joint estimates of the work-related burden of disease and injury. Ginebra: World Health Organization, 2021.
J. F. Gallegos. “En verano, reforzar cuidados para reducir riesgos de cáncer de piel”. GOB.mx. Disponible: https://www.gob.mx/imss/articulos/en-verano-reforzar-cuidados-para-reducir-riesgos-de-cancer-de-piel?idiom=es (accedido: oct. 23, 2024).
A. Cámara-Salazar et al., “Características individuales y por entidad federativa de la mortalidad por melanoma en México entre 2014 y 2018”, Dermatol Rev Mex, vol. 64, n.º 3, pp. 248-254, may. 2020.
J. F. Gallegos. “Día Mundial del Melanoma Cutáneo”. GOB.mx. Disponible: https://www.gob.mx/imss/articulos/dia-mundial-del-melanoma-cutaneo?idiom=es (accedido: oct. 23, 2024).
American Cancer Society. “Cáncer de piel tipo melanoma”. CANCER.net. https://www.cancer.org/es/cancer/tipos/cancer-de-piel-tipo-melanoma.html (accedido: ag. 23, 2025).
IARC, “Melanoma Awareness Month 2022”. IARC.who.int. https://www.iarc.who.int/news-events/melanoma-awareness-month-2022/ (accedido: oct. 17, 2022).
C. Alonso-Belmonte, T. Montero-Vilchez, S. Arias-Santiago y A. Buendía-Eisman, “Situación actual de la prevención del cáncer de piel: una revisión sistemática”, Actas Dermosifiliogr, vol. 113, n.º 8, pp. 781-791, sept. 2022, doi: 10.1016/j.ad.2022.04.015.
Secretaría de Salud. “Falta de prevención y detección tardía ocasiona 30% de fallecimientos en pacientes con melanoma”. GOB.mx. https://www.gob.mx/salud/prensa/196-falta-de-prevencion-y-deteccion-tardia-ocasiona-30-de-fallecimientos-en-pacientes-con-melanoma (accedido: oct. 23, 2024).
Mayo Clinic. “Diagnóstico y tratamiento”. Cáncer de piel. https://www.mayoclinic.org/es-es/diseases-conditions/skin-cancer/diagnosis-treatment/drc-20377608 (accedido: oct. 17, 2022).
D. N. H. Thanh, V. B. S. Prasath, L. M. Hieu y N. N. Hien, “Melanoma Skin Cancer Detection Method Based on Adaptive Principal Curvature, Colour Normalisation and Feature Extraction with the ABCD Rule”, J Digit Imaging, vol. 33, n.º 3, pp. 574-585, jun. 2020, doi: 10.1007/s10278-019-00316-x.
P. Castañeda y J. E. Téllez, “El cáncer de piel, un problema actual”, Rev. Fac. Med. (Méx.), vol. 59, n.º 2, pp. 6-14, mar./abr. 2016.
“Abordaje Diagnóstico del Melanoma Maligno”, catálogo maestro de guías de práctica clínica IMSS-547-1, Instituto Mexicano del Seguro Social, Ciudad de México, 2012. [En línea]. Disponible: https://www.imss.gob.mx/sites/all/statics/guiasclinicas/547GRR.pdf
I. Arellano, Saúl. Lecciones de Dermatología, 16.ª ed. México: McGraw Hill, 2015.
H. Kittler, H. Pehamberger, K. Wolff y M. Binder, “Diagnostic accuracy of dermoscopy”, Lancet Oncol, vol. 3, n.º 3, pp. 159-165, mar. 2002, doi: 10.1016/S1470-2045(02)00679-4.
P. Weber, P. Tschandl, C. Sinz y H. Kittler, “Dermatoscopy of Neoplastic Skin Lesions: Recent Advances, Updates, and Revisions”, Curr Treat Options Oncol, vol. 19, n.º 11, sept. 2018, doi: 10.1007/s11864-018-0573-6.
N. C. F. Codella et al., “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)”, arXiv:1710.05006, oct. 2017. [En línea]. Disponible: arXiv, doi: 10.48550/arXiv.1710.05006. [Accedido: oct. 23, 2024].
S. Jinnai, N. Yamazaki, Y. Hirano, Y. Sugawara, Y. Ohe y R. Hamamoto, “The development of a skin cancer classification system for pigmented skin lesions using deep learning”, Biomolecules, vol. 10, n.º 8, pp. 1-13, ag. 2020, doi: 10.3390/biom10081123.
P. Tschandl, C. Rosendahl y H. Kittler, “Data descriptor: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions”, Sci Data, vol. 5, n.º 180161, pp. 1-9, 2018, doi: 10.1038/sdata.2018.161.
J. Bobadilla, Machine Learning y Deep Learning: Usando Python, Scikit y Keras. Colombia: Ediciones de la U, 2021.
H.-J. Chiu, T.-H. S. Li y P.-H. Kuo, “Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine”, en IEEE Access, vol. 8, pp. 204309-204324, 2020, doi: 10.1109/ACCESS.2020.3036912.
L. Hoang, S. H. Lee, E. J. Lee y K. R. Kwon, “Multiclass Skin Lesion Classification Using a Novel Lightweight Deep Learning Framework for Smart Healthcare”, Appl. Sci., vol. 12, n.º 5, mar. 2022, doi: 10.3390/app12052677.
C. Shorten y T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning”, J Big Data, vol. 6, n.º 60, 2019, doi: 10.1186/s40537-019-0197-0.
L. Taylor y G. Nitschke, “Improving Deep Learning with Generic Data Augmentation”, 2018 IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, India, 2018, pp. 1542-1547, doi: 10.1109/SSCI.2018.8628742.
I. S. Ali, M. F. Mohamed y Y. B. Mahdy, “Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network”, arXiv:1910.11960, oct. 2019. [En línea]. Disponible: arXiv, doi: 10.48550/arXiv.1910.11960. [Accedido: oct. 23, 2024].
D. Bisla, A. Choromanska, R. S. Berman, J. A. Stein, D. Polsky y R. O. Perelman, “Towards Automated Melanoma Detection with Deep Learning: Data Purification and Augmentation”, arXiv:1902.06061, 2019. [En línea]. Disponible: arXiv, doi: 10.48550/arXiv.1902.06061. [Accedido: oct. 23, 2024].
S. Joshi, J. A. Owens, S. Shah y T. Munasinghe, “Analysis of Preprocessing Techniques, Keras Tuner, and Transfer Learning on Cloud Street image data”, 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, EUA, 2021, pp. 4165-4168, doi: 10.1109/BigData52589.2021.9671878.
P. Sutradhar, P. Kumer, I. Prodan, S. Saddi y V. S. Rozario, “Multi-Modal Case Study on MRI Brain Tumor Detection Using Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbor, Temporal Convolution & Transfer Learning”, AIUB J. Sci. Eng., vol. 20, n.º 3, sept. 2021.
D. N. T. Le, H. X. Le, L. T. Ngo y H. T. Ngo, “Transfer learning with class-weighted and focal loss function for automatic skin cancer classification”, arXiv:2009.05977, sept. 2020. [En línea]. Disponible: arXiv, doi: 10.48550/arXiv.2009.05977.
A. Abbas, M. M. Abdelsamea y M. M. Gaber, “DeTrac: Transfer Learning of Class Decomposed Medical Images in Convolutional Neural Networks”, IEEE Access, vol. 8, pp. 74901-74913, 2020, doi: 10.1109/ACCESS.2020.2989273. [Accedido: oct. 23, 2024].
L. Singh, R. R. Janghel y S. P. Sahu, “TrCSVM: a novel approach for the classification of melanoma skin cancer using transfer learning”, Data Technol. Appl., vol. 55, n.º 1, pp. 64-81, en. 2021, doi: 10.1108/DTA-06-2020-0126.
H. K. Kondaveeti y P. Edupuganti, “Skin Cancer Classification using Transfer Learning”, 2020 IEEE International Conference on Advent Trends in Multidisciplinary Research and Innovation (ICATMRI), Buldhana, India, 2020, pp. 1-4, doi: 10.1109/ICATMRI51801.2020.9398388.
S. Jain, U. Singhania, B. Tripathy, E. A. Nasr, M. K. Aboudaif y A. K. Kamrani, “Deep learning-based transfer learning for classification of skin cancer”, Sensors, vol. 21, n.º 23, dic. 2021, doi: 10.3390/s21238142.
S. A. Althubiti, F. Alenezi, S. Shitharth, K. Sangeetha y V. S. R. Chennareddy, “Circuit Manufacturing Defect Detection Using VGG16 Convolutional Neural Networks”, Wirel Commun Mob Comput, vol. 2022, n.º 1070405, 2022, doi: 10.1155/2022/1070405.
M. P. Uddin, M. Al Mamun y M. A. Hossain, “PCA-based Feature Reduction for Hyperspectral Remote Sensing Image Classification”, IETE Tech. Rev., vol. 38, n.º 4, pp. 377-396, 2020, doi: 10.1080/02564602.2020.1740615.
R. O. Ogundokun, S. Misra, A. O. Akinrotimi y H. Ogul, “MobileNet-SVM: A Lightweight Deep Transfer Learning Model to Diagnose BCH Scans for IoMT-Based Imaging Sensors”, Sensors 2023, vol. 23, n.º 2, en. 2023, doi: 10.3390/S23020656.
A. Kumar, A. Ashok y M. A. Ansari, “Brain Tumor Classification Using Hybrid Model Of PSO And SVM Classifier”, 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida, India, 2018, pp. 1022-1026, doi: 10.1109/ICACCCN.2018.8748787.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Verónica Angélica Villalobos Romo, Soledad Vianey Torres Argüelles, José David Díaz Román
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Todos los contenidos de CULCYT se distribuyen bajo una licencia de uso y distribución “Creative Commons Reconocimiento-No Comercial 4.0 Internacional” (CC-BY-NC). Puede consultar desde aquí la versión informativa de la licencia.
Los autores/as que soliciten publicar en esta revista, aceptan los términos siguientes: a) los/las autores/as conservarán sus derechos de autor y garantizarán a la revista el derecho de primera publicación de su obra; y b) se permite y recomienda a los/las autores/as agregar enlaces de sus artículos en CULCYT en la página web de su institución o en la personal, debido a que ello puede generar intercambios interesantes y aumentar las citas de su obra publicada.
