Web application for skin cancer detection based on deep learning
DOI:
https://doi.org/10.37135/ns.01.17.03Keywords:
Web Application, Deep Learning, Skin Cancer, Convolutional Neural Networks, TensorFlowAbstract
Developing advanced healthcare technologies is one of the most exciting and challenging areas of the 21st century. The application of deep learning to medical diagnosis represents a significant advance in the ability of automated systems to assist professionals in critical decision-making. This work presents a web application for early skin cancer detection using convolutional neural networks, specifically ResNet. It enables the automatic detection of eight types of skin cancer: melanoma, melanocytic nevus, basal cell carcinoma, actinic keratosis, dermatofibroma, squamous cell carcinoma, vascular lesion, and seborrheic keratosis. The CRISP-DM methodology used in this study includes data preprocessing using TensorFlow and model performance evaluation using metrics such as accuracy, sensitivity, average loss, and mAP (mean average precision). The model uses a dataset of 25,331 images, divided into 20,265 for training and 5.066 for testing. The results of this study yielded 94% accuracy and 87% sensitivity. Future work is proposed to optimize the model, explore its application in other dermatological pathologies, and expand its usefulness in clinical contexts assisted by artificial intelligence.
Downloads
References
A. Naeem, M. S. Farooq, A. Khelifi, y A. Abid, “Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities,” IEEE Access, vol. 8, pp. 110575–110597, 2020, doi: https://doi.org/10.1109/ACCESS.2020.3001507.
H. Zanddizari, N. Nguyen, B. Zeinali, y J. M. Chang, “A new preprocessing approach to improve the performance of CNN-based skin lesion classification,” Med. Biol. Eng. Comput., vol. 59, no. 5, pp. 1123– 1131, abr. 2021, doi: https://doi.org/10.1007/s11517-021-02355-5.
A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, ene. 2017, doi: https://doi.org/10.1038/nature21056.
S. Kaymak, P. Esmaili, y A. Serener, “Deep Learning for Two-Step Classification of Malignant Pigmented Skin Lesions,” 2018 14th Symp. Neural Networks Appl. NEUREL 2018, pp. 1–6, nov. 2018, doi: https://doi.org/10.1109/NEUREL.2018.8587019.
A. K. Morales, D. R. Lepe, y J. F. Díaz, “Redes Neuronales Convolucionales para Detección de Carcinoma Basocelular (Cáncer de Piel) por Medio de Imágenes para Pacientes Adultos en la Región Facial,” Ciencia Latina, vol. 8, no. 4, pp. 582-599, ago. 2024, doi: https://doi.org/10.37811/cl_rcm.v8i4.12300.
Y. Fontaine Pérez, D. Sotolongo Díaz, I. Espinosa Carballosa, M. Roque Morgado, M. Montes de Oca Álvarez, y M. Figueroa García, “Utilidad del dermatoscopio en la correlación clínica e histológica de nevus pigmentados,” Rev Cubana Inv Bioméd, vol. 40, no. 2, ago. 2021.
B. S. Ankad, S. S. Mukherjee, y B. Pralhadrao, Dermoscopy - Histopathology Correlation. Springer Singapore, 2021. doi: https://doi.org/10.1007/978-981-33-4638-3.
S. Rajarajeswari, J. Prassanna, M. Abdul Quadir, J. Christy Jackson, S. Sharma, y B. Rajesh, “Skin Cancer Detection using Deep Learning,” Res. J. Pharm. Technol., vol. 15, no. 10, pp. 4519–4525, oct. 2022, doi: https://doi.org/10.52711/0974-360X.2022.00758.
I. H. Sarker, “Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions,” SN Comput. Sci., vol. 2, no. 6, ago. 2021, doi: https://doi.org/10.1007/s42979-021-00815-1.
A. A. Adegun y S. Viriri, “Deep learning-based system for automatic melanoma detection,” IEEE Access, vol. 8, pp. 7160–7172, 2020, doi: https://doi.org/10.1109/ACCESS.2019.2962812.
C. K. Juan et al., “Deep convolutional neural network with fusion strategy for skin cancer recognition: model development and validation,” Sci. Rep., vol. 13, no. 1, oct. 2023, doi: https://doi.org/10.1038/s41598-023-42693-y.
K. Thurnhofer-Hemsi y E. Domínguez, “A Convolutional Neural Network Framework for Accurate Skin Cancer Detection,” Neural Process. Lett., vol. 53, no. 5, pp. 3073–3093, oct. 2021, doi: https://doi.org/10.1007/s11063-020-10364-y.
K. M. Hosny, M. A. Kassem, y M. M. Foaud, “Skin Cancer Classification using Deep Learning and Transfer Learning,” 2018 9th Cairo Int. Biomed. Eng. Conf. CIBEC 2018 - Proc., pp. 90–93, dic. 2018, doi: https://doi.org/10.1109/CIBEC.2018.8641762.
C. Schröer, F. Kruse, y J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” Procedia Comput. Sci., vol. 181, pp. 526–534, 2021, doi: https://doi.org/10.1016/j.procs.2021.01.199.
A. Maranhão, “Skin Lesion Analysis Dataset,” Kaggle, 2020. [En línea]. Disponible en: https://www.kaggle.com/datasets/andrewmvd/isic-2019/data
P. Tschandl, C. Rosendahl, y H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Sci. Data, vol. 5, no. 1, ago. 2018, doi: https://doi.org/10.1038/sdata.2018.161.
C. Hernández-Pérez et al., “BCN20000: Dermoscopic Lesions in the Wild,” Sci. Data, vol. 11, no. 1, jun. 2024, doi: https://doi.org/10.1038/s41597-024-03387-w.
J. Muñoz-Ordóñez, C. Cobos, M. Mendoza, E. Herrera-Viedma, F. Herrera, y S. Tabik, "Framework for the Training of Deep Neural Networks in TensorFlow Using Metaheuristics, Lecture Notes in Computer Science. Springer International Publishing, pp. 801-811, 2018. doi: https://doi.org/10.1007/978-3-030-03493-1_83.
V. R. Joseph, “Optimal ratio for data splitting,” Statistical Analysis, vol. 15, no. 4, pp. 531-538, abr. 2022, doi: https://doi.org/10.1002/sam.11583.
M. Anour Naoui, “Transferir el enfoque de aprendizaje basado en la detección del cáncer de piel,” vol. 16, no. 4, pp. 1–17, dic. 2022. Disponible en: http://ref.scielo.org/k754wb.
F. Farías Rivera y N. M. Loja Mora, “Entrenamiento para la detección de cáncer de piel,” ago. 13, 2025, Zenodo. doi: https://doi.org/10.5281/ZENODO.16827475.
S. E. Cerminara et al., “Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under realworld conditions: A new era of skin cancer screening?,” European Journal of Cancer, vol. 190, p. 112954, sep. 2023, doi: https://doi.org/10.1016/j.ejca.2023.112954.
S. Kim, E. Gaibor, y D. Haehn, “Web-based Melanoma Detection,” 2024, arXiv. doi: https://doi.org/10.48550/ARXIV.2403.14898.
D. Palacios-Martínez y R. A. Díaz-Alonso, “Dermatoscopia para principiantes (I): características generales,” Semergen, vol. 43, no. 3, pp. 216–221, abr. 2017, doi: https://doi.org/10.1016/j.semerg.2015.11.009.
O. Attallah, “Skin cancer classification leveraging multi-directional compact convolutional neural network ensembles and gabor wavelets,” Sci. Rep., vol. 14, no. 1, sep. 2024, doi: https://doi.org/10.1038/s41598-024-69954-8.
C. V. Niño-Rondón, D. A. Castellano-Carvajal, S. A. Castro-Casadiego, B. Medina-Delgado, y K. C. Puerto-López, “HASCC: A Hybrid Algorithm for Skin Cancer Classification,” Rev. Fac. Ing., vol. 33, no. 67, p. e16943, mar. 2024, doi: https://doi.org/10.19053/uptc.01211129.v33.n67.2024.16943.
J. Guillermo Guarnizo, S. Riaño Borda, E. C. Camacho Poveda, y A. Mateus Rojas, “Automated Malignant Melanoma Classification Using Convolutional Neural Networks,” Cien. Ing. Neogranadina, vol. 32, no. 2, pp. 171–185, dic. 2022, doi: https://doi.org/10.18359/rcin.6270.
W. Gouda, N. U. Sama, G. Al-Waakid, M. Humayun, y N. Z. Jhanjhi, “Detection of Skin Cancer Based on Skin Lesion Images Using Deep Learning,” Healthcare, vol. 10, no. 7, p. 1183, jun. 2022, doi: https://doi.org/10.3390/healthcare10071183.
A. Bello, S. C. Ng, y M. F. Leung, “Skin Cancer Classification Using Fine-Tuned Transfer Learning of DENSENET-121,” Applied Science, vol. 14, no. 17, p. 7707, ago. 2024, doi: https://doi.org/10.3390/app14177707.
O. Akinrinade y C. Du, “Skin cancer detection using deep machine learning techniques,” IntelligenceBased Medicine, vol. 11, p. 100191, 2025, doi: https://doi.org/10.1016/j.ibmed.2024.100191.
A. T. Ibrahim, M. Abdullahi, A. F. Donfack Kana, M. T. Mohammed, y I. H. Hassan, “Categorical classification of skin cancer using a weighted ensemble of transfer learning with test time augmentation Aliyu,” Data Sci. Manag., vol. 8, no. 2, pp. 174-184, jun. 2025, doi: https://doi.org/10.1016/j.dsm.2024.10.002.
S. A. Alshawi y G. F. K. AI Musawi, “Skin Cancer Image Detection and Classification by CNN based Ensemble Learning,” IJACSA, vol. 14, no. 5, 2023, doi: https://doi.org/10.14569/IJACSA.2023.0140575.
