Abstract
The incidence rate of skin cancer is increasing day by day due to the increased exposure to the ultraviolet rays of sunlight. It is vital to detect skin cancer at an early stage in order to facilitate proper treatment and avoid any serious complications. For this work, we have designed a simple algorithm which detects if the skin image is suffering from any skin disease or not using deep learning algorithms. For this purpose, we utilized a CNN model based on TensorFlow which helps us in analyzing the images. All images are preprocessed before feeding them into the model. Color, shape and texture are some of the patterns learned by the model from the data set. Moreover, we have designed a web application through which users can upload images and get instant results. Cancerous or non-cancerous is the output of the system. The output obtained is reasonable enough for classification problems.
References
- Srisuma, V., Yalavarthi, S., Inaganti, R.. Efficient Diagnosis of Skin Cancer Utilizing Swin Transformers Through Dermatoscopic Image Analysis. In: Kriksciuniene, D., Bajaj, A., Abraham, A. (eds) Bio-Inspired Computing. IBICA 2023. Lecture Notes in Networks and Systems, vol 1228. Springer, Cham. https://doi.org/10.1007/978-3-031-78937-3_42, 2025.
- A. Esteva, B. Kuprel, R. A. Novoa, et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017, doi: 10.1038/nature21056.
- N. Codella, D. Gutman, M. Celebi, et al., “Skin lesion analysis toward melanoma detection: A challenge at the International Symposium on Biomedical Imaging,” IEEE ISBI, 2018, pp. 168–172.
- P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset: A large collection of multi-source dermatoscopic images,” Scientific Data, vol. 5, 2019.
- H. Brinker, A. Hekler, J. S. Utikal, et al., “Skin cancer classification using convolutional neural networks: Systematic review,” J. Med. Internet Res., vol. 21, no. 10, 2019.
- M. Mahbod, G. Schaefer, C. Wang, et al., “Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification,” Computers in Biology and Medicine, vol. 105, pp. 176–185, 2019.
- M. A. Almaraz-Damian, V. Ponomaryov, S. Sadovnychiy, and H. Castillejos-Fernandez, “Melanoma and nevus skin lesion classification using hand-crafted and deep learning features,” IEEE Access, vol. 8, pp. 188329–188339, 2020.
- F. Chollet, “Keras: Deep learning library for Python,” 2015. [Online]. Available: https://keras.io
- M. Abadi, P. Barham, J. Chen, et al., “TensorFlow: A system for large-scale machine learning,” OSDI, 2016.
