DermaVision: EfficientNetB3-Based Deep Learning for Skin Cancer Diagnosis
Abstract
Skin cancer is one of the most prevalent and life-threatening diseases throughout the world, where it is essential to start timely and precise diagnosis of the disease to enhance the survival rate of the patients. Recent progress in deep learning approaches has revealed the great potential to conduct skin cancer detection using dermoscopic images. In this study, we propose DermaVision, a robust and efficient deep learning based on a fine-tuned EfficientNetB3 architecture for binary skin cancer diagnosis. The model takes advantage of transfer learning and compound scaling to uncover highly discriminative features from dermoscopic images while retaining computational efficiency. The data used in this study is taken from Kaggle and it contains benign and cancerous skin lesion images, which are preprocessed, augmented, and divided into training, validation, and testing datasets in a systematic manner. Experimental evaluation shows that the proposed DermaVision framework is able to obtain an overall classification accuracy of 97% and also achieves high precision, recall and ROC-AUC performance, indicating that it has excellent discriminative capability. The results are confirmed that DermaVision provides a reliable, accurate and clinically applicable solution for automated skin cancer screening and decision-support systems.
References
[1] Lilhore, U.K., Sharma, Y.K., Simaiya, S., Alroobaea, R., Baqasah, A.M., Alsafyani, M. and Alhazmi, A., 2025. SkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems. Scientific Reports, 15(1), p.14913.
[2] Ozdemir, B. and Pacal, I., 2025. A robust deep learning framework for multiclass skin cancer classification. Scientific Reports, 15(1), p.4938.
[3] Lin, T.L., Mukundan, A., Karmakar, R., Avala, P., Chang, W.Y. and Wang, H.C., 2025. Hyperspectral imaging for enhanced skin cancer classification using machine learning. Bioengineering, 12(7), p.755.
[4] Mavaddati, S., 2025. Skin cancer classification based on a hybrid deep model and long short-term memory. Biomedical Signal Processing and Control, 100, p.107109.
[5] Shakya, M., Patel, R. and Joshi, S., 2025. A comprehensive analysis of deep learning and transfer learning techniques for skin cancer classification. Scientific Reports, 15(1), p.4633.
[6] Abdulredah, A.A., Fadhel, M.A., Alzubaidi, L., Duan, Y., Kherallah, M. and Charfi, F., 2025. Towards unbiased skin cancer classification using deep feature fusion. BMC Medical Informatics and Decision Making, 25(1), p.48.
[7] Ashtikar, A. and Shastri, S., 2025. A CNN Model For Skin Cancer Detection And Classification By Using Image Processing Techniques. Journal of Scientific Research and Technology, pp.251–263.
[8] Alrabai, A., Echtioui, A. and Kallel, F., 2025. Exploring Pre-Trained Models for Skin Cancer Classification. Applied System Innovation, 8(2), p.35.
[9] Kant, V. and Kumar, B.V., 2025, April. Deep Learning-Based Classification of Lung and Colon Cancer Subtypes Using Histology Images. In 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 (pp. 1–5). IEEE.
[10] Verma, G., Pasha, S.N. and Singh, C., 2025, April. Leveraging EfficientNetB5 for Accurate Classification of Diverse Human Cancer Tissues. In 2025 3rd International Conference on Advancement in Computation & Computer Technologies (InCACCT) (pp. 20–24). IEEE.
[11] Halder, A., Dalal, A., Gharami, S., Wozniak, M., Ijaz, M.F. and Singh, P.K., 2025. A fuzzy rank-based deep ensemble methodology for multi-class skin cancer classification. Scientific Reports, 15(1), p.6268.
[12] Mandal, S., Ghosh, S., Jana, N.D., Chakraborty, S. and Mallik, S., 2025. Active learning with particle swarm optimization for enhanced skin cancer classification utilizing deep CNN models. Journal of Imaging Informatics in Medicine, 38(4), pp.2472–2489.
[13] Abdulazeez, A., 2024. A review on utilizing machine learning classification algorithms for skin cancer. Journal of Applied Science and Technology Trends, 5(2), pp.60–71.
[14] Yang, G., Luo, S. and Greer, P., 2025. Advancements in skin cancer classification: a review of machine learning techniques in clinical image analysis. Multimedia Tools and Applications, 84(11), pp.9837–9864.
[15] Jain, C., Das, P., Kant, V. and Bharany, S., 2025, June. A Deep Learning Framework Empowered by the Internet of Medical Devices for Skin Cancer Detection and Classification Through Transfer Learning. In 2025 5th International Conference on Intelligent Technologies (CONIT) (pp. 1–5). IEEE.
[16] Verma, G., 2024, December. Deep Learning-Based Classification of Lung and Colon Cancer using a Proposed CNN Architecture. In 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) (pp. 863–867). IEEE.