Skin Disease Detection using Deep Learning Techniques

Author

B. Yaswanth, B. Vinay, Ch. Dhana Sri, K. Akhil, Dr. T. Geetamma, Dr. S. Shanamthi

Abstract

 Skin diseases vary widely in appearance, making accurate classification from clinical images challenging. Conventional diagnosis relies primarily on clinical expertise and visual examination, which can be time-consuming and may be affected by similarities among different disease conditions. This study presents a deep learning-based framework for automated skin disease classification using transfer learning. Different convolution neural network architectures, namely EfficientNetV2B0, MobileNetV3-Large, ResNet50, and DenseNet121, SE-ResNet50 are investigated and comparatively evaluated under a common experimental framework. The proposed approach involves image pre processing, data augmentation, transfer learning, model training, and performance evaluation across multiple classification metrics. The pre trained models are adapted to extract different visual features from skin images and classify them into the corresponding disease categories. Model performance is assessed using accuracy, precision, recall, F1-score, and confusion matrix analysis. The comparative evaluation provides insights into the effectiveness of different CNN architectures for skin disease classification and identifies the architecture that provides the most suitable performance for the considered data-set. The proposed framework demonstrates the potential of transfer learning as a computer-aided approach for supporting preliminary skin disease identification, while emphasizing that automated predictions should be complemented rather than replacing professional clinical assessment.

Keywords

Automated skin disease classification, deep learning, transfer learning, convolution neural networks, medical image analysis, EfficientNetV2B0, comparative model analysis.

Full Text:

Download Paper PDF

References

[1] Z. Wu, S. Zhao, Y. Peng, X. He, X. Zhao, K. Huang, X. Wu, W. Fan, F. Li, M. Chen, J. Li, W. Huang, X. Chen, and Y. Li, “Studies on different CNN algorithms for face skin disease classification based on clinical images,” IEEE Access, vol. 7, pp. 66505–66511, 2019, doi: 10.1109/ACCESS.2019.2918221.

[2] B. Ahmad, M. Usama, C.-M. Huang, K. Hwang, M. S. Hossain, and G. Muhammad, “Discriminative feature learning for skin disease classification using deep convolutional neural network,” IEEE Access, vol. 8, pp. 39025–39033, 2020, doi: 10.1109/ACCESS.2020.2975198.

[3] Z. L. Fathonah, P. W. Adi, and H. A. Wibawa, “Optimized multiclass classification of skin lesions using a modified EfficientNetV2B0 with transfer learning,” Discover Artif. Intell., vol. 6, Art. no. 775, 2026, doi: 10.1007/s44163-026-01545-0.

[4] R. A. Hafizh, R. Wijaya, A. I. Yafi’, and S. A. P. Siwi, “Improving skin disease classification with EfficientNetB0: A deep learning approach to overfitting control,” in Proc. Int. Conf. Intell. Cybern. Technol. Appl. (ICICyTA), 2024, pp. 513–518, doi: 10.1109/ICICYTA64807.2024.10913154.

[5] K. Xia, Y. Zheng, and Q. He, “Skin lesion recognition with compound scaling and coordinated attention mechanism,” in Proc. 2nd Int. Conf. Health Big Data Intell. Healthc. (ICHIH), 2023, pp. 29–32, doi: 10.1109/ICHIH60370.2023.10396419.

[6] A. D. Khalaf, H. Hamdan, A. A. Halin, and N. Manshor, “Segmentation and classification of skin cancer diseases based on deep learning: Challenges and future directions,” IEEE Access, vol. 13, pp. 90163–90184, 2025, doi: 10.1109/ACCESS.2025.3569170.

[7] A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, and S. Thrun, “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, pp. 115–118, Feb. 2017.

[8] DermNet skin disease image library (T. Habif). [Online]. Available: http://www.dermnet.com

[9] P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Sci. Data, vol. 5, no. 1, pp. 1–9, Aug. 2018.

[10] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015, arXiv:1512.03385.

[11] M. Tan and Q. Le, “EfficientNetV2: Smaller models and faster training,” in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 10096–10106.

[12] F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, “A comprehensive survey on transfer learning,” Proc. IEEE, vol. 109, no. 1, pp. 43–76, Jan. 2021.

[13] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2009, pp. 248–255.

[14] S. Ibrahim, K. M. Amin, R. I. Alkanhel, H. A. Abdallah, and M. Ibrahim, “Soft attention based EfficientNetV2B3 model for skin cancer’s disease classification using dermoscopy images,” IEEE Access, vol. 12, pp. 161283–161295, 2024, doi: 10.1109/ACCESS.2024.3486153.

[15] F. Firdous, D. Yadav, S. Z. Rufai, S. Bashir, and S. S. Sarkar, “An ensemble deep learning framework for skin disease classification with explainable and generative AI support,” Discover Artif. Intell., vol. 6, Art. no. 524, 2026, doi: 10.1007/s44163-026-01218-y.

Share your valuable work from Social Media Buttons