Multi-Skin Disease Classification using Hybrid Deep Learning Framework Combining Convolutional Neural Networks and Support Vector Machines
DOI:
https://doi.org/10.65746/jbrha69Keywords:
skin disease classification, deep learning, CNN, SVM, hybrid framework, medical imagingAbstract
Skin disease classification has become a critical task in modern medical diagnostics, where accurate detection plays a vital role in patient care. This study introduces a hybrid deep learning framework that combines Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) to enhance diagnostic precision. Current methods in skin disease classification often suffer from high computational costs and limited accuracy due to data heterogeneity and insufficient feature extraction. These challenges impede reliable diagnosis and delay timely treatment. To address these issues, the proposed Skin Disease Prediction using Deep Learning (SDP-DL) approach integrates deep feature extraction with robust classification techniques. The framework leverages CNNs to capture complex visual patterns in skin lesions, while SVMs refine decision boundaries to reduce false positives. The proposed method systematically processes pre-processed images through CNN layers, extracting hierarchical features before applying SVM for final classification. Experimental results demonstrate improved accuracy, reduced misclassification rates, and enhanced robustness compared to conventional models. The hybrid framework shows promise in supporting clinical decision-making and advancing automated skin disease diagnostics. Findings suggest that the SDP-DL approach significantly improves detection reliability, paving the way for integration into medical imaging systems for early and precise skin disease diagnosis.
References
1. Vayadande K, Bhosle AA, Pawar RG, et al. Innovative approaches for skin disease identification in machine learning: A comprehensive study. Oral Oncology Reports. 2024; 10: 100365. doi: 10.1016/j.oor.2024.100365
2. Mohammed SS, Al-Tuwaijari JM. Skin disease classification system based on machine learning technique: A survey. IOP Conference Series: Materials Science and Engineering. 2021; 1076(1): 012045. doi: 10.1088/1757-899X/1076/1/012045
3. Verma S, Kumar M. A hybrid machine learning model for skin disease classification using discrete wavelet transform and gray level co-occurrence matrix (GLCM). Multimedia Tools and Applications. 2025; 84(14): 12835–12853. doi: 10.1007/s11042-024–19449-5
4. Elashiri MA, Rajesh A, Pandey SN, et al. Ensemble of weighted deep concatenated features for the skin disease classification model using modified long short term memory. Biomedical Signal Processing and Control. 2022; 76: 103729. doi: 10.1016/j.bspc.2022.103729
5. Yadav R, Bhat A. A systematic literature survey on skin disease detection and classification using machine learning and deep learning. Multimedia Tools and Applications. 2024; 83(32): 78093–78124. doi: 10.1007/s11042-024-18119-w
6. Allugunti VR. A machine learning model for skin disease classification using convolution neural network. International Journal of Computing, Programming and Database Management. 2022; 3(1): 141–147.
7. Ahmad B, Usama M, Ahmad T, et al. An ensemble model of convolution and recurrent neural network for skin disease classification. International Journal of Imaging Systems and Technology. 2022; 32(1): 218–229. doi: 10.1002/ima.22661
8. Melbin K, Raj YJV. Integration of modified ABCD features and support vector machine for skin lesion types classification. Multimedia Tools and Applications. 2021; 80(6): 8909–8929. doi: 10.1007/s11042-020-10056-8
9. Maniraj SP, Maran PS. A hybrid deep learning approach for skin cancer diagnosis using subband fusion of 3D wavelets. The Journal of Supercomputing. 2022; 78(10): 12394–12409. doi: 10.1007/s11227-022-04371-0
10. Verma S, Razzaque M A, Sangtongdee U, et al. Digital diagnosis of hand, foot, and mouth disease using hybrid deep neural networks. IEEE Access. 2021; 9: 143481–143494. doi: 10.1109/ACCESS.2021.3120199
11. Rasheed A, Umar AI, Shirazi SH, et al. Automatic eczema classification in clinical images based on hybrid deep neural network. Computers in Biology and Medicine, 2022; 147: 105807. doi: 10.1016/j.compbiomed.2022.105807
12. Bassel A, Abdulkareem AB, Alyasseri ZAA, et al. Automatic malignant and benign skin cancer classification using a hybrid deep learning approach. Diagnostics. 2022; 12(10): 2472. doi: 10.3390/diagnostics12102472
13. Almuayqil SN, Abd El-Ghany S, Elmogy M. Computer-aided diagnosis for early signs of skin diseases using multi types feature fusion based on a hybrid deep learning model. Electronics. 2022; 11(23): 4009. doi: 10.3390/electronics11234009
14. Kalpana B, Reshmy AK, Pandi SS, et al. OESV-KRF: Optimal ensemble support vector kernel random forest based early detection and classification of skin diseases. Biomedical Signal Processing and Control. 2023; 85: 104779. doi: 10.1016/j.bspc.2023.104779
15. Anggriandi D, Utami E, Ariatmanto D. Comparative analysis of CNN and CNN-SVM methods for classification types of human skin disease. Sinkron: Jurnal dan Penelitian Teknik Informatika. 2023; 7(4): 2168–2178. doi: 10.33395/sinkron.v8i4.12831
16. Bandyopadhyay SK, Bose P, Bhaumik A, et al. Machine learning and deep learning integration for skin diseases prediction. Int. J. Eng. Trends Technol. 2022; 70(3): 13–21. doi: 10.14445/22315381/IJETT-V70I2P202
17. Bilal A, Imran A, Liu X, et al. BC–QNet: A quantum-infused ELM model for breast cancer diagnosis. Computers in Biology and Medicine. 2024; 175: 108483. doi: 10.1016/j.compbiomed.2024.108483
18. Bilal A, Sun G, Li Y, et al. Lung nodules detection using grey wolf optimization by weighted filters and classification using CNN. Journal of the Chinese Institute of Engineers. 2022; 45(2): 175–186. doi: 10.1080/02533839.2021.2012525
19. Bilal A, Shafiq M, Fang F, et al. IGWO-IVNet3: DL-based automatic diagnosis of lung nodules using an improved gray wolf optimization and InceptionNet-V3. Sensors. 2022; 22(24): 9603. doi: 10.3390/s22249603
20. Bilal A, Sun G, Mazhar S, et al. Neuro-optimized numerical treatment of HIV infection model. International Journal of Biomathematics. 2021; 14(05): 2150033. doi: 10.1142/s1793524521500339
21. Bilal A, Sun G. Neuro-optimized numerical solution of non-linear problem based on Flierl–Petviashivili equation. SN Applied Sciences. 2020; 2(7): 1166. doi: 10.1007/s42452-020-2963-1
22. Lee T, Ng V, Gallagher R, et al. Dullrazor®: A software approach to hair removal from images. Computers in Biology and Medicine. 1997; 27(6): 533–543. doi: 10.1016/S0010-4825(97)00020-6
23. Abbas Q, Celebi ME, García IF. Hair removal methods: A comparative study for dermoscopy images. Biomedical Signal Processing and Control. 2011; 6(4): 395–404. doi: 10.1016/j.bspc.2011.01.003
24. Verma P. Skin Cancer Classification: CNN Approach. Kaggle; 2023.
Ángeles Rojas JA, Calderón Vilca HD, Tumi Figueroa EN, et al. Hybrid model of convolutional neural network and support vector machine to classify basal cell carcinoma. Computación y Sistemas. 2021; 25(1): 83–95. doi: 10.13053/cys-25-1-3431
Downloads
Published
Data Availability Statement
The data used in this study are available from the corresponding author upon reasonable request.
Issue
Section
License
Copyright (c) 2026 Jeyageetha Kaliraj, Vijayalakshmi Kandasamy, Bhuvanesh Aananthan
This work is licensed under a Creative Commons Attribution 4.0 International License.
