AI-Powered Hybrid Framework for Skin Disease Identification Using Hyper-CNN and MobileNetV2
DOI:
https://doi.org/10.15662/IJEETR.2026.0802161Keywords:
Skin disease classification, dermoscopic images, deep learning, EfficientNet, Hyper-Convolutional Neural Network (Hyper-CNN), hybrid model, medical image analysis, automated diagnosis, HAM10000 datasetAbstract
Automated skin disease classification using dermoscopic images has gained significant attention due to the rising incidence of skin-related disorders and the need for early diagnosis. However, the complex visual patterns of skin lesions, including variations in color, texture, shape, and scale, make accurate classification a challenging task. Conventional convolutional neural networks (CNNs) often suffer from limited feature representation and poor generalization when dealing with such high intra-class variability. To address these challenges, this paper proposes an AI-powered hybrid deep learning framework combining Hyper-Convolutional Neural Networks (Hyper-CNN) and Efficient Net for robust skin disease identification. In the proposed approach, Efficient Net is employed as a powerful feature extractor due to its compound scaling strategy, which efficiently balances network depth, width, and resolution to capture high-level semantic features from skin lesion images. These extracted features are further enhanced using a custom-designed Hyper-CNN architecture, which incorporates deeper convolutional blocks, batch normalization, and adaptive dropout mechanisms to learn fine-grained dermatological patterns. The hybrid framework enables effective extraction of both global and local lesion characteristics, improving discriminative capability across multiple skin disease classes. The proposed model is evaluated using the HAM10000 skin lesion dataset, achieving improved classification accuracy, stability, and confidence scores compared to traditional CNN-based methods. Experimental results demonstrate that the integration of Efficient Net with Hyper-CNN significantly enhances feature representation, reduces overfitting, and improves generalization performance. The proposed hybrid framework provides a reliable and scalable solution for automated skin disease diagnosis and has strong potential for deployment in real-time clinical decision-support systems
References
[1] Shaikh, Juveriya, Rubeena Khan, Yashwant Ingle, and Nuzhat Shaikh. “Improved skin cancer detection using CNN." International journal of health sciences (Qassim), pp. 14347-14360, 2022. https://www.ijhs.org.sa/
[2] Mazhar, T.; Haq, I.; Ditta, A.; Mohsan, S.A.H.; Rehman, F.; Zafar, I.; Gansau, J.A.; Goh, L.P.W. “The role of machine learning and deep learning approaches for the detection of skin Cancer”, healthcare, 2023. https://www.mdpi.com/journal/healthcare
[3] Melissa A. Trudrung, Cole Bacig, Brandon Vander Zee, Heather Potter, “Basal cell carcinoma and squamous cell carcinoma of the conjunctiva in a single lesion”, American Journal of Ophthalmology Case Reports, Volume 38, 2025. https://www.ajo.com/casereports/
[4] Raut, Roshani, Yogini Borole, Sonali Patil, V. N. Khan, and Dattatray G. Takale, “Skin disease classification using machine learning algorithms”, Neuro Quantology 20, no. 10, pp. 9624-9629, 2022. https://www.neuroquantology.com/
[5] Balasundaram, A. Shaik, B. R. Alroy, A. Singh and S. J. Shivaprakash, “Genetic Algorithm optimized stacking approach to skin disease detection”, IEEE Access, vol. 12, pp. 88950-88962, 2024. https://ieeexplore.ieee.org/document/10157064
[6] Srinivasu, P.N.; SivaSai, J.G.; Ijaz, M.F.; Bhoi, A.K.; Kim, W.; Kang, J.J, “Classification of skin disease using deep learning neural networks with Mobile Net V2 and LSTM”, Sensors 2021. https://www.mdpi.com/journal/sensors
[7] K. Lee et al., “Multi-Task and Few-Shot Learning-Based Fully Automatic Deep Learning Platform for Mobile Diagnosis of Skin Diseases”, IEEE journal of biomedical and health informatics, vol. 27, no. 1, pp. 176-187, 2023. https://ieeexplore.ieee.org/document/9810870
[8] Rashid, J.; Ishfaq, M.; Ali, G.; Saeed, M.R.; Hussain, M.; Alkhalifah, T.; Alturise, F.; Samand, N, “Skin cancer disease detection using transfer learning technique”, Applied Science, 2022. https://www.mdpi.com/journal/applscition
[9] M. Fahaad Almufareh, “An Edge computing-based factor-aware novel framework for early detection and classification of melanoma disease through a Customized VGG16 Architecture with privacy preservation and real-time analysis”, IEEE Access, vol. 12, pp. 113580-113596, 2024. https://ieeexplore.ieee.org/document/10185094
[10] Jagdish, M., Gualán Guamangate, S. P., López, M. A. G., De La Cruz-Vargas, J. A., and Camacho, M. E. R, “Advance study of skin diseases detection using image processing methods”, 2022. https://www.nveo.org/index.php/journal/article/view/4651
[11] P. Yao et al., "Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification," in IEEE Transactions on Medical Imaging, vol. 41, no. 5, pp. 1242-1254, 2022. https://ieeexplore.ieee.org/document/9746381
[12] Gairola, A. K., Kumar, V., Sahoo, A. K., Diwakar, M., Singh, P., and Garg, D, “Multi-feature fusion deep network for skin disease diagnosis”, Multimedia Tools and Applications, 84(1), pp.419-444, 2025. https://link.springer.com/article/10.1007/s11042-023-14679-z.
[13] A. A. Salam, M. Usman Akram, M. Haroon Yousaf and B. Rao, “Derma Trans Net: where transformer attention meets U-Net for skin image segmentation”, IEEE Access, vol. 13, pp. 64305-64329, 2025 https://ieeexplore.ieee.org/document/10436943.
[14] Rokade, Sonali, and Nilamadhab Mishra, “A blockchain-based deep learning system with optimization for skin disease classification”, Biomedical Signal Processing and Control, 2024. https://link.springer.com/article/10.1007/s11042-023-14679-z
[15] K. Thurnhofer-Hemsi, E. López-Rubio, E. Domínguez and D. A. Elizondo, “Skin Lesion classification by ensembles of deep convolutional networks and regularly spaced shifting”, IEEE Access, vol. 9, pp. 112193-112205, 2021. https://ieeexplore.ieee.org/document/10436943
[16] Reddy, D. A., Roy, S., Kumar, S., & Tripathi, R, “Enhanced U-Net segmentation with ensemble convolutional neural network for automated skin disease classification”, Knowledge and Information Systems, 65(10), pp. 4111-4156, 2023. https://link.springer.com/article/10.1007/s10115-023-01877-9
[17] M. Gallazzi, S. Biavaschi, A. Bulgheroni, T. M. Gatti, S. Corchs and I. Gallo, "A large dataset to enhance skin cancer classification with transformer-based deep neural networks”, IEEE Access, vol. 12, pp. 109544-109559, 2024. https://ieeexplore.ieee.org/document/10157283
[18] Anand, V.; Gupta, S.; Altameem, A.; Nayak, S.R.; Poonia, R.C.; Saudagar, A.K.J. “An Enhanced transfer learning based classification for diagnosis of Skin Cancer”, Diagnostics 2022. https://www.mdpi.com/journal/diagnostics
[19] K. Thurnhofer-Hemsi, E. López-Rubio, E. Domínguez and D. A. Elizondo, “Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting”, IEEE Access, vol. 9, pp. 112193-112205, 2021. https://www.mdpi.com/2227-9032/10/7
[20] Gouda, W., Sama, N. U., Al-Waakid, G., Humayun, M., and Jhanjhi, N. Z, “Detection of skin cancer based on skin lesion images using deep learning”, In Healthcare, Vol. 10, no. 7, 2022 https://ieeexplore.ieee.org/document/10016079
[21] R. Mittal, F. Jeribi, R. J. Martin, V. Malik, S. J. Menachery and J. Singh, "DermCDSM: Clinical decision support model for dermatosis using systematic approaches of machine learning and deep learning," in IEEE Access, vol. 12, pp. 47319-47337, 2024. https://www.routledge.com/Deep-Learning-in-Medical-Image-Analysis
[22] Rajeswari, R., P. G. Sivagaminathan, and A. R. Arunachalam, “Skin cancer detection and classification using deep learning techniques”, Deep Learning in Medical Image Analysis. Chapman and Hall/CRC, pp. 97-117, 2024. https://ieeexplore.ieee.org/document/10157440
[23] Akila, R. (2024). A deep reinforcement learning approach for optimizing inventory management in the agri-food supply chain. J. Electrical Systems, 20(4s), 2238-2247.
[24] Sugumar, R. (2025). Designing Resilient and Scalable Cloud-Native Frameworks for Generative AI Content Production. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(6), 13268-13279.
[25] Bhatnagar, G., Rajoria, Y. K., Sakeel, M., Vigenesh, M., Premananthan, G., & Dongre, D. (2023, September). IoT malware detection tool with CNN classification for small devices. In 2023 6th International Conference on Contemporary Computing and Informatics (IC3I) (Vol. 6, pp. 2017-2023). IEEE.
[26] Q. Sun, Y. Tang, S. Wang, J. Chen, H. Xu and Y. Ling, “A Deep learning based melanocytic nevi classification algorithm by leveraging physiologic-inspired knowledge and channel encoded information”, IEEE Access, vol. 12, pp. 113072-113086, 2024. https://www.mdpi.com/1424-8220/21/23/7884
[27] Jain, S.; Singhania, U.; Tripathy, B.; Nasr, E.A.; Aboudaif, M.K.; Kamrani, A.K, “Deep learning-based transfer learning for classification of Skin cancer”, Sensors, 2021. https://www.acadlore.com/journals/at-aiml
[28] Ashtagi, R., Kharat, P. V., Sarmalkar, V., Hosmani, S., Patil, A. R., Akkalkot, A. I., and Padthe, A, “Enhancing melanoma skin cancer diagnosis through transfer learning: An EfficientNetb0 approach”, Acadlore Transactions on AI and Machine Learning, 3(1), 57-69, 2024. https://www.sciepublish.com/journals/msj
