Skin Disease Detection and Classification of Actinic Keratosis and Psoriasis Utilizing Deep Transfer Learning
DOI:
https://doi.org/10.64296/vijir.v1i2.04Keywords:
Skin Cancer, Actinic Keratosis, Psoriasis, CNN, DenseNet201, EnsembleAbstract
Skin diseases can arise from infections, allergies, genetic factors, autoimmune disorders, hormonal imbalances, or environmental triggers such as sun damage and pollution. Skin diseases such as Actinic Keratosis and Psoriasis can be fatal. These are treatable if identified early. However, its diagnostic methods are expensive and not widely accessible. In this study, a novel and efficient method for diagnosing skin diseases using deep learning techniques has been proposed. This approach employs multiple modified Convolutional Neural Network (CNN) models like DenseNet169, DenseNet201 and VGG16. Soft voting ensemble strategy is applied to combine the strengths of individual models to get better result. These models include several convolutional layers. The models have been employed using ImageNet weights and modified top layers. The top layers are modified by fully connected layers and a final softmax activation layer to obtain the result. The dataset analyzed is publicly available and titled “Skin Disease Dataset”. The CNN architecture does not include augmentation by default; data augmentation is typically performed during preprocessing prior to model training. The proposed methodology achieved 93.11% accuracy using the ensemble strategy, demonstrating reliability in classifying skin diseases. The modified pre-trained models showed promising results, increasing its potential for real-world applications.
References
[1] D. Seth, K. Cheldize, D. Brown, and E. F. Freeman, “Global burden of skin disease: Inequities and innovations,” Current Dermatology Reports, vol. 6, no. 3, pp. 204–210, 2017.
[2] World Health Organization, “WHO’s first global meeting on skin NTDs calls for greater efforts to address their bur den,” 2023. [Online]. Available: https://www.who.int/news/item/31-03-2023-who-first-global meeting-on-skin-ntds-calls-for-greater-efforts-to-address-their-burden. [Accessed: Jan. 11, 2025].
[3] World Health Organization, “Radiation: Ultraviolet (UV) radiation and skin cancer,” [Online]. Avail able: https://www.who.int/news-room/questions-and-answers/item/radiation-ultraviolet (uv)-radiation-and-skin-cancer. [Accessed: Jan. 11, 2025].
[4] Department of Dermatology and Venereology, Chittagong Medical College and Hospital, Bangladesh et al., “The burden of dermatoses: Evidence from Bangladesh,” Global Journal of Dermatology and Venereology, vol. 8, no. 1, pp. 10–16, 2020.
[5] M. R. Kabir, M. A. K. Khan, and A. K. Karmakar, “Dermatological patients at the outdoor of an upazila health complex,” TAJ Journal of Teachers Association, vol. 17, no. 2, pp. 93–94, 1970. 17
[6] T.-C. Pham, A. Doucet, C.-M. Luong, C.-T. Tran, and V.-D. Hoang, “Improving skin-disease classification based on customized loss function combined with balanced mini-batch logic and real-time image augmentation,” IEEE Access, vol. 8, pp. 150725–150737, 2020.
[7] S. G. Malik, S. S. Jamil, A. Aziz, S. Ullah, I. Ullah, and M. Abohashrh, “High-precision skin disease diagnosis through deep learning on dermoscopic images,” Bioengineering, vol. 11, no. 9, p. 867, 2024.
[8] X. Zhang, S. Wang, J. Liu, and C. Tao, “Towards improving diagnosis of skin diseases by combining deep neural network and human knowledge,” BMC Medical Informatics and Decision Making, vol. 18, no. S2, 2018.
[9] K. Sriwong, S. Bunrit, K. Kerdprasop, and N. Kerdprasop, “Dermatological classification using deep learning of skin image and patient background knowledge,” International Journal of Machine Learning and Computing, vol. 9, no. 6, pp. 862–867, 2019.
[10] Kaggle, “Skin Disease Dataset,” [Online]. Available: https://www.kaggle.com/datasets/pacificrm/ skindiseasedataset. [Accessed: Jan. 11, 2025].
[11] M. N. Hossen, V. Panneerselvam, D. Koundal, K. Ahmed, F. M. Bui, and S. M. Ibrahim, “Federated machine learning for detection of skin diseases and enhancement of internet of medical things (IoMT) security,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 2, pp. 835–841, 2023.
[12] T. M. Fahrudin and I. Z. A. Illah, “SkinMate: Mobile-based application for detecting multi-class skin diseases classification using pre-trained MobileNetV2 on CNN architecture,” in Proceedings of the IEEE 9th Information Technology International Seminar (ITIS), 2023, pp. 1–6.
[13] D. M. Asadujjaman and P. C. Shill, “Cardiovascular disease diagnosis prediction system using machine learning,” in Smart Innovation, Systems and Technologies, Singapore: Springer Nature Singapore, 2024, pp. 309–319.
[14] M. J. Ferdous, D. M. Asadujjaman, and M. M. Rahman, “An ensemble deep transfer learning approach for classifying COVID-19, pneumonia, and healthy lungs in chest X-ray images with GRAD-CAM visualization,” in 2024 27th International Conference on Computer and Information Technology (ICCIT), 2024, pp. 3075–3080.
[15] M. M. Ikbal et al., “Intelligent Recognition of Bangla Handwritten Digits,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), 2025, pp. 1–6.
[16] M. Z. Hasan et al., “A CNN approach to automated detection and classification of brain tumors,” in 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), 2025, pp. 1–6.
[17] F. Ahmmed, M. Z. Raihan, K. Nahar, and D. M. Asadujjaman, “Automated detection and classification method of brain tumors using CNNs and deep transfer learning,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), 2025, pp. 1–6.
[18] C. Mitra, M. M. Ikbal, F. Parvin, M. M. Rahman, and D. M. Asadujjaman, “Transfer learning based multiclass brain tumor classification using MRI data,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), 2025, pp. 1–6.
[19] M. M. Rahman et al., “Recognizing Bangla numerals: A deep learning approach on a novel handwritten dataset,” in Lecture Notes in Networks and Systems, Cham: Springer Nature Switzerland, 2026, pp. 100–111.
[20] A. Tamim, M. W. Jahan, M. R. S. Chowdhury, A. Hossain, M. M. Rahman, and A. H. M. R. Imon, “Machine learning-driven market value prediction for European football players,” J. Comput. Math. Data Sci., vol. 15, no. 100118, p. 100118, 2025.
