Abstract
Diagnosing dermatological disorders accurately and on time is essential for the right patient care, but traditional clinical evaluations that are solely based on visual inspection are subjective and may vary from one practitioner to another. This research, therefore, proposes an intelligent deep learning approach to help dermatological diagnostics be more efficient using Convolutional Neural Networks (CNNs). In this article, we summarize and evaluate the research on CNN-based architectures such as VGG, ResNet, Inception, and EfficientNet for dermoscopic image classification. We experiment with different training methods like transfer learning, fine-tuning, and data augmentation to address the problems of overfitting and class imbalance. The comparison with traditional machine learning methods indicates that CNNs have a higher ability of feature extraction, lesion segmentation, and multi-class classification. Different metrics like accuracy, sensitivity, specificity, and AUC-ROC are considered to measure the performance of the models in a complete way. Besides that, the authors point out the present difficulties, such as few annotated datasets, explainability, and clinical integration, in a very critical manner. After that, the paper sketches out the open research problems that will help in the creation of the CNN-based systems that are interpretable, trustworthy, and easily adaptable to clinical settings. It is one of the growing pieces of evidence that deep learning might be a revolutionary tool in dermatology, thus making the diagnosis highly accurate, less time-consuming, and more accessible. In this way, early skin disease detection becomes possibleKeywords
- Convolutional Neural Networks CNN
- Deep learning
- skin disease
- biomedical image processing
References
- Ahmed, H. M., & Kashmola, M. Y. (2023). Performance Improvement of Convolutional Neural Network Architectures for Skin Disease Detection. International Journal of Computing and Digital Systems, 13(1). doi:10.12785/ijcds/130152
- Albawi, S., Abbas, Y. A., Almadanie, Y., & Almadany, Y. (2019). Robust skin diseases detection and classification using deep neural networks. Article in International Journal of Engineering and Technology, 7(4).
- Alghieth, M. (2022). Skin Disease Detection for Kids at School Using Deep Learning Techniques. International journal of online and biomedical engineering, 18(10). doi:10.3991/ijoe.v18i10.31879
- Bandyopadhyay, S. K., Bose, P., Bhaumik, A., & Poddar, S. (2022). Machine Learning and Deep Learning Integration for Skin Diseases Prediction. International Journal of Engineering Trends and Technology, 70(2). doi:10.14445/22315381/IJETT-V70I2P202
- Chakraborty, S., Mali, K., Chatterjee, S., Anand, S., Basu, A., Banerjee, S., . . . Bhattacharya, A. (2017). Image based skin disease detection using hybrid neural network coupled bag-of-features., 2018-January. doi:10.1109/UEMCON.2017.8249038
- Dodia, D., Jakharia, H., Soni, R., Borade, S., & Jain, N. (2022). Human Skin Disease Detection using MLXG model., 3338.
- Hu, Y., Zhu, Y., Lian, N., Chen, M., Bartke, A., & Yuan, R. (2019). Metabolic Syndrome and Skin Diseases. Metabolic Syndrome and Skin Diseases, 10. doi:10.3389/fendo.2019.00788
- Jagdish, M., Paola, S., Guamangate, G., López, M. A., De, J. A., Cruz-Vargas, L., . . . Camacho, R. (2022). Advance Study Of Skin Diseases Detection Using Image Processing Methods. Advance Study Of Skin Diseases Detection Using Image Processing Methods, 9(1).
- Khandagale, M. G., Agunde, M. T., & Hiray, P. S. (2019). Skin disease detection using Image Processing and Machine Learning. IJARCCE, 8(4). doi:10.17148/ijarcce.2019.8448
- Kuzhaloli, S., Varalakshmi, L. M., Gulati, K., Upadhyaya, M., Bhasin, N. K., & Peroumal, V. (2022). Skin disease detection using artificial intelligence., 2393. doi:10.1063/5.0074207
- Lim, H. W., Collins, S. A., Resneck, J. S., Bolognia, J. L., Hodge, J. A., Rohrer, T. A., . . . Moyano, J. V. (2017). The burden of skin disease in the United States. Journal of the American Academy of Dermatology, 76(5). doi:10.1016/j.jaad.2016.12.043
- Manzoor, K., Majeed, F., Siddique, A., Meraj, T., Rauf, H. T., El-Meligy, M. A., . . . Elgawad, A. E. (2021). A lightweight approach for skin lesion detection through optimal features fusion. Computers, Materials and Continua, 70(1). doi:10.32604/cmc.2022.018621
- Mcphie, M. L., Bridgman, A. C., & Kirchhof, M. G. (2021). A Review of Skin Disease in Schizophrenia. A Review of Skin Disease in Schizophrenia, 237(2). doi:10.1159/000508868
- Naji, Z. H., & Abbadi, N. K. (2022). Skin Diseases Detection, Classification, and Segmentation. doi:10.1109/GECOST55694.2022.10009921
- Ojha, M. K., Karakattil, D. R., Sharma, A. D., & Bency, S. M. (2022). Skin Disease Detection and Classification. doi:10.1109/INDISCON54605.2022.9862834
- Owda, A. Y., & Owda, M. (2022). Early Detection of Skin Disorders and Diseases Using Radiometry. Diagnostics, 12(9). doi:10.3390/diagnostics12092117
- Rashid, J., Ishfaq, M., Ali, G., Saeed, M. R., Hussain, M., Alkhalifah, T., . . . Samand, N. (2022). Skin Cancer Disease Detection using Transfer Learning Technique. Applied Sciences (Switzerland), 12(11). doi:10.3390/app12115714
- Reddy, D. A., Roy, S., Kumar, S., & Tripathi, R. (2022). A Scheme for Effective Skin Disease Detection using Optimized Region Growing Segmentation and Autoencoder based Classification., 218. doi:10.1016/j.procs.2023.01.009
- Roy, K., Chaudhuri, S. S., Ghosh, S., Dutta, S. K., Chakraborty, P., & Sarkar, R. (2019). Skin disease detection based on different segmentation techniques. doi:10.1109/OPTRONIX.2019.8862403
- Yadav, N., Kumar, V., & Shrivastava, U. (2016). Skin Diseases Detection Models using Image Processing: A Survey. International Journal of Computer Applications, 137(12). doi:10.5120/ijca2016909001
- Yu, H. Q., & Reiff-Marganiec, S. (2021). Targeted ensemble machine classification approach for supporting iot enabled skin disease detection. IEEE Access, 9. doi:10.1109/ACCESS.2021.3069024