Classification of Skin Diseases with Different Deep Learning Models and Comparison of the Performances of the Models

Abstract

Classification of skin diseases is a important isssue for early diagnosis and treatment. The process of determining the disease by the specialist physician also delays the treatment process to be applied to the patient. Computer-aided diagnosis systems play an important role in early diagnosis and initiation of treatment by minimizing such processes. In this study, high-performance classification of skin lesions was performed by using Deep Learning models. Dataset was ISIC data set, dataset were expanded by using data augmentation techniques. In the images in this dataset, there are images of Actinic Keratosis, Dermatofibroma, Pigmented Benign Keratosis, Seborrheic Keratosis, Vascular Lesion skin diseases. The data set was classified by Deep Learning models by using the supervised learning method.. SequeezeNet, AlexNet, GoogleNet, Vgg-19, ResNet101, DenseNet201, ResNet-50, ResNet-18, Vgg-16 DL models were used for classification. To evaluate of classification success of Deep Learning models, confusion matrix and F1-score, precision, sensitivity and accuracy metrics obtained from the matrix were used. According to the F1-score, the most successful model is Vgg16 with 97.41%, while the highest accuracy rate obtained by ResNet18 with 98.06%. High success rate shows that such systems can be used for diagnosis and treatment processes.

Keywords

• Skin diseases
• Artificial intelligence
• Deep learning
• Skin classification
• Disease detection

References

1. Hameed, N., A.M. Shabut, and M.A. Hossain. Multi-class skin diseases classification using deep convolutional neural network and support vector machine. in 2018 12th International Conference on Software, Knowledge, Information Management & Applications (SKIMA). 2018. IEEE.
2. Manoorkar, P., D. Kamat, and P. Patil. Analysis and classification of human skin diseases. in 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT). 2016. IEEE.
3. Hu, Y., et al., Metabolic syndrome and skin diseases. Frontiers in endocrinology, 2019. 10: p. 788.
4. Flohr, C., & Hay, R. (2021). Putting the burden of skin diseases on the global map. British Journal of Dermatology, 184(2), 189-190.
5. Anand, V., Gupta, S., & Koundal, D. (2022). Skin disease diagnosis: challenges and opportunities. In Proceedings of Second Doctoral Symposium on Computational Intelligence: DoSCI 2021 (pp. 449-459). Springer Singapore.
6. Saunte, D. M., Gaitanis, G., & Hay, R. J. (2020). Malassezia-associated skin diseases, the use of diagnostics and treatment. Frontiers in cellular and infection microbiology, 10, 112.
7. Outerbridge, C. A., & Owens, T. J. (2023). Nutritional management of skin diseases. Applied Veterinary Clinical Nutrition, 345-383.
8. Arı, A., O.F. Alcin, and D. Hanbay, Brain MR image classification based on deep features by using extreme learning machines. Biomedical Journal of Scientific and Technical Research, 2020. 25(3).

9. Toraman, S., T.B. Alakus, and I. Turkoglu, Convolutional capsnet: A novel artificial neural network approach to detect COVID-19 disease from X-ray images using capsule networks. Chaos, Solitons & Fractals, 2020. 140: p. 110122.
10. Alakus, T.B. and I. Turkoglu, Comparison of DL approaches to predict COVID-19 infection. Chaos, Solitons & Fractals, 2020. 140: p. 110120.
11. Aktaş, M., F. Doğan, and İ. Türkoğlu. Analysis Of Cracks In Photovoltaic Module Cells From Electroluminescence Images By DL. in 1st International Conference on Computing and Machine Intelligence. 2021.
12. Dogan, F. and I. Turkoglu, Comparison of DL models in terms of multiple object detection on satellite images. Journal of Engineering Research, 2021.
13. Das, B., & Toraman, S. (2022). Deep transfer learning for automated liver cancer gene recognition using spectrogram images of digitized DNA sequences. Biomedical Signal Processing and Control, 72, 103317
14. Demir, F., Sengur, A., Ari, A., Siddique, K., & Alswaitti, M. (2021). Feature mapping and deep long short term memory network-based efficient approach for Parkinson’s disease diagnosis. IEEE Access, 9, 149456-149464.
15. Çalışan, M., Gündüzalp, V., & Olgun, N. Evaluatıon of U-Net and Resnet Archıtectures for Biomedıcal Image Segmentatıon. International Journal of 3D Printing Technologies and Digital Industry, 7(3), 561-570.
16. Sunnetci, K. M., Kaba, E., Beyazal Çeliker, F., & Alkan, A. (2023). Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images. Concurrency and Computation: Practice and Experience, 35(1), e7405.
17. Doğan, F. and İ. Türkoğlu, Derin öğrenme modelleri ve uygulama alanlarına ilişkin bir derleme. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 2019. 10(2): p. 409-445.
18. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2016). Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261.
19. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708.
20. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
21. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097- 1105).
22. Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360
23. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
24. Selçuk, T., Beyoğlu, A., & Alkan, A. (2022). Automatic detection of exudates and hemorrhages in low‐contrast color fundus images using multi semantic convolutional neural network. Concurrency and Computation: Practice and Experience, 34(6), e6768.
25. Zhou, H., et al., Mean shift based gradient vector flow for image segmentation. Computer Vision and Image Understanding, 2013. 117(9): p. 1004-1016.
26. Sadri, A.R., et al., Segmentation of dermoscopy images using wavelet networks. IEEE Transactions on Biomedical Engineering, 2012. 60(4): p. 1134-1141.
27. Xie, F. and A.C. Bovik, Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Pattern Recognition, 2013. 46(3): p. 1012-1019.
28. Kassem, M.A., K.M. Hosny, and M.M. Fouad, Skin lesions classification into eight classes for ISIC 2019 using deep convolutional neural network and transfer learning. IEEE Access, 2020. 8: p. 114822-114832.
29. Kaymak, S., P. Esmaili, and A. Serener. DL for two-step classification of malignant pigmented skin lesions. in 2018 14th Symposium on Neural Networks and Applications (NEUREL). 2018. IEEE.
30. Carcagnì, P., et al. Classification of skin lesions by combining multilevel learnings in a DenseNet architecture. in International conference on image analysis and processing. 2019. Springer.
31. Hosny, K.M., M.A. Kassem, and M.M. Fouad, Classification of skin lesions into seven classes using transfer learning with AlexNet. Journal of digital imaging, 2020. 33(5): p. 1325-1334.