DIAGNOSIS OF SKIN LESIONS BASED ON GRAPH SEGMENTATION ALGORITHM
Main Article Content
Abstract
The skin is the largest organ and the outer protective layer of the human body. With its seven layers safeguarding the internal organs, the skin plays a vital role and requires proper care. Skin conditions are related to skin health and encompass various types of skin diseases, posing a challenge for physicians in their classification. They have explored machine learning systems to predict and classify these skin conditions, aiming to aid in treatment or minimize their impact. If symptoms such as acne, dermatitis, candida infection, eczema, sclerosis, fungal infections, psoriasis, dermatitis, and other conditions are not treated early, they can lead to severe health issues and even mortality. Image segmentation is a supportive method for identifying external skin diseases. Graph-cut algorithms have been discussed and utilized in various applications, including image blurring, image segmentation, and energy consumption issues. In this paper, we propose a novel dynamic graph-cut algorithm for segmenting skin lesions and subsequently employ a Naive Bayes probabilistic classifier to classify skin diseases. Our approach was experimentally tested on the ISIC 2017 dataset and demonstrated superior results compared to many other modern methods.
Keywords
Bayes, graph cut, image classification, skin lesions
Article Details
References


Ambad, P. S., & Shirsat, A. (2016). A image analysis system to detect skin diseases. IOSR Journal of VLSI Signal Processing, 6(5), 17-25.

Eriksson, A. P., Barr, O., & Astrom, K. (2006). Image segmentation using minimal graph cuts. In SSBA Symposium on Image Analysis (pp. 16-17). https://eprints.qut.edu.au/108194/1/108194.pdf

Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59, 167-181.

Ghosh, S., Das, N., Das, I., & Maulik, U. (2019). Understanding deep learning techniques for image segmentation. ACM computing surveys, 52(4), 1-35.

Harangi, B. (2018). Skin lesion classification with ensembles of deep convolutional neural networks. Journal of biomedical informatics, 86, 25-32.

Hoshyar, A. N., Al-Jumaily, A., & Hoshyar, A. N. (2014). Comparing the performance of various filters on skin cancer images. Procedia computer science, 42, 32-37.

Huynh, A. T., Hoang, V.-D., Vu, S., Le, T. T., & Nguyen, H. D. (2022). Skin Cancer Classification Using Different Backbones of Convolutional Neural Networks. In Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence: 35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2022, Kitakyushu, Japan, July 19–22, 2022, Proceedings (pp. 160-172). Springer-Verlag. https://doi.org/10.1007/978-3-031-08530-7_14


Kolkur, S., Kalbande, D., Shimpi, P., Bapat, C., & Jatakia, J. (2016). Human Skin Detection Using RGB, HSV and YCbCr Color Models. In Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016). https://doi.org/10.2991/iccasp-16.2017.51


Liao, H. (2016). A Deep Learning Approach to Universal Skin Disease Classification. CSC 400 - Graduate Problem Seminar - Project Report.

Liu, X., Deng, Z., & Yang, Y. (2019). Recent progress in semantic image segmentation. Artificial Intelligence Review, 52, 1089-1106.

Maglogiannis, I., Zafiropoulos, E., & Kyranoudis, C. (2006). Intelligent Segmentation and Classification of Pigmented Skin Lesions in Dermatological Images. In G. Antoniou, G. Potamias, C. Spyropoulos, & D. Plexousakis (Eds.), Advances in Artificial Intelligence. SETN 2006. Lecture Notes in Computer Science (Vol. 3955). Springer, Berlin, Heidelberg. https://doi.org/10.1007/11752912_23


Mansour, A. M. (2018). Texture classification using Naïve Bayes classifier. International Journal of Computer Science and Network Security, 18(1), 112-120. http://paper.ijcsns.org/07_book/201801/20180113.pdf

Mendes, D. B., & da Silva, N. C. (2018). Skin Lesions Classification Using Convolutional Neural Networks in Clinical Images. arXiv Preprint. https://doi.org/10.48550/arXiv.1812.02316


Subramanian, R. R., Achuth, D., Kumar, P. S., Reddy, K. N. K., Amara, S., & Chowdary, A. S. (2021). Skin cancer classification using Convolutional neural networks. In 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence) (pp. 13-19). https://doi.org/10.1109/Confluence51648.2021.9377155


Sumithra, R., Suhil, M., & Guru, D. (2015). Segmentation and classification of skin lesions for disease diagnosis. Procedia computer science, 45, 76-85.

Tran, N. N., Nguyen, H. D., Huynh, N. T., Tran, N. P., & Nguyen, L. V. (2022). Segmentation on chest CT imaging in COVID-19 based on the improvement attention U-Net model. In New Trends in Intelligent Software Methodologies, Tools and Techniques (pp. 596-606), IOS Press.

Wei, L., Gan, Q., & Ji, T. (2018). Skin Disease Recognition Method Based on Image Color and Texture Features. Computational and Mathematical Methods in Medicine, 2018, Article 8145713. https://doi.org/10.1155/2018/8145713


Yi, F., & Moon, I. (2012). Image segmentation: A survey of graph-cut methods. In 2012 International Conference on Systems and Informatics (ICSAI2012) (pp. 1936-1941). https://doi.org/10.1109/ICSAI.2012.6223428


Zaqout, I. (2019). Diagnosis of Skin Lesions Based on Dermoscopic Images Using Image Processing Techniques. In Pattern Recognition - Selected Methods and Applications (pp. 1-16). IntechOpen. https://doi.org/10.5772/intechopen.88065

