SkinCancer

AI/DL/ML for Skin Lesions Segmentation, Melanoma Classification

Abstract:

Melanoma, which is the deadliest type of skin cancer, occurs when there is something serious with melanocytes which are melanin-producing cells in the skin. This project investigates on how we can leverage AI models for skin lesions classification:

1. Melnoma skin cancer detection using standard image processing techniques such as the morphological features of the lesions [1]

2. Skin lesion segmentation with image processing [2,3] and compute-efficient deep learning [4]

3. Multi-class classification with deep learning [5] - classes : Nevi (nv), Actinic Keratosis (akiec), Melanoma (mel), Basal Cell Carcinoma (bcc), Vascular Skin Lesions (vasc), Benign Keratosis-like Lesions (bkl), and DermatoFibroma (df)

References:

[1] D. N. H. Thanh, V. B. S. Prasath, L. M. Hieu, N. N. Hien. Melanoma skin cancer detection method based on adaptive principal curvature, colour normalisation and feature extraction with the ABCD rule. Journal of Digital Imaging, 33(3), 574-585, June 2020. doi:10.1007/s10278-019-00316-x

[2] D. N. H. Thanh, N. H. Hai, L. M. Hieu, P. Tiwari, V. B. S. Prasath. Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation. Computer Optics, 45(1), 122-129, January 2021. doi:10.18287/2412-6179-CO-748

[3] D. N. H. Thanh, U. Erkan, V. B. S. Prasath, V. Kumar, N. N. Hien. A skin lesion segmentation method for dermoscopic images based on adaptive thresholding with normalization of color models. 6th International Conference on Electrical and Electronics Engineering (ICEEE), Istanbul, Turkey. Proc. IEEE, pp. 116-120, April 2019. doi:10.1109/ICEEE2019.2019.00030

[4] D. N. H. Thanh, N. N. Hien, V. B. S. Prasath, U. Erkan, A. Khamparia. Adaptive thresholding skin lesion segmentation with Gabor filters and principal component analysis. 4th International Conference on Research in Intelligent and Computing in Engineering (RICE), Hanoi, Vietnam. Proc. Springer AISC, vol. 1125, 811-820, August 2019. doi:10.1007/978-981-15-2780-7_87

[5] P. V. S. P. Raghavendra, C. Charitha, K. G. Begum, V. B. S. Prasath. Deep learning-based skin lesion multi-class classification with global average pooling improvement. Journal of Digital Imaging, 36(5), 2227-2248, October 2023. doi:10.1007/s10278-023-00862-5.

[6] N. Salamat, S. A. Idris, Z. A. Shaikh, A. Yousef, V. B. S, Prasath. Anonymous submission. Submitted, 2024.