Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation

Компьютерная оптика

Le Minh Hieu¹  Prayag Tiwari²  Dang N.H. Thanh³  V.B. Surya Prasath⁴  Nguyen Hoang Hai⁵ 

[1] Department of Economics, University of Economics, University of Danang, Vietnam;Department of Information Engineering, University of Padua, Italy;Department of Information Technology, School of Business Information Technology, University of Economics Ho Chi Minh City, Vietnam;Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH USA;Faculty of Computer Science, Vietnam-Korea University of Information and Communication Technology – The University of Danang, Vietnam;

关键词: image segmentation;    medical image segmentation;    semantic segmentation;    melanoma;    skin cancer;    skin lesion;    deep learning;    cancer;   

DOI  :  10.18287/2412-6179-CO-748

来源: DOAJ

【 摘 要 】

Melanoma skin cancer is one of the most dangerous forms of skin cancer because it grows fast and causes most of the skin cancer deaths. Hence, early detection is a very important task to treat melanoma. In this article, we propose a skin lesion segmentation method for dermoscopic images based on the U-Net architecture with VGG-16 encoder and the semantic segmentation. Base on the segmented skin lesion, diagnostic imaging systems can evaluate skin lesion features to classify them. The proposed method requires fewer resources for training, and it is suitable for computing systems without powerful GPUs, but the training accuracy is still high enough (above 95 %). In the experiments, we train the model on the ISIC dataset – a common dermoscopic image dataset. To assess the performance of the proposed skin lesion segmentation method, we evaluate the Sorensen-Dice and the Jaccard scores and compare to other deep learning-based skin lesion segmentation methods. Experimental results showed that skin lesion segmentation quality of the proposed method are better than ones of the compared methods.

【 授权许可】

Unknown