Lesion detection in dermoscopy images using Sarsa Reinforcement algorithm

Dermoscopy is one of the major imaging techniques used in diagnoses of Melanoma and other skin diseases. Because of difficulties and subjectivity of human interpretation, automatic and computerized analysis of dermoscopic images has opened an important research area. Skin lesion detection is as the first step in this analysis. Finding an optimal threshold for segmenting the lesion is a severe task in image processing. Different methods for thresholding already exist. In this work, we use a combination of well-known thresholding methods and fuse them by Sarsa Reinforcement algorithm which leads to a reinforced threshold. The reinforced agent learns optimal weights for different thresholding methods and finally segments the dermoscopic image with optimal threshold. A reward function is designed for achieving the similarity ratio between the binary output image and original gray level image and calculating reward/punish signal which should be exerted to reinforced agent. We use three thresholding methods for combination in the reinforced agent and the detected lesions are compared with the ground-truth which is determined by three different dermatologists.