Feature extraction of dermatoscopic images by iterative segmentation algorithm

Since the introduction of epiluminescence microscopy (ELM), image analysis tools have been extended to the field of dermatology, as an attempt to algorithmically reproduce clinical evaluation. Accurate image segmentation of skin lesions is one of the key steps for useful, early, and non-invasive diagnosis of coetaneous melanomas. This paper proposes an image segmentation algorithm to extract the true border that reveals the global structure irregularity (indentations and protrusions), which may suggest excessive cell growth or regression of a melanoma. The algorithm is applied to the blue channel of the RGB colour vectors to distinguish lesions from the skin and. Analysis of image background is applied by recursive measure of the median and standard deviation of background. This will facilitate automatic and recurring noise reduction and enhancement by image pre-processing. The algorithm also does not depend on the use of rigid threshold values, because an optimal thresholding algorithm "isodata algorithm" that is used determines an optimal threshold iteratively. Experiments are performed on diversity of synthetic skin images that model real hair and lesions of different border irregularities. The aim is to verify the capability of the segmentation algorithm in extracting and characterizing the true features of the processed skin lesions. The next phase of test applies the algorithm to real skin lesions representing high resolution ELM images. We demonstrate that we can enhance and delineate pigmented networks in skin lesions visually, and make them accessible for further analysis and classification.