Segmentation methods for computer aided melanoma detection

Melanoma is one of the deadly diseases among skin cancer. Melanoma detection can be done by dermatological screening and biopsy tests which are time consuming and expensive that requires experts from medical field. Due to cost of dermatologist to screen every patient, an automated system is needed for melanoma detection so that death rates can be minimized if detected early. It can be done using various image processing techniques. An important step in the automated system of melanoma detection is the segmentation process which locates the border of skin lesion in order to separate the lesion part from background skin for further feature extraction. This paper gives a study on various segmentation techniques that can be applied for melanoma detection using image processing. Statistical region merging, iterative stochastic region merging, adaptive thresholding, color enhancement and iterative segmentation, multilevel thresholding are discussed in this paper. A comparative study of these segmentation methods is also performed based on the parameters accuracy, sensitivity and specificity. Multilevel thresholding has the highest accuracy and specificity and maximum sensitivity is obtained for iterative stochastic region merging.