In the diagnosis of skin melanoma by analyzing histopathological images, the detection of the melanocytes in the epidermis area is an important step. However, the detection of the melanocytes from the epidermis area is difficult because other keratinocytes that are very similar to the melanocytes are also present. This paper proposes a novel computer-aided technique for detection of the melanocytes in the epidermis area of skin histopathological images. An adaptive threshold technique is first applied to segment all the keratinocytes in the image. In order to distinguish the melanocytes from other keratinocytes, a novel technique based on radial line scanning is proposed to estimate the halo region of the melanocytes. Based on the estimated halo region of all the nuclei, an area ratio of estimated halo region and the nuclei is used to detect the melanocytes from all the keratinocytes. Experimental results on 40 different histopathological images of skin tissue containing 341 melanocytes show that the proposed technique provides a superior performance.
Read full abstract