Detection and Analysis of Local Dermoscopic Features in Malignant Melanoma

Skin cancer is the most commonly diagnosed type of cancer in all people, regardless of age, gender, or race. One of the most common malignant. skin cancer is melanoma which is a dangerous proliferation of melanocytes. In the last several years an increasing melanoma incidence has been observed worldwide, and the diagnosis and deaths are increasing faster than those of any other skin cancer. In the light of the above data, prevention and early diagnosis of melanoma (tumour thickness below 0.75 mm) becomes an extremely important issue. This can be achieved on the basis of advanced devices connected with a computer-aided system. One of the most widely used diagnostic algorithm is the 7-point chechlist that requires the identification of 7 dermoscopic criteria (local features) and can be used for the early assessment of skin lesions.

 

In this talk I will discuss the aim of my research and describe implemented algorithm steps containing: image enhancement, lesion segmentation, local feature detection as well as classification. I will also present challenges in skin lesion segmentation and local feature detection as well as outline new research plans in the field of dermoscopic images.