Image Processing Techniques for Analysis of Pigmented Lesions

A noninvasive technique to assist dermatologists in the diagnosis of melanoma is dermoscopy, which is an epiluminescence light microscopy technique that magnifies lesions and enables examination down to the dermoepidermal junction. There are four main diagnostic methods for dermoscopic images: the ABCD rule, pattern analysis, Menzies method, and the 7-point checklist. These methods were evaluated at the 2000 Consensus Net Meeting on Dermoscopy by experts from all over the world. Pattern analysis, considered as the classic approach for diagnosis with dermoscopic images, was deemed to be superior to the other methods. Pattern analysis seeks to identify specific patterns that may be local or global. Melanocytic lesions are identified by their general dermoscopic features, defining their global pattern, or by specific dermoscopic criteria that determine their local patterns. A lesion is categorized by its global pattern, although it can present more than one local pattern. In this seminar, image processing techniques to help physicians to determine different pattern features presented by lesions will be described. For further information contact: Professor Raj Rangayyan – ranga@ucalgary.ca

Location:

Information and Communications Technologies (ICT) 516

Speaker:

Carmen Serrano, PhD, Signal Processing and communications Department, University of Seville, Spain

More information at http://www.ucalgary.ca/events/calendar/image-processing-techniques-analysis-pigmented-lesions