Pigmented skin lesion segmentation based on sparse texture representations

CÉSAR E. MARTINEZ; ENRIQUE M. ALBORNOZ

Tandil, Buenos Aires

Congreso; 12th International Symposium on Medical Information Processing and Analysis; 2016

SIPAIM Society

Among the most dangerous cancers, there is the Melanoma that affects millions of people. As this is a type ofmalignant pigmented skin lesion and it can be recognized by medical experts, computer-aided diagnostic systemsare developed in order to assist dermatologists in clinical routine. One of the more difficult tasks is to find theright segmentation of lesions whose precision is very important to distinguish benign from malignant cases. Inthis work, we propose a new method based on sparse representation. First, an alternative representation of theimage is obtained from the texture information. A sparse non-negative dictionary is computed and every imageis projected onto this space. The reconstruction is calculated using only the most active atoms, which allows toobtaining an enhanced version of the texture where the morphological post-processing can effectively extract thelesion area. The experiments were carried out on a publicly available database and performance was evaluatedin terms of segmentation error, accuracy, and specificity. Results showed that this first approach performs betterthan methods reported in the literature on this same data.