3D-based skin roughness measurement for lesion classification

Abstract

Skin surface roughness can be changed due to skin lesion progression. The evaluation of the damage of the skin is assessed on the base of clinical experience of dermatologists. Currently, the assessment of skin surface is made by running a finger across the skin. It is found that this tactile evaluation may result in inter and intra variations. The objective of our research is to develop an objective assessment tool in evaluation skin roughness. Psoriasis is used as a sample of skin lesion that can change skin surface roughness as its extents develop. 3D surface images of 120 psoriasis lesions scanned from 29 patients are analysed in the study. The lesions are previously grouped into four categorises based on its tactile characteristics by dermatologists. The proposed method converts the 3D images into 2D height maps. The 2D height maps are then fitted and filtered using averaging filter. Finally, Mean Square Error (MSE) between the fitted and filtered 2D height maps are computed and utilized as skin roughness descriptors. Results show that the proposed method has been able to differentiate each lesion according to its group perfectly.