Melanoma and Melanocyte Identification from Hyperspectral Pathology Images Using Object-Based Multiscale Analysis

Abstract

Pathological skin imaging analysis is identified as an efficient technique to diagnose melanoma and provide necessary information for treatment. Automatic detection of melanoma and melanocytes in the epidermis area can be a challenging task as a result of the variability of melanocytes and similarity among cytological components. In order to develop a practical and reliable approach to address the issue, this paper proposed a melanoma and melanocyte detection method based on hyperspectral pathology images. Given the abundant and related spectral and spatial information associated with the hyperspectral skin pathological image, an object-based method was first used to construct the image into the object level; then a multiscale descriptor was performed to extract specific features of melanoma and melanocytes. A quantitative evaluation of 100 scenes of hyperspectral pathology images from 49 patients showed the optimal accuracy, sensitivity, and specificity of 94.29%, 95.57%, and 93.15%, respectively. The results can be interpreted that hyperspectral pathology imaging techniques help to detect the melanoma and melanocytes effectively and provide useful information for further segmentation and classification.