Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing

Abstract

This paper shows new contributions in the detection of skin cancer, where we present the use of a customized hyperspectral system that captures images in the spectral range from 450 to 950 nm. By choosing a 7 × 7 sub-image of each channel in the hyperspectral image (HSI) and then taking the mean and standard deviation of these sub-images, we were able to make fits of the resulting curves. These fitted curves had certain characteristics, which then served as a basis of classification. The most distinct fit was for the melanoma pigmented skin lesions (PSLs), which is also the most aggressive malignant cancer. Furthermore, we were able to classify the other PSLs in malignant and benign classes. This gives us a rather complete classification method for PSLs with a novel perspective of the classification procedure by exploiting the variability of each channel in the HSI.

Towards Real-Time Hyperspectral Multi-Image Super-Resolution Reconstruction Applied to Histological Samples

“…In a certain sense, this is by itself an act of gathering information about an object or scene without coming into physical contact. There are many specific cases for which HSI presents an interesting approach, such as satellite remote sensing [ 13 ], food quality assessment [ 14 ], and agriculture [ 15 ], dermatology [ 16 ]. In this publication we focus on medical applications, in particular on computational histology [ 17 ].…”