Identification of melanoma diseases from multispectral dermatological images using a novel BSS approach

TL;DR

This paper introduces a novel blind source separation method to identify melanoma by estimating skin chromophore distributions from multispectral images, improving accuracy over RGB-based methods by accounting for shading effects.

Contribution

It presents a new BSS approach that estimates chromophore distributions from multispectral images with at least four bands, without prior information, enhancing melanoma detection accuracy.

Findings

Effective identification of melanoma using multispectral images.

Outperforms RGB-based methods by accounting for shading.

New criterion based on independence hypothesis validates results.

Abstract

In this paper we propose a new approach to identify melanoma diseases by identifying the distribution of its main skin chromophores (melanin, oxyhemoglobin and deoxyhemoglobin) from multispectral dermatological images. Based on Blind Source Separation (BSS), our approach takes into account the shading present in most of the images. Assuming that the multispectral images have at least 4 spectral bands, it allows to estimate the distribution of each chromophore in addition to the shading without any a priori information, contrary to all existing methods that use 3 bands, i.e. RGB images. Indeed, the fact of neglecting the shading degrades their performance. To validate our method, we used a database of real multispectral dermatological images of skin affected by melanoma cancer. To measure our performance, in addition to the classical criterion of visually analyzing the estimated distributions with referring to the physiological knowledge of the disease, we proposed a new criterion that is based on our independence hypothesis. Using these two criteria, we could see that our approach is very efficient for the identification of melanoma.