Patch Selection for Melanoma Classification

TL;DR

This paper explores automatic patch selection criteria for melanoma image classification, demonstrating that entropy-based patch selection improves training efficiency and accuracy over spectral similarity methods.

Contribution

It introduces and compares entropy and spectral similarity criteria for patch selection, showing entropy's superiority in melanoma classification tasks.

Findings

Entropy-based patch selection converges faster.

Higher entropy patches yield better accuracy.

Entropy method reduces preprocessing time.

Abstract

In medical image processing, the most important information is often located on small parts of the image. Patch-based approaches aim at using only the most relevant parts of the image. Finding ways to automatically select the patches is a challenge. In this paper, we investigate two criteria to choose patches: entropy and a spectral similarity criterion. We perform experiments at different levels of patch size. We train a Convolutional Neural Network on the subsets of patches and analyze the training time. We find that, in addition to requiring less preprocessing time, the classifiers trained on the datasets of patches selected based on entropy converge faster than on those selected based on the spectral similarity criterion and, furthermore, lead to higher accuracy. Moreover, patches of high entropy lead to faster convergence and better accuracy than patches of low entropy.