Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis

TL;DR

This paper introduces a novel data augmentation method for dermoscopic skin images using color constancy techniques, improving deep learning models for skin lesion analysis without external data.

Contribution

It proposes a new augmentation approach leveraging shades of gray color constancy to enhance deep skin image analysis models.

Findings

Improved segmentation and classification performance on ISIC 2017 dataset.

Effective augmentation without external dermatologic image sets.

Promising validation results indicating potential for clinical application.

Abstract

Dermoscopic skin images are often obtained with different imaging devices, under varying acquisition conditions. In this work, instead of attempting to perform intensity and color normalization, we propose to leverage computational color constancy techniques to build an artificial data augmentation technique suitable for this kind of images. Specifically, we apply the \emph{shades of gray} color constancy technique to color-normalize the entire training set of images, while retaining the estimated illuminants. We then draw one sample from the distribution of training set illuminants and apply it on the normalized image. We employ this technique for training two deep convolutional neural networks for the tasks of skin lesion segmentation and skin lesion classification, in the context of the ISIC 2017 challenge and without using any external dermatologic image set. Our results on the validation set are promising, and will be supplemented with extended results on the hidden test set when available.