Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation

TL;DR

This paper introduces an adaptive color augmentation method for CNNs to improve skin lesion segmentation in dermatoscopic images, enhancing model robustness and accuracy while controlling synthetic data risks.

Contribution

It proposes a novel adaptive color augmentation technique that boosts data diversity and model performance in skin lesion segmentation tasks.

Findings

Achieved Dice Ratio of 0.891 on ISIC 2018 dataset

Attained 0.943 sensitivity and 0.932 specificity

Validated effectiveness through deep visualization analysis

Abstract

Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum of annotated dermatoscopic screening images, where color is an important discriminative feature. In this paper, we propose an adaptive color augmentation technique to amplify data expression and model performance, while regulating color difference and saturation to minimize the risks of using synthetic data. Through deep visualization, we qualitatively identify and verify the semantic structural features learned by the network for discriminating skin lesions against normal skin tissue. The overall system achieves a Dice Ratio of 0.891 with 0.943 sensitivity and 0.932 specificity on the ISIC 2018 Testing Set for segmentation.