CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions

TL;DR

CIRCLe is a novel deep learning method that enhances fairness in skin lesion classification by learning color-invariant representations, reducing bias across diverse skin types while maintaining high accuracy.

Contribution

It introduces a regularization-based approach to achieve skin color invariance in deep models, improving fairness without sacrificing accuracy.

Findings

Outperforms state-of-the-art on 16k+ images across 6 skin types

Reduces bias as measured by equal opportunity difference

Proposes a new fairness metric, normalized accuracy range

Abstract

While deep learning based approaches have demonstrated expert-level performance in dermatological diagnosis tasks, they have also been shown to exhibit biases toward certain demographic attributes, particularly skin types (e.g., light versus dark), a fairness concern that must be addressed. We propose CIRCLe, a skin color invariant deep representation learning method for improving fairness in skin lesion classification. CIRCLe is trained to classify images by utilizing a regularization loss that encourages images with the same diagnosis but different skin types to have similar latent representations. Through extensive evaluation and ablation studies, we demonstrate CIRCLe's superior performance over the state-of-the-art when evaluated on 16k+ images spanning 6 Fitzpatrick skin types and 114 diseases, using classification accuracy, equal opportunity difference (for light versus dark groups), and normalized accuracy range, a new measure we propose to assess fairness on multiple skin type groups.