CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions
This addresses fairness concerns in dermatological AI by reducing demographic biases, specifically for skin type groups, though it is incremental as it builds on existing representation learning techniques.
The paper tackled bias in skin lesion classification across different skin types by proposing CIRCLe, a color invariant representation learning method that uses a regularization loss to align latent representations for the same diagnosis across skin types, achieving superior performance on fairness metrics over state-of-the-art methods on a dataset of 16k+ images spanning 6 skin types and 114 diseases.
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.