Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

TL;DR

This study estimates skin tone in dermatology datasets using the individual typology angle (ITA) and investigates its impact on machine learning model performance, revealing under-representation of darker skin tones and no clear performance correlation.

Contribution

Introduces a method to estimate skin tone in dermatology datasets and analyzes its relationship with model performance, highlighting dataset biases.

Findings

Most data have lighter skin tones (ITA 34.5°-48°).

Darker skin tones are under-represented in datasets.

No measurable correlation between skin tone and model performance.

Abstract

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.