PASSION for Dermatology: Bridging the Diversity Gap with Pigmented Skin Images from Sub-Saharan Africa

TL;DR

The PASSION project creates the first open-source dataset of pigmented skin images from Sub-Saharan Africa to improve AI dermatology models' accuracy for diverse populations, addressing a significant healthcare gap.

Contribution

This study introduces a novel, publicly available dataset of pigmented skin images from Sub-Saharan Africa and provides baseline AI models tailored for diverse skin types.

Findings

Dataset includes 4,901 images from 1,653 patients.

Baseline models show performance disparities across skin types.

Open-source data aims to improve AI generalization for pigmented skin.

Abstract

Africa faces a huge shortage of dermatologists, with less than one per million people. This is in stark contrast to the high demand for dermatologic care, with 80% of the paediatric population suffering from largely untreated skin conditions. The integration of AI into healthcare sparks significant hope for treatment accessibility, especially through the development of AI-supported teledermatology. Current AI models are predominantly trained on white-skinned patients and do not generalize well enough to pigmented patients. The PASSION project aims to address this issue by collecting images of skin diseases in Sub-Saharan countries with the aim of open-sourcing this data. This dataset is the first of its kind, consisting of 1,653 patients for a total of 4,901 images. The images are representative of telemedicine settings and encompass the most common paediatric conditions: eczema, fungals, scabies, and impetigo. We also provide a baseline machine learning model trained on the dataset and a detailed performance analysis for the subpopulations represented in the dataset. The project website can be found at https://passionderm.github.io/.