Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation

TL;DR

This paper presents a transfer learning and domain adaptation approach to improve skin disease prediction accuracy across diverse skin tones, addressing biases and data scarcity in dermatology AI models.

Contribution

It introduces a novel multi-source transfer learning framework combined with domain adaptation to enhance inclusivity in skin disease diagnosis models.

Findings

Med-ViT achieved top performance among evaluated models.

Domain adaptation significantly improved model accuracy across skin tones.

The approach effectively reduces bias in dermatological AI diagnostics.

Abstract

In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.