Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions

TL;DR

This paper introduces a visual meta-domain adaptation method that enhances the robustness of skin lesion classification models across different clinical and acquisition conditions by transferring visual representations from dermoscopic datasets.

Contribution

It proposes a novel adaptation strategy based on visual meta-domains to improve generalization of skin lesion classifiers across diverse imaging conditions.

Findings

Significant performance improvements across multiple dermatology datasets.

Reduced domain gap between dermoscopic and clinical images.

Enhanced robustness of skin lesion classification models.

Abstract

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual artifacts and domain shifts affect deep learning-based skin lesion classification. We propose an adaptation strategy, grounded in the idea of visual meta-domains, that transfers visual representations from larger dermoscopic datasets into clinical image domains, thereby improving generalization robustness. Experiments across multiple dermatology datasets show consistent gains in classification performance and reduced gaps between dermoscopic and clinical images. These results emphasize the importance of domain-aware training for deployable systems.