Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions
This addresses the challenge of deployable dermatological image analysis systems by improving robustness across clinical and acquisition conditions, though it is incremental as it builds on existing domain adaptation methods.
The paper tackled the problem of deep learning models for skin lesion classification being sensitive to acquisition variability and domain shifts, and proposed a contrastive meta-domain adaptation strategy that improved generalization robustness, showing consistent gains in classification performance and reduced gaps between dermoscopic and clinical images.
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.