Test-Time Selection for Robust Skin Lesion Analysis
This addresses bias in skin lesion analysis for medical practitioners, but it is incremental as it builds on existing test-time debiasing techniques.
The paper tackles the problem of skin lesion analysis models being biased by image acquisition artifacts, proposing TTS (Test-Time Selection), a human-in-the-loop method that uses keypoints to steer models away from spurious correlations without retraining, achieving robustness with less annotation requirements.
Skin lesion analysis models are biased by artifacts placed during image acquisition, which influence model predictions despite carrying no clinical information. Solutions that address this problem by regularizing models to prevent learning those spurious features achieve only partial success, and existing test-time debiasing techniques are inappropriate for skin lesion analysis due to either making unrealistic assumptions on the distribution of test data or requiring laborious annotation from medical practitioners. We propose TTS (Test-Time Selection), a human-in-the-loop method that leverages positive (e.g., lesion area) and negative (e.g., artifacts) keypoints in test samples. TTS effectively steers models away from exploiting spurious artifact-related correlations without retraining, and with less annotation requirements. Our solution is robust to a varying availability of annotations, and different levels of bias. We showcase on the ISIC2019 dataset (for which we release a subset of annotated images) how our model could be deployed in the real-world for mitigating bias.