XAI for Skin Cancer Detection with Prototypes and Non-Expert Supervision
This work addresses the need for interpretable and reliable AI models in medical diagnostics for physicians, though it is incremental as it builds on existing prototypical methods with new supervision techniques.
The paper tackled the problem of skin cancer detection from dermoscopy images by proposing an interpretable prototypical-part model that uses non-expert supervision with binary masks and user-refined prototypes to improve reliability and generalization, achieving superior performance compared to non-interpretable models.
Skin cancer detection through dermoscopy image analysis is a critical task. However, existing models used for this purpose often lack interpretability and reliability, raising the concern of physicians due to their black-box nature. In this paper, we propose a novel approach for the diagnosis of melanoma using an interpretable prototypical-part model. We introduce a guided supervision based on non-expert feedback through the incorporation of: 1) binary masks, obtained automatically using a segmentation network; and 2) user-refined prototypes. These two distinct information pathways aim to ensure that the learned prototypes correspond to relevant areas within the skin lesion, excluding confounding factors beyond its boundaries. Experimental results demonstrate that, even without expert supervision, our approach achieves superior performance and generalization compared to non-interpretable models.