Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers
This work addresses the need for reliable explanations in skin cancer predictions for clinical applications, but it is incremental as it evaluates existing methods without introducing new ones.
The paper tackled the problem of understanding deep learning models for skin lesion classification by analyzing seven explainability methods, finding that while they reveal biases, improvements are needed for comprehensive transparency.
Deep Learning has shown outstanding results in computer vision tasks; healthcare is no exception. However, there is no straightforward way to expose the decision-making process of DL models. Good accuracy is not enough for skin cancer predictions. Understanding the model's behavior is crucial for clinical application and reliable outcomes. In this work, we identify desiderata for explanations in skin-lesion models. We analyzed seven methods, four based on pixel-attribution (Grad-CAM, Score-CAM, LIME, SHAP) and three on high-level concepts (ACE, ICE, CME), for a deep neural network trained on the International Skin Imaging Collaboration Archive. Our findings indicate that while these techniques reveal biases, there is room for improving the comprehensiveness of explanations to achieve transparency in skin-lesion models.