Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers

Paccotacya-Yanque R.Y.G.; Bissoto A.; Avila S. · Proceedings of the 20th International Symposium on Medical Information Processing and Analysis, SIPAIM 2024 (2024) · DOI: 10.1109/sipaim62974.2024.10783606

Resumen

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 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.

Instituciones: Universidad Católica San Pablo