Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging

Understand

Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image.

• They are increasingly being used in medical imaging to provide clinically plausible explanations for the decisions the neural network makes.
• However, the utility and robustness of these visualization maps has not yet been rigorously examined in the context of medical imaging.
• We posit that trustworthiness in this context requires 1) localization utility, 2) sensitivity to model weight randomization, 3) repeatability, and 4) reproducibility.