Assessing the validity of saliency maps for abnormality localization in medical imaging

Nishanth Thumbavanam Arun, Nathan Gaw, Praveer Singh, Ken Chang, Katharina Viktoria Hoebel, Jay Patel, Mishka Gidwani, Jayashree Kalpathy-Cramer

Track: short paper

Keywords: Saliency maps, localization, anomaly detection, medical imaging, deep learning.

Abstract: Saliency maps have become a widely used method to assess which areas of the input image are most pertinent to the prediction of a trained neural network. However, in the context of medical imaging, there is no study to our knowledge that has examined the efficacy of these techniques and quantified them using overlap with ground truth bounding boxes. In this work, we explored the credibility of the various existing saliency map methods on the RSNA Pneumonia dataset. We found that GradCAM was the most sensitive to model parameter and label randomization, and was highly agnostic to model architecture.

Paper Type: well-validated application

Presentation Upload Agreement: I agree that my presentation material (videos and slides) will be made public.