Evaluating Adversarial Robustness of Low dose CT Recovery
This work addresses the critical need for robust CT recovery methods in clinical settings, highlighting vulnerabilities that could impact patient diagnosis, though it is incremental as it focuses on evaluation rather than proposing new solutions.
The study evaluated the adversarial robustness of low dose CT recovery methods, finding that deep networks are more susceptible to untargeted attacks and that both classical and deep learning approaches are vulnerable to localized attacks causing small perturbations in lesions, with high data consistency maintained.
Low dose computed tomography (CT) acquisition using reduced radiation or sparse angle measurements is recommended to decrease the harmful effects of X-ray radiation. Recent works successfully apply deep networks to the problem of low dose CT recovery on bench-mark datasets. However, their robustness needs a thorough evaluation before use in clinical settings. In this work, we evaluate the robustness of different deep learning approaches and classical methods for CT recovery. We show that deep networks, including model-based networks encouraging data consistency, are more susceptible to untargeted attacks. Surprisingly, we observe that data consistency is not heavily affected even for these poor quality reconstructions, motivating the need for better regularization for the networks. We demonstrate the feasibility of universal attacks and study attack transferability across different methods. We analyze robustness to attacks causing localized changes in clinically relevant regions. Both classical approaches and deep networks are affected by such attacks leading to changes in the visual appearance of localized lesions, for extremely small perturbations. As the resulting reconstructions have high data consistency with the original measurements, these localized attacks can be used to explore the solution space of the CT recovery problem.