Abstract
Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS’s efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.
Funding Information
  • U.S. National Library of Medicine (NIH R01 LM013151)
  • Science and Technology Facilities Council
  • Engineering and Physical Sciences Research Council (EP/T022159/1)
  • Cambridge Service for Data Driven Discovery
  • National Science Foundation (DMS-1749857)

This publication has 22 references indexed in Scilit: