RobMedNAS: searching robust neural network architectures for medical image synthesis

Biomed Phys Eng Express. 2024 Aug 13. doi: 10.1088/2057-1976/ad6e87. Online ahead of print.

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.&#xD.

PMID:39137798 | DOI:10.1088/2057-1976/ad6e87