RobMedNAS: searching robust neural network architectures for medical image synthesis

Biomed Phys Eng Express. 2024 Aug 23;10(5):055029. doi: 10.1088/2057-1976/ad6e87.

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.

Keywords: image synthesis; neural architecture search (NAS); robustness.

MeSH terms

  • Algorithms*
  • Brain / diagnostic imaging
  • Humans
  • Image Processing, Computer-Assisted* / methods
  • Magnetic Resonance Imaging* / methods
  • Neural Networks, Computer*
  • Retrospective Studies
  • Tomography, X-Ray Computed* / methods