Automated Quality Control (QC) & Quality Assurance (QA) in MRI

Suboptimal image quality due to motion artifacts, low signal-to-noise ratio, or scanner inhomogeneities can lead to diagnostic misinterpretations or time-consuming re-scans.

Research Focus:

• • Building real-time, AI-driven QC/QA pipelines for automated detection, grading, and classification of image artifacts immediately post-acquisition.

  • Utilizing generative architectures (e.g., conditional Generative Adversarial Networks – cGANs) for artifact reduction, image reconstruction, and synthetic enhancement.

  • Standardizing quality metrics across multi-center setups and clinical routine workflows.