MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction
Researchers have developed MoE-dqINR, a new framework for reconstructing images from undersampled MRI data. This method utilizes a Mixture-of-Experts approach, separating shared spatial information from state-specific synthesis to improve flexibility and efficiency. The framework significantly reduces scan-specific optimization time to approximately 30 seconds per scan, down from hundreds or thousands of seconds with previous methods. AI
IMPACT Introduces a more efficient method for MRI reconstruction, potentially speeding up diagnostic processes.