Accelerated MRI Reconstruction

MRI: Magnetic Resonance Imaging

Overview

The field studies how to reconstruct MRI images from fewer k-space measurements, reducing scan time while retaining structures and signals needed for diagnosis. Methods range from compressed sensing and parallel-coil models to unrolled networks, implicit neural representations, and diffusion or flow-based priors, often enforcing consistency with acquired measurements. Researchers also learn acquisition patterns and develop techniques for dynamic, multi-contrast, low-field, and motion-affected MRI. A central challenge is balancing speed and image quality with generalization across scanners and patients, while detecting hallucinations and estimating when a reconstruction is unreliable.

Latest papers

CardsList

94 papers11 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction

    Feb 20, 2026Qingyong Zhu, Yumin Tan, Xiang Gu +1Accelerated MRI ReconstructionGenerative Modeling

  2. MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI

    Jan 30, 2026Zhengyi Lu, Ming Lu, Chongyu Qu +11Magnetic Resonance ImagingAccelerated MRI Reconstruction

  3. Pixelwise Uncertainty Quantification of Accelerated MRI Reconstruction

    Jan 19, 2026Ilias I. Giannakopoulos, Lokesh B Gautham Muthukumar, Yvonne W. Lui +1Uncertainty QuantificationAccelerated MRI Reconstruction

  4. Accelerated MR Elastography Using Learned Neural Network Representation

    Jan 17, 2026Xi PengRepresentation LearningAccelerated MRI Reconstruction