Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces HieraSample, a novel framework for active sampling in MRI that strategically prioritizes low and high spatial frequencies based on their diagnostic relevance. By employing a cosine-annealed curriculum to gradually reduce the acceleration factor while maintaining low-frequency data, and utilizing a Mamba-based policy to select high-frequency coordinates, the method achieves significant improvements in diagnostic accuracy. On the fastMRI+ knee benchmark, HieraSample not only matches the performance of fully-sampled oracles but also surpasses existing Cartesian baselines by up to 20.4 AUC points in ACL severity assessment.
HieraSample achieves unprecedented diagnostic accuracy in accelerated MRI by intelligently balancing low and high-frequency sampling, outperforming traditional methods by over 20 AUC points.
Active sampling for accelerated MRI must distribute a tight sampling budget across spatial frequencies that carry very different kinds of information. Low frequencies hold most of the anatomical context; high frequencies carry the fine details that drive pathology assessment. Existing active samplers either treat both regions identically or restrict the action space to entire Cartesian rows, which forces a poor compromise at high acceleration. We propose HieraSample, a task-driven framework built around this hierarchy. A cosine-annealed curriculum lowers the acceleration factor from 20x to 4x across 80 acquisition steps while keeping a fully-sampled low-frequency disk at every step; a Mamba-based policy then picks individual high-frequency coordinates from features extracted by dual disease and severity classifiers. The reward is the per-sample reduction in class-weighted cross-entropy after each action, so a positive reward corresponds directly to a more confident correct prediction. On the fastMRI+ knee benchmark, HieraSample matches the fully-sampled oracle on ACL diagnosis from 4x to 10x acceleration, and improves on a recent Cartesian baseline by as much as 20.4 AUC points on ACL severity.