Researchers have developed a novel framework for magnetic resonance imaging (MRI) that adaptively learns where and how much to sample k-space across an entire MRI volume. This approach aims to reduce acquisition times and costs by intelligently allocating sampling budgets across slices and identifying informative k-space lines, moving beyond predefined patterns. The system utilizes acquired auto-calibration signal (ACS) measurements to exploit anatomical information and coordinate sampling decisions while maintaining a total acquisition budget. A complementary reconstruction network refines neighboring-slice reconstructions and enforces data consistency, with both networks optimized jointly without requiring fully sampled k-space during inference. AI
IMPACT This adaptive sampling approach could significantly reduce MRI scan times and costs, improving accessibility and patient comfort.
RANK_REASON Academic paper detailing a new method for MRI acquisition and reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- magnetic resonance imaging
- Reyhaneh Neshatavar
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →