Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging
Xinyu Peng, Ziyang Zheng, Wenrui Dai, Duoduo Xue, Shaohui Li, Chenglin Li, Junni Zou, Hongkai Xiong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add uncertainty-aware information objective (vs MSE only) (ablation) | InfoMRI-Unroll · Brain MRI 100/15x | PSNR: 40.32 -> 40.96 | Improved |
| add uncertainty-aware information objective (vs MSE only) (ablation) | InfoMRI-Unroll · Brain MRI 100/10x | PSNR: 38.61 -> 39.22 | Improved |
| add uncertainty-aware information objective (vs MSE only) (ablation) | InfoMRI-Unroll · Brain MRI 100/5x | PSNR: 35.91 -> 36.61 | Improved |
| replace U-Net backbone with unrolled network | InfoMRI · Brain MRI 100/15x | PSNR: 38.35 -> 40.96 | Improved |
| replace U-Net backbone with PnP DRUNet | InfoMRI · Brain MRI 100/10x | PSNR: 36.93 -> 38.54 | Improved |
| use learned sampling instead of fixed radial pattern | InfoMRI-Unroll vs ISTA-Net+ · Brain MRI 100/5x | SSIM: 0.8176 -> 0.9393 | Improved |
| train amortized over sampling ratios U[0,0.3] instead of per-ratio models (ablation) | InfoMRI · fastMRI 2D unconstrained | PSNR/SSIM | No clear effect |
| use InfoMRI-Unroll instead of PUERT | InfoMRI-Unroll · Brain MRI 100/15x | PSNR: 41.01 -> 40.96 | No clear effect |
| use InfoMRI amortized sampling instead of LOUPE at 6.25% (1D Cartesian) | InfoMRI · fastMRI 1D Cartesian 6.25% | PSNR/SSIM | Hurt |
Closest papers by meaning
- A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI (AAAI 2019 · similarity 0.91)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.88)
- Efficient Noise Calculation in Deep Learning-based MRI Reconstructions (ICML 2025 · similarity 0.85)
- Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction (ICML 2024 · similarity 0.85)
- AeSPa : Attention-guided Self-supervised Parallel Imaging for MRI Reconstruction (CVPR 2025 · similarity 0.85)
- Fast MRI for All: Bridging Access Gaps by Training without Raw Data (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
