Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Learning Optimal K-Space Acquisition and Reconstruction Using Physics-Informed Neural Networks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Learn the k-space trajectory jointly with image reconstruction rather than use a fixed trajectory | MRI acquisition and U-Net reconstruction · AXT1 and AXT1POST brain images; Cartesian, radial and spiral sampling | PSNR: 24.24 \pm 0.83 -> 24.98 \pm 0.85; 30.18 \pm 0.73 -> 33.06 \pm 1.23 | Helped |
| Use neural ODE trajectory optimization instead of PILOT's learnable-matrix acquisition optimization | Radial acquisition and reconstruction · AXT1POST, 16-shots and 32-shots | PSNR: 28.62 \pm 0.66 -> 31.03 \pm 0.59; 31.24 \pm 0.61 -> 33.06 \pm 1.23 | Helped |
| Add MRI gradient-amplitude and slew-rate constraints to trajectory optimization (ablation) | Neural ODE trajectory optimization · Cartesian and non-Cartesian MRI acquisition | hardware feasibility | Helped |
| Use learned rather than fixed trajectories | MRI acquisition and reconstruction · AXT1 and AXT1POST brain images; all reported acceleration levels and sampling patterns | SSIM | Helped |
| Remove trajectory optimization and train only the reconstruction U-Net (ablation) | Joint acquisition and reconstruction framework · Brain and knee MRI | reconstruction quality | Hurt |
Closest papers by meaning
- Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction (ICML 2024 · similarity 0.88)
- Improving Deep Learning for Accelerated MRI With Data Filtering (NeurIPS 2025 · similarity 0.87)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.86)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.86)
- Efficient Noise Calculation in Deep Learning-based MRI Reconstructions (ICML 2025 · similarity 0.86)
- AeSPa : Attention-guided Self-supervised Parallel Imaging for MRI Reconstruction (CVPR 2025 · similarity 0.85)
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.