Research map / Image generation / Fast diffusion sampling
Implicit Neural Representation for Spherical Harmonics Reconstruction of Motion-Corrupted Fetal Diffusion MRI
Wenxuan Wu, Irina Grigorescu, Ruowen Qu, Jo Hajnal, J-Donald Tournier, Maria Deprez
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 Through-Plane Continuity regularization (ablation) | Proposed INR (with bias field) · Fetal dMRI | PSNR: 23.25 -> 23.54 | Improved |
| add Through-Plane Continuity regularization (ablation) | Proposed INR (with bias field) · Fetal dMRI | NCC: 0.8071 -> 0.8194 | Improved |
| add bias field network (ablation) | Proposed INR (with TPC) · Fetal dMRI | PSNR: 23.07 -> 23.54 | Improved |
| add both bias field network and TPC (ablation) | Proposed INR · Fetal dMRI | NRMSE: 0.1954 -> 0.1788 | Improved |
| add both bias field network and TPC (ablation) | Proposed INR · Fetal dMRI | SSIM: 0.8898 -> 0.9014 | Improved |
| raise SH order from 4 to 6 (ablation) | Proposed INR · Fetal dMRI | PSNR: 23.54 -> 23.14 | Hurt |
| raise SH order from 4 to 8 (ablation) | Proposed INR · Fetal dMRI | PSNR: 23.54 -> 22.41 | Hurt |
| lower SH order from 4 to 2 (ablation) | Proposed INR · Fetal dMRI | PSNR: 23.54 -> 23.59 | No clear effect |
| use INR framework instead of IRTK | Proposed INR · Fetal dMRI | SSIM: 0.7516 -> 0.9014 | Improved |
| use INR framework instead of IRTK | Proposed INR · Simulated neonatal dMRI | PSNR: 23.99 -> 25.20 | Improved |
| use INR framework instead of IRTK | Proposed INR · Simulated neonatal dMRI | Run time: 47.80 -> 6.75 | Improved |
| use INR framework instead of IRTK | Proposed INR · Simulated neonatal template dMRI | PSNR: 24.74 -> 24.88 | Improved |
Closest papers by meaning
- Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI (CVPR 2024 · similarity 0.85)
- SVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba (AAAI 2025 · similarity 0.84)
- Equivariant spatio-hemispherical networks for diffusion MRI deconvolution (NeurIPS 2024 · similarity 0.83)
- Efficient Noise Calculation in Deep Learning-based MRI Reconstructions (ICML 2025 · similarity 0.83)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.83)
- Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data (ICLR 2025 · similarity 0.82)
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.
