Research map / Label-efficient and robust learning / Domain adaptation and generalization
Generalized Brain Image Synthesis with Transferable Convolutional Sparse Coding Networks
Yawen Huang, Feng Zheng, Xu Sun, Yuexiang Li, Ling Shao, Yefeng Zheng
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 GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · IXI T2w->PDw | PSNR (dB): 32.57 -> 37.18 | Improved |
| add GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · IXI T2w->PDw | Dice (%): 70.71 -> 82.03 | Improved |
| add GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · BraTS T1w->FLAIR | PSNR (dB): 30.08 -> 39.12 | Improved |
| add GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · BraTS T1w->FLAIR | Dice (%): 64.19 -> 85.68 | Improved |
| add GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · BraTS T1w->FLAIR | SSIM: 0.806 -> 0.943 | Improved |
| add GN, LHk, LG and LS regularizers to CSCNet (ablation) | CSCNet · IXI T2w->PDw | SSIM: 0.845 -> 0.904 | Improved |
| TransCSCN versus the strongest baseline CSCl4Net | CSCNet · IXI T2w->PDw | PSNR (dB): 36.64 -> 37.18 | Improved |
| TransCSCN versus the strongest baseline CSCl4Net | CSCNet · BraTS T1w->FLAIR | PSNR (dB): 37.36 -> 39.12 | Improved |
| TransCSCN versus the strongest baseline CSCl4Net | CSCNet · BraTS FLAIR->T1w | Dice (%): 82.58 -> 84.02 | Improved |
| TransCSCN versus the strongest baseline CSCl4Net | CSCNet · IXI PDw->T2w | SSIM: 0.959 -> 0.960 | No clear effect |
| TransCSCN versus supervised REPLICA, trained unpaired | CSCNet · BraTS T1w->FLAIR | PSNR (dB): 31.60 -> 39.12 | Improved |
Closest papers by meaning
- Brain Image Synthesis With Unsupervised Multivariate Canonical CSCl4Net (CVPR 2021 · similarity 0.87)
- Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images Using Weakly-Supervised Joint Convolutional Sparse Coding (CVPR 2017 · similarity 0.87)
- Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications (TPAMI 2017 · similarity 0.86)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.85)
- Bigger Isn’t Always Better: Towards a General Prior for Medical Image Reconstruction (IJCV 2026 · similarity 0.85)
- Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging (ECCV 2024 · 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.
