Research map / Federated learning and privacy / Personalized and heterogeneous FL
Multi-Institutional Collaborations for Improving Deep Learning-Based Magnetic Resonance Image Reconstruction Using Federated Learning
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 |
|---|---|---|---|
| add latent-feature adversarial cross-site modeling (ablation) | FL-MR · Scenario 1, four-site average, T1-weighted | SSIM: 0.8976 -> 0.9108 | Helped |
| add latent-feature adversarial cross-site modeling (ablation) | FL-MR · Scenario 1, four-site average, T2-weighted | SSIM: 0.8997 -> 0.9113 | Helped |
| add latent-feature adversarial cross-site modeling (ablation) | FL-MR · Scenario 2, four-site average, T1-weighted | SSIM: 0.9294 -> 0.9381 | Helped |
| add latent-feature adversarial cross-site modeling (ablation) | FL-MR · Scenario 2, four-site average, T2-weighted | SSIM: 0.9238 -> 0.9373 | Helped |
| add federated collaboration across institutions | single-site reconstruction models · Scenario 2, HPKS T2-weighted | SSIM: 0.9001 -> 0.9232 | Helped |
| add federated collaboration across institutions | single-site reconstruction models · Scenario 2, HPKS T2-weighted | PSNR: 31.29 -> 32.44 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on BraTS · T2-weighted, average across fastMRI, HPKS, and IXI targets | SSIM: 0.7057 -> 0.7525 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on fastMRI · T2-weighted, average across BraTS, HPKS, and IXI targets | SSIM: 0.8921 -> 0.9027 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on HPKS · T2-weighted, average across BraTS, fastMRI, and IXI targets | SSIM: 0.8501 -> 0.8582 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on IXI · T2-weighted, average across BraTS, fastMRI, and HPKS targets | SSIM: 0.8738 -> 0.8949 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on BraTS · T2-weighted, average across fastMRI, HPKS, and IXI targets | PSNR: 27.22 -> 27.32 | Helped |
| add cross-site modeling (ablation) | a reconstruction model trained on fastMRI · T2-weighted, average across BraTS, HPKS, and IXI targets | PSNR: 30.92 -> 31.58 | Helped |
Closest papers by meaning
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.87)
- Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model (CVPR 2025 · similarity 0.83)
- Fast MRI for All: Bridging Access Gaps by Training without Raw Data (NeurIPS 2025 · similarity 0.83)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.83)
- FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models (CVPR 2025 · similarity 0.83)
- FedPIA – Permuting and Integrating Adapters Leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning (AAAI 2025 · similarity 0.83)
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.