ArticleIEEE transactions on computational imaging2023
A Theoretical Framework for Self-Supervised MR Image Reconstruction Using Sub-Sampling via Variable Density Noisier2Noise.
Article in IEEE transactions on computational imaging, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed.
- Accelerating Stroke MRI With Diffusion Probabilistic Models Through Large-Scale Pre-Training and Target-Specific Fine-Tuning.Magnetic resonance in medicine · 2026Article
- Dual-branch MRI denoising and motion artifact suppression with uncertainty estimation and segmentation-based evaluation.Medical physics · 2026Article
- Few-shot learning for highly accelerated 3D time-of-flight MRA reconstruction.Magnetic resonance in medicine · 2026Article
- Self-supervised learning for MRI reconstruction: a review and new perspective.Magma (New York, N.Y.) · 2025Review
- Robust multi-coil MRI reconstruction via self-supervised denoising.Magnetic resonance in medicine · 2025Article
- SPARSITY-DRIVEN PARALLEL IMAGING CONSISTENCY FOR IMPROVED SELF-SUPERVISED MRI RECONSTRUCTION.Proceedings. International Conference on Image Processing · 2025Article
- Repeatability-encouraging self-supervised learning reconstruction for quantitative MRI.Magnetic resonance in medicine · 2025Article
- Deep Learning-Based Accelerated MR Cholangiopancreatography Without Fully-Sampled Data.NMR in biomedicine · 2025Article
- MRI recovery with self-calibrated denoisers without fully-sampled data.Magma (New York, N.Y.) · 2025Article
- Ground-truth-free deep learning approach for accelerated quantitative parameter mapping with memory efficient learning.PloS one · 2025Article
- Clean Self-Supervised MRI Reconstruction from Noisy, Sub-Sampled Training Data with Robust SSDU.Bioengineering (Basel, Switzerland) · 2024Article
- Self-supervised learning for improved calibrationless radial MRI with NLINV-Net.Magnetic resonance in medicine · 2024Article
- Deep learning for accelerated and robust MRI reconstruction.Magma (New York, N.Y.) · 2024Review
- CYCLE-CONSISTENT SELF-SUPERVISED LEARNING FOR IMPROVED HIGHLY-ACCELERATED MRI RECONSTRUCTION.Proceedings. IEEE International Symposium on Biomedical Imaging · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
Abstract
In recent years, there has been attention on leveraging the statistical modeling capabilities of neural networks for reconstructing sub-sampled Magnetic Resonance Imaging (MRI) data. Most proposed methods assume the existence of a representative fully-sampled dataset and use fully-supervised training. However, for many applications, fully sampled training data is not available, and may be highly impractical to acquire. The development and understanding of self-supervised methods, which use only sub-sampled data for training, are therefore highly desirable. This work extends the Noisier2Noise framework, which was originally constructed for self-supervised denoising tasks, to variable density sub-sampled MRI data. We use the Noisier2Noise framework to analytically explain the performance of Self-Supervised Learning via Data Undersampling (SSDU), a recently proposed method that performs well in practice but until now lacked theoretical justification. Further, we propose two modifications of SSDU that arise as a consequence of the theoretical developments. Firstly, we propose partitioning the sampling set so that the subsets have the same type of distribution as the original sampling mask. Secondly, we propose a loss weighting that compensates for the sampling and partitioning densities. On the fastMRI dataset we show that these changes significantly improve SSDU's image restoration quality and robustness to the partitioning parameters.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.