mlsanityData to 7 Oct 2026

NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation

arXiv 2404.04550 ↗First posted 6 Apr 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The ability to reconstruct high-quality images from undersampled MRI data is vital in improving MRI temporal resolution and reducing acquisition times. Deep learning methods have been proposed for this task, but the lack of verified methods to quantify the uncertainty in the reconstructed images hampered clinical applicability. We introduce "NPB-REC", a non-parametric fully Bayesian framework, for MRI reconstruction from undersampled data with uncertainty estimation. We use Stochastic Gradient Langevin Dynamics during training to characterize the posterior distribution of the network parameters. This enables us to both improve the quality of the reconstructed images and quantify the uncertainty in the reconstructed images. We demonstrate the efficacy of our approach on a multi-coil MRI dataset from the fastMRI challenge and compare it to the baseline End-to-End Variational Network (E2E-VarNet). Our approach outperforms the baseline in terms of reconstruction accuracy by means of PSNR and SSIM (34.55, 0.908 vs. 33.08, 0.897, p<0.01, acceleration rate R=8) and provides uncertainty measures that correlate better with the reconstruction error (Pearson correlation, R=0.94 vs. R=0.91). Additionally, our approach exhibits better generalization capabilities against anatomical distribution shifts (PSNR and SSIM of 32.38, 0.849 vs. 31.63, 0.836, p<0.01, training on brain data, inference on knee data, acceleration rate R=8). NPB-REC has the potential to facilitate the safe utilization of deep learning-based methods for MRI reconstruction from undersampled data. Code and trained models are available at urlhttps://github.com/samahkh/NPB-REC.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 6 Apr 2024.

Builds on

29 of 47 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  5. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  6. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  7. 2021Score-based diffusion models for accelerated MRIcited by 308
  8. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  9. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  10. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  11. 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 144
  12. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121
17 more
  1. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  2. 2018GANs for Medical Image Analysiscited by 81
  3. 2019A Bayesian Perspective on the Deep Image Priorcited by 52
  4. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  5. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  6. 2017MR image reconstruction using deep density priorscited by 37
  7. 2021Bayesian Uncertainty Estimation of Learned Variational MRI Reconstructioncited by 30
  8. 2021fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Datacited by 29
  9. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 28
  10. 2021Uncertainty-Guided Mutual Consistency Learning for Semi-Supervised Medical Image Segmentationcited by 22
  11. 2017Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generationcited by 18
  12. 2019i-RIM applied to the fastMRI challengecited by 16
  13. 2021Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledgecited by 11
  14. 2022Adversarial Robustness of MR Image Reconstruction under Realistic Perturbationscited by 11
  15. 2020Learning to Predict Error for MRI Reconstructioncited by 9
  16. 2021Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of Prostate Zones and Beyondcited by 9
  17. 2021NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approachcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025The challenge of uncertainty quantification of large language models in medicinecited by 14
  2. 2025Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integrationcited by 0
  3. 2026HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histologycited by 0
  4. 2026Evaluating the Safety of Deep Learning-Based Brain MRI Reconstructioncited by 0