RECORD
Blind Primed Supervised (BLIPS) Learning for MR Image Reconstruction
Image and Video Processing · Submitted 11 Apr 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The improvements yielded by the proposed framework suggest that the blind dictionary-based approach preserves fine image details that the supervised approach can iteratively refine, suggesting that the features learned using the two methods are complementary
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
This paper examines a combined supervised-unsupervised framework involving dictionary-based blind learning and deep supervised learning for MR image reconstruction from under-sampled k-space data. A major focus of the work is to investigate the possible synergy of learned features in traditional shallow reconstruction using adaptive sparsity-based priors and deep prior-based reconstruction. Specifically, we propose a framework that uses an unrolled network to refine a blind dictionary learning-based reconstruction. We compare the proposed method with strictly supervised deep learning-based reconstruction approaches on several datasets of varying sizes and anatomies. We also compare the proposed method to alternative approaches for combining dictionary-based methods with supervised learning in MR image reconstruction. The improvements yielded by the proposed framework suggest that the blind dictionary-based approach preserves fine image details that the supervised approach can iteratively refine, suggesting that the features learned using the two methods are complementary
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | This paper examines a combined supervised-unsupervised framework involving dictionary-based blind learning and deep supervised learning for MR image reconstruction from under-sampled k-space data. | contribution 0.83 | 0.61 | 0.04 | asserted 0.90 |
| s1 | A major focus of the work is to investigate the possible synergy of learned features in traditional shallow reconstruction using adaptive sparsity-based priors and deep prior-based reconstruction. | contribution 0.48 | 0.26 | 0.04 | hedged possibility 0.94 |
| s2 | Specifically, we propose a framework that uses an unrolled network to refine a blind dictionary learning-based reconstruction. | method 0.75 | 0.88 | 0.04 | asserted 0.99 |
| s3 | We compare the proposed method with strictly supervised deep learning-based reconstruction approaches on several datasets of varying sizes and anatomies. | method 0.87 | 0.93 | 0.03 | asserted 0.89 |
| s4 | We also compare the proposed method to alternative approaches for combining dictionary-based methods with supervised learning in MR image reconstruction. | method 0.83 | 0.90 | 0.03 | asserted 0.75 |
| s5 | The improvements yielded by the proposed framework suggest that the blind dictionary-based approach preserves fine image details that the supervised approach can iteratively refine, suggesting that the features learned using the two methods are complementary | interpretation 0.96 | 0.92 | 0.86 | hedged possibility 0.99 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
This paper examines a combined supervised-unsupervised framework involving dictionary-based blind learning and deep supervised learning for MR image reconstruction from under-sampled k-space data. A major focus of the work is to investigate the possible synergy of learned features in traditional shallow reconstruction using adaptive sparsity-based priors and deep prior-based reconstruction. Specifically, we propose a framework that uses an unrolled network to refine a blind dictionary learning-based reconstruction. We compare the proposed method with strictly supervised deep learning-based reconstruction approaches on several datasets of varying sizes and anatomies. We also compare the proposed method to alternative approaches for combining dictionary-based methods with supervised learning in MR image reconstruction. The improvements yielded by the proposed framework suggest that the blind dictionary-based approach preserves fine image details that the supervised approach can iteratively refine, suggesting that the features learned using the two methods are complementary
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 5 sentences without a confident label
Uses the method or tool of 3 papers
-
1.1 For supervised learning reconstruction, this paper uses an unrolled network algorithm similar to the state-of-the-art method MoDL [ref] , whose variants have achieved top performance in recent open data-driven competitions in MR reconstruction [ref] .
$\Sigma$-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstruction · Problem Setup and Algorithms · 0.98
-
1.1 For supervised learning reconstruction, this paper uses an unrolled network algorithm similar to the state-of-the-art method MoDL [ref] , whose variants have achieved top performance in recent open data-driven competitions in MR reconstruction [ref] .
XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge · Problem Setup and Algorithms · 0.98
-
The optimizer was Adam [ref] , with parameter $β$s = $[0.5, 0.999]$.
Adam: A Method for Stochastic Optimization · Supervised Reconstruction · 1.00
Uses data or values from 1 paper
-
The first was a randomly selected subset from the fastMRI knee dataset, while the second consisted of the entire fastMRI brain dataset [ref] .
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI · Training and Test Dataset · 0.99
Cites as background 1 paper
-
With the success of deep-learning-based methods for computer vision and natural language processing, there has also been a rise in methods that use neural networks to “regularize” (often in implicit manner) MRI reconstruction problems [ref] .
$\Sigma$-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstruction · Introduction · 0.92
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.