Model-based super-resolution reconstruction with joint motion estimation for improved quantitative MRI parameter mapping

Beirinckx, Quinten; Jeurissen, Ben; Nicastro, Michele; Poot, Dirk H. J.; Verhoye, Marleen; Dekker, Arnold J. den; Sijbers, Jan

doi:10.1016/j.compmedimag.2022.102071

Cited by 10 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of SRR on the heart [23][24][25][26][27][28][29][30][31] has so far only been shown for qualitative imaging. For T1 Mapping, SRR taking into account different motion states of the individual LR stacks has so far only been applied on the brain 20,32,33 .…”

Section: Introductionmentioning

confidence: 99%

3D model-based super-resolution motion-corrected cardiac T1 mapping

Hufnagel¹,

Metzner²,

Kerkering³

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: To provide 3D high-resolution cardiac T1 maps using model-based super-resolution reconstruction (SRR). Approach: Due to signal-to-noise ratio (SNR) limitations and the motion of the heart during imaging, often 2D T1 maps with only low through-plane resolution (i.e. slice thickness of 6 to 8 mm) can be obtained. Here, a model-based SRR approach is presented, which combines multiple stacks of 2D acquisitions with 6 to 8 mm slice thickness and generates 3D high-resolution T1 maps with a slice thickness of 1.5 to 2 mm. Every stack was acquired in a different breath hold (BH) and any misalignment between BH was corrected retrospectively. The novelty of the proposed approach is the BH correction and the application of model-based SRR on cardiac T1 Mapping. The proposed approach was evaluated in numerical simulations and phantom experiments and demonstrated in four healthy subjects. Main results: Alignment of BH states was essential for SRR even in healthy volunteers. In simulations, respiratory motion could be estimated with an RMS error of 0.18 ± 0.28 mm. SRR improved the visualization of small structures. High accuracy and precision (average standard deviation of 69.62 ms) of the T1 values was ensured by SRR while the detectability of small structures increased by 40%. Significance: The proposed SRR approach provided T1 maps with high in-plane and high through-plane resolution (1.3×1.3×1.5 to 2 mm³). The approach led to improvements in the visualization of small structures and precise T1 values.

show abstract

Section: Introductionmentioning

confidence: 99%

3D model-based super-resolution motion-corrected cardiac T1 mapping

Hufnagel¹,

Metzner²,

Kerkering³

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Super-resolution methods aim to estimate an unknown HR MRI from one or more acquired low-resolution (LR) MRIs. Model-based methods assume an explicit imaging model of the MRI acquisition and seek a numerical solution of the ill-posed inverse problem by introducing regularization terms to constrain the solution space [6,7,8,9]. These model-based SR methods, however, require multiple multi-slice LR images to reconstruct one HR MRI.…”

Section: Introductionmentioning

confidence: 99%

Perceptual super-resolution in multiple sclerosis MRI

Giraldo,

Khan,

Pineda

et al. 2024

Preprint

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is crucial for diagnosing and monitoring of multiple sclerosis (MS) as it is used to assess lesions in the brain and spinal cord. However, in real-world clinical settings, MRI scans are often acquired with thick slices, limiting their utility for automated quantitative analyses. This work presents a single-image super-resolution (SR) reconstruction framework that leverages SR convolutional neural networks (CNN) to enhance the through-plane resolution of structural MRI in people with MS (PwMS). Our strategy involves the supervised fine-tuning of CNN architectures, guided by a content loss function that promotes perceptual quality, as well as reconstruction accuracy, to recover high-level image features. Extensive evaluation with MRI data of PwMS shows that our SR strategy leads to more accurate MRI reconstructions than competing methods. Furthermore, it improves lesion segmentation on low-resolution MRI, approaching the performance achievable with high-resolution images. Results demonstrate the potential of our SR framework to facilitate the use of low-resolution retrospective MRI from real-world clinical settings to investigate quantitative image-based biomarkers of MS.

show abstract

“…Examples are relaxation times estimation with Markov Random Fields, 5 coherent region smoothness, 6,7 and total variation priors. 8,9 Other Bayesian methods address, for instance, intravoxel incoherent voxel modeling, 10,11 field map reconstruction, 12 myelin water fraction estimation, 13 and applications in dynamic contrast-enhanced-MRI. [14][15][16] Other approaches address MRI signal denoising before the tissue parameter reconstruction, for example, with Marchenko-Pastur Principal Component Analysis 17 or Beltrami Denoising.…”

Section: Introductionmentioning

confidence: 99%

“…A common approach is implementing a Bayesian framework to denoise the parameter reconstruction with a spatial prior distribution. Examples are relaxation times estimation with Markov Random Fields, 5 coherent region smoothness, 6,7 and total variation priors 8,9 . Other Bayesian methods address, for instance, intravoxel incoherent voxel modeling, 10,11 field map reconstruction, 12 myelin water fraction estimation, 13 and applications in dynamic contrast‐enhanced‐MRI 14–16 .…”

Section: Introductionmentioning

confidence: 99%

Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors

Hellström

Löfstedt

Garpebring

2023

Magnetic Resonance in Med

View full text Add to dashboard Cite

PurposeTo mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors.MethodsWe extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image‐generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low‐level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application‐specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi‐echo T2 mapping, and apparent diffusion coefficient mapping.ResultsWe found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise‐reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior.ConclusionDIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time‐consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.

show abstract

Model-based super-resolution reconstruction with joint motion estimation for improved quantitative MRI parameter mapping

Cited by 10 publications

References 53 publications

3D model-based super-resolution motion-corrected cardiac T1 mapping

3D model-based super-resolution motion-corrected cardiac T1 mapping

Perceptual super-resolution in multiple sclerosis MRI

Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors

Contact Info

Product

Resources

About