Model-Based Deep Learning for Reconstruction of Joint k-q Under-sampled High Resolution Diffusion MRI

Mani, Merry; Aggarwal, Hemant Kumar; Ghosh, Sanjay; Jacob, Mathews

doi:10.1109/isbi45749.2020.9098593

Cited by 13 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To accelerate such acquisitions, joint k-q undersampled methods were proposed to provide high acceleration rates. 16,17,[27][28][29] 2.2 | Review of joint reconstruction for k-q accelerated dMRI…”

Section: The Multi-shot Epi Acquisition Modelmentioning

confidence: 99%

“…The above reconstruction can be solved in an iterative fashion by alternating between data consistency enforcement and qspace signal projection using the neural networks as proposed in. 29 Here, we derive a traditional iterative model-based reconstruction incorporating the projection into the reconstruction process. Conveniently, the DAE encoder-decoder mapping can be incorporated into a traditional model-based reconstruction setting with the knowledge of the weights learned from each layer of the DAE after training.…”

Section: Joint Reconstruction Using Qspace Priormentioning

confidence: 99%

See 1 more Smart Citation

qModeL: A plug‐and‐play model‐based reconstruction for highly accelerated multi‐shot diffusion MRI using learned priors

Mani

Magnotta

Jacob

2021

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose: To introduce a joint reconstruction method for highly undersampled multishot diffusion weighted (msDW) scans. Methods: Multi-shot EPI methods enable higher spatial resolution for diffusion MRI, but at the expense of long scan-time. Highly accelerated msDW scans are needed to enable their utilization in advanced microstructure studies, which require high q-space coverage. Previously, joint k-q undersampling methods coupled with compressed sensing were shown to enable very high acceleration factors. However, the reconstruction of this data using sparsity priors is challenging and is not suited for multi-shell data. We propose a new reconstruction that recovers images from the combined k-q data jointly.The proposed qModeL reconstruction brings together the advantages of model-based iterative reconstruction and machine learning, extending the idea of plug-and-play algorithms. Specifically, qModeL works by prelearning the signal manifold corresponding to the diffusion measurement space using deep learning. The prelearned manifold prior is incorporated into a model-based reconstruction to provide a voxel-wise regularization along the q-dimension during the joint recovery. Notably, the learning does not require in vivo training data and is derived exclusively from biophysical modeling.Additionally, a plug-and-play total variation denoising provides regularization along the spatial dimension. The proposed framework is tested on k-q undersampled singleshell and multi-shell msDW acquisition at various acceleration factors. Results: The qModeL joint reconstruction is shown to recover DWIs from 8-fold accelerated msDW acquisitions with error less than 5% for both single-shell and multi-shell data. Advanced microstructural analysis performed using the undersampled reconstruction also report reasonable accuracy. Conclusion: qModeL enables the joint recovery of highly accelerated multi-shot dMRI utilizing learning-based priors. The bio-physically driven approach enables the use of accelerated multi-shot imaging for multi-shell sampling and advanced microstructure studies. K E Y W O R D Sautoencoder neural network, deep learning, k-q acceleration, machine learning, multi-shot diffusion, multi-shell, NODDI SUPPORTING INFORMATIONAdditional Supporting Information may be found online in the Supporting Information section.How to cite this article: Mani M, Magnotta VA, Jacob M, et al. qModeL: A plug-and-play modelbased reconstruction for highly accelerated multi-shot diffusion MRI using learned priors.

show abstract

Section: The Multi-shot Epi Acquisition Modelmentioning

confidence: 99%

Section: Joint Reconstruction Using Qspace Priormentioning

confidence: 99%

qModeL: A plug‐and‐play model‐based reconstruction for highly accelerated multi‐shot diffusion MRI using learned priors

Mani

Magnotta

Jacob

2021

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work, we demonstrate the utility of the previously proposed qModeL framework 16,17 for the recovery of dMRI data acquired with both MB and in-plane acceleration. The qModeL framework synergistically combines the power of joint reconstruction and DL in the setting of an iterative model-based reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Multi‐band‐ and in‐plane‐accelerated diffusion MRI enabled by model‐based deep learning in q‐space and its extension to learning in the spherical harmonic domain

Mani

Yang²,

Bathla

et al. 2021

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

To propose a new method for the recovery of combined in-plane-and multi-band (MB)-accelerated diffusion MRI data. Methods:Combining MB acceleration with in-plane acceleration is crucial to improve the time efficiency of high (angular and spatial) resolution diffusion scans. However, as the MB factor and in-plane acceleration increase, the reconstruction becomes challenging due to the heavy aliasing. The new reconstruction utilizes an additional q-space prior to constrain the recovery, which is derived from the previously proposed qModeL framework. Specifically, the qModeL prior provides a pre-learned representation of the diffusion signal space to which the measured data belongs. We show that the pre-learned q-space prior along with a model-based iterative reconstruction that accommodate multi-band unaliasing, can efficiently reconstruct the in-plane-and MB-accelerated data. The power of joint reconstruction is maximally utilized by using an incoherent under-sampling pattern in the k-q domain. We tested the proposed method on single-and multi-shell data, with high/low angular resolution, high/low spatial resolution, healthy/abnormal tissues, and 3T/7T field strengths. Furthermore, the learning is extended to the spherical harmonic basis, to provide a rotational invariant learning framework. Results:The qModeL joint reconstruction is shown to simultaneously unalias and jointly recover DWIs with reasonable accuracy in all the cases studied. The reconstruction error from 18-fold accelerated multi-shell datasets was <3%. The microstructural maps derived from the accelerated acquisitions also exhibit reasonable accuracy for both healthy and abnormal tissues. The deep learning (DL)-enabled reconstructions are comparable to those derived using traditional methods.

show abstract

“…Magnetic Resonance Imaging (MRI) is an indispensable technique in many clinical scenarios, which provides visual images for human issue [7,17,20,37,39]. However, MRI suffers from its comparative long data acquisition times which imposes significant distress on patients and makes this imaging modality less accessible [17,28,30,34,35].…”

Section: Introductionmentioning

confidence: 99%

MRI Measurement Matrix Learning via Correlation Reweighting

Zhang

Chen

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

In Compressive Sensing MRI (CS-MRI), measurement matrix learning has been developed as a promising method for measurement matrix designing. Research on MRI measurement task suggests that Relative 2-Norm Error (RLNE) of measurement images is imbalanced. However, current learning-based investigations suffer from the lack of probing imbalanced characteristic on measurement matrix learning. In this paper, we propose a novel Measurement Matrix Learning via Correlation Reweighting (MML-CR) approach for exploring and solving this problem by optimizing reweighted model. Specifically, we introduce a reweighting expected minimization model to obtain an essential measurement matrix in k-space. Besides, we propose an example correlation regularizer to prevent trivial solution for learning weights. Furthermore, we present an alternating solution and perform convergence analysis for the optimization. We also demonstrate quantitative and qualitative experimental results which show that our algorithm outperforms several state-of-art measurements methods. Compared with conventional methods, MML-CR achieves better performance on universal task. CCS CONCEPTS • Computing methodologies → Reconstruction.

show abstract

Model-Based Deep Learning for Reconstruction of Joint k-q Under-sampled High Resolution Diffusion MRI

Cited by 13 publications

References 13 publications

qModeL: A plug‐and‐play model‐based reconstruction for highly accelerated multi‐shot diffusion MRI using learned priors

qModeL: A plug‐and‐play model‐based reconstruction for highly accelerated multi‐shot diffusion MRI using learned priors

Multi‐band‐ and in‐plane‐accelerated diffusion MRI enabled by model‐based deep learning in q‐space and its extension to learning in the spherical harmonic domain

MRI Measurement Matrix Learning via Correlation Reweighting

Contact Info

Product

Resources

About