Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications

Zibetti, Marcelo V. W.; Knoll, Florian; Regatte, Ravinder R.

doi:10.1109/tci.2022.3176129

Cited by 13 publications

(13 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These changes usually cause a reduction in SNR and accuracy, but the OVFA can minimize this loss, achieving similar performance as a slower sequence. If time is still of concern, one can still include undersampling, particularly data-driven learned undersampling [18][19][20][21][22] and deep learning reconstructions. [51][52][53][54][55] Assuming fully sampled data are acquired, the reduction of scan time happens here because of acquiring more data per unit of time.…”

Section: Discussionmentioning

confidence: 99%

“…Compressed sensing, [15][16][17] which relies on incoherent sampling and sparse reconstruction, also reduces time by undersampling, while obtaining high-quality images from advanced nonlinear reconstruction. Recent advancements with data-driven approaches for learned reconstruction and sampling pattern have shown that k-space sampling can be optimized for specific anatomy and reconstruction methods [18][19][20][21][22] for improved quality in accelerated MRI. All these improvements can be combined, allowing 3D MRI with short scan times.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing variable flip angles in magnetization‐prepared gradient‐echo sequences for efficient 3D‐T1ρ mapping

Zibetti

Moura

Keerthivasan³

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose To optimize the choice of the flip angles of magnetization‐prepared gradient‐echo sequences for improved accuracy, precision, and speed of 3D‐T1ρ mapping. Methods We propose a new optimization approach for finding variable flip‐angle values that improve magnetization‐prepared gradient‐echo sequences used for 3D‐T1ρ mapping. This new approach can improve the accuracy and SNR, while reducing filtering effects. We demonstrate the concept in the three different versions of the magnetization‐prepared gradient‐echo sequences that are typically used for 3D‐T1ρ mapping and evaluate their performance in model agarose phantoms (n = 4) and healthy volunteers (n = 5) for knee joint imaging. We also tested the optimization with sequence parameters targeting faster acquisitions. Results Our results show that optimized variable flip angle can improve the accuracy and the precision of the sequences, seen as a reduction of the mean of normalized absolute difference from about 5%–6% to 3%–4% in model phantoms and from 15%–16% to 11%–13% in the knee joint, and improving SNR from about 12–28 to 22–32 in agarose phantoms and about 7–14 to 13–17 in healthy volunteers. The optimization can also compensate for the loss in quality caused by making the sequence faster. This results in sequence configurations that acquire more data per unit of time with SNR and mean of normalized absolute difference measurements close to its slower versions. Conclusion The optimization of the variable flip angle can be used to increase accuracy and precision, and to improve the speed of the typical imaging sequences used for quantitative 3D‐T1ρ mapping of the knee joint.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimizing variable flip angles in magnetization‐prepared gradient‐echo sequences for efficient 3D‐T1ρ mapping

Zibetti

Moura

Keerthivasan³

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…Joint learning of sampling pattern (SP) and DL reconstruction was proposed in the literature 64 . The results showed that the quality of spatiotemporal undersampling could be improved by 20% or more if learned together with the DL reconstruction parameters.…”

Section: Emerging Methods For Quantitative Mri For Cartilagementioning

confidence: 99%

“…In Fig. 4, some results of the literature 64 illustrate how the learned SP may differ depending on the choice of DL architecture for reconstruction. Improvements can be easily seen in the joint learning approach when compared against the DL reconstruction with fixed SP, such as variable density with Poisson disc (VD + PD).…”

Section: Emerging Methods For Quantitative Mri For Cartilagementioning

confidence: 99%

See 1 more Smart Citation

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Zibetti

Menon

Moura

et al. 2023

Magnetic Resonance Imaging

Self Cite

View full text Add to dashboard Cite

Osteoarthritis (OA) is a widely occurring degenerative joint disease that is severely debilitating and causes significant socioeconomic burdens to society. Magnetic resonance imaging (MRI) is the preferred imaging modality for the morphological evaluation of cartilage due to its excellent soft tissue contrast and high spatial resolution. However, its utilization typically involves subjective qualitative assessment of cartilage. Compositional MRI, which refers to the quantitative characterization of cartilage using a variety of MRI methods, can provide important information regarding underlying compositional and ultrastructural changes that occur during early OA. Cartilage compositional MRI could serve as early imaging biomarkers for the objective evaluation of cartilage and help drive diagnostics, disease characterization, and response to novel therapies. This review will summarize current and ongoing state‐of‐the‐art cartilage compositional MRI techniques and highlight emerging methods for cartilage compositional MRI including MR fingerprinting, compressed sensing, multiexponential relaxometry, improved and robust radio‐frequency pulse sequences, and deep learning‐based acquisition, reconstruction, and segmentation. The review will also briefly discuss the current challenges and future directions for adopting these emerging cartilage compositional MRI techniques for use in clinical practice and translational OA research studies. Evidence Level 2 Technical Efficacy Stage 2.

show abstract

Knowledge‐driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un‐supervised learning

Wang,

Wu,

Jia

et al. 2024

Magnetic Resonance in Med

View full text Add to dashboard Cite

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics‐based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data‐driven approaches. Our review will introduce the significant challenges faced by such knowledge‐driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi‐supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.

show abstract

Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications

Cited by 13 publications

References 66 publications

Optimizing variable flip angles in magnetization‐prepared gradient‐echo sequences for efficient 3D‐T1ρ mapping

Optimizing variable flip angles in magnetization‐prepared gradient‐echo sequences for efficient 3D‐T1ρ mapping

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Knowledge‐driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un‐supervised learning

Contact Info

Product

Resources

About