A Simulation Pipeline to Generate Realistic Breast Images for Learning DCE-MRI Reconstruction

Huang, Zhengnan; Bae, Jonghyun; Johnson, Patricia M.; Sood, Terlika Pandit; Heacock, Laura; Fogarty, Justin; Moy, Linda; Kim, Sungheon; Knoll, Florian

doi:10.1007/978-3-030-88552-6_5

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To process the 3D+t in the regularization network, convolution operations are split into 3D spatial convolutions, followed by 1D temporal convolutions. In this setting, a variational network was trained on simulated data with radial k-space trajectories, as fully sampled dataset with both high spatial and temporal resolution was infeasible to acquire [58].…”

Section: B Canonical Mri Reconstruction With the Linear Forward Modelmentioning

confidence: 99%

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging

Hammernik¹,

Küstner²,

Huang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Physics-driven deep learning methods have emerged as a powerful tool for computational magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new limits. This article provides an overview of the recent developments in incorporating physics information into learningbased MRI reconstruction. We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these. We then focus on physics-driven deep learning approaches, covering physics-driven loss functions, plug-and-play methods, generative models, and unrolled networks. We highlight domain-specific challenges such as real-and complex-valued building blocks of neural networks, and translational applications in MRI with linear and non-linear forward models. Finally, we discuss common issues and open challenges, and draw connections to the importance of physics-driven learning when combined with other downstream tasks in the medical imaging pipeline.

show abstract

Section: B Canonical Mri Reconstruction With the Linear Forward Modelmentioning

confidence: 99%

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging

Hammernik¹,

Küstner²,

Huang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, the performance of the trained networks would degrade when the data is acquired with different scan parameters or pathological conditions. While in the case of DCE MRI, the ground-truth data are not available [20]. Alternatively, the unsupervised-learning strategy was introduced to the DL-based dynamic MRI reconstruction without involving external data in the training process.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstruction

Feng¹,

Feng²,

Wu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has appeared as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled k-space data, which only takes spatiotemporal coordinates as inputs. Specifically, the proposed INR represents the dynamic MRI images as an implicit function and encodes them into neural networks. The weights of the network are learned from sparsely-acquired (k, t)-space data itself only, without external training datasets or prior images. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared scan-specific methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 5.5 ∼ 7.1 dB in PSNR for extremely high accelerations (up to 41.6 ×). The high-quality and inner continuity of the images provided by INR has great potential to further improve the spatiotemporal resolution of dynamic MRI, without the need of any training data.

show abstract

A Simulation Pipeline to Generate Realistic Breast Images for Learning DCE-MRI Reconstruction

Cited by 2 publications

References 12 publications

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging

Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstruction

Contact Info

Product

Resources

About