Domain Knowledge Augmentation of Parallel MR Image Reconstruction using Deep Learning

Deep learning has shown potential in significantly improving performance for undersampled magnetic resonance (MR) image reconstruction. However, one challenge for the application of deep learning to clinical scenarios is the requirement of large, high-quality patient-based datasets for network training. In this paper, we propose a novel deep learning-based method for undersampled MR image reconstruction that does not require pre-training procedure and pre-training datasets. The proposed reference-driven method using wavelet sparsity-constrained deep image prior (RWS-DIP) is based on the DIP framework and thereby reduces the dependence on datasets. Moreover, RWS-DIP explores and introduces structure and sparsity priors into network learning to improve the efficiency of learning. By employing a high-resolution reference image as the network input, RWS-DIP incorporates structural information into network. RWS-DIP also uses the wavelet sparsity to further enrich the implicit regularization of traditional DIP by formulating the training of network parameters as a constrained optimization problem, which is solved using the alternating direction method of multipliers (ADMM) algorithm. Experiments on in vivo MR scans have demonstrated that the RWS-DIP method can reconstruct MR images more accurately and preserve features and textures from undersampled k -space measurements.

Download Full-text

Reference-Driven Compressed Sensing MR Image Reconstruction Using Deep Convolutional Neural Networks without Pre-Training

Sensors ◽

10.3390/s20010308 ◽

2020 ◽

Vol 20 (1) ◽

pp. 308 ◽

Cited By ~ 2

Author(s):

Di Zhao ◽

Feng Zhao ◽

Yongjin Gan

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Compressed Sensing ◽

Training Dataset ◽

Reconstruction Method ◽

Training Procedure ◽

Deep Convolutional Neural Networks ◽

Mr Image ◽

Space Data ◽

Mr Image Reconstruction

Deep learning has proven itself to be able to reduce the scanning time of Magnetic Resonance Imaging (MRI) and to improve the image reconstruction quality since it was introduced into Compressed Sensing MRI (CS-MRI). However, the requirement of using large, high-quality, and patient-based datasets for network training procedures is always a challenge in clinical applications. In this paper, we propose a novel deep learning based compressed sensing MR image reconstruction method that does not require any pre-training procedure or training dataset, thereby largely reducing clinician dependence on patient-based datasets. The proposed method is based on the Deep Image Prior (DIP) framework and uses a high-resolution reference MR image as the input of the convolutional neural network in order to induce the structural prior in the learning procedure. This reference-driven strategy improves the efficiency and effect of network learning. We then add the k-space data correction step to enforce the consistency of the k-space data with the measurements, which further improve the image reconstruction accuracy. Experiments on in vivo MR datasets showed that the proposed method can achieve more accurate reconstruction results from undersampled k-space data.

Download Full-text

Bayesian Deep Learning for Accelerated MR Image Reconstruction

Machine Learning for Medical Image Reconstruction - Lecture Notes in Computer Science ◽

10.1007/978-3-030-00129-2_8 ◽

2018 ◽

pp. 64-71 ◽

Cited By ~ 2

Author(s):

Jo Schlemper ◽

Daniel C. Castro ◽

Wenjia Bai ◽

Chen Qin ◽

Ozan Oktay ◽

...

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Mr Image ◽

Mr Image Reconstruction

Download Full-text

Deep Learning Within a Priori Temporal Feature Spaces for Large-Scale Dynamic MR Image Reconstruction: Application to 5-D Cardiac MR Multitasking

Lecture Notes in Computer Science - Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 ◽

10.1007/978-3-030-32245-8_55 ◽

2019 ◽

pp. 495-504 ◽

Cited By ~ 2

Author(s):

Yuhua Chen ◽

Jaime L. Shaw ◽

Yibin Xie ◽

Debiao Li ◽

Anthony G. Christodoulou

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Large Scale ◽

A Priori ◽

Mr Image ◽

Cardiac Mr ◽

Feature Spaces ◽

Dynamic Mr ◽

Temporal Feature ◽

Mr Image Reconstruction

Download Full-text

MR image reconstruction using deep learning: evaluation of network structure and loss functions

Quantitative Imaging in Medicine and Surgery ◽

10.21037/qims.2019.08.10 ◽

2019 ◽

Vol 9 (9) ◽

pp. 1516-1527 ◽

Cited By ~ 4

Author(s):

Vahid Ghodrati ◽

Jiaxin Shao ◽

Mark Bydder ◽

Ziwu Zhou ◽

Wotao Yin ◽

...

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Network Structure ◽

Loss Functions ◽

Mr Image ◽

Learning Evaluation ◽

Mr Image Reconstruction

Download Full-text

POCS-Augmented CycleGAN for MR Image Reconstruction

Applied Sciences ◽

10.3390/app12010114 ◽

2021 ◽

Vol 12 (1) ◽

pp. 114

Author(s):

Yiran Li ◽

Hanlu Yang ◽

Danfeng Xie ◽

David Dreizin ◽

Fuqing Zhou ◽

...

Keyword(s):

Deep Learning ◽

Magnetic Resonance ◽

Image Reconstruction ◽

State Of The Art ◽

Training Data ◽

Reconstruction Method ◽

Mr Image ◽

Reconstruction Process ◽

Reconstruction Methods ◽

Mr Image Reconstruction

Recent years have seen increased research interest in replacing the computationally intensive Magnetic resonance (MR) image reconstruction process with deep neural networks. We claim in this paper that the traditional image reconstruction methods and deep learning (DL) are mutually complementary and can be combined to achieve better image reconstruction quality. To test this hypothesis, a hybrid DL image reconstruction method was proposed by combining a state-of-the-art deep learning network, namely a generative adversarial network with cycle loss (CycleGAN), with a traditional data reconstruction algorithm: Projection Onto Convex Set (POCS). The output of the first iteration’s training results of the CycleGAN was updated by POCS and used as the extra training data for the second training iteration of the CycleGAN. The method was validated using sub-sampled Magnetic resonance imaging data. Compared with other state-of-the-art, DL-based methods (e.g., U-Net, GAN, and RefineGAN) and a traditional method (compressed sensing), our method showed the best reconstruction results.

Download Full-text