scholarly journals Reference-Driven Undersampled MR Image Reconstruction Using Wavelet Sparsity-Constrained Deep Image Prior

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Di Zhao ◽  
Yanhu Huang ◽  
Feng Zhao ◽  
Binyi Qin ◽  
Jincun Zheng
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Structural Information ◽  
Reference Image ◽  
Training Procedure ◽  
Mr Image ◽  
Image Prior ◽  
Clinical Scenarios ◽  
Deep Image ◽  
Mr Image Reconstruction

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.

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

Sensors ◽  
2020 ◽  
Vol 20 (1) ◽  
pp. 308 ◽  
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.

An Efficient Light-Weight Network for Fast Reconstruction on MR Images

2021 ◽  
Vol 17 ◽  
Author(s):  
Bowen Zhen ◽  
Yingjie Zheng ◽  
Bensheng Qiu
Keyword(s):  
Feature Extraction ◽  
Image Reconstruction ◽  
Data Consistency ◽  
Training Procedure ◽  
Light Weight ◽  
Mr Images ◽  
High Quality ◽  
Mr Image ◽  
Generalization Ability ◽  
Mr Image Reconstruction

Background: In recent years, deep learning (DL) algorithms have emerged in endlessly and achieved impressive performance, which makes it possible to accelerate magnetic resonance (MR) image reconstruction with DL instead of compressed sensing (CS) methods. However, a DL-based MR image reconstruction method has always suffered from its heavy learning parameters and poor generalization ability so far. Therefore, an efficient light-weight network is still in desperate need of fast MR image reconstruction. Methods: We propose an efficient and light-weight MR reconstruction network (named RecNet) that uses a Convolutional Neural Network (CNN) to fast reconstruct high-quality MR images. Specifically, the network is composed of cascade modules, and each cascade module is further divided into feature extraction blocks and a data consistency layer. The feature extraction block can not only effectively extract the features of MR images, but also do not introduce too many parameters for the whole network. To stabilize the training procedure, the correction information of image frequency is adopted in the data consistency (DC) layer. Results: We have evaluated RecNet on a public dataset and the results show that the image quality reconstructed by RecNet is the best on the peak a signal-to-noise ratio (PSNR) and structural similarity index (SSIM) evaluation standards. In addition, the pre-trained RecNet can also reconstruct high-quality MR images on an unseen dataset. Conclusion: The results demonstrate that the RecNet has superior reconstruction ability in various metrics than comparative methods. The RecNet can quickly generate high-quality MR images in fewer parameters. Furthermore, the RecNet has an excellent generalization ability on pathological images and different sampling rates data.

Bayesian Deep Learning for Accelerated MR Image Reconstruction

2018 ◽  
pp. 64-71 ◽  
Author(s):  
Jo Schlemper ◽  
Daniel C. Castro ◽  
Wenjia Bai ◽  
Chen Qin ◽  
Ozan Oktay ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Mr Image ◽  
Mr Image Reconstruction

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

2019 ◽  
Vol 9 (9) ◽  
pp. 1516-1527 ◽  
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

scholarly journals POCS-Augmented CycleGAN for MR Image Reconstruction

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.

Sign in / Sign up

Export Citation Format

Share Document