POCS-Augmented CycleGAN for 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

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

Approximate Sparsity and Nonlocal Total Variation Based Compressive MR Image Reconstruction

Mathematical Problems in Engineering ◽

10.1155/2014/137616 ◽

2014 ◽

Vol 2014 ◽

pp. 1-13 ◽

Cited By ~ 5

Author(s):

Chengzhi Deng ◽

Shengqian Wang ◽

Wei Tian ◽

Zhaoming Wu ◽

Saifeng Hu

Keyword(s):

Image Reconstruction ◽

Total Variation ◽

Optimization Problems ◽

Reconstruction Method ◽

Mr Image ◽

Scanning Time ◽

Reconstruction Methods ◽

Nonlocal Total Variation ◽

Space Data ◽

Mr Image Reconstruction

Recent developments in compressive sensing (CS) show that it is possible to accurately reconstruct the magnetic resonance (MR) image from undersampledk-space data by solving nonsmooth convex optimization problems, which therefore significantly reduce the scanning time. In this paper, we propose a new MR image reconstruction method based on a compound regularization model associated with the nonlocal total variation (NLTV) and the wavelet approximate sparsity. Nonlocal total variation can restore periodic textures and local geometric information better than total variation. The wavelet approximate sparsity achieves more accurate sparse reconstruction than fixed waveletl0andl1norm. Furthermore, a variable splitting and augmented Lagrangian algorithm is presented to solve the proposed minimization problem. Experimental results on MR image reconstruction demonstrate that the proposed method outperforms many existing MR image reconstruction methods both in quantitative and in visual quality assessment.

Download Full-text

Median Filter Based Compressed Sensing Model with Application to MR Image Reconstruction

Mathematical Problems in Engineering ◽

10.1155/2018/8316194 ◽

2018 ◽

Vol 2018 ◽

pp. 1-9 ◽

Cited By ~ 2

Author(s):

Yunyun Yang ◽

Xuxu Qin ◽

Boying Wu

Keyword(s):

Magnetic Resonance ◽

Image Reconstruction ◽

Compressed Sensing ◽

Total Variation ◽

Median Filter ◽

Mr Images ◽

Mr Image ◽

Reconstruction Process ◽

Sensing Model ◽

Mr Image Reconstruction

Magnetic resonance imaging (MRI) has become a helpful technique and developed rapidly in clinical medicine and diagnosis. Magnetic resonance (MR) images can display more clearly soft tissue structures and are important for doctors to diagnose diseases. However, the long acquisition and transformation time of MR images may limit their application in clinical diagnosis. Compressed sensing methods have been widely used in faithfully reconstructing MR images and greatly shorten the scanning and transforming time. In this paper we present a compressed sensing model based on median filter for MR image reconstruction. By combining a total variation term, a median filter term, and a data fitting term together, we first propose a minimization problem for image reconstruction. The median filter term makes our method eliminate additional noise from the reconstruction process and obtain much clearer reconstruction results. One key point of the proposed method lies in the fact that both the total variation term and the median filter term are presented in the L1 norm formulation. We then apply the split Bregman technique for fast minimization and give an efficient algorithm. Finally, we apply our method to numbers of MR images and compare it with a related method. Reconstruction results and comparisons demonstrate the accuracy and efficiency of the proposed model.

Download Full-text

Nonuniform Variational Network: Deep Learning for Accelerated Nonuniform MR Image Reconstruction

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

10.1007/978-3-030-32248-9_7 ◽

2019 ◽

pp. 57-64

Author(s):

Jo Schlemper ◽

Seyed Sadegh Mohseni Salehi ◽

Prantik Kundu ◽

Carole Lazarus ◽

Hadrien Dyvorne ◽

...

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Mr Image ◽

Mr Image Reconstruction

Download Full-text

Novel deep learning-based noise reduction technique for prostate magnetic resonance imaging

Abdominal Radiology ◽

10.1007/s00261-021-02964-6 ◽

2021 ◽

Author(s):

Xinzeng Wang ◽

Jingfei Ma ◽

Priya Bhosale ◽

Juan J. Ibarra Rovira ◽

Aliya Qayyum ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Prostate Cancer ◽

Deep Learning ◽

Magnetic Resonance ◽

Image Quality ◽

Reconstruction Method ◽

Anatomical Landmarks ◽

Resonance Imaging ◽

Endorectal Coil ◽

Reconstruction Methods

Abstract Introduction Magnetic resonance imaging (MRI) has played an increasingly major role in the evaluation of patients with prostate cancer, although prostate MRI presents several technical challenges. Newer techniques, such as deep learning (DL), have been applied to medical imaging, leading to improvements in image quality. Our goal is to evaluate the performance of a new deep learning-based reconstruction method, “DLR” in improving image quality and mitigating artifacts, which is now commercially available as AIRTM Recon DL (GE Healthcare, Waukesha, WI). We hypothesize that applying DLR to the T2WI images of the prostate provides improved image quality and reduced artifacts. Methods This study included 31 patients with a history of prostate cancer that had a multiparametric MRI of the prostate with an endorectal coil (ERC) at 1.5 T or 3.0 T. Four series of T2-weighted images were generated in total: one set with the ERC signal turned on (ERC) and another set with the ERC signal turned off (Non-ERC). Each of these sets then reconstructed using two different reconstruction methods: conventional reconstruction (Conv) and DL Recon (DLR): ERCDLR, ERCConv, Non-ERCDLR, and Non-ERCConv. Three radiologists independently reviewed and scored the four sets of images for (i) image quality, (ii) artifacts, and (iii) visualization of anatomical landmarks and tumor. Results The Non-ERCDLR scored as the best series for (i) overall image quality (p < 0.001), (ii) reduced artifacts (p < 0.001), and (iii) visualization of anatomical landmarks and tumor. Conclusion Prostate imaging without the use of an endorectal coil could benefit from deep learning reconstruction as demonstrated with T2-weighted imaging MRI evaluations of the prostate.

Download Full-text

An Efficient MR Image Reconstruction Method for Arbitrary K-space Trajectories Without Density Compensation

2006 International Conference of the IEEE Engineering in Medicine and Biology Society ◽

10.1109/iembs.2006.4398269 ◽

2006 ◽

Author(s):

Jiayu Song ◽

Qing H. Liu

Keyword(s):

Image Reconstruction ◽

Reconstruction Method ◽

Space Trajectories ◽

Mr Image ◽

Density Compensation ◽

Image Reconstruction Method ◽

Mr Image Reconstruction

Download Full-text

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

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/8865582 ◽

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.

Download Full-text