scholarly journals A review on deep learning MRI reconstruction without fully sampled k-space

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Gushan Zeng ◽  
Yi Guo ◽  
Jiaying Zhan ◽  
Zi Wang ◽  
Zongying Lai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Parallel Imaging ◽  
Prior Information ◽  
Clinical Medicine ◽  
Ground Truth ◽  
Acquisition Time ◽  
Sampled Data ◽  
Mri Reconstruction ◽  
Magnetic Resonance Imaging Mri ◽  
Space Data

Abstract Background Magnetic resonance imaging (MRI) is an effective auxiliary diagnostic method in clinical medicine, but it has always suffered from the problem of long acquisition time. Compressed sensing and parallel imaging are two common techniques to accelerate MRI reconstruction. Recently, deep learning provides a new direction for MRI, while most of them require a large number of data pairs for training. However, there are many scenarios where fully sampled k-space data cannot be obtained, which will seriously hinder the application of supervised learning. Therefore, deep learning without fully sampled data is indispensable. Main text In this review, we first introduce the forward model of MRI as a classic inverse problem, and briefly discuss the connection of traditional iterative methods to deep learning. Next, we will explain how to train reconstruction network without fully sampled data from the perspective of obtaining prior information. Conclusion Although the reviewed methods are used for MRI reconstruction, they can also be extended to other areas where ground-truth is not available. Furthermore, we may anticipate that the combination of traditional methods and deep learning will produce better reconstruction results.

scholarly journals Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Data

2020 ◽  
Author(s):  
Burhaneddin Yaman ◽  
Seyed Amir Hossein Hosseini ◽  
Steen Moeller ◽  
Jutta Ellermann ◽  
Kamil Ugurbil ◽  
...  
Keyword(s):  
Deep Learning ◽  
Sampled Data ◽  
Mri Reconstruction

scholarly journals GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction

2020 ◽  
Author(s):  
Anuroop Sriram ◽  
Jure Zbontar ◽  
Tullie Murrell ◽  
C. Lawrence Zitnick ◽  
Aaron Defazio ◽  
...  
Keyword(s):  
Deep Learning ◽  
Parallel Imaging ◽  
Mri Reconstruction

scholarly journals The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

Cancers ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 36
Author(s):  
Ilyass Moummad ◽  
Cyril Jaudet ◽  
Alexis Lechervy ◽  
Samuel Valable ◽  
Charlotte Raboutet ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Metastases ◽  
Pearson Correlation ◽  
Texture Features ◽  
Acquisition Time ◽  
Brain Images ◽  
Fast Mri ◽  
Long Time ◽  
Magnetic Resonance Imaging Mri ◽  
The Impact

Background: Magnetic resonance imaging (MRI) is predominant in the therapeutic management of cancer patients, unfortunately, patients have to wait a long time to get an appointment for examination. Therefore, new MRI devices include deep-learning (DL) solutions to save acquisition time. However, the impact of these algorithms on intensity and texture parameters has been poorly studied. The aim of this study was to evaluate the impact of resampling and denoising DL models on radiomics. Methods: Resampling and denoising DL model was developed on 14,243 T1 brain images from 1.5T-MRI. Radiomics were extracted from 40 brain metastases from 11 patients (2049 images). A total of 104 texture features of DL images were compared to original images with paired t-test, Pearson correlation and concordance-correlation-coefficient (CCC). Results: When two times shorter image acquisition shows strong disparities with the originals concerning the radiomics, with significant differences and loss of correlation of 79.81% and 48.08%, respectively. Interestingly, DL models restore textures with 46.15% of unstable parameters and 25.96% of low CCC and without difference for the first-order intensity parameters. Conclusions: Resampling and denoising DL models reconstruct low resolution and noised MRI images acquired quickly into high quality images. While fast MRI acquisition loses most of the radiomic features, DL models restore these parameters.

scholarly journals Improving Non-Cartesian MRI Reconstruction through Discontinuity Subtraction

2006 ◽  
Vol 2006 ◽  
pp. 1-9 ◽  
Author(s):  
Jiayu Song ◽  
Qing Huo Liu
Keyword(s):  
Reconstruction Method ◽  
Reconstruction Methods ◽  
Spread Function ◽  
Data Fidelity ◽  
Mri Reconstruction ◽  
Magnetic Resonance Imaging Mri ◽  
Space Data ◽  
2D And 3D ◽  
Undersampled Data

Non-Cartesian sampling is widely used for fast magnetic resonance imaging (MRI). Accurate and fast image reconstruction from non-Cartesiank-space data becomes a challenge and gains a lot of attention. Images provided by conventional direct reconstruction methods usually bear ringing, streaking, and other leakage artifacts caused by discontinuous structures. In this paper, we tackle these problems by analyzing the principal point spread function (PSF) of non-Cartesian reconstruction and propose a leakage reduction reconstruction scheme based on discontinuity subtraction. Data fidelity ink-space is enforced during each iteration. Multidimensional nonuniform fast Fourier transform (NUFFT) algorithms are utilized to simulate thek-space samples as well as to reconstruct images. The proposed method is compared to the direct reconstruction method on computer-simulated phantoms and physical scans. Non-Cartesian sampling trajectories including 2D spiral, 2D and 3D radial trajectories are studied. The proposed method is found useful on reducing artifacts due to high image discontinuities. It also improves the quality of images reconstructed from undersampled data.

scholarly journals MRI Reconstruction with Interpretable Pixel-Wise Operations Using Reinforcement Learning

2020 ◽  
Vol 34 (01) ◽  
pp. 792-799 ◽  
Author(s):  
Wentian Li ◽  
Xidong Feng ◽  
Haotian An ◽  
Xiang Yao Ng ◽  
Yu-Jin Zhang
Keyword(s):  
Reinforcement Learning ◽  
Data Acquisition ◽  
Acquisition Time ◽  
Reconstruction Process ◽  
Anatomical Structures ◽  
Markov Decision ◽  
Data Acquisition Time ◽  
Mri Reconstruction ◽  
Space Data ◽  
Medical Analysis

Compressed sensing magnetic resonance imaging (CS-MRI) is a technique aimed at accelerating the data acquisition of MRI. While down-sampling in k-space proportionally reduces the data acquisition time, it results in images corrupted by aliasing artifacts and blur. To reconstruct images from the down-sampled k-space, recent deep-learning based methods have shown better performance compared with classical optimization-based CS-MRI methods. However, they usually use deep neural networks as a black-box, which directly maps the corrupted images to the target images from fully-sampled k-space data. This lack of transparency may impede practical usage of such methods. In this work, we propose a deep reinforcement learning based method to reconstruct the corrupted images with meaningful pixel-wise operations (e.g. edge enhancing filters), so that the reconstruction process is transparent to users. Specifically, MRI reconstruction is formulated as Markov Decision Process with discrete actions and continuous action parameters. We conduct experiments on MICCAI dataset of brain tissues and fastMRI dataset of knee images. Our proposed method performs favorably against previous approaches. Our trained model learns to select pixel-wise operations that correspond to the anatomical structures in the MR images. This makes the reconstruction process more interpretable, which would be helpful for further medical analysis.

scholarly journals Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

2020 ◽  
Vol 10 (5) ◽  
pp. 1816 ◽  
Author(s):  
Zaccharie Ramzi ◽  
Philippe Ciuciu ◽  
Jean-Luc Starck
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Resonance Imaging ◽  
Mr Image ◽  
Space Network ◽  
Mri Reconstruction ◽  
Public Dataset ◽  
Magnetic Resonance Imaging Mri ◽  
Public Datasets ◽  
Space Data

Deep learning is starting to offer promising results for reconstruction in Magnetic Resonance Imaging (MRI). A lot of networks are being developed, but the comparisons remain hard because the frameworks used are not the same among studies, the networks are not properly re-trained, and the datasets used are not the same among comparisons. The recent release of a public dataset, fastMRI, consisting of raw k-space data, encouraged us to write a consistent benchmark of several deep neural networks for MR image reconstruction. This paper shows the results obtained for this benchmark, allowing to compare the networks, and links the open source implementation of all these networks in Keras. The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.

scholarly journals Post mortem validation of DSI compressed sensing with optical imaging

2021 ◽  
Author(s):  
Robert Jones ◽  
Chiara Maffei ◽  
Jean Augustinack ◽  
Bruce Fischl ◽  
Hui Wang ◽  
...  
Keyword(s):  
Compressed Sensing ◽  
Ex Vivo ◽  
Ground Truth ◽  
Acceleration Factor ◽  
Training Data ◽  
Acquisition Time ◽  
Human Brain Tissue ◽  
Diffusion Spectrum Imaging ◽  
Reconstruction Methods ◽  
Space Data

AbstractCompressed sensing (CS) has been used to enhance the feasibility of diffusion spectrum imaging (DSI) by reducing the required acquisition time. CS applied to DSI (CS-DSI) attempts to reconstruct diffusion probability density functions (PDFs) from significantly undersampled q-space data. Dictionary-based CS-DSI using L2-regularized algorithms is an intriguing approach that has demonstrated high fidelity reconstructions, fast computation times and inter-subject generalizability when tested on in vivo data. CS-DSI reconstruction fidelity is typically evaluated using the fully sampled data as ground truth. However, it is difficult to gauge how great an error with respect to the fully sampled PDF we can tolerate, without knowing whether that error also translates to substantial loss of accuracy with respect to the true fiber orientations. Here, we obtain direct measurements of axonal orientations in ex vivo human brain tissue at microscopic resolution with polarization-sensitive optical coherence tomography (PSOCT). We employ dictionary-based CS reconstruction methods to DSI data from the same samples, acquired at high max b-value (40000 s/mm2) and with high spatial resolution. We compare the diffusion orientation estimates from both CS and fully sampled DSI to the ground-truth orientations from PSOCT. This allows us to investigate the conditions under which CS reconstruction preserves the accuracy of diffusion orientation estimates with respect to PSOCT. We find that, for a CS acceleration factor of R=3, CS-DSI preserves the accuracy of the fully sampled DSI data. That acceleration is sufficient to make the acquisition time of DSI comparable to that of state-of-the-art single- or multi-shell acquisitions. We also show that, as the acceleration factor increases further, different CS reconstruction methods degrade in different ways. Finally, we find that the signal-to-noise (SNR) of the training data used to construct the dictionary can have an impact on the accuracy of the CS-DSI, but that there is substantial robustness to loss of SNR in the test data.

scholarly journals Deep learning-based thin-section MRI reconstruction improves tumour detection and delineation in pre- and post-treatment pituitary adenoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Da Hyun Lee ◽  
Ji Eun Park ◽  
Yeo Kyung Nam ◽  
Joonsung Lee ◽  
Seonok Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pituitary Adenoma ◽  
Thin Section ◽  
Signal To Noise Ratio ◽  
Imaging Protocol ◽  
Normal Pituitary Gland ◽  
Significant Difference ◽  
Mri Reconstruction ◽  
Magnetic Resonance Imaging Mri ◽  
Higher Sensitivity

AbstractEven a tiny functioning pituitary adenoma could cause symptoms; hence, accurate diagnosis and treatment are crucial for management. However, it is difficult to diagnose a small pituitary adenoma using conventional MR sequence. Deep learning-based reconstruction (DLR) using magnetic resonance imaging (MRI) enables high-resolution thin-section imaging with noise reduction. In the present single-institution retrospective study of 201 patients, conducted between August 2019 and October 2020, we compared the performance of 1 mm DLR MRI with that of 3 mm routine MRI, using a combined imaging protocol to detect and delineate pituitary adenoma. Four readers assessed the adenomas in a pairwise fashion, and diagnostic performance and image preferences were compared between inexperienced and experienced readers. The signal-to-noise ratio (SNR) was quantitatively assessed. New detection of adenoma, achieved using 1 mm DLR MRI, was not visualised using 3 mm routine MRI (overall: 6.5% [13/201]). There was no significant difference depending on the experience of the readers in new detections. Readers preferred 1 mm DLR MRI over 3 mm routine MRI (overall superiority 56%) to delineate normal pituitary stalk and gland, with inexperienced readers more preferred 1 mm DLR MRI than experienced readers. The SNR of 1 mm DLR MRI was 1.25-fold higher than that of the 3 mm routine MRI. In conclusion, the 1 mm DLR MRI achieved higher sensitivity in the detection of pituitary adenoma and provided better delineation of normal pituitary gland than 3 mm routine MRI.

scholarly journals Inter-Vendor Performance of Deep Learning in Segmenting Acute Ischemic Lesions on Diffusion-Weighted Imaging: A Multicenter Study

2020 ◽  
Author(s):  
Deniz Alis ◽  
Mert Yergin ◽  
Ceren Alis ◽  
Cagdas Topel ◽  
Ozan Asmakutlu ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Diffusion Weighted Imaging ◽  
Ground Truth ◽  
Resonance Imaging ◽  
Validation Data ◽  
Clinical Applicability ◽  
Diffusion Weighted ◽  
Test Sets ◽  
Magnetic Resonance Imaging Mri

Abstract There is little evidence on the applicability of deep learning (DL) in segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n=2986) and B (n=3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets and six neuroradiologist created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B and also fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist’s performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.

scholarly journals Which GAN? A comparative study of generative adversarial network-based fast MRI reconstruction

2021 ◽  
Vol 379 (2200) ◽  
Author(s):  
Jun Lv ◽  
Jin Zhu ◽  
Guang Yang
Keyword(s):  
Comparative Study ◽  
Superior Performance ◽  
Perceptual Quality ◽  
Generative Adversarial Network ◽  
Fast Mri ◽  
Tomographic Image Reconstruction ◽  
Adversarial Network ◽  
Mri Reconstruction ◽  
Magnetic Resonance Imaging Mri ◽  
Space Data

Fast magnetic resonance imaging (MRI) is crucial for clinical applications that can alleviate motion artefacts and increase patient throughput. K -space undersampling is an obvious approach to accelerate MR acquisition. However, undersampling of k -space data can result in blurring and aliasing artefacts for the reconstructed images. Recently, several studies have been proposed to use deep learning-based data-driven models for MRI reconstruction and have obtained promising results. However, the comparison of these methods remains limited because the models have not been trained on the same datasets and the validation strategies may be different. The purpose of this work is to conduct a comparative study to investigate the generative adversarial network (GAN)-based models for MRI reconstruction. We reimplemented and benchmarked four widely used GAN-based architectures including DAGAN, ReconGAN, RefineGAN and KIGAN. These four frameworks were trained and tested on brain, knee and liver MRI images using twofold, fourfold and sixfold accelerations, respectively, with a random undersampling mask. Both quantitative evaluations and qualitative visualization have shown that the RefineGAN method has achieved superior performance in reconstruction with better accuracy and perceptual quality compared to other GAN-based methods. This article is part of the theme issue ‘Synergistic tomographic image reconstruction: part 1’.

Sign in / Sign up

Export Citation Format

Share Document