MRI Image Reconstruction Research Articles

Joint [Formula: see text] and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning.

We present a model-based image reconstruction approach based on unrolled neural networks which corrects for image distortion and noise in low-field ( B0 ∼ 50 mT) MRI. Utilising knowledge about the underlying physics, a novel network architecture (SH-Net) is introduced which involves the estimation of spherical harmonic coefficients to guarantee a spatially smooth field map estimate. The SH-Net is integrated in an end-to-end trainable model which jointly estimates the B0-field map as well as the image. Experiments were conducted on retrospectively simulated low-field data of human knees. We compare our model to different model-based approaches at distinct noise levels and various B0-field distributions. Our results show that our physics-informed neural network approach outperforms the purely model-based methods by improving the PSNR up to 11.7% and the RMSE up to 86.3%. Our end-to-end trained model-based approach outperforms existing methods in reconstructing image and B0-field maps in the low-field regime. low-field MRI is becoming increasingly more popular as it enables access to MR in challenging situations such as intensive care units or resource poor areas. Our method allows for fast and accurate image reconstruction in such low-field imaging with B0-inhomogeneity compensation under a wide range of various environmental conditions.

The role of deep learning algorithms in enhancing MRI image reconstruction quality

The role of deep learning algorithms in enhancing MRI image reconstruction quality

One-Step Image Reconstruction for Cine MRI with a Quadratic Constraint

Motivation: In cine MRI, the measurements within each timeframe alone are too noisy for image reconstruction. Some information must be ‘borrowed’ from other time frames and the reconstruction algorithm is a slow iterative procedure. Goals: We set up a constrained objective function, which uses the measurements at other time frames to regularize the image reconstruction. We derive a non-iterative algorithm to minimize this objective function. Approach: The derivation of the algorithm is based on the calculus of variations. The resultant algorithm is in the form of filtered backprojection. Results: The feasibility of the proposed algorithm is demonstrated with a clinical patient brain study. Impact: Non-iterative reconstruction that minimizes a constrained objective function significantly increases the throughput in healthcare institutions. This may translate to reduced healthcare costs. The new reconstruction formula has a closed form that gives an explicit expression of how to incorporate the reference image in dynamic reconstruction.

Comparative Analysis of MRI Image Reconstruction Techniques for Improved Diagnosis

This paper presents a comparative analysis of MRI image reconstruction techniques aimed at enhancing diagnostic accuracy. The study investigates various reconstruction methods to improve image quality and aid in precise medical diagnosis. Through a systematic evaluation, the effectiveness of each technique is assessed, considering factors such as computational efficiency, artifact reduction, and diagnostic utility. The results highlight the strengths and limitations of different approaches, providing valuable insights for medical imaging practitioners and researchers. Ultimately, this research contributes to advancing MRI technology and facilitating more accurate and efficient diagnosis.

Advanced deep learning-based image reconstruction in lumbar spine MRI at 0.55 T – Effects on image quality and acquisition time in comparison to conventional deep learning-based reconstruction

ObjectivesTo evaluate an optimized deep leaning-based image post-processing technique in lumbar spine MRI at 0.55 T in terms of image quality and image acquisition time. Materials and methodsLumbar spine imaging was conducted on 18 patients using a 0.55 T MRI scanner, employing conventional (CDLR) and advanced (ADLR) deep learning-based post-processing techniques. Two musculoskeletal radiologists visually evaluated the images using a 5-point Likert scale to assess image quality and resolution. Quantitative assessment in terms of signal intensities (SI) and contrast ratios was performed by region of interest measurements in different body-tissues (vertebral bone, intervertebral disc, spinal cord, cerebrospinal fluid and autochthonous back muscles) to investigate differences between CDLR and ADLR sequences. ResultsThe images processed with the advanced technique (ADLR) were rated superior to the conventional technique (CDLR) in terms of signal/contrast, resolution, and assessability of the spinal canal and neural foramen. The interrater agreement was moderate for signal/contrast (ICC = 0.68) and good for resolution (ICC = 0.77), but moderate for spinal canal and neuroforaminal assessability (ICC = 0.55). Quantitative assessment showed a higher contrast ratio for fluid-sensitive sequences in the ADLR images. The use of ADLR reduced image acquisition time by 44.4%, from 14:22 min to 07:59 min. ConclusionsAdvanced deep learning-based image reconstruction algorithms improve the visually perceived image quality in lumbar spine imaging at 0.55 T while simultaneously allowing to substantially decrease image acquisition times. Clinical relevanceAdvanced deep learning-based image post-processing techniques (ADLR) in lumbar spine MRI at 0.55 T significantly improves image quality while reducing image acquisition time.

Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI.

To compare a previous model-based image reconstruction (MBIR) with a newly developed deep learning (DL)-based image reconstruction for providing improved signal-to-noise ratio (SNR) in high through-plane resolution (1mm) T2-weighted spin-echo (T2SE) prostate MRI. Large-area contrast and high-contrast spatial resolution of the reconstruction methods were assessed quantitatively in experimental phantom studies. The methods were next evaluated radiologically in 17 subjects at 3.0 Tesla for whom prostate MRI was clinically indicated. For each subject, the axial T2SE raw data were directed to MBIR and to the DL reconstruction at three vendor-provided levels: (L)ow, (M)edium, and (H)igh. Thin-slice images from the four reconstructions were compared using evaluation criteria related to SNR, sharpness, contrast fidelity, and reviewer preference. Results were compared using the Wilcoxon signed-rank test using Bonferroni correction, and inter-reader comparisons were done using the Cohen and Krippendorf tests. Baseline contrast and resolution in phantom studies were equivalent for all four reconstruction pathways as desired. In vivo, all three DL levels (L, M, H) provided improved SNR versus MBIR. For virtually, all other evaluation criteria DL L and M were superior to MBIR. DL L and M were evaluated as superior to DL H in fidelity of contrast. For 44 of the 51 evaluations, the DL M reconstruction was preferred. The deep learning reconstruction method provides significant SNR improvement in thin-slice (1mm) T2SE images of the prostate while retaining image contrast. However, if taken to too high a level (DL High), both radiological sharpness and fidelity of contrast diminish.

Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality.

This study explores the use of deep learning (DL) techniques in MRI of the orbit to enhance imaging. Standard protocols, although detailed, have lengthy acquisition times. We investigate DL-based methods for T2-weighted and T1-weighted, fat-saturated, contrast-enhanced turbo spin echo (TSE) sequences, aiming to improve image quality, reduce acquisition time, minimize artifacts, and enhance diagnostic confidence in orbital imaging. In a 3-Tesla MRI study of 50 patients evaluating orbital diseases from March to July 2023, conventional (TSES ) and DL TSE sequences (TSEDL ) were used. Two neuroradiologists independently assessed the image datasets for image quality, diagnostic confidence, noise levels, artifacts, and image sharpness using a randomized and blinded 4-point Likert scale. TSEDL significantly reduced image noise and artifacts, enhanced image sharpness, and decreased scan time, outperforming TSES (p<.05). TSEDL showed superior overall image quality and diagnostic confidence, with relevant findings effectively detected in both DL-based and conventional images. In 94% of cases, readers preferred accelerated imaging. The study proved that using DL for MRI image reconstruction in orbital scans significantly cut acquisition time by 69%. This approach also enhanced image quality, reduced image noise, sharpened images, and boosted diagnostic confidence.

Kiosk 10R-TB-10 - Evaluation of Accelerated Deep-learning Based Image Reconstruction for Cine MRI

Kiosk 10R-TB-10 - Evaluation of Accelerated Deep-learning Based Image Reconstruction for Cine MRI

CMR 3-95 - Accelerated Image Reconstruction in Cardiac Cine MRI: A 3D Cnn-based Modl Approach

CMR 3-95 - Accelerated Image Reconstruction in Cardiac Cine MRI: A 3D Cnn-based Modl Approach

MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation

Background and objectiveHigh-quality reconstruction of MRI images from under-sampled ‘k-space’ data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle the complex, ill-posed inverse problem linked to this process. However, their instability against variations in the acquisition process and anatomical distribution exposes a deficiency in the generalization of relevant physical models within these DNN architectures. The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing ‘MA-RECON’, an innovative mask-aware DNN architecture and associated training method. MethodsUnlike preceding approaches, our ‘MA-RECON’ architecture encodes not only the observed data but also the under-sampling mask within the model structure. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem. Therefore, effectively represents the associated inverse problem, akin to the classical compressed sensing approach. ResultsThe benefits of our MA-RECON approach were affirmed through rigorous testing with the widely accessible fastMRI dataset. Compared to standard DNN methods and DNNs trained with under-sampling mask augmentation, our approach demonstrated superior generalization capabilities. This resulted in a considerable improvement in robustness against variations in both the acquisition process and anatomical distribution, especially in regions with pathology. ConclusionIn conclusion, our mask-aware strategy holds promise for enhancing the generalization capacity and robustness of DNN-based methodologies for MRI reconstruction from undersampled k-space data.Code is available in the following link: https://github.com/nitzanavidan/PD_Recon

A lightweight super-resolution network with skip-connections.

In some hospitals in remote areas, due to the lack of MRI scanners with high magnetic field intensity, only low-resolution MRI images can be obtained, hindering doctors from making correct diagnoses. In our study, higher-resolution images were obtained through low-resolution MRI images. Moreover, as our algorithm is a lightweight algorithm with a small number of parameters, it can be carried out in remote areas under the condition of the lack of computing resources. Moreover, our algorithm is of great clinical significance in providing references for doctors' diagnoses and treatment in remote areas. We compared different super-resolution algorithms to obtain high-resolution MRI images, including SRGAN, SPSR, and LESRCNN. A global skip connection was applied to the original network of LESRCNN to use global semantic information to get better performance. Experiments reported that our network improved SSMI by 0.8% and also achieved an obvious increase in PSNR, PI, and LPIPS compared to LESRCNN in our dataset. Similar to LESRCNN, our network has a very short running time, a small number of parameters, low time complexity, and low space complexity while ensuring high performance compared to SRGAN and SPSR. Five MRI doctors were invited for a subjective evaluation of our algorithm. All agreed on significant improvements and that our algorithm could be used clinically in remote areas and has great value. The experimental results demonstrated the performance of our algorithm in super-resolution MRI image reconstruction. It allows us to obtain high-resolution images in the absence of high-field intensity MRI scanners, which have great clinical significance. The short running time, a small number of parameters, low time complexity, and low space complexity ensure that our network can be used in grassroots hospitals in remote areas that lack computing resources. We can reconstruct high-resolution MRI images in a short time, thus saving time for patients. Our algorithm can be biased towards practical applications; however, doctors have affirmed the clinical value of our algorithm.

Diffusion Weighted Imaging Super-Resolution Algorithm for Highly Sparse Raw Data Sequences

The utilization of quick compression-sensed magnetic resonance imaging results in an enhancement of diffusion imaging. Wasserstein Generative Adversarial Networks (WGANs) leverage image-based information. The article presents a novel G-guided generative multilevel network, which leverages diffusion weighted imaging (DWI) input data with constrained sampling. The present study aims to investigate two primary concerns pertaining to MRI image reconstruction, namely, image resolution and reconstruction duration. The implementation of simultaneous k-q space sampling has been found to enhance the performance of Rotating Single-Shot Acquisition (RoSA) without necessitating any hardware modifications. Diffusion weighted imaging (DWI) is capable of decreasing the duration of testing by minimizing the amount of input data required. The synchronization of diffusion directions within PROPELLER blades is achieved through the utilization of compressed k-space synchronization. The grids utilized in DW-MRI are represented by minimal-spanning trees. The utilization of conjugate symmetry in sensing and the Partial Fourier approach has been observed to enhance the efficacy of data acquisition as compared to unaltered k-space sampling systems. The image’s sharpness, edge readings, and contrast have been enhanced. These achievements have been certified by numerous metrics including PSNR and TRE. It is desirable to enhance image quality without necessitating any modifications to the hardware.

Cloud-enabled Internet of Things Medical Image Processing Compressed Sensing Reconstruction

Deep learning compresses medical image processing in IoMT. CS-MRI acquires quickly. It has various medicinal uses due to its advantages. This lowers motion artifacts and contrast washout. Reduces patient pressure and scanning costs. CS-MRI avoids the Nyquist-Shannon sampling barrier. Parallel imagingbased fast MRI uses many coils to reconstruct MRI images with less raw data. Parallel imaging enables rapid MRI. This research developed a deep learning-based method for reconstructing CS-MRI images that bridges the gap between typical non-learning algorithms that employ data from a single image and enormous training datasets. Conventional approaches only reconstruct CS-MRI data from one picture. Reconstructing CS-MRI images. CS-GAN is recommended for CS-MRI reconstruction. For success. Refinement learning stabilizes our C-GAN-based generator, which eliminates aliasing artifacts. This improved newly produced data. Product quality increased. Adversarial and information loss recreated the picture. We should protect the image’s texture and edges. Picture and frequency domain data establish consistency. We want frequency and picture domain information to match. It offers visual domain data. Traditional CS-MRI reconstruction and deep learning were used in our broad comparison research. C-GAN enhances reconstruction while conserving perceptual visual information. MRI image reconstruction takes 5 milliseconds, allowing real-time analysis.

PNCS: Pixel-Level Non-Local Method Based Compressed Sensing Undersampled MRI Image Reconstruction

PNCS: Pixel-Level Non-Local Method Based Compressed Sensing Undersampled MRI Image Reconstruction

Pyramid Convolutional RNN for MRI Image Reconstruction.

Fast and accurate MRI image reconstruction from undersampled data is crucial in clinical practice. Deep learning based reconstruction methods have shown promising advances in recent years. However, recovering fine details from undersampled data is still challenging. In this paper, we introduce a novel deep learning based method, Pyramid Convolutional RNN (PC-RNN), to reconstruct images from multiple scales. Based on the formulation of MRI reconstruction as an inverse problem, we design the PC-RNN model with three convolutional RNN (ConvRNN) modules to iteratively learn the features in multiple scales. Each ConvRNN module reconstructs images at different scales and the reconstructed images are combined by a final CNN module in a pyramid fashion. The multi-scale ConvRNN modules learn a coarse-to-fine image reconstruction. Unlike other common reconstruction methods for parallel imaging, PC-RNN does not employ coil sensitive maps for multi-coil data and directly model the multiple coils as multi-channel inputs. The coil compression technique is applied to standardize data with various coil numbers, leading to more efficient training. We evaluate our model on the fastMRI knee and brain datasets and the results show that the proposed model outperforms other methods and can recover more details. The proposed method is one of the winner solutions in the 2019 fastMRI competition.

Velocity vector reconstruction for real-time phase-contrast MRI with radial Maxwell correction.

To develop an auto-calibrated image reconstruction for highly accelerated multi-directional phase-contrast (PC) MRI that compensates for (1) reconstruction instabilities occurring for phase differences near and (2) phase errors by concomitant magnetic fields that differ for individual radial spokes. A model-based image reconstruction for real-time PC MRI based on nonlinear inversion is extended to multi-directional flow by exploiting multiple flow-encodings for the estimation of velocity vectors. An initial smoothing constraint during iterative optimization is introduced to resolve the ambiguity of the solution space by penalizing phase wraps. Maxwell terms are considered as part of the signal model on a line-by-line basis to address phase errors by concomitant magnetic fields. The reconstruction methods are evaluated using simulated data and cross-sectional imaging of a rotating-disc, as well as in vivo for the aortic arch and cervical spinal canal at 3T. Real-time three-directional velocity mapping in the aortic arch is achieved at 1.8 × 1.8 × 6 mm3 spatial and 60 ms temporal resolution. Artificial phase wraps are avoided in all cases using the smoothness constraint. Inter-spoke differences of concomitant magnetic fields are effectively compensated for by the model-based image reconstruction with integrated radial Maxwell correction. Velocity vector reconstructions based on nonlinear inversion allow for high degrees of radial data undersampling paving the way for multi-directional PC MRI in real time. Whether a spoke-wise treatment of Maxwell terms is required or a computationally cheaper frame-wise approach depends on the individual application.

Deep Learning Applications in Magnetic Resonance Imaging: Has the Future Become Present?

Deep learning technologies and applications demonstrate one of the most important upcoming developments in radiology. The impact and influence of these technologies on image acquisition and reporting might change daily clinical practice. The aim of this review was to present current deep learning technologies, with a focus on magnetic resonance image reconstruction. The first part of this manuscript concentrates on the basic technical principles that are necessary for deep learning image reconstruction. The second part highlights the translation of these techniques into clinical practice. The third part outlines the different aspects of image reconstruction techniques, and presents a review of the current literature regarding image reconstruction and image post-processing in MRI. The promising results of the most recent studies indicate that deep learning will be a major player in radiology in the upcoming years. Apart from decision and diagnosis support, the major advantages of deep learning magnetic resonance imaging reconstruction techniques are related to acquisition time reduction and the improvement of image quality. The implementation of these techniques may be the solution for the alleviation of limited scanner availability via workflow acceleration. It can be assumed that this disruptive technology will change daily routines and workflows permanently.

Musiré: multimodal simulation and reconstruction framework for the radiological imaging sciences.

A software-based workflow is proposed for managing the execution of simulation and image reconstruction for SPECT, PET, CBCT, MRI, BLI and FMI packages in single and multimodal biomedical imaging applications. The workflow is composed of a Bash script, the purpose of which is to provide an interface to the user, and to organize data flow between dedicated programs for simulation and reconstruction. The currently incorporated simulation programs comprise GATE for Monte Carlo simulation of SPECT, PET and CBCT, SpinScenario for simulating MRI, and Lipros for Monte Carlo simulation of BLI and FMI. Currently incorporated image reconstruction programs include CASToR for SPECT and PET as well as RTK for CBCT. MetaImage (mhd) standard is used for voxelized phantom and image data format. Meshlab project (mlp) containers incorporating polygon meshes and point clouds defined by the Stanford triangle format (ply) are employed to represent anatomical structures for optical simulation, and to represent tumour cell inserts. A number of auxiliary programs have been developed for data transformation and adaptive parameter assignment. The software workflow uses fully automatic distribution to, and consolidation from, any number of Linux workstations and CPU cores. Example data are presented for clinical SPECT, PET and MRI systems using the Mida head phantom and for preclinical X-ray, PET and BLI systems employing the Digimouse phantom. The presented method unifies and simplifies multimodal simulation setup and image reconstruction management and might be of value for synergistic image research. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 2'.

Ground-truth-free deep learning for artefacts reduction in 2D radial cardiac cine MRI using a synthetically generated dataset

In this work, we consider the task of image reconstruction in 2D radial cardiac cine MRI using deep learning (DL)-based regularization. As the regularization is achieved by employing an image-prior predicted by a pre-trained convolutional neural network (CNN), the quality of the image-prior is of essential importance. The achievable performance of any DL-based method is limited by the amount and the quality of the available training data. For fast dynamic processes, obtaining good-quality MR data is challenging because of technical and physiological reasons. In this work, we try to overcome these problems by a transfer-learning approach which is motivated by a previously presented DL-method (XT,YT U-Net). There, instead of training the network on the whole 2D dynamic images, it is trained on 2D spatio-temporal profiles (xt,yt-slices) which show the temporal changes of the imaged object. Therefore, for the training and test data, it is more important that their spatio-temporal profiles share similar local features rather than being images of the same anatomy. This allows us to equip arbitrary data with simulated motion that resembles the cardiac motion and use it as training data. By doing so, it is possible to train a CNN which is applicable to cardiac cine MR data without using ground-truth cine MR images for training. We demonstrate that combining XT,YT U-Net with the proposed transfer-learning strategy delivers comparable performance to CNNs trained on cardiac cine MR images and in some cases even qualitatively surpasses these. Additionally, the transfer-learning strategy was investigated for a 2D and 3D U-Net. The images processed by the the CNNs were used as image-priors in the CNN-regularized iterative reconstruction. The XT,YT U-Net yielded visibly better results than the 2D U-Net and slightly better results than the 3D U-Net when used in combination with the presented transfer learning-strategy.

MRI Image Reconstruction Based on Artificial Intelligence

Artificial intelligence is a new high and new technology, which has powerful functional advantages in processing big data, complex and non-deterministic data, and in-depth mining of hidden information behind the data. Magnetic resonance is a common diagnosis and treatment technology in medical clinics. The use of magnetic resonance imaging technology to construct medical images has a great auxiliary effect for doctors to make accurate medical diagnosis. This article proposes to combine artificial intelligence and magnetic resonance technology to construct magnetic resonance images based on artificial intelligence, in order to reconstruct high-quality magnetic resonance images, thereby improving the efficiency of doctors’ diagnosis and treatment and reducing misdiagnosis. This paper uses the deep learning algorithm of artificial intelligence to compare the analytic dictionary method, the synthetic dictionary method and the deep dictionary method based on convolutional neural network, and obtain the peak-to-noise ratio of the image reconstructed by the three algorithms under the same sampling rate. They are 42.56, 44.17 and 45.55 respectively; the structural similarity is 0.9387, 0.9536 and 0.9867, respectively. The study concluded that the deep dictionary method based on convolutional neural network has more advantages in reconstructing MRI images, and the effect is more obvious.