Interpolated compressed sensing for 2D multiple slice fast MR imaging

MRI super-resolution using similarity distance and multi-scale receptive field based feature fusion GAN and pre-trained slice interpolation network

Challenges arise in achieving high-resolution Magnetic Resonance Imaging (MRI) to improve disease diagnosis accuracy due to limitations in hardware, patient discomfort, long acquisition times, and high costs. While Convolutional Neural Networks (CNNs) have shown promising results in MRI super-resolution, they often don't look into the structural similarity and prior information available in consecutive MRI slices. By leveraging information from sequential slices, more robust features can be obtained, potentially leading to higher-quality MRI slices. We propose a multi-slice two-dimensional (2D) MRI super-resolution network that combines a Generative Adversarial Network (GAN) with feature fusion and a pre-trained slice interpolation network to achieve three-dimensional (3D) super-resolution. The proposed model requires consecutively acquired three low-resolution (LR) MRI slices along a specific axis, and achieves the reconstruction of the MRI slices in the remaining two axes. The network effectively enhances both in-plane and out-of-plane resolution along the sagittal axis while addressing computational and memory constraints in 3D super-resolution. The proposed generator has a in-plane and out-of-plane Attention (IOA) network that fuses both in-plane and out-plane features of MRI dynamically. In terms of out-of-plane attention, the network merges features by considering the similarity distance between features and for in-plane attention, the network employs a two-level pyramid structure with varying receptive fields to extract features at different scales, ensuring the inclusion of both global and local features. Subsequently, to achieve 3D MRI super-resolution, a pre-trained slice interpolation network is used that takes two consecutive super-resolved MRI slices to generate a new intermediate slice. To further enhance the network performance and perceptual quality, we introduce a feature up-sampling layer and a feature extraction block with Scaled Exponential Linear Unit (SeLU). Moreover, our super-resolution network incorporates VGG loss from a fine-tuned VGG-19 network to provide additional enhancement. Through experimental evaluations on the IXI dataset and BRATS dataset, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and the number of training parameters, we demonstrate the superior performance of our method compared to the existing techniques. Also, the proposed model can be adapted or modified to achieve super-resolution for both 2D and 3D MRI data.

Complexities of deep learning-based undersampled MR image reconstruction

Artificial intelligence has opened a new path of innovation in magnetic resonance (MR) image reconstruction of undersampled k-space acquisitions. This review offers readers an analysis of the current deep learning-based MR image reconstruction methods. The literature in this field shows exponential growth, both in volume and complexity, as the capabilities of machine learning in solving inverse problems such as image reconstruction are explored. We review the latest developments, aiming to assist researchers and radiologists who are developing new methods or seeking to provide valuable feedback. We shed light on key concepts by exploring the technical intricacies of MR image reconstruction, highlighting the importance of raw datasets and the difficulty of evaluating diagnostic value using standard metrics.Relevance statement Increasingly complex algorithms output reconstructed images that are difficult to assess for robustness and diagnostic quality, necessitating high-quality datasets and collaboration with radiologists.Key points• Deep learning-based image reconstruction algorithms are increasing both in complexity and performance.• The evaluation of reconstructed images may mistake perceived image quality for diagnostic value.• Collaboration with radiologists is crucial for advancing deep learning technology.

Improving delineation of the corticospinal tract in the monkey brain scanned with conventional DTI by using a compressed sensing based algorithm

Background

The corticospinal tract (CST) is a major tract for motor function. It can be impaired by stroke. Its degeneration is associated with stroke outcome. Diffusion tensor imaging (DTI) tractography plays an important role in assessing fiber bundle integrity. However, it is limited in detecting crossing fibers in the brain. The crossing fiber angular resolution of intra-voxel structure (CFARI) algorithm shows potential to resolve complex fibers in the brain. The objective of the present study was to improve delineation of CST pathways in monkey brains scanned by conventional DTI.

Methods

Healthy rhesus monkeys were scanned by diffusion MRI with 128 diffusion encoding directions to evaluate the CFARI algorithm. Four monkeys with ischemic occlusion were also scanned with DTI (b = 1000 s/mm², 30 diffusion directions) at 6, 48, and 96 hours post stroke. CST fibers were reconstructed with DTI and CFARI-based tractography and evaluated. A two-way repeated MANOVA was used to determine significances of changes in DTI indices, tract number, and volumes of the CST between hemispheres or post-stroke time points.

Results

CFARI algorithm revealed substantially more fibers originated from the ventral premotor cortex in healthy and stroke monkey brains than DTI tractography. In addition, CFARI showed better sensitivity in detecting CST abnormality than DTI tractography following stroke.

Conclusion

CFARI significantly improved delineation of the CST in the brain scanned by DTI with 30 gradient directions. It showed better sensitivity in detecting abnormity of the CST following stroke. Preliminary results suggest that CFARI could facilitate prediction of function outcomes after stroke.

Calibrationless multi-slice Cartesian MRI via orthogonally alternating phase encoding direction and joint low-rank tensor completion

We propose a multi-slice acquisition with orthogonally alternating phase encoding (PE) direction and subsequent joint calibrationless reconstruction for accelerated multiple individual 2D slices or multi-slice 2D Cartesian MRI. Specifically, multi-slice multi-channel data are first acquired with random or uniform PE undersampling while orthogonally alternating PE direction between adjacent slices. They are then jointly reconstructed through a recently developed low-rank multi-slice Hankel tensor completion (MS-HTC) approach. The proposed acquisition and reconstruction strategy was evaluated with human brain MR data. It effectively suppressed aliasing artifacts even at high acceleration factor, outperforming the existing MS-HTC approach, where PE direction is the same between adjacent slices. More importantly, the new strategy worked robustly with uniform undersampling or random undersampling without any consecutive central k-space lines. In summary, our proposed multi-slice MRI strategy exploits both coil sensitivity and image content similarities across adjacent slices. Orthogonally alternating PE direction among slices substantially facilitates the low-rank completion process and improves image reconstruction quality. This new strategy is applicable to uniform and random PE undersampling. It can be easily implemented in practice for Cartesian parallel imaging of multiple individual 2D slices without any coil sensitivity calibration.

Compressed Sensing Cardiac Cine Imaging Compared with Standard Balanced Steady-State Free Precession Cine Imaging in a Pediatric Population

Purpose

To compare real-time compressed sensing (CS) and standard balanced steady-state free precession (bSSFP) cardiac cine imaging in children.

Materials and Methods

Twenty children (mean age, 15 years ± 5 [SD], range, 7-21 years; 10 male participants) with biventricular congenital heart disease (n = 11) or cardiomyopathy (n = 9) were prospectively included. Examinations were performed with 1.5-T imagers by using both bSSFP and CS sequences in all participants. Quantification of ventricular volumes and function was performed for all images by two readers blinded to patient diagnosis and type of sequence. Values were correlated with phase-contrast flow measurements by one reader. Intra- and interreader agreement were analyzed.

Results

There were no significant differences between ventricular parameters measured on CS compared with those of bSSFP (P > .05) for reader 1. Only ejection fraction showed a significant difference (P = .02) for reader 2. Intrareader agreement was considerable for both sequences (bSSFP: mean difference range, +1 to -2.6; maximum CI, +7.9, -13; bias range, 0.1%-4.1%; intraclass correlation coefficient [ICC] range, 0.931-0.997. CS: mean difference range, +7.4 to -5.6; maximum CI, +37.2, -48.8; bias range, 0.5%-7.5%; ICC range, 0.717-0.997). Interreader agreement was acceptable but less robust, especially for CS (bSSFP: mean difference range, +2.6 to -5.6; maximum CI, +60.7, -65.3; bias range, 1.6%-6.2%; ICC range, 0.726-0.951. CS: mean difference range, +10.7 to -9.1; maximum CI, +87.5, -84.6; bias range, 1.1%-17.3%; ICC range, 0.509-0.849). The mean acquisition time was shorter for CS (20 seconds; range, 17-25 seconds) compared with that for bSSFP (160 seconds; range, 130-190 seconds) (P < .001).

Conclusion

CS cardiac cine imaging provided equivalent ventricular volume and function measurements with shorter acquisition times compared with those of bSSFP and may prove suitable for the pediatric population.Keywords: Compressed Sensing, Balanced Steady-State Free Precession, Cine Imaging, Cardiovascular MRI, Pediatrics, Cardiac, Heart, Cardiomyopathies, Congenital, Segmentation© RSNA, 2022.

Radial Undersampling-Based Interpolation Scheme for Multislice CSMRI Reconstruction Techniques

Magnetic Resonance Imaging (MRI) is an important yet slow medical imaging modality. Compressed sensing (CS) theory has enabled to accelerate the MRI acquisition process using some nonlinear reconstruction techniques from even 10% of the Nyquist samples. In recent years, interpolated compressed sensing (iCS) has further reduced the scan time, as compared to CS, by exploiting the strong interslice correlation of multislice MRI. In this paper, an improved efficient interpolated compressed sensing (EiCS) technique is proposed using radial undersampling schemes. The proposed efficient interpolation technique uses three consecutive slices to estimate the missing samples of the central target slice from its two neighboring slices. Seven different evaluation metrics are used to analyze the performance of the proposed technique such as structural similarity index measurement (SSIM), feature similarity index measurement (FSIM), mean square error (MSE), peak signal to noise ratio (PSNR), correlation (CORR), sharpness index (SI), and perceptual image quality evaluator (PIQE) and compared with the latest interpolation techniques. The simulation results show that the proposed EiCS technique has improved image quality and performance using both golden angle and uniform angle radial sampling patterns, with an even lower sampling ratio and maximum information content and using a more practical sampling scheme.

SR-Net: A sequence offset fusion net and refine net for undersampled multislice MR image reconstruction

BACKGROUND AND OBJECTIVE

The study of deep learning-based fast magnetic resonance imaging (MRI) reconstruction methods has become popular in recent years. However, there is still a challenge when MRI results undersample large acceleration factors. The objective of this study was to improve the reconstruction quality of undersampled MR images by exploring data redundancy among slices.

METHODS

There are two aspects of redundancy in multislice MR images including correlations inside a single slice and correlations among slices. Thus, we built two subnets for the two kinds of redundancy. For correlations among slices, we built a bidirectional recurrent convolutional neural network, named Sequence Offset Fusion Net (S-Net). In S-Net, we used a deformable convolution module to construct a neighbor slice feature extractor. For the correlation inside a single slice, we built a Refine Net (R-Net), which has 5 layers of 2D convolutions. In addition, we used a data consistency (DC) operation to maintain data fidelity in k-space. Finally, we treated the reconstruction task as a dealiasing problem in the image domain, and S-Net and R-Net are applied alternately and iteratively to generate the final reconstructions.

RESULTS

The proposed algorithm was evaluated using two online public MRI datasets. Compared with several state-of-the-art methods, the proposed method achieved better reconstruction results in terms of dealiasing and restoring tissue structure. Moreover, with over 14 slices per second reconstruction speed on 256x256 pixel images, the proposed method can meet the need for real-time processing.

CONCLUSION

With spatial correlation among slices as additional prior information, the proposed method dramatically improves the reconstruction quality of undersampled MR images.

Evaluation of magnetic resonance image segmentation in brain low-grade gliomas using support vector machine and convolutional neural network

BACKGROUND

Image segmentation of brain low-grade glioma (LGG) magnetic resonance imaging (MRI) contributes tremendously to diagnosis, classification and treatment of the disease. A tangible, accurate, reliable and fast image segmentation technique is demanded in clinical diagnosis and research.

METHODS

The emerging machine learning technique has been demonstrated its unique capability in the field of medical image processing, including medical image segmentation. Support vector machine (SVM) and convolutional neural network (CNN) are two widely used machine learning methods. In this work, image segmentation tools based on SVM and CNN are developed and evaluated for brain LGG MR image segmentation studies. The segmentation performance in terms of accuracy and cost is quantitatively analyzed and compared between the SVM and CNN techniques developed.

RESULTS

Computed on the Google CoLab, each of the 109 SVM models represents an individual patient, is trained using a single image of that patient and takes a few seconds to complete. The CNN model is trained on a drastically larger dataset of 19,760 data augmented images and takes approximately 2 hours to obtain the most optimal result. The SVM models achieved an average and median accuracy of 0.937 and 0.976 respectively, precision of 0.456 and 0.535 respectively, recall of 0.878 and 0.906 respectively, and F1 score of 0.546 and 0.662 respectively. Although the CNN model required a significantly longer calculation time, it surpassed the SVM models in performance in LGG MR image segmentation, achieving an accuracy of 0.998, a precision of 0.999, a recall of 0.999 and an F1 score of 0.999.

CONCLUSIONS

This study shows that SVM with appropriate filtering techniques is capable of obtaining reliable and fast segmentation of brain LGG MR images with sufficient accuracy and limited image data. CNN technique outperforms SVM in the accuracy of segmentation with requirements of significantly enlarged data set, long computation time and high-performance computer.

Calibrationless parallel imaging reconstruction for multislice MR data using low-rank tensor completion

PURPOSE

To provide joint calibrationless parallel imaging reconstruction of highly accelerated multislice 2D MR k-space data.

METHODS

Adjacent image slices in multislice MR data have similar coil sensitivity maps, spatial support, and image content. Such similarities can be utilized to improve image quality by reconstructing multiple slices jointly with low-rank tensor completion. Specifically, the multichannel k-space data from multiple slices are constructed into a block-wise Hankel tensor and iteratively updated by promoting tensor low-rankness through higher-order SVD. This multislice block-wise Hankel tensor completion was implemented for 2D spiral and Cartesian k-space undersampling where sampling patterns vary between adjacent slices. The approach was evaluated with human brain MR data and compared to the traditional single-slice simultaneous autocalibrating and k-space estimation reconstruction.

RESULTS

The proposed multislice block-wise Hankel tensor completion approach robustly reconstructed highly undersampled multislice 2D spiral and Cartesian data. It produced substantially lower level of artifacts compared to the traditional single-slice simultaneous autocalibrating and k-space estimation reconstruction. Quantitative evaluation using error maps and root mean square error demonstrated its significantly improved performance in terms of residual artifacts and root mean square error.

CONCLUSION

Our proposed multislice block-wise Hankel tensor completion method exploits the similar coil sensitivity and image content within multislice MR data through a tensor completion framework. It offers a new and effective approach to acquire and reconstruct highly undersampled multislice MR data in a calibrationless manner.

Highly and Adaptively Undersampling Pattern for Pulmonary Hyperpolarized 129Xe Dynamic MRI

Hyperpolarized (HP) gas (e.g., ³He or ¹²⁹Xe) dynamic MRI could visualize the lung ventilation process, which provides characteristics regarding lung physiology and pathophysiology. Compressed sensing (CS) is generally used to increase the temporal resolution of such dynamic MRI. Nevertheless, the acceleration factor of CS is constant, which results in difficulties in precisely observing and/or measuring dynamic ventilation process due to bifurcating network structure of the lung. Here, an adaptive strategy is proposed to highly undersample pulmonary HP dynamic k-space data, according to the characteristics of both lung structure and gas motion. After that, a valid reconstruction algorithm is developed to reconstruct dynamic MR images, considering the low-rank, global sparsity, gas-inflow effects, and joint sparsity. Both the simulation and the in vivo results verify that the proposed approach outperforms the state-of-the-art methods both in qualitative and quantitative comparisons. In particular, the proposed method acquires 33 frames within 6.67 s (more than double the temporal resolution of the recently proposed strategy), and achieves high-image quality [the improvements are 29.63%, 3.19%, 2.08%, and 13.03% regarding the mean absolute error (MAE), structural similarity index (SSIM), quality index based on local variance (QILV), and contrast-to-noise ratio (CNR) comparisons]. This provides accurate structural and functional information for early detection of obstructive lung diseases.

Balanced sparse model for tight frames in compressed sensing magnetic resonance imaging

Compressed sensing has shown to be promising to accelerate magnetic resonance imaging. In this new technology, magnetic resonance images are usually reconstructed by enforcing its sparsity in sparse image reconstruction models, including both synthesis and analysis models. The synthesis model assumes that an image is a sparse combination of atom signals while the analysis model assumes that an image is sparse after the application of an analysis operator. Balanced model is a new sparse model that bridges analysis and synthesis models by introducing a penalty term on the distance of frame coefficients to the range of the analysis operator. In this paper, we study the performance of the balanced model in tight frame based compressed sensing magnetic resonance imaging and propose a new efficient numerical algorithm to solve the optimization problem. By tuning the balancing parameter, the new model achieves solutions of three models. It is found that the balanced model has a comparable performance with the analysis model. Besides, both of them achieve better results than the synthesis model no matter what value the balancing parameter is. Experiment shows that our proposed numerical algorithm constrained split augmented Lagrangian shrinkage algorithm for balanced model (C-SALSA-B) converges faster than previously proposed algorithms accelerated proximal algorithm (APG) and alternating directional method of multipliers for balanced model (ADMM-B).

Enhancement of the low resolution image quality using randomly sampled data for multi-slice MR imaging

Low resolution images are often acquired in in vivo MR applications involving in large field-of-view (FOV) and high speed imaging, such as, whole-body MRI screening and functional MRI applications. In this work, we investigate a multi-slice imaging strategy for acquiring low resolution images by using compressed sensing (CS) MRI to enhance the image quality without increasing the acquisition time. In this strategy, low resolution images of all the slices are acquired using multiple-slice imaging sequence. In addition, extra randomly sampled data in one center slice are acquired by using the CS strategy. These additional randomly sampled data are multiplied by the weighting functions generated from low resolution full k-space images of the two slices, and then interpolated into the k-space of other slices. In vivo MR images of human brain were employed to investigate the feasibility and the performance of the proposed method. Quantitative comparison between the conventional low resolution images and those from the proposed method was also performed to demonstrate the advantage of the method.

Sparse parallel transmission on randomly perturbed spiral k-space trajectory

Combination of parallel transmission and sparse pulse is able to shorten the excitation by using both the coil sensitivity and sparse k-space, showing improved fast excitation capability over the use of parallel transmission alone. However, to design an optimal k-space trajectory for sparse parallel transmission is a challenging task. In this work, a randomly perturbed sparse k-space trajectory is designed by modifying the path of a spiral trajectory along the sparse k-space data, and the sparse parallel transmission RF pulses are subsequently designed based on this optimal trajectory. This method combines the parallel transmission and sparse spiral k-space trajectory, potentially to further reduce the RF transmission time. Bloch simulation of 90° excitation by using a four channel coil array is performed to demonstrate its feasibility. Excitation performance of the sparse parallel transmission technique at different reduction factors of 1, 2, and 4 is evaluated. For comparison, parallel excitation using regular spiral trajectory is performed. The passband errors of the excitation profiles of each transmission are calculated for quantitative assessment of the proposed excitation method.

Exploiting similarity in adjacent slices for compressed sensing MRI

Due to fundamental characteristics of MRI that limit scan speedup, sub-sampling techniques such as compressed sensing (CS) have been developed for rapid MRI. Current CS MRI approaches utilize sparsity of the image in the wavelet or other transform domains to speed-up acquisition. Another drawback of MRI is its poor signal-to-noise ratio (SNR), which is proportional to the image slice thickness. In this paper, we use the difference between adjacent slices as the sparse domain for CS MRI. We propose to acquire thick MRI slices and to reconstruct the thin slices from the thick slices' data, utilizing the similarity between adjacent thin slices. The acquisition of thick slices, instead of thin ones, improves the total SNR of the reconstructed image. Experimental results show that the image reconstruction quality of the proposed method outperforms existing CS MRI methods using the same number of measurements.

Planar quadrature RF transceiver design using common-mode differential-mode (CMDM) transmission line method for 7T MR imaging

The use of quadrature RF magnetic fields has been demonstrated to be an efficient method to reduce transmit power and to increase the signal-to-noise (SNR) in magnetic resonance (MR) imaging. The goal of this project was to develop a new method using the common-mode and differential-mode (CMDM) technique for compact, planar, distributed-element quadrature transmit/receive resonators for MR signal excitation and detection and to investigate its performance for MR imaging, particularly, at ultrahigh magnetic fields. A prototype resonator based on CMDM method implemented by using microstrip transmission line was designed and fabricated for 7T imaging. Both the common mode (CM) and the differential mode (DM) of the resonator were tuned and matched at 298MHz independently. Numerical electromagnetic simulation was performed to verify the orthogonal B1 field direction of the two modes of the CMDM resonator. Both workbench tests and MR imaging experiments were carried out to evaluate the performance. The intrinsic decoupling between the two modes of the CMDM resonator was demonstrated by the bench test, showing a better than -36 dB transmission coefficient between the two modes at resonance frequency. The MR images acquired by using each mode and the images combined in quadrature showed that the CM and DM of the proposed resonator provided similar B1 coverage and achieved SNR improvement in the entire region of interest. The simulation and experimental results demonstrate that the proposed CMDM method with distributed-element transmission line technique is a feasible and efficient technique for planar quadrature RF coil design at ultrahigh fields, providing intrinsic decoupling between two quadrature channels and high frequency capability. Due to its simple and compact geometry and easy implementation of decoupling methods, the CMDM quadrature resonator can possibly be a good candidate for design blocks in multichannel RF coil arrays.