Search

Compressed sensing is commonly concerned with optimizing the image quality after a partial undersampling of the measurable k -space to accelerate MRI. In this article, we propose to change the focus from the quality of the reconstructed image to the quality of the downstream image analysis outcome. Specifically, we propose to optimize the patterns according to how well a sought-after pathology could be detected or localized in the reconstructed images. We find the optimal undersampling patterns in k -space that maximize target value functions of interest in commonplace medical vision problems (reconstruction, segmentation, and classification) and propose a new iterative gradient sampling routine universally suitable for these tasks. We validate the proposed MRI acceleration paradigm on three classical medical datasets, demonstrating a noticeable improvement of the target metrics at the high acceleration factors (for the segmentation problem at ×16 acceleration, we report up to 12% improvement in Dice score over the other undersampling patterns). • New paradigm for accelerating MRI, where k-space is undersampled intelligently for the benefit of downstream image analysis. • In this paradigm, the learned pattern can ruin the look of the image, while boosting the target metrics. • Our iterative gradient sampling (IGS) algorithm optimizes undersampling patterns for specific medical vision tasks and applications (cardiac, neurological, and orthopedic utility confirmed). • Noticeable improvement to target value metrics compared to the other undersampling patterns, such as equispaced or central masks. • The method proves especially instrumental at the highest acceleration factors when good image quality is impossible to obtain. [ABSTRACT FROM AUTHOR]

To assess the possibility of reducing the image acquisition time for diffusion-weighted whole-body imaging with background body signal suppression (DWIBS) by denoising with deep learning-based reconstruction (dDLR). Seventeen patients with prostate cancer who underwent DWIBS by 1.5 T magnetic resonance imaging with a number of excitations of 2 (NEX2) and 8 (NEX8) were prospectively enrolled. The NEX2 image data were processed by dDLR (dDLR-NEX2), and the NEX2, dDLR-NEX2, and NEX8 image data were analyzed. In qualitative analysis, two radiologists rated the perceived coarseness, conspicuity of metastatic lesions (lymph nodes and bone), and overall image quality. The contrast-to-noise ratios (CNRs), contrast ratios, and mean apparent diffusion coefficients (ADCs) of metastatic lesions were calculated in a quantitative analysis. The image acquisition time of NEX2 was 2.8 times shorter than that of NEX8 (3 min 30 s vs 9 min 48 s). The perceived coarseness and overall image quality scores reported by both readers were significantly higher for dDLR-NEX2 than for NEX2 (P = 0.005–0.040). There was no significant difference between dDLR-NEX2 and NEX8 in the qualitative analysis. The CNR of bone metastasis was significantly greater for dDLR-NEX2 than for NEX2 and NEX8 (P = 0.012 for both comparisons). The contrast ratios and mean ADCs were not significantly different among the three image types. dDLR improved the image quality of DWIBS with NEX2. In the context of lymph node and bone metastasis evaluation with DWIBS in patients with prostate cancer, dDLR-NEX2 has potential to be an alternative to NEX8 and reduce the image acquisition time. • Denoising with deep learning-based reconstruction (dDLR) is a new technique. • dDLR improved the image quality of whole-body diffusion-weighted imaging (DWI). • dDLR has potential to reduce the image acquisition time of whole-body DWI. [ABSTRACT FROM AUTHOR]

• Despite high demand, long MRI acquisition times lead to extended patient wait times. • CS-SuperRes reconstructions for low-resolution matches image quality of standard CS. • Using CS-SuperRes resulted in a 57% reduction in scan time. • 2D knee MRI protocol within 5 min while maintaining excellent image quality. • Enabling new ways for patients' logistics and workflow-management. To investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting of a series of convolutional neural networks (CNN) for a complete five-minute 2D knee MRI protocol. In this prospective study, 20 volunteers were examined using a 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, the protocol consists of a fat-saturated 2D-proton-density-sequence in coronal, sagittal and transversal orientation as well as a sagittal T1-weighted sequence. The sequences were acquired with two different resolutions (standard and low resolution) and the raw data reconstructed with two different reconstruction algorithms: a conventional Compressed SENSE (CS) and a new CNN-based algorithm for denoising and subsequently to interpolate and therewith increase the sharpness of the image (CS-SuperRes). Subjective image quality was evaluated by two blinded radiologists reviewing 8 criteria on a 5-point Likert scale and signal-to-noise ratio calculated as an objective parameter. The protocol reconstructed with CS-SuperRes received higher ratings than the time-equivalent CS reconstructions, statistically significant especially for low resolution acquisitions (e.g., overall image impression: 4.3 ± 0.4 vs. 3.4 ± 0.4, p < 0.05). CS-SuperRes reconstructions for the low resolution acquisition were comparable to traditional CS reconstructions with standard resolution for all parameters, achieving a scan time reduction from 11:01 min to 4:46 min (57 %) for the complete protocol (e.g. overall image impression: 4.3 ± 0.4 vs. 4.0 ± 0.5, p < 0.05). The newly-developed AI-based reconstruction algorithm CS-SuperRes allows to reduce scan time by 57% while maintaining unchanged image quality compared to the conventional CS reconstruction. [ABSTRACT FROM AUTHOR]

Purpose: To optimize operations for a newly implemented abbreviated MR (AB-MR) breast cancer screening protocol, activity times were compared with the full-protocol examination.Methods: Activity times from 70 AB-MR and 736 full MR screening studies were analyzed. Total study time was measured from opening to closing examinations and expected scan time by summing the time of acquisition for each imaging series for either protocol. Actual scan time was obtained from DICOM headers. Total technologist activity time was obtained by subtracting expected scan time from total study time. Technologist activity time included both scan-related and non-scan-related activities.Results: The actual scan time for the AB protocol was 17.5 ± 0.5 min, compared with 28.8 ± 0.3 min (mean ± SE) for the full protocol (difference, 11.3 min; P < .0001). The total study time was 36.0 ± 3.2 min for AB-MRI and 49.7 ± 0.8 min for the full protocol (difference, 13.7 min; P < .0001), implying that the AB-MR protocol had only a 38% greater patient flow rate than the full protocol.Conclusions: The realized gains in patient flow rate were lower than expected based on scan times (65%) because of increased technologist activity time for the AB-MR protocol. [ABSTRACT FROM AUTHOR]

In the last two decades, functional imaging of the lungs using hyperpolarized noble gases has entered the clinical stage. Both helium (3He) and xenon (129Xe) gas have been thoroughly investigated for their ability to assess both the global and regional patterns of lung ventilation. With advances in polarizer technology and the current transition towards the widely available 129Xe gas, this method is ready for translation to the clinic. Currently, hyperpolarized (HP) noble gas lung MRI is limited to selected academic institutions; yet, the promising results from initial clinical trials have drawn the attention of the pulmonary medicine community. HP 129Xe MRI provides not only 3-dimensional ventilation imaging, but also unique capabilities for probing regional lung physiology. In this review article, we aim to (1) provide a brief overview of current ventilation MR imaging techniques, (2) emphasize the role of HP 129Xe MRI within the array of different imaging strategies, (3) discuss the unique imaging possibilities with HP 129Xe MRI, and (4) propose clinical applications. [ABSTRACT FROM AUTHOR]

• Sampling patterns and reconstruction are jointly optimized for fast MRI. • Identical morphologic information in multi-contrast images helps to accelerate MRI. • End-to-end learning enable achievement of multiple adaptive sampling patterns. • Adaptive sampling patterns improve reconstruction quality of under-sampled images. Compressed sensing (CS) has gained increased attention in magnetic resonance imaging (MRI), leveraging its efficacy to accelerate image acquisition. Incoherence measurement and non-linear reconstruction are the most crucial guarantees of accurate restoration. However, the loose link between measurement and reconstruction hinders the further improvement of reconstruction quality, i.e., the default sampling pattern is not adaptively tailored to the downstream reconstruction method. When single-contrast reconstruction (SCR) has been upgraded to its multi-contrast reconstruction (MCR) variant, the identical morphologic information as a priori source could be integrated into the reconstruction procedure. How to measure less and reconstruct effectively by using the shareable morphologic information of various contrast images is an attractive topic. An adaptive sampling (AS) based end-to-end framework (ASSCR or ASMCR) is proposed to address this issue, which simultaneously optimizes sampling patterns and reconstruction from under-sampled data in SCR or MCR scenarios. Several deep probabilistic subsampling (DPS) modules are used in AS network to construct a sampling pattern generator. In SCR and MCR, a convolution block and a data consistency layer are iteratively applied in the reconstruction network. Specifically, the learned optimal sampling pattern output from the trained AS sub-net is used for under-sampling. Incoherence measurement for single-contrast images and the combination of sampling patterns for multi-contrast data are guided by the SCR/MCR sub-net. Experiments were conducted on two single-contrast and one multi-contrast public MRI datasets. Compared with several state-of-the-art reconstruction methods, SCR results show that a learned sampling pattern brings the quality of the reconstructed image closer to the fully-sampled reference. With the addition of different contrast images, under-sampled images with higher acceleration factors could be well recovered. The proposed method could improve the reconstruction quality of under-sampled images by using adaptive sampling patterns and learning-based reconstruction. [ABSTRACT FROM AUTHOR]

• We present a reconstruction algorithm for diffusion MRI data acquired with slice-level diffusion encoding (SIDE) to significantly reduce acquisition time. • We propose a robust reconstruction algorithm for undersampled SIDE data. • Our results indicate that more than 100 high isotropic resolution diffusion-weighted images can be acquired within a minute. [Display omitted] In this paper, we present a robust reconstruction scheme for diffusion MRI (dMRI) data acquired using slice-interleaved diffusion encoding (SIDE). When combined with SIDE undersampling and simultaneous multi-slice (SMS) imaging, our reconstruction strategy is capable of significantly reducing the amount of data that needs to be acquired, enabling high-speed diffusion imaging for pediatric, elderly, and claustrophobic individuals. In contrast to the conventional approach of acquiring a full diffusion-weighted (DW) volume per diffusion wavevector, SIDE acquires in each repetition time (TR) a volume that consists of interleaved slice groups, each group corresponding to a different diffusion wavevector. This strategy allows SIDE to rapidly acquire data covering a large number of wavevectors within a short period of time. The proposed reconstruction method uses a diffusion spectrum model and multi-dimensional total variation to recover full DW images from DW volumes that are slice-undersampled due to unacquired SIDE volumes. We formulate an inverse problem that can be solved efficiently using the alternating direction method of multipliers (ADMM). Experiment results demonstrate that DW images can be reconstructed with high fidelity even when the acquisition is accelerated by 25 folds. [ABSTRACT FROM AUTHOR]

Abstract: One of the main problems with rapid magnetic resonance imaging (MRI) techniques is the artifacts that result from off-resonance effects. The proposed off-resonance frequency filtered MRI (OFF-MRI) method focuses on the elimination of off-resonance components from the image of the observed object. To maintain imaging speed and simultaneously achieve good frequency selectivity, MRI is divided into two steps: signal acquisition and post-processing. After the preliminary phase in which we determine imaging parameters, MRI takes place; the signal from the same object is successively acquired M times. As a result, we obtain M partial signals in k-space, from which we form the image of the observed object in the post-processing phase, after signal acquisition has been completed. This paper demonstrates that with proper selection of acquisition parameters and weighting coefficients in the post-processing phase, OFF-MRI is equivalent to filtering the signal by finite impulse response filter of length M. It is shown that with M successive acquisitions M−1 off-resonance components can be eliminated (filtered-out) from images, and therefore, only two acquisitions are needed to eliminate one off-resonance components. On the other hand, with OFF-MRI, it is also possible to form the image of an arbitrary off-resonance component by eliminating all other off-resonance components, including the on-resonance component. The proposed OFF-MRI method is suitable for MRI where rapid acquisition is required and elimination of off-resonance components can improve reliability of measurements. [Copyright &y& Elsevier]

Abstract: Current efficient magnetic resonance imaging (MRI) methods such as parallel-imaging and k−t methods encode MR signals using a set of effective encoding functions other than the Fourier basis. This work revisits the proposition of directly manipulating the set of effective encoding functions at the radiofrequency excitation step in order to increase MRI efficiency. This approach, often termed “broadband encoding,” enables the application of algebraic matrix factorization technologies to extract efficiency by representing and encoding MR signal content in a compacted form. Broadband imaging equivalents of fast multiecho, parallel and k−t MRI are developed and analyzed. The potential of these techniques to increase the time efficiency of data acquisition is experimentally verified on a commercial MRI scanner using simple spin-echo imaging. A three-dimensional gradient-echo dynamic imaging application that demonstrates the potential benefits of this approach compared to the present state of the art for certain applications is also presented. [Copyright &y& Elsevier]

Abstract: Combining fast MR acquisition sequences and high resolution imaging is a major issue in dynamic imaging. Reducing the acquisition time can be achieved by using non-Cartesian and sparse acquisitions. The reconstruction of MR images from these measurements is generally carried out using gridding that interpolates the missing data to obtain a dense Cartesian k-space filling. The MR image is then reconstructed using a conventional fast Fourier transform (FFT). The estimation of the missing data unavoidably introduces artifacts in the image that remain difficult to quantify. A general reconstruction method is proposed to take into account these limitations. It can be applied to any sampling trajectory in k-space, Cartesian or not, and specifically takes into account the exact location of the measured data, without making any interpolation of the missing data in k-space. Information about the expected characteristics of the imaged object is introduced to preserve the spatial resolution and improve the signal-to-noise ratio in a regularization framework. The reconstructed image is obtained by minimizing a non-quadratic convex objective function. An original rewriting of this criterion is shown to strongly improve the reconstruction efficiency. Results on simulated data and on a real spiral acquisition are presented and discussed. [Copyright &y& Elsevier]

Abstract: Sensitivity-encoded phase undersampling has been combined with simultaneous slice excitation to produce a parallel MRI method with a high volumetric acquisition acceleration factor without the need for auxiliary stepped field coils. Dual-slice excitation was produced by modulating both spin and gradient echo sequences at ±6 kHz. Frequency aliasing of simultaneously excited slices was prevented by using an additional gradient applied along the slice axis during data acquisition. Data were acquired using a four-channel receiver array and ×4 sensitivity encoding on a 1.5 T MR system. The simultaneous parallel inclined readout image technique has been successfully demonstrated in both phantoms and volunteers. A multiplicative image acquisition acceleration factor of up to ×8 was achieved. Image SNR and resolution was dependent on the ratio of the readout gradient to the additional slice gradient. A ratio of approximately 2:1 produced acceptable image quality. Use of RF pulses with additional excitation bands should enable the technique to be extended to volumetric acquisition acceleration factors in the range of ×16–24 without the SNR limitations of pure partially parallel phase reduction methods. [Copyright &y& Elsevier]

Abstract: With the proposed fast frequency selective MR imaging (FFSMRI) method, we focused on the elimination of all off-resonance components from the image of the observed object. To maintain imaging speed and simultaneously achieve good frequency selectivity, MRI was divided into two steps: signal acquisition and postprocessing. After the preliminary phase in which we determine imaging parameters, MRI takes place; the signal from the same object is successively acquired M times. As a result, we obtain M partial signals in k-space, from which we calculate the image of the observed object in postprocessing phase, after signal acquisition has been completed. With proper selection of parameters, it is possible to exclude from the image a majority of off-resonance components present in the observed object. However, we can decide to keep only a chosen off-resonance component in the image and eliminate all other components, including the on-resonance component and thus producing a different image from the same acquisition. The experiments with Fe(OH)3 and oil showed that signal-to-noise ratio (SNR) can be improved by about a factor of four. The proposed FFSMRI method is suitable for frequency selective MR imaging and quantitative measurements in dynamic MRI where exclusion of off-resonance components can improve the reliability of measurement. [Copyright &y& Elsevier]