Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning.

OBJECT: Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality. MATERIALS AND METHODS: An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data. RESULTS: Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%. DISCUSSION: Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.

Deep learning intravoxel incoherent motion modeling: Exploring the impact of training features and learning strategies.

PURPOSE: The development of advanced estimators for intravoxel incoherent motion (IVIM) modeling is often motivated by a desire to produce smoother parameter maps than least squares (LSQ). Deep neural networks show promise to this end, yet performance may be conditional on a myriad of choices regarding the learning strategy. In this work, we have explored potential impacts of key training features in unsupervised and supervised learning for IVIM model fitting. METHODS: Two synthetic data sets and one in-vivo data set from glioma patients were used in training of unsupervised and supervised networks for assessing generalizability. Network stability for different learning rates and network sizes was assessed in terms of loss convergence. Accuracy, precision, and bias were assessed by comparing estimations against ground truth after using different training data (synthetic and in vivo). RESULTS: A high learning rate, small network size, and early stopping resulted in sub-optimal solutions and correlations in fitted IVIM parameters. Extending training beyond early stopping resolved these correlations and reduced parameter error. However, extensive training resulted in increased noise sensitivity, where unsupervised estimates displayed variability similar to LSQ. In contrast, supervised estimates demonstrated improved precision but were strongly biased toward the mean of the training distribution, resulting in relatively smooth, yet possibly deceptive parameter maps. Extensive training also reduced the impact of individual hyperparameters. CONCLUSION: Voxel-wise deep learning for IVIM fitting demands sufficiently extensive training to minimize parameter correlation and bias for unsupervised learning, or demands a close correspondence between the training and test sets for supervised learning.

Multiple-echo steady-state (MESS): Extending DESS for joint T2 mapping and chemical-shift corrected water-fat separation.

PURPOSE: To extend the double echo steady-state (DESS) sequence to enable chemical-shift corrected water-fat separation. METHODS: This study proposes multiple-echo steady-state (MESS), a sequence that modifies the readouts of the DESS sequence to acquire two echoes each with bipolar readout gradients with higher readout bandwidth. This enables water-fat separation and eliminates the need for water-selective excitation that is often used in combination with DESS, without increasing scan time. An iterative fitting approach was used to perform joint chemical-shift corrected water-fat separation and T2 estimation on all four MESS echoes simultaneously. MESS and water-selective DESS images were acquired for five volunteers, and were compared qualitatively as well as quantitatively on cartilage T2 and thickness measurements. Signal-to-noise ratio (SNR) and T2 quantification were evaluated numerically using pseudo-replications of the acquisition. RESULTS: The water-fat separation provided by MESS was robust and with quality comparable to water-selective DESS. MESS T2 estimation was similar to DESS, albeit with slightly higher variability. Noise analysis showed that SNR in MESS was comparable to DESS on average, but did exhibit local variations caused by uncertainty in the water-fat separation. CONCLUSION: In the same acquisition time as DESS, MESS provides water-fat separation with comparable SNR in the reconstructed water and fat images. By providing additional image contrasts in addition to the water-selective DESS images, MESS provides a promising alternative to DESS.

Deep learning-based MR-to-CT synthesis: The influence of varying gradient echo-based MR images as input channels.

PURPOSE: To study the influence of gradient echo-based contrasts as input channels to a 3D patch-based neural network trained for synthetic CT (sCT) generation in canine and human populations. METHODS: Magnetic resonance images and CT scans of human and canine pelvic regions were acquired and paired using nonrigid registration. Magnitude MR images and Dixon reconstructed water, fat, in-phase and opposed-phase images were obtained from a single T1 -weighted multi-echo gradient-echo acquisition. From this set, 6 input configurations were defined, each containing 1 to 4 MR images regarded as input channels. For each configuration, a UNet-derived deep learning model was trained for synthetic CT generation. Reconstructed Hounsfield unit maps were evaluated with peak SNR, mean absolute error, and mean error. Dice similarity coefficient and surface distance maps assessed the geometric fidelity of bones. Repeatability was estimated by replicating the training up to 10 times. RESULTS: Seventeen canines and 23 human subjects were included in the study. Performance and repeatability of single-channel models were dependent on the TE-related water-fat interference with variations of up to 17% in mean absolute error, and variations of up to 28% specifically in bones. Repeatability, Dice similarity coefficient, and mean absolute error were statistically significantly better in multichannel models with mean absolute error ranging from 33 to 40 Hounsfield units in humans and from 35 to 47 Hounsfield units in canines. CONCLUSION: Significant differences in performance and robustness of deep learning models for synthetic CT generation were observed depending on the input. In-phase images outperformed opposed-phase images, and Dixon reconstructed multichannel inputs outperformed single-channel inputs.

Reducing distortions in echo-planar breast imaging at ultrahigh field with high-resolution off-resonance maps.

PURPOSE: DWI is a promising modality in breast MRI, but its clinical acceptance is slow. Analysis of DWI is hampered by geometric distortion artifacts, which are caused by off-resonant spins in combination with the low phase-encoding bandwidth of the EPI sequence used. Existing correction methods assume smooth off-resonance fields, which we show to be invalid in the human breast, where high discontinuities arise at tissue interfaces. METHODS: We developed a distortion correction method that incorporates high-resolution off-resonance maps to better solve for severe distortions at tissue interfaces. The method was evaluated quantitatively both ex vivo in a porcine tissue phantom and in vivo in 5 healthy volunteers. The added value of high-resolution off-resonance maps was tested using a Wilcoxon signed rank test comparing the quantitative results obtained with a low-resolution off-resonance map with those obtained with a high-resolution map. RESULTS: Distortion correction using low-resolution off-resonance maps corrected most of the distortions, as expected. Still, all quantitative comparison metrics showed increased conformity between the corrected EPI images and a high-bandwidth reference scan for both the ex vivo and in vivo experiments. All metrics showed a significant improvement when a high-resolution off-resonance map was used (P < 0.05), in particular at tissue boundaries. CONCLUSION: The use of off-resonance maps of a resolution higher than EPI scans significantly improves upon existing distortion correction techniques, specifically by superior correction at glandular tissue boundaries.

Fast Fourier-based simulation of off-resonance artifacts in steady-state gradient echo MRI applied to metal object localization.

PURPOSE: To accelerate simulation of off-resonance artifacts in steady-state gradient echo MRI by using fast Fourier transforms and demonstrate its applicability to metal object localization. THEORY AND METHODS: By exploiting the repetitive nature of steady-state pulse sequences it is possible to use fast Fourier transforms to calculate the MR signal. Based on this principle, a method for fast simulation of off-resonance artifacts was designed. The method was validated against Bloch simulations and MRI scans. Its clinical relevance was demonstrated by employing it for template matching-based metal object localization, as applied to a titanium cylinder, an oxidized zirconium knee implant, and gold fiducials. RESULTS: The fast simulations were accurate compared with actual MRI scans of the objects. The differences between the fast simulations and Bloch simulations were minor, while the acceleration scaled linearly with the number of phase-encoding lines. The object localization method accurately localized the various metal objects. CONCLUSION: The proposed simulation methodology provided accurate 3D simulations of off-resonance artifacts with a lower computational complexity than Bloch simulations. The speed of the simulations opens up possibilities in image reconstructions involving off-resonance phenomena that were previously infeasible due to computational limitations, as demonstrated for metal object localization. Magn Reson Med 78:2035-2041, 2017. © 2016 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

MRI-based synthetic CT shows equivalence to conventional CT for the morphological assessment of the hip joint.

This study evaluated the accuracy of synthetic computed tomography (sCT), as compared to CT, for the 3D assessment of the hip morphology. Thirty male patients with asymptomatic hips, referred for magnetic resonance (MR) imaging and CT, were included in this retrospective study. sCT images were generated from three-dimensional radiofrequency-spoiled T1-weighted multi-echo gradient-echo MR images using a commercially available deep learning-enabled software and were compared with CT images through mean error and surface distance computation and by means of eight clinical morphometric parameters relevant for hip care. Parameters included center-edge angle (CEA), sharp angle, acetabular index, extrusion index, femoral head center-to-midline distance, acetabular version (AV), and anterior and posterior acetabular sector angles. They were measured by two senior orthopedic surgeons and a radiologist in-training on CT and sCT images. The reliability and agreement of CT- and sCT-based measurements were assessed using intraclass correlation coefficients (ICCs) for absolute agreement, Bland-Altman plots, and two one-sided tests for equivalence. The surface distance between CT- and sCT-based bone models were on average submillimeter. CT- and sCT-based measurements showed moderate to excellent interobserver and intraobserver correlation (0.56 < ICC < 0.99). In particular, the inter/intraobserver agreements were good for AV (ICC > 0.75). For CEA, the intraobserver agreement was good (ICC > 0.75) and the interobserver agreement was moderate (ICC > 0.69). Limits of agreements were similar between intraobserver CT and intermodal measurements. All measurements were found statistically equivalent, with average intermodal differences within the intraobserver limits of agreement. In conclusion, sCT and CT were equivalent for the assessment of the hip joint bone morphology.

CT to MR registration of complex deformations in the knee joint through dual quaternion interpolation of rigid transforms.

Purpose.To develop a method that enables computed tomography (CT) to magnetic resonance (MR) image registration of complex deformations typically encountered in rotating joints such as the knee joint.Methods.We propose a workflow, denoted quaternion interpolated registration (QIR), consisting of three steps, which makes use of prior knowledge of tissue properties to initialise deformable registration. In the first step, the rigid skeletal components were individually registered. Next, the deformation of soft tissue was estimated using a dual quaternion-based interpolation method. In the final step, the registration was fine-tuned with a rigidity-constrained deformable registration step. The method was applied to paired, unregistered CT and MR images of the knee of 92 patients. It was compared to registration using B-Splines (BS) and B-Splines with a rigidity penalty (BSRP). Registration accuracy was evaluated using mutual information, and by calculating Dice similarity coefficient (DSC), mean absolute surface distance (MASD) and 95th percentile Hausdorff distance (HD95) on bone, and DSC on water and fat dominated tissue. To evaluate the rigidity of bone in the registration, the Jacobian determinant (JD) was calculated.Results.QIR achieved improved results with 0.93, 0.76 mm and 1.88 mm on the DSC, MASD and HD95 metrics on bone, compared to 0.87, 1.40 mm and 4.99 mm for method and 0.87, 1.40 mm and 3.56 mm for the BSRP method. The average DSC of water and fat was 0.77 and 0.86 for the QIR, 0.75 and 0.84 for BS and 0.74 and 0.84 for BSRP. Comparison of the median JD and median interquartile (IQR) ranges of the JD indicated that the QIR (1.00 median, 0.03 IQR) resulted in higher rigidity in the rigid skeletal tissues compared to the BS (0.98 median, 0.19 IQR) and BSRP (1.00 median, 0.05 IQR) methods.Conclusion.This study showed that QIR could improve the outcome of complex registration problems, encountered in joints involving rigid and non-rigid bodies such as occur in the knee, as compared to a conventional registration approach.

3D-printed saw guides for lower arm osteotomy, a comparison between a synthetic CT and CT-based workflow.

BACKGROUND: Three-dimensional (3D)-printed saw guides are frequently used to optimize osteotomy results and are usually designed based on computed tomography (CT), despite the radiation burden, as radiation-less alternatives like magnetic resonance imaging (MRI) have inferior bone visualization capabilities. This study investigated the usability of MR-based synthetic-CT (sCT), a novel radiation-less bone visualization technique for 3D planning and design of patient-specific saw guides. METHODS: Eight human cadaveric lower arms (mean age: 78y) received MRI and CT scans as well as high-resolution micro-CT. From the MRI scans, sCT were generated using a conditional generative adversarial network. Digital 3D bone surface models based on the sCT and general CT were compared to the surface model from the micro-CT that was used as ground truth for image resolution. From both the sCT and CT digital bone models saw guides were designed and 3D-printed in nylon for one proximal and one distal bone position for each radius and ulna. Six blinded observers placed these saw guides as accurately as possible on dissected bones. The position of each guide was assessed by optical 3D-scanning of each bone with positioned saw guide and compared to the preplanning. Eight placement errors were evaluated: three translational errors (along each axis), three rotational errors (around each axis), a total translation (∆T) and a total rotation error (∆R). RESULTS: Surface models derived from micro-CT were on average smaller than sCT and CT-based models with average differences of 0.27 ± 0.30 mm for sCT and 0.24 ± 0.12 mm for CT. No statistically significant positioning differences on the bones were found between sCT- and CT-based saw guides for any axis specific translational or rotational errors nor between the ∆T (p = .284) and ∆R (p = .216). On Bland-Altman plots, the ∆T and ∆R limits of agreement (LoA) were within the inter-observer variability LoA. CONCLUSIONS: This research showed a similar error for sCT and CT digital surface models when comparing to ground truth micro-CT models. Additionally, the saw guide study showed equivalent CT- and sCT-based saw guide placement errors. Therefore, MRI-based synthetic CT is a promising radiation-less alternative to CT for the creation of patient-specific osteotomy surgical saw guides.

Deep learning-enabled MRI-only photon and proton therapy treatment planning for paediatric abdominal tumours.

PURPOSE: To assess the feasibility of magnetic resonance imaging (MRI)-only treatment planning for photon and proton radiotherapy in children with abdominal tumours. MATERIALS AND METHODS: The study was conducted on 66 paediatric patients with Wilms' tumour or neuroblastoma (age 4 ± 2 years) who underwent MR and computed tomography (CT) acquisition on the same day as part of the clinical protocol. MRI intensities were converted to CT Hounsfield units (HU) by means of a UNet-like neural network trained to generate synthetic CT (sCT) from T1- and T2-weighted MR images. The CT-to-sCT image similarity was evaluated by computing the mean error (ME), mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and Dice similarity coefficient (DSC). Synthetic CT dosimetric accuracy was verified against CT-based dose distributions for volumetric-modulated arc therapy (VMAT) and intensity-modulated pencil-beam scanning (PBS). Relative dose differences (Ddiff) in the internal target volume and organs-at-risk were computed and a three-dimensional gamma analysis (2 mm, 2%) was performed. RESULTS: The average ± standard deviation ME was -5 ± 12 HU, MAE was 57 ± 12 HU, PSNR was 30.3 ± 1.6 dB and DSC was 76 ± 8% for bones and 92 ± 9% for lungs. Average Ddiff were <0.5% for both VMAT (range [-2.5; 2.4]%) and PBS (range [-2.7; 3.7]%) dose distributions. The average gamma pass-rates were >99% (range [85; 100]%) for VMAT and >96% (range [87; 100]%) for PBS. CONCLUSION: The deep learning-based model generated accurate sCT from planning T1w- and T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon and proton radiotherapy, demonstrating the feasibility of an MRI-only workflow for paediatric patients with abdominal tumours.

SMART tracking: Simultaneous anatomical imaging and real-time passive device tracking for MR-guided interventions.

PURPOSE: This study demonstrates a proof of concept of a method for simultaneous anatomical imaging and real-time (SMART) passive device tracking for MR-guided interventions. METHODS: Phase Correlation template matching was combined with a fast undersampled radial multi-echo acquisition using the white marker phenomenon after the first echo. In this way, the first echo provides anatomical contrast, whereas the other echoes provide white marker contrast to allow accurate device localization using fast simulations and template matching. This approach was tested on tracking of five 0.5 mm steel markers in an agarose phantom and on insertion of an MRI-compatible 20 Gauge titanium needle in ex vivo porcine tissue. The locations of the steel markers were quantitatively compared to the marker locations as found on a CT scan of the same phantom. RESULTS: The average pairwise error between the MRI and CT locations was 0.30 mm for tracking of stationary steel spheres and 0.29 mm during motion. Qualitative evaluation of the tracking of needle insertions showed that tracked positions were stable throughout needle insertion and retraction. CONCLUSION: The proposed SMART tracking method provided accurate passive tracking of devices at high framerates, inclusion of real-time anatomical scanning, and the capability of automatic slice positioning. Furthermore, the method does not require specialized hardware and could therefore be applied to track any rigid metal device that causes appreciable magnetic field distortions.

Dosimetric evaluation of synthetic CT for head and neck radiotherapy generated by a patch-based three-dimensional convolutional neural network.

PURPOSE: To develop and evaluate a patch-based convolutional neural network (CNN) to generate synthetic computed tomography (sCT) images for magnetic resonance (MR)-only workflow for radiotherapy of head and neck tumors. A patch-based deep learning method was chosen to improve robustness to abnormal anatomies caused by large tumors, surgical excisions, or dental artifacts. In this study, we evaluate whether the generated sCT images enable accurate MR-based dose calculations in the head and neck region. METHODS: We conducted a retrospective study on 34 patients with head and neck cancer who underwent both CT and MR imaging for radiotherapy treatment planning. To generate the sCTs, a large field-of-view T2-weighted Turbo Spin Echo MR sequence was used from the clinical protocol for multiple types of head and neck tumors. To align images as well as possible on a voxel-wise level, CT scans were nonrigidly registered to the MR (CTreg ). The CNN was based on a U-net architecture and consisted of 14 layers with 3 × 3 × 3 filters. Patches of 48 × 48 × 48 were randomly extracted and fed into the training. sCTs were created for all patients using threefold cross validation. For each patient, the clinical CT-based treatment plan was recalculated on sCT using Monaco TPS (Elekta). We evaluated mean absolute error (MAE) and mean error (ME) within the body contours and dice scores in air and bone mask. Also, dose differences and gamma pass rates between CT- and sCT-based plans inside the body contours were calculated. RESULTS: sCT generation took 4 min per patient. The MAE over the patient population of the sCT within the intersection of body contours was 75 ± 9 Hounsfield Units (HU) (±1 SD), and the ME was 9 ± 11 HU. Dice scores of the air and bone masks (CTreg vs sCT) were 0.79 ± 0.08 and 0.70 ± 0.07, respectively. Dosimetric analysis showed mean deviations of -0.03% ± 0.05% for dose within the body contours and -0.07% ± 0.22% inside the >90% dose volume. Dental artifacts obscuring the CT could be circumvented in the sCT by the CNN-based approach in combination with Turbo Spin Echo (TSE) magnetic resonance imaging (MRI) sequence that typically is less prone to susceptibility artifacts. CONCLUSIONS: The presented CNN generated sCTs from conventional MR images without adding scan time to the acquisition. Dosimetric evaluation suggests that dose calculations performed on the sCTs are accurate, and can therefore be used for MR-only radiotherapy treatment planning of the head and neck.

Challenges in MR-only seed localization for postimplant dosimetry in permanent prostate brachytherapy.

PURPOSE: An MR-only postimplant dosimetry workflow for low dose rate (LDR) brachytherapy could reduce patient burden, improve accuracy, and improve cost efficiency. However, localization of brachytherapy seeds on MRI scans remains a major challenge for this type of workflow. In this study, we propose and validate an MR-only seed localization method and identify remaining challenges. METHODS AND MATERIALS: The localization method was based on template matching of simulations of complex-valued imaging artifacts around metal brachytherapy seeds. The method was applied to MRI scans of 25 prostate cancer patients who underwent LDR brachytherapy and for whom postimplant dosimetry was performed after 4 weeks. The seed locations found with the MR-only method were validated against the seed locations found on CT. The circumstances in which detection errors were made were classified to gain an insight in the nature of the errors. RESULTS: A total of 1490 of 1557 (96%) seeds were correctly detected, while 67 false-positive errors were made. The correctly detected seed locations had a high spatial accuracy with an average error of 0.8 mm compared with CT. A majority of the false positives occurred near other seeds. Most false negatives were found in either stranded configurations without spacers or near other seeds. CONCLUSIONS: The low detection error rate and high localization accuracy obtained by the complex-valued template matching approach are promising for future clinical application of MR-only dosimetry. The most important remaining challenge is robustness with regard to configurations of multiple seeds in close vicinity, such as in strands of seeds without spacers. This issue could potentially be resolved by simulating specific configurations of multiple seeds or by constraining the treatment planning to avoid these configurations, which could make the proposed method competitive with CT-based seed localization.

Evaluation of an automatic MR-based gold fiducial marker localisation method for MR-only prostate radiotherapy.

An MR-only radiotherapy planning (RTP) workflow would reduce the cost, radiation exposure and uncertainties introduced by CT-MRI registrations. In the case of prostate treatment, one of the remaining challenges currently holding back the implementation of an RTP workflow is the MR-based localisation of intraprostatic gold fiducial markers (FMs), which is crucial for accurate patient positioning. Currently, MR-based FM localisation is clinically performed manually. This is sub-optimal, as manual interaction increases the workload. Attempts to perform automatic FM detection often rely on being able to detect signal voids induced by the FMs in magnitude images. However, signal voids may not always be sufficiently specific, hampering accurate and robust automatic FM localisation. Here, we present an approach that aims at automatic MR-based FM localisation. This method is based on template matching using a library of simulated complex-valued templates, and exploiting the behaviour of the complex MR signal in the vicinity of the FM. Clinical evaluation was performed on seventeen prostate cancer patients undergoing external beam radiotherapy treatment. Automatic MR-based FM localisation was compared to manual MR-based and semi-automatic CT-based localisation (the current gold standard) in terms of detection rate and the spatial accuracy and precision of localisation. The proposed method correctly detected all three FMs in 15/17 patients. The spatial accuracy (mean) and precision (STD) were 0.9 mm and 0.5 mm respectively, which is below the voxel size of [Formula: see text] mm3 and comparable to MR-based manual localisation. FM localisation failed (3/51 FMs) in the presence of bleeding or calcifications in the direct vicinity of the FM. The method was found to be spatially accurate and precise, which is essential for clinical use. To overcome any missed detection, we envision the use of the proposed method along with verification by an observer. This will result in a semi-automatic workflow facilitating the introduction of an MR-only workflow.

Evaluation of Variable Density and Data-Driven K-Space Undersampling for Compressed Sensing Magnetic Resonance Imaging.

OBJECTIVES: The aim of this study was to investigate the influence of variable density and data-driven k-space undersampling patterns on reconstruction quality for compressed sensing (CS) magnetic resonance imaging to provide recommendations on how to avoid suboptimal CS reconstructions. MATERIALS AND METHODS: First, we investigated the influence of randomness and sampling density on the reconstruction quality when using random variable density and variable density Poisson disk undersampling. Compressed sensing reconstructions on 1 knee and 2 brain data sets were compared with fully sampled data sets and reconstruction errors were measured. Sampling coherence was evaluated on the undersampling patterns to investigate whether there was a relation between this coherence measure and reconstruction error.Second, we investigated whether data-driven undersampling methods could improve reconstruction quality when 1 or more fully sampled scans are available as a training set. We implemented 3 different data-driven undersampling methods: (1) Monte Carlo optimization of variable density and variable density Poisson disk undersampling, (2) calculating sampling probabilities directly from the k-space power spectra of the training data, and (3) iterative design of undersampling patterns based on CS reconstruction errors in k-space.Two cross-validation experiments were set up using retrospective undersampling to evaluate the 3 data-driven methods and the influence of the size of the training set. Furthermore, in an experiment that included prospective under sampling, we show the practical applicability of 2 of the data-driven methods. Compressed sensing reconstruction quality was measured with both the normalized root-mean-square error metric and the mean structural similarity index measure. RESULTS: Different optimal variable sampling densities were found for each of the data sets, showing that the optimal sampling density is data dependent. Choosing a sampling density other than the optimal density decreased reconstruction quality. These results suggest that choosing a sampling density without having any reference scans is likely suboptimal. Furthermore, no meaningful correlation was found between sampling coherence and reconstruction error.For the data-driven methods, the iterative method yielded statistically significantly higher reconstruction quality in both retrospective and prospective experiments. In retrospective experiments, the power spectrum method yielded a reconstruction quality that was comparable with the data-driven variable density method. The size of the training set had only a minor influence on the reconstruction quality. CONCLUSIONS: Data-driven undersampling methods can be used to avoid suboptimal reconstruction quality in CS magnetic resonance imaging, provided that at least 1 fully sampled scan is available to train the data-driven method. The iterative design method resulted in the highest reconstruction quality.

Geometrically undistorted MRI in the presence of field inhomogeneities using compressed sensing accelerated broadband 3D phase encoded turbo spin-echo imaging.

In this study, we explore the potential of compressed sensing (CS) accelerated broadband 3D phase-encoded turbo spin-echo (3D-PE-TSE) for the purpose of geometrically undistorted imaging in the presence of field inhomogeneities. To achieve this goal 3D-PE-SE and 3D-PE-TSE sequences with broadband rf pulses and dedicated undersampling patterns were implemented on a clinical scanner. Additionally, a 3D multi-spectral spin-echo (ms3D-SE) sequence was implemented for reference purposes. First, we demonstrated the influence of susceptibility induced off-resonance effects on the spatial encoding of broadband 3D-SE, ms3D-SE, 3D-PE-SE and 3D-PE-TSE using a grid phantom containing a titanium implant (Δχ = 182 ppm) with x-ray CT as a gold standard. These experiments showed that the spatial encoding of 3D-PE-(T)SE was unaffected by susceptibility induced off-resonance effects, which caused geometrical distortions and/or signal hyper-intensities in broadband 3D-SE and, to a lesser extent, in ms3D-SE frequency encoded methods. Additionally, an SNR analysis was performed and the temporally resolved signal of 3D-PE-(T)SE sequences was exploited to retrospectively decrease the acquisition bandwidth and obtain field offset maps. The feasibility of CS acceleration was studied retrospectively and prospectively for the 3D-PE-SE sequence using an existing CS algorithm adapted for the reconstruction of 3D data with undersampling in all three phase encoded dimensions. CS was combined with turbo-acceleration by variable density undersampling and spherical stepwise T2 weighting by randomly sorting consecutive echoes in predefined spherical k-space layers. The CS-TSE combination resulted in an overall acceleration factor of 60, decreasing the original 3D-PE-SE scan time from 7 h to 7 min. Finally, CS accelerated 3D-PE-TSE in vivo images of a titanium screw were obtained within 10 min using a micro-coil demonstrating the feasibility of geometrically undistorted MRI near severe field inhomogeneities.

Multiple single-point imaging (mSPI) as a tool for capturing and characterizing MR signals and repetitive signal disturbances with high temporal resolution: the MRI scanner as a high-speed camera.

In this paper we aim to lay down and demonstrate the use of multiple single-point imaging (mSPI) as a tool for capturing and characterizing steady-state MR signals and repetitive disturbances thereof with high temporal resolution. To achieve this goal, various 2D mSPI sequences were derived from the nearest standard 3D imaging sequences by (i) replacing the excitation of a 3D slab by the excitation of a 2D slice orthogonal to the read axis, (ii) setting the readout gradient to zero, and (iii) leaving out the inverse Fourier transform in the read direction. The thus created mSPI sequences, albeit slow with regard to the spatial encoding part, were shown to result into a series of densely spaced 2D single-point images in the time domain enabling monitoring of the evolution of the magnetization with a high temporal resolution and without interference from any encoding gradients. The high-speed capabilities of mSPI were demonstrated by capturing and characterizing the free induction decays and spin echoes of substances with long T2s (>30 ms) and long and short T2*s (4 - >30 ms) and by monitoring the perturbation of the transverse magnetization by, respectively, a titanium cylinder, representing a static disturbance; a pulsed magnetic field gradient, representing a stimulus inherent to a conventional MRI experiment; and a pulsed electric current, representing an external stimulus. The results of the study indicate the potential of mSPI for assessing the evolution of the magnetization and, when properly synchronized with the acquisition, repeatable disturbances thereof with a temporal resolution that is ultimately limited by the bandwidth of the receiver, but in practice governed by the SNR of the experiment and the magnitude of the disturbance. Potential applications of mSPI can be envisaged in research areas that are concerned with MR signal behavior, MR system performance and MR evaluation of magnetically evoked responses.