FastMRI Prostate: A public, biparametric MRI dataset to advance machine learning for prostate cancer imaging.

Magnetic resonance imaging (MRI) has experienced remarkable advancements in the integration of artificial intelligence (AI) for image acquisition and reconstruction. The availability of raw k-space data is crucial for training AI models in such tasks, but public MRI datasets are mostly restricted to DICOM images only. To address this limitation, the fastMRI initiative released brain and knee k-space datasets, which have since seen vigorous use. In May 2023, fastMRI was expanded to include biparametric (T2- and diffusion-weighted) prostate MRI data from a clinical population. Biparametric MRI plays a vital role in the diagnosis and management of prostate cancer. Advances in imaging methods, such as reconstructing under-sampled data from accelerated acquisitions, can improve cost-effectiveness and accessibility of prostate MRI. Raw k-space data, reconstructed images and slice, volume and exam level annotations for likelihood of prostate cancer are provided in this dataset for 47468 slices corresponding to 1560 volumes from 312 patients. This dataset facilitates AI and algorithm development for prostate image reconstruction, with the ultimate goal of enhancing prostate cancer diagnosis.

Impact of fat on the apparent T1 value of the liver: assessment by water-only derived T1 mapping.

OBJECTIVES: To determine the impact of fat on the apparent T1 value of the liver using water-only derived T1 mapping. METHODS: 3-T MRI included 2D Look-Locker T1 mapping and proton density fat fraction (PDFF) mapping. T1 values of the liver were compared among T1 maps obtained by in-phase (IP), opposed-phase (OP), and Dixon water sequences using paired t-test. The correlation between T1 values of the liver on each T1 map and PDFF was assessed using Spearman correlation coefficient. The absolute differences between T1 value of the liver on Dixon water images and that on IP or OP images were also correlated with PDFF. RESULTS: One hundred sixty-two patients (median age, 70 [range, 24-91] years, 90 men) were retrospectively evaluated. The T1 values of the liver on each T1 map were significantly different (p < 0.001). The T1 value of the liver on IP images was significantly negatively correlated with PDFF (r = - 0.438), while the T1 value of the liver on OP images was slightly positively correlated with PDFF (r = 0.164). The T1 value of the liver on Dixon water images was slightly negatively correlated with PDFF (r = - 0.171). The absolute differences between T1 value of the liver on Dixon water images and that on IP or OP images were significantly correlated with PDFF (r = 0.606, 0.722; p < 0.001). CONCLUSION: Fat correction for the apparent T1 value by water-only derived T1 maps will be helpful for accurately evaluating the T1 value of the liver. CLINICAL RELEVANCE STATEMENT: Fat-corrected T1 mapping of the liver with the water component only obtained from the 2D Dixon Look-Locker sequence could be useful for accurately evaluating the T1 value of the liver without the impact of fat in daily clinical practice. KEY POINTS: • The T1 values of the liver on the conventional T1 maps are significantly affected by the presence of fat. • The apparent T1 value of the liver on water-only derived T1 maps would be slightly impacted by the presence of fat. • Fat correction for the apparent T1 values is necessary for the accurate assessment of the T1 values of the liver.

Optimizing variable flip angles in magnetization-prepared gradient-echo sequences for efficient 3D-T1ρ mapping.

PURPOSE: To optimize the choice of the flip angles of magnetization-prepared gradient-echo sequences for improved accuracy, precision, and speed of 3D-T1ρ mapping. METHODS: We propose a new optimization approach for finding variable flip-angle values that improve magnetization-prepared gradient-echo sequences used for 3D-T1ρ mapping. This new approach can improve the accuracy and SNR, while reducing filtering effects. We demonstrate the concept in the three different versions of the magnetization-prepared gradient-echo sequences that are typically used for 3D-T1ρ mapping and evaluate their performance in model agarose phantoms (n = 4) and healthy volunteers (n = 5) for knee joint imaging. We also tested the optimization with sequence parameters targeting faster acquisitions. RESULTS: Our results show that optimized variable flip angle can improve the accuracy and the precision of the sequences, seen as a reduction of the mean of normalized absolute difference from about 5%-6% to 3%-4% in model phantoms and from 15%-16% to 11%-13% in the knee joint, and improving SNR from about 12-28 to 22-32 in agarose phantoms and about 7-14 to 13-17 in healthy volunteers. The optimization can also compensate for the loss in quality caused by making the sequence faster. This results in sequence configurations that acquire more data per unit of time with SNR and mean of normalized absolute difference measurements close to its slower versions. CONCLUSION: The optimization of the variable flip angle can be used to increase accuracy and precision, and to improve the speed of the typical imaging sequences used for quantitative 3D-T1ρ mapping of the knee joint.

FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging.

The fastMRI brain and knee dataset has enabled significant advances in exploring reconstruction methods for improving speed and image quality for Magnetic Resonance Imaging (MRI) via novel, clinically relevant reconstruction approaches. In this study, we describe the April 2023 expansion of the fastMRI dataset to include biparametric prostate MRI data acquired on a clinical population. The dataset consists of raw k-space and reconstructed images for T2-weighted and diffusion-weighted sequences along with slice-level labels that indicate the presence and grade of prostate cancer. As has been the case with fastMRI, increasing accessibility to raw prostate MRI data will further facilitate research in MR image reconstruction and evaluation with the larger goal of improving the utility of MRI for prostate cancer detection and evaluation. The dataset is available at https://fastmri.med.nyu.edu.

Comparison of a Deep Learning-Accelerated vs. Conventional T2-Weighted Sequence in Biparametric MRI of the Prostate.

BACKGROUND: Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2-weighted imaging (T2WI). PURPOSE: To compare conventional bpMRIs (CL-bpMRI) with bpMRIs including a deep learning-accelerated T2WI (DL-bpMRI) in diagnosing prostate cancer. STUDY TYPE: Retrospective. POPULATION: Eighty consecutive men, mean age 66 years (47-84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow-up included prostate biopsy or stability of prostate-specific antigen (PSA) for 1 year. FIELD STRENGTH AND SEQUENCES: A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL-T2), 3-fold deep learning-accelerated axial and coronal T2-weighted sequence (DL-T2), diffusion weighted imaging (DWI) with b = 50 sec/mm2 , 1000 sec/mm2 , calculated b = 1500 sec/mm2 . ASSESSMENT: CL-bpMRI and DL-bpMRI including the same conventional diffusion-weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer-assisted detection algorithm (DL-CAD). The readers evaluated image quality using a 4-point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI-RADS) v2.1. DL-CAD identified and assigned lesions of PI-RADS 3 or greater. STATISTICAL TESTS: Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test. SIGNIFICANCE: P = 0.05. RESULTS: Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL-T2, DL-T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (P = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (P = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient-based analysis, the reader results of AUC are (CL-bpMRI, DL-bpMRI): reader 1: 0.77, 0.78 (P = 0.98), reader 2: 0.65, 0.66 (P = 0.99), reader 3: 0.57, 0.60 (P = 0.52). Diagnostic statistics from DL-CAD (CL-bpMRI, DL-bpMRI) are sensitivity (0.71, 0.71, P = 1.00), specificity (0.59, 0.44, P = 0.05), positive predictive value (0.23, 0.24, P = 0.25), negative predictive value (0.88, 0.88, P = 0.48). CONCLUSION: Deep learning-accelerated T2-weighted imaging may potentially be used to decrease acquisition time for bpMRI. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Modern Low-Field MRI of the Musculoskeletal System: Practice Considerations, Opportunities, and Challenges.

ABSTRACT: Magnetic resonance imaging (MRI) provides essential information for diagnosing and treating musculoskeletal disorders. Although most musculoskeletal MRI examinations are performed at 1.5 and 3.0 T, modern low-field MRI systems offer new opportunities for affordable MRI worldwide. In 2021, a 0.55 T modern low-field, whole-body MRI system with an 80-cm-wide bore was introduced for clinical use in the United States and Europe. Compared with current higher-field-strength MRI systems, the 0.55 T MRI system has a lower total ownership cost, including purchase price, installation, and maintenance. Although signal-to-noise ratios scale with field strength, modern signal transmission and receiver chains improve signal yield compared with older low-field magnetic resonance scanner generations. Advanced radiofrequency coils permit short echo spacing and overall compacter echo trains than previously possible. Deep learning-based advanced image reconstruction algorithms provide substantial improvements in perceived signal-to-noise ratios, contrast, and spatial resolution. Musculoskeletal tissue contrast evolutions behave differently at 0.55 T, which requires careful consideration when designing pulse sequences. Similar to other field strengths, parallel imaging and simultaneous multislice acquisition techniques are vital for efficient musculoskeletal MRI acquisitions. Pliable receiver coils with a more cost-effective design offer a path to more affordable surface coils and improve image quality. Whereas fat suppression is inherently more challenging at lower field strengths, chemical shift selective fat suppression is reliable and homogeneous with modern low-field MRI technology. Dixon-based gradient echo pulse sequences provide efficient and reliable multicontrast options, including postcontrast MRI. Metal artifact reduction MRI benefits substantially from the lower field strength, including slice encoding for metal artifact correction for effective metal artifact reduction of high-susceptibility metallic implants. Wide-bore scanner designs offer exciting opportunities for interventional MRI. This review provides an overview of the economical aspects, signal and image quality considerations, technological components and coils, musculoskeletal tissue relaxation times, and image contrast of modern low-field MRI and discusses the mainstream and new applications, challenges, and opportunities of musculoskeletal MRI.

Low-field 0.55 T MRI for assessment of pulmonary groundglass and fibrosis-like opacities: Inter-reader and inter-modality concordance.

PURPOSE: To evaluate detection and characterization of groundglass and fibrosis-like opacities imaged by non-contrast 0.55 Tesla MRI, and versus clinically-acquired chest CT images, in a cohort of post-Covid patients. MATERIALS AND METHODS: 64 individuals (26 women, mean age 53 ± 14 years, range 19-85) with history of Covid-19 pneumonia were recruited through a survivorship registry, with 106 non-contrast low-field 0.55 T cardiopulmonary MRI exams acquired from 9/8/2020-9/28/2021. MRI exams were obtained at an average interval of 9.5 ± 4.5 months from initial symptom report (range 1-18 months). Of these, 20 participants with 22 MRI exams had corresponding clinically-acquired CT chest imaging obtained within 30 days of MRI (average interval 18 ± 9 days, range 0-30). MR and CT images were reviewed and scored by two thoracic radiologists, for presence and extent of lung opacity by quadrant, opacity distribution, and presence versus absence of fibrosis-like subpleural reticulation and subpleural lines. Scoring was performed for each of four lung quadrants: right upper and middle lobe, right lower lobe, left upper lobe and lingula, and left lower lobe. Agreement between readers and modalities was assessed with simple and linear weighted Cohen's kappa (k) coefficients. RESULTS: Inter-reader concordance on CT for opacity presence, opacity extent, opacity distribution, and presence of subpleural lines and reticulation was 99%, 78%, 97%, 99%, and 94% (k 0.96, 0.86, 0.94, 0.97, 0.89), respectively. Inter-reader concordance on MR, among all 106 exams, for opacity presence, opacity extent, opacity distribution, and presence of subpleural lines and reticulation was 85%, 48%, 70%, 86%, and 76% (k 0.57, 0.32, 0.46, 0.47, 0.37), respectively. Inter-modality agreement between CT and MRI for opacity presence, opacity extent, opacity distribution, and presence subpleural lines and reticulation was 86%, 52%, 79%, 93%, and 76% (k 0.43, 0.63, 0.65, 0.80, 0.52). CONCLUSION: Low-field 0.55 T non-contrast MRI demonstrates fair to moderate inter-reader concordance, and moderate to substantial inter-modality agreement with CT, for detection and characterization of groundglass and fibrosis-like opacities.

New-Generation Low-Field Magnetic Resonance Imaging of Hip Arthroplasty Implants Using Slice Encoding for Metal Artifact Correction: First In Vitro Experience at 0.55 T and Comparison With 1.5 T.

OBJECTIVES: Despite significant progress, artifact-free visualization of the bone and soft tissues around hip arthroplasty implants remains an unmet clinical need. New-generation low-field magnetic resonance imaging (MRI) systems now include slice encoding for metal artifact correction (SEMAC), which may result in smaller metallic artifacts and better image quality than standard-of-care 1.5 T MRI. This study aims to assess the feasibility of SEMAC on a new-generation 0.55 T system, optimize the pulse protocol parameters, and compare the results with those of a standard-of-care 1.5 T MRI. MATERIALS AND METHODS: Titanium (Ti) and cobalt-chromium total hip arthroplasty implants embedded in a tissue-mimicking American Society for Testing and Materials gel phantom were evaluated using turbo spin echo, view angle tilting (VAT), and combined VAT and SEMAC (VAT + SEMAC) pulse sequences. To refine an MRI protocol at 0.55 T, the type of metal artifact reduction techniques and the effect of various pulse sequence parameters on metal artifacts were assessed through qualitative ranking of the images by 3 expert readers while taking measured spatial resolution, signal-to-noise ratios, and acquisition times into consideration. Signal-to-noise ratio efficiency and artifact size of the optimized 0.55 T protocols were compared with the 1.5 T standard and compressed-sensing SEMAC sequences. RESULTS: Overall, the VAT + SEMAC sequence with at least 6 SEMAC encoding steps for Ti and 9 for cobalt-chromium implants was ranked higher than other sequences for metal reduction ( P < 0.05). Additional SEMAC encoding partitions did not result in further metal artifact reductions. Permitting minimal residual artifacts, low magnetic susceptibility Ti constructs may be sufficiently imaged with optimized turbo spin echo sequences obviating the need for SEMAC. In cross-platform comparison, 0.55 T acquisitions using the optimized protocols are associated with 45% to 64% smaller artifacts than 1.5 T VAT + SEMAC and VAT + compressed-sensing/SEMAC protocols at the expense of a 17% to 28% reduction in signal-to-noise ratio efficiency. B 1 -related artifacts are invariably smaller at 0.55 T than 1.5 T; however, artifacts related to B 0 distortion, although frequently smaller, may appear as signal pileups at 0.55 T. CONCLUSIONS: Our results suggest that new-generation low-field SEMAC MRI reduces metal artifacts around hip arthroplasty implants to better advantage than current 1.5 T MRI standard of care. While the appearance of B 0 -related artifacts changes, reduction in B 1 -related artifacts plays a major role in the overall benefit of 0.55 T.

Abdominal T2-Weighted Imaging and T2 Mapping Using a Variable Flip Angle Radial Turbo Spin-Echo Technique.

BACKGROUND: T2 mapping is of great interest in abdominal imaging but current methods are limited by low resolution, slice coverage, motion sensitivity, or lengthy acquisitions. PURPOSE: Develop a radial turbo spin-echo technique with refocusing variable flip angles (RADTSE-VFA) for high spatiotemporal T2 mapping and efficient slice coverage within a breath-hold and compare to the constant flip angle counterpart (RADTSE-CFA). STUDY TYPE: Prospective technical efficacy. SUBJECTS: Testing performed on agarose phantoms and 12 patients. Focal liver lesion classification tested on malignant (N = 24) and benign (N = 11) lesions. FIELD STRENGTH/SEQUENCE: 1.5 T/RADTSE-VFA, RADTSE-CFA. ASSESSMENT: A constrained objective function was used to optimize the refocusing flip angles. Phantom and/or in vivo data were used to assess relative contrast, T2 estimation, specific absorption rate (SAR), and focal liver lesion classification. STATISTICAL TESTS: t-Tests or Mann-Whitney Rank Sum tests were used. RESULTS: Phantom data did not show significant differences in mean relative contrast (P = 0.10) and T2 accuracy (P = 0.99) between RADTSE-VFA and RADTSE-CFA. Adding noise caused T2 overestimation predominantly for RADTSE-CFA and low T2 values. In vivo results did not show significant differences in mean spleen-to-liver (P = 0.62) and kidney-to-liver (P = 0.49) relative contrast between RADTSE-VFA and RADTSE-CFA. Mean T2 values were not significantly different between the two techniques for spleen (T2VFA  = 109.2 ± 12.3 msec; T2CFA  = 110.7 ± 11.1 msec; P = 0.78) and kidney-medulla (T2VFA  = 113.0 ± 8.7 msec; T2CFA  = 114.0 ± 8.6 msec; P = 0.79). Liver T2 was significantly higher for RADTSE-CFA (T2VFA  = 52.6 ± 6.6 msec; T2CFA  = 60.4 ± 8.0 msec) consistent with T2 overestimation in the phantom study. Focal liver lesion classification had comparable T2 distributions for RADTSE-VFA and RADTSE-CFA for malignancies (P = 1.0) and benign lesions (P = 0.39). RADTSE-VFA had significantly lower SAR than RADTSE-CFA increasing slice coverage by 1.5. DATA CONCLUSION: RADTSE-VFA provided noise-robust T2 estimation compared to the constant flip angle counterpart while generating T2-weighted images with comparable contrast. The VFA scheme minimized SAR improving slice efficiency for breath-hold imaging. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 1.

Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate.

BACKGROUND: Early diagnosis and treatment of prostate cancer (PCa) can be curative; however, prostate-specific antigen is a suboptimal screening test for clinically significant PCa. While prostate magnetic resonance imaging (MRI) has demonstrated value for the diagnosis of PCa, the acquisition time is too long for a first-line screening modality. PURPOSE: To accelerate prostate MRI exams, utilizing a variational network (VN) for image reconstruction. STUDY TYPE: Retrospective. SUBJECTS: One hundred and thirteen subjects (train/val/test: 70/13/30) undergoing prostate MRI. FIELD STRENGTH/SEQUENCE: 3.0 T; a T2 turbo spin echo (TSE) T2-weighted image (T2WI) sequence in axial and coronal planes, and axial echo-planar diffusion-weighted imaging (DWI). ASSESSMENT: Four abdominal radiologists evaluated the image quality of VN reconstructions of retrospectively under-sampled biparametric MRIs (bp-MRI), and standard bp-MRI reconstructions for 20 test subjects (studies). The studies included axial and coronal T2WI, DWI B50 seconds/mm2 and B1000 seconds/mm (4-fold T2WI, 3-fold DWI), all of which were evaluated separately for image quality on a Likert scale (1: non-diagnostic to 5: excellent quality). In another 10 test subjects, three readers graded lesions on bp-MRI-which additionally included calculated B1500 seconds/mm2 , and apparent diffusion coefficient map-according to the Prostate Imaging Reporting and Data System (PI-RADS v2.1), for both VN and standard reconstructions. Accuracy of PI-RADS ≥3 for clinically significant cancer was computed. Projected scan time of the retrospectively under-sampled biparametric exam was also computed. STATISTICAL TESTS: One-sided Wilcoxon signed-rank test was used for comparison of image quality. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for lesion detection and grading. Generalized estimating equation with cluster effect was used to compare differences between standard and VN bp-MRI. A P-value of <0.05 was considered statistically significant. RESULTS: Three of four readers rated no significant difference for overall quality between the standard and VN axial T2WI (Reader 1: 4.00 ± 0.56 (Standard), 3.90 ± 0.64 (VN) P = 0.33; Reader 2: 4.35 ± 0.74 (Standard), 3.80 ± 0.89 (VN) P = 0.003; Reader 3: 4.60 ± 0.50 (Standard), 4.55 ± 0.60 (VN) P = 0.39; Reader 4: 3.65 ± 0.99 (Standard), 3.60 ± 1.00 (VN) P = 0.38). All four readers rated no significant difference for overall quality between standard and VN DWI B1000 seconds/mm2 (Reader 1: 2.25 ± 0.62 (Standard), 2.45 ± 0.75 (VN) P = 0.96; Reader 2: 3.60 ± 0.92 (Standard), 3.55 ± 0.82 (VN) P = 0.40; Reader 3: 3.85 ± 0.72 (Standard), 3.55 ± 0.89 (VN) P = 0.07; Reader 4: 4.70 ± 0.76 (Standard); 4.60 ± 0.73 (VN) P = 0.17) and three of four readers rated no significant difference for overall quality between standard and VN DWI B50 seconds/mm2 (Reader 1: 3.20 ± 0.70 (Standard), 3.40 ± 0.75 (VN) P = 0.98; Reader 2: 2.85 ± 0.81 (Standard), 3.00 ± 0.79 (VN) P = 0.93; Reader 3: 4.45 ± 0.72 (Standard), 4.05 ± 0.69 (VN) P = 0.02; Reader 4: 4.50 ± 0.69 (Standard), 4.45 ± 0.76 (VN) P = 0.50). In the lesion evaluation study, there was no significant difference in the number of PI-RADS ≥3 lesions identified on standard vs. VN bp-MRI (P = 0.92, 0.59, 0.87) with similar sensitivity and specificity for clinically significant cancer. The average scan time of the standard clinical biparametric exam was 11.8 minutes, and this was projected to be 3.2 minutes for the accelerated exam. DATA CONCLUSION: Diagnostic accelerated biparametric prostate MRI exams can be performed using deep learning methods in <4 minutes, potentially enabling rapid screening prostate MRI. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 5.

Improving subspace constrained radial fast spin echo MRI using block matching driven non-local low rank regularization.

Subspace-constrained reconstruction methods restrict the relaxation signals (of size M) in the scene to a pre-determined subspace (of size K≪M) and allow multi-contrast imaging and parameter mapping from accelerated acquisitions. However, these constraints yield poor image quality at some imaging contrasts, which can impact the parameter mapping performance. Additional regularization such as the use of joint-sparse (JS) or locally-low-rank (LLR) constraints can help improve the recovery of these images but are not sufficient when operating at high acceleration rates. We propose a method, non-local rank 3D (NLR3D), that is built on block matching and transform domain low rank constraints to allow high quality recovery of subspace-coefficient images (SCI) and subsequent multi-contrast imaging and parameter mapping. The performance of NLR3D was evaluated using Monte-Carlo (MC) simulations and compared against the JS and LLR methods. In vivo T 2 mapping results are presented on brain and knee datasets. MC results demonstrate improved bias, variance, and MSE behavior in both the multi-contrast images and parameter maps when compared to the JS and LLR methods. In vivo brain and knee results at moderate and high acceleration rates demonstrate improved recovery of high SNR early TE images as well as parameter maps. No significant difference was found in the T2 values measured in ROIs between the NLR3D reconstructions and the reference images (Wilcoxon signed rank test). The proposed method, NLR3D, enables recovery of high-quality SCI and, consequently, the associated multi-contrast images and parameter maps.

A multi-scale residual network for accelerated radial MR parameter mapping.

A deep learning MR parameter mapping framework which combines accelerated radial data acquisition with a multi-scale residual network (MS-ResNet) for image reconstruction is proposed. The proposed supervised learning strategy uses input image patches from multi-contrast images with radial undersampling artifacts and target image patches from artifact-free multi-contrast images. Subspace filtering is used during pre-processing to denoise input patches. For each anatomy and relaxation parameter, an individual network is trained. in vivo T1 mapping results are obtained on brain and abdomen datasets and in vivo T2 mapping results are obtained on brain and knee datasets. Quantitative results for the T2 mapping of the knee show that MS-ResNet trained using either fully sampled or undersampled data outperforms conventional model-based compressed sensing methods. This is significant because obtaining fully sampled training data is not possible in many applications. in vivo brain and abdomen results for T1 mapping and in vivo brain results for T2 mapping demonstrate that MS-ResNet yields contrast-weighted images and parameter maps that are comparable to those achieved by model-based iterative methods while offering two orders of magnitude reduction in reconstruction times. The proposed approach enables recovery of high-quality contrast-weighted images and parameter maps from highly accelerated radial data acquisitions. The rapid image reconstructions enabled by the proposed approach makes it a good candidate for routine clinical use.

Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks.

PURPOSE: To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei. METHODS: A cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy. RESULTS: Segmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05-0.18) and VSI for four nuclei (increase in the range of 0.05-0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14-0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004). CONCLUSION: The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.

Radial streak artifact reduction using phased array beamforming.

PURPOSE: A new method for streak artifact reduction in radial MRI based on phased array filtering. THEORY: Radial imaging in applications that require large fields-of-view can be susceptible to streaking artifacts due to gradient nonlinearities. Coil removal methods prune the coils contributing the most to streaking artifacts at the expense of signal loss. Phased array beamforming is a form of spatial filtering used to suppress unwanted signals. The proposed method uses interference covariance generated from the streaking artifact samples which are manually extracted with phased array beamforming to suppress streaking in the images. METHODS: The performance of the proposed method was evaluated on abdomen radial fast spin echo images acquired on a 1.5T Siemens scanner and compared with previously proposed methods. RESULTS: Our results demonstrate that the proposed method can effectively suppress streaking artifacts without any noticeable loss in signal levels. Coil removal methods can suppress streaks as well but they may incur significant signal loss due to coil pruning. Quantitative metrics also demonstrate the superiority of the proposed method over earlier methods. CONCLUSION: The use of interference covariance with phased array beamforming can help reduce streaking artifacts.

Accelerated MR parameter mapping with a union of local subspaces constraint.

PURPOSE: A new reconstruction method for multi-contrast imaging and parameter mapping based on a union of local subspaces constraint is presented. THEORY: Subspace constrained reconstructions use a predetermined subspace to explicitly constrain the relaxation signals. The choice of subspace size ( K ) impacts the approximation error vs noise-amplification tradeoff associated with these methods. A different approach is used in the model consistency constraint (MOCCO) framework to leverage the subspace model to enforce a softer penalty. Our proposed method, MOCCO-LS, augments the MOCCO model with a union of local subspaces (LS) approach. The union of local subspaces model is coupled with spatial support constraints and incorporated into the MOCCO framework to regularize the contrast signals in the scene. METHODS: The performance of the MOCCO-LS method was evaluated in vivo on T1 and T2 mapping of the human brain and with Monte-Carlo simulations and compared against MOCCO and the explicit subspace constrained models. RESULTS: The results demonstrate a clear improvement in the multi-contrast images and parameter maps. We sweep across the model order space ( K ) to compare the different reconstructions and demonstrate that the reconstructions have different preferential operating points. Experiments on T2 mapping show that the proposed method yields substantial improvements in performance even when operating at very high acceleration rates. CONCLUSIONS: The use of a union of local subspace constraints coupled with a sparsity promoting penalty leads to improved reconstruction quality of multi-contrast images and parameter maps.