Evaluation of a Deep Learning Reconstruction for High-Quality T2-Weighted Breast Magnetic Resonance Imaging.

Deep learning (DL) reconstruction techniques to improve MR image quality are becoming commercially available with the hope that they will be applicable to multiple imaging application sites and acquisition protocols. However, before clinical implementation, these methods must be validated for specific use cases. In this work, the quality of standard-of-care (SOC) T2w and a high-spatial-resolution (HR) imaging of the breast were assessed both with and without prototype DL reconstruction. Studies were performed using data collected from phantoms, 20 retrospectively collected SOC patient exams, and 56 prospectively acquired SOC and HR patient exams. Image quality was quantitatively assessed via signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Qualitatively, all in vivo images were scored by either two or four radiologist readers using 5-point Likert scales in the following categories: artifacts, perceived sharpness, perceived SNR, and overall quality. Differences in reader scores were tested for significance. Reader preference and perception of signal intensity changes were also assessed. Application of the DL resulted in higher average SNR (1.2-2.8 times), CNR (1.0-1.8 times), and image sharpness (1.2-1.7 times). Qualitatively, the SOC acquisition with DL resulted in significantly improved image quality scores in all categories compared to non-DL images. HR acquisition with DL significantly increased SNR, sharpness, and overall quality compared to both the non-DL SOC and the non-DL HR images. The acquisition time for the HR data only required a 20% increase compared to the SOC acquisition and readers typically preferred DL images over non-DL counterparts. Overall, the DL reconstruction demonstrated improved T2w image quality in clinical breast MRI.

Automated Placement of Scan and Pre-Scan Volumes for Breast MRI Using a Convolutional Neural Network.

Graphically prescribed patient-specific imaging volumes and local pre-scan volumes are routinely placed by MRI technologists to optimize image quality. However, manual placement of these volumes by MR technologists is time-consuming, tedious, and subject to intra- and inter-operator variability. Resolving these bottlenecks is critical with the rise in abbreviated breast MRI exams for screening purposes. This work proposes an automated approach for the placement of scan and pre-scan volumes for breast MRI. Anatomic 3-plane scout image series and associated scan volumes were retrospectively collected from 333 clinical breast exams acquired on 10 individual MRI scanners. Bilateral pre-scan volumes were also generated and reviewed in consensus by three MR physicists. A deep convolutional neural network was trained to predict both the scan and pre-scan volumes from the 3-plane scout images. The agreement between the network-predicted volumes and the clinical scan volumes or physicist-placed pre-scan volumes was evaluated using the intersection over union, the absolute distance between volume centers, and the difference in volume sizes. The scan volume model achieved a median 3D intersection over union of 0.69. The median error in scan volume location was 2.7 cm and the median size error was 2%. The median 3D intersection over union for the pre-scan placement was 0.68 with no significant difference in mean value between the left and right pre-scan volumes. The median error in the pre-scan volume location was 1.3 cm and the median size error was -2%. The average estimated uncertainty in positioning or volume size for both models ranged from 0.2 to 3.4 cm. Overall, this work demonstrates the feasibility of an automated approach for the placement of scan and pre-scan volumes based on a neural network model.

Characterization and correction of cardiovascular motion artifacts in diffusion-weighted imaging of the pancreas.

PURPOSE: To assess the effects of cardiovascular-induced motion on conventional DWI of the pancreas and to evaluate motion-robust DWI methods in a motion phantom and healthy volunteers. METHODS: 3T DWI was acquired using standard monopolar and motion-compensated gradient waveforms, including in an anatomically accurate pancreas phantom with controllable compressive motion and healthy volunteers (n = 8, 10). In volunteers, highly controlled single-slice DWI using breath-holding and cardiac gating and whole-pancreas respiratory-triggered DWI were acquired. For each acquisition, the ADC variability across volunteers, as well as ADC differences across parts of the pancreas were evaluated. RESULTS: In motion phantom scans, conventional DWI led to biased ADC, whereas motion-compensated waveforms produced consistent ADC. In the breath-held, cardiac-triggered study, conventional DWI led to heterogeneous DW signals and highly variable ADC across the pancreas, whereas motion-compensated DWI avoided these artifacts. In the respiratory-triggered study, conventional DWI produced heterogeneous ADC across the pancreas (head: 1756 ± 173 × 10-6 mm2 /s; body: 1530 ± 338 × 10-6 mm2 /s; tail: 1388 ± 267 × 10-6 mm2 /s), with ADCs in the head significantly higher than in the tail (P < .05). Motion-compensated ADC had lower variability across volunteers (head: 1277 ± 102 × 10-6 mm2 /s; body: 1204 ± 169 × 10-6 mm2 /s; tail: 1235 ± 178 × 10-6 mm2 /s), with no significant difference (P ≥ .19) across the pancreas. CONCLUSION: Cardiovascular motion introduces artifacts and ADC bias in pancreas DWI, which are addressed by motion-robust DWI.

High-resolution double arterial phase hepatic MRI using adaptive 2D centric view ordering: initial clinical experience.

OBJECTIVE: The objective of our study was to evaluate a new 3D fast spoiled gradient-recalled echo (FSPGR) sequence referred to as modified liver acceleration volume acquisition (LAVA) for high-resolution gadolinium-enhanced dual arterial phase liver MRI and to determine the effect of this technique on the timing of the contrast bolus and lesion detection. MATERIALS AND METHODS: Gadolinium-enhanced dual arterial phase liver MRI was performed in 109 patients using a modified LAVA sequence that supports adaptive 2D centric view ordering, efficient 2D autocalibrated acceleration, and partial-Fourier to achieve faster scan times while maintaining the same slice thickness, resolution, and coverage as single-phase imaging. After a fixed 20-second scan delay, a modified LAVA acquisition required a single 24- to 26-second breath-hold for two arterial phases with 56-60 slices per pass. Images were reviewed for timing relative to liver enhancement, lesion conspicuity, and lesion detection. Liver lesion depiction was evaluated qualitatively and quantitatively. A control group of 109 patients underwent imaging using a single arterial phase 3D FSPGR sequence, which was also performed with a fixed 20-second scan delay. RESULTS: The single arterial phase images produced optimal timing in the middle or late arterial phase in 79 (72%) of the 109 control group patients compared with 99 (91%) of the 109 study group patients who underwent imaging using a dynamic modified LAVA dual arterial phase sequence. For the modified LAVA sequence, the first-pass images were obtained during the mid arterial phase in 34 patients (31%). The second-pass images were obtained during the mid arterial phase in 51 patients (47%) and late arterial phase in 26 patients (24%). Sixty-two patients had liver lesions showing greater conspicuity--on the first phase in 17 patients (27%) and second phase in 45 patients (73%). Hypovascular lesions were more conspicuous on second-phase images in 24 (86%) of 28 patients. Hypervascular lesions were more conspicuous on first-phase images in 13 patients (38%) and on second-phase images in 21 (62%) of 34 patients. The first-phase images detected 165 and 155 liver lesions, respectively, for two observers compared with 233 and 224 lesions on the second-phase images, whereas the combined dual arterial phase images detected 256 and 248 hepatic lesions. CONCLUSION: High-resolution dual arterial phase 3D FSPGR MRI improves the timing of the arterial phase of liver enhancement and provides additional information for liver lesion detection.

Three-dimensional fast spoiled gradient-echo dual echo (3D-FSPGR-DE) with water reconstruction: preliminary experience with a novel pulse sequence for gadolinium-enhanced abdominal MR imaging.

PURPOSE: To compare three-dimensional fast spoiled gradient-echo dual-echo (3D-FSPGR-DE) with water reconstruction to conventional 3D-FSPGR for gadolinium-enhanced abdominal imaging. MATERIALS AND METHODS: Sixty-five patients underwent abdominal MRI on a 1.5T GE-HDx MR scanner using gadolinium-enhanced 3D-FSPGR and 3D-FSPGR-DE imaging. Qualitatively, FSPGR-DE and 3D-FSPGR images were reviewed side by side for normal anatomic structures, artifacts, and image quality. The images were reviewed separately for abnormalities of abdominal organs. Receiver operating characteristic (ROC) curve analysis was performed. Quantitative analysis measured mean signal intensity of liver, spleen, aorta, liver lesions, and noise. RESULTS: Observers preferred FSPGR-DE for evaluating liver, vessels, muscles, and subcutaneous tissues. Fat suppression was superior on FSPGR-DE in 63 (0.97) and 61 (0.94) of 65 cases for two observers. FSPGR-DE showed less susceptibility artifact in 47 (0.72) and 41 (0.63) cases, better signal in edge slices in 60 (0.92) and 60 (0.92) cases, less phase artifact in 42 (0.65) and 45 (0.69) cases, and less parallel imaging artifact in 13 (0.20) and 10 (0.15) cases. Images were equivalent for depicting abdominal findings with no difference in the area under the ROC curve. FSPGR-DE images showed a 20%, 29%, and 34% increase in liver, splenic, and aortic signal, respectively, and a 45% and 62% increase in liver-lesion contrast and contrast-to-noise ratio (CNR), respectively. CONCLUSION: Gadolinium-enhanced 3D-FSPGR-DE with water reconstruction provides volumetric abdominal imaging with superior image quality, more homogeneous fat suppression, reduced artifacts, and improved image signal and homogeneity.