3D T1-weighted Gradient-echo Imaging Research Articles

Deep learning LI-RADS grading system based on contrast enhanced multiphase MRI for differentiation between LR-3 and LR-4/LR-5 liver tumors.

BackgroundTo develop a deep learning (DL) method based on multiphase, contrast-enhanced (CE) magnetic resonance imaging (MRI) to distinguish Liver Imaging Reporting and Data System (LI-RADS) grade 3 (LR-3) liver tumors from combined higher-grades 4 and 5 (LR-4/LR-5) tumors for hepatocellular carcinoma (HCC) diagnosis.MethodsA total of 89 untreated LI-RADS-graded liver tumors (35 LR-3, 14 LR-4, and 40 LR-5) were identified based on the radiology MRI interpretation reports. Multiphase 3D T1-weighted gradient echo imaging was acquired at six time points: pre-contrast, four phases immediately post-contrast, and one hepatobiliary phase after intravenous injection of gadoxetate disodium. Image co-registration was performed across all phases on the center tumor slice to correct motion. A rectangular tumor box centered on the tumor area was drawn to extract subset tumor images for each imaging phase, which were used as the inputs to a convolutional neural network (CNN). The pre-trained AlexNet CNN model underwent transfer learning using liver MRI data for LI-RADS tumor grade classification. The output probability number closer to 1 or 0 indicated a higher possibility of being combined LR-4/LR-5 tumor or LR-3 tumor, respectively. Five-fold cross validation was used for training (60% dataset), validation (20%) and testing processes (20%).ResultsThe DL CNN model for LI-RADS grading using inputs of multiphase liver MRI data acquired at three time points (pre-contrast, arterial, and washout phase) achieved a high accuracy of 0.90, sensitivity of 1.0, precision of 0.835, and AUC of 0.95 with reference to the expert human radiologist report. The CNN output of probability provided radiologists a confidence level of the model’s grading for each liver lesion.ConclusionsAn AlexNet CNN model for LI-RADS grading of liver lesions provided diagnostic performance comparable to radiologists and offered valuable clinical guidance for differentiating intermediate LR-3 liver lesions from more-likely malignant LR-4/LR-5 lesions in HCC diagnosis.

Machine Learning Based Detection of Brain Cancer Metastases in MR Images for Stereotactic Radiosurgery Using Single-Shot Detectors

Identification of brain cancer metastases in MR images for stereotactic radiation treatment is presently performed manually by a radiologist/radiation oncologist and can be time-consuming. The purpose of this study was to investigate machine learning based single-shot detectors (SSDs) for automatic detection of brain metastases. Post-contrast 3D T1-weighted gradient echo images (FOV=24 cm, TR/TE=6.947/2.428 ms, voxel size=0.94×0.94×1.00 mm) from 146 patients who underwent noninvasive stereotactic radiosurgery at our institution were included in the study. The manual identification and contouring of the brain metastases by neuroradiologists and treating radiation oncologists were used as the ground truth. The patients were partitioned into 3 cohorts of 99/25/22 for training/validation/testing purposes with a total of 438/117/93 brain metastases, respectively. The size of the brain metastases ranged from 1.88 to 50.63 mm and was distributed similarly in the 3 cohorts. We constructed a multibox SSD with 16 convolutional layers, of which 6 layers of different resolution scales (128×128, 64×64, 32×32, 16×16, 8×8 and 6×6) were used for prediction. We used the SSD loss function with a weighted sum between the localization loss (Smooth L1) and the classification loss (Softmax). Inputs to the network were the axial slices of the MR images, and the outputs were the bounding box coordinates and the associated confidence of the classifier. An Adam optimizer was used to train the network and the initial learning rate was set to 2×10-4. Random affine transformation augmentations, decayed learning rates and an early stopping scheme were applied during the training procedure. The detection performance was analyzed on 11 different confidence thresholds ranging from 99% to 0%. For each threshold, the predicted volumes of interest were reconstructed using the output bounding box coordinates and were compared with the ground truth. True positives (TPs) were defined as predictions having at least one voxel overlap with the ground truth bounding box; otherwise, they were considered false positives (FPs). An average sensitivity of 73.5% and FP/TP ratio of 15.8 were achieved across all sizes of brain metastases and all confidence thresholds. For metastases ≥6 mm, the average sensitivity was 94.5%, and the FP/TP ratio was 7.9. Detection performance for 30%, 60%, and 90% confidence thresholds are listed in Table 1. The SSD was able to detect almost all brain metastases ≥6 mm with high confidence and specificity, and nearly half the metastases <6mm with low specificity. The performance of the model is expected to further improve through ablation studies, hyperparameter searches, and inclusion of additional curated patient data.Abstract 1002; Table 1Detection performance of the SSD for 3 confidence thresholds.Confidence threshold<6 mm≥6 mmSensitivityFP/TP ratioSensitivityFP/TP ratio90%33.3%1.7190.2%0.9160%42.9%3.0696.1%1.8230%54.8%5.8796.1%3.69 Open table in a new tab

Multiparametric MRI Characterization of Funaki Types of Uterine Fibroids Considered for MR-Guided High-Intensity Focused Ultrasound (MR-HIFU) Therapy

To compare quantitative multiparametric magnetic resonance imaging (mpMRI) data of symptomatic uterine fibroids being considered for MR-guided high-intensity focused ultrasound ablation with fibroid characterization based on the Funaki Classification scheme. This was a prospective, Institutional Review Board -approved, Health Insurance Portability, and Accountability Act-compliant study. Informed consent was obtained. From December 2013 to April 2015, 48 women with symptomatic fibroids underwent screening with mpMRI protocol including sagittal/axial T2-weighted fast spin-echo, sagittal diffusion-weighted, and sagittal dynamic contrast-enhanced 3D T1-weighted gradient echo imaging on a 3T magnet. All fibroids were assigned Funaki type 1, 2, or 3 based on T2-weighted imaging. Differences in size, perfusion, and diffusion/intravoxel incoherent motion parameters among the three Funaki types were determined using linear mixed model. A logistic regression analysis was performed to select the best model in predicting type 3 fibroids. A total of 100 fibroids were assessed (20 type 1, 66 type 2, and 14 type 3). Apparent diffusion coefficient and D of type 3 fibroids were significantly higher than those of type 1 (P < 0.0001, P < 0.0001) and 2 fibroids (P = 0.004, P < 0.0001) respectively. Transfer constant of type 3 fibroids was significantly higher than type 1 (P = 0.0357), but not than type 2 (P = 0.0752). A cutoff value of D = 1 × 10-3 mm2/s offers an accuracy, sensitivity, and specificity of 76%, 71%, and 77%, respectively, for the diagnosis of Funaki 3 fibroids. mpMRI-derived quantitative parameters may enable a more objective selection of patients prior to MR-guided high-intensity focused ultrasound therapy.

Evaluation of deep gray matter volume, cortical thickness and white matter integrity in patients with typical absence epilepsy: a study using voxelwise-based techniques.

The objective of this study was to evaluate the cortical thickness and the volume of deep gray matter structures, measured from 3D T1-weighted gradient echo imaging, and white matter integrity, by diffusion tensor imaging (DTI) in patients with typical absence epilepsy (AE). Patients (n=19) with typical childhood AE and juvenile AE, currently taking antiepileptic medication, were compared with control subjects (n=19), matched for gender and age. 3D T1 magnetization-prepared rapid gradient echo-weighted imaging and DTI along 30 noncolinear directions were performed using a 1.5-T MR scanner. FreeSurfer was used to perform cortical volumetric reconstruction and segmentation of deep gray matter structures. For tract-based spatial statistics analysis of DTI, a white matter skeleton was created, along with a permutation-based inference with 5000 permutations. A threshold of p<0.05 was used to identify abnormalities in fractional anisotropy (FA). The mean, radial, and axial diffusivities were also projected onto the mean FA skeleton. Patients with AE presented decreased FA and increased mean diffusivity and radial diffusivity values in the genu and the body of the corpus callosum and right anterior corona radiata, as well as decreased axial diffusivity in the left posterior thalamic radiation, inferior cerebellar peduncle, right cerebral peduncle, and right corticospinal tract. However, there were no significant differences in cortical thickness or deep gray matter structure volumes between patients with AE and controls. Abnormalities found in white matter integrity may help to better understand the pathophysiology of AE and optimize diagnosis and treatment strategies.

Efficacy of Maximum Intensity Projection of Contrast-Enhanced 3D Turbo-Spin Echo Imaging with Improved Motion-Sensitized Driven-Equilibrium Preparation in the Detection of Brain Metastases

ObjectiveTo evaluate the diagnostic benefits of 5-mm maximum intensity projection of improved motion-sensitized driven-equilibrium prepared contrast-enhanced 3D T1-weighted turbo-spin echo imaging (MIP iMSDE-TSE) in the detection of brain metastases. The imaging technique was compared with 1-mm images of iMSDE-TSE (non-MIP iMSDE-TSE), 1-mm contrast-enhanced 3D T1-weighted gradient-echo imaging (non-MIP 3D-GRE), and 5-mm MIP 3D-GRE.Materials and MethodsFrom October 2014 to July 2015, 30 patients with 460 enhancing brain metastases (size > 3 mm, n = 150; size ≤ 3 mm, n = 310) were scanned with non-MIP iMSDE-TSE and non-MIP 3D-GRE. We then performed 5-mm MIP reconstruction of these images. Two independent neuroradiologists reviewed these four sequences. Their diagnostic performance was compared using the following parameters: sensitivity, reading time, and figure of merit (FOM) derived by jackknife alternative free-response receiver operating characteristic analysis. Interobserver agreement was also tested.ResultsThe mean FOM (all lesions, 0.984; lesions ≤ 3 mm, 0.980) and sensitivity ([reader 1: all lesions, 97.3%; lesions ≤ 3 mm, 96.2%], [reader 2: all lesions, 97.0%; lesions ≤ 3 mm, 95.8%]) of MIP iMSDE-TSE was comparable to the mean FOM (0.985, 0.977) and sensitivity ([reader 1: 96.7, 99.0%], [reader 2: 97, 95.3%]) of non-MIP iMSDE-TSE, but they were superior to those of non-MIP and MIP 3D-GREs (all, p < 0.001). The reading time of MIP iMSDE-TSE (reader 1: 47.7 ± 35.9 seconds; reader 2: 44.7 ± 23.6 seconds) was significantly shorter than that of non-MIP iMSDE-TSE (reader 1: 78.8 ± 43.7 seconds, p = 0.01; reader 2: 82.9 ± 39.9 seconds, p < 0.001). Interobserver agreement was excellent (κ > 0.75) for all lesions in both sequences.ConclusionMIP iMSDE-TSE showed high detectability of brain metastases. Its detectability was comparable to that of non-MIP iMSDE-TSE, but it was superior to the detectability of non-MIP/MIP 3D-GREs. With a shorter reading time, the false-positive results of MIP iMSDE-TSE were greater. We suggest that MIP iMSDE-TSE can provide high diagnostic performance and low false-positive rates when combined with 1-mm sequences.

Fat suppression techniques for obtaining high resolution dynamic contrast enhanced bilateral breast MR images at 7 T

ObjectivesTo compare water selective excitation (WSE) and Dixon fat suppression in the context of high-resolution dynamic contrast enhanced MRI of the breast at 7T. MethodsTen healthy volunteers and one patient with a malignant breast lesion were scanned at 7T. The MRI protocol contained 3D T1-weighted gradient echo images obtained with both WSE fat suppression, multi echo Dixon fat suppression, and without fat suppression. Images were acquired at a (0.8mm)3 or (0.7mm)3 isotropic resolution with equal field of view and optimized such to obtain a maximal SNR. Image quality was scored qualitatively on overall image quality, sharpness of anatomical details, presence of artifacts, inhomogeneous fat suppression and the presence of water-fat shift. A quantitative scoring was obtained from the signal to noise ratio and contrast to noise ratio. ResultsWSE scored significantly better in terms of overall image quality and the absence of artifacts. No significant difference in contrast to noise ratio was found between the two fat suppression methods. ConclusionWhen maximizing temporal and spatial resolution of high resolution DCE MRI of the breast, water selective excitation provides better image quality than multi echo Dixon at 7T.

Breast MRI at 7 Tesla with a bilateral coil and T1-weighted acquisition with robust fat suppression: image evaluation and comparison with 3 Tesla

To evaluate the image quality of T1-weighted fat-suppressed breast MRI at 7 T and to compare 7-T and 3-T images. Seventeen subjects were imaged using a 7-T bilateral transmit-receive coil and 3D gradient echo sequence with adiabatic inversion-based fat suppression (FS). Images were graded on a five-point scale and quantitatively assessed through signal-to-noise ratio (SNR), fibroglandular/fat contrast and signal uniformity measurements. Image scores at 7 and 3 T were similar on standard-resolution images (1.1 × 1.1 × 1.1-1.6 mm(3)), indicating that high-quality breast imaging with clinical parameters can be performed at 7 T. The 7-T SNR advantage was underscored on 0.6-mm isotropic images, where image quality was significantly greater than at 3 T (4.2 versus 3.1, P ≤ 0.0001). Fibroglandular/fat contrast was more than two times higher at 7 T than at 3 T, owing to effective adiabatic inversion-based FS and the inherent 7-T signal advantage. Signal uniformity was comparable at 7 and 3 T (P < 0.05). Similar 7-T image quality was observed in all subjects, indicating robustness against anatomical variation. The 7-T bilateral transmit-receive coil and adiabatic inversion-based FS technique produce image quality that is as good as or better than at 3 T. • High image quality bilateral breast MRI is achievable with clinical parameters at 7 T. • 7-T high-resolution imaging improves delineation of subtle soft tissue structures. • Adiabatic-based fat suppression provides excellent fibroglandular/fat contrast at 7 T. • 7- and 3-T 3D T1-weighted gradient-echo images have similar signal uniformity. • The 7-T dual solenoid coil enables bilateral imaging without compromising uniformity.

Clinical application of controlled aliasing in parallel imaging results in a higher acceleration (CAIPIRINHA)‐volumetric interpolated breathhold (VIBE) sequence for gadoxetic acid‐enhanced liver MR imaging

To determine whether a controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA) technique can improve the image quality of three-dimensional (3D), T1-weighted gradient echo (T1w-GRE) imaging compared with the use of a standard, parallel acquisition technique (PAT). Sixty-four patients who underwent liver MR on a 3 Tesla (T) scanner, were included in this study. Twenty minutes after the injection of 0.025 mmole/kg of gadoxetic acid, 3D T1w-GRE imaging (volumetric interpolated breathhold examination [VIBE]) was acquired twice using a generalized autocalibrating partially parallel acquisition (384 × 250 matrix, acceleration factor [AF] of 2) and a CAIPIRINHA (384 × 380 matrix, AF of 4), respectively. Qualitative image analysis was performed for two image sets. CAIPIRINHA-VIBE showed better hepatic vessel clarity and lesion conspicuity than standard VIBE (P < 0.05). CAIPIRINHA-VIBE in the coronal plane also provided better results of motion artifact and liver edge sharpness than the standard VIBE (P < 0.05). Despite the more apparent PAT artifact on CAIPIRINHA-VIBE than on standard VIBE (P < 0.05), CAIPIRINHA-VIBE showed better overall image quality. The CAIPIRINHA-VIBE was able to provide a higher spatial resolution, T1-weighted imaging with better image quality compared with a standard VIBE.

The value of 3D T1-weighted gradient-echo MR imaging for evaluation of the appendix during pregnancy: preliminary results

The use of oral contrast has been essential for the identification of a normal appendix on MR imaging during pregnancy. However, stool could be used as a positive oral contrast as it is characterized by a relatively high signal on T1-weighted imaging, and 3D T1-weighted gradient-echo (T1W-GRE) MR imaging has been used to evaluate 3 mm diameter intestines in fetuses. To evaluate the added value of 3D T1W-GRE MR imaging in combination with T2-weighted imaging (T2WI) compared to T2WI alone for evaluating the appendix during pregnancy. Eighteen consecutive pregnant patients who were clinically suspected of having acute appendicitis underwent appendix MR imaging which included T2WI with or without spectral presaturation attenuated inversion-recovery (SPAIR) fat suppression, and 3D T1W-GRE with SPAIR fat suppression. Two radiologists reviewed the two image sets (the T2WI set and the combined set of T2WI and 3D T1W-GRE images). Pathologic and clinical results served as the reference standard. The differences in the degree of visibility of the appendix and confidence scale for diagnosing acute appendicitis between two image sets were compared by using the paired Wilcoxon signed rank test. For both reviewers, the degree of visibility of the appendix using the combined T2WI and 3D T1W-GRE images was significantly higher than using T2WI alone (P < 0.01), and the confidence levels for acute appendicitis using combined T2WI and 3D T1W-GRE images were significantly different from those using T2WI alone (P < 0.01). In the 13 patients with a normal appendix, both reviewers showed improved confidence levels for appendicitis using combined T2WI and 3D T1W-GRE images than T2WI alone. Adding 3D T1W-GRE images to T2WI is helpful for identification of the appendix, as compared to T2WI alone in pregnant women without ingestion of oral contrast material. This may improve diagnostic confidence for acute appendicitis in pregnant patients.

Absolute Quantification of Regional Renal Blood Flow in Swine by Dynamic Contrast-Enhanced Magnetic Resonance Imaging Using a Blood Pool Contrast Agent

To evaluate for the first time in an animal model the possibility of absolute regional quantification of renal medullary and cortical perfusion by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using a blood pool contrast agent. A total of 18 adult female pigs (age, 16-22 weeks; body weight, 45-65 kg; no dietary restrictions) were investigated by DCE-MRI. Absolute renal blood flow (RBF) measured by an ultrasound transit time flow probe around the renal vein was used as the standard of reference. An inflatable stainless cuff placed around the renal artery near its origin from the abdominal aorta was used to reduce RBF to 60%, 40%, and 20% of the baseline flow. The last measurement was performed with the cuff fully reopened. Absolute RBF values during these 4 perfusion states were compared with the results of DCE-MRI performed on a 1.5-T scanner with an 8-channel phased-array surface coil. All scans were acquired in breath-hold technique in the coronal plane using a field of view of 460 mm.Each dynamic scan commenced with a set of five 3D T1-weighted gradient echo sequences with different flip angles (alpha = 2 degrees, 5 degrees, 10 degrees, 20 degrees, 30 degrees): TE, 0.88 milliseconds; TR, 2.65 milliseconds; slice thickness, 8.8 mm for 4 slices; acquisition matrix, 128 x 128; and acquisitions, 4. These data served to calculate 3D intrinsic longitudinal relaxation rate maps (R10) and magnetization (M0). Immediately after these images, the dynamic 3D T1-weighted gradient echo images were acquired with the same parameters and a constant alpha = 30 degrees, half Fourier, 1 acquisition, 64 frames, a time interval of 1.65 seconds between each frame, and a total duration of 105.6. Three milliliters of an albumin-binding blood pool contrast agent (0.25 mmol/mL gadofosveset trisodium, Vasovist, Bayer Schering Pharma AG, Berlin, Germany) was injected at a rate of 3 mL/s. Perfusion was calculated using the arterial input function from the aorta, which was extracted from the dynamic relaxation rate change maps and perfusion images were calculated on a voxel-by-voxel basis using a singular value decomposition. In 11 pigs, 4 different perfusion states were investigated sequentially. The reduced kidney perfusion measured by ultrasound highly correlated with total renal blood flow determined by DCE-MRI, P < 0.001. The correlation coefficient between both measurements was 0.843. Regional cortical and medullary renal flow was also highly correlated (r = 0.77/0.78, P < 0.001) with the degree of flow reduction. Perfusion values smaller than 50 mL/min/100 cm were overestimated by MRI, high perfusion values slightly underestimated. DCE-MRI using a blood pool contrast agent allows absolute quantification of total kidney perfusion as well as separate determination of cortical and medullary flow. The results show that our technique has sufficient accuracy and reproducibility to be transferred to the clinical setting.

Is True FISP Imaging Reliable in the Evaluation of Venous Thrombosis?

The objective of our study was to evaluate the accuracy of true fast imaging with steady-state precession (FISP) in the diagnosis of venous thrombosis using gadolinium-enhanced 3D T1-weighted gradient-echo images and correlative imaging as the gold standard. Twenty-five MR examinations were retrospectively reviewed independently by two radiologists to rule out thrombosis in the central veins of the body. The presence of venous thrombus was assessed separately in 80 veins using true FISP and gadolinium-enhanced T1-weighted images. Diagnosis was confirmed by another imaging technique (sonography, CT, and/or conventional venography) in all positive cases. Negative examinations were confirmed using imaging, clinical follow-up, or both. Venous thrombosis was present in 25 veins in 18 patients. True FISP images had a lower sensitivity (66%) and specificity (70.9%) for the diagnosis of venous thrombosis than gadolinium-enhanced MR images (p < 0.01). True FISP images have lower sensitivity and specificity in the diagnosis of venous thrombosis than gadolinium-enhanced T1-weighted gradient-echo images. True FISP images should not be used exclusively for the diagnosis of venous thrombosis.