3D T2-FLAIR Research Articles

Accelerating brain three-dimensional T2 fluid-attenuated inversion recovery using artificial intelligence-assisted compressed sensing: a comparison study with parallel imaging.

Shortening the acquisition time of brain three-dimensional T2 fluid-attenuated inversion recovery (3D T2 FLAIR) by using acceleration techniques has the potential to reduce motion artifacts in images and facilitate clinical application. This study aimed to assess the image quality of brain 3D T2 FLAIR accelerated by artificial intelligence-assisted compressed sensing (ACS) in comparison to 3D T2 FLAIR accelerated by parallel imaging (PI). In this prospective cohort study, 102 consecutive participants, including both healthy individuals and those with suspected brain diseases, were recruited and underwent both ACS- and PI-3D T2 FLAIR scans with a 3.0-Tesla magnetic resonance imaging system from February 2023 to October 2023 in Beijing Tiantan Hospital, Capital Medical University. Quantitative assessment involved white matter (WM) and gray matter (GM) signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), whole-image sharpness, and tumor volume. Qualitative assessment included the scoring of overall image quality, GM-WM border sharpness, and diagnostic confidence in lesion detection. ACS-3D T2 FLAIR exhibited a shorter acquisition time compared to PI-3D T2 FLAIR (105 vs. 320 seconds). ACS-3D T2 FLAIR, compared to PI-3D T2 FLAIR, demonstrated a significantly higher mean SNRWM (25.922±6.811 vs. 22.544±5.853; P<0.001), SNRGM (18.324±7.137 vs. 17.102±6.659; P=0.049), CNRWM/GM (4.613±1.547 vs. 4.160±1.552; P<0.001), and sharpness (0.413±0.049 vs. 0.396±0.034; P<0.001), while no significant differences were found for the overall image quality ratings (P=0.063) or GM-WM border sharpness ratings (P=0.125). A good agreement on tumor volume was achieved between ACS-3D T2 FLAIR and PI-3D T2 FLAIR images (intraclass correlation coefficient =0.999; 0.998-1.000; P<0.001). Images acquired with ACS demonstrated nearly equivalent diagnostic confidence to those obtained with PI (P>0.05). The ACS technique offers a substantial reduction in scanning time for brain 3D T2 FLAIR compared to PI while maintaining good image quality and equivalent diagnostic confidence.

Deep learning for efficient reconstruction of highly accelerated 3D FLAIR MRI in neurological deficits.

To compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed. Twelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold. Interventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002). Patients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.

Compressed SENSitivity Encoding (SENSE): Qualitative and Quantitative Analysis.

This study aimed to qualitatively and quantitatively evaluate T1-TSE, T2-TSE and 3D FLAIR sequences obtained with and without Compressed-SENSE technique by assessing the contrast (C), the contrast-to-noise ratio (CNR) and the signal-to-noise ratio (SNR). A total of 142 MRI images were acquired: 69 with Compressed-SENSE and 73 without Compressed-SENSE. All the MRI images were contoured, spatially aligned and co-registered using 3D Slicer Software. Two radiologists manually drew 12 regions of interests on three different structures of CNS: white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF). C values were significantly higher in Compressed-SENSE T1-TSE compared to No Compressed-SENSE T1-TSE for three different structures of the CNS. C values were also significantly lower for Compressed-SENSE 3D FLAIR and Compressed-SENSE T2-TSE compared to the corresponding No Compressed-SENSE scans. While CNR values did not significantly differ in GM-WM between Compressed-SENSE and No Compressed-SENSE for the 3D FLAIR and T1-TSE sequences, the differences in GM-CSF and WM-CSF were always statistically significant. Compressed-SENSE for 3D T2 FLAIR, T1w and T2w sequences enables faster MRI acquisition, reducing scan time and maintaining equivalent image quality. Compressed-SENSE is very useful in specific medical conditions where lower SAR levels are required without sacrificing the acquisition of helpful diagnostic sequences.

Central Vein Sign, Cortical Lesions, and Paramagnetic Rim Lesions for the Diagnostic and Prognostic Workup of Multiple Sclerosis.

The diagnosis of multiple sclerosis (MS) can be challenging in clinical practice because MS presentation can be atypical and mimicked by other diseases. We evaluated the diagnostic performance, alone or in combination, of the central vein sign (CVS), paramagnetic rim lesion (PRL), and cortical lesion (CL), as well as their association with clinical outcomes. In this multicenter observational study, we first conducted a cross-sectional analysis of the CVS (proportion of CVS-positive lesions or simplified determination of CVS in 3/6 lesions-Select3*/Select6*), PRL, and CL in MS and non-MS cases on 3T-MRI brain images, including 3D T2-FLAIR, T2*-echo-planar imaging magnitude and phase, double inversion recovery, and magnetization prepared rapid gradient echo image sequences. Then, we longitudinally analyzed the progression independent of relapse and MRI activity (PIRA) in MS cases over the 2 years after study entry. Receiver operating characteristic curves were used to test diagnostic performance and regression models to predict diagnosis and clinical outcomes. The presence of ≥41% CVS-positive lesions/≥1 CL/≥1 PRL (optimal cutoffs) had 96%/90%/93% specificity, 97%/84%/60% sensitivity, and 0.99/0.90/0.77 area under the curve (AUC), respectively, to distinguish MS (n = 185) from non-MS (n = 100) cases. The Select3*/Select6* algorithms showed 93%/95% specificity, 97%/89% sensitivity, and 0.95/0.92 AUC. The combination of CVS, CL, and PRL improved the diagnostic performance, especially when Select3*/Select6* were used (93%/94% specificity, 98%/96% sensitivity, 0.99/0.98 AUC; p = 0.002/p < 0.001). In MS cases (n = 185), both CL and PRL were associated with higher MS disability and severity. Longitudinal analysis (n = 61) showed that MS cases with >4 PRL at baseline were more likely to experience PIRA at 2-year follow-up (odds ratio 17.0, 95% confidence interval: 2.1-138.5; p = 0.008), whereas no association was observed between other baseline MRI measures and PIRA, including the number of CL. The combination of CVS, CL, and PRL can improve MS differential diagnosis. CL and PRL also correlated with clinical measures of poor prognosis, with PRL being a predictor of disability accrual independent of clinical/MRI activity.

IMG-27. ASSESSMENT OF VARIABILITY OF PEDIATRIC BRAIN TUMOR IMAGING PROTOCOLS ACROSS INSTITUTIONS: ARE WE FOLLOWING RECOMMENDATIONS?

Abstract BACKGROUND Evaluating pediatric brain tumors requires imaging children with tailored MRI protocols. Considerable variation in pediatric brain tumor imaging protocols exist across institutions, which can cause inaccuracies in staging. Although recently consensus guidelines for pediatric brain tumor imaging protocols have been established, adherence to these guidelines across institutions is unknown. Institutions may perceive guidelines as applicable for research purposes rather than routine clinical practice. We aim to explore variability in pediatric brain tumor imaging protocols across institutions and determine the factors influencing guideline divergence. METHODS AND METHODOLOGY Faculty at institutions routinely imaging pediatric patients with brain tumors were invited to share brain tumor MRI protocols and complete a structured survey. The survey included multiple choice and open-ended queries concerning practice type, the presence of an institutional imaging protocol for pediatric brain tumors and if the protocol was based on specific consensus recommendations. We assessed if protocols included the 7 minimum recommended MRI sequences by the Children’s Oncology Group (COG) guidelines, including slice thickness and gap. RESULTS Twenty emails were sent and responses were received from 12 institutions (the data collection is still ongoing). 2 institutions did not have dedicated protocols for pediatric brain tumors. On average, institutions had 5.7 out of the 7 minimum COG-recommended sequences. All 10 institutions included 3D T1 IR-GRE/TSE, DWI or DTI, and SWI sequences in their protocols. 9 (90%) included post-contrast 3D T1 IR-GRE/TSE, 7 (70%) included T2 TSE/FSE, 7 (70%) included either 3D T2 FLAIR or T2 FLAIR TSE/FSE, and 4 (40%) included T1/TSE/FSE. Across all sequences in all protocols, adherence to recommended imaging parameters was 87% for plane, 71% for slice thickness, and 85% for gap. CONCLUSION Significant variability in pediatric brain tumor imaging protocols exists across institutions Standardizing imaging protocols through collaboration is vital in ensuring uniformity in care.

Increased Intracranial Arterial Pulsatility and Microvascular Brain Damage in Pseudoxanthoma Elasticum.

Carotid siphon calcification might contribute to the high prevalence of cerebrovascular disease in pseudoxanthoma elasticum through increased arterial flow pulsatility. This study aimed to compare intracranial artery flow pulsatility, brain volumes, and small-vessel disease markers between patients with pseudoxanthoma elasticum and controls and the association between arterial calcification and pulsatility in pseudoxanthoma elasticum. Fifty patients with pseudoxanthoma elasticum and 40 age- and sex-matched controls underwent 3T MR imaging, including 2D phase-contrast acquisitions for flow pulsatility in the assessment of ICA and MCA and FLAIR acquisitions for brain volumes, white matter lesions, and infarctions. All patients with pseudoxanthoma elasticum underwent CT scanning to measure siphon calcification. Flow pulsatility (2D phase-contrast), brain volumes, white matter lesions, and infarctions (3D T1 and 3D T2 FLAIR) were compared between patients and controls. The association between siphon calcification and pulsatility in pseudoxanthoma elasticum was tested with linear regression models. Patients with pseudoxanthoma elasticum (mean age, 57 [SD, 12] years; 24 men) had significantly higher pulsatility indexes (1.05; range, 0.94-1.21 versus 0.94; range, 0.82-1.04; P = .02), lower mean GM volumes (597 [SD, 53] mL versus 632 [SD, 53] mL; P < .01), more white matter lesions (2.6; range, 0.5-7.5 versus 1.1; range, 0.5-2.4) mL; P = .05), and more lacunar infarctions (64 versus 8, P = .04) than controls (mean age, 58 [SD, 11] years; 20 men). Carotid siphon calcification was associated with higher pulsatility indexes in patients with pseudoxanthoma elasticum (β = 0.10; 95% CI, 0.01-0.18). Patients with pseudoxanthoma elasticum have increased intracranial artery flow pulsatility and measures of small-vessel disease. Carotid siphon calcification might underlie the high prevalence of cerebrovascular disease in pseudoxanthoma elasticum.

Neuroimaging of brain tumors: back to the standardized MRI-protocol

Despite the widespread application of MRI in brain tumor MR-imaging, the standardized MRI protocol has not yet been approved. This fact creates obstacles for interpreting of the obtained data and even limits the diagnostic power of MRI. Standardization of MRI studies facilitates successful planning of surgery, chemotherapy, or radiation therapy and provides more reliable follow-up. In this regard, unification of image acquisition parameters and protocols remains relevant. We propose a standard MRI protocol that includes axial and coronal T2-weighted images, axial or 3D T2-FLAIR, 3D T2* (gradient echo), diffusion-weighted imaging, axial T1-weighted images, contrast-enhanced spin-echo T1-weighted images (either axial or three planes) and obligatory subsequent isotropic 3D T1 images. The following combination of sequences facilitates the correct diagnosis and follow-up. The least magnetic field strength should be 1.5 T.

The Drainage Dysfunction of Meningeal Lymphatic Vessels Is Correlated with the Recurrence of Chronic Subdural Hematoma: a Prospective Study.

Meningeal lymphatic vessels (mLVs) were recently discovered to be involved in the waste drainage process in the brain, which has also been associated with a variety of neurological diseases. This research paper hypothesizes that the drainage function of mLVs may be affected after chronic subdural hematoma (CSDH) and the alterations of mLVs' drainage may predict CSDH recurrence. In this prospective observational study, unenhanced 3D T2-fluid-attenuated inversion recovery (3D T2-FLAIR) MRI data were collected from CSDH patients and healthy participants for analysis. Patients with CSDH who underwent surgery received MRI scans before and after surgery, whereas healthy controls and patients with CSDH who received pharmaceutical treatment received only one MRI scan at enrollment. The signal unit ratio (SUR) of mLVs were then measured according to the MRI data and calculated to define mLVs' drainage function. Finally, the relationship between mLVs' drainage function and CSDH recurrence was analyzed accordingly. Thirty-four participants were enrolled in this study, including 27 CSDH patients and 7 controls. The SUR of mLVs in all CSDH patients changed significantly before and after surgery. Moreover, the drainage function of the mLVs ipsilateral to hematoma (mLVs-IH) in CSDH patients was significantly lower than that in the controls (p < 0.05). Last, a higher improvement rate of the drainage function of the mLVs-IH is correlated to a lower risk of recurrence (p < 0.05). This study revealed the mLVs' drainage dysfunction after CSDH through non-invasive MRI. Furthermore, the drainage function of mLVs is an independent predictive factor of CSDH recurrence.

A face-off of MRI research sequences by their need for de-facing

It is now widely known that research brain MRI, CT, and PET images may potentially be re-identified using face recognition, and this potential can be reduced by applying face-deidentification (“de-facing”) software. However, for research MRI sequences beyond T1-weighted (T1-w) and T2-FLAIR structural images, the potential for re-identification and quantitative effects of de-facing are both unknown, and the effects of de-facing T2-FLAIR are also unknown. In this work we examine these questions (where applicable) for T1-w, T2-w, T2*-w, T2-FLAIR, diffusion MRI (dMRI), functional MRI (fMRI), and arterial spin labelling (ASL) sequences. Among current-generation, vendor-product research-grade sequences, we found that 3D T1-w, T2-w, and T2-FLAIR were highly re-identifiable (96–98%). 2D T2-FLAIR and 3D multi-echo GRE (ME-GRE) were also moderately re-identifiable (44–45%), and our derived T2* from ME-GRE (comparable to a typical 2D T2*) matched at only 10%. Finally, diffusion, functional and ASL images were each minimally re-identifiable (0–8%). Applying de-facing with mri_reface version 0.3 reduced successful re-identification to ≤8%, while differential effects on popular quantitative pipelines for cortical volumes and thickness, white matter hyperintensities (WMH), and quantitative susceptibility mapping (QSM) measurements were all either comparable with or smaller than scan-rescan estimates. Consequently, high-quality de-facing software can greatly reduce the risk of re-identification for identifiable MRI sequences with only negligible effects on automated intracranial measurements. The current-generation echo-planar and spiral sequences (dMRI, fMRI, and ASL) each had minimal match rates, suggesting that they have a low risk of re-identification and can be shared without de-facing, but this conclusion should be re-evaluated if they are acquired without fat suppression, with a full-face scan coverage, or if newer developments reduce the current levels of artifacts and distortion around the face.

Structural covariance in subcortical regions in multiple sclerosis and neuromyelitis optica spectrum disorders: An MRI-based study with automated brain volumetry.

This study aimed to investigate the alterations of brain volumetry and associated structural covariance in subcortical regions in multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD). Fourty MS patients, 35 NMOSD patients and 34 healthy controls (HC) underwent 3D T1-weighted image and 3D T2 FLAIR of MRI. The volume differences in subcortical regions were compared between the MS, NMOSD, and HC groups by automated brain volumetry. Structural covariance analysis was performed with each pair of these regions to investigate the alterations of anatomical connections in MS and NMOSD compared to HC. Compared with HC, MS patients presented significantly smaller volume in some subcortical and infratentorial regions (P<0.05), while NMOSD patients showed no significant difference of volumetry in any of the brain regions (P>0.05), although they had no significant difference in disease duration (MS 3.95±3.73 ys; NMOSD 3.11±4.61 ys; P>0.05). In addition, the structural covariance analyses revealed synergic volume alteration in subcortical regions both in the MS and NMOSD groups. More extensive additional connections compared with HC were found in MS patients and more extensive missing connections compared with HC were found in NMOSD patients. This study revealed distinct patterns of brain structural damage and reorganization in MS and NMOSD, which could facilitate a better distinction between these two entities.

Deep learning-based 3D MRI contrast-enhanced synthesis from a 2D noncontrast T2Flair sequence.

Gadolinium-based contrast agents (GBCAs) have been successfully applied in magnetic resonance (MR) imaging to facilitate better lesion visualization. However, gadolinium deposition in the human brain raised widespread concerns recently. On the other hand, although high-resolution three-dimensional (3D) MR images are more desired for most existing medical image processing algorithms, their long scan duration and high acquiring costs make 2D MR images still much more common clinically. Therefore, developing alternative solutions for 3D contrast-enhanced MR image synthesis to replace GBCAs injection becomes an urgent requirement. This study proposed a deep learning framework that produces 3D isotropic full-contrast T2Flair images from 2D anisotropic noncontrast T2Flair image stacks. The super-resolution (SR) and contrast-enhanced (CE) synthesis tasks are completed in sequence by using an identical generative adversarial network (GAN) with the same techniques. To solve the problem that intramodality datasets from different scanners have specific combinations of orientations, contrasts, and resolutions, we conducted a region-based data augmentation technique on the fly during training to simulate various imaging protocols in the clinic. We further improved our network by introducing atrous spatial pyramid pooling, enhanced residual blocks, and deep supervision for better quantitative and qualitative results. Our proposed method achieved superior CE-synthesized performance in quantitative metrics and perceptual evaluation. In detail, the PSNR, structural-similarity-index, and AUC are 32.25dB, 0.932, and 0.991 in the whole brain and 24.93dB, 0.851, and 0.929 in tumor regions. The radiologists' evaluations confirmed that our proposed method has high confidence in the diagnosis. Analysis of the generalization ability showed that benefiting from the proposed data augmentation technique, our network can be applied to "unseen" datasets with slight drops in quantitative and qualitative results. Our work demonstrates the clinical potential of synthesizing diagnostic 3D isotropic CE brain MR images from a single 2D anisotropic noncontrast sequence.

Semiquantitative 3T Brain Magnetic Resonance Imaging for Dynamic Visualization of the Glymphatic-Lymphatic Fluid Transport System in Humans: A Pilot Study.

Recently, a novel clearing system for interstitial solutes of the brain was described as a perivascular pathway named the glymphatic system. Furthermore, lymphatic vessels were found in the meninges to drain interstitial fluids. It is hypothesized that interstitial solutes, such as amyloid β, are firstly processed through the brain by the glymphatic system and secondly drained out of the brain by lymphatic vessels (glymphatic-lymphatic fluid transport system [GLS]). Since then, various neurological disorders, such as Alzheimer disease, have been associated with a dysfunction of the GLS. In the current study, we aimed to establish a clinical magnetic resonance imaging (MRI) study protocol for visualizing lymphatic vessels as part of the GLS in humans. More importantly, we aimed to describe the dynamic changes of a contrast agent in these lymphatic vessels over time. Twenty volunteers with an unremarkable neurological/psychiatric history were included in this 3T MRI study. Serial MRI sequence blocks were performed at 3 predefined time points (TPs): TP 1, precontrast MRI before administration of a gadolinium-based contrast agent (GBCA); TP 2, immediately post-GBCA (early ce-MRI); and TP 3, 60 minutes post-GBCA (late ce-MRI). Each MRI block contained the following sequences obtained in the same order: whole-brain 3D T1-MPRAGE, whole-brain 3D T2-FLAIR, focused 2D T2-FLAIR, and whole-brain 3D T1-SPACE. Signal intensity (SI) in compartments of the GLS adjacent to the superior sagittal sinus, gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) was calculated by manually placed regions of interest. The time course of the signal intensities was examined by generalized linear mixed models. The data were adjusted for age, cognitive function (Montreal-Cognitive-Assessment test), and sleep quality (Pittsburgh Sleep Quality Index questionnaire). The GLS was best visualized in the 2D T2-FLAIR and 3D T1-SPACE sequences, enabling further SI measurement. In precontrast (TP 1), the SI within the GLS was significantly higher than in CSF and significantly lower than in GM and WM. In post-GBCA, a significant increase (TP 2) and decrease (TP 3), respectively, of the GLS SI values were noted (86.3 ± 25.2% increase and subsequent decrease by 25.4 ± 9% in the 3D T1-SPACE sequence). The SI values of CSF, GM, and WM did not change significantly between the 3 TPs. A clinical MRI study protocol was established for the visualization of lymphatic vessels as an important part of the GLS and therefore the brain's clearing mechanism of interstitial solutes. Furthermore, dynamic changes in the GLS were described over time, possibly reflecting the clearing function of the GLS. This might constitute the basis for evaluating the GLS function in manifold neurological pathologies in the future.

Automatic segmentation of white matter hyperintensities: validation and comparison with state-of-the-art methods on both Multiple Sclerosis and elderly subjects

Different types of white matter hyperintensities (WMH) can be observed through MRI in the brain and spinal cord, especially Multiple Sclerosis (MS) lesions for patients suffering from MS and age-related WMH for subjects with cognitive disorders and/or elderly people. To better diagnose and monitor the disease progression, the quantitative evaluation of WMH load has proven to be useful for clinical routine and trials. Since manual delineation for WMH segmentation is highly time-consuming and suffers from intra and inter observer variability, several methods have been proposed to automatically segment either MS lesions or age-related WMH, but none is validated on both WMH types. Here, we aim at proposing the White matter Hyperintensities Automatic Segmentation Algorithm adapted to 3D T2-FLAIR datasets (WHASA-3D), a fast and robust automatic segmentation tool designed to be implemented in clinical practice for the detection of both MS lesions and age-related WMH in the brain, using both 3D T1-weighted and T2-FLAIR images. In order to increase its robustness for MS lesions, WHASA-3D expands the original WHASA method, which relies on the coupling of non-linear diffusion framework and watershed parcellation, where regions considered as WMH are selected based on intensity and location characteristics, and finally refined with geodesic dilation. The previous validation was performed on 2D T2-FLAIR and subjects with cognitive disorders and elderly subjects. 60 subjects from a heterogeneous database of dementia patients, multiple sclerosis patients and elderly subjects with multiple MRI scanners and a wide range of lesion loads were used to evaluate WHASA and WHASA-3D through volume and spatial agreement in comparison with consensus reference segmentations. In addition, a direct comparison on the MS database with six available supervised and unsupervised state-of-the-art WMH segmentation methods (LST-LGA and LPA, Lesion-TOADS, lesionBrain, BIANCA and nicMSlesions) with default and optimised settings (when feasible) was conducted. WHASA-3D confirmed an improved performance with respect to WHASA, achieving a better spatial overlap (Dice) (0.67 vs 0.63), a reduced absolute volume error (AVE) (3.11 vs 6.2 mL) and an increased volume agreement (intraclass correlation coefficient, ICC) (0.96 vs 0.78). Compared to available state-of-the-art algorithms on the MS database, WHASA-3D outperformed both unsupervised and supervised methods when used with their default settings, showing the highest volume agreement (ICC = 0.95) as well as the highest average Dice (0.58). Optimising and/or retraining LST-LGA, BIANCA and nicMSlesions, using a subset of the MS database as training set, resulted in improved performances on the remaining testing set (average Dice: LST-LGA default/optimized = 0.41/0.51, BIANCA default/optimized = 0.22/0.39, nicMSlesions default/optimized = 0.17/0.63, WHASA-3D = 0.58). Evaluation and comparison results suggest that WHASA-3D is a reliable and easy-to-use method for the automated segmentation of white matter hyperintensities, for both MS lesions and age-related WMH. Further validation on larger datasets would be useful to confirm these first findings.

Deep Learning Reconstruction Helps to Achieve Diagnostic-like Image Quality in MR Radiation Therapy of Brain

Deep Learning Reconstruction Helps to Achieve Diagnostic-like Image Quality in MR Radiation Therapy of Brain

Improved Brain MR Imaging from a Compact, Lightweight 3T Scanner with High-Performance Gradients.

A low-cryogen, compact 3T (C3T) MRI scanner with high-performance gradients capable of simultaneously achieving 80 mT/m gradient amplitude and 700 T/m/second slew rate has been in use to study research patients since March 2016 but has not been implemented in the clinical practice. To compare head MRI examinations obtained with the C3T system and a conventional whole-body 3T (WB3T) scanner in seven parameters across five commonly used brain imaging sequences. Prospective. Thirty patients with a clinically indicated head MRI. 3T; T1 FLAIR, T1 MP-RAGE, 3D T2 FLAIR, T2 FSE, and DWI. All patients tolerated the scans well. Three board-certified neuroradiologists scored the comparative quality of C3T and WB3T images in blinded fashion using a five-point Likert scale in terms of: signal-to-noise ratio, lesion conspicuity, motion artifact, gray/white matter contrast, cerebellar folia, susceptibility artifact, and overall quality. Left-sided, right-sided, and two-sided Wilcoxon signed rank test; Fisher's method. A P value <0.05 was considered statistically significant. The C3T system performed better than the WB3T in virtually all comparisons, except for motion artifacts for the T1 FLAIR and T1 MP-RAGE sequences, where the WB3T system was deemed better. When combining all sequences together, the C3T system outperformed the WB3T system in all image quality parameters evaluated, except for motion artifact (P=0.13). The C3T scanner provided better overall image quality for all sequences, and performed better in all individual categories, except for motion artifact on the T1 FLAIR and T1 MP-RAGE. 2 TECHNICAL EFFICACY STAGE: 1.

Quantity and Morphology of Perivascular Spaces: Associations With Vascular Risk Factors and Cerebral Small Vessel Disease.

Perivascular spaces (PVSs) are important component of the brain glymphatic system. While visual rating has been widely used to assess PVS, computational measures may have higher sensitivity for capturing PVS characteristics under disease conditions. To compute quantitative and morphological PVS features and to assess their associations with vascular risk factors and cerebral small vessel disease (CSVD). Prospective. One hundred sixty-one middle-aged/later middle-aged subjects (age=60.4 ± 7.3). 3D T1-weighted, T2-weighted and T2-FLAIR sequences, and susceptibility-weighted multiecho gradient-echo sequence on a 3 T scanner. Automated PVS segmentation was performed on sub-millimeter T2-weighted images. Quantitative and morphological PVS features were calculated in white matter (WM) and basal ganglia (BG) regions, including volume, count, size, length (Lmaj ), width (Lmin ), and linearity. Visual PVS scores were also acquired for comparison. Simple and multiple linear regression analyses were used to explore the associations among variables. WM-PVS visual score and count were associated with hypertension (β=0.161, P < 0.05; β=0.193, P < 0.05), as were BG-PVS rating score, volume, count and Lmin (β=0.197, P < 0.05; β=0.170, P < 0.05; β=0.200, P < 0.05; β=0.172, P < 0.05). WM-PVS size was associated with diabetes (β=0.165, P < 0.05). WM-PVS and BG-PVS were associated with CSVD markers, especially white matter hyperintensities (WMHs) (P < 0.05). Multiple regression analysis showed that WM/BG-PVS quantitative measures were widely associated with vascular risk factors and CSVD markers (P < 0.05). Morphological measures were associated with WMH severity in WM region and also associated with lacunes and microbleeds (P < 0.05) in BG region. These novel PVS measures may capture mild PVS alterations driven by different pathologies. 2 TECHNICAL EFFICACY: Stage 2.

A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images.

Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images. Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer's Disease Neuroimaging Initiative-3 (n = 20). StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations. A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

Added Value of Contrast-enhanced 3D-FLAIR MR Imaging for Differentiating Cystic Pituitary Adenoma from Rathke's Cleft Cyst.

PurposeHalf of the surgically proven Rathke’s cleft cysts (RCCs) can be preoperatively misdiagnosed as cystic pituitary adenoma (CPA). We aimed to evaluate the usefulness of contrast-enhanced (CE) 3D T2 fluid-attenuated inversion-recovery (3D T2-FLAIR) imaging for differentiating between CPA and RCC.MethodsThis retrospective study included six patients with RCC (all pathologically confirmed) and six patients with CPA (five pathologically confirmed, one clinically diagnosed). The 12 patients underwent pre- and post-contrast T1-weighted (T1W)- and 3D T2-FLAIR imaging at 3T. Based on the degree of enhancement of the lesion wall, two radiologists independently scored the images using a 3-point grading system. Interobserver agreement was calculated by using the κ coefficient. The statistical significance of grading differences was analyzed with the Mann–Whitney U-test. Another neuroradiologist first interpreted conventional MR images (1st session), and then the reader read images to which the 3D T2-FLAIR images had been added (2nd session). Sensitivity, specificity, and accuracy of the reader’s interpretation were calculated.ResultsInterobserver agreement for post-contrast T1W- and 3D T2-FLAIR images was excellent (κ = 1.000 and 0.885, respectively). Although the mean enhancement grade on post-contrast T1W images of RCCs and CPAs was not significantly different, on post-contrast 3D T2-FLAIR images it was significantly higher for RCCs and CPAs (P < 0.05). Three CPAs (50%) showed remarkable, donut-like enhancement along the inner margin of the cyst on CE-3D T2-FLAIR images; this was not the case on CE-T1W images. The sensitivity, specificity, and accuracy of the 2nd session were 1.00, 0.83, and 0.92, respectively, which were improved compared to the 1st session (1.00, 0.50, and 0.75, respectively).ConclusionCE-3D FLAIR imaging is useful for discriminating CPAs and RCCs.

Sensitive Detection of Infratentorial and Upper Cervical Cord Lesions in Multiple Sclerosis with Combined 3D FLAIR and T2-Weighted (FLAIR3) Imaging.

Infratentorial and spinal cord lesions are important for diagnosing and monitoring multiple sclerosis, but they are difficult to detect on conventional MR imaging. We sought to improve the detection of infratentorial and upper cervical cord lesions using composite FLAIR3 images. 3D T2-weighted FLAIR and 3D T2-weighted images were acquired in 30 patients with MS and combined using the FLAIR3 formula. FLAIR3 was assessed against 3D T2-FLAIR by comparing the number of infratentorial and upper cervical cord lesions per subject using the Wilcoxon signed rank test. Intrarater and interrater reliability was evaluated using the intraclass correlation coefficient. The number of patients with and without ≥1 visible infratentorial/spinal cord lesion on 3D T2-FLAIR versus FLAIR3 was calculated to assess the potential impact on the revised MS diagnostic criteria. Compared with 3D T2-FLAIR, FLAIR3 detected significantly more infratentorial (mean, 4.6 ± 3.6 versus 2.0 ± 1.8, P < .001) and cervical cord (mean, 1.58 ± 0.94 versus 0.46 ± 0.45, P < .001) lesions per subject. FLAIR3 demonstrated significantly improved interrater reliability (intraclass correlation coefficient = 0.77 [95% CI, 0.63-0.87] versus 0.60 [95% CI, 0.40-0.76] with 3D T2-FLAIR, P = .019) and a tendency toward a higher intrarater reliability (0.86 [95% CI, 0.73-0.93] versus 0.79 [95% CI, 0.61-0.89], P = .23). In our cohort, 20%-30% (47%-67%) of the subjects with MS had ≥ 1 infratentorial (cervical cord) lesion visible only on FLAIR3. FLAIR3 provides higher sensitivity than T2-FLAIR for the detection of MS lesions in infratentorial brain parenchyma and the upper cervical cord.

Olfactory Bulb Signal Abnormality in Patients with COVID-19 Who Present with Neurologic Symptoms.

Unique among the acute neurologic manifestations of Severe Acute Respiratory Syndrome coronavirus 2, the virus responsible for the coronavirus disease 2019 (COVID-19) pandemic, is chemosensory dysfunction (anosmia or dysgeusia), which can be seen in patients who are otherwise oligosymptomatic or even asymptomatic. The purpose of this study was to determine if there is imaging evidence of olfactory apparatus pathology in patients with COVID-19 and neurologic symptoms. A retrospective case-control study compared the olfactory bulb and olfactory tract signal intensity on thin-section T2WI and postcontrast 3D T2 FLAIR images in patients with COVID-19 and neurologic symptoms, and age-matched controls imaged for olfactory dysfunction. There was a significant difference in normalized olfactory bulb T2 FLAIR signal intensity between the patients with COVID-19 and the controls with anosmia (P = .003). Four of 12 patients with COVID-19 demonstrated intraneural T2 signal hyperintensity on postcontrast 3D T2 FLAIR compared with none of the 12 patients among the controls with anosmia (P = .028). Olfactory bulb 3D T2 FLAIR signal intensity was greater in the patients with COVID-19 and neurologic symptoms compared with an age-matched control group with olfactory dysfunction, and this was qualitatively apparent in 4 of 12 patients with COVID-19. Analysis of these preliminary finding suggests that olfactory apparatus vulnerability to COVID-19 might be supported on conventional neuroimaging and may serve as a noninvasive biomarker of infection.