Fluid-attenuated Inversion Recovery Magnetic Resonance Imaging Research Articles

Effect of white matter hyperintensity on dopamine transporter availability of striatum measured by F-18 FP-CIT PET.

We aimed to evaluate the white matter hyperintensity (WMH) effect on dopamine transporter availability (DAT) of striatum. A total of 48 patients who showed visually normal F-18 FP-CIT uptake were included in this study. Each FP-CIT image were pre-processed using SPM12. Co-registration and spatial normalization of FP-CIT image conducted using T1-weighted magnetic resonance imaging (MRI). And then smoothing of normalized FP-CIT image was performed. Intensity normalization was performed using cerebellum as a reference region. With pre-defined volume of interest template, the specific binding ratio (SBR) of both side of caudate nucleus and putamen was calculated. Fluid attenuated inversion recovery MRI scans were used to evaluate WMH number and volume. SBRs of left and right caudate nucleus were correlated with age (r = -0.615; p < 0.0001; n = 48, r = -0.607; p < 0.0001; n = 48, respectively), high density lipoprotein cholesterol (r = 0.296; p = 0.041; n = 48, r = 0.29; p = 0.0455; n = 48, respectively), and WMH number (r = -0.459; p = 0.001; n = 48, r = -0.481; p = 0.0005; n = 48, respectively) and volume (r = -0.407; p = 0.0041; n = 48, r = -0.428; p = 0.0024; n = 48, respectively). DAT availability of patients who showed visually normal F-18 FP-CIT uptake was correlated with number and volume of WMH.

Semi-Supervised Learning in Medical MRI Segmentation: Brain Tissue with White Matter Hyperintensity Segmentation Using FLAIR MRI.

White-matter hyperintensity (WMH) is a primary biomarker for small-vessel cerebrovascular disease, Alzheimer’s disease (AD), and others. The association of WMH with brain structural changes has also recently been reported. Although fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) provide valuable information about WMH, FLAIR does not provide other normal tissue information. The multi-modal analysis of FLAIR and T1-weighted (T1w) MRI is thus desirable for WMH-related brain aging studies. In clinical settings, however, FLAIR is often the only available modality. In this study, we thus propose a semi-supervised learning method for full brain segmentation using FLAIR. The results of our proposed method were compared with the reference labels, which were obtained by FreeSurfer segmentation on T1w MRI. The relative volume difference between the two sets of results shows that our proposed method has high reliability. We further evaluated our proposed WMH segmentation by comparing the Dice similarity coefficients of the reference and the results of our proposed method. We believe our semi-supervised learning method has a great potential for use for other MRI sequences and will encourage others to perform brain tissue segmentation using MRI modalities other than T1w.

MRI-based radiomics signature for the prediction of response of lung cancer brain metastases after whole-brain radiotherapy.

e21096 MRI-based Radiomics signature for the Prediction of Response of Lung Cancer Brain Metastases After Whole-Brain Radiotherapy Background: Local response prediction for brain metastases (BMs) from lung cancer after Whole-Brain Radiotherapy (WBRT) is challenging, as existing criteria are based solely on unidimensional measurements. This study sought to determine whether radiomic features of lung cancer BMs derived from pre-treatment magnetic resonance imaging (MRI) could be used to predict local response following WBRT. Methods: A total of 88 Lung Cancer patients with BMs treated with WBRT were analyzed. After volumes of interest were drawn, 944 radiomic features including first-order, shape, Gray Level Co-occurrence Matrix (GLCM), Gray Level Dependence Matrix (GLDM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), Neighborhood Gray Tone Difference Matrix (NGTDM), and Laplacian of Gaussian (LoG) features were extracted, using the baseline pre-treatment post-contrast T1 (T1c) and T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences, respectively. Local response status was determined by contrasting the baseline and follow-up MRI according to the RANO-BM criteria. The independent samples t test or Mann-Whitney U test, and then least absolute shrinkage and selection operator (LASSO) were used for dimensionality reduction and feature selection. An adaboost classifier was trained using the selected radiomic features and evaluated using the area under the receiver operating characteristic curve (AUC) in both the training and testing sets. Other discrimination metrics, including classification accuracy, positive predictive value (PPV), negative predictive value (NPV), sensitivity, and specificity, were also calculated. Results: The optimal radiomics signature was developed based on a multivariable logistic regression with 4, 5, 6 radiomic features on T1c, T2 FLAIR and T1c+T2 FLAIR, respectively. The radiomics model based on T1c features presented the AUC of (0.920 vs. 0.805, respectively) for both the training and testing sets, followed by T2 FLAIR features (0.893 vs. 0.701, respectively), and T1c+T2 FLAIR features (0.971 vs. 0.857, respectively). The classification accuracy of the radiomics model also well predicted the local response of BMs for both the the training and testing sets (T1c: 82.9% vs. 77.8%, T2 FLAIR: 82.9% vs. 77.8%, T1c+T2 FLAIR: 90.0% vs. 77.8%, respectively). Conclusions: Radiomics holds promise for predicting local tumor response following WBRT in patients with lung cancer and brain metastases. A predictive model built on radiomic features from an institutional cohort performed well on cross-validation testing. These results warrant further validation in independent datasets. Such work could prove invaluable for guiding management of individual patients and assessing outcomes of novel interventions.

Correlation of 4\u2032-[methyl-11C]-thiothymidine PET with Gd-enhanced and FLAIR MRI in patients with newly diagnosed glioma

PurposeTo elucidate the biological association between tumor proliferation, tumor infiltration and neovascularization, we analyzed the association between volumetric information of 4′-[methyl-11C]thiothymidine (4DST) positron emission tomography (PET) and fluid-attenuated inversion recovery (FLAIR) and T1-weighted gadopentetate dimeglumine (Gd)-enhanced magnetic resonance imaging (MRI), in patients with newly diagnosed glioma.MethodsA total of 23 patients with newly diagnosed glioma who underwent both 4DST PET/CT and Gd-enhanced MRI before therapy were available for a retrospective analysis of prospectively collected data. The maximum standardized uptake value (SUVmax) for tumor (T) and the mean SUV for normal contralateral hemisphere (N) were calculated, and the tumor-to-normal (T/N) ratio was determined. Proliferative tumor volume (PTV) from 4DST PET and the volume of Gd enhancement (GdV) and hyperintense region on FLAIR (FLAIRV) from MRI were calculated.ResultsAll gliomas but 3 diffuse astrocytomas and one anaplastic astrocytoma had 4DST uptake and Gd enhancement on MRI. There was no significant difference between PTV and GdV although the exact edges of the tumor differed in each modality. The FLAIRV was significantly larger than PTV (P < 0.001). Significant correlations between PTV and GdV (ρ = 0.941, P < 0.001) and FLAIRV (ρ = 0.682, P < 0.001) were found.ConclusionThese preliminary results indicate that tumor proliferation assessed by 4DST PET is closely associated with tumor-induced neovascularization determined by Gd-enhanced MRI in patients with newly diagnosed glioma.

Prognostic Value of a Structural Brain MRI Score in the Acute Phase of Aneurysmal Subarachnoid Hemorrhage: A Pilot Study

Aneurysmal subarachnoid hemorrhage (aSAH) is associated with high morbidity and mortality despite advances in management. We evaluated the prognostic significance of a qualitative score using brain magnetic resonance imaging (MRI) features obtained early after aSAH. Patients with aSAH were enrolled in a prospective observational cohort and underwent brain MRI during their acute hospitalization. MRIs were rated using a scoring system that considers the anatomical location of signal intensity changes on diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences. The relationship between MRI scores and functional outcome defined by modified Rankin scale (mRS) at 6months was evaluated in uni- and multivariable models. The cohort included 45 aSAH patients (median World Federation of Neurologic Surgeons (IQR) 2 (1-4)) who underwent brain MRI a mean (SD) of 9.0 ± 8.0days after aSAH. At 6months after aSAH, 26 patients had achieved a favorable outcome (mRS ≤ 2) while 15 had an unfavorable outcome (mRS > 2). Deep gray nuclei (DGN) score (p = 0.016), cortex + DGN score (p = 0.015), FLAIR score (p = 0.016), DWI score (p = 0.0045), and overall score (p = 0.0081) were significantly lower in patients with favorable outcome compared to those with unfavorable outcome. However, MRI scores were not independent predictors of outcome in multivariable models adjusting for admission Hunt and Hess, Glasgow Coma Scale, or World Federation of Neurologic Surgeons scales. In this pilot study, a qualitative scoring system using anatomically defined MRI FLAIR and DWI signal abnormalities identified in the acute phase of aSAH was linked to 6-month functional outcome. However, these scores did not add prognostic value to established indices of neurological severity.

Intracranial volume segmentation for neurodegenerative populations using multicentre FLAIR MRI

Intracranial volume (ICV) segmentation, also known as brain extraction or skull-stripping, is a critical preprocessing step in analytical pipelines for studying neurodegenerative diseases in magnetic resonance imaging (MRI). While the fluid-attenuated inversion recovery (FLAIR) MRI modality has emerged as an important sequence for analyzing cerebrovascular and neurodegenerative disease, most existing automated ICV segmentation methods have been developed for T1-weighted or multi-modal inputs. Additionally, many methods have been designed using single centre data of healthy subjects and encounter difficulties using images with varying acquisition parameters and neurodegenerative pathology. In this work, we develop and evaluate 2 traditional and 8 deep learning algorithms for ICV segmentation in FLAIR MRI. Training and testing were completed on 175 ​vol (8317 images) from 2 dementia and 1 vascular disease cohort. A human phantom FLAIR MRI dataset from a repeatedly scanned, healthy individual was also utilized for reliability analysis. Images were acquired from 47 imaging centres with varying scanners and parameters. To measure and compare performance, we present a novel framework for evaluating the effectiveness of computer generated segmentations on multicentre datasets. The evaluation framework includes assessments of algorithm accuracy, generalization capabilities, robustness to pathology and spatial location, and volumetric measurement reliability – all important dimensions for establishing proof of effectiveness (a prerequisite to clinical translation). The top performing method was a multiple resolution U-Net (MultiResUNet), which achieved a mean Dice similarity coefficient greater than 98% and was robust across pathology levels and spatial locations. Our results confirm a FLAIR-based ICV analytical pipeline can alone be utilized for large-scale neurodegenerative disease research. The presented evaluation framework can be deployed by other researchers to assess the viability of tools proposed for automated analysis of diverse, clinical MRI datasets.

Evaluation of brain changes in systemic sclerosis (SSc) patients using two different techniques of MRI: Is it really worthy?

BackgroundSystemic sclerosis (SSc) is a rare chronic multi-system autoimmune disease of unknown cause and a complex pathogenesis. The hallmark of the disease is microvascular vasculopathy which results in tissue ischemia with recurrent episodes of reperfusion. Diffusion-weighted (DW) Magnetic Resonance imaging (MRI) is an excellent tool for the detection of activity of any vascular or inflammatory lesions. ObjectivesDetect brain changes in systemic sclerosis patients with asymptomatic CNS manifestations using fluid attenuation inversion recovery (FLAIR) weighted sequence and diffusion-weighted (DW) sequence MRI. MethodsFifteen systemic sclerosis female patients aged 27–60 years old with disease duration of 1–20 years with no CNS clinical manifestations were included. A controlled group of 14 clinically normal persons, age and sex matched. Both groups were subjected to brain MR examination at 1.5T; a FLAIR weighted sequence and a DW sequence. SPSS (version 20) was used for statistical analysis. Results37 white matter hyperintense lesions (≤2 to ≥ 5mm in diameter) were detected in patient group using FLAIR weighted MRI while diffusion-weighted MRI failed to detect the same lesions. A non-significant relation (P=.259) between the presence of white matter hyperintense lesions and the severity of peripheral vascular affection of the disease was observed. ConclusionsAsymptomatic central nervous system vasculopathy is detected in systemic sclerosis using FLAIR MRI, while diffusion MRI failed to detect such lesions. These findings suggest a non-inflammatory form of central nervous system microvasculopathy in SSc patients.

Differential Diagnosis of Endolymphatic Hydrops Between "Probable" and "Definite" Ménière's Disease via Magnetic Resonance Imaging.

To investigate the grade of endolymphatic hydrops in patients with "probable" and "definite" Ménière's disease via magnetic resonance imaging (MRI) and to determine whether MRI could assist clinicians in differential diagnosis between probable and definite Ménière's disease. Prospective study. Three-dimensional FLAIR MRI (fluid-attenuated inversion recovery) to examine endolymphatic hydrops in Ménière's disease. A total of 51 patients diagnosed with probable (n = 20) or definite (n = 31) unilateral Ménière's disease were enrolled. Three-dimensional FLAIR MRI was performed to evaluate the grade of endolymphatic hydrops. The differences in endolymphatic hydrops between the probable and definite groups were analyzed. The grade of endolymphatic hydrops was more severe in the definite group than in the probable group (P < .05). MRI revealed a higher grade of endolymphatic hydrops in patients with definite Ménière's disease than in patients with probable Ménière's disease. As a result, it may be clinically useful and an effective tool in the differentiation between definite and probable Ménière's disease.

Radiogenomic modeling predicts survival-associated prognostic groups in glioblastoma.

BackgroundCombined whole-exome sequencing (WES) and somatic copy number alteration (SCNA) information can separate isocitrate dehydrogenase (IDH)1/2-wildtype glioblastoma into two prognostic molecular subtypes, which cannot be distinguished by epigenetic or clinical features. The potential for radiographic features to discriminate between these molecular subtypes has yet to be established.MethodsRadiologic features (n = 35 340) were extracted from 46 multisequence, pre-operative magnetic resonance imaging (MRI) scans of IDH1/2-wildtype glioblastoma patients from The Cancer Imaging Archive (TCIA), all of whom have corresponding WES/SCNA data. We developed a novel feature selection method that leverages the structure of extracted MRI features to mitigate the dimensionality challenge posed by the disparity between a large number of features and the limited patients in our cohort. Six traditional machine learning classifiers were trained to distinguish molecular subtypes using our feature selection method, which was compared to least absolute shrinkage and selection operator (LASSO) feature selection, recursive feature elimination, and variance thresholding.ResultsWe were able to classify glioblastomas into two prognostic subgroups with a cross-validated area under the curve score of 0.80 (±0.03) using ridge logistic regression on the 15-dimensional principle component analysis (PCA) embedding of the features selected by our novel feature selection method. An interrogation of the selected features suggested that features describing contours in the T2 signal abnormality region on the T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI sequence may best distinguish these two groups from one another.ConclusionsWe successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying IDH1/2-wildtype glioblastoma patient groups.

Clinical comparative analysis of monophasic and multiphasic acute disseminated encephalomyelitis in adults.

This study aims to explore the clinical features and prognostic factors for relapse of acute disseminated encephalomyelitis (ADEM) in adults. 56 patients with ADEM were retrospectively analyzed. The epidemiological characteristics, clinical manifestations, laboratory features, magnetic resonance imaging (MRI), treatment and prognosis data of these patients were analyzed using the χ2 test for categorical variables and Mann-Whitney U-test for continuous variables. Then, the clinical characteristics and recurrence factors were summarized. 56 patients with ADEM, based on the criteria of the International Pediatric Multiple Sclerosis Study Group, were recruited to the study. Among these patients, 31 were male and 25 were female. Furthermore, 13 patients had multiphasic ADEM, and 29 patients (52%) had definite incentive factors before onset. The commonest presenting symptoms and signs were fever (36%), disturbance of consciousness (52%), mental disorder (38%), seizure (14%), headache and dizziness (43%), optic neuritis (34%), autonomic nervous system symptoms (43%), limb paralysis or abnormal sensation (73%), and unilateral or bilateral pyramidal tract signs (48%). Inflammatory changes in the cerebrospinal fluid were prominent. MRI T2-weighted and fluid-attenuated inversion recovery images displayed multiple or large flaky high signals, and the lesions were usually different in the number and distribution of these lesions. Intravenous corticosteroids and/or immunoglobulin were still important treatments in the acute phase. After treatment, 38 patients completely recovered, 9 patients had neurologic deficits, and 9 patients died. ADEM in adults is not uncommon, its clinical features are complex and varied, and some of these are multiphasic. There may be some potential clinical predictors at first onset.

Influence of simultaneous pressor and vasodilatory agents on the evolution of infarct growth in experimental acute middle cerebral artery occlusion

BackgroundThis study sought to test the hypothesis that simultaneous central blood pressure elevation and potent vasodilation can mitigate pial collateral-dependent infarct growth in acute ischemic stroke.MethodsTwenty mongrel canines (20–30 kg)...

Leptomeningeal Enhancement on 3D-FLAIR MRI in Multiple Sclerosis: Systematic Observations in Clinical Practice.

Meningeal inflammation is implicated in cortical demyelination and disability progression in multiple sclerosis (MS). Gadolinium (Gd)-enhanced 3-dimensional (3D) FLAIR (fluid-attenuated inversion recovery) magnetic resonance imaging (MRI) can identify leptomeningeal enhancement (LME) in MS. Further characterization is needed to determine if LME is an imaging biomarker for meningeal inflammation. We sought to characterize the natural history of LME in the community setting, including persistence/resolution, effect of disease-modifying therapy, scanner variability, timing of acquisition, and imaging pitfalls that may lead to misinterpretation. A total of 341 MRI exams with Gd-enhanced 3D-FLAIR were reviewed in MS and non-MS patients to determine frequency of enhancement by MS subtype and association with therapy. A phantom was used to assess scanner variability. Two MS patients with seven LME were imaged at four postinjection time points to generate time-intensity curves. Imaging pitfalls were compiled. A total of 16.6% (40/241) of MS patients revealed LME compared to 8% (8/100) in non-MS patients (P = .04). There was no association with MS subtype, therapy, or disease activity. Detection using General Electric's version of 3D-FLAIR (29%) was greater than with Siemen's 3D-FLAIR (12%) at 1.5T (Tesla) (P<.001). Lesions were generally stable but resolved in 2 patients following high-dose steroids. LME kinetics were heterogeneous, even within patients, without uniform optimal time for acquisition. Enhancement curves exhibited three different variations, similar to the two-compartment model. Imaging pitfalls included enhancements of uncertain biologic significance, cortical veins and anatomic structures, and imaging artifacts. Awareness of LME characteristics, variability with imaging parameters, and imaging pitfalls will facilitate determining the potential role as an imaging biomarker for meningeal inflammation.

Smart Identification of Topographically Variant Anomalies in Brain Magnetic Resonance Imaging Using a Fish School-Based Fuzzy Clustering Approach

Inaccuracies in anomaly prediction have become an alarming issue in the field of medical image analysis, and these quandaries have burgeoned due to the errors caused by the operator, instrument/device and environment, whereof, these troubles can be unanimously rectified with the advent of a novel segmentation approach proposed through this article. The novel approach encapsulates the functionary of spatially constrained fish school optimization (SCFSO) algorithm and interval type-II fuzzy logic system (IT2FLS) techniques, which resolves the erroneous prediction of anomalies present in various topographical locations in brain subjects of magnetic resonance imaging (MRI) modality. Huge datasets and complex tumor (anomalies) can be intervened and examined with ease by the developed approach, and this could be a proactive measure for being implemented or incorporated in clinical practice for the betterment of both doctors and patients, and it can perpetuate a profound experience to the doctors. The developed SCFSO-IT2FLS technique was applied to BRATS-SICAS dataset, and the evaluation metrics—namely, the Dice overlap index and sensitivity value were delivered as 96 ± 2.1 and 98 ± 1.1 by the proposed technique. These values are better than the conventional techniques and the proposed technique is applicable for the segmentation of T1-weighted, T2-weighted, and fluid attenuated inversion recovery MRI sequences of various axes coordination. A clear extraction of tumor region from nontumor region (edema) is rendered by the proposed technique and a therapeutic preplanning could always be made with such a provision/advantage.

Radiotherapy target volume definition in newly diagnosed high grade glioma using 18F-FET PET imaging and multiparametric perfusion MRI: A prospective study (IMAGG)

PurposeThe aim of this study was to prospectively investigate tumor volume delineation by amino acid PET and multiparametric perfusion magnetic resonance imaging (MRI) in patients with newly diagnosed, untreated high grade glioma (HGG). Materials and methodsThirty patients with histologically confirmed HGG underwent O-(2-[18F]-fluoroethyl)-l-tyrosine (18F-FET) positron emission tomography (PET), conventional Magnetic Resonance Imaging (MRI) as contrast-enhanced (CE) and fluid-attenuated inversion recovery (FLAIR) and multiparametric MRI as relative cerebral blood volume (rCBV) and permeability estimation map (K2). Areas of MRI volumes were semi-automatically segmented. The percentage overlap volumes, Dice and Jaccard spatial similarity coefficients (OV, DSC, JSC) were calculated. ResultsThe 18F-FET tumor volume was significantly larger than the CE volume (median 43.5 mL (2.5–124.9) vs. 23.8 mL (1.4–80.3), p = 0.005). The OV between 18F-FET uptake and CE volume was low (median OV 0.59 (0.10–1)), as well as spatial similarity (median DSC 0.52 (0.07–0.78); median JSC 0.35 (0.03–0.64)). Twenty-five patients demonstrated both rCBV and CE on MRI: The median rCBV tumor volume was significantly smaller than the median CE volume (p < 0.001). The OV was high (median 0.83 (0.54–1)), but the spatial similarity was low (median DSC 0.45 (0.04–0.83); median JSC 0.29 (0.07–0.71)). Twenty-eight patients demonstrated both K2 and CE on MRI. The median K2 tumor volume was not significantly larger than the median CE volume. The OV was high (median OV 0.90 (0.61–1)), and the spatial similarity was moderate (median DSC 0.75 (0.01–0.83); median JSC 0.60 (0.11–0.89)). ConclusionWe demonstrated that multiparametric perfusion MRI volumes (rCBV, K2) were highly correlated with CE T1 gadolinium volumes whereas 18F-FET PET provided complementary information, suggesting that the metabolically active tumor volume in patients with newly diagnosed untreated HGG is critically underestimated by contrast enhanced MRI. 18F-FET PET imaging may help to improve target volume delineation accuracy for radiotherapy planning.

Inner ear fluid-attenuated inversion recovery MRI signal intensity in dogs with vestibular disease.

The inner ear contains endolymph and perilymph. The second is comparable and in continuity with the cerebrospinal fluid (CSF) so it is expected to suppress in fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) if normal. Even though inner ear FLAIR abnormalities have been extensively described in humans with inner ear disease, its diagnostic value in dogs is yet to be proven. The goal of this retrospective cohort study was to investigate the diagnostic utility of FLAIR MRI in dogs with vestibular disease. A review of medical records identified 101 dogs that had brain MRI performed because of vestibular signs. Based on the final diagnosis, patients were allocated to three groups: otitis media/interna, idiopathic vestibular disease, and central vestibular disease. Additionally, a control group (n=73) included dogs with normal MRI and without vestibular signs. Inner ears were delineated using a region of interest, and signal intensity was measured in FLAIR and T2-weighted images. The percentages of suppression in FLAIR were calculated and compared between affected and unaffected sides of each individual and between groups using a general linear mixed model. Correlation between suppression and CSF cell count and protein concentration was assessed. Affected inner ears in dogs with otitis media/interna had decreased suppression in FLAIR compared to the unaffected side (P<.001), and all other groups (P<.01). No significant correlation was detected between CSF results and suppression. These results show the diagnostic value of FLAIR in otitis media/interna due to lack of suppression in the affected inner ear.

DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images

PurposeGliomas are the most common and aggressive type of brain tumors due to their infiltrative nature and rapid progression. The process of distinguishing tumor boundaries from healthy cells is still a challenging task in the clinical routine. Fluid-attenuated inversion recovery (FLAIR) MRI modality can provide the physician with information about tumor infiltration. Therefore, this paper proposes a new generic deep learning architecture, namely DeepSeg, for fully automated detection and segmentation of the brain lesion using FLAIR MRI data.MethodsThe developed DeepSeg is a modular decoupling framework. It consists of two connected core parts based on an encoding and decoding relationship. The encoder part is a convolutional neural network (CNN) responsible for spatial information extraction. The resulting semantic map is inserted into the decoder part to get the full-resolution probability map. Based on modified U-Net architecture, different CNN models such as residual neural network (ResNet), dense convolutional network (DenseNet), and NASNet have been utilized in this study.ResultsThe proposed deep learning architectures have been successfully tested and evaluated on-line based on MRI datasets of brain tumor segmentation (BraTS 2019) challenge, including s336 cases as training data and 125 cases for validation data. The dice and Hausdorff distance scores of obtained segmentation results are about 0.81 to 0.84 and 9.8 to 19.7 correspondingly.ConclusionThis study showed successful feasibility and comparative performance of applying different deep learning models in a new DeepSeg framework for automated brain tumor segmentation in FLAIR MR images. The proposed DeepSeg is open source and freely available at https://github.com/razeineldin/DeepSeg/.

Abstract 180: Women Have Higher Neurological Severity and Worse Functional Outcome Than Men With Similar Infarct Volume and Leukoaraiosis Burden

Background: Women, compared with men, tend to have worse functional outcome after stroke. The gender effect is not fully explained by age, pre-stroke dependency, and stroke severity. We hypothesized that it might be due to different prognostic impacts of stroke-related brain lesions in women vs. men. Objective: To investigate if the effects of acute infarct volume and white matter hyperintensity (WMH) volume on initial stroke severity and 3-month functional outcome are modified by gender. Methods: This prospective study included 6748 patients with acute ischemic stroke (&lt;1-week) recruited (May 2011 to February 2013) consecutively from 11 academic stroke centers. The volumes (% of brain parenchyma) of acute infarct and WMH were measured in all patients by using diffusion-weighted magnetic resonance images (MRIs) and fluid-attenuated inversion recovery MRIs. Multivariable analyses were performed to test gender-related interactions in the relationship of MR lesion (infarct or WMH) volume (quartiles) with admission NIH stroke scale (NIHSS) score or 3-month modified Rankin scale (mRS) score, after adjusting for relevant covariates. Results: Women, compared with men, were older (mean 72 vs. 65, p&lt;0.01), and had more risk factors, a higher admission NIHSS score (median 4 vs. 3; p&lt;0.01), and a higher WMH volume (median 0.98% vs. 0.74%, p&lt;0.01). Acute infarct volume was not different between the two groups (median 0.15% vs. 0.16%, p=0.27), however its impact on the NIHSS score was greater in women than in men (adjusted analysis, p&lt;0.01). At 3 months, women had worse functional outcome than men (mRS&gt;2: adjusted OR [95%], 1.36 [1.09-1.69]). The association of WMH volume with 3-month mRS score was significantly modified by gender (p-for-interaction=0.049), with the WMH effect being greater in women (adjusted ORs of the highest vs. lowest quartile for the worse outcome: 2.47 in women vs. 1.51 in men). Conclusion: Women, compared with men, are probably more susceptible to the adverse effects of infarct volume and WMH volume on stroke severity and functional outcome.

Clinical Relevance of Cerebral Small Vessel Diseases.

Clinical Relevance of Cerebral Small Vessel Diseases.

7T MRI cerebral leptomeningeal enhancement is common in relapsing-remitting multiple sclerosis and is associated with cortical and thalamic lesions

Background: Meningeal inflammation may contribute to gray matter (GM) involvement in multiple sclerosis (MS) and is proposed to manifest as magnetic resonance imaging (MRI) leptomeningeal enhancement (LME). Objective: To investigate how LME relates to GM lesions in relapsing-remitting multiple sclerosis (RRMS) at 7T. Methods: A total of 30 RRMS subjects (age (mean ± standard deviation (SD)): 44.0 ± 11.3 years, 93% on disease-modifying treatment) and 15 controls underwent gadolinium-enhanced three-dimensional (3D) MP2RAGE (magnetization-prepared 2 rapid gradient-echo) and fluid-attenuated inversion recovery (FLAIR) MRI. LME, cortical lesions (CLs), thalamic lesions (TLs), and white matter (WM) lesions were expert-quantified. Wilcoxon rank-sum, two-sample t-tests, Spearman correlations, and regression models were employed. Results: Two-thirds (20/30) of MS subjects and 1/15 controls (6.7%) had LME. LME+ MS subjects had 2.7 ± 1.5 foci, longer disease duration (14.9 ± 10.4 vs. 8.1 ± 5.7 years, p = 0.028), increased CL number (21.5 ± 12.6 vs. 5.5 ± 5.0, p < 0.001) and volume (0.80 ± 1.13 vs. 0.13 ± 0.13 mL, p = 0.002), and increased TL number (3.95 ± 2.11 vs. 0.70 ± 1.34, p < 0.001) and volume (0.106 ± 0.09 vs. 0.007 ± 0.01 mL, p < 0.001) versus LME– subjects. LME focus number correlated more highly with CL (rs = 0.50, p = 0.01) and TL (rs = 0.81, p < 0.001) than WM lesion (rs = 0.34, p > 0.05) volume. Similar LME–CL number associations were observed in unadjusted and WM lesion–adjusted comparisons (both p < 0.001). Conclusion: Cerebral LME is common in RRMS at 7T and is independently associated with GM injury. We hypothesize that cerebrospinal fluid (CSF)-related inflammation links cortical and thalamic injury.

The prognostic value and pathophysiologic significance of three-dimensional fluid-attenuated inversion recovery (3D-FLAIR) magnetic resonance imaging in idiopathic sudden sensorineural hearing loss: A systematic review and meta-analysis.

The underlying pathophysiology of idiopathic sudden sensorineural hearing loss (ISSNHL) is still unknown. However, an increasing number of observational studies report intralabyrinthine signal alterations in patients with ISSNHL using three-dimensional fluid-attenuated inversion recovery (3D-FLAIR) magnetic resonance imaging (MRI). These findings warrant a meta-analysis. To conduct a meta-analysis assessing the value of 3D-FLAIR MRI in identifying possible underlying labyrinthine pathophysiologic mechanisms and prognostication in patients with ISSNHL. Two reviewers independently searched the Pubmed, Embase and Cochrane Library from inception until October 10, 2018 and evaluated eligibility based on titles and abstracts of all retrieved studies. All studies reporting on 3D-FLAIR imaging in ISSNHL were included. Subsequently, the full text of eligible studies were evaluated. Adhering to the MOOSE guideline, two independent reviewers extracted data, assessed risk of bias and evaluated the relevance and quality of evidence. Data on the number of patients and events were extracted and hearing levels were converted to standardised mean differences (SMD) for conducting meta-analyses. Random effects models for meta-analyses were applied. Eight observational studies met our inclusion criteria (n=638 patients). In 29%, high signal intensity was found on 3D-FLAIR imaging, suggesting labyrinthine pathology (labyrinthitis [79%], intralabyrinthine haemorrhage [21%]). High signal intensity on 3D-FLAIR was associated with poorer hearing (SMD: 14dB, 95% CI 5.67-22.94) and vertigo (RR: 1.92, 95% CI 1.16-3.17) at baseline. Multivariate analyses demonstrated that patients with high 3D-FLAIR signal intensity had 21dB lower final hearing pure-tone averages (SMD: 21dB, 95% CI 9.08-33.24). Three-dimensional fluid-attenuated inversion recovery MR imaging can identify an underlying labyrinthine condition in up to 29% of patients with sudden hearing loss in whom previously no cause could be identified. Their final pure-tone averages are more than 20dB worse than 3D-FLAIR-negative patients, suggesting more severe labyrinthine damage. Findings such as these may contribute to our understanding of pathophysiologic mechanisms of ISSNHL.