Fluid-attenuated Inversion Recovery Data Research Articles

A Multimodal Ensemble Deep Learning Model for Functional Outcome Prognosis of Stroke Patients.

The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS. We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3-6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3-6. Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3-6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004). The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.

Characterization of white matter lesions in multiple sclerosis using proton density and T1-relaxation measures

PurposeAlthough lesion dissemination in time is a defining characteristic of multiple sclerosis (MS), there is a limited understanding of lesion heterogeneity. Currently, conventional sequences such as fluid attenuated inversion recovery (FLAIR) and T1-weighted (T1W) data are used to assess MS lesions qualitatively. Estimating water content could provide a measure of local tissue rarefaction, or reduced tissue density, resulting from chronic inflammation. Our goal was to utilize the proton spin density (PD), derived from a rapid, multi-contrast STAGE (strategically acquired gradient echo) protocol to characterize white matter (WM) lesions seen on T2W, FLAIR and T1W data. Materials and methodsTwenty (20) subjects with relapsing-remitting MS were scanned at 3 T using T1W, T2-weighted, FLAIR and strategically acquired gradient echo (STAGE) sequences. PD and T1 maps were derived from the STAGE data. Disease severity scores, including Extended Disability Status Scale (EDSS) and Multiple Sclerosis Functional Composite (MSFC), were correlated with total, high PD and high T1 lesion volumes. A probability map of high PD regions and all lesions across all subjects was generated. Five perilesional normal appearing WM (NAWM) bands surrounding the lesions were generated to compare the median PD and T1 values in each band with the lesional values and the global WM. ResultsT1W intensity was negatively correlated with PD as expected (R = −0.87, p < 0.01, R2 = 0.756) and the FLAIR signal was suppressed for high PD volumes within the lesions, roughly for PD ≥ 0.85. The threshold for high PD and T1 regions was set to 0.909 and 1953.6 ms, respectively. High PD regions showed a high probability of occurrence near the boundary of the lateral ventricles. EDSS score and nine-hole peg test (dominant and non-dominant hand) were significantly correlated with the total lesion volume and the volumes of high PD and T1 regions (p < 0.05). There was a significant difference in PD/T1 values between the high PD/T1 regions within the lesions and the remaining lesional tissue (p < 0.001). In addition, the PD values of the first NAWM perilesional band directly adjacent to the lesional boundary displayed a significant difference (p < 0.05) compared to the global WM. ConclusionLesions with high PD and T1s had the highest probability of occurrence at the boundary of the lateral ventricles and likely represent chronic lesions with significant local tissue rarefaction. Moreover, the perilesional NAWM exhibited subtly increasing PD and T1 values from the NAWM up to the lesion boundary. Unlike on the T1 maps, the perilesional band adjacent to the lesion boundary possessed a significantly higher PD value than the global WM PD values. This shows that PD maps were sensitive to the subtle changes in NAWM surrounding the lesions.

Deep learning for the diagnosis of mesial temporal lobe epilepsy.

This study aimed to enable the automatic detection of the hippocampus and diagnose mesial temporal lobe epilepsy (MTLE) with the hippocampus as the epileptogenic area using artificial intelligence (AI). We compared the diagnostic accuracies of AI and neurosurgical physicians for MTLE with the hippocampus as the epileptogenic area. In this study, we used an AI program to diagnose MTLE. The image sets were processed using a code written in Python 3.7.4. and analyzed using Open Computer Vision 4.5.1. The deep learning model, which was a fine-tuned VGG16 model, consisted of several layers. The diagnostic accuracies of AI and board-certified neurosurgeons were compared. AI detected the hippocampi automatically and diagnosed MTLE with the hippocampus as the epileptogenic area on both T2-weighted imaging (T2WI) and fluid-attenuated inversion recovery (FLAIR) images. The diagnostic accuracies of AI based on T2WI and FLAIR data were 99% and 89%, respectively, and those of neurosurgeons based on T2WI and FLAIR data were 94% and 95%, respectively. The diagnostic accuracy of AI was statistically higher than that of board-certified neurosurgeons based on T2WI data (p = 0.00129). The deep learning-based AI program is highly accurate and can diagnose MTLE better than some board-certified neurosurgeons. AI can maintain a certain level of output accuracy and can be a reliable assistant to doctors.

Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data.

The biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal for brain tumor patients. As a result, a non-invasive computer-aided diagnosis (CAD) tool is required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been proposed for brain tumor grading. The MRI has several sequences, which can express tumor structure in different ways. However, a suitable MRI sequence for brain tumor classification is not yet known. The most common brain tumor is 'glioma', which is the most fatal form. Therefore, in the proposed study, to maximize the classification ability between low-grade versus high-grade glioma, three datasets were designed comprising three MRI sequences: T1-Weighted (T1W), T2-weighted (T2W), and fluid-attenuated inversion recovery (FLAIR). Further, five well-established convolutional neural networks, AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 were adopted for tumor classification. An ensemble algorithm was proposed using the majority vote of above five deep learning (DL) models to produce more consistent and improved results than any individual model. Five-fold cross validation (K5-CV) protocol was adopted for training and testing. For the proposed ensembled classifier with K5-CV, the highest test accuracies of 98.88 ± 0.63%, 97.98 ± 0.86%, and 94.75 ± 0.61% were achieved for FLAIR, T2W, and T1W-MRI data, respectively. FLAIR-MRI data was found to be most significant for brain tumor classification, where it showed a 4.17% and 0.91% improvement in accuracy against the T1W-MRI and T2W-MRI sequence data, respectively. The proposed ensembled algorithm (MajVot) showed significant improvements in the average accuracy of three datasets of 3.60%, 2.84%, 1.64%, 4.27%, and 1.14%, respectively, against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50.

The Boston ASL Template and Simulator: Initial development and implementation.

Templates are a hallmark of image analysis in neuroimaging. However, while numerous structural templates exist and have facilitated single-subject and large group studies, templates based on functional contrasts, such as arterial spin labeling (ASL) perfusion, are scarce, have an inherently low spatial resolution, and are not as widely distributed. Having such tools at one's disposal is desirable, for example, in the case of studies not acquiring structural scans. We here propose an initial development of an ASL adult template based on high-resolution fast spin echo acquisitions. High-resolution single-delay ASL, low-resolution multi-delay ASL, T1 -weighted magnetization prepared rapid acquisition 2 gradient echoes, and T2 fluid attenuated inversion recovery data were acquired in a cohort of 10 healthy volunteers (6 males and 4 females, 30± 7 years old). After offline reconstruction of high-resolution perfusion arterial transit time (ATT) and T1 maps, we built a multi-contrast template relying on the Advanced Normalization Toolbox multivariate template nonlinear construction framework. We offer examples for the registration of ASL data acquired with different sequences. Finally, we propose an ASL simulator based on our templates and a standard kinetic model that allows generating synthetic ASL contrasts based on user-specified parameters. Boston ASL Template and Simulator (BATS) offers high-quality, high-resolution perfusion-weighted and quantitative perfusion templates accompanied by ATT and different anatomical contrasts readily available in the Montreal Neurological Institute space. In addition, examples of use for data registration and as a synthetic contrast generator show various applications in which BATS could be used. We propose a new ASL template collection, named BATS, that also includes a simulator allowing the generation of synthetic ASL contrasts. BATS is available at http://github.com/manueltaso/batsasltemplate.

Quantitative susceptibility mapping of both ring and non-ring white matter lesions in relapsing remitting multiple sclerosis

BackgroundRecent evidence suggests that the presence of magnetic susceptibility changes in MS lesions correlates with patients' expanded disability status scale (EDSS). PurposeThis study evaluated the presence of ring lesions (RLs) and non-RLs, as well as changes in lesion susceptibility and lesion volume over a two-year time period in relapsing-remitting multiple sclerosis (RRMS) patients and compared these measures to the EDSS. Study typeLongitudinal cohort. Materials and methodsA total of forty-three (43) patients with RRMS were recruited for this study. All subjects underwent 3 T MRI at baseline and forty-one (41) subjects had follow-up scans over a two-year period. The protocol included T2 fluid attenuated inversion recovery (FLAIR), pre- and post-contrast 2D T1-weighted gradient echo imaging and susceptibility weighted imaging (SWI) sequences. All data were acquired prior to gadolinium-based contrast agent injection except for SWI and post-contrast T1-weighted data. Mean and peak susceptibilities of lesions were measured using quantitative susceptibility mapping (QSM). For the RLs, inner−/outer-diameters from SWI data and absolute intensity from the FLAIR data were measured. The susceptibility and volumes of RLs and non-RLs were correlated with EDSS. ResultsThe number of RLs correlated positively with EDSS (p-value = 0.04), but the RL volumes did not show a correlation with EDSS. Measurements of the annular ring and regions with high susceptibility remained constant over time (p = 0.2). For non-ring QSM-positive (QSM+) lesions, the average susceptibility was significantly correlated to EDSS (p < 0.01.) This was also the case for lesion volume, as well as the product of volume and susceptibility when compared to EDSS (p < 0.01 for both). ConclusionsThe susceptibility distribution and lesion volumes for the RLs remained almost constant over time, suggesting that the changes in pathophysiology of the RLs is a gradual process. On the other hand, the presence of more than one RL along with both volume and susceptibility of non-RL QSM+ lesions were significantly associated with increased disability as measured by EDSS. These findings may strengthen the role of QSM in assessing MS patients radiologically.

Synthetic FLAIR as a Substitute for FLAIR Sequence in Acute Ischemic Stroke.

Background In acute ischemic stroke (AIS), fluid-attenuated inversion recovery (FLAIR) is used for treatment decisions when onset time is unknown. Synthetic FLAIR could be generated with deep learning from information embedded in diffusion-weighted imaging (DWI) and could replace acquired FLAIR sequence (real FLAIR) and shorten MRI duration. Purpose To compare performance of synthetic and real FLAIR for DWI-FLAIR mismatch estimation and identification of patients presenting within 4.5 hours from symptom onset. Materials and Methods In this retrospective study, all pretreatment and early follow-up (<48 hours after symptom onset) MRI data sets including DWI (b = 0-1000 sec/mm2) and FLAIR sequences obtained in consecutive patients with AIS referred for reperfusion therapies between January 2002 and May 2019 were included. On the training set (80%), a generative adversarial network was trained to produce synthetic FLAIR with DWI as input. On the test set (20%), synthetic FLAIR was computed without real FLAIR knowledge. The DWI-FLAIR mismatch was evaluated on both FLAIR data sets by four independent readers. Interobserver reproducibility and DWI-FLAIR mismatch concordance between synthetic and real FLAIR were evaluated with κ statistics. Sensitivity and specificity for identification of AIS within 4.5 hours were compared in patients with known onset time by using McNemar test. Results The study included 1416 MRI scans (861 patients; median age, 71 years [interquartile range, 57-81 years]; 375 men), yielding 1134 and 282 scans for training and test sets, respectively. Regarding DWI-FLAIR mismatch, interobserver reproducibility was substantial for real and synthetic FLAIR (κ = 0.80 [95% CI: 0.74, 0.87] and 0.80 [95% CI: 0.74, 0.87], respectively). After consensus, concordance between real and synthetic FLAIR was almost perfect (κ = 0.88; 95% CI: 0.82, 0.93). Diagnostic value for identifying AIS within 4.5 hours did not differ between real and synthetic FLAIR (sensitivity: 107 of 131 [82%] vs 111 of 131 [85%], P = .2; specificity: 96 of 104 [92%] vs 96 of 104 [92%], respectively, P > .99). Conclusion Synthetic fluid-attenuated inversion recovery (FLAIR) had diagnostic performances similar to real FLAIR in depicting diffusion-weighted imaging-FLAIR mismatch and in helping to identify early acute ischemic stroke, and it may accelerate MRI protocols. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Carroll and Hurley in this issue.

FLAIR-Wise Machine-Learning Classification and Lateralization of MRI-Negative 18F-FDG PET-Positive Temporal Lobe Epilepsy.

Objective: In this study, we investigated the ability of fluid-attenuated inversion recovery (FLAIR) data coupled with machine-leaning algorithms to differentiate normal and epileptic brains and identify the laterality of focus side in temporal lobe epilepsy (TLE) patients with visually negative MRI.Materials and Methods: The MRI data were acquired on a 3-T MR system (Philips Medical Systems). After pre-proceeding stage, the FLAIR signal intensities were extracted from specific regions of interest, such as the amygdala, cerebral white matter, inferior temporal gyrus, middle temporal gyrus, parahippocampal gyrus, superior temporal gyrus, and temporal pole, and fed into a classification framework followed by a support vector machine as classifier. The proposed lateralization framework was assessed in a group of MRI-negative unilateral TLE patients (N = 42; 23 left TLE and 19 right TLE) and 34 healthy controls (HCs) based on a leave-one-out cross-validation strategy.Results: Using the FLAIR data, we obtained a 75% accuracy for discriminating the three groups, as well as 87.71, 83.01, and 76.19% accuracies for HC/right TLE, HC/left TLE, and left TLE/right TLE tasks, respectively.Interpretation: The experimental results show that FLAIR data can potentially be considered an informative biomarker for improving the pre-surgical diagnostic confidence in patients with MRI-negative TLE.

Multi-atlas based detection and localization (MADL) for location-dependent quantification of white matter hyperintensities.

The extent and spatial location of white matter hyperintensities (WMH) on brain MRI may be relevant to the development of cognitive decline in older persons. Here, we introduce a new method, known as the Multi-atlas based Detection and Localization (MADL), to evaluate WMH on fluid-attenuated inversion recovery (FLAIR) data. This method simultaneously parcellates the whole brain into 143 structures and labels hyperintense areas within each WM structure. First, a multi-atlas library was established with FLAIR data of normal elderly brains; and then a multi-atlas fusion algorithm was developed by which voxels with locally abnormal intensities were detected as WMH. At the same time, brain segmentation maps were generated from the multi-atlas fusion process to determine the anatomical location of WMH. Areas identified using the MADL method agreed well with manual delineation, with an interclass correlation of 0.97 and similarity index (SI) between 0.55 and 0.72, depending on the total WMH load. Performance was compared to other state-of-the-art WMH detection methods, such as BIANCA and LST. MADL-based analyses of WMH in an older population revealed a significant association between age and WMH load in deep WM but not subcortical WM. The findings also suggested increased WMH load in selective brain regions in subjects with mild cognitive impairment compared to controls, including the inferior deep WM and occipital subcortical WM. The proposed MADL approach may facilitate location-dependent characterization of WMH in older individuals with memory impairment.

MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation?

IntroductionMagnetic resonance imaging (MRI) has become key in the diagnosis and disease monitoring of patients with multiple sclerosis (MS). Both, T2 lesion load and Gadolinium (Gd) enhancing T1 lesions represent important endpoints in MS clinical trials by serving as a surrogate of clinical disease activity. T2- and fluid-attenuated inversion recovery (FLAIR) lesion quantification - largely due to methodological constraints – is still being performed manually or in a semi-automated fashion, although strong efforts have been made to allow automated quantitative lesion segmentation. In 2012, Schmidt and co-workers published an algorithm to be applied on FLAIR sequences. The aim of this study was to apply the Schmidt algorithm on an independent data set and compare automated segmentation to inter-rater variability of three independent, experienced raters.MethodsMRI data of 50 patients with RRMS were randomly selected from a larger pool of MS patients attending the MS Clinic at the Brain and Mind Centre, University of Sydney, Australia. MRIs were acquired on a 3.0T GE scanner (Discovery MR750, GE Medical Systems, Milwaukee, WI) using an 8 channel head coil. We determined T2-lesion load (total lesion volume and total lesion number) using three versions of an automated segmentation algorithm (Lesion growth algorithm (LGA) based on SPM8 or SPM12 and lesion prediction algorithm (LPA) based on SPM12) as first described by Schmidt et al. (2012). Additionally, manual segmentation was performed by three independent raters. We calculated inter-rater correlation coefficients (ICC) and dice coefficients (DC) for all possible pairwise comparisons.ResultsWe found a strong correlation between manual and automated lesion segmentation based on LGA SPM8, regarding lesion volume (ICC = 0.958 and DC = 0.60) that was not statistically different from the inter-rater correlation (ICC = 0.97 and DC = 0.66). Correlation between the two other algorithms (LGA SPM12 and LPA SPM12) and manual raters was weaker but still adequate (ICC = 0.927 and DC = 0.53 for LGA SPM12 and ICC = 0.949 and DC = 0.57 for LPA SPM12). Variability of both manual and automated segmentation was significantly higher regarding lesion numbers.ConclusionAutomated lesion volume quantification can be applied reliably on FLAIR data sets using the SPM based algorithm of Schmidt et al. and shows good agreement with manual segmentation.

On the filtering properties of classic-curvature and intensity-curvature functional images: applications in magnetic resonance imaging

Eight subjects affected from various typologies of human brain tumour were scanned using the magnetic resonance imaging (MRI) modality known as fluid attenuated inversion recovery (FLAIR). The intensity-curvature measurement approaches called: 1) classic-curvature; 2) intensity-curvature functional; were calculated when fitting to the MRI data two mathematical models: 1) the bivariate cubic polynomial; 2) the bivariate linear function, respectively. The classic-curvature and the intensity-curvature functional show well behaved medical intensity-curvature maps of the human brain and they were used as filter masks to convolve the FLAIR data. As a result of the convolution, the filtered FLAIR images were obtained and analysed searching for evidence of feature extraction. The resulting filtered FLAIR images show: 1) well behaved presentation of the tumour; 2) well behaved delineation of the parenchyma surrounding the tumour; 3) well behaved separation between the tumour and the surrounding oedema; 4) clear and neat delineation of grey and white matter of the brain. The comparison between the filtered FLAIR and the filtered T2-weighted MRI images indicates that filtering FLAIR images yields a more effective highlight of the tumour structures than filtering the T2-weighted MRI.

Quantitative assessment of cerebral gray matter density change in progressive supranuclear palsy using voxel based morphometry analysis and cerebral MR T1-weighted FLAIR imaging

PurposeTo investigate the gray matter (GM) atrophy in Progressive supranuclear palsy (PSP) using T1-weighted Fluid-Attenuated Inversion Recovery (FLAIR) images based on voxel based morphometry (VBM) method. Materials and methodsIn this study, we firstly modified the conventional VBM method to make it can process the T1-weighted FLAIR brain images. Then, we used this method on the 24 PSP patients and 23 healthy age- and sex-matched control subjects to find the local gray matter density changes of PSP patients. ResultsCompared with healthy controls, GM reductions of PSP patients mainly located in the thalamus, basal ganglia, pons, midbrain, insular cortex, frontal cortex, temporal lobe, cerebellum, cingulate cortex and hippocampus. ConclusionWe used the modified VBM technique into T1 FLAIR data to study the brain gray matter atrophy in PSP, and found some new atrophy areas, including pallidum, middle and posterior cingulum, lingual, fusiform gyrus and the post part of inferior temporal gyrus. These areas have not been described in the former VBM studies, but they revealed abnormity in the pathologic and other studies on PSP. Our results might be expected to provide significant underlining neurology information and diagnostic value for PSP.

Detecting subarachnoid hemorrhage: Comparison of combined FLAIR/SWI versus CT

ObjectivesAim of this study was to compare the utility of susceptibility weighted imaging (SWI) with the established diagnostic techniques CT and fluid attenuated inversion recovery (FLAIR) in their detecting capacity of subarachnoid hemorrhage (SAH), and further to compare the combined SWI/FLAIR MRI data with CT to evaluate whether MRI is more accurate than CT. MethodsTwenty-five patients with acute SAH underwent CT and MRI within 6 days after symptom onset. Underlying pathology for SAH was head trauma (n=9), ruptured aneurysm (n=6), ruptured arteriovenous malformation (n=2), and spontaneous bleeding (n=8). SWI, FLAIR, and CT data were analyzed. The anatomical distribution of SAH was subdivided into 8 subarachnoid regions with three peripheral cisterns (frontal-parietal, temporal-occipital, sylvian), two central cisterns and spaces (interhemispheric, intraventricular), and the perimesencephalic, posterior fossa, superior cerebellar cisterns. ResultsSAH was detected in a total of 146 subarachnoid regions. CT identified 110 (75.3%), FLAIR 127 (87%), and SWI 129 (88.4%) involved regions. Combined FLAIR and SWI identified all 146 detectable regions (100%). FLAIR was sensitive for frontal-parietal, temporal-occipital and Sylvian cistern SAH, while SWI was particularly sensitive for interhemispheric and intraventricular hemorrhage. ConclusionsBy combining SWI and FLAIR, MRI yields a distinctly higher detection rate for SAH than CT alone, particularly due to their complementary detection characteristics in different anatomical regions. Detection strength of SWI is high in central areas, whereas FLAIR shows a better detection rate in peripheral areas.

Analysis of multiple sclerosis lesions using a fusion of 3.0 T FLAIR and 7.0 T SWI phase: FLAIR SWI

To improve multiple sclerosis (MS) research by introducing a new type of contrast, namely, the combination of fluid-attenuated inversion recovery (FLAIR) data acquired at 3.0 T and 7.0 T susceptibility-weighted imaging (SWI) phase data. The approach of this new contrast is whole-brain coverage with 3.0 T-FLAIR data for lesion detection--currently limited at 7.0 T due to specific absorption rate (SAR) limits--overlaid with high-resolution, small vessel, and iron-related 7.0 T SWI contrast. Lesion analysis in terms of penetrating veins and local iron depositions were performed. Data from 10 MS patients were acquired at 3.0 T and at 7.0 T. FLAIR data, acquired at 3.0 T, were registered to 7.0 T SWI phase data and SWI image processing was performed using 3.0 T FLAIR data instead of SWI magnitude data. A total of 299 MS plaques were detected in eight MS patients. Penetrating veins were found in 75 MS plaques, iron depositions in 48 MS plaques, and veins accompanied with iron depositions in 44 MS plaques. FLAIR-SWI provides radiologically known, hyperintense definition of MS lesions overlaid with high-resolution visualization of iron deposits and venous blood vessels and offers new insights into MS lesions.