Search

BACKGROUND AND PURPOSE: Accurate automated infarct segmentation is needed for acute ischemic stroke studies relying on infarct volumes as an imaging phenotype or biomarker that require large numbers of subjects. This study investigates whether an ensemble of convolutional neural networks (CNN) trained on multiparametric DWI maps outperforms single networks trained on solo DWI parametric maps. MATERIALS AND METHODS: CNNs were trained on combinations of DWI, ADC, and low b-value-weighted images from 116 subjects. The performances of the networks (measured by Dice score, sensitivity and precision) were compared to one another and to ensembles of 5 networks. To assess the generalizability of the approach, the best performing model was applied to an independent evaluation cohort of 151 subjects. Agreement between manual and automated segmentations for identifying patients with large lesions volumes was calculated across multiple thresholds (21 cm(3), 31 cm(3), 51 cm(3), and 70 cm(3)). RESULTS: An ensemble of CNNs trained on DWI, ADC and low b-value-weighted images produced the most accurate acute infarct segmentation over individual networks (p

In genetic frontotemporal dementia, cross-sectional studies have identified profiles of presymptomatic neuroanatomical loss for C9orf72 repeat expansion, MAPT, and GRN mutations. In this study, we characterize longitudinal gray matter (GM) and white matter (WM) brain changes in presymptomatic frontotemporal dementia. We included healthy carriers of C9orf72 repeat expansion (n = 12), MAPT (n = 15), GRN (n = 33) mutations, and related noncarriers (n = 53), that underwent magnetic resonance imaging at baseline and 2-year follow-up. We analyzed cross-sectional baseline, follow-up, and longitudinal GM and WM changes using voxel-based morphometry and cortical thickness analysis in SPM and tract-based spatial statistics in FSL. Compared with noncarriers, C9orf72 repeat expansion carriers showed lower GM volume in the cerebellum and insula, and WM differences in the anterior thalamic radiation, at baseline and follow-up. MAPT mutation carriers showed emerging GM temporal lobe changes and longitudinal WM degeneration of the uncinate fasciculus. GRN mutation carriers did not show presymptomatic neurodegeneration. This study shows distinct presymptomatic cross-sectional and longitudinal patterns of GM and WM changes across C9orf72 repeat expansion, MAPT, and GRN mutation carriers compared with noncarriers.

Frontotemporal dementia is a highly heritable and devastating neurodegenerative disease. About 10–20% of all frontotemporal dementia is caused by known pathogenic mutations, but a reliable tool to predict clinical conversion in mutation carriers is lacking. In this retrospective proof-of-concept case-control study, we investigate whether MRI-based and cognition-based classifiers can predict which mutation carriers from genetic frontotemporal dementia families will develop symptoms (‘convert’) within 4 years. From genetic frontotemporal dementia families, we included 42 presymptomatic frontotemporal dementia mutation carriers. We acquired anatomical, diffusion-weighted imaging, and resting-state functional MRI, as well as neuropsychological data. After 4 years, seven mutation carriers had converted to frontotemporal dementia (‘converters’), while 35 had not (‘non-converters’). We trained regularized logistic regression models on baseline MRI and cognitive data to predict conversion to frontotemporal dementia within 4 years, and quantified prediction performance using area under the receiver operating characteristic curves. The prediction model based on fractional anisotropy, with highest contribution of the forceps minor, predicted conversion to frontotemporal dementia beyond chance level (0.81 area under the curve, family-wise error corrected P = 0.025 versus chance level). Other MRI-based and cognitive features did not outperform chance level. Even in a small sample, fractional anisotropy predicted conversion in presymptomatic frontotemporal dementia mutation carriers beyond chance level. After validation in larger data sets, conversion prediction in genetic frontotemporal dementia may facilitate early recruitment into clinical trials., MRI-based classification combining anatomical, structural connectivity and functional connectivity measures may aid early frontotemporal dementia diagnosis. Feis et al. report that MRI-based classification using fractional anisotropy predicts frontotemporal dementia onset within 4 years beyond chance level in frontotemporal dementia mutation carriers., Graphical Abstract Graphical Abstract

BackgroundMultimodal MRI-based classification may aid early frontotemporal dementia (FTD) diagnosis. Recently, presymptomatic FTD mutation carriers, who have a high risk of developing FTD, were separated beyond chance level from controls using MRI-based classification. However, it is currently unknown how these scores from classification models progress as mutation carriers approach symptom onset. In this longitudinal study, we investigated multimodal MRI-based classification scores between presymptomatic FTD mutation carriers and controls. Furthermore, we contrasted carriers that converted during follow-up (‘converters’) and non-converting carriers (‘non-converters’).MethodsWe acquired anatomical MRI, diffusion tensor imaging and resting-state functional MRI in 55 presymptomatic FTD mutation carriers and 48 healthy controls at baseline, and at 2, 4, and 6 years of follow-up as available. At each time point, FTD classification scores were calculated using a behavioural variant FTD classification model. Classification scores were tested in a mixed-effects model for mean differences and differences over time.ResultsPresymptomatic mutation carriers did not have higher classification score increase over time than controls (p=0.15), although carriers had higher FTD classification scores than controls on average (p=0.032). However, converters (n=6) showed a stronger classification score increase over time than non-converters (pConclusionsOur findings imply that presymptomatic FTD mutation carriers may remain similar to controls in terms of MRI-based classification scores until they are close to symptom onset. This proof-of-concept study shows the promise of longitudinal MRI data acquisition in combination with machine learning to contribute to early FTD diagnosis.

As age and Parkinson's disease (PD) both play a role in the degeneration of brain white matter, we aimed to investigate a possible interaction effect of age and disease presence on white matter integrity in patients with PD. We studied white matterhyperintensity volume, global fractional anisotropy, mean diffusivity and mean magnetization transfer ratio of normal appearing white matter in 163 patients with PD and 218 age- and gender-matched healthy control subjects. We investigated the relationship between age and these parameters in both groups, and interaction between age and disease presence. Patients with PD had a higher load of white matter hyperintensities with a preferential periventricular and anterior distribution as compared with healthy control subjects. Visuospatial functioning was related to total and postural instability and gait difficultywas related to periventricular white matter hyperintensity volume in patients with PD. The age-related decline of white matter integrity was similar for both groups. Global microstructural integrity of the normal appearing white matter did not differ betweenpatients and healthy control subjects, suggesting that PD-specific changes do not exceed normal age-associated change in white matter without lesions. (C) 2019 The Authors. Published by Elsevier Inc.

Early and accurate mild cognitive impairment (MCI) detection within a heterogeneous, nonclinical population is needed to improve care for persons at risk of developing dementia. Magnetic resonance imaging (MRI)‐based classification may aid early diagnosis of MCI, but has only been applied within clinical cohorts. We aimed to determine the generalizability of MRI‐based classification probability scores to detect MCI on an individual basis within a general population. To determine classification probability scores, an AD, mild‐AD, and moderate‐AD detection model were created with anatomical and diffusion MRI measures calculated from a clinical Alzheimer's Disease (AD) cohort and subsequently applied to a population‐based cohort with 48 MCI and 617 normal aging subjects. Each model's ability to detect MCI was quantified using area under the receiver operating characteristic curve (AUC) and compared with an MCI detection model trained and applied to the population‐based cohort. The AD‐model and mild‐AD identified MCI from controls better than chance level (AUC = 0.600, p = 0.025; AUC = 0.619, p = 0.008). In contrast, the moderate‐AD‐model was not able to separate MCI from normal aging (AUC = 0.567, p = 0.147). The MCI‐model was able to separate MCI from controls better than chance (p = 0.014) with mean AUC values comparable with the AD‐model (AUC = 0.611, p = 1.0). Within our population‐based cohort, classification models detected MCI better than chance. Nevertheless, classification performance rates were moderate and may be insufficient to facilitate robust MRI‐based MCI detection on an individual basis. Our data indicate that multiparametric MRI‐based classification algorithms, that are effective in clinical cohorts, may not straightforwardly translate to applications in a general population.

Background Cerebral amyloid angiopathy ( CAA ) is a major cause of lobar intracerebral hemorrhage in elderly adults; however, presymptomatic diagnosis of CAA is difficult. Hereditary cerebral hemorrhage with amyloidosis–Dutch type ( HCHWA ‐D) is a rare autosomal‐dominant disease that leads to pathology similar to sporadic CAA . Presymptomatic HCHWA ‐D mutation carriers provide a unique opportunity to study CAA ‐related changes before any symptoms have occurred. In this study we investigated early CAA ‐related alterations in the white matter. Methods and Results We investigated diffusion magnetic resonance imaging ( dMRI ) data for 15 symptomatic and 11 presymptomatic HCHWA ‐D mutation carriers and 30 noncarrier control participants using 4 different approaches. We looked at (1) the relation between age and global dMRI measures for mutation carriers versus controls, (2) voxel‐wise d MRI , (3) independent component‐clustered dMRI measures, and (4) structural connectomics between presymptomatic or symptomatic carriers and controls. Fractional anisotropy decreased, and mean diffusivity and peak width of the skeletonized mean diffusivity increased significantly over age for mutation carriers compared with controls. In addition, voxel‐wise and independent component‐wise fractional anisotropy, and mean diffusivity, and structural connectomics were significantly different between HCHWA ‐D patients and control participants, mainly in the periventricular frontal and occipital regions and in the occipital lobe. We found no significant differences between presymptomatic carriers and control participants. Conclusions The d MRI technique is sensitive in detecting alterations in symptomatic HCHWA ‐d carriers but did not show alterations in presymptomatic carriers. This result indicates that d MRI may be less suitable for identifying early white matter changes in CAA .

Background and Purpose— We evaluated deep learning algorithms’ segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods— Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms’ performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results— The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (ρ=0.92; P 3 (0.9–16.6 cm 3 ). Patients with small artery occlusion stroke subtype had smaller lesion volumes ( P Conclusions— Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.

Background and purposeFunctional outcomes after ischaemic stroke are worse in women, despite adjusting for differences in comorbidities and treatment approaches. White matter microvascular integrity represents one risk factor for poor long-term functional outcomes after ischaemic stroke. The aim of the study is to characterise sex-specific differences in microvascular integrity in individuals with acute ischaemic stroke.MethodsA retrospective analysis of subjects with acute ischaemic stroke and brain MRI with diffusion-weighted (DWI) and dynamic-susceptibility contrast-enhanced (DSC) perfusion-weighted imaging obtained within 9 hours of last known well was performed. In the hemisphere contralateral to the acute infarct, normal-appearing white matter (NAWM) microvascular integrity was measured using the K2 coefficient and apparent diffusion coefficient (ADC) values. Regression analyses for predictors of K2 coefficient, DWI volume and good outcome (90-day modified Rankin scale (mRS) score Results105 men and 79 women met inclusion criteria for analysis. Despite no difference in age, women had increased NAWM K2 coefficient (1027.4 vs 692.7×10–6/s; p=0.006). In women, atrial fibrillation (β=583.6; p=0.04) and increasing NAWM ADC (β=4.4; p=0.02) were associated with increased NAWM K2 coefficient. In multivariable regression analysis, the K2 coefficient was an independent predictor of DWI volume in women (β=0.007; p=0.01) but not men.ConclusionsIn women with acute ischaemic stroke, increased NAWM K2 coefficient is associated with increased infarct volume and chronic white matter structural integrity. Prospective studies investigating sex-specific differences in white matter microvascular integrity are needed.

Background Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.570, p = 0.11). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.646 (p = 0.021). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.680, p = 0.005). Conclusions FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter., Highlights • MRI-based classification was performed on presymptomatic FTD gene carriers and controls. • Presymptomatic carriers were separated from controls significantly better than chance-level. • The best performing model was based on white matter features from structural and diffusion scans. • Multimodal MRI-based classification scores may be useful to aid earlier FTD diagnosis.

Objective Posterior circulation ischemic stroke (PCiS) constitutes 20–30% of ischemic stroke cases. Detailed information about differences between PCiS and anterior circulation ischemic stroke (ACiS) remains scarce. Such information might guide clinical decision making and prevention strategies. We studied risk factors and ischemic stroke subtypes in PCiS vs. ACiS and lesion location on magnetic resonance imaging (MRI) in PCiS. Methods Out of 3,301 MRIs from 12 sites in the National Institute of Neurological Disorders and Stroke (NINDS) Stroke Genetics Network (SiGN), we included 2,381 cases with acute DWI lesions. The definition of ACiS or PCiS was based on lesion location. We compared the groups using Chi-squared and logistic regression. Results PCiS occurred in 718 (30%) patients and ACiS in 1663 (70%). Diabetes and male sex were more common in PCiS vs. ACiS (diabetes 27% vs. 23%, p .05; male sex 68% vs. 58%, p p p p Conclusion Ischemic stroke subtypes differ between the two phenotypes. Diabetes and male sex have a stronger association with PCiS than ACiS. Definitive MRI-based PCiS diagnosis aids etiological investigation and contributes additional insights into specific risk factors and mechanisms of injury in PCiS.

BACKGROUND/OBJECTIVE: Overlapping clinical symptoms often complicate differential diagnosis between patients with Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD). Magnetic resonance imaging (MRI) reveals disease specific structural and functional differences that aid in differentiating AD from bvFTD patients. However, the benefit of combining structural and functional connectivity measures to-on a subject-basis-differentiate these dementia-types is not yet known.METHODS: Anatomical, diffusion tensor (DTI), and resting-state functional MRI (rs-fMRI) of 30 patients with early stage AD, 23 with bvFTD, and 35 control subjects were collected and used to calculate measures of structural and functional tissue status. All measures were used separately or selectively combined as predictors for training an elastic net regression classifier. Each classifier's ability to accurately distinguish dementia-types was quantified by calculating the area under the receiver operating characteristic curves (AUC).RESULTS: Highest AUC values for AD and bvFTD discrimination were obtained when mean diffusivity, full correlations between rs-fMRI-derived independent components, and fractional anisotropy (FA) were combined (0.811). Similarly, combining gray matter density (GMD), FA, and rs-fMRI correlations resulted in highest AUC of 0.922 for control and bvFTD classifications. This, however, was not observed for control and AD differentiations. Classifications with GMD (0.940) and a GMD and DTI combination (0.941) resulted in similar AUC values (p = 0.41).CONCLUSION: Combining functional and structural connectivity measures improve dementia-type differentiations and may contribute to more accurate and substantiated differential diagnosis of AD and bvFTD patients. Imaging protocols for differential diagnosis may benefit from also including DTI and rs-fMRI.

The pattern of vascular remodelling in relation to recovery after stroke remains largely unclear. We used steady-state contrast-enhanced magnetic resonance imaging to assess the development of cerebral blood volume and microvascular density in perilesional and exofocal areas from (sub)acutely to chronically after transient stroke in rats. Microvascular density was verified histologically after infusion with Evans Blue dye. At day 1, microvascular cerebral blood volume and microvascular density were reduced in and around the ischemic lesion (intralesional borderzone: microvascular cerebral blood volume = 72 ± 8%; microvascular density = 76 ± 8%) (P

Estimation of hemorrhagic transformation (HT) risk is crucial for treatment decision–making after acute ischemic stroke. We aimed to determine the accuracy of multiparametric MRI-based predictive algorithms in calculating probability of HT after stroke. Spontaneously, hypertensive rats were subjected to embolic stroke and, after 3 h treated with tissue plasminogen activator (Group I: n = 6) or vehicle (Group II: n = 7). Brain MRI measurements of T2, T2*, diffusion, perfusion, and blood–brain barrier permeability were obtained at 2, 24, and 168 h post-stroke. Generalized linear model and random forest (RF) predictive algorithms were developed to calculate the probability of HT and infarction from acute MRI data. Validation against seven-day outcome on MRI and histology revealed that highest accuracy of hemorrhage prediction was achieved with a RF-based model that included spatial brain features (Group I: area under the receiver-operating characteristic curve (AUC) = 0.85 ± 0.14; Group II: AUC = 0.89 ± 0.09), with significant improvement over perfusion- or permeability-based thresholding methods. However, overlap between predicted and actual tissue outcome was significantly lower for hemorrhage prediction models (maximum Dice’s Similarity Index (DSI) = 0.20 ± 0.06) than for infarct prediction models (maximum DSI = 0.81 ± 0.06). Multiparametric MRI-based predictive algorithms enable early identification of post-ischemic tissue at risk of HT and may contribute to improved treatment decision-making after acute ischemic stroke.

Highlights • Multimodal MRI AD classification models were pre-trained on AD patients and controls. • Generalisation of these models was tested on a multi-centre memory clinic data set. • AD scores were assigned to AD patients, MCI patients and memory complainers. • Anatomical MRI performed better than diffusion MRI and resting state fMRI. • Combining imaging modalities did not improve the results over anatomical MRI only., Anatomical magnetic resonance imaging (MRI), diffusion MRI and resting state functional MRI (rs-fMRI) have been used for Alzheimer’s disease (AD) classification. These scans are typically used to build models for discriminating AD patients from control subjects, but it is not clear if these models can also discriminate AD in diverse clinical populations as found in memory clinics. To study this, we trained MRI-based AD classification models on a single centre data set consisting of AD patients (N = 76) and controls (N = 173), and used these models to assign AD scores to subjective memory complainers (N = 67), mild cognitive impairment (MCI) patients (N = 61), and AD patients (N = 61) from a multi-centre memory clinic data set. The anatomical MRI scans were used to calculate grey matter density, subcortical volumes and cortical thickness, the diffusion MRI scans were used to calculate fractional anisotropy, mean, axial and radial diffusivity, and the rs-fMRI scans were used to calculate functional connectivity between resting state networks and amplitude of low frequency fluctuations. Within the multi-centre memory clinic data set we removed scan site differences prior to applying the models. For all models, on average, the AD patients were assigned the highest AD scores, followed by MCI patients, and later followed by SMC subjects. The anatomical MRI models performed best, and the best performing anatomical MRI measure was grey matter density, separating SMC subjects from MCI patients with an AUC of 0.69, MCI patients from AD patients with an AUC of 0.70, and SMC patients from AD patients with an AUC of 0.86. The diffusion MRI models did not generalise well to the memory clinic data, possibly because of large scan site differences. The functional connectivity model separated SMC subjects and MCI patients relatively good (AUC = 0.66). The multimodal MRI model did not improve upon the anatomical MRI model. In conclusion, we showed that the grey matter density model generalises best to memory clinic subjects. When also considering the fact that grey matter density generally performs well in AD classification studies, this feature is probably the best MRI-based feature for AD diagnosis in clinical practice.

We sought to investigate the relationship between blood–brain barrier (BBB) permeability and microstructural white matter integrity, and their potential impact on long-term functional outcomes in patients with acute ischemic stroke (AIS). We studied 184 AIS subjects with perfusion-weighted MRI (PWI) performed

Background: Multimodal MRI may support single-subject differentiation diagnosis of Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD). Yet, what MRI modality combinations maximize classification accuracy is not yet known. We analyzed various MRI modality combinations to determine what combinations suit single-subject classification of AD patients, bvFTD patients, and control subjects best. Methods: Thirty-seven patients with probable AD, 28 patients with bvFTD, and 40 cognitively normal subjects (Controls) (Table 1) underwent diffusion tensor imaging (DTI), resting-state functional, and T1-weighted structural MRI at 3T. From each T1-w image, probabilistic gray matter (GM) maps were calculated and used to estimate local GM density (GMD) within 96 Harvard-Oxford cortical and 14 deep GM regions. 20 tracts of the Johns-Hopkins-University tractography atlas were used to determine local white matter density (WMD) values and, after projection on the study-specific skeleton calculated with tract-based spatial statistics, local measures of fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity, and radial diffusivity. Seventy rs-fMRI components, derived from a temporally concatenated independent component analysis, were used to calculate the components' pairwise correlations and partial correlations. These features were used to establish classification accuracy using nested cross-validation classification analyses with elastic net classifiers. Individual and combinations of MRI modalities were step-wise evaluated to determine classification accuracy, expressed as area under the receiver operating characteristic curves (AUC). A three-group classification model was used to determine the accuracy for differentiating between AD, bvFTD, and Control subjects. Three two-group models were calculated to differentiate AD from Controls, bvFTD from Controls, and AD from bvFTD subjects. Results: Classification accuracy for three-group and AD versus Control classifications were highest with GMD-based features ((AUC [min-max]) 0.7±5[0.711-0.847] and 0.933[0.886- 0.963]) (Table 2). bvFTD versus Control and AD versus bvFTD classification models were most accurate using DTI-based features (FA: 0.860[0.807-0.913], MD: 0.693[0.614-0.821]). Overall, rsfMRI features did not improve classification accuracy. Conclusions: MRI-based differentiation of dementia forms may depend on dementia- type and MRI modality. T1-w-based measures particularly supported AD classifications, whereas DTI-based measurements facilitated bvFTD classifications. Functional connectivity measures and multimodal combinations did not substantially improve dementia- type discrimination. For MRI-based differential dementiatype diagnosis careful selection of MRI modalities is warranted.

Magnetic resonance imaging (MRI) provides a powerful (neuro)imaging modality for the diagnosis and outcome prediction after (acute) stroke. Since MRI allows noninvasive, longitudinal, and three-dimensional assessment of vessel occlusion (with magnetic resonance angiography (MRA)), tissue injury (with T1-, T2-, T2∗-, and/or diffusion-weighted MRI), and hemodynamics (with perfusion MRI), it offers a valuable tool for (pre)clinical and experimental studies on stroke pathology, treatment, and recovery. Combined MRI protocols that inform of different aspects of stroke pathophysiology enable the delineation of irreversibly damaged tissue and, potentially salvageable, tissue at risk of infarction, based on concepts like the perfusion-diffusion mismatch, or by predictive modeling of infarct probability. These approaches can aid in the selection of patients who could respond favorably to thrombolysis or thrombectomy. Furthermore, structural and functional MRI of the progression of affected tissue may contribute to the monitoring and characterization of effects of (experimental) therapeutic interventions aimed at improving outcome after stroke.

Background: In acute ischemic stroke (AIS), therapeutic decisions are increasingly being based upon the volume of likely-unsalvageable brain tissue, which is often estimated using DWI. Deep learning algorithms, e.g. convolutional neural networks (CNN), have been employed for chronic stroke lesion segmentation. Here we investigate the applicability of CNN for DWI lesion measurement in acute stroke. Methods: 50 AIS patients underwent DWI < 12h from last known well. Apparent diffusion coefficient maps, T2WI, and DWI were used as covariates in a 2D CNN (5-fold cross validation). Including convolutional, inception and fully connected dense layers, a CNN of 15 layers was trained using manually outlined DWI lesions. To avoid overfitting, statistical dropout, L1- and L2-regularization and batch-normalization were used. Automatically segmented lesion volumes (ALV) using a 50% risk threshold were compared to the manual lesion volumes (MLV) using Dice similarity index (DSI, a measure of overlap) and Spearman’s correlation coefficient. Subset analysis was performed evaluating results between small ( Results: The figure shows examples of CNN segmentation. The median [IQR] measured lesion volume and DSI were 25 [13-46] mL and 66% [35-75%], respectively. The correlation of MLV with ALV was 86% (P Discussion: Automatic DWI lesion segmentation for large lesions is feasible using CNN. CNN tended to overestimate the volumes of small lesions. Prior methods have used a priori heuristics or morphometric operations to remove artifacts. CNN methods show promise for “learning” to discriminate artifacts from real lesions.

Vascular occlusion sites largely determine the pattern of cerebral tissue damage and likelihood of subsequent reperfusion after acute ischemic stroke. We aimed to elucidate relationships between flow obstruction in segments of the internal carotid artery (ICA) and middle cerebral artery (MCA), and (1) profiles of acute ischemic lesions and (2) probability of subsequent beneficial reperfusion. Embolic stroke was induced by unilateral intracarotid blood clot injection in normotensive ( n=53) or spontaneously hypertensive ( n=20) rats, followed within 2 hours by magnetic resonance (MR) angiography (MRA), diffusion- (DWI) and perfusion-weighted magnetic resonance imaging (MRI) (PWI). In a subset of animals ( n=9), MRI was repeated after 24 and 168 hours to determine the predictive value of the occlusion pattern on benefit of reperfusion. The extent of cerebral perfusion and diffusion abnormality was related to the pattern of flow obstruction in ICA and MCA segments. Hypertensive animals displayed significantly larger cortical perfusion lesions. Acute perfusion-diffusion lesion mismatches were detected in all animals that subsequently benefitted from reperfusion. Yet, the presence of an angiography-diffusion mismatch was more specific in predicting reperfusion benefit. Combination of DWI, PWI, and MRA exclusively informs on the impact of arterial occlusion profiles after acute ischemic stroke, which may improve prognostication and subsequent treatment decisions.

Individualized stroke treatment decisions can be improved by accurate identification of the extent of salvageable tissue. Magnetic resonance imaging (MRI)-based approaches, including measurement of a ‘perfusion-diffusion mismatch’ and calculation of infarction probability, allow assessment of tissue-at-risk;however, the ability to explicitly depict potentially salvageable tissue remains uncertain. In this study, five predictive algorithms (generalized linear model (GLM), generalized additive model, support vector machine, adaptive boosting, and random forest) were tested in their potency to depict acute cerebral ischemic tissue that can recover after reperfusion. Acute T2-, diffusion-, and perfusion-weighted MRI, and follow-up T2 maps were collected from rats subjected to right-sided middle cerebral artery occlusion without subsequent reperfusion, for training of algorithms (Group I), and with spontaneous (Group II) or thrombolysis-induced reperfusion (Group III), to determine infarction probability-based viability thresholds and prediction accuracies. The infarction probability difference between irreversible—i.e., infarcted after reperfusion— and salvageable tissue injury—i.e., noninfarcted after reperfusion—was largest for GLM (20 ± 7%) with highest accuracy of risk-based identification of acutely ischemic tissue that could recover on subsequent reperfusion (Dice's similarity index = 0.79 ± 0.14). Our study shows that assessment of the heterogeneity of infarction probability with MRI-based algorithms enables estimation of the extent of potentially salvageable tissue after acute ischemic stroke.

Variable efficacies have been reported for glucocorticoid drugs as anti-inflammatory treatment after stroke. We applied an alternative drug delivery strategy, by injection of dexamethasone phosphate-containing liposomes in combination with recombinant tissue plasminogen activator (rtPA), in an experimental stroke model, and tested the hypothesis that this approach improves behavioral recovery and reduces lesion growth. Rats were subjected to right middle cerebral artery occlusion with a blood clot. After 2 h, animals were intravenously injected with rtPA plus empty long-circulating liposomes (LCL), free dexamethasone phosphate (DXP), or DXP-containing LCL (LCL-DXP). Neurological status was evaluated with different behavioral tests up to 7 days after stroke. Lesion development was assessed by magnetic resonance imaging of tissue and perfusion parameters from 0-2 h until 7 days after stroke. Expression of brain inflammatory markers was measured with RT-PCR at post-stroke day 7. Treatment with rtPA plus LCL-DXP resulted in significantly improved behavioral outcome as compared to treatment with rtPA plus empty LCL or free DXP. Acute and final brain lesion sizes were comparable between treatment groups; however a predictive algorithm revealed a significantly larger salvaged tissue area after treatment with LCL-DXP. We conclude that delivery of dexamethasone phosphate via LCL in combination with rtPA-induced thrombolysis can significantly improve outcome after stroke. Furthermore, magnetic resonance imaging-based predictive algorithms provide a sensitive means to measure treatment effects on lesion development., The research leading to these results was funded by the Netherlands Heart Foundation (2005B156), The Netherlands Organization for Scientific Research (NWO-Vidi 917.76.351), and the European Union’s Seventh Framework Programme (FP7/2007-2013) under grant agreements nº 201024 and nº 202213 (European Stroke Network) and MediTrans.

Background and Purpose— Acute infarct volume, often proposed as a biomarker for evaluating novel interventions for acute ischemic stroke, correlates only moderately with traditional clinical end points, such as the modified Rankin Scale. We hypothesized that the topography of acute stroke lesions on diffusion-weighted magnetic resonance imaging may provide further information with regard to presenting stroke severity and long-term functional outcomes. Methods— Data from a prospective stroke repository were limited to acute ischemic stroke subjects with magnetic resonance imaging completed within 48 hours from last known well, admission NIH Stroke Scale (NIHSS), and 3-to-6 months modified Rankin Scale scores. Using voxel-based lesion symptom mapping techniques, including age, sex, and diffusion-weighted magnetic resonance imaging lesion volume as covariates, statistical maps were calculated to determine the significance of lesion location for clinical outcome and admission stroke severity. Results— Four hundred ninety subjects were analyzed. Acute stroke lesions in the left hemisphere were associated with more severe NIHSS at admission and poor modified Rankin Scale at 3 to 6 months. Specifically, injury to white matter (corona radiata, internal and external capsules, superior longitudinal fasciculus, and uncinate fasciculus), postcentral gyrus, putamen, and operculum were implicated in poor modified Rankin Scale. More severe NIHSS involved these regions, as well as the amygdala, caudate, pallidum, inferior frontal gyrus, insula, and precentral gyrus. Conclusions— Acute lesion topography provides important insights into anatomic correlates of admission stroke severity and poststroke outcomes. Future models that account for infarct location in addition to diffusion-weighted magnetic resonance imaging volume may improve stroke outcome prediction and identify patients likely to benefit from aggressive acute intervention and personalized rehabilitation strategies.

Background: In acute ischemic stroke (AIS) patients, multi-parametric MRI-based predictive algorithms have shown promise in identifying tissue at risk of infarction, but do not consider the intrinsic variations of normal or pathological tissue. We hypothesized that extending MRI-based algorithms to take into consideration tissue type will improve predictions of tissue outcome. Methods: We retrospectively analyzed AIS patients who received neither revascularization nor experimental interventional treatment, who underwent MRI within 12 h from the time since they were last known well and who had follow-up imaging >4 days. Perfusion- and diffusion-parametric maps were combined to predict tissue outcome using 2 models: 1) a generalized linear model (GLM) trained with data from the whole ipsilateral hemisphere (sGLM), irrespective of tissue type, or 2) an anatomically-weighted GLM (aGLM) that was calculated using a weighted average to combine results from models generated using entire white or gray matter regions only. Both methods were evaluated using jack-knifing and predicted and follow-up regions were compared in terms of accuracy (measured as area under the receiver operator characteristic curve, AUC), Dice similarity index (DSI) and root mean square error (RMSE). Results: Results from 109 patients (65% male, median 68 y IQR [55-77], NIHSS 14 [9-25]) showed that, compared to sGLM, aGLM’s predictions had higher DSI (0.48 [0.19-0.59], P Discussion: We showed that anatomically-weighted algorithms may better capture differences in tissue vulnerability in acute ischemic stroke, contributing to improved MRI-based tissue outcome predictions.

Objective:To describe the design and rationale for the genetic analysis of acute and chronic cerebrovascular neuroimaging phenotypes detected on clinical MRI in patients with acute ischemic stroke (AIS) within the scope of the MRI–GENetics Interface Exploration (MRI-GENIE) study.Methods:MRI-GENIE capitalizes on the existing infrastructure of the Stroke Genetics Network (SiGN). In total, 12 international SiGN sites contributed MRIs of 3,301 patients with AIS. Detailed clinical phenotyping with the web-based Causative Classification of Stroke (CCS) system and genome-wide genotyping data were available for all participants. Neuroimaging analyses include the manual and automated assessments of established MRI markers. A high-throughput MRI analysis pipeline for the automated assessment of cerebrovascular lesions on clinical scans will be developed in a subset of scans for both acute and chronic lesions, validated against gold standard, and applied to all available scans. The extracted neuroimaging phenotypes will improve characterization of acute and chronic cerebrovascular lesions in ischemic stroke, including CCS subtypes, and their effect on functional outcomes after stroke. Moreover, genetic testing will uncover variants associated with acute and chronic MRI manifestations of cerebrovascular disease.Conclusions:The MRI-GENIE study aims to develop, validate, and distribute the MRI analysis platform for scans acquired as part of clinical care for patients with AIS, which will lead to (1) novel genetic discoveries in ischemic stroke, (2) strategies for personalized stroke risk assessment, and (3) personalized stroke outcome assessment.

Background: The pathogenesis of delayed cerebral injury after aneurysmal subarachnoid hemorrhage (SAH) is largely unresolved. In particular, the progression and interplay of tissue and perfusion changes, which can significantly affect the outcome, remain unclear. Only a few studies have assessed pathophysiological developments between subacute and chronic time points after SAH, which may be ideally studied with noninvasive methods in standardized animal models. Therefore, our objective was to characterize the pattern and correlation of brain perfusion and lesion status with serial multiparametric magnetic resonance imaging (MRI) from subacute to chronical after experimental SAH in rats. Methods: SAH was induced by endovascular puncture of the intracranial bifurcation of the right internal carotid artery in adult male Wistar rats (n = 30). Diffusion-, T2-, perfusion- and contrast-enhanced T1-weighted MRI were performed on a 4.7-tesla animal MR system to measure cytotoxic and vasogenic edema, hemodynamic parameters and blood-brain barrier permeability, respectively, at days 2 and 7 after SAH. The neurological status was repeatedly monitored with different behavioral tests between days -1 and 7 after SAH. Lesioned tissue - identified by edema-associated T2 prolongation - and unaffected tissue were outlined on multislice images and further characterized based on tissue and perfusion indices. Correlation analyses were performed to evaluate relationships between different MRI-based parameters and between MRI-based parameters and neurological scores. Results: Similar to clinical SAH and previous studies in this experimental SAH model, mortality up to day 2 was high (43%). In surviving animals, neurological function was significantly impaired subacutely, and tissue damage (characterized by T2 prolongation and diffusion reduction) and blood-brain barrier leakage (characterized by contrast agent extravasation) were apparent in ipsilateral cortical and subcortical tissue as well as in contralateral cortical tissue. Notably, ipsilateral cortical areas revealed increased cerebral blood flow and volume. Animals that subsequently died between days 2 and 7 after SAH had markedly elevated ipsilateral perfusion levels at day 2. After a week, neurological function had improved in surviving animals, and brain edema was partially resolved, while blood-brain barrier permeability and hyperperfusion persisted. The degree of brain damage correlated significantly with the level of perfusion elevation (r = 0.78 and 0.85 at days 2 and 7, respectively; p < 0.05). Furthermore, chronic (day 7 after SAH) blood-brain barrier permeability and vasogenic edema formation were associated with subacute (day 2 after SAH) hyperperfusion (r = 0.53 and 0.66, respectively; p < 0.05). Conclusion: Our imaging findings indicate that SAH-induced brain injury at later stages is associated with progressive changes in tissue perfusion and that chronic hyperperfusion may contribute or point to delayed cerebral damage. Furthermore, multiparametric MRI may significantly aid in diagnosing the brain's status after SAH.

INTRODUCTION: Aneurysmal subarachnoid hemorrhage (SAH) has a poor outcome, particularly attributed to progressive injury after the initial incident. Several studies suggest a critical role for inflammation in lesion progression after SAH. Our goal was to test whether treatment with anti-inflammatory interferon-β, which has shown promise as a therapeutic agent in experimental ischaemic stroke, can protect the brain after SAH.METHODS: SAH was induced in adult male Wistar rats by puncturing the intracranial bifurcation of the right internal carotid artery. Treatment effects of daily interferon-β (n = 16) or vehicle (n = 14) injections were serially evaluated with multiparametric MRI and behavioral tests from day 0 to 7, in compliance with recent recommendations for pre-clinical drug testing. Outcome measures included neurological status, brain lesion volume, blood-brain barrier (BBB) leakage, and levels of inflammatory markers.RESULTS: In animals that survived up to 7 days post-SAH, we found no significant differences between vehicle- and interferon-β-treated animals with respect to final neurological score (14.3 ± 1.0 vs. 13.0 ± 2.2), brain lesion size on T(2)-weighted MR images (59 ± 83 vs. 124 ± 99 mm(3)), BBB leakage (0.26 ± 0.05 vs. 0.22 ± 0.08 contrast-induced relative MR signal change), upregulation of brain RNA for cytokines, chemokines and cell adhesion molecules, and increased neutrophil activation.CONCLUSIONS: In contrast to previously published findings in experimental ischemic stroke models, interferon-β has no clear efficacy to protect the brain after SAH. In line with recent highlighting of the significance of negative findings, our data currently do not recommend clinical testing of interferon-β to prevent neurological damage in SAH patients.

Restoration of function after stroke may be associated with structural remodeling of neuronal connections outside the infarcted area. However, the spatiotemporal profile of poststroke alterations in neuroanatomical connectivity in relation to functional recovery is still largely unknown. We performed in vivo magnetic resonance imaging (MRI)-based neuronal tract tracing with manganese in combination with immunohistochemical detection of the neuronal tracer wheat-germ agglutinin horseradish peroxidase (WGA-HRP), to assess changes in intra- and interhemispheric sensorimotor network connections from 2 to 10 weeks after unilateral stroke in rats. In addition, functional recovery was measured by repetitive behavioral testing. Four days after tracer injection in perilesional sensorimotor cortex, manganese enhancement and WGA-HRP staining were decreased in subcortical areas of the ipsilateral sensorimotor network at 2 weeks after stroke, which was restored at later time points. At 4 to 10 weeks after stroke, we detected significantly increased manganese enhancement in the contralateral hemisphere. Behaviorally, sensorimotor functions were initially disturbed but subsequently recovered and plateaued 17 days after stroke. This study shows that manganese-enhanced MRI can provide unique in vivo information on the spatiotemporal pattern of neuroanatomical plasticity after stroke. Our data suggest that the plateau stage of functional recovery is associated with restoration of ipsilateral sensorimotor pathways and enhanced interhemispheric connectivity.

Background: Spatial and temporal changes in brain tissue after acute ischemic stroke are still poorly understood. Aims of this study were three-fold: (1) to determine unique temporal magnetic resonance imaging (MRI) patterns at the acute, subacute and chronic stages after stroke in macaques by combining quantitative T-2 and diffusion MRI indices into MRI 'tissue signatures', (2) to evaluate temporal differences in these signatures between transient (n = 2) and permanent (n = 2) middle cerebral artery occlusion, and (3) to correlate histopathology findings in the chronic stroke period to the acute and subacute MRI derived tissue signatures. Results: An improved iterative self-organizing data analysis algorithm was used to combine T-2, apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps across seven successive timepoints (1, 2, 3, 24, 72, 144, 240 h) which revealed five temporal MRI signatures, that were different from the normal tissue pattern (P