Search

BackgroundAccess to endovascular thrombectomy (EVT) is relatively limited. Hub‐and‐spoke networks seek to transfer appropriate large‐vessel occlusion stroke candidates to EVT‐capable hubs. However, some patients are ineligible upon hub arrival, and factors that drive transfer inefficiencies are not well described. We sought to quantify EVT transfer efficiency and identify reasons for EVT ineligibility.MethodsConsecutive EVT candidates presenting to 25 spokes from 2018 to 2020 with pretransfer computed tomography angiography‐defined large‐vessel occlusion and Alberta Stroke Program Early Computed Tomography Score of ≥6 were identified from a prospectively maintained database. Outcomes of interest included hub EVT, reasons for EVT ineligibility, and 90‐day modified Rankin scale score of ≤2.ResultsAmong 258 patients, the median age was 70 years (interquartile range, 60–81 years); 50% were women. A total of 56% were ineligible for EVT after hub arrival. Cited reasons were large established infarct (49%), mild symptoms (33%), recanalization (6%), distal occlusion (5%), subocclusive lesion (3%), and goals of care (3%). Late window patients (last known well >6 hours) were more likely to be ineligible (67% versus 43%;PP=0.04), had lower National Institutes of Health Stroke Scale score (10 versus 16;PPPP=0.04) compared with eligible patients. EVT ineligibility independently reduced the odds of 90‐day modified Rankin scale score of ≤2 (adjusted odds ratio, 0.26; 95% CI, 0.12–0.56;P=0.001) when controlling for age, National Institutes of Health Stroke Scale score, and last known well‐to‐hub arrival time.ConclusionsAmong patients transferred for EVT, there are multiple reasons for ineligibility upon hub arrival, with most excluded for infarct growth and mild symptoms. Understanding factors that drive transfer inefficiencies is important to improve EVT access and outcomes.

This study aimed to investigate the influence of stroke lesions in pre-defined highly interconnected (rich club) brain regions on functional outcome post-stroke, determine their spatial specificity and explore the effects of biological sex on their relevance.We analyzed MRI data recorded at index stroke and ∼3-months modified Rankin Scale (mRS) data from patients with acute ischemic stroke (AIS) enrolled in the multisite MRI-GENIE study. Structural stroke lesions were spatially normalized and parcellated into 108 atlas-defined bilateral (sub)cortical brain regions. Unfavorable outcome (mRS>2) was modeled in a Bayesian logistic regression framework that relied on both lesion location, as well as the covariates: age, sex, total DWI lesion volume and comorbidities. Effects of individual brain regions were captured as two compound effects for (i) six bilateral rich club and (ii) all further non-rich club regions. Via model comparisons, we first tested whether the rich club region model was superior to a baseline model considering clinical covariates and lesion volume only. In spatial specificity analyses, we randomized the split into “rich club” and “non-rich club” regions and compared the effect of the actual rich club regions to the distribution of effects from 1,000 combinations of six random regions. In sex-specific analyses, we introduced an additional hierarchical level in our model structure to compare male and female-specific rich club region effects.A total of 822 patients (age: 64.7 (standard deviation: 15.0), 39% women, 27.7% with mRS>2) were analyzed. The rich club model substantially outperformed the baseline model (weights of model comparison: rich club model: 0.96; baseline: 0.04). Rich club regions had substantial relevance in explaining unfavorable functional outcome (mean of posterior distribution: 0.08, area under the curve: 0.8). In particular, the rich club-combination had a higher relevance than 98.4% of random constellations (15/1,000 random constellations with higher mean posterior values). Among the these 15 random constellations with higher means, the most frequently selected regions were the inferior temporal gyrus (posterior division, 8/15), the putamen (8/15), the cingulate gyrus (7/15) and the superior parietal lobule (6/15). Rich club regions were substantially more important in explaining long-term outcome in women than in men (mean of the difference distribution:-0.107, 90%-HDPI:-0.193 to -0.0124).Lesions in rich club regions were associated with increased odds of unfavorable outcome. These effects were spatially specific, i.e., the majority of random combinations of six regions had comparably smaller effects on long-term outcome. Effects were substantially more pronounced in women.

Introduction As more large vessel occlusion stroke patients are treated with endovascular thrombectomy (EVT), understanding the pathophysiology of reperfusion injury and the risks of hemorrhagic transformation (HT) are increasingly important. Pre‐EVT infarct topography may have implications for acute interventional treatments such as stenting, and post thrombectomy care such as antithrombotic choice. We sought to quantify region‐specific volumes of infarcted tissue on pre‐EVT MRI, understand their importance for HT, and identify associations with clinical and imaging characteristics. Methods Patients with pre‐EVT MRI were identified retrospectively from a prospectively maintained database. Each patient’s diffusion weighted sequence underwent manual infarct delineation and was registered to a standard space for overlay with cortical, subcortical, and white matter atlases. Structure‐specific lesion volumes were determined. HT was defined as PH1 or PH2 hemorrhage by ECASS criteria. Variables with p< 0.10 in univariate analyses were included in multivariable models. Logistic regression was performed for associations with hemorrhagic transformation and linear regressions for infarct volumes. Results 165 participants [median age 69 years (interquartile range, IQR 56–79), 56% women] were identified. Risk factors included hypertension (70%), diabetes (20%), atrial fibrillation (34%), and prior stroke/TIA (13%). 52% were treated with intravenous alteplase; 70% achieved TICI 2b‐3 reperfusion. HT occurred in 8%. Pre‐EVT infarct volumes [median (IQR)] were 22 cc (12‐43 cc) for total, 11 cc (6‐19 cc) for white matter, 5 cc (1‐19 cc) for cortex, and 3 cc (1‐6 cc) for basal ganglia. Pre‐EVT infarcts [median (IQR)] were made up of 48% (38‐60%) white matter, 23% (6‐47%) cortex, and 15% (4‐28%) basal ganglia. Paramagnetic sequences showed 3% had petechial hemorrhage and 40% had susceptibility vessel sign. Basal ganglia infarct volume was independently associated with HT (OR = 1.342, 95%CI = 1.002,1.797) in a model including white matter infarct volume, cortex infarct volume, smoking, and puncture‐recanalization time. Basal ganglia infarct volume was linked to susceptibility vessel sign (Beta = 0.233, p = 0.006) and NIHSS (Beta = 0.220, p = 0.012), when controlling for total infarct volume. Conclusions In this cohort, greater basal ganglia infarct volume was associated with a higher risk of hemorrhagic transformation, even when accounting for infarct volume in other regions. Susceptibility vessel sign was associated with basal ganglia infarct volume, which may be related to acute middle cerebral artery thrombus occlusion of perforators. These findings require further study in larger cohorts.

Introduction: Predicting individual outcomes post-stroke with the highest possible accuracy is a crucial steppingstone in the realization of precision medicine. We here evaluated various types of lesion information in their capacity to predict stroke severity in a large cohort of patients with acute ischemic stroke. Methods: A total of 1,075 patients of the MRI-GENIE study [age: 64.2(14.7), 38% women] contributed to analyses (N=792 as train and N=283 as test sample). We employed ridge regression with hyperparameter optimization and nested five-fold cross-validation to predict acute NIHSS-based stroke severity. Our baseline model considered DWI lesion volume. Further models tested structural lesion location, indirect structural and functional lesion connectivity, individually and combined with lesion volume. Data was preprocessed by principal component analysis (PCA), retaining 95% of the variance of the original data. Model performance was compared in terms of explained variance (R-squared) and 95% confidence intervals in the outer loop of the training set and the test set. Results: Structural lesion connectivity enabled the highest prediction performance in the test set ( Figure 1 ). Prediction performance did not change notably with inclusion of lesion volume information. This contrasted with the combination of functional lesion connectivity and lesion volume that achieved a substantially higher prediction performance compared to functional lesion connectivity or lesion volume in isolation. Lesion location resulted in a prediction performance that was in the range of lesion volume alone and significantly lower than the ones of structural or functional connectivity with lesion volume. Conclusions: Structural connectivity facilitated the most convincing prediction of stroke severity. The capacity of functional lesion connectivity was substantially improved by the inclusion of lesion volume, indicating both represent complementary information.

Introduction: Deep learning (DL) has allowed for substantial progress in many, often machine vision-focused medical scenarios. Since DL models typically require 10 5 -10 7 examples, it is currently unknown whether DL can also enhance predictions of outcomes post-stroke in real-world samples of stroke patients that are several magnitudes smaller. We here compared the capacities of linear and DL algorithms regarding their prediction of stroke severity. Methods: Our analyses relied on a total of 1435 patients assembled from the MRI-GENIE study and a Massachusetts General Hospital-based study. The primary outcome was acute NIHSS-based stroke severity, which we predicted by means of lesion location. We automatically derived lesion segmentations from DWI scans, performed spatial normalization and principal component analysis (PCA), retaining 95% of the variance of the original data. We then separated a train, validation, and test set, of sizes 918, 230, and 287 respectively. We downsampled the train set to 100, 300, and 900 and learned to predict the NIHSS score for each sample size with regularized linear regression and an 8-layered neural network. We selected hyperparameters on the validation set and conducted 500 dataset splits. We here report explained variance (R-squared) in the test set. Results: While linear regression performed favorably for a sample size of 100 patients (R-squared=0.28), DL started to significantly outperform linear regression when trained on 900 patients (R-squared=0.34, Figure 1 ). Average prediction performance improved by ~20% when increasing the sample size 9x. Conclusions: For sample sizes of ~1000 patients, DL showed a more convincing prediction performance for stroke severity than typically employed linear methods. Our findings suggest the existence of non-linear relationships between lesion location and outcome post-stroke that can be utilized for an improved prediction performance once samples are reasonably large.

Background and ObjectivesThe care of patients with large vessel occlusion (LVO) stroke has been revolutionized by endovascular thrombectomy (EVT). While EVT has a large effect size, most patients treated with EVT remain disabled or die within 90 days. A better understanding of outcomes may influence EVT selection criteria, novel therapies, and prognostication. We sought to identify associations between outcomes and brain regions involved in ischemic lesions.MethodsFor this cohort study, consecutive patients with LVO who were treated with EVT and underwent post-EVT MRI were identified from a tertiary referral center (2011–2019). Acute ischemic lesions were manually segmented from diffusion-weighted imaging and spatially normalized. Individual lesions were parcellated (atlas-defined 94 cortical regions, 14 subcortical nuclei, 20 white matter tracts) and reduced to 10 essential lesion patterns with the use of unsupervised dimensionality reduction techniques. Ninety-day modified Rankin Scale (mRS) score (>2) was modeled via bayesian regression, taking the 10 lesion patterns as inputs and controlling for lesion size, age, sex, acute NIH Stroke Scale (NIHSS) score, alteplase, prior stroke, intracerebral hemorrhage, and good reperfusion (Thrombolysis in Cerebral Infarction 2b–3). In comparative analyses, 90-day mRS score was modeled considering covariates only, and compartment-wise relevances for acute stroke severity and 90-day mRS score were evaluated.ResultsThere were 151 patients with LVO identified (age 68 ± 15 years, 52% female). The median NIHSS score was 16 (interquartile range 13–20); 56% had mRS score >2. Lesion locations predictive of 90-day mRS score involved bilateral but left hemispherically more pronounced precentral and postcentral gyri, insular and opercular cortex, and left putamen and caudate (area under the curve 0.91, highest probability density interval [HPDI] covering 90% certainty 0.90–0.92). The lesion location model outperformed the simpler model relying on covariates only (bayesian model comparison of 97% weight to the model with vs 3% weight to the model without lesion location). While lesions affecting subcortical nuclei had the highest relevance for stroke severity (posterior distribution mean 0.75, 90% HPDI 0.256–1.31), lesions affecting white matter tracts had the highest relevance for 90-day mRS score (0.656, 90% HPDI 0.0864–1.12).DiscussionThese data describe the significance for outcomes of specific brain regions involved in ischemic lesions on MRI after EVT. Future work in additional datasets is needed to confirm these granular findings.

IntroductionStroke causes different levels of impairment and the degree of recovery varies greatly between patients. The majority of recovery studies are biased towards patients with mild-to-moderate impairments, challenging a unified recovery process framework. Our aim was to develop a statistical framework to analyse recovery patterns in patients with severe and non-severe initial impairment and concurrently investigate whether they recovered differently.MethodsWe designed a Bayesian hierarchical model to estimate 3–6 months upper limb Fugl-Meyer (FM) scores after stroke. When focusing on the explanation of recovery patterns, we addressed confounds affecting previous recovery studies and considered patients with FM-initial scores FM-initial=5–30). In model comparisons, we evaluated whether impairment-level-specific recovery patterns indeed existed. Finally, we estimated the out-of-sample prediction performance for patients across the entire initial impairment range.ResultsRecovery data was assembled from eight patient cohorts (n=489). Data were best modelled by incorporating two subgroups (breakpoint: FM-initial=10). Both subgroups recovered a comparable constant amount, but with different proportional components: severely affected patients recovered more the smaller their impairment, while non-severely affected patients recovered more the larger their initial impairment. Prediction of 3–6 months outcomes could be done with an R2=63.5% (95% CI=51.4% to 75.5%).ConclusionsOur work highlights the benefit of simultaneously modelling recovery of severely-to-non-severely impaired patients and demonstrates both shared and distinct recovery patterns. Our findings provide evidence that the severe/non-severe subdivision in recovery modelling is not an artefact of previous confounds. The presented out-of-sample prediction performance may serve as benchmark to evaluate promising biomarkers of stroke recovery.

IntroductionDeep learning has allowed for remarkable progress in many medical scenarios. Since deep learning prediction models often require 105-107examples, it is currently unknown whether deep learning can also enhance predictions of symptoms post-stroke in real-world samples of stroke patients that are often several magnitudes smaller. Such stroke outcome predictions however could be particularly instrumental in guiding acute clinical and rehabilitation care decisions. We here compared the capacities of classically used linear and novel deep learning algorithms in their prediction of stroke severity.MethodsOur analyses relied on a total of 1,430 patients assembled from the MRI-GENIE collaboration and a Massachusetts General Hospital-based study. The outcome of interest was NIHSS-based stroke severity in the acute phase after ischemic stroke onset, which we predict by means of MRI-derived lesion location. We automatically derived lesion segmentations from diffusion-weighted clinical MRI scans, performed spatial normalization and included a principal component analysis (PCA) step, retaining 95% of the variance of the original data. We then repeatedly separated a train, validation, and test set to investigate the effects of sample size, we subsampled the train set to 100, 300, and 900 and trained the algorithms to predict the NIHSS score for each sample size with regularized linear regression and an 8-layered neural network. We selected hyperparameters on the validation set. We evaluated model performance based on the explained variance (R-squared) in the test set.ResultsWhile linear regression performed significantly better for a sample size of 100 patients, deep learning started to significantly outperform linear regression when trained on 900 patients. Average prediction performance improved by ∼20% when increasing the sample size 9x (maximum for 100 patients: 0.279 ± 0.005 (R2, 95% confidence interval), 900 patients: 0.337 ± 0.006).ConclusionsFor sample sizes of 900 patients, deep learning showed a higher prediction performance than typically employed linear methods. These findings suggest the existence of non-linear relationships between lesion location and stroke severity that can be utilized for an improved prediction performance for larger sample sizes.

BACKGROUND AND PURPOSE Ischemic diffusion-weighted imaging-fluid-attenuated inversion recovery (DWI-FLAIR) mismatch may be useful in guiding acute stroke treatment decisions given its relationship to onset time and parenchymal viability; however, it relies on subjective grading. Radiomics is an emerging image quantification methodology that may objectively represent continuous image characteristics. We propose a novel radiomics approach to characterize DWI-FLAIR mismatch. METHODS Ischemic lesions were visually graded for FLAIR positivity (absent, subtle, obvious) among consecutive large vessel occlusion stroke patients who underwent hyperacute MRI. Radiomic features were extracted from within the lesions on DWI and FLAIR. The DWI-FLAIR mismatch radiomics signature was built with features systematically selected by a cross-validated ElasticNet linear regression model of mismatch. RESULTS We identified 103 patients with mean age 68 ± 16 years; 63% were female. FLAIR hyperintensity was absent in 25%, subtle in 55%, and obvious in 20%. Inter-rater agreement for visual grading was moderate (Κ = .58). The radiomics signature of DWI-FLAIR mismatch included native FLAIR histogram kurtosis and local binary pattern-filtered FLAIR gray-level cluster shade; both correlated with visual grading (ρ = -.42, p

BackgroundDifferences in dopaminergic motor response in Parkinson’s disease (PD) patients are related to specific PD subtypes. An important factor driving dopaminergic response might lie in the temporal dynamics in corticostriatal connections.ObjectivesThe aim of this study is to determine if altered resting-state dynamic functional network connectivity (dFNC) is associated with dopaminergic motor response.MethodsWe assessed static and dFNC in 32 PD patients and 18 healthy controls (HC). Patients were subgrouped according to their dopaminergic motor response as low and high responders using a median split.ResultsPatients featuring high dopaminergic responses spent more time in a regionally more integrated state 1 compared to HC. Furthermore, dFNC between aMCC/dACC (anterior midcingulate cortex/dorsal anterior cingulate cortex) and putamen was lower in low responders during a more segregated state 2 and correlated with dopaminergic motor response.ConclusionsAlterations in temporal dynamics of fronto-striatal connectivity might underlie treatment response in PD.

Background and ObjectivesTo examine whether high white matter hyperintensity (WMH) burden is associated with greater stroke severity and worse functional outcomes in lesion pattern–specific ways.MethodsMR neuroimaging and NIH Stroke Scale data at index stroke and the modified Rankin Scale (mRS) score at 3–6 months after stroke were obtained from the MRI–Genetics Interface Exploration study of patients with acute ischemic stroke (AIS). Individual WMH volume was automatically derived from fluid-attenuated inversion recovery images. Stroke lesions were automatically segmented from diffusion-weighted imaging (DWI) images, parcellated into atlas-defined brain regions and further condensed to 10 lesion patterns via machine learning–based dimensionality reduction. Stroke lesion effects on AIS severity and unfavorable outcomes (mRS score >2) were modeled within purpose-built Bayesian linear and logistic regression frameworks. Interaction effects between stroke lesions and a high vs low WMH burden were integrated via hierarchical model structures. Models were adjusted for age, age2, sex, total DWI lesion and WMH volumes, and comorbidities. Data were split into derivation and validation cohorts.ResultsA total of 928 patients with AIS contributed to acute stroke severity analyses (age: 64.8 [14.5] years, 40% women) and 698 patients to long-term functional outcome analyses (age: 65.9 [14.7] years, 41% women). Stroke severity was mainly explained by lesions focused on bilateral subcortical and left hemispherically pronounced cortical regions across patients with both a high and low WMH burden. Lesions centered on left-hemispheric insular, opercular, and inferior frontal regions and lesions affecting right-hemispheric temporoparietal regions had more pronounced effects on stroke severity in case of high compared with low WMH burden. Unfavorable outcomes were predominantly explained by lesions in bilateral subcortical regions. In difference to the lesion location–specific WMH effects on stroke severity, higher WMH burden increased the odds of unfavorable outcomes independent of lesion location.DiscussionHigher WMH burden may be associated with an increased stroke severity in case of stroke lesions involving left-hemispheric insular, opercular, and inferior frontal regions (potentially linked to language functions) and right-hemispheric temporoparietal regions (potentially linked to attention). Our findings suggest that patients with specific constellations of WMH burden and lesion locations may have greater benefits from acute recanalization treatments. Future clinical studies are warranted to systematically assess this assumption and guide more tailored treatment decisions.

Cognitive and behavioural outcomes in stroke reflect the interaction between two complex anatomically-distributed patterns: the functional organization of the brain and the structural distribution of ischaemic injury. Conventional outcome models—for individual prediction or population-level inference—commonly ignore this complexity, discarding anatomical variation beyond simple characteristics such as lesion volume. This sets a hard limit on the maximum fidelity such models can achieve. High-dimensional methods can overcome this problem, but only at prohibitively large data scales. Drawing on one of the largest published collections of anatomically-registered imaging of acute stroke—N = 1333—here we use non-linear dimensionality reduction to derive a succinct latent representation of the anatomical patterns of ischaemic injury, agglomerated into 21 distinct intuitive categories. We compare the maximal predictive performance it enables against both simpler low-dimensional and more complex high-dimensional representations, employing multiple empirically-informed ground truth models of distributed structure–outcome relationships. We show our representation sets a substantially higher ceiling on predictive fidelity than conventional low-dimensional approaches, but lower than that achievable within a high-dimensional framework. Where descriptive simplicity is a necessity, such as within clinical care or research trials of modest size, the representation we propose arguably offers a favourable compromise of compactness and fidelity.

Introduction: Endovascular thrombectomy (EVT) has revolutionized the care of emergent large vessel occlusion (ELVO) stroke patients. It is, therefore, crucial to optimize its delivery to eligible candidates. Within hub-and-spoke hospital system models, some patients first present to distant spoke hospitals and require transfer to hub hospitals for EVT. We sought to understand changes in EVT eligibility during transfer. Methods: Consecutive EVT candidates presenting to 25 spokes from 2018 to 2020 with pre-transfer CTA-defined ELVO and Alberta Stroke Program Early CT Score ≥6 were identified from a prospectively maintained database. Outcomes of interest included hub EVT, reasons for EVT ineligibility, and 90-day functional independence (modified Rankin Scale, mRS ≤2). Results: Among 258 patients, the median age was 70 years (IQR 60-81) and 50% were female. Forty-four percent underwent EVT upon hub arrival, of which 87% achieved Thrombolysis in Cerebral Infarction 2b-3 reperfusion. Compared to EVT-eligible patients, ineligible patients were older (73 vs 68 years, p=0.04), had lower NIH Stroke Scale (NIHSS, 10 vs 16, p Conclusions: These data support that approaches to increase EVT eligibility among ELVO transfers may improve long term outcomes. Infarct growth represents the primary reason for ineligibility. Possible interventions include direct field triage to the hub when feasible, improving inter-hospital transfer times, supporting ischemic penumbra before EVT, and developing novel agents to slow infarct growth.

Given the efficacy of endovascular thrombectomy (EVT), optimizing systems of delivery is crucial. Magnetic resonance imaging (MRI) is the gold standard for evaluating tissue viability but may require more time to obtain and interpret. We sought to identify determinants of arrival-to-puncture time for patients who underwent MRI-based EVT selection in a real-world setting.Patients were identified from a prospectively maintained database from 2011-2019 that included demographics, presentations, treatments, and outcomes. Process times were obtained from the medical charts. MRI times were obtained from time stamps on the first sequence. Linear and logistic regressions were used to infer explanatory variables of arrival-to-puncture times and effects of arrival-to-puncture time on functional outcomes.In this study 192 patients (median age 70 years, 57% women, 12% non-white) underwent MRI-based EVT selection. 66% also underwent computed tomography (CT) at the hub before EVT. General anesthesia was used for 33%. Among the entire cohort, the median arrival-to-puncture was 102 min; however, among those without CT it was 77 min. Longer arrival-to-puncture times independently reduced the odds of 90-day good outcome (∆mRS ≤ 2 from pre-stroke, aOR = 0.990, 95%CI = 0.981-0.999, p = 0.040) when controlling for age, NIHSS, and good reperfusion (TICI 2b-3). Independent determinants of longer arrival-to-puncture were CT plus MRI (β = 0.205, p = 0.003), non-white race/ethnicity (β = 0.162, p = 0.012), coronary disease (β = 0.205, p = 0.001), and general anesthesia (β = 0.364, p 0.0001).Minimizing arrival-to-puncture time is important for outcomes. Real-world challenges exist in an MRI-based EVT selection protocol; avoiding double imaging is key to saving time. Racial/ethnic disparities require further study. Understanding variables associated with delay will inform protocol changes.

ObjectiveTo examine whether high white matter hyperintensity (WMH) burden is associated with greater stroke severity and worse functional outcomes in lesion pattern-specific ways.MethodsMR neuroimaging and National Institutes of Health Stroke Scale data at index stroke, as well as modified Rankin Scale (mRS) at 3-6 months post-stroke were obtained from MRI-GENIE study of acute ischemic stroke (AIS) patients. Individual WMH volume was automatically derived from FLAIR-images. Stroke lesions were automatically segmented from DWI-images, spatially normalized and parcellated into atlas-defined brain regions. Stroke lesion effects on AIS severity and unfavorable outcomes (mRS>2) were modeled within a purpose-built machine learning and Bayesian regression framework. In particular, interaction effects between stroke lesions and a high versus low WMH burden were integrated via hierarchical model structures. Models were adjusted for the covariates age, age2, sex, total DWI-lesion and WMH volumes, and comorbidities. Data were split into derivation and validation cohorts.ResultsA total of 928 AIS patients contributed to stroke severity analyses (mean age: 64.8(14.5), 40% women), 698 patients to functional outcome analyses (mean age: 65.9(14.7), 41% women). Individual stroke lesions were represented in five anatomically distinct left-hemispheric and five right-hemispheric lesion patterns. Across all patients, acute stroke severity was substantially explained by three of these patterns, that were particularly focused on bilateral subcortical and left-hemispherically pronounced cortical regions. In high WMH burden patients, two lesion patterns consistently emerged as more pronounced in case of stroke severity: the first pattern was centered on left-hemispheric insular, opercular and inferior frontal regions, while the second pattern combined right-hemispheric temporo-parietal regions. Bilateral subcortical regions were most relevant in explaining long term unfavorable outcome. No WMH-specific lesion patterns of functional outcomes were substantiated. However, a higher overall WMH burden was associated with higher odds of unfavorable outcomes.ConclusionsHigher WMH burden increases stroke severity in case of stroke lesions involving left-hemispheric insular, opercular and inferior frontal regions (potentially linked to language functions) and right-hemispheric temporo-parietal regions (potentially linked to attention). These findings may contribute to augment stroke outcome predictions and motivate a WMH burden and stroke lesion pattern-specific clinical management of AIS patients.

This meeting abstract was removed due to the OA licensing requirements of this journal. The full abstract is listed here : https://www.svin.org/files/SVIN_2021_Abstracts_for_Web.pdf

Introduction : The care of emergent large vessel occlusion (ELVO) stroke patients has been revolutionized by endovascular thrombectomy (EVT). Given its robust efficacy, it is crucial to optimize delivery to eligible patients. Within hub‐and‐spoke hospital system models, some patients first present to distant spoke hospitals and require transfer to hub hospitals for EVT. We sought to understand reasons EVT candidates become ineligible after transfer for treatment. Methods : Consecutive EVT candidates presenting to 25 spokes from 2018 to 2020 with pre‐transfer CTA‐defined ELVO and Alberta Stroke Program Early CT Score ≥6 were identified from a prospectively maintained database. Outcomes of interest included hub EVT, reasons for EVT ineligibility, and 90‐day functional independence (modified Rankin Scale, mRS ≤2). Results : 258 patients were identified with median age 70 years (IQR 60–81) and 50% female. 44% underwent EVT upon hub arrival, of which 87% achieved Thrombolysis in Cerebral Infarction 2b‐3 reperfusion. Compared to EVT‐eligible patients, ineligible patients were older (73 vs 68 years, p = 0.04), had lower NIH Stroke Scale (NIHSS, 10 vs 16, p Conclusions : Approaches to increase EVT eligibility among ELVO transfers may improve long term outcomes. A primary reason for becoming EVT ineligible is infarct growth. Future studies should explore triaging patients directly to EVT‐capable hubs when feasible, improving inter‐hospital transfer times, supporting ischemic penumbra before EVT, and developing novel neuroprotective agents.

While chronological age is one of the most influential determinants of post-stroke outcomes, little is known of the impact of neuroimaging-derived biological brain age. We here first examine whether radiomics analysis of the texture of brain T2-FLAIR MRI images can be used to predict brain age in stroke patients. We then assess the clinical determinants of accelerated brain aging and, finally, its impact on post-stroke functional outcomes. Leveraging a multisite cohort of 4,163 ischemic stroke patients, we show that older-appearing patients have more hypertension, diabetes mellitus, prior strokes, and smoking history and are more likely to develop worse post-stroke outcomes than their younger-appearing counterparts. Our results strengthen the importance of preventive medicine for maintaining brain health in stroke patients as they age and suggest a novel methodology to capture previously undescribed prognostic information available on commonly acquired MRI sequences during routine stroke care.

Acute ischemic stroke affects men and women differently. In particular, women are often reported to experience higher acute stroke severity than men. We derived a low-dimensional representation of anatomical stroke lesions and designed a Bayesian hierarchical modeling framework tailored to estimate possible sex differences in lesion patterns linked to acute stroke severity (National Institute of Health Stroke Scale). This framework was developed in 555 patients (38% female). Findings were validated in an independent cohort (n = 503, 41% female). Here, we show brain lesions in regions subserving motor and language functions help explain stroke severity in both men and women, however more widespread lesion patterns are relevant in female patients. Higher stroke severity in women, but not men, is associated with left hemisphere lesions in the vicinity of the posterior circulation. Our results suggest there are sex-specific functional cerebral asymmetries that may be important for future investigations of sex-stratified approaches to management of acute ischemic stroke., Acute ischemic stroke impacts men and women differently. Here, the authors show how different lesion patterns in men and women are linked to the extent of stroke severity.

ObjectiveTo test the hypothesis that cognitive demands influence motor performance during recovery from acute stroke, we tested patients with acute stroke on 2 motor tasks with different cognitive demands and related task performance to cognitive impairment and neuroanatomic injury.MethodsWe assessed the contralesional and ipsilesional upper extremities of a cohort of 50 patients with weakness after unilateral acute ischemic stroke at 3 time points with 2 tasks: the Box & Blocks Test, a task with greater cognitive demand, and Grip Strength, a simple and ballistic motor task. We compared performance on the 2 tasks, related motor performance to cognitive dysfunction, and used voxel-based lesion symptom mapping to determine neuroanatomic sites associated with motor performance.ResultsConsistent across contralesional and ipsilesional upper extremities and most pronounced immediately after stroke, Box & Blocks scores were significantly more impaired than Grip Strength scores. The presence of cognitive dysfunction significantly explained up to 33% of variance in Box & Blocks performance but was not associated with Grip Strength performance. While Grip Strength performance was associated with injury largely restricted to sensorimotor regions, Box & Blocks performance was associated with broad injury outside sensorimotor structures, particularly the dorsal anterior insula, a region known to be important for complex cognitive function.ConclusionsTogether, these results suggest that cognitive demands influence upper extremity motor performance during recovery from acute stroke. Our findings emphasize the integrated nature of motor and cognitive systems and suggest that it is critical to consider cognitive demands during motor testing and neurorehabilitation after stroke.

The proportional recovery rule states that most survivors recover a fixed proportion (~70%) of lost function after stroke. A strong (negative) correlation between the initial score and subsequent change (outcome minus initial; i.e. recovery) is interpreted as empirical support for the proportional recovery rule. However, this rule has recently been critiqued, with a central observation being that the correlation of initial-scores with change over time is confounded in the situations in which it is typically assessed. This critique has prompted reassessments of patients’ behavioural trajectory following stroke in two prominent papers. The first of these, by van der Vliet and collaborators presented an impressive modelling of upper limb deficits following stroke, which avoided the confounded correlation of initial-scores with change. The second by Kundert and collaborators reassessed the value of the proportional recovery rule, as classically formulated as the correlation between initial-scores and change. They argued that, while effective prediction of recovery trajectories of individual patients is not supported by the available evidence, group-level inferences about the existence of proportional recovery are reliable. In this paper, we respond to the van der Vliet and Kundert papers by distilling the essence of the argument for why the classic assessment of proportional recovery is confounded. In this respect, we re-emphasize the role of mathematical coupling and compression to ceiling in the confounded nature of the correlation of initial-scores with change. We further argue that this confound will be present for both individual-level and group-level inference. We then focus on the difficulties that can arise from ceiling effects, even when initial-scores are not being correlated with change/ recovery. We conclude by emphasizing the need for new techniques to analyse recovery after stroke that are not confounded in the ways highlighted here.

Cognitive impairment is a frequent and disabling sequela of stroke. There is however incomplete understanding of how lesion topographies in the left and right cerebral hemisphere brain interact to cause distinct cognitive deficits. We integrated machine learning and Bayesian hierarchical modelling to enable a hemisphere-aware analysis of 1080 acute ischaemic stroke patients with deep profiling ∼3 months after stroke. We show the relevance of the left hemisphere in the prediction of language and memory assessments and relevance of the right hemisphere in the prediction of visuospatial functioning. Global cognitive impairments were equally well predicted by lesion topographies from both sides. Damage to the hippocampal and occipital regions on the left was particularly informative about lost naming and memory functions, while damage to these regions on the right was linked to lost visuospatial functioning. Global cognitive impairment was predominantly linked to lesioned tissue in the supramarginal and angular gyrus, the post-central gyrus as well as the lateral occipital and opercular cortices of the left hemisphere. Hence, our analysis strategy uncovered that lesion patterns with unique hemispheric distributions are characteristic of how cognitive capacity is lost due to ischaemic brain tissue damage., Bonkhoff et al. integrate machine learning and Bayesian hierarchical modelling to enable hemisphere-aware analysis of 1080 stroke patients. They quantify lateralization effects of cortical and subcortical regions, such as the pallidum and hippocampus, of middle and posterior cerebral artery vascular territories to the left for naming/memory and to the right for visuospatial functions., Graphical Abstract Graphical Abstract

Individuals can be characterized in a population according to their brain measurements and activity, given the inter-subject variability in brain anatomy, structure-function relationships, or life experience. Many neuroimaging studies have demonstrated the potential of functional network connectivity patterns estimated from resting functional magnetic resonance imaging (fMRI) to discriminate groups and predict information about individual subjects. However, the predictive signal present in the spatial heterogeneity of brain connectivity networks is yet to be extensively studied. In this study, we investigate, for the first time, the use of pairwise-relationships between resting-state independentspatial mapsto characterize individuals. To do this, we develop a deep Siamese framework comprising three-dimensional convolution neural networks for contrastive learning based on individual-level spatial maps estimated via a fully automated fMRI independent component analysis approach. The proposed framework evaluates whether pairs of spatial networks (e.g., visual network and auditory network) are capable of subject identification and assesses the spatial variability in different network pairs’ predictive power in an extensive whole-brain analysis. Our analysis on nearly 12,000 unaffected individuals from the UK Biobank study demonstrates that the proposed approach can discriminate subjects with an accuracy of up to 88% for a single network pair on the test set (best model, after several runs), and 82% average accuracy at the subcortical domain level, notably the highest average domain level accuracy attained. Further investigation of our network’s learned features revealed a higher spatial variability in predictive accuracy among younger brains and significantly higher discriminative power among males. In sum, the relationship among spatial networks appears to be both informative and discriminative of individuals and should be studied further as putative brain-based biomarkers.

Stroke ranks among the leading causes for morbidity and mortality worldwide. New and continuously improving treatment options such as thrombolysis and thrombectomy have revolutionized acute stroke treatment in recent years. Following modern rhythms, the next revolution might well be the strategic use of the steadily increasing amounts of patient-related data for generating models enabling individualized outcome predictions. Milestones have already been achieved in several health care domains, as big data and artificial intelligence have entered everyday life. The aim of this review is to synoptically illustrate and discuss how artificial intelligence approaches may help to compute single-patient predictions in stroke outcome research in the acute, subacute and chronic stage. We will present approaches considering demographic, clinical and electrophysiological data, as well as data originating from various imaging modalities and combinations thereof. We will outline their advantages, disadvantages, their potential pitfalls and the promises they hold with a special focus on a clinical audience. Throughout the review we will highlight methodological aspects of novel machine-learning approaches as they are particularly crucial to realize precision medicine. We will finally provide an outlook on how artificial intelligence approaches might contribute to enhancing favourable outcomes after stroke.

Introduction: As a radiographic signature of end-stage small vessel disease, white matter hyperintensity (WMH) burden impacts recovery and outcomes after acute ischemic stroke (AIS). In this study, we sought to investigate the effect of WMH volume (WMHv) on stroke severity and functional outcomes independent of the infarct size and topography. Methods: We analyzed 503 AIS patients with MRI data obtained on admission for index stroke enrolled in the multi-center MRI-GENIE study (cohort 1), followed by validation of the findings in an independent single-site study of 555 AIS patients (cohort 2). Stroke severity (NIHSS score) at index stroke and the long-term outcome (3-6 months mRS score) were modeled via Bayesian linear regression. Models included WMHv, age, sex, a 10-dimensional spatial ischemic lesion representation, acute infarct (DWI) volume, and common vascular risk factors (hypertension, diabetes mellitus, atrial fibrillation, coronary artery disease). Results: Cohorts did not differ significantly in major clinical characteristics [cohort 1: age: 65.0±14.6, 41% female, NIHSS: 5.5±5.4, mRS: 1(iqr 2); cohort 2: age: 65.0±14.8, 38% female, NIHSS: 5.0±6.0, mRS: 1(iqr 3), p >0.05 for all comparisons]. WMHv did not substantially affect AIS severity ( Fig A ); in contrast, it emerged as an independent predictor of functional outcome in both datasets ( Fig B ). Conclusions: When accounted for AIS lesion topography and stroke volume, total WMH lesion burden did not appear to modulate initial stroke severity but was associated with worse functional post-stroke outcomes. Future studies are needed to explore potential origins of these detrimental effects of pre-existing WMH burden on recovery after AIS.

Introduction: MRI-detected white matter hyperintensity (WMH) burden is linked to the overall brain health and incident stroke outcomes. However, data are limited as to whether specific acute stroke lesion patterns purport greater stroke severity in patients with extensive pre-existing WMH. In this analysis, we sought to investigate lesion pattern-specific WMH effects on AIS severity. Methods: We analyzed clinical and lesion data from 621 AIS patients enrolled in the multi-site MRI-GENIE study. The acute NIHSS was modelled via Bayesian hierarchical regression. Using ten stroke lesion patterns, that served as input variables of main interest, we introduced a hierarchical level differentiating between patients with higher and lower than median WMH volume (WMHv). Lesion pattern posterior distributions for higher and lower WMHv patients were subtracted to infer substantial differences. Results: In this AIS cohort [age: 65.3±14.6, 60% male], a higher WMHv was associated with greater stroke severity only when specific left-hemispheric brain regions were infarcted. This “lesion pattern 3” was mainly characterized by left middle and inferior frontal gyrus, insular and opercular cortex, pre- and post-central gyrus, and subcortical basal ganglia regions ( Fig ). Conclusions: Higher WMH burden appears to enhance the detrimental effect of acute stroke lesions involving left-hemispheric brain regions underlying language and motor functions. This effect might be due to an exacerbated disruption of functional network integrity by the combination of WMH and stroke lesions and could be explored further in functional imaging studies that simultaneously considered information from both lesion types.

Objective: Ability of the brain to recover after an acute ischemic stroke (AIS) is linked to the pre-stroke burden of white matter hyperintensity (WMH), a radiographic marker of brain health. We sought to determine the excessive WMH burden in an AIS population and investigate its association with 3-month stroke outcomes. Data: We used 2,435 subjects from the MRI-GENIE study. Three-month functional outcomes of 872 subjects among those subjects were measured by 90-day modified Ranking Scale (mRS). Methods: We automatically quantified WMH volume (WMHv) on FLAIR images and adjusted for a brain volume. We modeled a trend using the factor analysis (FA) log-linear regression using age, sex, atrial fibrillation, diabetes, hypertension, coronary artery disease and smoking as input variables. We categorized three WMH burden groups based on the conditional probability given by the model (LOW: lower 33%, MED: middle 34%, and HIGH: upper 33%). The subgroups were compared with respect to mRS (median and dichotomized odds ratio (OR) (good/poor: mRS 0-2/3-6)). Results: Five FA components out of seven with significant relationship to WMHv (p2 =0.359). The HIGH group showed higher median (median=2, IQR=2) mRS score than LOW (median=1, IQR=1) and MED (median=1, IQR=1). The odds (OR) of good AIS outcome for LOW and MED were 1.8 (p=0.0001) and 1.6 (p=0.006) times higher than HIGH, respectively. Conclusion: Once accounted for clinical covariates, the excessive WMHv was associated with worse 3-month stroke outcomes. These data suggest that a life-time of injury to the white matter reflected in WMH is an important factor for stroke recovery and an indicator of the brain health.

Introduction: Endovascular thrombectomy (EVT) has revolutionized large vessel occlusion (LVO) stroke care. However, over half remain functionally disabled or die despite treatment. Understanding outcomes may influence EVT selection, novel therapies, and prognostication. We sought to identify associations between outcomes and brain regions involved in ischemic lesions. Methods: For consecutive LVO patients with post-EVT MRI, acute ischemic lesions were manually segmented from DWI and spatially normalized. Individual lesion volumes were automatically parcellated (atlas-defined 94 cortical regions, 14 subcortical nuclei, 20 white matter tracts) and then reduced to ten anatomically plausible lesion patterns using unsupervised dimensionality reduction techniques. Ninety-day modified Rankin Scale (mRS) was modeled via Bayesian regression, taking the ten lesion patterns as inputs and controlling for lesion size, age, sex, acute NIH Stroke Scale, alteplase, and TICI 2b-3 reperfusion. Results: We identified 153 LVO patients with mean age 68±15 years and 51% female. Median NIHSS was 16 (IQR 13-20), 56% received alteplase, and 84% achieved TICI2b-3. The lesion patterns predictive of 90-day mRS involved bilateral subcortical nuclei, pre- and postcentral gyri, insular and opercular cortex, as well as left-sided inferior frontal and angular gyri ( Figure 1A ). Lesions affecting white matter tracts had the highest relevance predicting 90-day mRS ( Figure 1B ). Conclusions: These data describe the significance for outcomes of specific brain regions involved in ischemic lesions on MRI after EVT. Future work in additional datasets is needed to confirm these granular findings.

Introduction: Severity of leukoaraiosis detected on T2 MRI scans as white matter hyperintensities (WMH) is associated with infarct growth and poor poststroke outcomes in patients with acute ischemic stroke (AIS). Traditional vascular risk factors (VRF) such as age, hypertension (HTN), type 2 diabetes mellitus (T2D), and cigarette smoking are linked to WMH in large population-based studies, yet casual inferences for WMH in AIS patients are limited. We sought to examine the VRFs for evidence of causal relationships with WMH burden in AIS patients using mendelian randomization principles and polygenic risk score (PRS) methods. Method: We examined FLAIR MRIs obtained within 48 hours of AIS onset in 4,362 European Caucasian patients from the MRI-GENetics Interface Exploration (MRI-GENIE) study. WMH volume (WMHv) was measured using a fully automated deep-learning trained algorithm. We considered 13 VRFs: blood pressure (HTN, SBP, DBP, Pulse Pressure), lipid (total cholesterol, HDL, LDL, TG), BMI, T2D, atrial fibrillation, alcohol use and smoking. For each factor, we calculated a weighted PRS for each individual based on the most recent GWAS with various GWAS p-value cutoff. We then used linear regression to estimate associations between each PRS and log transformed WMHv, controlling for age, gender and principal components of genetic ancestries. Strata-specific estimates were combined using inverse-variance weighting based meta-analysis. Results: PRS of both SBP and DBP were positively and robustly associated with WMHv in the meta-analysis (p value of the association ranging from Conclusion: Using mendelian randomization, our results lend further evidence that high blood pressure is a causal risk factor for WMH in AIS patients. This result is consistent with previous epidemiological studies of leukoaraiosis in stroke-free populations, and it supports universal control of HTN as common contributor to WMH burden and the overall brain health.

Introduction: Structural integrity of cerebral parenchyma is an essential radiographic equivalent of brain health; but its assessment usually requires dedicated advanced image acquisitions. Radiomics analyses bear the potential to describe radiophenotypes beyond what meets the naked eye. We sought to: 1) evaluate this novel approach to predict white matter hyperintensity (WMH) burden and 2) uncover latent clinico-radiological associations. Methods: An international, multi-site cohort of 4,164 acute ischemic stroke (AIS) patients with FLAIR MRI (MRI-GENIE study) underwent total brain and WMH lesion segmentation using convolutional neural networks. Radiomic features (n=1905) were extracted from clinical FLAIR images outside of the WMH (brain mask - WMH mask). Prediction of the WMH burden using radiomics was done using LASSO regression. Radiomic signature of WMH was built with the most stable selected features, then compared to the clinical variables using canonical correlation analysis. Results: In this cohort, (mean age=62.8±15.0, median WMH volume=4.2cc IQR 1.4-11.2), radiomic features were highly predictive of WMH burden (R2=0.8±0.012). Radiomic signature of WMH included 68 features. All 7 pairs of extracted canonical variates (CV) were statistically significant with respective canonical correlations of 0.79, 0.64, 0.44, 0.21, 0.16, 0.15 (Bonferroni corrected p-values CV1-6 CV7 =.003). Upon examination, CV1 was mainly influenced by age, CV2 by sex, CV3 by history of smoking and diabetes mellitus (DM), CV4 by hypertension, CV5 by atrial fibrillation (AF) and DM, CV6 by coronary artery disease (CAD) and CV7 by CAD and DM. Conclusion: Radiomics extracted from clinical grade FLAIR images of AIS patients seem able to capture structural integrity of the cerebral parenchyma and to correlate with clinical phenotypes. Further research could evaluate radiomics to predict the progression of cerebral small vessel disease on longitudinal data.

Thorough assessment of cerebral dysfunction after acute lesions is paramount to optimize predicting clinical outcomes. We here built random forest classifier-based prediction models of acute motor impairment and recovery post-stroke. Predictions relied on structural and resting-state fMRI data from 54 stroke patients scanned within the first days of symptom onset. Functional connectivity was estimated via static and dynamic approaches. Motor performance was phenotyped in the acute phase and 6 months later. A model based on the time spent in specific dynamic connectivity configurations achieved the best discrimination between patients with and without motor impairments (out-of-sample area under the curve, 95% confidence interval: 0.67 ± 0.01). In contrast, patients with moderate-to-severe impairments could be differentiated from patients with mild deficits using a model based on the variability of dynamic connectivity (0.83 ± 0.01). Here, the variability of the connectivity between ipsilesional sensorimotor cortex and putamen discriminated the most between patients. Finally, motor recovery was best predicted by the time spent in specific connectivity configurations (0.89 ± 0.01) in combination with the initial impairment. Here, better recovery was linked to a shorter time spent in a functionally integrated configuration. Dynamic connectivity-derived parameters constitute potent predictors of acute impairment and recovery, which, in the future, might inform personalized therapy regimens to promote stroke recovery., Bonkhoff et al. report the prediction of acute motor impairments and recovery in the first six months post-stroke based on dynamic connectivity information of 54 acute stroke patients. The time spent in specific connectivity configurations and the variability of dynamic connectivity involving the putamen contributed most to prediction performance., Graphical Abstract Graphical Abstract

IntroductionNeuroimaging measurements of brain structural integrity are thought to be surrogates for brain health, but precise assessments require dedicated advanced image acquisitions. By means of describing the texture of conventional images beyond what meets the naked eye, radiomic analyses hold potential for evaluating brain health. We sought to: 1) evaluate this novel approach to assess brain structural integrity by predicting white matter hyperintensities burdens (WMH) and 2) uncover associations between predictive radiomic features and patients’ clinical phenotypes.MethodsOur analyses were based on a multi-site cohort of 4,163 acute ischemic strokes (AIS) patients with T2-FLAIR MR images and corresponding deep-learning-generated total brain and WMH segmentation. Radiomic features were extracted from normal-appearing brain tissue (brain mask–WMH mask). Radiomics-based prediction of personalized WMH burden was done using ElasticNet linear regression. We built a radiomic signature of WMH with the most stable selected features predictive of WMH burden and then related this signature to clinical variables (age, sex, hypertension (HTN), atrial fibrillation (AF), diabetes mellitus (DM), coronary artery disease (CAD), and history of smoking) using canonical correlation analysis.ResultsRadiomic features were highly predictive of WMH burden (R2=0.855±0.011). Seven pairs of canonical variates (CV) significantly correlated the radiomics signature of WMH and clinical traits with respective canonical correlations of 0.81, 0.65, 0.42, 0.24, 0.20, 0.15, and 0.15 (FDR-corrected p-valuesCV1-6CV7=.012). The clinical CV1 was mainly influenced by age, CV2 by sex, CV3 by history of smoking and DM, CV4 by HTN, CV5 by AF and DM, CV6 by CAD, and CV7 by CAD and DM.ConclusionRadiomics extracted from T2-FLAIR images of AIS patients capture microstructural damage of the cerebral parenchyma and correlate with clinical phenotypes. Further research could evaluate radiomics to predict the progression of WMH.Research in contextEvidence before this studyWe did a systematic review on PubMed until December 1, 2020, for original articles and reviews in which radiomics were used to characterize stroke or cerebrovascular diseases. Radiomic analyses cover a broad ensemble of high-throughput quantification methods applicable to digitalized medical images that extract high-dimensional data by describing a given region of interest by its size, shape, histogram, and relationship between voxels. We used the search terms “radiomics” or “texture analysis”, and “stroke”, “cerebrovascular disease”, “small vessel disease”, or “white matter hyperintensities”. Our research identified 24 studies, 18 studying radiomics of stroke lesions and 6 studying cerebrovascular diseases. All the latter six studies were based on MRI (T1-FLAIR, dynamic contrast-enhanced imaging, T1 & T2-FLAIR, T2-FLAIR post-contrast, T2-FLAIR, and T2-TSE images). Four studies were describing small vessel disease, and two were predicting longitudinal progression of WMH. The average sample size was small with 96 patients included (maximum: 204). One study on 141 patients identified 7 T1-FLAIR radiomic features correlated with cardiovascular risk factors (age and hyperlipidemia) using univariate correlations. All studies were monocentric and performed on a single MRI scanner.Added value of this studyTo date and to the best of our knowledge, this is the largest radiomics study performed on cerebrovascular disease or any topic, and one of the very few to include a great diversity of participating sites with diverse clinical MRI scanners. This study is the first one to establish a radiomic signature of WMH and to interpret its relationship with common cardiovascular risk factors. Our findings add to the body of evidence that damage caused by small vessel disease extend beyond the visible white matter hyperintensities, but the added value resides in the detection of that subvisible damage on routinely acquired T2-FLAIR imaging. It also suggests that cardiovascular phenotypes might manifest in distinct textural patterns detectable on conventional clinical-grade T2-FLAIR images.Implications of all the available evidenceAssessing brain structural integrity has implications for treatment selection, follow-up, prognosis, and recovery prediction in stroke patients but also other neurological disease populations. Measuring cerebral parenchymal structural integrity usually requires advanced imaging such as diffusion tensor imaging or functional MRI. Translation of those neuroimaging biomarkers remains uncommon in clinical practice mainly because of their time-consuming and costly acquisition. Our study provides a potential novel solution to assess brains’ structural integrity applicable to standard, routinely acquired T2-FLAIR imaging.Future research could, for instance, benchmark this radiomics approach against diffusion or functional MRI metrics in the prediction of cognitive or functional outcomes after stroke.

Background and Purpose: Men and women are differently affected by acute ischemic stroke (AIS) in many aspects. Prior studies on sex disparities were limited by moderate sample sizes, varying years of data acquisition, and inconsistent inclusions of covariates leading to controversial findings. We aimed to analyze sex differences in AIS severity, treatments, and early outcome and to systematically evaluate the effect of important covariates in a large German stroke registry. Methods: Analyses were based on the Stroke Registry of Northwestern Germany from 2000 to 2018. We focused on admission-stroke severity and disability, acute recanalization treatment, and early stroke outcomes. Potential sex divergences were investigated via odds ratio (OR) using logistic regression models. Covariates were introduced in 3 steps: (1) base models (age and admission year), (2) partially adjusted models (additionally corrected for acute stroke severity and recanalization treatment), (3) fully adjusted models (additionally adjusted for onset-to-admission time interval, prestroke functional status, comorbidities, and stroke cause). Models were separately fitted for the periods 2000 to 2009 and 2010 to 2018. Results: Data from 761 106 patients with AIS were included. In fully adjusted models, there were no sex differences with respect to treatment with intravenous thrombolysis (2000–2009: OR, 0.99 [95% CI, 0.94–1.03]; 2010–2018: OR, 1.0 [0.98–1.02]), but women were more likely to receive intraarterial therapy (2010–2018: OR, 1.12 [1.08–1.15]). Despite higher disability on admission (2000–2009: OR, 1.10 [1.07–1.13]; 2010–2018: OR, 1.09 [1.07–1.10]), female patients were more likely to be discharged with a favorable functional outcome (2003–2009: OR, 1.05 [1.02–1.09]; 2010–2018: OR, 1.05 [1.04–1.07]) and experienced lower in-hospital mortality (2000–2009: OR, 0.92 [0.86–0.97]; 2010–2018: OR, 0.91 [0.88–0.93]). Conclusions: Female patients with AIS have a higher chance of receiving intraarterial treatment that cannot be explained by clinical characteristics, such as age, premorbid disability, stroke severity, or cause. Women have a more favorable in-hospital recovery than men because their higher disability upon admission was followed by a lower in-hospital mortality and a higher likelihood of favorable functional outcome at discharge after adjustment for covariates.

The aim of the current study was to explore the whole‐brain dynamic functional connectivity patterns in acute ischemic stroke (AIS) patients and their relation to short and long‐term stroke severity. We investigated resting‐state functional MRI‐based dynamic functional connectivity of 41 AIS patients two to five days after symptom onset. Re‐occurring dynamic connectivity configurations were obtained using a sliding window approach and k‐means clustering. We evaluated differences in dynamic patterns between three NIHSS‐stroke severity defined groups (mildly, moderately, and severely affected patients). Furthermore, we built Bayesian hierarchical models to evaluate the predictive capacity of dynamic connectivity and examine the interrelation with clinical measures, such as white matter hyperintensity lesions. Finally, we established correlation analyses between dynamic connectivity and AIS severity as well as 90‐day neurological recovery (ΔNIHSS). We identified three distinct dynamic connectivity configurations acutely post‐stroke. More severely affected patients spent significantly more time in a configuration that was characterized by particularly strong connectivity and isolated processing of functional brain domains (three‐level ANOVA: p, By employing dynamic functional connectivity analyses, Bonkhoff et al. demonstrate that severe acute ischemic stroke is linked to transiently increased isolated information processing in multiple functional domains. Additionally, they show that dynamic connectivity involving default mode network components significantly correlates with recovery in the first three months poststroke.