A deep learning analysis of stroke onset time prediction and comparison to DWI-FLAIR mismatch.

INTRODUCTION: When time since stroke onset is unknown, DWI-FLAIR mismatch rating is an established technique for patient stratification. A visible DWI lesion without corresponding parenchymal hyperintensity on FLAIR suggests time since onset of under 4.5 h and thus a potential benefit from intravenous thrombolysis. To improve accuracy and availability of the mismatch concept, deep learning might be able to augment human rating and support decision-making in these cases. METHODS: We used unprocessed DWI and coregistered FLAIR imaging data to train a deep learning model to predict dichotomized time since ischemic stroke onset. We analyzed the performance of Group Convolutional Neural Networks compared to other deep learning methods. Unlabeled imaging data was used for pre-training. Prediction performance of the best deep learning model was compared to the performance of four independent junior and senior raters. Additionally, in cases deemed indeterminable by human raters, model ratings were used to augment human performance. Post-hoc gradient-based explanations were analyzed to gain insights into model predictions. RESULTS: Our best predictive model performed comparably to human raters. Using model ratings in cases deemed indeterminable by human raters improved rating accuracy and interrater agreement for junior and senior ratings. Post-hoc explainability analyses showed that the model localized stroke lesions to derive predictions. DISCUSSION: Our analysis shows that deep learning based clinical decision support has the potential to improve the accessibility of the DWI-FLAIR mismatch concept by supporting patient stratification.

Personalised simulation of hemodynamics in cerebrovascular disease: lessons learned from a study of diagnostic accuracy.

Intracranial atherosclerotic disease (ICAD) poses a significant risk of subsequent stroke but current prevention strategies are limited. Mechanistic simulations of brain hemodynamics offer an alternative precision medicine approach by utilising individual patient characteristics. For clinical use, however, current simulation frameworks have insufficient validation. In this study, we performed the first quantitative validation of a simulation-based precision medicine framework to assess cerebral hemodynamics in patients with ICAD against clinical standard perfusion imaging. In a retrospective analysis, we used a 0-dimensional simulation model to detect brain areas that are hemodynamically vulnerable to subsequent stroke. The main outcome measures were sensitivity, specificity, and area under the receiver operating characteristics curve (ROC AUC) of the simulation to identify brain areas vulnerable to subsequent stroke as defined by quantitative measurements of relative mean transit time (relMTT) from dynamic susceptibility contrast MRI (DSC-MRI). In 68 subjects with unilateral stenosis >70% of the internal carotid artery (ICA) or middle cerebral artery (MCA), the sensitivity and specificity of the simulation were 0.65 and 0.67, respectively. The ROC AUC was 0.68. The low-to-moderate accuracy of the simulation may be attributed to assumptions of Newtonian blood flow, rigid vessel walls, and the use of time-of-flight MRI for geometric representation of subject vasculature. Future simulation approaches should focus on integrating additional patient data, increasing accessibility of precision medicine tools to clinicians, addressing disease burden disparities amongst different populations, and quantifying patient benefit. Our results underscore the need for further improvement of mechanistic simulations of brain hemodynamics to foster the translation of the technology to clinical practice.

Anatomical labeling of intracranial arteries with deep learning in patients with cerebrovascular disease.

Brain arteries are routinely imaged in the clinical setting by various modalities, e.g., time-of-flight magnetic resonance angiography (TOF-MRA). These imaging techniques have great potential for the diagnosis of cerebrovascular disease, disease progression, and response to treatment. Currently, however, only qualitative assessment is implemented in clinical applications, relying on visual inspection. While manual or semi-automated approaches for quantification exist, such solutions are impractical in the clinical setting as they are time-consuming, involve too many processing steps, and/or neglect image intensity information. In this study, we present a deep learning-based solution for the anatomical labeling of intracranial arteries that utilizes complete information from 3D TOF-MRA images. We adapted and trained a state-of-the-art multi-scale Unet architecture using imaging data of 242 patients with cerebrovascular disease to distinguish 24 arterial segments. The proposed model utilizes vessel-specific information as well as raw image intensity information, and can thus take tissue characteristics into account. Our method yielded a performance of 0.89 macro F1 and 0.90 balanced class accuracy (bAcc) in labeling aggregated segments and 0.80 macro F1 and 0.83 bAcc in labeling detailed arterial segments on average. In particular, a higher F1 score than 0.75 for most arteries of clinical interest for cerebrovascular disease was achieved, with higher than 0.90 F1 scores in the larger, main arteries. Due to minimal pre-processing, simple usability, and fast predictions, our method could be highly applicable in the clinical setting.

Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks.

Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data using a Generative Adversarial Network (GAN) with differential privacy guarantees could be a solution to ensure the patient's privacy while maintaining the predictive properties of the data. In this study, we implemented a Wasserstein GAN (WGAN) with and without differential privacy guarantees to generate privacy-preserving labeled Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) image patches for brain vessel segmentation. The synthesized image-label pairs were used to train a U-net which was evaluated in terms of the segmentation performance on real patient images from two different datasets. Additionally, the Fréchet Inception Distance (FID) was calculated between the generated images and the real images to assess their similarity. During the evaluation using the U-Net and the FID, we explored the effect of different levels of privacy which was represented by the parameter ϵ. With stricter privacy guarantees, the segmentation performance and the similarity to the real patient images in terms of FID decreased. Our best segmentation model, trained on synthetic and private data, achieved a Dice Similarity Coefficient (DSC) of 0.75 for ϵ = 7.4 compared to 0.84 for ϵ = ∞ in a brain vessel segmentation paradigm (DSC of 0.69 and 0.88 on the second test set, respectively). We identified a threshold of ϵ <5 for which the performance (DSC <0.61) became unstable and not usable. Our synthesized labeled TOF-MRA images with strict privacy guarantees retained predictive properties necessary for segmenting the brain vessels. Although further research is warranted regarding generalizability to other imaging modalities and performance improvement, our results mark an encouraging first step for privacy-preserving data sharing in medical imaging.

Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks.

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark U-Net trained on real data (DSC 0.901; bAVD 0.294) for intracranial vessels. In conclusion, our solution generates realistic 3D TOF-MRA patches and labels for brain vessel segmentation. We demonstrate the benefit of using mixed precision for computational efficiency resulting in the best-performing GAN-architecture. Our work paves the way towards sharing of labeled 3D medical data which would increase generalizability of deep learning models for clinical use.

Image-to-image generative adversarial networks for synthesizing perfusion parameter maps from DSC-MR images in cerebrovascular disease.

Stroke is a major cause of death or disability. As imaging-based patient stratification improves acute stroke therapy, dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) is of major interest in image brain perfusion. However, expert-level perfusion maps require a manual or semi-manual post-processing by a medical expert making the procedure time-consuming and less-standardized. Modern machine learning methods such as generative adversarial networks (GANs) have the potential to automate the perfusion map generation on an expert level without manual validation. We propose a modified pix2pix GAN with a temporal component (temp-pix2pix-GAN) that generates perfusion maps in an end-to-end fashion. We train our model on perfusion maps infused with expert knowledge to encode it into the GANs. The performance was trained and evaluated using the structural similarity index measure (SSIM) on two datasets including patients with acute stroke and the steno-occlusive disease. Our temp-pix2pix architecture showed high performance on the acute stroke dataset for all perfusion maps (mean SSIM 0.92-0.99) and good performance on data including patients with the steno-occlusive disease (mean SSIM 0.84-0.99). While clinical validation is still necessary for future studies, our results mark an important step toward automated expert-level perfusion maps and thus fast patient stratification.

A precision medicine framework for personalized simulation of hemodynamics in cerebrovascular disease.

BACKGROUND: Cerebrovascular disease, in particular stroke, is a major public health challenge. An important biomarker is cerebral hemodynamics. To measure and quantify cerebral hemodynamics, however, only invasive, potentially harmful or time-to-treatment prolonging methods are available. RESULTS: We present a simulation-based approach which allows calculation of cerebral hemodynamics based on the patient-individual vessel configuration derived from structural vessel imaging. For this, we implemented a framework allowing segmentation and annotation of brain vessels from structural imaging followed by 0-dimensional lumped simulation modeling of cerebral hemodynamics. For annotation, a 3D-graphical user interface was implemented. For 0D-simulation, we used a modified nodal analysis, which was adapted for easy implementation by code. The simulation enables identification of areas vulnerable to stroke and simulation of changes due to different systemic blood pressures. Moreover, sensitivity analysis was implemented allowing the live simulation of changes to simulate procedures and disease progression. Beyond presentation of the framework, we demonstrated in an exploratory analysis in 67 patients that the simulation has a high specificity and low-to-moderate sensitivity to detect perfusion changes in classic perfusion imaging. CONCLUSIONS: The presented precision medicine approach using novel biomarkers has the potential to make the application of harmful and complex perfusion methods obsolete.

Synthesizing anonymized and labeled TOF-MRA patches for brain vessel segmentation using generative adversarial networks.

Anonymization and data sharing are crucial for privacy protection and acquisition of large datasets for medical image analysis. This is a big challenge, especially for neuroimaging. Here, the brain's unique structure allows for re-identification and thus requires non-conventional anonymization. Generative adversarial networks (GANs) have the potential to provide anonymous images while preserving predictive properties. Analyzing brain vessel segmentation, we trained 3 GANs on time-of-flight (TOF) magnetic resonance angiography (MRA) patches for image-label generation: 1) Deep convolutional GAN, 2) Wasserstein-GAN with gradient penalty (WGAN-GP) and 3) WGAN-GP with spectral normalization (WGAN-GP-SN). The generated image-labels from each GAN were used to train a U-net for segmentation and tested on real data. Moreover, we applied our synthetic patches using transfer learning on a second dataset. For an increasing number of up to 15 patients we evaluated the model performance on real data with and without pre-training. The performance for all models was assessed by the Dice Similarity Coefficient (DSC) and the 95th percentile of the Hausdorff Distance (95HD). Comparing the 3 GANs, the U-net trained on synthetic data generated by the WGAN-GP-SN showed the highest performance to predict vessels (DSC/95HD 0.85/30.00) benchmarked by the U-net trained on real data (0.89/26.57). The transfer learning approach showed superior performance for the same GAN compared to no pre-training, especially for one patient only (0.91/24.66 vs. 0.84/27.36). In this work, synthetic image-label pairs retained generalizable information and showed good performance for vessel segmentation. Besides, we showed that synthetic patches can be used in a transfer learning approach with independent data. This paves the way to overcome the challenges of scarce data and anonymization in medical imaging.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease.

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

Association of Surgical Hematoma Evacuation vs Conservative Treatment With Functional Outcome in Patients With Cerebellar Intracerebral Hemorrhage.

Importance: The association of surgical hematoma evacuation with clinical outcomes in patients with cerebellar intracerebral hemorrhage (ICH) has not been established. Objective: To determine the association of surgical hematoma evacuation with clinical outcomes in cerebellar ICH. Design, Setting, and Participants: Individual participant data (IPD) meta-analysis of 4 observational ICH studies incorporating 6580 patients treated at 64 hospitals across the United States and Germany (2006-2015). Exposure: Surgical hematoma evacuation vs conservative treatment. Main Outcomes and Measures: The primary outcome was functional disability evaluated by the modified Rankin Scale ([mRS] score range: 0, no functional deficit to 6, death) at 3 months; favorable (mRS, 0-3) vs unfavorable (mRS, 4-6). Secondary outcomes included survival at 3 months and at 12 months. Analyses included propensity score matching and covariate adjustment, and predicted probabilities were used to identify treatment-related cutoff values for cerebellar ICH. Results: Among 578 patients with cerebellar ICH, propensity score-matched groups included 152 patients with surgical hematoma evacuation vs 152 patients with conservative treatment (age, 68.9 vs 69.2 years; men, 55.9% vs 51.3%; prior anticoagulation, 60.5% vs 63.8%; and median ICH volume, 20.5 cm3 vs 18.8 cm3). After adjustment, surgical hematoma evacuation vs conservative treatment was not significantly associated with likelihood of better functional disability at 3 months (30.9% vs 35.5%; adjusted odds ratio [AOR], 0.94 [95% CI, 0.81 to 1.09], P = .43; adjusted risk difference [ARD], -3.7% [95% CI, -8.7% to 1.2%]) but was significantly associated with greater probability of survival at 3 months (78.3% vs 61.2%; AOR, 1.25 [95% CI, 1.07 to 1.45], P = .005; ARD, 18.5% [95% CI, 13.8% to 23.2%]) and at 12 months (71.7% vs 57.2%; AOR, 1.21 [95% CI, 1.03 to 1.42], P = .02; ARD, 17.0% [95% CI, 11.5% to 22.6%]). A volume range of 12 to 15 cm3 was identified; below this level, surgical hematoma evacuation was associated with lower likelihood of favorable functional outcome (volume ≤12 cm3, 30.6% vs 62.3% [P = .003]; ARD, -34.7% [-38.8% to -30.6%]; P value for interaction, .01), and above, it was associated with greater likelihood of survival (volume ≥15 cm3, 74.5% vs 45.1% [P < .001]; ARD, 28.2% [95% CI, 24.6% to 31.8%]; P value for interaction, .02). Conclusions and Relevance: Among patients with cerebellar ICH, surgical hematoma evacuation, compared with conservative treatment, was not associated with improved functional outcome. Given the null primary outcome, investigation is necessary to establish whether there are differing associations based on hematoma volume.

Characteristics in Non-Vitamin K Antagonist Oral Anticoagulant-Related Intracerebral Hemorrhage.

Background and Purpose- Given inconclusive studies, it is debated whether clinical and imaging characteristics, as well as functional outcome, differ among patients with intracerebral hemorrhage (ICH) related to vitamin K antagonists (VKA) versus non-vitamin K antagonist (NOAC)-related ICH. Notably, clinical characteristics according to different NOAC agents and dosages are not established. Methods- Multicenter observational cohort study integrating individual patient data of 1328 patients with oral anticoagulation-associated ICH, including 190 NOAC-related ICH patients, recruited from 2011 to 2015 at 19 tertiary centers across Germany. Imaging, clinical characteristics, and 3-months modified Rankin Scale (mRS) outcomes were compared in NOAC- versus VKA-related ICH patients. Propensity score matching was conducted to adjust for clinically relevant differences in baseline parameters. Subgroup analyses were performed regarding NOAC agent, dosing and present clinically relevant anticoagulatory activity (last intake <12h/24h or NOAC level >30 ng/mL). Results- Despite older age in NOAC patients, there were no relevant differences in clinical and hematoma characteristics between NOAC- and VKA-related ICH regarding baseline hematoma volume (median [interquartile range]: NOAC, 14.7 [5.1-42.3] mL versus VKA, 16.4 [5.8-40.6] mL; P=0.33), rate of hematoma expansion (NOAC, 49/146 [33.6%] versus VKA, 235/688 [34.2%]; P=0.89), and the proportion of patients with unfavorable outcome at 3 months (mRS, 4-6: NOAC 126/179 [70.4%] versus VKA 473/682 [69.4%]; P=0.79). Subgroup analyses revealed that NOAC patients with clinically relevant anticoagulatory effect had higher rates of intraventricular hemorrhage (n/N [%]: present 52/109 [47.7%] versus absent 9/35 [25.7%]; P=0.022) and hematoma expansion (present 35/90 [38.9%] versus absent 5/30 [16.7%]; P=0.040), whereas type of NOAC agent or different NOAC-dosing regimens did not result in relevant differences in imaging characteristics or outcome. Conclusions- If effectively anticoagulated, there are no differences in hematoma characteristics and functional outcome among patients with NOAC- or VKA-related ICH. Clinical Trial Registration- URL: https://www.clinicaltrials.gov . Unique identifier: NCT03093233.

Heparin for prophylaxis of venous thromboembolism in intracerebral haemorrhage.

OBJECTIVE: To determine the occurrence of intracranial haemorrhagic complications (IHC) on heparin prophylaxis (low-dose subcutaneous heparin, LDSH) in primary spontaneous intracerebral haemorrhage (ICH) (not oral anticoagulation-associated ICH, non-OAC-ICH), vitamin K antagonist (VKA)-associated ICH and non-vitamin K antagonist oral anticoagulant (NOAC)-associated ICH. METHODS: Retrospective cohort study (RETRACE) of 22 participating centres and prospective single-centre study with 1702 patients with VKA-associated or NOAC-associated ICH and 1022 patients with non-OAC-ICH with heparin prophylaxis between 2006 and 2015. Outcomes were defined as rates of IHC during hospital stay among patients with non-OAC-ICH, VKA-ICH and NOAC-ICH, mortality and functional outcome at 3 months between patients with ICH with and without IHC. RESULTS: IHC occurred in 1.7% (42/2416) of patients with ICH. There were no differences in crude incidence rates among patients with VKA-ICH, NOAC-ICH and non-OAC-ICH (log-rank p=0.645; VKA-ICH: 27/1406 (1.9%), NOAC-ICH 1/130 (0.8%), non-OAC-ICH 14/880 (1.6%); p=0.577). Detailed analysis according to treatment exposure (days with and without LDSH) revealed no differences in incidence rates of IHC per 1000 patient-days (LDSH: 1.43 (1.04-1.93) vs non-LDSH: 1.32 (0.33-3.58), conditional maximum likelihood incidence rate ratio: 1.09 (0.38-4.43); p=0.953). Secondary outcomes showed differences in functional outcome (modified Rankin Scale=4-6: IHC: 29/37 (78.4%) vs non-IHC: 1213/2048 (59.2%); p=0.019) and mortality (IHC: 14/37 (37.8%) vs non-IHC: 485/2048 (23.7%); p=0.045) in disfavour of patients with IHC. Small ICH volume (OR: volume <4.4 mL: 0.18 (0.04-0.78); p=0.022) and low National Institutes of Health Stroke Scale (NIHSS) score on admission (OR: NIHSS <4: 0.29 (0.11-0.78); p=0.014) were significantly associated with fewer IHC. CONCLUSIONS: Heparin administration for venous thromboembolism (VTE) prophylaxis in patients with ICH appears to be safe regarding IHC among non-OAC-ICH, VKA-ICH and NOAC-ICH in this observational cohort analysis. Randomised controlled trials are needed to verify the safety and efficacy of heparin compared with other methods for VTE prevention.

A U-Net Deep Learning Framework for High Performance Vessel Segmentation in Patients With Cerebrovascular Disease.

Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are insufficiently validated. A specialized deep learning method-the U-net-is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies.

Diagnostic and prognostic benefit of arterial spin labeling in subacute stroke.

BACKGROUND AND PURPOSE: Brain perfusion measurement in the subacute phase of stroke may support therapeutic decisions. We evaluated whether arterial spin labeling (ASL), a noninvasive perfusion imaging technique based on magnetic resonance imaging (MRI), adds diagnostic and prognostic benefit to diffusion-weighted imaging (DWI) in subacute stroke. METHODS: In a single-center imaging study, patients with DWI lesion(s) in the middle cerebral artery (MCA) territory were included. Onset to imaging time was ≤7 days and imaging included ASL and DWI sequences. Qualitative (standardized visual analysis) and quantitative perfusion analyses (region of interest analysis) were performed. Dichotomized early outcome (modified Rankin Scale [mRS] 0-2 vs. 3-6) was analyzed in two logistic regression models. Model 1 included DWI lesion volume, age, vascular pathology, admission NIHSS, and acute stroke treatment as covariates. Model 2 added the ASL-based perfusion pattern to Model 1. Receiver-operating-characteristic (ROC) and area-under-the-curve (AUC) were calculated for both models to assess their predictive power. The likelihood-ratio-test compared both models. RESULTS: Thirty-eight patients were included (median age 70 years, admission NIHSS 4, onset to imaging time 67 hr, discharge mRS 2). Qualitative perfusion analysis yielded additional diagnostic information in 84% of the patients. In the quantitative analysis, AUC for outcome prediction was 0.88 (95% CI 0.77-0.99) for Model 1 and 0.97 (95% CI 0.91-1.00) for Model 2. Inclusion of perfusion data significantly improved performance and outcome prediction (p = 0.002) of stroke imaging. CONCLUSIONS: In patients with subacute stroke, our study showed that adding perfusion imaging to structural imaging and clinical data significantly improved outcome prediction. This highlights the usefulness of ASL and noninvasive perfusion biomarkers in stroke diagnosis and management.

Outcomes of Hypothermia in Addition to Decompressive Hemicraniectomy in Treatment of Malignant Middle Cerebral Artery Stroke: A Randomized Clinical Trial.

Importance: Moderate hypothermia in addition to early decompressive hemicraniectomy has been suggested to further reduce mortality and improve functional outcome in patients with malignant middle cerebral artery (MCA) stroke. Objective: To investigate whether moderate hypothermia vs standard treatment after early hemicraniectomy reduces mortality at day 14 in patients with malignant MCA stroke. Design, Setting, and Participants: This randomized clinical trial recruited patients from August 2011 through September 2015 at 6 German university hospitals with dedicated neurointensive care units. Of the patients treated with hemicraniectomy and assessed for eligibility, patients were randomly assigned to either standard care or moderate hypothermia. Data analysis was completed from December 2016 to June 2018. Interventions: Moderate hypothermia (temperature, 33.0 ± 1.0°C) was maintained for at least 72 hours immediately after hemicraniectomy. Main Outcomes and Measures: The primary outcome was mortality rate at day 14 compared with the Fisher exact test and expressed as odds ratio (ORs) with 95% CIs. Rates of patients with serious adverse events were estimated for the period of the first 14 days after hemicraniectomy and 12 months of follow-up. Secondary outcome measures included functional outcome at 12 months. Results: Of the 50 study participants, 24 were assigned to standard care and 26 to moderate hypothermia. Twenty-eight were male (56%); the mean (SD) patient age was 51.3 (6.6) years. Recruitment was suspended for safety concerns: 12 of 26 patients (46%) in the hypothermia group and 7 of 24 patients (29%) receiving standard care had at least 1 serious adverse event within 14 days (OR, 2.05 [95% CI, 0.56-8.00]; P = .26); after 12 months, rates of serious adverse events were 80% (n = 20 of 25) in the hypothermia group and 43% (n = 10 of 23) in the standard care group (hazard ratio, 2.54 [95% CI, 1.29-5.00]; P = .005). The mortality rate at day 14 was 19% (5 of 26 patients) in the hypothermia group and 13% (3 of 24 patients) in the group receiving standard care (OR, 1.65 [95% CI, 0.28-12.01]; P = .70). There was no significant difference regarding functional outcome after 12 months of follow-up. Interpretation: In patients with malignant MCA stroke, moderate hypothermia early after hemicraniectomy did not improve mortality and functional outcome compared with standard care, but may cause serious harm in this specific setting. Trial Registration: http://www.drks.de, identifier DRKS00000623.

The choice of embedding media affects image quality, tissue R2* , and susceptibility behaviors in post-mortem brain MR microscopy at 7.0T.

PURPOSE: The quality and precision of post-mortem MRI microscopy may vary depending on the embedding medium used. To investigate this, our study evaluated the impact of 5 widely used media on: (1) image quality, (2) contrast of high spatial resolution gradient-echo (T1 and T2* -weighted) MR images, (3) effective transverse relaxation rate (R2* ), and (4) quantitative susceptibility measurements (QSM) of post-mortem brain specimens. METHODS: Five formaldehyde-fixed brain slices were scanned using 7.0T MRI in: (1) formaldehyde solution (formalin), (2) phosphate-buffered saline (PBS), (3) deuterium oxide (D2 O), (4) perfluoropolyether (Galden), and (5) agarose gel. SNR and contrast-to-noise ratii (SNR/CNR) were calculated for cortex/white matter (WM) and basal ganglia/WM regions. In addition, median R2* and QSM values were extracted from caudate nucleus, putamen, globus pallidus, WM, and cortical regions. RESULTS: PBS, Galden, and agarose returned higher SNR/CNR compared to formalin and D2 O. Formalin fixation, and its use as embedding medium for scanning, increased tissue R2* . Imaging with agarose, D2 O, and Galden returned lower R2* values than PBS (and formalin). No major QSM offsets were observed, although spatial variance was increased (with respect to R2* behaviors) for formalin and agarose. CONCLUSIONS: Embedding media affect gradient-echo image quality, R2* , and QSM in differing ways. In this study, PBS embedding was identified as the most stable experimental setup, although by a small margin. Agarose and Galden were preferred to formalin or D2 O embedding. Formalin significantly increased R2* causing noisier data and increased QSM variance.

Is Perfusion MRI without Deconvolution Reliable for Mismatch Detection in Acute Stroke? Validation with 15O-Positron Emission Tomography.

BACKGROUND: In acute stroke, the magnetic resonance (MR) imaging-based mismatch concept is used to select patients with tissue at risk of infarction for reperfusion therapies. There is however a controversy if non-deconvolved or deconvolved perfusion weighted (PW) parameter maps perform better in tissue at risk prediction and which parameters and thresholds should be used to guide treatment decisions. METHODS: In a group of 22 acute stroke patients with consecutive MR and quantitative positron emission tomography (PET) imaging, non-deconvolved parameters were validated with the gold standard for penumbral-flow (PF) detection 15O-water PET. Performance of PW parameters was assessed by a receiver operating characteristic curve analysis to identify the accuracy of each PWI map to detect the -upper PF threshold as defined by PET cerebral blood flow <20 mL/100 g/min. RESULTS: Among normalized non-deconvolved parameters, PW-first moment without delay correction (FM without DC) > 3.6 s (area under the curve [AUC] = 0.89, interquartile range [IQR] 0.85-0.94), PW-maximum of the concentration curve (Cmax) < 0.66 (AUC = 0.92, IQR 0.84-0.96) and PW-time to peak (TTP) > 4.0 s (AUC = 0.92, IQR 0.87-0.94) perform significantly better than other non-deconvolved parameters to detect the PF threshold as defined by PET. CONCLUSIONS: Non-deconvolved parameters FM without DC, Cmax and TTP are an observer-independent alternative to established deconvolved parameters (e.g., Tmax) to guide treatment decisions in acute stroke.

Boosted Tree Model Reforms Multimodal Magnetic Resonance Imaging Infarct Prediction in Acute Stroke.

BACKGROUND AND PURPOSE: Stroke imaging is pivotal for diagnosis and stratification of patients with acute ischemic stroke to treatment. The potential of combining multimodal information into reliable estimates of outcome learning calls for robust machine learning techniques with high flexibility and accuracy. We applied the novel extreme gradient boosting algorithm for multimodal magnetic resonance imaging-based infarct prediction. METHODS: In a retrospective analysis of 195 patients with acute ischemic stroke, fluid-attenuated inversion recovery, diffusion-weighted imaging, and 10 perfusion parameters were derived from acute magnetic resonance imaging scans. They were integrated to predict final infarct as seen on follow-up T2-fluid-attenuated inversion recovery using the extreme gradient boosting and compared with a standard generalized linear model approach using cross-validation. Submodels for recanalization and persistent occlusion were calculated and were used to identify the important imaging markers. Performance in infarct prediction was analyzed with receiver operating characteristics. Resulting areas under the curve and accuracy rates were compared using Wilcoxon signed-rank test. RESULTS: The extreme gradient boosting model demonstrated significantly higher performance in infarct prediction compared with generalized linear model in both cross-validation approaches: 5-folds (P<10e-16) and leave-one-out (P<0.015). The imaging parameters time-to-peak, mean transit time, time-to-maximum, and diffusion-weighted imaging were indicated as most valuable for infarct prediction by the systematic algorithm rating. Notably, the performance improvement was higher with 5-folds cross-validation approach than leave-one-out. CONCLUSIONS: We demonstrate extreme gradient boosting as a state-of-the-art method for clinically applicable multimodal magnetic resonance imaging infarct prediction in acute ischemic stroke. Our findings emphasize the role of perfusion parameters as important biomarkers for infarct prediction. The effect of cross-validation techniques on performance indicates that the intrapatient variability is expressed in nonlinear dynamics of the imaging modalities.

Management of therapeutic anticoagulation in patients with intracerebral haemorrhage and mechanical heart valves.

Aims: Evidence is lacking regarding acute anticoagulation management in patients after intracerebral haemorrhage (ICH) with implanted mechanical heart valves (MHVs). Our objective was to investigate anticoagulation reversal and resumption strategies by evaluating incidences of haemorrhagic and thromboembolic complications, thereby defining an optimal time-window when to restart therapeutic anticoagulation (TA) in patients with MHV and ICH. Methods and results: We pooled individual patient-data (n = 2504) from a nationwide multicentre cohort-study (RETRACE, conducted at 22 German centres) and eventually identified MHV-patients (n = 137) with anticoagulation-associated ICH for outcome analyses. The primary outcome consisted of major haemorrhagic complications analysed during hospital stay according to treatment exposure (restarted TA vs. no-TA). Secondary outcomes comprised thromboembolic complications, the composite outcome (haemorrhagic and thromboembolic complications), timing of TA, and mortality. Adjusted analyses involved propensity-score matching and multivariable cox-regressions to identify optimal timing of TA. In 66/137 (48%) of patients TA was restarted, being associated with increased haemorrhagic (TA = 17/66 (26%) vs. no-TA = 4/71 (6%); P < 0.01) and a trend to decreased thromboembolic complications (TA = 1/66 (2%) vs. no-TA = 7/71 (10%); P = 0.06). Controlling treatment crossovers provided an incidence rate-ratio [hazard ratio (HR) 10.31, 95% confidence interval (CI) 3.67-35.70; P < 0.01] in disadvantage of TA for haemorrhagic complications. Analyses of TA-timing displayed significant harm until Day 13 after ICH (HR 7.06, 95% CI 2.33-21.37; P < 0.01). The hazard for the composite-balancing both complications, was increased for restarted TA until Day 6 (HR 2.51, 95% CI 1.10-5.70; P = 0.03). Conclusion: Restarting TA within less than 2 weeks after ICH in patients with MHV was associated with increased haemorrhagic complications. Optimal weighing-between least risks for thromboembolic and haemorrhagic complications-provided an earliest starting point of TA at Day 6, reserved only for patients at high thromboembolic risk.