Anti-rheumatic colchicine phytochemical exhibits potent antiviral activities against avian and seasonal Influenza A viruses (IAVs) via targeting different stages of IAV replication cycle.

BACKGROUND: The continuous evolution of drug-resistant influenza viruses highlights the necessity for repurposing naturally-derived and safe phytochemicals with anti-influenza activity as novel broad-spectrum anti-influenza medications. METHODS: In this study, nitrogenous alkaloids were tested for their viral inhibitory activity against influenza A/H1N1 and A/H5N1 viruses. The cytotoxicity of tested alkaloids on MDCK showed a high safety range (CC50 > 200 µg/ml), permitting the screening for their anti-influenza potential. RESULTS: Herein, atropine sulphate, pilocarpine hydrochloride and colchicine displayed anti-H5N1 activities with IC50 values of 2.300, 0.210 and 0.111 µg/ml, respectively. Validation of the IC50 values was further depicted by testing the three highly effective alkaloids, based on their potent IC50 values against seasonal influenza A/H1N1 virus, showing comparable IC50 values of 0.204, 0.637 and 0.326 µg/ml, respectively. Further investigation suggests that colchicine could suppress viral infection by primarily interfering with IAV replication and inhibiting viral adsorption, while atropine sulphate and pilocarpine hydrochloride could directly affect the virus in a cell-free virucidal effect. Interestingly, the in silico molecular docking studies suggest the abilities of atropine, pilocarpine, and colchicine to bind correctly inside the active sites of the neuraminidases of both influenza A/H1N1 and A/H5N1 viruses. The three alkaloids exhibited good binding energies as well as excellent binding modes that were similar to the co-crystallized ligands. On the other hand, consistent with in vitro results, only colchicine could bind correctly against the M2-proton channel of influenza A viruses (IAVs). This might explicate the in vitro antiviral activity of colchicine at the replication stage of the virus replication cycle. CONCLUSION: This study highlighted the anti-influenza efficacy of biologically active alkaloids including colchicine. Therefore, these alkaloids should be further characterized in vivo (preclinical and clinical studies) to be developed as anti-IAV agents.

Vaccination and Antiviral Treatment against Avian Influenza H5Nx Viruses: A Harbinger of Virus Control or Evolution.

Despite the panzootic nature of emergent highly pathogenic avian influenza H5Nx viruses in wild migratory birds and domestic poultry, only a limited number of human infections with H5Nx viruses have been identified since its emergence in 1996. Few countries with endemic avian influenza viruses (AIVs) have implemented vaccination as a control strategy, while most of the countries have adopted a culling strategy for the infected flocks. To date, China and Egypt are the two major sites where vaccination has been adopted to control avian influenza H5Nx infections, especially with the widespread circulation of clade 2.3.4.4b H5N1 viruses. This virus is currently circulating among birds and poultry, with occasional spillovers to mammals, including humans. Herein, we will discuss the history of AIVs in Egypt as one of the hotspots for infections and the improper implementation of prophylactic and therapeutic control strategies, leading to continuous flock outbreaks with remarkable virus evolution scenarios. Along with current pre-pandemic preparedness efforts, comprehensive surveillance of H5Nx viruses in wild birds, domestic poultry, and mammals, including humans, in endemic areas is critical to explore the public health risk of the newly emerging immune-evasive or drug-resistant H5Nx variants.

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.

Immunogenicity and Cross-Protective Efficacy Induced by an Inactivated Recombinant Avian Influenza A/H5N1 (Clade 2.3.4.4b) Vaccine against Co-Circulating Influenza A/H5Nx Viruses.

Controlling avian influenza viruses (AIVs) is mainly based on culling of the infected bird flocks or via the implementation of inactivated vaccines in countries where AIVs are considered to be endemic. Over the last decade, several avian influenza virus subtypes, including highly pathogenic avian influenza (HPAI) H5N1 clade 2.2.1.2, H5N8 clade 2.3.4.4b and the recent H5N1 clade 2.3.4.4b, have been reported among poultry populations in Egypt. This demanded the utilization of a nationwide routine vaccination program in the poultry sector. Antigenic differences between available avian influenza vaccines and the currently circulating H5Nx strains were reported, calling for an updated vaccine for homogenous strains. In this study, three H5Nx vaccines were generated by utilizing the reverse genetic system: rgH5N1_2.3.4.4, rgH5N8_2.3.4.4 and rgH5N1_2.2.1.2. Further, the immunogenicity and the cross-reactivity of the generated inactivated vaccines were assessed in the chicken model against a panel of homologous and heterologous H5Nx HPAIVs. Interestingly, the rgH5N1_2.3.4.4 induced high immunogenicity in specific-pathogen-free (SPF) chicken and could efficiently protect immunized chickens against challenge infection with HPAIV H5N1_2.3.4.4, H5N8_2.3.4.4 and H5N1_2.2.1.2. In parallel, the rgH5N1_2.2.1.2 could partially protect SPF chickens against infection with HPAIV H5N1_2.3.4.4 and H5N8_2.3.4.4. Conversely, the raised antibodies to rgH5N1_2.3.4.4 could provide full protection against HPAIV H5N1_2.3.4.4 and HPAIV H5N8_2.3.4.4, and partial protection (60%) against HPAIV H5N1_2.2.1.2. Compared to rgH5N8_2.3.4.4 and rgH5N1_2.2.1.2 vaccines, chickens vaccinated with rgH5N1_2.3.4.4 showed lower viral shedding following challenge infection with the predefined HPAIVs. These data emphasize the superior immunogenicity and cross-protective efficacy of the rgH5N1_2.3.4.4 in comparison to rgH5N8_2.3.4.4 and rgH5N1_2.2.1.2.

Reproducibility of cerebral perfusion measurements using BOLD delay.

BOLD delay is an emerging, noninvasive method for assessing cerebral perfusion that does not require the use of intravenous contrast agents and is thus particularly suited for longitudinal monitoring. In this study, we assess the reproducibility of BOLD delay using data from 136 subjects with normal cerebral perfusion scanned on two separate occasions with scanners, sequence parameters, and intervals between scans varying between subjects. The effects of various factors on the reproducibility of BOLD delay, defined here as the differences in BOLD delay values between the scanning sessions, were investigated using a linear mixed model. Reproducibility was additionally assessed using the intraclass correlation coefficient of BOLD delay between sessions. Reproducibility was highest in the posterior cerebral artery territory. The mean BOLD delay test-retest difference after accounting for the aforementioned factors was 1.2 s (95% CI = 1.0 to 1.4 s). Overall, BOLD delay shows good reproducibility, but care should be taken when interpreting longitudinal BOLD delay changes that are either very small or are located in certain brain regions.

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.

Differentiation of Cerebral Neoplasms with Vessel Size Imaging (VSI).

PURPOSE: Cerebral neoplasms of various histological origins may show comparable appearances on conventional Magnetic Resonance Imaging (MRI). Vessel size imaging (VSI) is an MRI technique that enables noninvasive assessment of microvasculature by providing quantitative estimates of microvessel size and density. In this study, we evaluated the potential of VSI to differentiate between brain tumor types based on their microvascular morphology. METHODS: Using a clinical 3T MRI scanner, VSI was performed on 25 patients with cerebral neoplasms, 10 with glioblastoma multiforme (GBM), 8 with primary CNS lymphoma (PCNSL) and 7 with cerebral lung cancer metastasis (MLC). Following the postprocessing of VSI maps, mean vessel diameter (vessel size index, vsi) and microvessel density (Q) were compared across tumors, peritumoral areas, and healthy tissues. RESULTS: The MLC tumors have larger and less dense microvasculature compared to PCNSLs in terms of vsi and Q (p = 0.0004 and p < 0.0001, respectively). GBM tumors have higher yet non-significantly different vsi values than PCNSLs (p = 0.065) and non-significant differences in Q. No statistically significant differences in vsi or Q were present between GBMs and MLCs. GBM tumor volume was positively correlated with vsi (r = 0.502, p = 0.0017) and negatively correlated with Q (r = -0.531, p = 0.0007). CONCLUSION: Conventional MRI parameters are helpful in differentiating between PCNSLs, GBMs, and MLCs. Additionally incorporating VSI parameters into the diagnostic protocol could help in further differentiating between PCNSLs and metastases and potentially between PCNSLs and GBMs. Future studies in larger patient cohorts are required to establish diagnostic cut-off values for VSI.

An evaluation of performance measures for arterial brain vessel segmentation.

BACKGROUND: Arterial brain vessel segmentation allows utilising clinically relevant information contained within the cerebral vascular tree. Currently, however, no standardised performance measure is available to evaluate the quality of cerebral vessel segmentations. Thus, we developed a performance measure selection framework based on manual visual scoring of simulated segmentation variations to find the most suitable measure for cerebral vessel segmentation. METHODS: To simulate segmentation variations, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation. In 10 patients, we generated a set of approximately 300 simulated segmentation variations for each ground truth image. Each segmentation was visually scored based on a predefined scoring system and segmentations were ranked based on 22 performance measures common in the literature. The correlation of visual scores with performance measure rankings was calculated using the Spearman correlation coefficient. RESULTS: The distance-based performance measures balanced average Hausdorff distance (rank = 1) and average Hausdorff distance (rank = 2) provided the segmentation rankings with the highest average correlation with manual rankings. They were followed by overlap-based measures such as Dice coefficient (rank = 7), a standard performance measure in medical image segmentation. CONCLUSIONS: Average Hausdorff distance-based measures should be used as a standard performance measure in evaluating cerebral vessel segmentation quality. They can identify more relevant segmentation errors, especially in high-quality segmentations. Our findings have the potential to accelerate the validation and development of novel vessel segmentation approaches.

A novel approach for assessing hypoperfusion in stroke using spatial independent component analysis of resting-state fMRI.

Individualized treatment of acute stroke depends on the timely detection of ischemia and potentially salvageable tissue in the brain. Using functional MRI (fMRI), it is possible to characterize cerebral blood flow from blood-oxygen-level-dependent (BOLD) signals without the administration of exogenous contrast agents. In this study, we applied spatial independent component analysis to resting-state fMRI data of 37 stroke patients scanned within 24 hr of symptom onset, 17 of whom received follow-up scans the next day. Our analysis revealed "Hypoperfusion spatially-Independent Components" (HICs) whose spatial patterns of BOLD signal resembled regions of delayed perfusion depicted by dynamic susceptibility contrast MRI. These HICs were detected even in the presence of excessive patient motion, and disappeared following successful tissue reperfusion. The unique spatial and temporal features of HICs allowed them to be distinguished with high accuracy from other components in a user-independent manner (area under the curve = 0.93, balanced accuracy = 0.90, sensitivity = 1.00, and specificity = 0.85). Our study therefore presents a new, noninvasive method for assessing blood flow in acute stroke that minimizes interpretative subjectivity and is robust to severe patient motion.

Magnetic resonance imaging-based changes in vascular morphology and cerebral perfusion in subacute ischemic stroke.

MRI-based vessel size imaging (VSI) allows for in-vivo assessment of cerebral microvasculature and perfusion. This exploratory analysis of vessel size (VS) and density (Q; both assessed via VSI) in the subacute phase of ischemic stroke involved sixty-two patients from the BAPTISe cohort ('Biomarkers And Perfusion--Training-Induced changes after Stroke') nested within a randomized controlled trial (intervention: 4-week training vs. relaxation). Relative VS, Q, cerebral blood volume (rCBV) and -flow (rCBF) were calculated for: ischemic lesion, perilesional tissue, and region corresponding to ischemic lesion on the contralateral side (mirrored lesion). Linear mixed-models detected significantly increased rVS and decreased rQ within the ischemic lesion compared to the mirrored lesion (coefficient[standard error]: 0.2[0.08] p = 0.03 and -1.0[0.3] p = 0.02, respectively); lesion rCBF and rCBV were also significantly reduced. Mixed-models did not identify time-to-MRI, nor training as modifying factors in terms of rVS or rQ up to two months post-stroke. Larger lesion VS was associated with larger lesion volumes (ß 34, 95%CI 6.2-62; p = 0.02) and higher baseline NIHSS (ß 3.0, 95%CI 0.49-5.3;p = 0.02), but was not predictive of six-month outcome. In summary, VSI can assess the cerebral microvasculature and tissue perfusion in the subacute phases of ischemic stroke, and may carry relevant prognostic value in terms of lesion volume and stroke severity.

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.

On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking.

Average Hausdorff distance is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, it is used to compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average Hausdorff distance making it less suitable for applications in segmentation performance assessment. To mitigate this error, we present a modified calculation of this performance measure that we have coined "balanced average Hausdorff distance". To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using both performance measures. We calculated the Kendall rank correlation coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by balanced average Hausdorff distance had a significantly higher median correlation (1.00) than those by average Hausdorff distance (0.89). In 200 total rankings, the former misranked 52 whilst the latter misranked 179 segmentations. Balanced average Hausdorff distance is more suitable for rankings and quality assessment of segmentations than average Hausdorff distance.

The Effect of Scan Length on the Assessment of BOLD Delay in Ischemic Stroke.

Objectives: To evaluate the impact of resting-state functional MRI scan length on the diagnostic accuracy, image quality and lesion volume estimation of BOLD delay maps used for brain perfusion assessment in acute ischemic stroke. Methods: Sixty-three acute ischemic stroke patients received a 340 s resting-state functional MRI within 24 h of stroke symptom onset. BOLD delay maps were calculated from the full scan and four shortened versions (68 s, 136 s, 204 s, 272 s). The BOLD delay lesions on these maps were compared in terms of spatial overlap and volumetric agreement with the lesions derived from the full scans and with time-to-maximum (Tmax) lesions derived from DSC-MRI in a subset of patients (n = 10). In addition, the interpretability and quality of these maps were compared across different scan lengths using mixed models. Results: Shortened BOLD delay scans showed a small volumetric bias (ranging from 0.05 to 5.3 mL; between a 0.13% volumetric underestimation and a 7.7% overestimation relative to the mean of the volumes, depending on scan length) compared to the full scan. Decreased scan length was associated with decreased spatial overlap with both the BOLD delay lesions derived from the full scans and with Tmax lesions. Only the two shortest scan lengths (68 and 136 s) were associated with substantially decreased interpretability, decreased structure clarity, and increased noisiness of BOLD delay maps. Conclusions: BOLD delay maps derived from resting-state fMRI scans lasting 272 and 204 s provide sufficient diagnostic quality and adequate assessment of perfusion lesion volumes. Such shortened scans may be helpful in situations where quick clinical decisions need to be made.

Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome.

State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features' importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.

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.

Elevated brain oxygen extraction fraction measured by MRI susceptibility relates to perfusion status in acute ischemic stroke.

Recent clinical trials of new revascularization therapies in acute ischemic stroke have highlighted the importance of physiological imaging to identify optimal treatments for patients. Oxygen extraction fraction (OEF) is a hallmark of at-risk tissue in stroke, and can be quantified from the susceptibility effect of deoxyhemoglobin molecules in venous blood on MRI phase scans. We measured OEF within cerebral veins using advanced quantitative susceptibility mapping (QSM) MRI reconstructions in 20 acute stroke patients. Absolute OEF was elevated in the affected (29.3 ± 3.4%) versus the contralateral hemisphere (25.5 ± 3.1%) of patients with large diffusion-perfusion lesion mismatch (P = 0.032). In these patients, OEF negatively correlated with relative CBF measured by dynamic susceptibility contrast MRI (P = 0.004), suggesting compensation for reduced flow. Patients with perfusion-diffusion match or no hypo-perfusion showed less OEF difference between hemispheres. Nine patients received longitudinal assessment and showed OEF ratio (affected to contralateral) of 1.2 ± 0.1 at baseline that normalized (decreased) to 1.0 ± 0.1 at follow-up three days later (P = 0.03). Our feasibility study demonstrates that QSM MRI can non-invasively quantify OEF in stroke patients, relates to perfusion status, and is sensitive to OEF changes over time. Clinical trial registration: Longitudinal MRI examinations of patients with brain ischemia and blood brain barrier permeability; clinicaltrials.org :NCT02077582.

Non-invasive monitoring of longitudinal changes in cerebral hemodynamics in acute ischemic stroke using BOLD signal delay.

Relative delays in blood-oxygen-level-dependent (BOLD) signal oscillations can be used to assess cerebral perfusion without using contrast agents. However, little is currently known about the utility of this method in detecting clinically relevant perfusion changes over time. We investigated the relationship between longitudinal BOLD delay changes, vessel recanalization, and reperfusion in 15 acute stroke patients with vessel occlusion examined within 24 h of symptom onset (D0) and one day later (D1). We created BOLD delay maps using time shift analysis of resting-state functional MRI data and quantified perfusion lesion volume changes (using the D1/D0 volume ratio) and severity changes (using a linear mixed model) over time. Between baseline and follow-up, BOLD delay lesions shrank (median D1/D0 ratio = 0.2, IQR = 0.03-0.7) and BOLD delay severity decreased (b = -4.4 s) in patients with recanalization, whereas they grew (median D1/D0 ratio = 1.47, IQR = 1.1-1.7) and became more severe (b = 4.3 s) in patients with persistent vessel occlusion. Clinically relevant changes in cerebral perfusion in early stroke can be detected using BOLD delay, making this non-invasive method a promising option for detecting tissue at risk of infarction and monitoring stroke patients following recanalization therapy.