Perfusion parameter map generation from TOF-MRA in stroke using generative adversarial networks.

PURPOSE: To generate perfusion parameter maps from Time-of-flight magnetic resonance angiography (TOF-MRA) images using artificial intelligence to provide an alternative to traditional perfusion imaging techniques. MATERIALS AND METHODS: This retrospective study included a total of 272 patients with cerebrovascular diseases; 200 with acute stroke (from 2010 to 2018), and 72 with steno-occlusive disease (from 2011 to 2014). For each patient the TOF MRA image and the corresponding Dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) were retrieved from the datasets. The authors propose an adapted generative adversarial network (GAN) architecture, 3D pix2pix GAN, that generates common perfusion maps (CBF, CBV, MTT, TTP, Tmax) from TOF-MRA images. The performance was evaluated by the structural similarity index measure (SSIM). For a subset of 20 patients from the acute stroke dataset, the Dice coefficient was calculated to measure the overlap between the generated and real hypoperfused lesions with a time-to-maximum (Tmax) > 6 s. RESULTS: The GAN model exhibited high visual overlap and performance for all perfusion maps in both datasets: acute stroke (mean SSIM 0.88-0.92, mean PSNR 28.48-30.89, mean MAE 0.02-0.04 and mean NRMSE 0.14-0.37) and steno-occlusive disease patients (mean SSIM 0.83-0.98, mean PSNR 23.62-38.21, mean MAE 0.01-0.05 and mean NRMSE 0.03-0.15). For the overlap analysis for lesions with Tmax>6 s, the median Dice coefficient was 0.49. CONCLUSION: Our AI model can successfully generate perfusion parameter maps from TOF-MRA images, paving the way for a non-invasive alternative for assessing cerebral hemodynamics in cerebrovascular disease patients. This method could impact the stratification of patients with cerebrovascular diseases. Our results warrant more extensive refinement and validation of the method.

Ongoing Challenges in the Diagnosis of Myelin Oligodendrocyte Glycoprotein Antibody-Associated Disease.

This cross-sectional study examines whether proposed myelin oligodendrocyte glycoprotein antibody­associated disease (MOGAD) diagnostic criteria can exclude other diseases, such as multiple sclerosis, and rely on results of cell-based assays.

Clinical outcome and outcome prediction of octogenarians with acute basilar artery occlusion and endovascular stroke treatment compared to younger patients.

Background and aims: Octogenarians are underrepresented in recently published studies that showed the benefit of endovascular stroke treatment (EST) for patients with acute basilar artery occlusion (BAO). We aimed to compare the clinical outcome of octogenarians with BAO and EST compared to younger patients (YPs) and identify independent outcome predictors. Methods: This is a retrospective, single-center analysis of patients treated for BAO with EST from January 2013 until June 2021 in a tertiary stroke center. Octogenarians (80-89 years) were compared to YPs. A study endpoint was a favorable clinical outcome as per the modified Rankin Scale (mRS 0-3), 90 days after stroke onset. The study groups were compared using univariate analysis, and a multivariable logistic regression analysis was performed to define independent predictors for favorable and unfavorable (mRS 5-6) clinical outcomes. Results: In this study cohort, 74/191 (38.7%) octogenarians had a higher pre-stroke mRS [median, interquartile range (IQR): 2, 1-3 octogenarians vs. 0, 0-1 YP, p < 0.001] and a comparable National Institutes of Health Stroke Scale (NIHSS) before EST (median, IQR: 21, 10-38 vs. 20, 8-35 in YP, p = 0.487). They showed a comparable rate of favorable outcome (mRS 0-3, 90 days, 23.0 vs. 25.6% in YP, p = 0.725), but were less often functionally independent (mRS 0-2: 10.8% in octogenarians vs. 23.0% in YP, p = 0.049). The rate of unfavorable clinical outcome was comparable (mRS 5-6, n = 40, 54.1% in octogenarians vs. n = 64, 54.7% in YP, p = 0.831). A baseline NIHSS was an independent predictor for clinical outcome in YPs [e.g., for unfavorable clinical outcome: odds ratio (OR) 1.061, confidence interval (CI) 1.027-1.098, p = 0.005] and for favorable clinical outcome in octogenarians. Pre-stroke mRS predicted favorable outcomes in octogenarians (OR 0.54, CI 0.30-0.90, p = 0.0291), while age predicted unfavorable outcomes in YPs (OR 1.045, CI 1.011-1.086, p = 0.0137). Conclusion: Octogenarians with acute BAO eligible for EST are as likely to achieve a favorable outcome as YPs, and the rate of death or severe disability is comparable. The admission NIHSS is an independent predictor for favorable and unfavorable outcomes in YP and for favorable outcomes in octogenarians. In this study cohort, pre-stroke mRS predicted favorable outcomes in octogenarians while age predicted an unfavorable outcome in YPs.

What is the impact of head movement on automated CT perfusion mismatch evaluation in acute ischemic stroke?

OBJECTIVES: Automated CT perfusion mismatch assessment is an established treatment decision tool in acute ischemic stroke. However, the reliability of this method in patients with head motion is unclear. We therefore sought to evaluate the influence of head movement on automated CT perfusion mismatch evaluation. METHODS: Using a realistic CT brain-perfusion-phantom, 7 perfusion mismatch scenarios were simulated within the left middle cerebral artery territory. Real CT noise and artificial head movement were added. Thereafter, ischemic core, penumbra volumes and mismatch ratios were evaluated using an automated mismatch analysis software (RAPID, iSchemaView) and compared with ground truth simulated values. RESULTS: While CT scanner noise alone had only a minor impact on mismatch evaluation, a tendency towards smaller infarct core estimates (mean difference of -5.3 (-14 to 3.5) mL for subtle head movement and -7.0 (-14.7 to 0.7) mL for strong head movement), larger penumbral estimates (+9.9 (-25 to 44) mL and +35 (-14 to 85) mL, respectively) and consequently larger mismatch ratios (+0.8 (-1.5 to 3.0) for subtle head movement and +1.9 (-1.3 to 5.1) for strong head movement) were noted in dependence of patient head movement. CONCLUSIONS: Motion during CT perfusion acquisition influences automated mismatch evaluation. Potentially treatment-relevant changes in mismatch classifications in dependence of head movement were observed and occurred in favor of mechanical thrombectomy.