Deep learning prediction of stroke thrombus red blood cell content from multiparametric MRI.

BACKGROUND AND PURPOSE: Thrombus red blood cell (RBC) content has been shown to be a significant factor influencing the efficacy of acute ischemic stroke treatment. In this study, our objective was to evaluate the ability of convolutional neural networks (CNNs) to predict ischemic stroke thrombus RBC content using multiparametric MR images. MATERIALS AND METHODS: Retrieved stroke thrombi were scanned ex vivo using a three-dimensional multi-echo gradient echo sequence and histologically analyzed. 188 thrombus R2*, quantitative susceptibility mapping and late-echo GRE magnitude image slices were used to train and test a 3-layer CNN through cross-validation. Data augmentation techniques involving input equalization and random image transformation were employed to improve network performance. The network was assessed for its ability to quantitatively predict RBC content and to classify thrombi into RBC-rich and RBC-poor groups. RESULTS: The CNN predicted thrombus RBC content with an accuracy of 62% (95% CI 48-76%) when trained on the original dataset and improved to 72% (95% CI 60-84%) on the augmented dataset. The network classified thrombi as RBC-rich or poor with an accuracy of 71% (95% CI 58-84%) and an area under the curve of 0.72 (95% CI 0.57-0.87) when trained on the original dataset and improved to 80% (95% CI 69-91%) and 0.84 (95% CI 0.73-0.95), respectively, on the augmented dataset. CONCLUSIONS: The CNN was able to accurately predict thrombus RBC content using multiparametric MR images, and could provide a means to guide treatment strategy in acute ischemic stroke.

Acute ischaemic stroke associated with SARS-CoV-2 infection in North America.

BACKGROUND: To analyse the clinical characteristics of COVID-19 with acute ischaemic stroke (AIS) and identify factors predicting functional outcome. METHODS: Multicentre retrospective cohort study of COVID-19 patients with AIS who presented to 30 stroke centres in the USA and Canada between 14 March and 30 August 2020. The primary endpoint was poor functional outcome, defined as a modified Rankin Scale (mRS) of 5 or 6 at discharge. Secondary endpoints include favourable outcome (mRS ≤2) and mortality at discharge, ordinal mRS (shift analysis), symptomatic intracranial haemorrhage (sICH) and occurrence of in-hospital complications. RESULTS: A total of 216 COVID-19 patients with AIS were included. 68.1% (147/216) were older than 60 years, while 31.9% (69/216) were younger. Median [IQR] National Institutes of Health Stroke Scale (NIHSS) at presentation was 12.5 (15.8), and 44.2% (87/197) presented with large vessel occlusion (LVO). Approximately 51.3% (98/191) of the patients had poor outcomes with an observed mortality rate of 39.1% (81/207). Age >60 years (aOR: 5.11, 95% CI 2.08 to 12.56, p<0.001), diabetes mellitus (aOR: 2.66, 95% CI 1.16 to 6.09, p=0.021), higher NIHSS at admission (aOR: 1.08, 95% CI 1.02 to 1.14, p=0.006), LVO (aOR: 2.45, 95% CI 1.04 to 5.78, p=0.042), and higher NLR level (aOR: 1.06, 95% CI 1.01 to 1.11, p=0.028) were significantly associated with poor functional outcome. CONCLUSION: There is relationship between COVID-19-associated AIS and severe disability or death. We identified several factors which predict worse outcomes, and these outcomes were more frequent compared to global averages. We found that elevated neutrophil-to-lymphocyte ratio, rather than D-Dimer, predicted both morbidity and mortality.

Sertraline-induced Hemichorea.

Background: Hemichorea-hemiballism is a syndrome secondary to different etiologies. Drug-induced hemichorea is a rare syndrome related to selective serotonin reuptake inhibitors. To the best of our knowledge, no previous cases of hemichorea associated with sertraline have been reported. Case Report: A 65-year-old female noticed hemichorea 1 week after initiation of sertraline. After extensive investigations, other causes of hemichorea were excluded. Hemichorea remitted after sertraline withdrawal. Discussion: In our patient, temporal association and the negative clinical assessment supported a diagnosis of likely drug-induced involuntary movement. We hypothesized that enhanced serotonergic transmission in the ventral tegmental area or nigrostriatum may be involved in sertraline-induced hemichorea.