Search

Residual blood flow distal to an arterial occlusion in patients with acute ischemic stroke (AIS) is associated with favorable patient outcome. Both collateral flow and thrombus permeability may contribute to such residual flow. We propose a method for discriminating between these two mechanisms, based on determining the direction of flow in multiple branches distal to the occluding thrombus using dynamic Computed Tomography Angiography (dynamic CTA). We analyzed dynamic CTA data of 30 AIS patients and present patient-specific cases that identify typical blood flow patterns and velocities. We distinguished patterns with anterograde (N = 10), retrograde (N = 9), and both flow directions (N = 11), with a large variability in velocities for each flow pattern. The observed flow patterns reflect the interplay between permeability and collaterals. The presented method characterizes distal flow and provides a tool to study patient-specific distal tissue perfusion.

Background and Purpose- If a relationship between stroke etiology and thrombus computed tomography characteristics exists, assessing these characteristics in clinical practice could serve as a useful additional diagnostic tool for the identification of stroke subtype. Our purpose was to study the association of stroke etiology and thrombus computed tomography characteristics in patients with acute ischemic stroke due to a large vessel occlusion. Methods- For 1429 consecutive patients enrolled in the MR CLEAN Registry, we determined stroke cause as defined by the TOAST (Trial of ORG 10172 in Acute Stroke Treatment) criteria. The association of stroke etiology with the hyperdense artery sign, clot burden score, and thrombus location was estimated with univariable and multivariable binary and ordinal logistic regression. Additionally, for 367 patients with available thin-section imaging, we assessed the association of stroke etiology with absolute and relative thrombus attenuation, distance from internal carotid artery-terminus to thrombus, thrombus length, and thrombus attenuation increase with univariable and multivariable linear regression. Results- Compared with cardioembolic strokes, noncardioembolic strokes were associated with presence of hyperdense artery sign (odds ratio, 2.2 [95% CI, 1.6-3.0]), lower clot burden score (common odds ratio, 0.4 [95% CI, 0.3-0.6]), shift towards a more proximal thrombus location (common odds ratio, 0.2 [95% CI, 0.2-0.3]), higher absolute thrombus attenuation (β, 3.6 [95% CI, 0.9-6.4]), decrease in distance from the ICA-terminus (β, -5.7 [95% CI, -8.3 to -3.0]), and longer thrombi (β, 8.6 [95% CI, 6.5-10.7]), based on univariable analysis. Thrombus characteristics of strokes with undetermined cause were similar to those of cardioembolic strokes. Conclusions- Thrombus computed tomography characteristics of cardioembolic stroke are distinct from those of noncardioembolic stroke. Additionally, our study supports the general hypothesis that many cryptogenic strokes have a cardioembolic cause. Further research should focus on the use of thrombus computed tomography characteristics as a diagnostic tool for stroke cause in clinical practice.

Treatment selection is becoming increasingly more important in acute ischemic stroke patient care. Clinical variables and radiological image biomarkers (old age, pre-stroke mRS, NIHSS, occlusion location, ASPECTS, among others) have an important role in treatment selection and prognosis. Radiological biomarkers require expert annotation and are subject to inter-observer variability. Recently, Deep Learning has been introduced to reproduce these radiological image biomarkers. Instead of reproducing these biomarkers, in this work, we investigated Deep Learning techniques for building models to directly predict good reperfusion after endovascular treatment (EVT) and good functional outcome using CT angiography images. These models do not require image annotation and are fast to compute. We compare the Deep Learning models to Machine Learning models using traditional radiological image biomarkers. We explored Residual Neural Network (ResNet) architectures, adapted them with Structured Receptive Fields (RFNN) and auto-encoders (AE) for network weight initialization. We further included model visualization techniques to provide insight into the network's decision-making process. We applied the methods on the MR CLEAN Registry dataset with 1301 patients. The Deep Learning models outperformed the models using traditional radiological image biomarkers in three out of four cross-validation folds for functional outcome (average AUC of 0.71) and for all folds for reperfusion (average AUC of 0.65). Model visualization showed that the arteries were relevant features for functional outcome prediction. The best results were obtained for the ResNet models with RFNN. Auto-encoder initialization often improved the results. We concluded that, in our dataset, automated image analysis with Deep Learning methods outperforms radiological image biomarkers for stroke outcome prediction and has the potential to improve treatment selection., (Copyright © 2019. Published by Elsevier Ltd.)