Automated occlusion detection for the diagnosis of acute ischemic stroke: A detailed performance review

Abstract

Introduction: Stroke is a leading cause of adult disability and death worldwide. Automated detection of stroke on brain imaging has promise in a time critical environment. We present a method for the automated detection of intracranial occlusions on dynamic CT Angiography (CTA) causing acute ischemic stroke. Methods: We derived dynamic CTA images from CT Perfusion (CTP) data and utilised advanced image processing to enhance and display major cerebral blood vessels for symmetry analysis. We reviewed the performance of the algorithm on a cohort of 207 patients from the International Stroke Perfusion Imaging Registry (INSPIRE), with Large Vessel Occlusion (LVO) and non-LVO strokes. Included in the data were images with chronic stroke, various artefacts, incomplete vessel occlusions, and images of poorer quality. All images were annotated by stroke experts. In addition, each image was graded in terms of the difficulty of the task of occlusion detection. Performance was evaluated on the overall cohort, and with respect to occlusion location, collateral grade, and task difficulty. We also evaluated the impact of including additional perfusion data. Results: Images with a rating of lower difficulty achieved a sensitivity and specificity of 96% and 90%, respectively, while images with a moderate difficulty rating achieved 88% and 50%, respectively. For cases of high difficulty, where more than two experts or additional data were required to reach consensus, sensitivity and specificity was 53% and 11%. The addition of perfusion data to the dCTA images increased the specificity by 38%. Conclusion: We have provided an unbiased interpretation of algorithm performance. Further developments include generalising to conventional CTA and employing the algorithm in a clinical setting for prospective studies. ? 2023