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

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.

Benchmark dataset for clot detection in ischemic stroke vessel-based imaging: CODEC-IV.

We present an annotated dataset for the purposes of creating a benchmark in Artificial Intelligence for automated clot detection. While there are commercial tools available for automated clot detection on computed tomographic (CT) angiographs, they have not been compared in a standardized manner whereby accuracy is reported on a publicly available benchmark dataset. Furthermore, there are known difficulties in automated clot detection - namely, cases where there is robust collateral flow, or residual flow and occlusions of the smaller vessels - and it is necessary to drive an initiative to overcome these challenges. Our dataset contains 159 multiphase CTA patient datasets, derived from CTP and annotated by expert stroke neurologists. In addition to images where the clot is marked, the expert neurologists have provided information about clot location, hemisphere and the degree of collateral flow. The data is available on request by researchers via an online form, and we will host a leaderboard where the results of clot detection algorithms on the dataset will be displayed. Participants are invited to submit an algorithm to us for evaluation using the evaluation tool, which is made available at together with the form at https://github.com/MBC-Neuroimaging/ClotDetectEval.