Thrombus volume in posterior circulation stroke (PCS) has been associated with outcome, through recanalization. Manual thrombus segmentation is impractical for large scale analysis of image... Show moreThrombus volume in posterior circulation stroke (PCS) has been associated with outcome, through recanalization. Manual thrombus segmentation is impractical for large scale analysis of image characteristics. Hence, in this study we develop the first automatic method for thrombus localization and segmentation on CT in patients with PCS. In this multi-center retrospective study, 187 patients with PCS from the MR CLEAN Registry were included. We developed a convolutional neural network (CNN) that segments thrombi and restricts the volume-of-interest (VOI) to the brainstem (Polar-UNet). Furthermore, we reduced false positive localization by removing small-volume objects, referred to as volume-based removal (VBR). Polar-UNet is benchmarked against a CNN that does not restrict the VOI (BL-UNet). Performance metrics included the intra-class correlation coefficient (ICC) between automated and manually segmented thrombus volumes, the thrombus localization precision and recall, and the Dice coefficient. The majority of the thrombi were localized. Without VBR, Polar-UNet achieved a thrombus localization recall of 0.82, versus 0.78 achieved by BL-UNet. This high recall was accompanied by a low precision of 0.14 and 0.09. VBR improved precision to 0.65 and 0.56 for Polar-UNet and BL-UNet, respectively, with a small reduction in recall to 0.75 and 0.69. The Dice coefficient achieved by Polar-UNet was 0.44, versus 0.38 achieved by BL-UNet with VBR. Both methods achieved ICCs of 0.41 (95% CI: 0.27-0.54). Restricting the VOI to the brainstem improved the thrombus localization precision, recall, and segmentation overlap compared to the benchmark. VBR improved thrombus localization precision but lowered recall. Show less
Background and Purpose: The benefit of endovascular treatment (EVT) for posterior circulation stroke (PCS) remains uncertain, and little is known on treatment outcomes in clinical practice. This... Show moreBackground and Purpose: The benefit of endovascular treatment (EVT) for posterior circulation stroke (PCS) remains uncertain, and little is known on treatment outcomes in clinical practice. This study evaluates outcomes of a large PCS cohort treated with EVT in clinical practice. Simultaneous to this observational study, several intervention centers participated in the BASICS trial (Basilar Artery International Cooperation Study), which tested the efficacy of EVT for basilar artery occlusion in a randomized setting. We additionally compared characteristics and outcomes of patients treated outside BASICS in trial centers to those from nontrial centers. Methods: We included patients with PCS from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands Registry: a prospective, multicenter, observational study of patients who underwent EVT in the Netherlands between 2014 and 2018. Primary outcome was a score of 0 to 3 on the modified Rankin Scale at 90 days. Secondary outcomes included reperfusion status and symptomatic intracranial hemorrhage. For outcome comparison between patients treated in trial versus nontrial centers, we used ordinal logistic regression analysis. Results: We included 264 patients of whom 135 (51%) had received intravenous thrombolysis. The basilar artery was most often involved (77%). Favorable outcome (modified Rankin Scale score 0-3) was observed in 115/252 (46%) patients, and 109/252 (43%) patients died. Successful reperfusion was achieved in 178/238 (75%), and symptomatic intracranial hemorrhage occurred in 9/264 (3%). The 154 nontrial patients receiving EVT in BASICS trial centers had similar characteristics and outcomes as the 110 patients treated in nontrial centers (modified Rankin Scale adjusted cOR: 0.77 [95% CI, 0.5-1.2]). Conclusions: Our study shows that high rates of favorable clinical outcome and successful reperfusion can be achieved with EVT for PCS, despite high mortality. Characteristics and outcomes of patients treated in trial versus nontrial centers were similar indicating that our cohort is representative of clinical practice in the Netherlands. Randomized studies using modern treatment approaches are needed for further insight in the benefit of EVT for PCS. Show less
