Automated Segmentation of Intracranial Thrombus on NCCT and CTA in Patients with Acute Ischemic Stroke Using a Coarse-to-Fine Deep Learning Model.

BACKGROUND AND PURPOSE: Identifying the presence and extent of intracranial thrombi is crucial in selecting patients with acute ischemic stroke for treatment. This article aims to develop an automated approach to quantify thrombus on NCCT and CTA in patients with stroke. MATERIALS AND METHODS: A total of 499 patients with large-vessel occlusion from the Safety and Efficacy of Nerinetide in Subjects Undergoing Endovascular Thrombectomy for Stroke (ESCAPE-NA1) trial were included. All patients had thin-section NCCT and CTA images. Thrombi contoured manually were used as reference standard. A deep learning approach was developed to segment thrombi automatically. Of 499 patients, 263 and 66 patients were randomly selected to train and validate the deep learning model, respectively; the remaining 170 patients were independently used for testing. The deep learning model was quantitatively compared with the reference standard using the Dice coefficient and volumetric error. The proposed deep learning model was externally tested on 83 patients with and without large-vessel occlusion from another independent trial. RESULTS: The developed deep learning approach obtained a Dice coefficient of 70.7% (interquartile range, 58.0%-77.8%) in the internal cohort. The predicted thrombi length and volume were correlated with those of expert-contoured thrombi (r = 0.88 and 0.87, respectively; P < .001). When the derived deep learning model was applied to the external data set, the model obtained similar results in patients with large-vessel occlusion regarding the Dice coefficient (66.8%; interquartile range, 58.5%-74.6%), thrombus length (r = 0.73), and volume (r = 0.80). The model also obtained a sensitivity of 94.12% (32/34) and a specificity of 97.96% (48/49) in classifying large-vessel occlusion versus non-large-vessel occlusion. CONCLUSIONS: The proposed deep learning method can reliably detect and measure thrombi on NCCT and CTA in patients with acute ischemic stroke.

Proximal Region of Carotid Atherosclerotic Plaque Shows More Intraplaque Hemorrhage: The Plaque at Risk Study.

BACKGROUND AND PURPOSE: Intraplaque hemorrhage contributes to lipid core enlargement and plaque progression, leading to plaque destabilization and stroke. The mechanisms that contribute to the development of intraplaque hemorrhage are not completely understood. A higher incidence of intraplaque hemorrhage and thin/ruptured fibrous cap (upstream of the maximum stenosis in patients with severe [≥70%] carotid stenosis) has been reported. We aimed to noninvasively study the distribution of intraplaque hemorrhage and a thin/ruptured fibrous cap in patients with mild-to-moderate carotid stenosis. MATERIALS AND METHODS: Eighty-eight symptomatic patients with stroke (<70% carotid stenosis included in the Plaque at Risk study) demonstrated intraplaque hemorrhage on MR imaging in the carotid artery plaque ipsilateral to the side of TIA/stroke. The intraplaque hemorrhage area percentage was calculated. A thin/ruptured fibrous cap was scored by comparing pre- and postcontrast black-blood TSE images. Differences in mean intraplaque hemorrhage percentages between the proximal and distal regions were compared using a paired-samples t test. The McNemar test was used to reveal differences in proportions of a thin/ruptured fibrous cap. RESULTS: We found significantly larger areas of intraplaque hemorrhage in the proximal part of the plaque at 2, 4, and 6 mm from the maximal luminal narrowing, respectively: 14.4% versus 9.6% (P = .04), 14.7% versus 5.4% (P < .001), and 11.1% versus 2.2% (P = .001). Additionally, we found an increased proximal prevalence of a thin/ruptured fibrous cap on MR imaging at 2, 4, 6, and 8 mm from the MR imaging section with the maximal luminal narrowing, respectively: 33.7% versus 18.1%, P = .007; 36.1% versus 7.2%, P < .001; 33.7% versus 2.4%, P = .001; and 30.1% versus 3.6%, P = .022. CONCLUSIONS: We demonstrated that intraplaque hemorrhage and a thin/ruptured fibrous cap are more prevalent on the proximal side of the plaque compared with the distal side in patients with mild-to-moderate carotid stenosis.