Search

Aneurysm size correlates with rupture risk and is important for treatment planning. User annotation of aneurysm size is slow and tedious, particularly for large data sets. Geometric shortcuts to compute size have been shown to be inaccurate, particularly for nonstandard aneurysm geometries. To develop and train a convolutional neural network (CNN) to detect and measure cerebral aneurysms from magnetic resonance angiography (MRA) automatically and without geometric shortcuts. In step 1, a CNN based on the U-net architecture was trained on 250 MRA maximum intensity projection (MIP) images, then applied to a testing set. In step 2, the trained CNN was applied to a separate set of 14 basilar tip aneurysms for size prediction. Step 1-the CNN successfully identified aneurysms in 85/86 (98.8% of) testing set cases, with a receiver operating characteristic (ROC) area-under-the-curve of 0.87. Step 2-automated basilar tip aneurysm linear size differed from radiologist-traced aneurysm size on average by 2.01 mm, or 30%. The CNN aneurysm area differed from radiologist-derived area on average by 8.1 mm2 or 27%. CNN correctly predicted the area trend for the set of aneurysms. This approach is to our knowledge the first using CNNs to derive aneurysm size. In particular, we demonstrate the clinically pertinent application of computing maximal aneurysm one-dimensional size and two-dimensional area. We propose that future work can apply this to facilitate pre-treatment planning and possibly identify previously missed aneurysms in retrospective assessment.

Background and Purpose- The WEAVE trial (Wingspan Stent System Post Market Surveillance) is a postmarket surveillance trial mandated by the Food and Drug Administration to assess the periprocedural safety of the Wingspan Stent system in the treatment of symptomatic intracranial atherosclerotic disease. Methods- A total of 152 consecutive patients who met the Food and Drug Administration on-label usage criteria were enrolled at 24 hospitals and underwent angioplasty and stenting with the Wingspan stent. On-label criteria included age 22 to 80 years, symptomatic intracranial atherosclerotic stenosis of 70% to 99%, baseline modified Rankin Scale score ≤3, ≥2 strokes in the vascular territory of the stenotic lesion with at least 1 stroke while on medical therapy, and stenting of the lesion ≥8 days after the last stroke. The primary analysis assessed the periprocedural stroke, bleed, and death rate within 72 hours of the procedure with adjudication by a core study Stroke Neurologist. Results- The trial was stopped early after interim analysis of 152 consecutive patients demonstrated a lower than expected 2.6% (4/152 patients) periprocedural stroke, bleed, and death rate. This was lower than the 4% periprocedural primary event safety benchmark set for the interim analysis in the study. A total of 97.4% (148/152) patients were event-free at 72 hours, 1.3% (2/152) had nonfatal strokes, and 1.3% (2/152) of patients died. Conclusions- With experienced interventionalists, and proper patient selection following the on-label usage guidelines, the use of the Wingspan stent for intracranial atherosclerotic disease demonstrated a low periprocedural complication rate and excellent safety profile. This is the largest on-label, multicenter, prospective trial of the Wingspan stent system to date with the lowest reported complication rate. Clinical Trial Registration- URL: https://www.clinicaltrials.gov . Unique identifier: NCT02034058.

Background and purposePatients with acute ischemic stroke are at increased risk of developing parenchymal hemorrhage (PH), particularly in the setting of reperfusion therapies. We have developed a predictive model to examine the risk of PH using combined magnetic resonance perfusion and diffusion parameters, including cerebral blood volume (CBV), apparent diffusion coefficient, and microvascular permeability (K2).MethodsVoxel-based values of CBV, K2, and apparent diffusion coefficient from the ischemic core were obtained using pretreatment magnetic resonance imaging data from patients enrolled in the MR RESCUE clinical trial (Mechanical Retrieval and Recanalization of Stroke Clots Using Embolectomy). The associations between PH and extreme values of imaging parameters were assessed in univariate and multivariate analyses. Receiver-operating characteristic curve analysis was performed to determine the optimal parameter(s) and threshold for predicting PH.ResultsIn 83 patients included in this analysis, 20 developed PH. Univariate analysis showed significantly lower 10th percentile CBV and 10th percentile apparent diffusion coefficient values and significantly higher 90th percentile K2 values within the infarction core of patients with PH. Using classification tree analysis, the 10th percentile CBV at threshold of 0.47 and 90th percentile K2 at threshold of 0.28 resulted in overall predictive accuracy of 88.7%, sensitivity of 90.0%, and specificity of 87.3%, which was superior to any individual or combination of other classifiers.ConclusionsOur results suggest that combined 10th percentile CBV and 90th percentile K2 is an independent predictor of PH in patients with acute ischemic stroke with diagnostic accuracy superior to individual classifiers alone. This approach may allow risk stratification for patients undergoing reperfusion therapies.Clinical trial registrationURL: https://www.clinicaltrials.gov. Unique identifier: NCT00389467.

Background and purposeAtherosclerotic vertebrobasilar disease is an important cause of posterior circulation stroke. To examine the role of hemodynamic compromise, a prospective multicenter study, Vertebrobasilar Flow Evaluation and Risk of Transient Ischemic Attack and Stroke (VERiTAS), was conducted. Here, we report clinical features and vessel flow measurements from the study cohort.MethodsPatients with recent vertebrobasilar transient ischemic attack or stroke and ≥50% atherosclerotic stenosis or occlusion in vertebral or basilar arteries (BA) were enrolled. Large-vessel flow in the vertebrobasilar territory was assessed using quantitative MRA.ResultsThe cohort (n=72; 44% women) had a mean age of 65.6 years; 72% presented with ischemic stroke. Hypertension (93%) and hyperlipidemia (81%) were the most prevalent vascular risk factors. BA flows correlated negatively with percentage stenosis in the affected vessel and positively to the minimal diameter at the stenosis site (P

Background To report the 3-year safety and effectiveness of the Surpass Streamline flow diverter in the SCENT trial (Surpass Intracranial Aneurysm Embolization System Pivotal Trial to Treat Large or Giant Wide-Neck Aneurysms). Methods The Surpass Streamline flow diverter device was evaluated in a multicenter, prospective, single-arm, non-randomized interventional trial including patients with uncoilable or previously treated but failed aneurysms of the intracranial internal carotid artery. 3-year outcomes were tabulated with descriptive statistics and compared with 1-year outcomes. Results Of 180 patients in the modified intent-to-treat (mITT) cohort, 36-month clinical and angiographic follow-up was available in 134 and 117 cases, respectively. Effectiveness endpoint of complete aneurysm occlusion without clinically significant stenosis or retreatment was met in 71.8% (79/110, 95% CI 62.4% to 80.0%) of cases. Safety composite endpoint was 12.2% (22/180) over the 3-year period, with two major safety events (ipsilateral ischemic strokes) occurring between 12-36 months. Complete aneurysm occlusion was noted in 77.8% (91/117), and 99.1% (116/117) of the patients demonstrated adequate aneurysm occlusion (complete occlusion or neck residual). There were four cases (2.2%) of aneurysm rupture, all occurring within the first month of the index procedure. Target aneurysm retreatment rate was 2.8% (5/180). Conclusion The present findings support the long-term safety and effectiveness of the Surpass Streamline flow diverter device. [ABSTRACT FROM AUTHOR]

Background The Surpass flow diverter was developed to treat intracranial aneurysms not amenable to standard treatment. Indications for use allow placement in the internal carotid artery to the terminus, including the communicating artery segment. Methods The Surpass Intracranial Aneurysm Embolization System Pivotal Trial to Treat Large or Giant Wide Neck Aneurysms (SCENT) trial is an international, multicenter, prospective, non-randomized trial comparing the outcomes of Surpass flow diverter treatment with historic control designed to evaluate the effectiveness and safety of Surpass for the treatment of wide neck (≥4 mm) large or giant intracranial aneurysms ≥10 mm. The primary effectiveness endpoint is the percentage of subjects with 100% aneurysm occlusion without significant stenosis of the parent artery and without retreatment of the target aneurysm at 12 months. The primary safety endpoint is the percentage of subjects experiencing neurologic death or major ipsilateral stroke at 12 months. We report the effectiveness and safety of flow diversion in the subgroup of posterior communicating artery (PComA) aneurysms. Results Of the 180 patients treated, 38 harbored a PComA aneurysm. Mean aneurysm size was 12.2 mm and mean neck width was 4.8 mm. The mean number of Surpass devices used was 1.1 per procedure, with 94.7% of aneurysms treated with one flow diverter. The 12 month primary effectiveness rate was 73.7% (28/38). At 36 months, 68.4% (26/38) of aneurysms remained completely occluded. The 12 month major ipsilateral stroke or neurological death rate was 10.5%. No patients with PComA occlusion after flow diverter placement (54.5%) had clinical sequelae. Conclusions SCENT demonstrated acceptable 12 month effectiveness of flow diversion in PComA aneurysms. Despite associated PComA occlusions in many cases, arterial occlusions were clinically silent. Trial registration number URL: https://www.clinicaltrials.gov. Unique identifier: NCT01716117. [ABSTRACT FROM AUTHOR]