Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience.

OBJECTIVE: To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. METHODS: Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist's report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm. RESULTS: AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist's report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon. CONCLUSIONS: AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.

Thromboembolic Events With the Woven Endobridge Device: Incidence, Predictive Factors, and Management.

BACKGROUND AND OBJECTIVES: The Woven EndoBridge (WEB) device has been increasingly used to treat wide-neck aneurysms showing a safe and effective profile, but a relatively high number of thromboembolic events (TEEs) have been reported with such treatment. We aimed to evaluate the incidence and management of TEEs and possible predictive factors related to WEB embolization of ruptured and unruptured intracranial aneurysms. METHODS: A single-center database with consecutive aneurysms treated with a WEB device between July 2012 and May 2022 was reviewed for intraoperative and delayed TEEs. Univariate and multivariable analyses were used to determine factors associated with TEEs. RESULTS: A total of 266 independent aneurysms were treated with WEB devices in 245 patients (mean age 55.78 ± 11.64 years, 169 (63.5%) females, 80 (30%) ruptured). The overall rate of TEEs is 13% (35/266), including 8.7% intraoperative. Symptomatic TEEs with clinical sequelae at a 3-month follow-up are reported to be 2.6% (7/266) with no TEE-related mortality. Both the replacement of a WEB device during the procedure (adjusted odds ratio = 2.61, 95% CI 1.24-5.49; P = .01) and ruptured aneurysms (adjusted odds ratio = 2.74, 95% CI 1.31-5.7; P = .007) were independent predictors of TEEs. A case-by-case management of intraprocedural TEE is also presented; tirofiban was successfully used in most cases of this cohort. CONCLUSION: In this study, we demonstrated that ruptured aneurysms and WEB device replacement during the procedure were independent predictive factors for TEEs. As a result, making the correct choice of WEB is crucial for improving treatment outcomes. Moreover, with proper medical management of TEEs, minimal morbidity and no mortality could be achieved, which reinforces the safety of the technique.