Quantitative Analysis of Hemodynamic Changes in Branch Arteries Covered by Flow Diverters.

BACKGROUND AND OBJECTIVES: Understanding post-treatment hemodynamic alterations and their association with the patency of covered branch arteries is limited. This study aims to identify hemodynamic changes after flow diverter stenting and investigate their correlation with the patency status of covered branch arteries. METHODS: All patients treated with pipeline embolization device for anterior cerebral artery aneurysms at our center between 2016 and 2020 were screened for inclusion. Quantitative digital subtraction angiography was used to analyze changes in hemodynamic parameters pre- and post-stenting. The patency status of covered branch arteries after stenting was categorized as either patent or flow impairment (defined as artery stenosis or occlusion). RESULTS: A total of 71 patients, encompassing 89 covered branch arteries, were enrolled. Flow impairment was observed in 11.2% (10/89) of the branches. The mean transit time and full width at half maximum (FWHM) in covered branches were significantly prolonged post-stenting (P = .004 and .023, respectively). Flow-impaired branch arteries exhibited hemodynamic shifts contrary to those in patent branch arteries. Specifically, flow-impaired branches showed marked reductions in time to peak, FWHM, and mean transit time (decreases of 32.8%, 32.6%, and 29%, respectively; P = .006, .002, and .002, respectively). Further multivariate analysis revealed that reductions in FWHM in the branches (odds ratio = 0.97, 95% CI: 0.95-0.99, P = .007) and smoking (odds ratio = 14.5, 95% CI: 1.39-151.76, P = .026) were independent predictors of flow impairment of covered branches. CONCLUSION: Pipeline embolization device stenting can cause a reduction in blood flow in branch arteries. Compared with patent branches, flow-impaired branches exhibit an increase in blood flow velocity after stenting. Smoking and ΔFWHM in the covered branches indicate flow impairment.

Diagnosis of intracranial aneurysms by computed tomography angiography using deep learning-based detection and segmentation.

BACKGROUND: Detecting and segmenting intracranial aneurysms (IAs) from angiographic images is a laborious task. OBJECTIVE: To evaluates a novel deep-learning algorithm, named vessel attention (VA)-Unet, for the efficient detection and segmentation of IAs. METHODS: This retrospective study was conducted using head CT angiography (CTA) examinations depicting IAs from two hospitals in China between 2010 and 2021. Training included cases with subarachnoid hemorrhage (SAH) and arterial stenosis, common accompanying vascular abnormalities. Testing was performed in cohorts with reference-standard digital subtraction angiography (cohort 1), with SAH (cohort 2), acquired outside the time interval of training data (cohort 3), and an external dataset (cohort 4). The algorithm's performance was evaluated using sensitivity, recall, false positives per case (FPs/case), and Dice coefficient, with manual segmentation as the reference standard. RESULTS: The study included 3190 CTA scans with 4124 IAs. Sensitivity, recall, and FPs/case for detection of IAs were, respectively, 98.58%, 96.17%, and 2.08 in cohort 1; 95.00%, 88.8%, and 3.62 in cohort 2; 96.00%, 93.77%, and 2.60 in cohort 3; and, 96.17%, 94.05%, and 3.60 in external cohort 4. The segmentation accuracy, as measured by the Dice coefficient, was 0.78, 0.71, 0.71, and 0.66 for cohorts 1-4, respectively. VA-Unet detection recall and FPs/case and segmentation accuracy were affected by several clinical factors, including aneurysm size, bifurcation aneurysms, and the presence of arterial stenosis and SAH. CONCLUSIONS: VA-Unet accurately detected and segmented IAs in head CTA comparably to expert interpretation. The proposed algorithm has significant potential to assist radiologists in efficiently detecting and segmenting IAs from CTA images.

Alcohol flushing syndrome is significantly associated with intracranial aneurysm rupture in the Chinese Han population.

Objective: Although alcohol flushing syndrome (AFS) has been associated with various diseases, its association with intracranial aneurysm rupture (IAR) is unclear. We aimed to examine this association in the Chinese Han population. Methods: We retrospectively reviewed Chinese Han patients with intracranial aneurysms who were evaluated and treated at our institution between January 2020 and December 2021. AFS was determined using a semi-structured telephone interview. Clinical data and aneurysm characteristics were assessed. Univariate and multivariate logistic regression were conducted to determine independent factors associated with aneurysmal rupture. Results: A total of 1,170 patients with 1,059 unruptured and 236 ruptured aneurysms were included. The incidence of aneurysm rupture was significantly higher in patients without AFS (p < 0.001). Meanwhile, there was a significantly difference between the AFS and non-AFS group in habitual alcohol consumption (10.5 vs. 27.2%, p < 0.001). In the univariate analyses, AFS [odds ratio (OR) 0.49; 95% confidence interval (CI), 0.34-0.72] was significantly associated with IAR. In the multivariate analysis, AFS was an independent predictor of IAR (OR 0.50; 95%, CI, 0.35-0.71). Multivariate analysis revealed that AFS was an independent predictor of IAR in both habitual (OR 0.11; 95% CI, 0.03-0.45) and non-habitual drinkers (OR 0.69; 95% CI, 0.49-0.96). Conclusion: Alcohol flushing syndrome may be a novel clinical marker to assess the risk of IAR. The association between AFS and IAR exists independently of alcohol consumption. Further single nucleotide polymorphism testing and molecular biology studies are warranted.

Long-term outcomes and dynamic changes of in-stent stenosis after Pipeline embolization device treatment of intracranial aneurysms.

BACKGROUND: Flow diverters have revolutionized the treatment of intracranial aneurysms. However, the delayed complications associated with flow diverter use are unknown. OBJECTIVE: To evaluate the incidence, severity, clinical outcomes, risk factors, and dynamic changes associated with in-stent stenosis (ISS) after treatment with a Pipeline embolization device (PED). METHODS: Patients who underwent PED treatment between 2015 and 2020 were enrolled. The angiographic, clinical, and follow-up data of 459 patients were independently reviewed by four neuroradiologists to identify ISS. Binary logistic regression was conducted to determine ISS risk factors, and an ISS-time curve was established to demonstrate dynamic changes in ISS after PED implantation. RESULTS: Of the 459 treated patients, 69 (15.0%) developed ISS. At follow-up, nine patients (2.0%) with ISS demonstrated reversal, while 18 (3.9%) developed parental artery occlusion. A total of 380 patients (82.8%) achieved complete aneurysm occlusion (O'Kelly-Marotta grade D). Patients with posterior-circulation aneurysm (OR=2.895, 95% CI (1.732 to 4.838; P<0.001) or balloon angioplasty (OR=1.992, 95% CI 1.162 to 3.414; P=0.037) were more likely to develop ISS. Patients aged >54 years (OR=0.464, 95% CI 0.274 to 0.785; P=0.006) or with a body mass index of >28 kg/m2 (OR=0.427, 95% CI 0.184 to 0.991; P=0.026) had a lower ISS risk. Intimal hyperplasia initiated by PED placement peaked within 1 year after the procedure, rarely progressed after 12 months, and tended to reverse within 24 months. CONCLUSIONS: ISS is a common, benign, and self-limiting complication of PED implantation in the Chinese population.

Automated anatomical labeling of the intracranial arteries via deep learning in computed tomography angiography.

Background and purpose: Anatomical labeling of the cerebral vasculature is a crucial topic in determining the morphological nature and characterizing the vital variations of vessels, yet precise labeling of the intracranial arteries is time-consuming and challenging, given anatomical structural variability and surging imaging data. We present a U-Net-based deep learning (DL) model to automatically label detailed anatomical segments in computed tomography angiography (CTA) for the first time. The trained DL algorithm was further tested on a clinically relevant set for the localization of intracranial aneurysms (IAs). Methods: 457 examinations with varying degrees of arterial stenosis were used to train, validate, and test the model, aiming to automatically label 42 segments of the intracranial arteries [e.g., 7 segments of the internal carotid artery (ICA)]. Evaluation metrics included Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD). Additionally, 96 examinations containing at least one IA were enrolled to assess the model's potential in enhancing clinicians' precision in IA localization. A total of 5 clinicians with different experience levels participated as readers in the clinical experiment and identified the precise location of IA without and with algorithm assistance, where there was a washout period of 14 days between two interpretations. The diagnostic accuracy, time, and mean interrater agreement (Fleiss' Kappa) were calculated to assess the differences in clinical performance of clinicians. Results: The proposed model exhibited notable labeling performance on 42 segments that included 7 anatomical segments of ICA, with the mean DSC of 0.88, MSD of 0.82 mm and HD of 6.59 mm. Furthermore, the model demonstrated superior labeling performance in healthy subjects compared to patients with stenosis (DSC: 0.91 vs. 0.89, p < 0.05; HD: 4.75 vs. 6.19, p < 0.05). Concurrently, clinicians with model predictions achieved significant improvements when interpreting the precise location of IA. The clinicians' mean accuracy increased by 0.04 (p = 0.003), mean time to diagnosis reduced by 9.76 s (p < 0.001), and mean interrater agreement (Fleiss' Kappa) increased by 0.07 (p = 0.029). Conclusion: Our model stands proficient for labeling intracranial arteries using the largest CTA dataset. Crucially, it demonstrates clinical utility, helping prioritize the patients with high risks and ease clinical workload.

Causal relationships between human blood metabolites and intracranial aneurysm and aneurysmal subarachnoid hemorrhage: a Mendelian randomization study.

Objective: The aim of this study was to assess the causal relationships between blood metabolites and intracranial aneurysm, aneurysmal subarachnoid hemorrhage, and unruptured intracranial aneurysm. Methods: Our exposure sample consisted of 7,824 individuals from a genome-wide association study of human blood metabolites. Our outcome sample consisted of 79,429 individuals (7,495 cases and 71,934 controls) from the International Stroke Genetics Consortium, which conducted a genome-wide association study of intracranial aneurysm, aneurysmal subarachnoid hemorrhage, and unruptured intracranial aneurysm. We identified blood metabolites with a potential causal effect on intracranial aneurysms and conducted sensitivity analyses to validate our findings. Results: After rigorous screening and Mendelian randomization tests, we found four, two, and three serum metabolites causally associated with intracranial aneurysm, aneurysmal subarachnoid hemorrhage, and unruptured intracranial aneurysm, respectively (all P < 0.05). Sensitivity analyses confirmed the robustness of these associations. Conclusions: Our Mendelian randomization analysis demonstrated causal relationships between human blood metabolites and intracranial aneurysm, aneurysmal subarachnoid hemorrhage, and unruptured intracranial aneurysm. Further research is required to explore the potential of targeting these metabolites in the management of intracranial aneurysm.

Case report: Covered stent placement to treat delayed aneurysmal rupture after flow diverter-assisted coil embolization.

Introduction: Flow diverter (FD) placement is widely accepted as a treatment for large saccular intracranial aneurysms. Delayed aneurysmal rupture (DAR) after FD placement is potentially catastrophic and difficult to treat. To our knowledge, using a Willis covered stent (WCS) to treat DAR after placement of a Pipeline Flex embolization device (PFED) combined with coiling has not been previously reported. Case presentation: A 49-year-old woman with an incidental asymptomatic large right supraclinoid internal carotid artery aneurysm was treated with PFED placement and adjunctive coiling. DAR causing subarachnoid hemorrhage occurred 11 hours after the procedure. Treatment using a WCS was successful and resulted in a favorable clinical outcome (modified Rankin scale score 2). Conclusion: DAR after FD implantation requires isolation of the aneurysm from the cerebral circulation as soon as possible. WCS placement can achieve this immediately and occlude the aneurysm. We hope our case could provide new idea for similar cases in the future.

Machine learning to predict in-stent stenosis after Pipeline embolization device placement.

Background: The Pipeline embolization device (PED) is a flow diverter used to treat intracranial aneurysms. In-stent stenosis (ISS) is a common complication of PED placement that can affect long-term outcome. This study aimed to establish a feasible, effective, and reliable model to predict ISS using machine learning methodology. Methods: We retrospectively examined clinical, laboratory, and imaging data obtained from 435 patients with intracranial aneurysms who underwent PED placement in our center. Aneurysm morphological measurements were manually measured on pre- and posttreatment imaging studies by three experienced neurointerventionalists. ISS was defined as stenosis rate >50% within the PED. We compared the performance of five machine learning algorithms (elastic net (ENT), support vector machine, Xgboost, Gaussian Naïve Bayes, and random forest) in predicting ISS. Shapley additive explanation was applied to provide an explanation for the predictions. Results: A total of 69 ISS cases (15.2%) were identified. Six predictors of ISS (age, obesity, balloon angioplasty, internal carotid artery location, neck ratio, and coefficient of variation of red cell volume distribution width) were identified. The ENT model had the best predictive performance with a mean area under the receiver operating characteristic curve of 0.709 (95% confidence interval [CI], 0.697-0.721), mean sensitivity of 77.9% (95% CI, 75.1-80.6%), and mean specificity of 63.4% (95% CI, 60.8-65.9%) in Monte Carlo cross-validation. Shapley additive explanation analysis showed that internal carotid artery location was the most important predictor of ISS. Conclusion: Our machine learning model can predict ISS after PED placement for treatment of intracranial aneurysms and has the potential to improve patient outcomes.

Protocol and Preliminary Results of the Establishment of Intracranial Aneurysm Database for Artificial Intelligence Application Based on CTA Images.

Background and Purpose: Unruptured intracranial aneurysms (UIAs) are increasingly being detected in clinical practice. Artificial intelligence (AI) has been increasingly used to assist diagnostic techniques and shows encouraging prospects. In this study, we reported the protocol and preliminary results of the establishment of an intracranial aneurysm database for AI application based on computed tomography angiography (CTA) images. Methods: Through a review of picture archiving and communication systems, we collected CTA images of patients with aneurysms between January 2010 and March 2021. The radiologists performed manual segmentation of all diagnosed aneurysms on subtraction CTA as the basis for automatic aneurysm segmentation. Then, AI will be applied to two stages of aneurysm treatment, namely, automatic aneurysm detection and segmentation model based on the CTA image and the aneurysm risk prediction model. Results: Three medical centers have been included in this study so far. A total of 3,190 cases of CTA examinations with 4,124 aneurysms were included in the database. All identified aneurysms from CTA images that enrolled in this study were manually segmented on subtraction CTA by six readers. We developed a structure of 3D-Unet for aneurysm detection and segmentation in CTA images. The algorithm was developed and tested using a total of 2,272 head CTAs with 2,938 intracranial aneurysms. The recall and false positives per case (FP/case) of this model for detecting aneurysms were 0.964 and 2.01, and the Dice values for aneurysm segmentation were 0.783. Conclusion: This study introduces the protocol and preliminary results of the establishment of the intracranial aneurysm database for AI applications based on CTA images. The establishment of a multicenter database based on CTA images of intracranial aneurysms is the basis for the application of AI in the diagnosis and treatment of aneurysms. In addition to segmentation, AI should have great potential for aneurysm treatment and management in the future.