Dataset Information

The Aneurysm Occlusion Assistant, an AI platform for real time surgical guidance of intracranial aneurysms.

ABSTRACT:

Purpose

In recent years, endovascular treatment has become the dominant approach to treat intracranial aneurysms (IAs). Despite tremendous improvement in surgical devices and techniques, 10-30% of these surgeries require retreatment. Previously, we developed a method which combines quantitative angiography with data-driven modeling to predict aneurysm occlusion within a fraction of a second. This is the first report on a semi-autonomous system, which can predict the surgical outcome of an IA immediately following device placement, allowing for therapy adjustment. Additionally, we previously reported various algorithms which can segment IAs, extract hemodynamic parameters via angiographic parametric imaging, and perform occlusion predictions.

Methods

We integrated these features into an Aneurysm Occlusion Assistant (AnOA) utilizing the Kivy library's graphical instructions and unique language properties for interface development, while the machine learning algorithms were entirely developed within Keras, Tensorflow and skLearn. The interface requires pre- and post-device placement angiographic data. The next steps for aneurysm segmentation, angiographic analysis and prediction have been integrated allowing either autonomous or interactive use.

Results

The interface allows for segmentation of IAs and cranial vasculature with a dice index of ~0.78 and prediction of aneurysm occlusion at six months with an accuracy 0.84, in 6.88 seconds.

Conclusion

This is the first report on the AnOA to guide endovascular treatment of IAs. While this initial report is on a stand-alone platform, the software can be integrated in the angiographic suite allowing direct communication with the angiographic system for a completely autonomous surgical guidance solution.

SUBMITTER: Williams KA

PROVIDER: S-EPMC8323517 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and purposeChildren with brain aneurysms may be at higher risk than adults to develop new or enlarging aneurysms in a relatively short time. We sought to identify comorbidities and angiographic features in children that predict new aneurysm formation or enlargement of untreated aneurysms.Materials and methodsRetrospective analysis of the University of California-San Francisco Pediatric Aneurysm Cohort data base including medical records and imaging studies was performed.ResultsOf 83 patients harboring 114 intracranial aneurysms not associated with brain arteriovenous malformations or intracranial arteriovenous fistulas, 9 (8.4%) developed new or enlarging brain aneurysms an average of 4.2 years after initial presentation. Comorbidities that may be related to aneurysm formation were significantly higher in patients who developed new aneurysms (89%) as opposed to patients who did not develop new or enlarging aneurysms (41%; RR, 9.5; 95% CI, 1.9%-48%; P = .0099). Patients with multiple aneurysms at initial presentation were more likely than patients with a single aneurysm at presentation to develop a new or enlarging aneurysm (RR, 6.2; 95% CI, 2.1%-185; P = .0058). Patients who initially presented with at least 1 fusiform aneurysm were more likely to develop a new or enlarging aneurysm than patients who did not present with a fusiform aneurysm (RR, 22; 95% CI, 3.6%-68%; P = .00050). Index aneurysm treatment with parent artery occlusion also was associated with higher risk of new aneurysm formation (RR, 4.2; 95% CI, 1.3%-13%; P = .024). New aneurysms did not necessarily arise near index aneurysms. The only fatality in the series was due to subarachnoid hemorrhage from a new posterior circulation aneurysm arising 20 months after index anterior circulation aneurysm treatment in an immunosuppressed patient.ConclusionsPatients who presented with a fusiform aneurysm had a significantly greater incidence of developing a new aneurysm or enlargement of an index aneurysm than did those who presented with a saccular aneurysm. In our patient cohort, 8 of the 9 children who eventually developed new or enlarging brain aneurysms initially presented with fusiform aneurysm morphology. Other comorbidities or multiple aneurysms were also common in these patients at initial presentation.

Project description:Background and objectiveIntracranial fusiform aneurysms (IFAs) are considered to have a complex pathophysiology process and poor natural history. The purpose of this study was to investigate the pathophysiological mechanisms of IFAs based on the characteristics of aneurysm wall enhancement (AWE), hemodynamics, and morphology.MethodsA total of 21 patients with 21 IFAs (seven fusiform types, seven dolichoectatic types, and seven transitional types) were included in this study. Morphological parameters of IFAs were measured from the vascular model, including the maximum diameter (Dmax), maximum length (Lmax), and centerline curvature and torsion of fusiform aneurysms. The three-dimensional (3D) distribution of AWE in IFAs was obtained based on high-resolution magnetic resonance imaging (HR-MRI). Hemodynamic parameters including time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), gradient oscillatory number (GON), and relative residence time (RRT) were extracted by computational fluid dynamics (CFD) analysis of the vascular model, and the relationship between these parameters and AWE was investigated.ResultsThe results showed that Dmax (p = 0.007), Lmax (p = 0.022), enhancement area (p = 0.002), and proportion of enhancement area (p = 0.006) were significantly different among three IFA types, and the transitional type had the largest Dmax, Lmax, and enhancement area. Compared with the non-enhanced regions of IFAs, the enhanced regions had lower TAWSS but higher OSI, GON, and RRT (p < 0.001). Furthermore, Spearman's correlation analysis showed that AWE was negatively correlated with TAWSS, but positively correlated with OSI, GON, and RRT.ConclusionThere were significant differences in AWE distributions and morphological features among the three IFA types. Additionally, AWE was positively associated with the aneurysm size, OSI, GON, and RRT, while negatively correlated with TAWSS. However, the underlying pathological mechanism of the three fusiform aneurysm types needs to be further studied.

Project description:Study objectivesObstructive sleep apnea is a risk factor for hypertension. Hypertension is associated with aneurysm formation, growth, and rupture of intracranial aneurysm (IA). Retrospectively, symptoms of obstructive sleep apnea are more prevalent in patients with IAs. Studies investigating the prevalence and effect of objectively measured sleep apnea in these patients are sparse. We report on the baseline data of an ongoing prospective study. We cross-sectionally analyzed whether obstructive sleep apnea was associated with larger IAs and increased need for antihypertensive medications in a population of patients with unruptured IA.Methods130 adult (≥ 18 years) patients with unruptured IAs were recruited. Patients with ischemic stroke or intracranial hemorrhage within 3 months prior to screening were excluded. We assessed obstructive sleep apnea by full-night respiratory polygraphy. Aneurysm size and antihypertensive medication-as a surrogate parameter for the severity of hypertension-were compared between patients with and without obstructive sleep apnea (apnea-hypopnea index >5 events/h). Aneurysm growth and rupture rate were retrospectively analyzed.Results101 patients completed the study protocol. Obstructive sleep apnea was diagnosed in 68.0% (17) of male and 34.2% (26) of female participants and associated with more severe hypertension (1.536 ± 0.2 vs 0.74 ± 0.1 drugs; P = .01) and larger aneurysms (6.9 ± 1.0 vs 3.8 ± 0.5 mm; P = .01).ConclusionsPatients with obstructive sleep apnea had more antihypertensive medication and larger IAs, probably due to accelerated aneurysm growth. Sleep apnea should be considered in patients with IAs. More research is needed to investigate the effects of sleep apnea on IAs and aneurysm outcome.Clinical trial registrationRegistry: ClinicalTrials.gov; Name: Incidence and Effects of Sleep Apnea on Intracerebral Aneurysms-IESA Study; URL: https://clinicaltrials.gov/ct2/show/NCT02880059; Identifier: NCT02880059.CitationZaremba S, Albus L, Hadjiathanasiou A, Vatter H, Wüllner U, Güresir E. Aneurysm size and blood pressure severity in patients with intracranial aneurysms and sleep apnea. J Clin Sleep Med. 2022;18(6):1539-1545.