Abstract
The assessment of rupture probability is crucial to identifying at risk intracranial aneurysms (IA) in patients harboring multiple aneurysms. We aimed to develop a computer-assisted detection system for small-sized aneurysm ruptures using a convolutional neural network (CNN) based on images of three-dimensional digital subtraction angiography. A retrospective data set, including 368 patients, was used as a training cohort for the CNN using the TensorFlow platform. Aneurysm images in six directions were obtained from each patient and the region-of-interest in each image was extracted. The resulting CNN was prospectively tested in 272 patients and the sensitivity, specificity, overall accuracy, and receiver operating characteristics (ROC) were compared to a human evaluator. Our system showed a sensitivity of 78.76% (95% CI: 72.30%–84.30%), a specificity of 72.15% (95% CI: 60.93%–81.65%), and an overall diagnostic accuracy of 76.84% (95% CI: 71.36%–81.72%) in aneurysm rupture predictions. The area under the ROC (AUROC) in the CNN was 0.755 (95% CI: 0.699%–0.805%), better than that obtained from a human evaluator (AUROC: 0.537; p < 0.001). The CNN-based prediction system was feasible to assess rupture risk in small-sized aneurysms with diagnostic accuracy superior to human evaluators. Additional studies based on a large data set are necessary to enhance diagnostic accuracy and to facilitate clinical application.
Highlights
The prevalence of intracranial aneurysms (IA) has been reported to be as high as 3.2 percent [1,2]
The rate of subarachnoid hemorrhage (SAH) due to aneurysm rupture is less than 2%, which means that only a small number of patients experience rupture events [3]
A retrospective data set composed of IA patients who underwent digital subtraction angiography (DSA) between January 2012 and December 2016 was used as a training cohort for the convolutional neural network (CNN) and the AlexNet architecture
Summary
The prevalence of intracranial aneurysms (IA) has been reported to be as high as 3.2 percent [1,2]. The identification of unruptured intracranial aneurysms (UIA) and the risk assessment of future rupture events are important in treatment planning. Aneurysm location and size are the main factors influencing UIA treatment. The annual rupture rate of aneurysms in the internal carotid artery (ICA), the posterior communicating (P-com) artery, and the middle cerebral artery (MCA) is 1.6%. UIA patients with aneurysms in the anterior cerebral artery (ACA), including the main anterior communicating (A-com) artery and the posterior cerebral artery, had higher annual rupture rates of up to 1.9% and 4%, respectively [6,7]. Aneurysm sizes of 7 mm and greater have been identified as risk factors increasing lifelong rupture risk [8]. Many uncertainties remain regarding rupture risk, in small saccular aneurysms less than 7 mm in size
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
