3D convolutional neural networks for detecting intracranial aneurysms on brachiocephalic arteries CTA scans

Abstract

Background: Computed tomography angiography (CTA) is the primary and minimally invasive imaging modality currently used for diagnosis and monitoring of intracranial aneurysms as well as preoperative planning of their treatment. However, its interpretation is time-consuming even for specially trained neuroradiologists. Nowadays little is known whether trained neural networks contribute to analyzing medical images and reduce the time to diagnosis, and how effective they are in detecting intracranial aneurysms according to the CTA findings.Objective: To assess the diagnostic value of a convolutional neural network prototype in the intracranial aneurysm detection according to the brachiocephalic arteries CTA findings.Materials and methods: We analyzed the 3D convolutional neural network prototype based at Kuban State University (Krasnodar, Russian Federation).This prototype was to determine the probability of intracranial aneurysms according to the brachiocephalic arteries CTA findings, obtained in the Radiology Department of Scientific Research Institute – Ochapovsky Regional Clinical Hospital No. 1. The study included 451 CTA scans of 205 patients with confirmed intracranial aneurysms and 246 patients without aneurysms.Results: The sensitivity of the 3D convolutional neural network prototype in the aneurysms detection according to the brachiocephalic arteries CTA findings was 85.1%, the specificity was 95.1%, and the overall accuracy was 91%.Conclusions: The 3D convolutional systems may predict aneurysms with a high accuracy as well as localize them with an accuracy of more than 90%. Such results require a larger dataset.

Keywords

• computed tomography
• cta
• intracranial aneurysms
• dicom
• machine learning
• high-accuracy neural network