Comparison Between the Stereoscopic Virtual Reality Display System and Conventional Computed Tomography Workstation in the Diagnosis and Characterization of Cerebral Arteriovenous Malformations

It is difficult to accurately understand the angioarchitecture of cerebral arteriovenous malformations (CAVMs) before surgery using existing imaging methods. This study aimed to evaluate the ability of the stereoscopic virtual reality display system (SVRDS) to display the angioarchitecture of CAVMs by comparing its accuracy with that of the conventional computed tomography workstation (CCTW). Nineteen patients with CAVM confirmed on digital subtraction angiography (DSA) or during surgery were studied. Computed tomography angiography images in the SVRDS and CCTW were retrospectively analyzed by two experienced neuroradiologists using a double-blind method. Angioarchitectural parameters, such as the location and size of the nidus, type and number of the arterial feeders and draining veins, and draining pattern of the vessels, were recorded and compared. The diameter of the nidus ranged from 1.1 to 9 cm. Both CCTW and SVRDS correctly diagnosed the location of the nidus in 19 patients with CAVM. Among the 19 patients, 35 arterial feeders and 25 draining veins were confirmed on DSA and during surgery. With the DSA and intraoperative results as the gold standard bases, the CCTW misjudged one arterial feeder and one draining vein and missed three arterial feeders and two draining veins; meanwhile, the SVRDS missed only two arterial feeders. SVRDS had some advantages in displaying nidus, arterial branches, and draining veins of the CAVM compared with CCTW, as well as SVRDS could more intuitively display the overall angio-architectural spatial picture of CAVM.

Deep Learning for Detection of Intracranial Aneurysms from Computed Tomography Angiography Images

The accuracy of computed tomography angiography (CTA) image interpretation depends on the radiologist. This study aims to develop a new method for automatically detecting intracranial aneurysms from CTA images using deep learning, based on a convolutional neural network (CNN) implemented on the DeepMedic platform. Ninety CTA scans of patients with intracranial aneurysms are collected and divided into two datasets: training (80 subjects) and test (10 subjects) datasets. Subsequently, a deep learning architecture with a three-dimensional (3D) CNN model is implemented on the DeepMedic platform for the automatic segmentation and detection of intracranial aneurysms from the CTA images. The samples in the training dataset are used to train the CNN model, and those in the test dataset are used to assess the performance of the established system. Sensitivity, positive predictive value (PPV), and false positives are evaluated. The overall sensitivity and PPV of this system for detecting intracranial aneurysms from CTA images are 92.3% and 100%, respectively, and the segmentation sensitivity is 92.3%. The performance of the system in the detection of intracranial aneurysms is closely related to their size. The detection sensitivity for small intracranial aneurysms (≤ 3 mm) is 66.7%, whereas the sensitivity of detection for large (> 10 mm) and medium-sized (3-10 mm) intracranial aneurysms is 100%. The deep learning architecture with a 3D CNN model on the DeepMedic platform can reliably segment and detect intracranial aneurysms from CTA images with high sensitivity.