Automated detection of intracranial aneurysms based on parent vessel 3D analysis

Abstract 

The detection of brain aneurysms plays a key role in reducing the incidence of intracranial subarachnoid hemorrhage (SAH) which carries a high rate of morbidity and mortality. The majority of non-traumatic SAH cases is caused by ruptured intracranial aneurysms and accurate detection can decrease a significant proportion of misdiagnosed cases. A scheme for automated detection of intracranial aneurysms is proposed in this study. Applied to the segmented cerebral vasculature, the method detects aneurysms as suspect regions on the vascular tree, and is designed to assist diagnosticians with their interpretations and thus reduce missed detections. In the current approach, the vessels are segmented and their medial axis is computed. Small regions along the vessels are inspected and the writhe number is introduced as a new surface descriptor to quantify how closely any given region approximates a tubular structure. Aneurysms are detected as non-tubular regions of the vascular tree. The geometric assumptions underlying the approach are investigated analytically and validated experimentally. The method is tested on 3D-rotational angiography (3D-RA) and computed tomography angiography (CTA). In our experiments, 100% sensitivity was achieved with average false positives rates of 0.66 per study on 3D-RA data and 5.36 false positive rates per study on CTA data.

Keywords: Intracranial aneurysms, Aneurysm detection, Computed-aided diagnostic, Surface descriptor, Writhe number