Detection method of cerebral aneurysm based on curvature analysis from 3D medical images

Abstract

Cerebral aneurysm is a weak spot in a blood vessel that usually enlarges. Nowadays, cerebral aneurysm detection method is still being done manually by visually observing 2D or 3D medical images (CTA). The main purpose of this paper is to design a method of cerebral aneurysm detection and classify different vascular geometry with color indicator. The method developed was based on curvature analysis of wall vasculatures model that were reconstructed from 3D CTA images. The curvature shape index defined as I=(K1+K2)/K1 where K1 and K2 are the main curvature of vascular model then used as the base of vascular coloring system. Results showed that the shape index is able to differentiate different parts of vasculature model and detect the present of an aneurysm.