Vascular surface segmentation for intracranial aneurysm isolation and quantification

TL;DR

This paper introduces a two-stage deep learning approach for vascular surface segmentation to accurately isolate intracranial aneurysms from 3D angiograms, improving robustness and reproducibility over traditional methods.

Contribution

The authors propose a novel deep learning method using point cloud representations and neural networks for reliable intracranial aneurysm segmentation, outperforming existing techniques.

Findings

High segmentation sensitivity of 0.985 achieved

Significant improvement over state-of-the-art method (0.830)

Validated across diverse imaging modalities

Abstract

Predicting rupture risk and deciding on optimal treatment plan for intracranial aneurysms (IAs) is possible by quantification of their size and shape. For this purpose the IA has to be isolated from 3D angiogram. State-of-the-art methods perform IA isolation by encoding neurosurgeon's intuition about former non-dilated vessel anatomy through principled approaches like fitting a cutting plane to vasculature surface, using Gaussian curvature and vessel centerline distance constraints, by deformable contours or graph cuts guided by the curvature or restricted by Voronoi surface decomposition and similar. However, the large variability of IAs and their parent vasculature configurations often leads to failure or non-intuitive isolation. Manual corrections are thus required, but suffer from poor reproducibility. In this paper, we aim to increase the accuracy, robustness and reproducibility of IA isolation through two stage deep learning based segmentation of vascular surface. The surface was represented by local patches in form of point clouds, which were fed into first stage multilayer neural network (MNN) to obtain descriptors invariant to point ordering, rotation and scale. Binary classifier as second stage MNN was used to isolate surface belonging to the IA. Method validation was based on 57 DSA, 28 CTA and 5 MRA images, where cross-validation showed high segmentation sensitivity of 0.985, a substantial improvement over 0.830 obtained for the state-of-the-art method on the same datasets. Visual analysis of IA isolation and its high accuracy and reliability consistent across CTA and DSA scans confirmed the clinical applicability of proposed method.