Cerebrovascular Segmentation via Vessel Oriented Filtering Network

TL;DR

This paper introduces VOF-Net, a vessel-oriented filtering neural network that incorporates domain knowledge and vessel orientation estimation to improve cerebrovascular segmentation accuracy in MRA and CTA images.

Contribution

The novel VOF-Net embeds vessel orientation filters into the segmentation network, leveraging prior knowledge of vessel structure for enhanced segmentation performance.

Findings

Effective vessel segmentation on CTA and MRA datasets.

Embedding vessel-oriented filters improves segmentation accuracy.

Utilizes vessel orientation estimation to guide filtering.

Abstract

Accurate cerebrovascular segmentation from Magnetic Resonance Angiography (MRA) and Computed Tomography Angiography (CTA) is of great significance in diagnosis and treatment of cerebrovascular pathology. Due to the complexity and topology variability of blood vessels, complete and accurate segmentation of vascular network is still a challenge. In this paper, we proposed a Vessel Oriented Filtering Network (VOF-Net) which embeds domain knowledge into the convolutional neural network. We design oriented filters for blood vessels according to vessel orientation field, which is obtained by orientation estimation network. Features extracted by oriented filtering are injected into segmentation network, so as to make use of the prior information that the blood vessels are slender and curved tubular structure. Experimental results on datasets of CTA and MRA show that the proposed method is effective for vessel segmentation, and embedding the specific vascular filter improves the segmentation performance.