3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images

TL;DR

This paper introduces a novel method for 3D arterial segmentation from a single 2D projection with depth supervision, significantly reducing annotation effort while maintaining high accuracy in contrast-enhanced CT images.

Contribution

The authors propose a new approach that uses only one annotated 2D projection per training sample with depth information to achieve 3D vessel segmentation, reducing annotation workload.

Findings

Comparable performance with multiple projections using single projection annotation

Effective use of depth supervision to bridge 2D and 3D segmentation performance gap

Reduced annotation effort without sacrificing segmentation accuracy

Abstract

Automated segmentation of the blood vessels in 3D volumes is an essential step for the quantitative diagnosis and treatment of many vascular diseases. 3D vessel segmentation is being actively investigated in existing works, mostly in deep learning approaches. However, training 3D deep networks requires large amounts of manual 3D annotations from experts, which are laborious to obtain. This is especially the case for 3D vessel segmentation, as vessels are sparse yet spread out over many slices and disconnected when visualized in 2D slices. In this work, we propose a novel method to segment the 3D peripancreatic arteries solely from one annotated 2D projection per training image with depth supervision. We perform extensive experiments on the segmentation of peripancreatic arteries on 3D contrast-enhanced CT images and demonstrate how well we capture the rich depth information from 2D projections. We demonstrate that by annotating a single, randomly chosen projection for each training sample, we obtain comparable performance to annotating multiple 2D projections, thereby reducing the annotation effort. Furthermore, by mapping the 2D labels to the 3D space using depth information and incorporating this into training, we almost close the performance gap between 3D supervision and 2D supervision. Our code is available at: https://github.com/alinafdima/3Dseg-mip-depth.