3D Reconstruction of Coronary Vessel Trees from Biplanar X-Ray Images Using a Geometric Approach

2025-09-15

AI Summary

This study addresses the limited 3D anatomical localization accuracy in coronary interventional procedures by proposing a novel biplane X-ray 3D reconstruction method that does not rely on epipolar geometry constraints. The method integrates semantic segmentation, inter-frame motion-phase alignment, heuristic keypoint matching, and a centerline reconstruction algorithm based on geometric surface intersection, enabling end-to-end mapping from 2D projections to 3D vascular structure. Its core innovation lies in explicitly modeling the geometric intersection relationships of vessel centerlines across the two views—thereby eliminating dependence on epipolar geometry and significantly enhancing robustness and accuracy. Evaluated on 62 clinical biplane X-ray video sequences, the method achieves a vessel segmentation Dice score of 0.703 and a reprojection error of 0.62 ± 0.38 mm for key anatomical landmarks—both metrics substantially outperforming existing geometric reconstruction paradigms.

Technology Category

• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

X-ray angiography is widely used in cardiac interventions to visualize coronary vessels, assess integrity, detect stenoses and guide treatment. We propose a framework for reconstructing 3D vessel trees from biplanar X-ray images which are extracted from two X-ray videos captured at different C-arm angles. The proposed framework consists of three main components: image segmentation, motion phase matching, and 3D reconstruction. An automatic video segmentation method for X-ray angiography to enable semantic segmentation for image segmentation and motion phase matching. The goal of the motion phase matching is to identify a pair of X-ray images that correspond to a similar respiratory and cardiac motion phase to reduce errors in 3D reconstruction. This is achieved by tracking a stationary object such as a catheter or lead within the X-ray video. The semantic segmentation approach assigns different labels to different object classes enabling accurate differentiation between blood vessels, balloons, and catheters. Once a suitable image pair is selected, key anatomical landmarks (vessel branching points and endpoints) are matched between the two views using a heuristic method that minimizes reconstruction errors. This is followed by a novel geometric reconstruction algorithm to generate the 3D vessel tree. The algorithm computes the 3D vessel centrelines by determining the intersection of two 3D surfaces. Compared to traditional methods based on epipolar constraints, the proposed approach simplifies there construction workflow and improves overall accuracy. We trained and validated our segmentation method on 62 X-ray angiography video sequences. On the test set, our method achieved a segmentation accuracy of 0.703. The 3D reconstruction framework was validated by measuring the reconstruction error of key anatomical landmarks, achieving a reprojection errors of 0.62mm +/- 0.38mm.

Problem

• Reconstructing 3D coronary vessel trees from biplanar X-ray images
• Matching motion phases to reduce cardiac and respiratory errors
• Segmenting vessels and instruments for accurate 3D reconstruction

Innovation

• Geometric reconstruction algorithm using surface intersections
• Automatic semantic segmentation for vessel differentiation
• Motion phase matching via stationary object tracking