ACCURATE: Arbitrary-shaped Continuum Reconstruction Under Robust Adaptive Two-view Estimation

TL;DR

ACCURATE is a novel 3D reconstruction framework for arbitrary-shaped continuum bodies that combines neural segmentation with geometry constraints, achieving high accuracy and robustness in clinical imaging scenarios.

Contribution

It introduces a geometry-constrained topology traversal and dynamic programming approach that enforces global geometric consistency for improved reconstruction accuracy.

Findings

Mean absolute error below 1.0 mm on datasets

Robust to occlusions and noise

Effective on simulated and real phantom data

Abstract

Accurate reconstruction of arbitrary-shaped long slender continuum bodies, such as guidewires, catheters and other soft continuum manipulators, is essential for accurate mechanical simulation. However, existing image-based reconstruction approaches often suffer from limited accuracy because they often underutilize camera geometry, or lack generality as they rely on rigid geometric assumptions that may fail for continuum robots with complex and highly deformable shapes. To address these limitations, we propose ACCURATE, a 3D reconstruction framework integrating an image segmentation neural network with a geometry-constrained topology traversal and dynamic programming algorithm that enforces global biplanar geometric consistency, minimizes the cumulative point-to-epipolar-line distance, and remains robust to occlusions and epipolar ambiguities cases caused by noise and discretization. Our method achieves high reconstruction accuracy on both simulated and real phantom datasets acquired using a clinical X-ray C-arm system, with mean absolute errors below 1.0 mm.