GeoPose: Patient-agnostic CTA-to-DSA registration through projection-space calibration

2026-08-17

AI Summary

This study addresses the challenges of initialization dependency and patient-specific training in intraoperative DSA-CTA registration by proposing GeoPose, a novel framework employing population-level training and projection-space calibration to align poses within the native coordinate system. By integrating residual networks with lightweight optimization, GeoPose achieves cross-individual generalization without patient adaptation and enables direct registration in native frames. Experimental results demonstrate that without optimization, the mean centerline distance (mPCD) is 5.8 mm (0.15 s); after 25 iterations, mPCD decreases to 4.6 mm and clDice increases to 0.58, significantly outperforming baseline methods. These improvements effectively support downstream biplane vascular reconstruction, offering a robust solution for real-time clinical applications.

Abstract

Aligning intraoperative biplanar digital subtraction angiography (DSA) to pre-procedural computed tomography angiography (CTA) requires rapid and accurate 3D-to-2D registration. Optimization-based methods are sensitive to initialization and may require hundreds of iterations, whereas learning-based approaches commonly rely on patient-specific training. We propose GeoPose, a population-trained framework that estimates the C-arm pose in a learned canonical frame and transfers it to the native frame of an unseen CTA through projection-space calibration and transform composition. A population-trained residual network refines the pose, followed optionally by low-budget image-driven optimization. GeoPose requires neither patient-specific adaptation nor explicit inter-volume preregistration. On 80 DSA observations from 20 held-out patients, optimization-free GeoPose achieved a carotid mean projected centerline distance (mPCD) of 5.8 mm and a clDice of 0.45, compared with 14.5 mm and 0.28 for the best-performing baseline, while requiring only 0.15 s. After 25 optimization iterations, GeoPose reached an mPCD of 4.6 mm and a clDice of 0.58 in approximately two seconds. Under the same budget, native-initialized optimization achieved 14.6 mm and 0.15, respectively. GeoPose thus provides rapid native-frame registration with fixed population-level weights and the geometric correspondence required for downstream biplanar 3D vascular reconstruction.

Problem

• CTA-to-DSA registration
• 3D-to-2D registration
• Patient-agnostic
• Biplane DSA

Innovation

• Patient-agnostic registration
• Projection-space calibration
• Canonical frame estimation
• Population-trained framework
• CTA-to-DSA alignment