Enabling Real-Time Volumetric Imaging in Interventional Radiology Suits via a Deep Learning Framework Robust to C-arm Tilt

TL;DR

This study demonstrates that a deep learning framework for 3D volumetric imaging in interventional radiology remains highly accurate across various C-arm tilt angles, supporting real-time guidance despite geometric complexities.

Contribution

The paper introduces a robust deep learning approach that maintains high-fidelity 3D reconstructions under diverse tilt conditions, advancing real-time interventional imaging capabilities.

Findings

High SSIM (>0.980) across all tilt angles

Minimal impact of C-arm tilt on reconstruction quality

Respiratory motion magnitude is the primary factor affecting accuracy

Abstract

Contemporary interventional imaging lacks the real-time 3D guidance needed for the precise localization of mobile thoracic targets. While Cone-Beam CT (CBCT) provides 3D data, it is often too slow for dynamic motion tracking. Deep learning frameworks that reconstruct 3D volumes from sparse 2D projections offer a promising solution, but their performance under the geometrically complex, non-zero tilt acquisitions common in interventional radiology is unknown. This study evaluates the robustness of a patient-specific deep learning framework, designed to estimate 3D motion, to a range of C-arm cranial-caudal tilts. Using a 4D digital phantom with a simulated respiratory cycle, 2D X-ray projections were simulated at five cranial-caudal tilt angles across 10 breathing phases. A separate deep learning model was trained for each tilt condition to reconstruct 3D volumetric images. The framework demonstrated consistently high-fidelity reconstruction across all tilts, with a mean Structural Similarity Index (SSIM) > 0.980. While statistical analysis revealed significant differences in performance between tilt groups (p < 0.0001), the absolute magnitude of these differences was minimal (e.g., the mean absolute difference in SSIM across all tilt conditions was ~0.0005), indicating they were not functionally significant. The magnitude of respiratory motion was found to be the dominant factor influencing accuracy, with the impact of C-arm tilt being a much smaller, secondary effect. These findings demonstrate that a patient-specific, motion-estimation-based deep learning approach is robust to geometric variations encountered in realistic clinical scenarios, representing a critical step towards enabling real-time 3D guidance in flexible interventional settings.