3D Path Planning for Robot-assisted Vertebroplasty from Arbitrary Bi-plane X-ray via Differentiable Rendering

2025-12-05

AI Summary

To address the cumbersome workflow and high cost associated with preoperative CT-based registration in robot-assisted vertebroplasty, this paper proposes a CT-free, 3D transpedicular trajectory planning method utilizing only intraoperative biplanar X-ray images. Our approach jointly optimizes vertebral morphology and pose by integrating differentiable rendering, a statistical shape model (SSM), and a learned similarity loss function—enabling robustness to arbitrary X-ray view angles and uncalibrated imaging geometry. To our knowledge, this is the first end-to-end 3D planning framework that eliminates reliance on fixed imaging configurations or preoperative CT scans. We further introduce a clinician-in-the-loop closed-loop validation protocol. Quantitative evaluation shows bilateral trajectory planning success rates of 82% (synthetic data) and 75% (cadaveric data), with a Dice score of 0.75. The method achieves performance comparable to ReVerteR while demonstrating superior generalizability.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Robotic systems are transforming image-guided interventions by enhancing accuracy and minimizing radiation exposure. A significant challenge in robotic assistance lies in surgical path planning, which often relies on the registration of intraoperative 2D images with preoperative 3D CT scans. This requirement can be burdensome and costly, particularly in procedures like vertebroplasty, where preoperative CT scans are not routinely performed. To address this issue, we introduce a differentiable rendering-based framework for 3D transpedicular path planning utilizing bi-planar 2D X-rays. Our method integrates differentiable rendering with a vertebral atlas generated through a Statistical Shape Model (SSM) and employs a learned similarity loss to refine the SSM shape and pose dynamically, independent of fixed imaging geometries. We evaluated our framework in two stages: first, through vertebral reconstruction from orthogonal X-rays for benchmarking, and second, via clinician-in-the-loop path planning using arbitrary-view X-rays. Our results indicate that our method outperformed a normalized cross-correlation baseline in reconstruction metrics (DICE: 0.75 vs. 0.65) and achieved comparable performance to the state-of-the-art model ReVerteR (DICE: 0.77), while maintaining generalization to arbitrary views. Success rates for bipedicular planning reached 82% with synthetic data and 75% with cadaver data, exceeding the 66% and 31% rates of a 2D-to-3D baseline, respectively. In conclusion, our framework facilitates versatile, CT-free 3D path planning for robot-assisted vertebroplasty, effectively accommodating real-world imaging diversity without the need for preoperative CT scans.

Problem

• Develops 3D path planning for vertebroplasty without preoperative CT scans
• Uses arbitrary bi-plane X-rays and differentiable rendering for planning
• Integrates statistical shape model with learned similarity for generalization

Innovation

• Differentiable rendering with vertebral atlas for 3D path planning
• Learned similarity loss refines shape and pose dynamically
• Enables CT-free planning from arbitrary-view X-rays