Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering
arxiv(2023)
摘要
Surgical decisions are informed by aligning rapid portable 2D intraoperative
images (e.g., X-rays) to a high-fidelity 3D preoperative reference scan (e.g.,
CT). 2D/3D image registration often fails in practice: conventional
optimization methods are prohibitively slow and susceptible to local minima,
while neural networks trained on small datasets fail on new patients or require
impractical landmark supervision. We present DiffPose, a self-supervised
approach that leverages patient-specific simulation and differentiable
physics-based rendering to achieve accurate 2D/3D registration without relying
on manually labeled data. Preoperatively, a CNN is trained to regress the pose
of a randomly oriented synthetic X-ray rendered from the preoperative CT. The
CNN then initializes rapid intraoperative test-time optimization that uses the
differentiable X-ray renderer to refine the solution. Our work further proposes
several geometrically principled methods for sampling camera poses from
𝐒𝐄(3), for sparse differentiable rendering, and for driving
registration in the tangent space 𝔰𝔢(3) with geodesic and
multiscale locality-sensitive losses. DiffPose achieves sub-millimeter accuracy
across surgical datasets at intraoperative speeds, improving upon existing
unsupervised methods by an order of magnitude and even outperforming supervised
baselines. Our code is available at https://github.com/eigenvivek/DiffPose.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要