Intraoperative Registration by Cross-Modal Inverse Neural Rendering
This work addresses a critical need for accurate and efficient registration in neurosurgery, representing an incremental improvement over existing methods.
The paper tackles the problem of 3D/2D intraoperative registration during neurosurgery by introducing a cross-modal inverse neural rendering approach that disentangles anatomical structure and appearance using a multi-style hypernetwork, resulting in a method that outperforms state-of-the-art techniques and meets clinical standards.
We present in this paper a novel approach for 3D/2D intraoperative registration during neurosurgery via cross-modal inverse neural rendering. Our approach separates implicit neural representation into two components, handling anatomical structure preoperatively and appearance intraoperatively. This disentanglement is achieved by controlling a Neural Radiance Field's appearance with a multi-style hypernetwork. Once trained, the implicit neural representation serves as a differentiable rendering engine, which can be used to estimate the surgical camera pose by minimizing the dissimilarity between its rendered images and the target intraoperative image. We tested our method on retrospective patients' data from clinical cases, showing that our method outperforms state-of-the-art while meeting current clinical standards for registration. Code and additional resources can be found at https://maxfehrentz.github.io/style-ngp/.