Most Emma, Hein Jonas, Giraud Frédéric, Cavalcanti Nicola A, Zingg Lukas, Brument Baptiste, Louman Nino, Carrillo Fabio, Fürnstahl Philipp, Calvet Lilian
Research in Orthopedic Computer Science, University Hospital Balgrist, University of Zurich, Zurich, Switzerland.
Computer Vision and Geometry, ETH Zurich, Zurich, Switzerland.
Int J Comput Assist Radiol Surg. 2025 May 14. doi: 10.1007/s11548-025-03385-2.
Advances in computer vision, particularly in optical image-based 3D reconstruction and feature matching, enable applications like marker-less surgical navigation and digitization of surgery. However, their development is hindered by a lack of suitable datasets with 3D ground truth. This work explores an approach to generating realistic and accurate ex vivo datasets tailored for 3D reconstruction and feature matching in open orthopedic surgery.
A set of posed images and an accurately registered ground truth surface mesh of the scene are required to develop vision-based 3D reconstruction and matching methods suitable for surgery. We propose a framework consisting of three core steps and compare different methods for each step: 3D scanning, calibration of viewpoints for a set of high-resolution RGB images, and an optical method for scene registration.
We evaluate each step of this framework on an ex vivo scoliosis surgery using a pig spine, conducted under real operating room conditions. A mean 3D Euclidean error of 0.35 mm is achieved with respect to the 3D ground truth.
The proposed method results in submillimeter-accurate 3D ground truths and surgical images with a spatial resolution of 0.1 mm. This opens the door to acquiring future surgical datasets for high-precision applications.
计算机视觉的进展，特别是基于光学图像的3D重建和特征匹配方面的进展，使得诸如无标记手术导航和手术数字化等应用成为可能。然而，缺乏带有3D地面真值的合适数据集阻碍了它们的发展。这项工作探索了一种生成逼真且准确的离体数据集的方法，该数据集专为开放骨科手术中的3D重建和特征匹配量身定制。
要开发适用于手术的基于视觉的3D重建和匹配方法，需要一组姿态图像和场景的精确配准地面真值表面网格。我们提出了一个由三个核心步骤组成的框架，并比较了每个步骤的不同方法：3D扫描、一组高分辨率RGB图像的视点校准以及场景配准的光学方法。
我们在真实手术室条件下使用猪脊柱进行的离体脊柱侧弯手术中评估了该框架的每个步骤。相对于3D地面真值，实现了平均0.35毫米的3D欧几里得误差。
所提出的方法产生了亚毫米级精确的3D地面真值和空间分辨率为0.1毫米的手术图像。这为获取用于高精度应用的未来手术数据集打开了大门。
