Pratt Philip, Bergeles Christos, Darzi Ara, Yang Guang-Zhong
Med Image Comput Comput Assist Interv. 2014;17(Pt 2):667-75. doi: 10.1007/978-3-319-10470-6_83.
Many of the currently available stereo endoscopes employed during minimally invasive surgical procedures have shallow depths of field. Consequently, focus settings are adjusted from time to time in order to achieve the best view of the operative workspace. Invalidating any prior calibration procedure, this presents a significant problem for image guidance applications as they typically rely on the calibrated camera parameters for a variety of geometric tasks, including triangulation, registration and scene reconstruction. While recalibration can be performed intraoperatively, this invariably results in a major disruption to workflow, and can be seen to represent a genuine barrier to the widespread adoption of image guidance technologies. The novel solution described herein constructs a model of the stereo endoscope across the continuum of focus settings, thereby reducing the number of degrees of freedom to one, such that a single view of reference geometry will determine the calibration uniquely. No special hardware or access to proprietary interfaces is required, and the method is ready for evaluation during human cases. A thorough quantitative analysis indicates that the resulting intrinsic and extrinsic parameters lead to calibrations as accurate as those derived from multiple pattern views.
目前在微创手术过程中使用的许多立体内窥镜景深较浅。因此，需要不时调整聚焦设置，以获得手术工作空间的最佳视野。这会使任何先前的校准程序无效，对于图像引导应用来说，这是一个重大问题，因为它们通常依赖校准后的相机参数来执行各种几何任务，包括三角测量、配准和场景重建。虽然可以在术中重新校准，但这必然会导致工作流程的重大中断，并且可以被视为图像引导技术广泛应用的一个真正障碍。本文所述的新颖解决方案构建了一个跨越聚焦设置连续体的立体内窥镜模型，从而将自由度数量减少到一个，这样，单个参考几何视图就能唯一确定校准。该方法无需特殊硬件或访问专有接口，并且已准备好在人体病例中进行评估。全面的定量分析表明，由此得到的内参和外参所导致的校准与从多个图案视图得出的校准一样准确。
