Work

Kidney endoscopy video to preoperative CT alignment for depth estimation

Year: 2025

Type: conference-paper

Abstract: Monocular depth estimation from kidney endoscopy optimally requires ground truth depth information for endoscopy videos in order to train a neural network. Kidney endoscopy is not compatible with real-time tracking of the scope tip via, e.g., optical trackers, which makes it difficult to directly obtain such depth information. To address this problem, we propose a pipeline to reconstruct a 3D point cloud from the endoscopy video, which we register to a segmentation obtained from the preoperative CT image. We then use the estimated camera poses from the reconstruction and the segmentation surface geometry from preoperative CT to create synthetic endoscopy frames and accurate depth information. We validate this method on kidney phantoms with sub-millimeter RMSE accuracy (0.61 ± 0.08 mm) and demonstrate it on real patient data (0.86 mm).

Source: SPIE Medical Imaging: Image-Guided Procedures, Robotic Interventions, and Modeling

DOI: 10.1117/12.3047484

Authors: Daiwei Lu, Hao Li, Clifford Pierre, Nicholas Kavoussi, Ipek Oguz

Institutions: Vanderbilt University, Meharry Medical College, Vanderbilt University Medical Center

Language: English

Topic: Advanced Vision and Imaging

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funder: National Institutes of Health