Paper 13408-11
Paper 13408-11
High-fidelity 3D reconstruction for accurate anatomical measurements in endoscopic sinus surgery
17 February 2025 • 3:50 PM - 4:10 PM PST | Town & Country D
Abstract
While NeRF has been extensively applied to generate implicit, qualitative reconstructions in vivo, it has yet to be effectively implemented and extensively tested in the quantitative representation of anatomical geometry. Our expanded workflow demonstrates the ability to create high-resolution and accurate 3D reconstructions of surgical scene anatomy. Using a series of three cadaveric specimens, measurements of critical anatomy were reconstructed and evaluated with average errors for ethmoid length and height being 0.17mm and 0.70mm, respectively.
Presenter
Nicole Gunderson
Univ. of Washington (United States)
Nicole Gunderson is a second-year PhD student in Mechanical Engineering at the University of Washington, having previously earned a BS in Biomedical Engineering from the University of Colorado Boulder. Her research focuses on developing novel methods for in vivo 3D modeling and reconstruction via endoscopy to aid minimally invasive surgical planning. Currently, she is researching point cloud optimization, explicit mesh construction from sparse point clouds, and the absolute scaling and registration of 3D models to CT scans. Nicole's research interests lie in surgical robotics, medical applications of computer vision, the use of AI in medicine, and the 3D modeling of tissue deformation.