Robust Shape Recovery of Deformable Soft-tissue Based on Information from Stereo Scope for Minimal Invasive Surgery

Publication Type:
Conference Proceeding
Hamlyn Symposium on Medical Robotics (HSMR 2017), 2017
Issue Date:
Filename Description Size
HamlynSymposium2017_Jingwei.pdfAccepted Manuscript version650.93 kB
Adobe PDF
Full metadata record
Overcoming small field of view of scopes is an important challenge in minimal invasive surgery (MIS). Efforts have been devoted in 3D soft-tissue construction and camera localization [1-2]. This paper proposes a robust strategy for simultaneous camera localization and dense reconstruction of deformable surfaces. The robustness is achieved by: (1) using a sequence of images collected from a stereoscope by considering uncertainty map; (2) filtering images with low intensity; (3) filtering depth by normals. Our approach greatly reduces depth estimation parameter adjustment efforts while still generates good results and preserves topological details. Experiments reveal that the proposed approach is convenient for dynamically rebuild and visualize the latest shape of soft-tissue to mitigate unnecessary tissue damages in minimal invasive surgery.
Please use this identifier to cite or link to this item: