Presentation
6 March 2023 SpecFlow: an end-to-end framework for specular reflection restoration in endoscopy videos using flow-guided video completion
Author Affiliations +
Abstract
Specular reflections (SR) commonly found in endoscopy videos can severely disrupt a surgeon’s observation and judgment, but existing methods to inpaint SR regions can result in false clinical interpretations. Therefore, we propose an end-to-end pipeline termed SpecFlow to detect and restore SR regions from endoscopy videos. Our proposed SpecFlow consists of two phases: detection using a reduced U-net model and a novel restoration method using optical flow-guided color propagation. Our detection pipeline achieves a competitive 82.8% Dice score with only 14ms of computational time (near real-time), and our restoration pipeline successfully incorporates temporal information for more accurate restorations.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Haoli Yin, Rachel L. Eimen, Daniel Moyer, and Audrey K. Bowden "SpecFlow: an end-to-end framework for specular reflection restoration in endoscopy videos using flow-guided video completion", Proc. SPIE PC12368, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXI, PC123680G (6 March 2023); https://doi.org/10.1117/12.2650509
Advertisement
Advertisement
KEYWORDS
Video

Endoscopy

Specular reflections

Optical flow

Visual process modeling

Image segmentation

Surgery

Back to Top