Deep homography estimation in dynamic surgical scenes for laparoscopic camera motion extraction. Issue 3 (4th May 2022)

• Record Type: Journal Article
• Authors: Huber, Martin; Ourselin, Sébastien; Bergeles, Christos; Vercauteren, Tom
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 10:Issue 3(2022)
• Page Start: 321
• Page End: 329
• Publication Date: 2022-05-04
• Subjects: Deep learning -- homography estimation -- laparoscopic surgery -- image processing and analysis -- visual data mining and knowledge discovery -- virtual reality; Imaging systems in biology -- Periodicals; Imaging systems in medicine -- Periodicals; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; 616.0757
• DOI: 10.1080/21681163.2021.2002195
• Languages: English
• ISSNs: 2168-1163

Abstract

ABSTRACT: Current laparoscopic camera motion automation relies on rule-based approaches or only focuses on surgical tools. Imitation Learning (IL) methods could alleviate these shortcomings, but have so far been applied to oversimplified setups. Instead of extracting actions from oversimplified setups, in this work we introduce a method that allows to extract a laparoscope holder's actions from videos of laparoscopic interventions. We synthetically add camera motion to a newly acquired dataset of camera motion free da Vinci surgery image sequences through a novel homography generation algorithm . The synthetic camera motion serves as a supervisory signal for camera motion estimation that is invariant to object and tool motion. We perform an extensive evaluation of state-of-the-art (SOTA) Deep Neural Networks (DNNs) across multiple compute regimes, finding our method transfers from our camera motion free da Vinci surgery dataset to videos of laparoscopic interventions, outperforming classical homography estimation approaches in both, precision by 41 %, and runtime on a CPU by 43 % .