Development of endoscopic SLAM and the challenges

Wenyue Jin

doi:10.1117/12.2691855

7 September 2023 Development of endoscopic SLAM and the challenges

Wenyue Jin

Proceedings Volume 12789, International Conference on Modern Medicine and Global Health (ICMMGH 2023); 1278907 (2023) https://doi.org/10.1117/12.2691855
Event: International Conference on Modern Medicine and Global Health (ICMMGH 2023), 2023, Oxford, United Kingdom

Abstract

Three-dimensional anatomical maps for minimally invasive surgery (MIS) can be better constructed by building a visual Simultaneous Localization and Mapping (vSLAM) system in clinical examination. Developing vSLAM systems is challenged by the fact that the highly variable colon environment places higher demands on visual processing. Researchers have adapted vSLAM to align with the distinct characteristics of the surgical environment, which mostly focused on offering a more reliable tracking procedure. Learning based methods were developed to extract sufficient repeatable features and to remove specular highlights which are miss-classified as features. By modifying the existing vSLAM systems and integrating with deep learning based approaches, endoscopic vSLAM has shown greater reliability, especially in dealing with deformation of organ. Due to lack of validation on public benchmarks and tracking failure, there are still under-explored issues to be addressed in the development.

Citation Download Citation

Wenyue Jin "Development of endoscopic SLAM and the challenges", Proc. SPIE 12789, International Conference on Modern Medicine and Global Health (ICMMGH 2023), 1278907 (7 September 2023); https://doi.org/10.1117/12.2691855

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available