Self-supervised monocular depth estimation for high field of view colonoscopy cameras

Alwyn Mathew, Ludovic Magerand, Emanuele Trucco, Luigi Manfredi (Lead / Corresponding author)

Research output: Contribution to journalArticlepeer-review

76 Downloads (Pure)

Abstract

Optical colonoscopy is the gold standard procedure to detect colorectal cancer, the fourth most common cancer in the United Kingdom. Up to 22%–28% of polyps can be missed during the procedure that is associated with interval cancer. A vision-based autonomous soft endorobot for colonoscopy can drastically improve the accuracy of the procedure by inspecting the colon more systematically with reduced discomfort. A three-dimensional understanding of the environment is essential for robot navigation and can also improve the adenoma detection rate. Monocular depth estimation with deep learning methods has progressed substantially, but collecting ground-truth depth maps remains a challenge as no 3D camera can be fitted to a standard colonoscope. This work addresses this issue by using a self-supervised monocular depth estimation model that directly learns depthfrom video sequences with view synthesis. In addition, our model accommodates wide field-of-view cameras typically used in colonoscopy and specific challenges such as deformable surfaces, specular lighting, non-Lambertian surfaces, and high occlusion. We performed qualitative analysis on a synthetic data set, a quantitative examination of the colonoscopy training model, and real colonoscopy videos in near real-time.
Original languageEnglish
Article number1212525
Number of pages9
JournalFrontiers in Robotics and AI
Volume10
DOIs
Publication statusPublished - 25 Jul 2023

Keywords

  • colonoscopy
  • depth estimation
  • wide-angle camera
  • endorobot
  • navigation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Self-supervised monocular depth estimation for high field of view colonoscopy cameras'. Together they form a unique fingerprint.

Cite this