Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Reconstruction from multi-planar MRI with foundation models for uterine fibroid analysis.

NPJ digital medicine·2026
Same author

Lignanamides, alkaloids, and other constituents from stems of <i>Tinospora crispa</i>.

Natural product research·2026
Same author

Brain Magnetic Resonance Elastography Experiments With an Electromagnetic Actuator.

Current protocols·2026
Same author

Towards boundary confusion for volumetric medical image segmentation.

Medical image analysis·2026
Same author

Magnetically Guided Microrobots for Targeted Drug Delivery.

Advanced healthcare materials·2026
Same author

Multiscale measurement of brain tissue and cell biomechanics using a mouse model.

Biophysics reports·2026

Related Experiment Video

Updated: Jan 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Trimming-then-augmentation: Towards robust depth and odometry estimation for endoscopic images.

Junyang Wu1, Yun Gu2, Guang-Zhong Yang1

  • 1Shanghai Key Laboratory of Flexible Medical Robotics, Tongren Hospital, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China.

Medical Image Analysis
|September 23, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a new unsupervised learning framework for depth and odometry estimation in endoscopic imaging. The method improves accuracy and generalizability by handling imaging artifacts and motion, crucial for robot-assisted interventions.

Keywords:
Endoscopic imagesRobustnessSelf-supervised monocular pose estimation

More Related Videos

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

489

Related Experiment Videos

Last Updated: Jan 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

489

Area of Science:

  • Medical Robotics
  • Computer Vision
  • Surgical Navigation

Background:

  • Depth and odometry estimation are critical for robot-assisted endoluminal interventions.
  • Unsupervised learning is preferred due to challenges in acquiring in vivo ground truth data.
  • Existing methods struggle with imaging artifacts, limited anatomical markers, tissue motion, and specular reflections, impacting accuracy and generalizability.

Purpose of the Study:

  • To develop an improved unsupervised learning framework for depth and odometry estimation in endoscopic imaging.
  • To enhance accuracy and generalizability of estimation methods in challenging in vivo conditions.

Main Methods:

  • A novel trimming-then-augmentation framework utilizing a "mask-then-recover" strategy.
  • Masking artifact regions and reconstructing depth/pose using convolutional networks.
  • Employing an augmentation module with a task-specific loss function for stable feature pair establishment.

Main Results:

  • Significant improvement in accuracy compared to state-of-the-art unsupervised methods.
  • Demonstrated effectiveness and resilience to image artifacts.
  • Showcased stability in in vivo settings.

Conclusions:

  • The proposed framework effectively addresses limitations of existing unsupervised methods for endoscopic depth and odometry estimation.
  • The method offers improved accuracy, generalizability, and robustness for robot-assisted endoluminal interventions.