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

Prediction of microvascular invasion in hepatocellular carcinoma using contrast-enhanced ultrasound and deep learning.

Nature communications·2026
Same author

Spatial signal distribution learning for high-resolution 3D system matrix calibration in magnetic particle imaging.

Physics in medicine and biology·2026
Same author

A compact low-power magnetic particle imaging scanner based on a permanent-magnet field-free-line generator with high gradient.

The Review of scientific instruments·2026
Same author

Breaking the Trade-off in MPI-Guided Magnetic Hyperthermia by Tailoring the Dynamic Magnetization of Magnetic Nanoparticles via Site-Selective Trace Doping.

Journal of the American Chemical Society·2026
Same author

TSMPI-Net: a time-series generative adversarial network for short-frame-interval magnetic particle imaging.

Physics in medicine and biology·2026
Same author

STimulated emission depletion (STED) magnetic particle imaging.

Medical physics·2025

Related Experiment Video

Updated: Jul 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

568

Specular highlight removal for endoscopic images using partial attention network.

Chong Zhang1,2, Yueliang Liu1, Kun Wang2

  • 1Department of Big Data Management and Application, School of International Economics and Management, Beijing Technology and Business University, Beijing, People's Republic of China.

Physics in Medicine and Biology
|October 12, 2023
PubMed
Summary

A new partial attention network (PatNet) effectively removes specular highlights in endoscopic imaging. This method improves visualization quality for minimally invasive surgery by restoring images close to their original state.

Keywords:
Endoscopic imagingdeep learninghighlight removalpartial attention network

More Related Videos

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

2.8K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

Related Experiment Videos

Last Updated: Jul 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

568
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

2.8K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Surgical Technology

Background:

  • Endoscopic imaging is crucial for minimally invasive surgery but often suffers from specular highlights caused by mucus layer reflections.
  • These highlights degrade image quality, hindering accurate surgical analysis and potentially impacting patient outcomes.

Purpose of the Study:

  • To develop and evaluate an effective specular highlight removal method for endoscopic imaging.
  • To improve the clarity and diagnostic value of endoscopic visual data.

Main Methods:

  • A novel partial attention network (PatNet) was proposed, comprising highlight segmentation and image inpainting.
  • Highlight segmentation utilized brightness thresholding with illumination compensation.
  • Image inpainting employed a partial convolution network with an integrated attention mechanism, trained on a simulated highlight dataset.

Main Results:

  • PatNet demonstrated superior performance compared to existing highlight segmentation, inpainting, and removal methods in both perceptual and quantitative evaluations.
  • Surgeons rated PatNet highest (4.18) for highlight removal under realistic conditions, indicating significant subjective improvement.
  • Statistical analysis (Kendall's W = 0.757, p < 0.01) confirmed high consistency and confidence in subjective assessments.

Conclusions:

  • The proposed PatNet effectively removes irregular specular highlights from endoscopic images.
  • The method achieves image restoration closely resembling ground truth, significantly enhancing endoscopic imaging quality for better surgical analysis.