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 Experiment Video

Updated: Sep 27, 2025

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K

Endoscopy image enhancement method by generalized imaging defect models based adversarial training.

Wenjie Li1, Jingfan Fan1, Yating Li1

  • 1Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China.

Physics in Medicine and Biology
|April 13, 2022
PubMed
Summary

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

The relationship between family function and behavioral decision-making in patients with gestational diabetes mellitus: a multiple mediation model and cross-lagged analysis of pregnancy-related anxiety and hope.

Frontiers in medicine·2026
Same author

Effect of different ultrasonic power levels on the structure and functional properties of soybean protein hydrolysates-soybean hull polysaccharide (SPHS-SSPS) complexes.

Food chemistry·2026
Same author

Ultrasound Slice-to-Volume Registration via Artifact-Suppressed Ultra-Feature Learning.

IEEE journal of biomedical and health informatics·2026
Same author

Three-dimensional Liver Respiratory Motion Tracking in Ultrasound Images via Vascular Structural Projection Optimization and Multi-path Constrained Estimation.

Ultrasound in medicine & biology·2026
Same author

Robot-Assisted Osteotomy and Reconstruction with AR Guidance in Maxillofacial Reconstructive Surgery.

Cyborg and bionic systems (Washington, D.C.)·2026
Same author

Baseline Hematological Parameters and Outcomes in Patients With Prostate Cancer Treated With Lu-177 PSMA Radioligand Therapy (RLT): A Multicenter Real-World Analysis.

Clinical genitourinary cancer·2026
Same journal

Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators.

Physics in medicine and biology·2026
Same journal

Corrigendum: Referenceless MR thermometry-a comparison of five methods (2017<i>Phys. Med. Biol</i>.<b>62</b>1-16).

Physics in medicine and biology·2026
Same journal

Corrigendum: Measured and Monte Carlo simulated electron backscatter to the monitor chamber for the varian TrueBeam linac (2016<i>Phys. Med. Biol</i>.<b>61</b>8779).

Physics in medicine and biology·2026
Same journal

Corrigendum: 3D range-modulator for scanned particle therapy: development, Monte Carlo simulations and experimental evaluation (2017<i>Phys. Med. Biol</i>.<b>62</b>7075).

Physics in medicine and biology·2026
Same journal

Recent progress in applications of computing to radiotherapy (ICCR 2016).

Physics in medicine and biology·2026
Same journal

Novel TMS coils designed using an inverse boundary element method.

Physics in medicine and biology·2026
See all related articles
This summary is machine-generated.

This study introduces a novel semi-supervised learning framework for enhancing endoscopic images, effectively addressing smoke, lighting, and color issues in surgery. The physics-driven approach significantly improves image quality and clinical usefulness.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Endoscopic surgery faces challenges like smoke, poor lighting, and color distortion, increasing surgical risks.
  • Existing image enhancement methods often require paired ground-truth data or lack generalizability.

Purpose of the Study:

  • To develop a generalizable, physics-driven semi-supervised learning framework for pixel-wise endoscopic image enhancement.
  • To improve smoke removal, light adjustment, and color correction in endoscopic visuals.
  • To address data scarcity in endoscopic enhancement tasks using transfer learning.

Main Methods:

  • A novel physics model-driven semi-supervised learning framework integrated with CycleGAN.
  • Incorporation of physical imaging defect models to enhance generated image authenticity.
Keywords:
cycle-consistent adversarial networkendoscopy image enhancementimaging defect modelsemi-supervised training

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

3.0K

Related Experiment Videos

Last Updated: Sep 27, 2025

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K
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

3.0K
  • Implementation of a transfer learning framework to improve performance with limited data.

    • Main Results:

    • The proposed network significantly outperforms state-of-the-art methods in qualitative and quantitative evaluations.
    • Demonstrated substantial improvements in structural similarity (0.7925 to 0.8648) and feature similarity (0.8917 to 0.9283) for smoke removal.
    • Transfer learning approach showed superior performance even with small datasets for target tasks.

    Conclusions:

    • The developed network effectively enhances endoscopic images, addressing key visual challenges.
    • The method shows excellent clinical usefulness and generalizability for smoke removal, light adjustment, and color correction.
    • The physics-driven and transfer learning approaches offer robust solutions for endoscopic image enhancement.