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

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy01:26

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

80
This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
80
Endoscopic Procedures II: Colonoscopy01:25

Endoscopic Procedures II: Colonoscopy

89
The colon, or large intestine, is the final segment of the digestive system. Its primary functions include absorbing water and vitamins produced by gut bacteria and transforming waste from liquid to solid to form stool. In adults, the large intestine is approximately 5 feet long and consists of four main sections:
89

You might also read

Related Articles

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

Sort by
Same author

Diagnostic Accuracy of Optical Endoscopic Evaluation and EUS for Differentiating T1a and T1b Barrett's Adenocarcinoma: A Systematic Review and Meta-Analysis.

Digestive diseases and sciences·2026
Same author

Sodium Alginate-Based Submucosal Lifting Hydrogel for Endoscopic Mucosal Resection and Endoscopic Submucosal Dissection.

Advanced healthcare materials·2026
Same author

LOCAL RECURRENCE AFTER COLORECTAL ENDOSCOPIC SUBMUCOSAL DISSECTION: A LARGE INTERNATIONAL WESTERN MULTICENTER STUDY.

Gastrointestinal endoscopy·2026
Same author

Adverse events associated with endoscopic retrograde cholangiopancreatography (ERCP) and ERCP-related procedures.

Gastrointestinal endoscopy·2026
Same author

Chromatix: a differentiable, GPU-accelerated wave-optics library.

Nature methods·2026
Same author

American Society for Gastrointestinal Endoscopy guideline on endoscopic management of benign and malignant colonic strictures.

Gastrointestinal endoscopy·2026

Related Experiment Video

Updated: Jun 27, 2025

Modeling Colitis-Associated Cancer with Azoxymethane AOM and Dextran Sulfate Sodium DSS
12:37

Modeling Colitis-Associated Cancer with Azoxymethane AOM and Dextran Sulfate Sodium DSS

Published on: September 11, 2012

46.9K

GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification.

Mayank V Golhar, Taylor L Bobrow, Saowanee Ngamruengphong

    IEEE Journal of Biomedical and Health Informatics
    |May 7, 2024
    PubMed
    Summary

    Synthetic images generated via Generative Adversarial Network (GAN) inversion improve deep learning models for colonoscopy polyp classification. This data augmentation technique enhances polyp detection performance and generalizability on unseen data.

    More Related Videos

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.3K
    Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
    15:49

    Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

    Published on: October 16, 2013

    31.8K

    Related Experiment Videos

    Last Updated: Jun 27, 2025

    Modeling Colitis-Associated Cancer with Azoxymethane AOM and Dextran Sulfate Sodium DSS
    12:37

    Modeling Colitis-Associated Cancer with Azoxymethane AOM and Dextran Sulfate Sodium DSS

    Published on: September 11, 2012

    46.9K
    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.3K
    Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
    15:49

    Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

    Published on: October 16, 2013

    31.8K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Computer Vision

    Background:

    • Deep learning models for medical imaging, particularly colonoscopy lesion classification, face a significant challenge due to the scarcity of annotated data.
    • Effective data augmentation is crucial to overcome data limitations and improve the robustness of these models.

    Purpose of the Study:

    • To investigate the efficacy of synthetic colonoscopy images, generated through Generative Adversarial Network (GAN) inversion, as a data augmentation strategy for improving deep learning-based polyp classification.
    • To explore GAN inversion for creating diverse synthetic data, including modality translation and lesion interpolation, to enhance training datasets.

    Main Methods:

    • Utilized GAN inversion to map image pairs to a disentangled latent space, enabling manipulation for synthetic image generation while preserving labels.
    • Performed image modality translation (style transfer) between white light and narrow-band imaging (NBI) using GAN inversion.
    • Generated realistic synthetic lesion images by interpolating latent representations of original training images to increase shape variability.

    Main Results:

    • GAN inversion-based data augmentation improved polyp classification performance by 2.7% in F1-score and 4.9% in sensitivity compared to other methods.
    • Testing on out-of-domain data showed improvements of 2.9% in F1-score and 2.7% in sensitivity, demonstrating strong domain generalizability.
    • The proposed method outperformed existing colonoscopy data augmentation techniques without requiring retraining of multiple generative models.

    Conclusions:

    • Generative Adversarial Network inversion is a powerful technique for generating effective synthetic data for colonoscopy lesion classification, significantly boosting deep learning model performance.
    • This approach enhances model robustness and generalizability by leveraging diverse data augmentation strategies, addressing the critical issue of limited annotated medical imaging data.
    • The method's efficiency and ability to utilize information from varied datasets make it a valuable tool for advancing AI in medical diagnostics.