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: May 20, 2026

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation
11:38

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation

Published on: October 4, 2024

Diverse image generation with diffusion models and cross class label learning for polyp classification.

Vanshali Sharma1, Debesh Jha2, M K Bhuyan3

  • 1Department of Computer Science & Engineering, Indian Institute of Technology Guwahati, Guwahati, 781039, India. vanshalisharma@alumni.iitg.ac.in.

Scientific Reports
|May 18, 2026
PubMed
Summary

Related Concept Videos

Polymer Classification: Stereospecificity01:26

Polymer Classification: Stereospecificity

Polymerization generates chiral centers along the entire backbone of a polymer chain. Accordingly, the stereochemistry of the substituent group has a significant effect on polymer properties. Polymers formed from monosubstituted alkene monomers feature chiral carbons at every alternate position in the polymer backbone. Relative to the predominant orientation of substituents at the adjacent chiral carbons, the polymer can exist in three different configurations: isotactic, syndiotactic, and...

You might also read

Related Articles

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

Sort by
Same author

REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis.

IEEE transactions on medical imaging·2026
Same author

Multimodal AI for early prediction of adverse clinical outcomes in acute pancreatitis.

Abdominal radiology (New York)·2026
Same author

A Predictive MRI Radiomics Model for Histologic Differentiation in Soft Tissue Sarcomas.

Cancers·2026
Same author

Evaluating the Predictive Value of Post-Treatment Superb Microvascular Imaging for Complete Response to Neoadjuvant Chemotherapy in Invasive Breast Cancer.

Bioengineering (Basel, Switzerland)·2026
Same author

Correction: Cicek et al. A New Risk Prediction Model for the Assessment of Myocardial Injury in Elderly Patients Undergoing Non-Elective Surgery. <i>J. Cardiovasc. Dev. Dis.</i> 2025, <i>12</i>, 6.

Journal of cardiovascular development and disease·2026
Same author

Uncertainty-Aware Explainable AI for Pancreatic Cysts: Identifying Deep Learning Vulnerabilities and Ensuring Safe Clinical Triage in IPMN Management.

Research square·2026
See all related articles
This summary is machine-generated.

This study introduces PathoPolyp-Diff, a novel generative AI model for creating diverse colonoscopy images. The model enhances colorectal cancer polyp classification by generating synthetic data, improving diagnostic accuracy with limited labels.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Gastroenterology

Background:

  • Colorectal cancer (CRC) diagnosis relies on accurate pathologic classification of colonic polyps.
  • Current polyp classification methods often use single imaging modalities (NBI, WLI), facing limitations due to data scarcity and performance constraints.
  • Generative AI offers potential for data augmentation, but text-controlled generation and cross-class label learning are underexplored in colonoscopy.

Purpose of the Study:

  • To develop a novel text-controlled generative model (PathoPolyp-Diff) for creating diverse synthetic colonoscopy images.
  • To address the challenge of limited annotated data in colonoscopy by enabling text-controlled image generation with varied pathologies and imaging qualities.
  • To improve downstream diagnostic models for polyp classification through effective data augmentation.

Related Experiment Videos

Last Updated: May 20, 2026

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation
11:38

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation

Published on: October 4, 2024

Main Methods:

  • Developed PathoPolyp-Diff, a two-stage generative model for colonoscopy images.
  • Implemented text prompts and cross-class label learning to generate diverse synthetic polyp images.
  • Validated the model's effectiveness by augmenting polyp classification tasks (adenomatous/hyperplastic) using NBI and WLI modalities.

Main Results:

  • Synthetic images generated by PathoPolyp-Diff improved polyp classification balanced accuracy by up to 7.91% on a public dataset.
  • Cross-class label learning significantly enhanced video-level polyp classification accuracy by up to 18.33%.
  • The model successfully generated diverse images controlled by text prompts, pathology, modality, and quality.

Conclusions:

  • PathoPolyp-Diff effectively generates diverse, text-controlled synthetic colonoscopy images for data augmentation.
  • The approach significantly enhances downstream diagnostic models for colorectal cancer polyp classification.
  • Cross-class label learning is a valuable technique for improving classification performance with limited annotated data.