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

Cervical and Cesarean Scar Pregnancy in One Patient: A Sequential Case with Literature Review.

Journal of clinical medicine·2026
Same author

Comparative Efficacy of Treatment Methods and Risk Factors for Treatment Failure in High-Grade Vaginal Intraepithelial Neoplasia: A Systematic Review and Meta-Analysis.

Cancers·2026
Same author

Accuracy of Blood Loss Estimation and Identification of Factors Contributing to Early Postpartum Hemorrhage Following Vaginal Delivery.

Journal of clinical medicine·2026
Same author

A Role of the Lower Genital Tract Microbiome in Promoting Cervical Intraepithelial Neoplasia: A Premalignant Precursor of Cervical Cancer-A Literature Review.

Viruses·2026
Same author

Exploring the Regulatory Function of NGAL in MMP-9 Complexes.

Computational and structural biotechnology journal·2026
Same author

Pregabalin as a co-analgesic in patients undergoing laparoscopic sleeve gastrectomy: a double-blind, randomized, prospective clinical trial.

Scientific reports·2026

Related Experiment Video

Updated: May 26, 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

Artificial Intelligence-Assisted Colposcopy: Deep Learning Multi-Class Segmentation of Anatomical Structures and

Marcin Jurczak1, Łukasz Charzewski1, Beata Goźlińska1

  • 1Proacta SA, Srebrna 16, 00-810 Warsaw, Poland.

Cancers
|May 13, 2026
PubMed
Summary

Deep learning models like YOLOv11 and RF-DETR can segment colposcopy images for cervical precancer screening. RF-DETR excels at complex findings, while YOLOv11 is more stable, aiding computer-aided diagnosis.

Keywords:
AIcolposcopycomputer visiondeep learningprecancer screeningsemantic segmentation

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: May 26, 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

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Gynecology

Background:

  • Accurate colposcopy is vital for cervical precancer detection but relies on subjective interpretation.
  • Artificial intelligence (AI) and deep learning offer automated image analysis for improved screening.
  • Limited interpretability of AI models hinders clinical adoption in gynecology.

Purpose of the Study:

  • To compare the diagnostic performance of YOLOv11 and RF-DETR for colposcopy image segmentation.
  • To quantify the strengths of different AI architectures in analyzing colposcopic images.
  • To evaluate AI's potential for computer-aided decision support in cervical precancer screening.

Main Methods:

  • Comparative analysis of YOLOv11 (convolutional neural network) and RF-DETR (transformer-based) architectures.
  • Training models on a custom dataset of expert-annotated digital colposcopic images.
  • Segmentation task involving 10 distinct classes, including anatomical structures, instruments, and colposcopic findings.

Main Results:

  • YOLOv11 demonstrated superior performance in segmenting anatomical structures.
  • RF-DETR achieved higher scores for segmenting colposcopy findings, indicating better performance on nuanced details.
  • Transformer architecture showed superiority in segmenting clinically relevant, complex findings.

Conclusions:

  • Both YOLOv11 and RF-DETR effectively segment colposcopic images, with performance varying by class characteristics.
  • Class imbalance and small/underrepresented findings pose challenges.
  • YOLOv11 offers stability and efficiency; RF-DETR excels in complex cases, providing a framework for AI-assisted colposcopy.