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

Reliability of Behavioral and fNIRS Neural Responses: Assessments During Posture-Inhibitory Control Dual Tasking.

NeuroSci·2026
Same author

Density-equalized RANDT scan matching with integrated outlier removal and point density uniformity.

PloS one·2026
Same author

Enhancing U-Net for image denoising with bilateral filter noise residue and gradient estimation (BIRUNet).

Scientific reports·2025
Same author

Adaptive spinal cord stimulation improves restless legs syndrome: Case report, literature review, and mechanistic hypothesis.

Sleep medicine·2025
Same author

A comprehensive review on the integration of air quality monitoring systems with hybrid electric vehicles for emission control in smart cities.

The Science of the total environment·2025
Same author

Systematic Review on Minimally Invasive Posterior Sacroiliac Joint Fusion.

Pain practice : the official journal of World Institute of Pain·2025

Related Experiment Video

Updated: Nov 5, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

306

Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images.

Venkatesan Chandran1, M G Sumithra1, Alagar Karthick2

  • 1Department of Electronics and Communication Engineering, KPR Institute of Engineering and Technology, Avinashi road, Coimbatore, 641407 Tamilnadu, India.

Biomed Research International
|May 17, 2021
PubMed
Summary

This study introduces CYENET, a deep learning model for cervical cancer detection using colposcopy images. CYENET significantly improves classification accuracy, offering a more efficient and reliable screening tool compared to traditional methods.

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.6K
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

484

Related Experiment Videos

Last Updated: Nov 5, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

306
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.6K
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

484

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Traditional cervical cancer screening relies on pathologist expertise, leading to potential inaccuracies and diagnostic inefficiencies.
  • Colposcopy is vital for cervical cancer prevention, but increased workload can compromise screening quality.
  • Deep learning, specifically Convolutional Neural Networks (CNNs), offers advanced capabilities for medical image analysis and classification.

Purpose of the Study:

  • To develop and evaluate deep learning models for automated cervical cancer classification from colposcopy images.
  • To compare the performance of a transfer learning approach (VGG19) with a novel CNN architecture (CYENET).
  • To enhance diagnostic accuracy and efficiency in cervical cancer screening.

Main Methods:

  • Two deep learning CNN architectures were proposed: VGG19 utilizing transfer learning (TL) and a newly developed Colposcopy Ensemble Network (CYENET).
  • Both models were trained and evaluated on colposcopy images for cervical cancer classification.
  • Key performance metrics including accuracy, sensitivity, and specificity were estimated.

Main Results:

  • The VGG19 (TL) model achieved a classification accuracy of 73.3% with a moderate kappa score.
  • The proposed CYENET model demonstrated superior performance, achieving high sensitivity (92.4%), specificity (96.2%), and a kappa score of 88%.
  • CYENET's classification accuracy reached 92.3%, representing a significant 19% improvement over the VGG19 (TL) model.

Conclusions:

  • Deep learning models, particularly CYENET, show significant promise for automated cervical cancer detection from colposcopy images.
  • CYENET offers a substantial improvement in diagnostic performance over traditional transfer learning methods, enhancing accuracy and efficiency.
  • The developed CYENET model can serve as a valuable tool to aid pathologists and improve cervical cancer screening outcomes.