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

Enantioselective Radical Cascade Cyclization to Axially Chiral Medium-Sized Lactones.

Angewandte Chemie (International ed. in English)·2026
Same author

(+)-Miliusol suppresses the Warburg effect and induces regulated cell death in triple-negative breast cancer through targeting EIF3D and remodeling cancer metabolism.

Acta pharmaceutica Sinica. B·2026
Same author

6-Methoxyluteolin from the Invasive Plant <i>Tithonia diversifolia</i> Suppresses Melanization and Impairs Epidermal Integrity in <i>Spodoptera litura</i> Larvae.

Insects·2026
Same author

ViT-ConvGAN: a hybrid model for spatiotemporal action recognition using video transformer and 3D CNN.

Scientific reports·2026
Same author

Cassane-Type Diterpenoids From the Seeds of Caesalpinia pulcherrima and Their Cytotoxic Activities.

Chemistry & biodiversity·2026
Same author

Multi-region proteomic mapping identifies FTL1 and SERPINA3K as protective factors in cardiac aging.

Cell death & disease·2026

Related Experiment Video

Updated: Oct 23, 2025

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

433

Computer-aided diagnostic system based on deep learning for classifying colposcopy images.

Lu Liu1, Ying Wang2, Xiaoli Liu1

  • 1Department of Obstetrics and Gynecology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.

Annals of Translational Medicine
|August 23, 2021
PubMed
Summary

A new deep learning model aids in cervical cancer detection using colposcopy images. This AI-powered system shows diagnostic performance comparable to experienced specialists, improving accuracy in classifying cervical lesions.

Keywords:
Computer-aided diagnosis (CAD)ResNetcervical lesioncolposcopy

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
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

Related Experiment Videos

Last Updated: Oct 23, 2025

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

433
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
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

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Oncology

Background:

  • Colposcopy is crucial for cervical cancer detection but requires expert interpretation.
  • Developing nations face a shortage of skilled colposcopists, impacting diagnostic accuracy.
  • Artificial intelligence (AI) offers potential solutions for computer-aided diagnosis (CAD) in healthcare.

Purpose of the Study:

  • To develop and validate a deep learning-based CAD model for classifying cervical lesions from colposcopy images.
  • To assess the model's diagnostic performance in differentiating normal cervix from low-grade squamous intraepithelial lesions or worse (LSIL+) and high-grade squamous intraepithelial lesions (HSIL).

Main Methods:

  • A deep learning model (ResNet) was trained on 15,276 colposcopy images from 7,530 patients.
  • A combined model integrated ResNet probabilities with clinical features.
  • Performance was evaluated by comparing the model's diagnoses against senior and junior colposcopists' assessments on a test set.

Main Results:

  • The combined model outperformed ResNet alone in classifying cervical lesions.
  • For Normal Cervix (NC) vs. LSIL+, the model achieved an AUC of 0.953, accuracy 0.886, sensitivity 0.932, specificity 0.846.
  • For HSIL- vs. HSIL+, the model achieved an AUC of 0.900, accuracy 0.807, sensitivity 0.823, specificity 0.800.

Conclusions:

  • The deep learning-based CAD system demonstrates strong performance in classifying cervical lesions.
  • The AI model provides an objective diagnostic aid for colposcopists.
  • The system's diagnostic capabilities are comparable to experienced specialists, offering potential to improve cervical cancer screening.