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

Risk of High-Grade Cervical Intraepithelial Neoplasia Using human Papillomavirus Extended Genotyping in Chinese Women With Normal Cervical Cytology: A Population-Based Screening Cohort.

Journal of medical virology·2026
Same author

Risk of 3-Year Cytological Progression by Baseline HPV Status Among Women With Normal Cytology: A Multicenter Cohort Study.

Cancer medicine·2026
Same author

HPV vaccine awareness and uptake among women attending cervical screening in health-resource-limited areas of China: A multicenter cross-sectional study.

Human vaccines & immunotherapeutics·2026
Same author

Temporal trends in cervical cancer incidence and mortality in economically emerging countries, 1992-2021: an age-period-cohort analysis.

BMJ global health·2026
Same author

Minimal benefit of co-testing over HPV primary screening with cytology triage from resource-limited settings in China.

Communications medicine·2026
Same author

HPV testing with 16/18 genotyping for risk stratification among women with normal cytology: a multicenter prospective cohort study from China.

Journal of clinical microbiology·2026
Same journal

Predictors of Telehealth Use Among Cancer Survivors: Retrospective Study.

JMIR cancer·2026
Same journal

Predicting Overall Survival in Patients With Multiple Primary Lung Cancer: Nomogram Development and Validation Study.

JMIR cancer·2026
Same journal

Large Language Models for Breast and Cervical Cancers Communication: Mixed Methods Evaluation Study Assessing Linguistic Quality, Safety, and Accessibility.

JMIR cancer·2026
Same journal

Multi-Turn LLM-Based Conversational Agents for Patients with Cancer and Caregivers: A Scoping Review.

JMIR cancer·2026
Same journal

Digital Intervention for Electronic Patient-Reported Outcomes in Advanced Cancer: Mixed Methods Study.

JMIR cancer·2026
Same journal

Online Intervention on Lung Cancer Screening Among High-Risk Individuals: Pilot Intervention Study.

JMIR cancer·2026
See all related articles

Related Experiment Video

Updated: May 16, 2025

Chromogenic In Situ Hybridization as a Tool for HPV-Related Head and Neck Cancer Diagnosis
06:57

Chromogenic In Situ Hybridization as a Tool for HPV-Related Head and Neck Cancer Diagnosis

Published on: June 14, 2019

10.3K

AI-Based Identification Method for Cervical Transformation Zone Within Digital Colposcopy: Development and

Tong Wu1, Yuting Wang1, Xiaoli Cui2

  • 1School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

JMIR Cancer
|March 31, 2025
PubMed
Summary
This summary is machine-generated.

An artificial intelligence (AI) system accurately identifies cervical transformation zone (TZ) types and locations from colposcopy images. This AI tool assists clinicians in precise cervical cancer screening, improving early detection and patient outcomes.

Keywords:
AIartificial intelligencecervical cancer screeningdiagnosis and early treatmentlightweight neural networktransformation zone

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.1K

Related Experiment Videos

Last Updated: May 16, 2025

Chromogenic In Situ Hybridization as a Tool for HPV-Related Head and Neck Cancer Diagnosis
06:57

Chromogenic In Situ Hybridization as a Tool for HPV-Related Head and Neck Cancer Diagnosis

Published on: June 14, 2019

10.3K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.1K

Area of Science:

  • Gynecology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Cervical cancer is a major health concern in low- and middle-income countries, necessitating early detection.
  • Colposcopy is crucial for identifying precancerous cervical lesions, but inexperienced practitioners may struggle with transformation zone (TZ) identification.
  • Accurate identification of TZ type and location is vital for effective cervical cancer prevention.

Purpose of the Study:

  • To develop and evaluate an artificial intelligence (AI) method for precise identification of cervical transformation zone (TZ) types and locations.
  • To enhance colposcopy examinations through AI-assisted TZ identification.
  • To assess the clinical applicability of an AI system for TZ classification and segmentation.

Main Methods:

  • Retrospective collection of anonymized data from 3616 women undergoing colposcopy across 6 Chinese tertiary hospitals (2019-2021).
  • Development of a lightweight neural network with multiscale feature enhancement for classifying 3 TZ types, using FastSAM for TZ segmentation.
  • Validation of model performance on an independent external dataset of 1335 cases, evaluating accuracy, precision, recall, sensitivity, and specificity.

Main Results:

  • The AI model achieved 83.97% classification accuracy on the test set, with high average precision for TZ types 1, 2, and 3 (91.84%, 89.06%, 95.62%).
  • The TZ segmentation model demonstrated a recall of 0.78 and mean average precision of 0.75.
  • External validation showed strong performance with sensitivities of 0.78-0.81 and specificities of 0.83-0.94 for TZ types 1, 2, and 3.

Conclusions:

  • The developed AI system accurately classifies cervical TZ types and delineates their locations using multicenter colposcopic images.
  • The AI model shows significant potential for accurate TZ type prediction and region identification.
  • This AI tool serves as a valuable assistant for improving the precision of colposcopic examinations in clinical practice.