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

Effect of H<sub>2</sub> treatment in a mouse model of rheumatoid arthritis-associated interstitial lung disease.

Journal of cellular and molecular medicine·2019
Same author

Group 1 innate lymphoid cells are involved in the progression of experimental anti-glomerular basement membrane glomerulonephritis and are regulated by peroxisome proliferator-activated receptor α.

Kidney international·2019
Same author

A case of membranous nephropathy diagnosed with lupus nephritis 11 years after onset.

CEN case reports·2019
Same author

Preparation of hybrid porcine thymus containing non-human primate thymic epithelial cells in miniature swine.

Xenotransplantation·2019
Same author

β<sub>2</sub>-Adrenergic receptor expression is associated with biomarkers of tumor immunity and predicts poor prognosis in estrogen receptor-negative breast cancer.

Breast cancer research and treatment·2019
Same author

Melanocyte lineage cells in piebald skin.

The Journal of dermatology·2019

Related Experiment Video

Updated: Mar 13, 2026

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

1.3K

Development and Clinical Application of a Deep Learning-Based AI Support Model for Endometrial Cancer Cytology.

Ichito Shimokawa1,2, Mika Terasaki1, Shun Tanaka1,3

  • 1Department of Analytic Human Pathology, Nippon Medical School.

Journal of Nippon Medical School = Nippon Ika Daigaku Zasshi
|March 11, 2026
PubMed
Summary

An improved AI model for endometrial cytology demonstrates high accuracy, assisting pathologists with diagnoses regardless of case difficulty. This AI system offers consistent performance and enhanced interpretability for clinical applications.

Keywords:
YOLO networksartificial intelligencecytologydeep learning-based object detection algorithmsendometrial cancer

More Related Videos

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

1.9K
Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy
05:52

Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy

Published on: August 19, 2021

13.7K

Related Experiment Videos

Last Updated: Mar 13, 2026

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

1.3K
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

1.9K
Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy
05:52

Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy

Published on: August 19, 2021

13.7K

Area of Science:

  • Artificial Intelligence in Pathology
  • Deep Learning for Medical Diagnostics
  • Endometrial Cytology Analysis

Background:

  • Rising endometrial cancer rates globally necessitate advanced diagnostic tools.
  • Shortages in pathology and cytotechnology professionals increase diagnostic workload.
  • AI-driven deep learning models offer potential solutions for diagnostic support.

Purpose of the Study:

  • To evaluate the clinical applicability of an enhanced AI-supported endometrial cytology model.
  • To compare the performance of different deep learning architectures (YOLOv5x, YOLOv7).
  • To assess AI diagnostic consistency across varying difficulty levels and enhance model interpretability.

Main Methods:

  • Utilized YOLOv5x and YOLOv7 models for cell cluster detection, comparing datasets with single and dual annotations.
  • Employed the Two One-Sided Tests (TOST) procedure to correlate AI accuracy with human-perceived diagnostic difficulty.
  • Applied Gradient-weighted Class Activation Mapping (Grad-CAM) for AI model interpretability.

Main Results:

  • The YOLOv5x model with comprehensive annotations achieved the highest malignant mean average precision (mAP) of 0.798.
  • AI diagnostic accuracy remained consistent regardless of perceived case difficulty, as shown by TOST analysis.
  • Grad-CAM visualizations revealed AI decision-making processes, sometimes highlighting different regions than human diagnosticians.

Conclusions:

  • The AI support model exhibits high and consistent accuracy in endometrial cytological analysis.
  • AI interpretability was enhanced via Grad-CAM, showing unique diagnostic patterns.
  • The study progresses a real-time, microscope-integrated AI system towards clinical adoption.