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

Whole-spine CT predictors of lumbar surgery in patients with ossification of the posterior longitudinal ligament.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

Three-dimensional observation of the muscle-tendon integration process in mouse embryos.

Developmental dynamics : an official publication of the American Association of Anatomists·2026
Same author

Skeletal muscle-specific deficiency of Rab geranylgeranyl transferase beta subunit induces myopathy and exacerbates the symptoms caused by HMG-CoA reductase deficiency in mice.

Molecular metabolism·2026
Same author

Absence of bone marrow edema on early postoperative MRI predicts fusion outcome after single-level lumbar interbody fusion.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

The development of Breast Apocrine Carcinoma (BAC) score that distinguishes breast and cutaneous apocrine carcinomas.

Research square·2026
Same author

UNC45B Reduction With Aging: A Myofiber-Intrinsic Promoting Factor for Sarcopenia.

Aging cell·2026

Related Experiment Video

Updated: Nov 1, 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

472

Urine cell image recognition using a deep-learning model for an automated slide evaluation system.

Masatomo Kaneko1, Keisuke Tsuji1, Keiichi Masuda2

  • 1Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.

BJU International
|June 18, 2021
PubMed
Summary

This study developed an artificial intelligence (AI) system for urine cytology, achieving over 90% accuracy in classifying cell subtypes. The AI system demonstrated superior diagnostic accuracy for malignancy compared to human cytotechnologists.

Keywords:
artificial intelligencecomputer-assisted image recognitiondeep learningurine cytologyurothelial carcinoma

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Related Experiment Videos

Last Updated: Nov 1, 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

472
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Area of Science:

  • Urology
  • Oncology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Urine cytology is crucial for diagnosing urothelial cancer.
  • Accurate classification of urine cells is essential for patient management.
  • Developing AI tools can enhance diagnostic accuracy and efficiency.

Purpose of the Study:

  • To develop and validate an artificial intelligence (AI) classification system for urine cytology.
  • To utilize a convolutional neural network (CNN) for classifying urine cell images as benign or malignant.
  • To compare the AI system's performance against human cytotechnologists.

Main Methods:

  • Collected 195 urine cytology slides from patients with confirmed urothelial cancer.
  • Selected 4637 cell images, labeled by certified cytotechnologists, for AI training and validation.
  • Employed customized CutMix (CircleCut) and Refined Data Augmentation for image processing.
  • Utilized EfficientNet B6 and Arcface architecture for the AI model.
  • Evaluated performance using fivefold cross-validation and ROC analysis.

Main Results:

  • The AI system achieved an area under the ROC curve of 0.99.
  • Highest accuracy was 95%, with sensitivity of 97% and specificity of 95%.
  • AI performance surpassed the highest level of cytotechnologists in binary classification (Pr(Y > X) = 0.95).
  • AI achieved >90% accuracy across all cell subtypes and 89-97% in subgroup analyses.

Conclusions:

  • A novel AI classification system for urine cytology was successfully developed.
  • The AI system demonstrated high accuracy (>90%) for all cell subtypes.
  • The AI system achieved superior diagnostic accuracy for malignancy compared to human experts.