Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Carbon-Core/Molecular-State-Regulated Red/Blue Dual-Emission Carbon Quantum Dots Covalently Anchored on Polyvinyl Alcohol for Multifunctional Agricultural Films in Greenhouse Potato Production.

Polymers·2026

Same author

Unraveling the Origins and Drivers of Potentially Toxic Elements (PTEs): A Sequential Framework Integrating Receptor Model and Machine Learning.

Toxics·2026

Same author

Disparities in Depression Among Older Asian, Native Hawaiian, and Pacific Islander Patients With Lung Cancer.

Cancer medicine·2026

Same author

Chinese expert consensus on conversion and perioperative therapy of primary liver cancer (2024 edition).

Hepatobiliary surgery and nutrition·2026

Same author

Nanomedicine orchestrated metabolic reprogramming of immune cells in antitumor immunity.

Cancer letters·2026

Same author

Response to Zhao et al, "Comment on 'Nevus-associated acral melanoma has lower risk of recurrence and mortality than de novo acral melanoma'".

Journal of the American Academy of Dermatology·2026

Same journal

The Development Path of Gynecological Cytology after Papanicolaou: from Bethesda to Artificial Intelligence and Personalized Medicine.

Acta cytologica·2026

Same journal

Cytological Features of CIC-rearranged Sarcoma. A Report of 5 New Cases and Review of the Literature.

Acta cytologica·2026

Same journal

Pericardial Fluid Metastatic Tumor Distribution and Fluid Volume Analysis, a 10-Year Institutional Experience.

Acta cytologica·2026

Same journal

The cytopathology of infectious disease: A review.

Acta cytologica·2026

Same journal

Investigation of a storage method for peritoneal and pleural effusion cytology specimens for long-term preservation of antigenicity in immunocytochemical staining.

Acta cytologica·2026

Same journal

Diagnostic Utility of endoscopic crush cytology in gastrointestinal malignancies.

Acta cytologica·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 6, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Developing a Machine Learning Algorithm for Identifying Abnormal Urothelial Cells: A Feasibility Study.

Zhihui Zhang¹, Xinyan Fu², Jiwei Liu³

¹Department of Pathology, Cancer Hospital, Chinese Academy of Medical Sciences (CHCAMS), Beijing, China.

Acta Cytologica

|October 6, 2020

Summary

This summary is machine-generated.

This study shows that the Morphogo machine learning algorithm can identify abnormal urothelial cells in urine cytology slides. Further research is needed to confirm its utility in diagnosing urothelial carcinoma (UC).

Keywords:

Carcinoma Digital imaging Machine learning Urine cytology Urothelial

More Related Videos

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

Published on: January 12, 2017

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Dec 6, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

Published on: January 12, 2017

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Urology
Pathology
Artificial Intelligence

Background:

Urine cytology is crucial for diagnosing urothelial carcinoma (UC) but interpretation can be subjective.
Morphogo, an automated system with a convolutional neural network, was initially developed for bone marrow analysis.
This study explored Morphogo's potential for identifying abnormal urothelial cells in urine cytology.

Purpose of the Study:

To assess the feasibility of using a machine learning algorithm on Morphogo for urine cytology.
To train and validate an algorithm to detect atypical and suspicious urothelial cells.

Main Methods:

A pathologist annotated 1,910 benign and 1,978 abnormal cells from 37 urine cytology slides.
The algorithm was trained and validated on these annotated slides.
A blind test was conducted on 12 unknown urine samples with diverse diagnoses.

Main Results:

The algorithm was trained on 3,888 cells and validated on 27 slides, identifying an average of 7.4 abnormal cells per slide.
In a blind test of 12 cases, Morphogo flagged 6 samples as abnormal, including cases of high-grade and low-grade urothelial carcinoma.
Morphogo correctly identified abnormal cells in 6 out of 12 unknown cases, demonstrating potential in detecting urothelial carcinoma.

Conclusions:

The Morphogo machine learning algorithm shows capability in identifying abnormal urothelial cells.
Further validation with larger datasets is necessary to establish its role in assisting urothelial carcinoma diagnosis.