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

First-In-Human [<sup>177</sup>Lu]Lu-FAPI-XT Therapy Combined With Anti-PD-1 Antibody in a Patient With Metastatic Colon Cancer Who Has Progressed on Multiple Prior Lines of Therapy.

JCO precision oncology·2026
Same author

Development and Validation of a Pathomics Model for Prognosis Prediction in Neoadjuvant Therapy-Treated Breast Cancer: A Retrospective, Multicenter Study.

MedComm·2026
Same author

[Optimization Path Selection for the Synergy of "Four Waters" in the Yellow River Basin from a Configurational Perspective].

Huan jing ke xue= Huanjing kexue·2026
Same author

Bioartificial Livers Developed From Gene-Edited Pig Hepatocyte Organoids Improve Amino Acid and Lipid Profiles in the Plasma of Patients With Liver Failure.

MedComm·2026
Same author

GGAs: Regulation of Multiple Sorting Pathways and Potential Association With Human Diseases.

Journal of cellular and molecular medicine·2026
Same author

Deep learning prediction of pathological complete response in breast cancer using Mamba architecture.

NPJ digital medicine·2026

Related Experiment Video

Updated: Oct 17, 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

412

[Automatic Segmentation of Digital Pathology Slides Based on Unsupervised Learning].

Hang-Yu Qin1, Yang Deng1, Yan-Yan Zhou1

  • 1Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, China.

Sichuan Da Xue Xue Bao. Yi Xue Ban = Journal of Sichuan University. Medical Science Edition
|October 8, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces an unsupervised image segmentation method for digital pathology slides, offering an efficient alternative to manual labeling. The novel approach demonstrates faster processing speeds and improved performance in image texture analysis compared to traditional methods.

Keywords:
Convolutional neural networkSuperpixelWhole slide images

More Related Videos

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.0K
Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
09:33

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

8.3K

Related Experiment Videos

Last Updated: Oct 17, 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

412
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.0K
Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
09:33

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

8.3K

Area of Science:

  • Digital Pathology
  • Computational Imaging
  • Machine Learning in Histopathology

Background:

  • Manual labeling of whole slide images (WSIs) is time-consuming and costly.
  • Unsupervised methods are needed to automate segmentation and reduce labeling burden.
  • Existing methods may lack efficiency or struggle with complex image features.

Purpose of the Study:

  • To develop and evaluate an unsupervised image segmentation technique for WSIs.
  • To compare its performance and efficiency against the region adjacency graph merging method.
  • To provide an alternative to manual labeling in digital pathology.

Main Methods:

  • Utilized a dataset of 100 WSIs (HE and Pap stained) including breast, lung, and thyroid tissues.
  • Developed an unsupervised segmentation algorithm combining superpixel and fully convolutional neural network approaches.
  • Assessed segmentation accuracy using under-segmentation error, boundary recall, and mean Intersection-over-Union (mIoU).

Main Results:

  • The unsupervised method achieved an mIoU of 45.06%, outperforming the region adjacency graph merging method (44.81%).
  • Segmentation speed was significantly faster: 0.27s (GPU) and 1.30s (CPU) compared to 10.5s (CPU only).
  • The method showed stable results across different tissue types but had average performance in differentiating inflammation from tumors.

Conclusions:

  • The unsupervised segmentation method yields ideal pixel-level labeling with minimal human interaction.
  • It effectively reduces the cost and effort associated with digital pathology slide data labeling.
  • Offers superior performance in image texture processing and faster execution speed compared to the region adjacency graph merging method.