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

Genome-wide DNA methylation dynamics and RNA-seq analysis during grape (cv. 'Cabernet Franc') skin coloration.

Genomics·2024
Same author

Delivery Strategies for Colchicine as a Critical Dose Drug: Reducing Toxicity and Enhancing Efficacy.

Pharmaceutics·2024
Same author

Occult urothelial carcinoma with mediastinal metastasis: A case report.

Oncology letters·2024
Same author

Phase Identification and Discovery of an Elusive Polymorph of Drug-Polymer Inclusion Complex Using Automated 3D Electron Diffraction.

Angewandte Chemie (International ed. in English)·2024
Same author

Mediating and moderating effects of authoritative parenting styles on adolescent behavioral problems.

Frontiers in psychology·2024
Same author

A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit.

Computer methods and programs in biomedicine·2024

Related Experiment Video

Updated: Aug 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Local augmentation based consistency learning for semi-supervised pathology image classification.

Lei Su1, Zhi Wang1, Yi Shi1

  • 1School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China.

Computer Methods and Programs in Biomedicine
|March 5, 2023
PubMed
Summary
This summary is machine-generated.

Semi-LAC, a novel semi-supervised method, enhances pathology image classification by using local augmentation and directional consistency loss. This approach reduces annotation costs and improves model performance for accurate diagnoses.

Keywords:
Consistency learningLocal augmentationPathology image classification

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

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

Published on: July 11, 2025

140

Related Experiment Videos

Last Updated: Aug 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

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

Published on: July 11, 2025

140

Area of Science:

  • Digital Pathology
  • Machine Learning
  • Computer-Aided Diagnosis

Background:

  • Supervised pathology image classification requires extensive labeled data, which is costly and time-consuming.
  • Traditional semi-supervised methods struggle with limited augmentation diversity and potential mixing of irrelevant image regions.
  • Existing regularization techniques may inaccurately align features by enforcing suboptimal consistency.

Purpose of the Study:

  • To introduce a novel semi-supervised method, Semi-LAC, for pathology image classification.
  • To address the limitations of existing augmentation and regularization strategies in semi-supervised learning.
  • To improve the efficiency and accuracy of pathology image analysis.

Main Methods:

  • Proposed Semi-LAC method utilizing local augmentation to enhance pathology image diversity without mixing regions.
  • Implemented directional consistency loss to enforce consistency in both features and predictions.
  • Applied the method to pathology image classification tasks.

Main Results:

  • Semi-LAC demonstrated superior performance compared to state-of-the-art methods on Bioimaging2015 and BACH datasets.
  • The local augmentation technique effectively boosted image diversity and avoided region mixing.
  • Directional consistency loss improved the robustness of network representations and prediction accuracy.

Conclusions:

  • Semi-LAC effectively reduces the need for extensive manual annotation in pathology.
  • The method enhances the representational capacity of classification networks for pathology images.
  • Local augmentation and directional consistency loss are key components for improving semi-supervised pathology image classification.