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

Prevalence, detection, and trajectory of combined pulmonary fibrosis and emphysema.

Chest·2026
Same author

TROP2 immunoreactivity in pulmonary large cell neuroendocrine carcinoma.

Histopathology·2026
Same author

Germline CDK12 variants in aggressive prostate cancer.

Cancer discovery·2026
Same author

Programs for responding after patients are harmed by their healthcare: A Making Healthcare Safer IV rapid review.

Journal of patient safety and risk management·2026
Same author

Automated H-Scoring in Muscle-Invasive Bladder Cancer IHC: An Internal Validation Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Clinical and Radiologic Characteristics of Familial Pulmonary Fibrosis.

Annals of the American Thoracic Society·2026

Related Experiment Video

Updated: Jun 20, 2025

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

6.8K

Learning generalizable AI models for multi-center histopathology image classification.

Maryam Asadi-Aghbolaghi1, Amirali Darbandsari2, Allen Zhang3,4

  • 1School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada.

NPJ Precision Oncology
|July 19, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces Adversarial Fourier-based Domain Adaptation (AIDA) to improve artificial intelligence (AI) in multi-center cancer diagnosis. AIDA enhances deep learning model generalization for more accurate histopathology slide analysis.

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

374

Related Experiment Videos

Last Updated: Jun 20, 2025

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

6.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

374

Area of Science:

  • Digital pathology
  • Computational oncology
  • Machine learning in medicine

Background:

  • Histopathology slide analysis is crucial for cancer diagnosis.
  • Artificial intelligence (AI) offers potential for improved accuracy and efficiency in pathology.
  • Generalizing deep learning models across multiple centers is essential due to data variations.

Purpose of the Study:

  • To develop a novel method for generalizing deep learning models for multi-center histopathology data.
  • To address the limitations of existing domain adaptation techniques in AI-powered pathology.
  • To improve the performance and reliability of AI in classifying cancer subtypes from diverse datasets.

Main Methods:

  • Proposed Adversarial Fourier-based Domain Adaptation (AIDA) leveraging Fourier transform properties.
  • Applied AIDA to multi-center datasets for ovarian, pleural, bladder, and breast cancers.
  • Compared AIDA against baseline, color augmentation, normalization, and standard Adversarial Domain Adaptation (ADA).

Main Results:

  • AIDA significantly improved classification performance in the target domain across four cancer types.
  • The proposed method outperformed baseline, color augmentation, normalization, and ADA techniques.
  • Pathologist reviews confirmed AIDA's ability to identify histotype-specific features.

Conclusions:

  • AIDA effectively addresses generalization challenges in deep learning for multi-center histopathology.
  • The approach shows significant potential for enhancing AI diagnostic tools in clinical pathology.
  • AIDA offers a promising solution for robust and accurate AI-driven cancer subtyping.