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

Pathogen-specific host responses define distinct pneumonia endotypes in the human lung.

bioRxiv : the preprint server for biology·2026
Same author

In silico perturbations provide multivariate interpretability in predicting post-lung transplant outcomes.

Scientific reports·2026
Same author

Multi-modal image analysis for large-scale cancer tissue studies within IMMUcan.

Cell reports methods·2025
Same author

AI-Driven Antimicrobial Peptide Discovery: Mining and Generation.

Accounts of chemical research·2025
Same author

Author Correction: Integrative spatial and genomic analysis of tumor heterogeneity with Tumoroscope.

Nature communications·2025
Same author

CaClust: linking genotype to transcriptional heterogeneity of follicular lymphoma using BCR and exomic variants.

Genome biology·2024

Related Experiment Video

Updated: Jan 6, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning.

Alicja Rączkowska1, Marcin Możejko1, Joanna Zambonelli2

  • 1Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland.

Scientific Reports
|October 6, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces an Accurate, Reliable, and Active (ARA) framework using Bayesian Convolutional Neural Networks (ARA-CNN) for colorectal cancer histopathology image analysis. The ARA-CNN model enhances accuracy and learning efficiency, while providing uncertainty measures for improved diagnostics.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
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

738

Related Experiment Videos

Last Updated: Jan 6, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
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

738

Area of Science:

  • Digital pathology
  • Computational oncology
  • Machine learning in medicine

Background:

  • Histopathological image analysis is crucial for clinical diagnosis but is labor-intensive.
  • Accurate and reliable machine learning models are needed for automated analysis.
  • Training these models requires extensive, manually annotated datasets, which are costly and time-consuming.

Purpose of the Study:

  • To develop an Accurate, Reliable, and Active (ARA) image classification framework for histopathological images.
  • To introduce a Bayesian Convolutional Neural Network (ARA-CNN) for colorectal cancer classification.
  • To improve the efficiency of training machine learning models by minimizing data requirements.

Main Methods:

  • Development of a novel Bayesian Convolutional Neural Network (ARA-CNN).
  • Implementation of an active learning workflow utilizing uncertainty measures.
  • Application of variational dropout-based entropy for uncertainty quantification.
  • Segmentation of whole-slide images and computation of spatial statistics.

Main Results:

  • The ARA-CNN model achieved exceptional classification accuracy on colorectal cancer histopathological images, outperforming existing models.
  • Uncertainty measures effectively identified mislabelled training samples.
  • The active learning workflow, incorporating uncertainty, accelerated the training process by approximately 45%.
  • Successful segmentation of whole-slide images and computation of relevant spatial statistics.

Conclusions:

  • The proposed ARA framework and ARA-CNN offer an accurate and reliable approach to histopathological image analysis.
  • Uncertainty quantification is valuable for improving training data quality and enabling efficient active learning.
  • This method significantly enhances the efficiency of machine learning model training in digital pathology.
  • The model's capabilities extend to image segmentation and spatial statistics for comprehensive tissue analysis.