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

Beyond the 'Pregnancy Black Box': a global roadmap for artificial intelligence-driven pharmacogenomics in maternal-neonatal health.

The pharmacogenomics journal·2026
Same author

The economic imperative of artificial intelligence in maternal and neonatal health: a review of evaluation benefits, frameworks, challenges, future perspectives, and limitations.

Cost effectiveness and resource allocation : C/E·2026
Same author

The strategic trajectory of artificial intelligence in Qatar's healthcare sector: a model for UN Sustainable Development Goal 9.

Frontiers in artificial intelligence·2026
Same author

Integrating pharmaco-multiomics and AI for precision perinatal psychiatry: A call for dynamic dosing.

Asian journal of psychiatry·2026
Same author

Immune checkpoint blockade in cancer: current insights and future horizons.

Discover oncology·2026
Same author

Rates of Cancer, Non-curative Resection, Adverse Event and Surgery After Colonic Endoscopic Submucosal Dissection (ESD)-Results from a Large International Multicenter Study.

Digestive diseases and sciences·2025
Same journal

Blind source separation of nonlinearly mixed plant leaf electrical signals using polynomial-mapped FastICA.

Computers in biology and medicine·2026
Same journal

MISSTE: a multiscale integrative spatial simulator for understanding the mechanisms underlying tissue ecosystems.

Computers in biology and medicine·2026
Same journal

GUSL: A novel and efficient machine learning model for prostate segmentation on MRI.

Computers in biology and medicine·2026
Same journal

Machine Learning-Based single-cell characterization of lipid metabolic reprogramming in prostate cancer.

Computers in biology and medicine·2026
Same journal

Peripheral arterial disease classification using machine learning and multi-point photoplethysmography.

Computers in biology and medicine·2026
Same journal

3D machine learning-based complexity variability and fluidity quantification of preterm and writhing general movements.

Computers in biology and medicine·2026
See all related articles

Related Experiment Video

Updated: Jun 3, 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

6.7K

Colorectal cancer classification using weakly annotated whole slide images: Multiple instance learning optimization

Ahmed Saeed1, Mohamed A Ismail1, Nagia M Ghanem1

  • 1Computer and Systems Engineering Department, Faculty of Engineering, Alexandria University, Alexandria, Egypt.

Computers in Biology and Medicine
|January 11, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces an improved deep learning method for classifying colorectal cancer (CRC) using weakly annotated whole slide images (WSIs). The novel approach enhances computer-aided diagnosis (CAD) system performance, achieving 93.05% accuracy.

Keywords:
Colorectal cancer (CRC)Computational pathology (CPATH)Computer-aided diagnosis (CAD)Deep learning (DL)Multiple instance learning (MIL)Whole slide image (WSI)

More Related Videos

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

1.3K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

13.9K

Related Experiment Videos

Last Updated: Jun 3, 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

6.7K
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

1.3K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

13.9K

Area of Science:

  • Oncology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Colorectal cancer (CRC) is a leading cause of cancer-related deaths, with early detection crucial for effective treatment.
  • Histopathological images are the gold standard for CRC diagnosis, but manual analysis is time-consuming.
  • Deep learning offers potential for developing automated computer-aided diagnosis (CAD) systems for CRC detection.

Purpose of the Study:

  • To develop and evaluate a deep learning-based CAD system for colorectal cancer classification using weakly annotated histopathological whole slide images (WSIs).
  • To enhance the performance of Multiple Instance Learning (MIL) algorithms for WSI-level classification by proposing novel WSI-label prediction functions.
  • To create a computationally efficient dataset representation through advanced preprocessing techniques.

Main Methods:

  • Utilized deep learning techniques for CRC classification on weakly annotated histopathological WSIs.
  • Developed and integrated novel WSI-label prediction functions with the Multiple Instance Learning (MIL) algorithm.
  • Applied efficient preprocessing methods to create a computationally power-efficient dataset.
  • Conducted multiple experiments to optimize the CAD system.

Main Results:

  • Achieved a classification accuracy of 93.05%, a significant improvement over the baseline accuracy of 84.17%.
  • Demonstrated that the proposed method using only weakly annotated WSIs outperformed baseline results that relied on pre-training with strongly annotated data.
  • The integrated WSI-label prediction functions substantially enhanced WSI-level classification performance.

Conclusions:

  • The proposed deep learning approach significantly improves the accuracy of colorectal cancer classification from weakly annotated whole slide images.
  • This method offers a more efficient and effective computer-aided diagnosis (CAD) system for colorectal cancer, outperforming traditional approaches.
  • The findings highlight the potential of leveraging weakly annotated data for robust CRC detection and diagnosis.