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

MR-Linac-Based SBRT for Prostate Cancer: Dosimetric Benefits for Urethral Sparing Compared to VMAT and Tomotherapy.

Cancers·2026
Same author

Overall Staging Prediction for Non-Small Cell Lung Cancer (NSCLC): A Local Pilot Study with Artificial Neural Network Approach.

Cancers·2025
Same author

Integrating Demographics and Imaging Features for Various Stages of Dementia Classification: Feed Forward Neural Network Multi-Class Approach.

Biomedicines·2024
Same author

Level of Amyloid-β (Aβ) Binding Leading to Differential Effects on Resting State Functional Connectivity in Major Brain Networks.

Biomedicines·2022
Same author

Radiomics from Various Tumour Volume Sizes for Prognosis Prediction of Head and Neck Squamous Cell Carcinoma: A Voted Ensemble Machine Learning Approach.

Life (Basel, Switzerland)·2022
Same author

Impact of Effective Intravesical Therapies on Quality of Life in Patients with Non-Muscle Invasive Bladder Cancer: A Systematic Review.

International journal of environmental research and public health·2022

Related Experiment Video

Updated: Jul 12, 2025

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

6.0K

AI Deployment on GBM Diagnosis: A Novel Approach to Analyze Histopathological Images Using Image Feature-Based

Eva Y W Cheung1, Ricky W K Wu2, Albert S M Li1,3

  • 1School of Medical and Health Sciences, Tung Wah College, 31 Wylie Road, HoManTin, Hong Kong.

Cancers
|October 28, 2023
PubMed
Summary

This study developed a computer model using histopathology images to diagnose glioblastoma (GBM). The support vector machine (SVM) model achieved 93.5% accuracy, showing potential for clinical use in GBM diagnosis.

Keywords:
GLCMGLRLMartificial intelligence (AI)glioblastoma (GBM)hematoxylin and eosin stained (H&E)histopathologyimage featuresprimary brain tumorsupport vector machine (SVM)whole slide image

More Related Videos

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections
05:45

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections

Published on: July 31, 2017

9.7K
Multimodal Imaging of Stem Cell Implantation in the Central Nervous System of Mice
10:25

Multimodal Imaging of Stem Cell Implantation in the Central Nervous System of Mice

Published on: June 13, 2012

11.2K

Related Experiment Videos

Last Updated: Jul 12, 2025

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

6.0K
Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections
05:45

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections

Published on: July 31, 2017

9.7K
Multimodal Imaging of Stem Cell Implantation in the Central Nervous System of Mice
10:25

Multimodal Imaging of Stem Cell Implantation in the Central Nervous System of Mice

Published on: June 13, 2012

11.2K

Area of Science:

  • Digital pathology
  • Artificial intelligence in oncology
  • Computational imaging

Background:

  • Glioblastoma (GBM) is a common, aggressive brain tumor.
  • Current GBM diagnosis relies on manual analysis of H&E stained slides.
  • Digital pathology and AI offer new avenues for quantitative image analysis.

Purpose of the Study:

  • To develop an image feature-based computer model for GBM diagnosis.
  • To differentiate glioblastoma patients from healthy controls using histopathology whole slide images.
  • To identify key image features for accurate GBM detection.

Main Methods:

  • Utilized two independent cohorts (TCGA-GBM and local hospital data).
  • Extracted 33 image features (GLCM and GLRLM) from H&E slides.
  • Trained and tested five machine learning algorithms (DT, EB, SVM, RF, LM).

Main Results:

  • All models achieved 100% accuracy in training/validation.
  • Identified 15 significant image features (12 GLCM, 3 GLRLM) differentiating GBM from normal tissue.
  • The SVM model demonstrated 93.5% accuracy, 86.95% sensitivity, and 99.73% specificity on an independent cohort.

Conclusions:

  • Identified specific GLCM and GLRLM image features aiding GBM diagnosis.
  • The SVM model shows high accuracy, sensitivity, and specificity for GBM detection.
  • The developed SVM model holds potential for future clinical application in GBM diagnosis.