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

SpaDiffHis: Sparse-point Guided Diffusion for Histopathology Image Synthesis with Contrastive Learning.

IEEE journal of biomedical and health informatics·2026
Same author

Integrated Molecular, Genomic, and Clinical Characterization of Pediatric and Adolescent Translocation Renal Cell Carcinoma: A Report from the Children's Oncology Group.

Biomedicines·2026
Same author

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

IEEE access : practical innovations, open solutions·2026
Same author

End-to-End Multimodal Multiple Instance Learning for Cancer Histopathology Classification with Dual-Attention Fusion.

Journal of medical systems·2026
Same author

Pathology Public Datasets for Artificial Intelligence: A Systematic Review.

Journal of imaging informatics in medicine·2026
Same author

AI-Based RGB Image Generation From RG Fundus Images Using Pix2Pix: Validation by Quantitative and Observer-Based Evaluations.

Translational vision science & technology·2026

Related Experiment Video

Updated: Jun 20, 2025

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
06:32

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures

Published on: January 9, 2019

7.8K

Deep learning-based IDH1 gene mutation prediction using histopathological imaging and clinical data.

Riku Nakagaki1, Shyam Sundar Debsarkar2, Hiroharu Kawanaka1

  • 1Graduate School of Engineering, Mie University, 1577 Kurima-machiya, Tsu, Mie 514-8507, Japan.

Computers in Biology and Medicine
|July 22, 2024
PubMed
Summary

This study developed an AI model to predict IDH1 mutations in glioma patients using whole slide images and clinical data. Combining both data types improved prediction accuracy, aiding in disease progression assessment.

Keywords:
Brain gliomaClinical dataDeep learningDigital pathologyFusion modelGene mutationWeakly supervised

More Related Videos

A Protocol for Explant Cultures of IDH1-mutant Diffuse Low-grade Gliomas
06:27

A Protocol for Explant Cultures of IDH1-mutant Diffuse Low-grade Gliomas

Published on: May 9, 2025

302
Primary Orthotopic Glioma Xenografts Recapitulate Infiltrative Growth and Isocitrate Dehydrogenase I Mutation
09:43

Primary Orthotopic Glioma Xenografts Recapitulate Infiltrative Growth and Isocitrate Dehydrogenase I Mutation

Published on: January 14, 2014

8.1K

Related Experiment Videos

Last Updated: Jun 20, 2025

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
06:32

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures

Published on: January 9, 2019

7.8K
A Protocol for Explant Cultures of IDH1-mutant Diffuse Low-grade Gliomas
06:27

A Protocol for Explant Cultures of IDH1-mutant Diffuse Low-grade Gliomas

Published on: May 9, 2025

302
Primary Orthotopic Glioma Xenografts Recapitulate Infiltrative Growth and Isocitrate Dehydrogenase I Mutation
09:43

Primary Orthotopic Glioma Xenografts Recapitulate Infiltrative Growth and Isocitrate Dehydrogenase I Mutation

Published on: January 14, 2014

8.1K

Area of Science:

  • Histopathology
  • Oncology
  • Artificial Intelligence in Medicine

Background:

  • Gliomas are brain tumors classified into astrocytoma, oligodendroglioma (collectively low-grade glioma, LGG), and glioblastoma (GBM).
  • Isocitrate dehydrogenase (IDH) mutations are crucial prognostic indicators in glioma, with IDH-mutated patients generally exhibiting better outcomes.
  • Accurate IDH mutation status is essential for glioma classification and treatment planning.

Purpose of the Study:

  • To develop and evaluate an AI model for classifying the presence or absence of IDH1 mutations in glioma patients.
  • To investigate the combined utility of whole slide images (WSIs) and clinical data for IDH1 mutation prediction.
  • To compare the performance of different deep learning and machine learning models for this classification task.

Main Methods:

  • Utilized a dataset of 546 glioma patients, incorporating hematoxylin and eosin (H&E) stained WSIs and associated clinical data.
  • Employed deep learning models, including attention-based multiple instance learning (ABMIL) for image analysis, and LightGBM for clinical data.
  • Implemented ensemble learning by combining WSI and clinical data models, with hyperparameter optimization to enhance classification accuracy.

Main Results:

  • The WSI model achieved an Area Under the Curve (AUC) of 0.823, while the clinical data model reached an AUC of 0.782.
  • The ensemble model, particularly the MaxViT and LightGBM combination, demonstrated the highest performance with an AUC of 0.852.
  • Integrating both imaging and clinical data significantly improved the overall accuracy of AI-driven IDH1 mutation prediction.

Conclusions:

  • AI models can effectively predict IDH1 mutation status in glioma using WSIs and clinical data.
  • Ensemble learning approaches that combine multi-modal data (imaging and clinical) offer superior predictive performance.
  • This integrated AI approach holds promise for enhancing glioma classification and disease progression assessment.