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

How to benchmark medical AI agents.

PLoS medicine·2026
Same authorSame journal

AI-based selection of tumor regions for genomic profiling in neuropathology.

Neuro-oncology advances·2026
Same author

Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction.

Brain informatics·2026
Same author

[Vaccination of immunocompromised individuals: Expert opinion - update 2026].

Wiener klinische Wochenschrift·2026
Same author

Established machine learning matches tabular foundation models in clinical predictions.

BMC medical informatics and decision making·2026
Same author

Clinical decision support in hematological malignancies using a case-grounded AI agent.

Nature medicine·2026

Related Experiment Video

Updated: Jul 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Direct image to subtype prediction for brain tumors using deep learning.

Katherine J Hewitt1,2, Chiara M L Löffler1,2,3, Hannah Sophie Muti2,4

  • 1Department of Medicine III, University Hospital RWTH Aachen, Aachen, North Rhine-Westphalia, Germany.

Neuro-Oncology Advances
|December 18, 2023
PubMed
Summary

Deep learning models can predict key molecular alterations and World Health Organization (WHO) brain tumor subtypes directly from routine histopathology slides, aiding diagnosis where molecular testing is limited.

Keywords:
IDHadult-type diffuse gliomasdeep learningmolecular signaturessubtype

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

8.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

Related Experiment Videos

Last Updated: Jul 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
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

8.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

Area of Science:

  • Computational pathology
  • Artificial intelligence in oncology
  • Neuro-oncology

Background:

  • The 2021 World Health Organization (WHO) classification for brain tumors integrates histopathological and molecular data.
  • Deep learning (DL) shows promise in predicting molecular alterations from solid tumor histopathology.
  • Accurate brain tumor subtyping relies on both histological and molecular features.

Purpose of the Study:

  • To investigate the capability of DL to predict molecular alterations and WHO brain tumor subtypes from H&E-stained histopathology slides.
  • To validate DL model performance on independent patient cohorts.

Main Methods:

  • Weakly supervised deep learning (DL) applied to three large brain tumor cohorts (N=2845 patients).
  • Histopathology slides were used as input for DL model training and validation.

Main Results:

  • DL accurately predicted IDH mutation (AUROC 0.95), ATRX loss (AUROC 0.90), and 1p19q codeletion (AUROC 0.80) in the training cohort.
  • External validation confirmed high predictive performance: IDH (AUROC 0.90), ATRX (AUROC 0.79), and 1p19q codeletion (AUROC 0.87).

Conclusions:

  • DL models can reliably predict critical molecular alterations and WHO brain tumor subtypes from routine histology.
  • These DL-based approaches may enhance diagnostic workflows, especially when advanced molecular testing is unavailable.