Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Distinguishing Molecular and Histologic Glioblastomas Using Multiparametric MRI-Based Habitat Analysis.

Korean journal of radiology·2026

Same author

Long-term outcomes and late complications of intracranial germinoma: Implications for follow-up policy.

Neuro-oncology advances·2026

Same author

The Limited Role of Hypocortisolism in the Development of Delayed Postoperative Hyponatremia After Pituitary Surgery.

Pituitary·2026

Same author

AOSNP-ADAPTR resource level-based recommendations on practical diagnostic strategies for ependymomas.

Brain pathology (Zurich, Switzerland)·2026

Same author

Comprehensive proteogenomic characterization reveals clinically relevant molecular subtypes associated with medulloblastoma progression.

Experimental & molecular medicine·2026

Same author

Comparative Outcomes of Consolidation Strategies After R-MVP Induction in Primary Diffuse Large B-Cell Lymphoma of the Central Nervous System.

Cancer medicine·2026

Search research articles

Related Experiment Video

Updated: Apr 30, 2026

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Published on: September 13, 2022

Deep Learning for Survival Prediction in Glioblastoma: Time-dependent Model Interpretability Using MRI, Clinical, and

Junhyeok Lee¹, Young Hun Jeon², Joon Jang³

¹Interdisciplinary Programs in Cancer Biology, Seoul National University Graduate School, Seoul, Republic of Korea.

Radiology. Artificial Intelligence

|April 29, 2026

Summary

A new multimodal model integrating MRI, clinical, and molecular data improves glioblastoma survival prediction. This advanced imaging-derived prognostic index offers sustained importance over time.

Keywords:

Brain Brain Stem Central Nervous System Comparative Studies Feature Detection MRI Neuro-Oncology Primary Neoplasms Prognosis Radiology-Pathology Integration Random Survival Forest

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

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

Published on: January 9, 2019

Related Experiment Videos

Last Updated: Apr 30, 2026

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Published on: September 13, 2022

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

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

Published on: January 9, 2019

Area of Science:

Neuro-oncology
Medical Imaging
Artificial Intelligence

Background:

Glioblastoma survival prediction is challenging.
Integrating diverse data types can enhance prognostic accuracy.

Purpose of the Study:

To develop a multimodal model for glioblastoma survival prediction.
To achieve time-dependent interpretability of prognostic factors.

Main Methods:

A deep learning-based prognostic index (DPI) was generated from preoperative multiparametric MRI using a Vision Transformer.
The DPI was integrated with clinical (age, KPS, EOR) and molecular (IDH, MGMT) variables using a random survival forest model.
Model performance was assessed using concordance index (C-index) and interpretability via Survival SHapley Additive Explanations (SurvSHAP(t)).

Main Results:

The multimodal model achieved C-indexes of 0.77 (internal) and 0.73/0.63 (external), outperforming the image-only model.
The imaging-derived DPI was a strong predictor, showing moderate correlations with clinical and molecular variables.
SurvSHAP(t) revealed time-dependent importance for factors like extent of resection and MGMT promoter methylation.

Conclusions:

The multimodal model demonstrates robust performance for glioblastoma survival prediction.
The imaging-derived prognostic index serves as a valuable, complementary biomarker with enduring prognostic significance.