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 Experiment Video

Updated: Mar 19, 2026

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis
06:48

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis

Published on: May 31, 2020

6.4K

Enhanced Glioma Genotype Prediction Using CEST MRI With Full Z-Spectrum Input, Pixel-Level Learning, and Majority

Zhekai Chen1,2, Jue Lu1, Xinli Zhang1

  • 1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.

NMR in Biomedicine
|March 18, 2026
PubMed
Summary

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

Characterizing Metabolic and Compositional Heterogeneity of Calf Muscle Using CEST MRI at 3 T.

NMR in biomedicine·2026
Same author

Noninvasive Mapping of Creatine Kinase Metabolism in Human Muscle Using pH-Insensitive PCrCEST MRI at 3 and 5 T.

NMR in biomedicine·2026
Same author

In vivo imaging of glycogen in human muscle.

Nature communications·2024
Same author

Accelerating multipool CEST MRI of Parkinson's disease using deep learning-based Z-spectral compressed sensing.

Magnetic resonance in medicine·2024
Same author

Boosting quantification accuracy of chemical exchange saturation transfer MRI with a spatial-spectral redundancy-based denoising method.

NMR in biomedicine·2023
Same author

Learned spatiotemporal correlation priors for CEST image denoising using incorporated global-spectral convolution neural network.

Magnetic resonance in medicine·2023
This summary is machine-generated.

This study introduces a deep learning framework for accurate glioma genotype prediction using Chemical Exchange Saturation Transfer (CEST) MRI. The novel method enhances noninvasive diagnosis of isocitrate dehydrogenase (IDH) and O6-methylguanine-DNA methyltransferase (MGMT) status, improving personalized treatment.

Area of Science:

  • Neuroimaging and Oncology
  • Artificial Intelligence in Medicine
  • Biomedical Engineering

Background:

  • Accurate glioma genotype prediction (IDH mutation, MGMT promoter methylation) is crucial for personalized treatment and prognosis.
  • Chemical Exchange Saturation Transfer (CEST) MRI offers noninvasive assessment of tumor metabolism and microenvironment for genotype prediction.
  • Existing CEST methods face limitations due to simplified quantification and ROI-dependent analysis instability.

Purpose of the Study:

  • To develop a robust deep learning framework for improved glioma genotype prediction using CEST MRI.
  • To overcome limitations of existing CEST methods by integrating full Z-spectrum input, pixel-level training, and majority voting.

Main Methods:

  • A feedforward neural network (FNN) was trained on the full Z-spectrum for pixel-wise predictions.
Keywords:
O6‐methylguanine‐DNA methyltransferase (MGMT)chemical exchange saturation transfer (CEST)deep learningisocitrate dehydrogenase (IDH)magnetic resonance imaging (MRI)

More Related Videos

Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain
09:29

Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain

Published on: July 29, 2022

3.3K

Related Experiment Videos

Last Updated: Mar 19, 2026

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis
06:48

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis

Published on: May 31, 2020

6.4K
Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain
09:29

Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain

Published on: July 29, 2022

3.3K
  • Majority voting aggregated pixel-level predictions for patient-level genotype outcomes (IDH, MGMT).
  • Model generalizability, robustness, and stability were assessed using cross-validation and coefficient of variation (CoV).

    • Main Results:

    • The full Z-spectrum input improved interclass separability (t-SNE score: 64.50) compared to APTw (55.60) and Lorentzian fitting (56.97).
    • Stable prediction performance was achieved for IDH (accuracy: 0.86 ± 0.04, AUC: 0.91 ± 0.03) and MGMT (accuracy: 0.82 ± 0.02, AUC: 0.91 ± 0.04) genotypes.
    • The approach demonstrated strong robustness to ROI selection (CoV: 0.69%), significantly outperforming existing methods.

    Conclusions:

    • Combining full Z-spectrum input, pixel-level learning, and majority voting enhances reliability in noninvasive glioma genotype prediction.
    • The proposed deep learning framework offers a more accurate and robust alternative for CEST MRI-based glioma diagnosis.
    • This advancement supports improved personalized treatment planning and prognosis for glioma patients.