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: May 10, 2026

Glioblastoma Relapse Post-Resection Model for Therapeutic Hydrogel Investigations
04:46

Glioblastoma Relapse Post-Resection Model for Therapeutic Hydrogel Investigations

Published on: February 24, 2023

Transformer-Based Deep Learning Model for Predicting Recurrence in High-Grade Glioma.

Xin Wang1, Mingjun Ding1, Dan Zong1

  • 1Department of Radiotherapy, The Affiliated Cancer Hospital of Nanjing Medical University, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing, China.

Cancer Medicine
|May 9, 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

Watch and Wait Strategy for Locally Advanced Rectal Cancer: Update From Results of Recent Clinical Trials.

Cancer medicine·2026
Same author

Multi-regional radiomics based on planning CT and information complementarity between GTVp and GTVn: an explainable model for predicting 5-year recurrence risk in HPV-positive oropharyngeal cancer.

Radiation oncology (London, England)·2026
Same author

Polymer-Based Multiparameter Sensing Integrated Photonic Chip for Health Monitoring.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Manganese enrichment in rice seedlings shifts cadmium accumulation from inhibition to promotion during growth via transcriptomic mechanisms.

Ecotoxicology and environmental safety·2026
Same author

An ambispective, observational real-world study of tumor-treating fields for treatment of Chinese patients with newly diagnosed or recurrent/progressive glioblastoma.

Neuro-oncology advances·2026
Same author

Deep learning-based independent lymph node segmentation in esophageal cancer: a precise and efficient approach for radiotherapy planning.

Quantitative imaging in medicine and surgery·2026

This study developed a fusion model integrating MRI and clinical data to predict high-grade glioma recurrence within one year. The Combined-Transformer-DenseNet121 model shows high accuracy for early identification of high-risk patients.

Area of Science:

  • Neuro-oncology
  • Medical Imaging
  • Artificial Intelligence in Medicine

Background:

  • The first year post-treatment is critical for high-grade glioma (HGG) recurrence.
  • Accurate prediction of HGG recurrence is vital for timely patient management.
  • This study addresses the need for improved HGG recurrence prediction models.

Purpose of the Study:

  • To develop and validate a fusion model integrating MRI-derived features and clinical variables.
  • To enhance the accuracy of predicting one-year recurrence in high-grade glioma patients.
  • To facilitate early identification of patients at high risk of recurrence.

Main Methods:

  • Retrospective analysis of 309 postoperative HGG patients treated with intensity-modulated radiation therapy (IMRT).
Keywords:
MRIdeep learninghigh‐grade gliomarecurrencetransformer

Related Experiment Videos

Last Updated: May 10, 2026

Glioblastoma Relapse Post-Resection Model for Therapeutic Hydrogel Investigations
04:46

Glioblastoma Relapse Post-Resection Model for Therapeutic Hydrogel Investigations

Published on: February 24, 2023

  • Extraction of deep-learning features from T2-weighted MRI using DenseNet architectures (121, 201, 169).
  • Development of integrated models combining deep-learning features with clinical variables, evaluated using ROC analysis, calibration curves, and DCA.

    • Main Results:

    • The Combined-Transformer-DenseNet121 model achieved an AUC of 0.903 (training) and 0.747 (test).
    • Improved calibration fidelity was observed, with excellent agreement between predicted and observed outcomes.
    • Decision curve analysis (DCA) demonstrated superior clinical utility and net benefit compared to traditional methods.

    Conclusions:

    • The proposed fusion model significantly outperforms traditional approaches in predicting one-year HGG recurrence.
    • The model offers high accuracy, enabling early identification of high-risk patients.
    • This AI-driven approach supports timely clinical intervention and improved patient outcomes.