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

Mechanical Ventilation-Associated Changes in Hippocampal Electroencephalogram: A Cross-Species Study in Humans and Rats.

CNS neuroscience & therapeutics·2026
Same author

Correlation Between SGK1 Expression Level and Multiple Myeloma Progression After Autologous Hematopoietic Stem Cell Transplantation.

Biochemical genetics·2026
Same author

Acupuncture promotes post-stroke angiogenesis and neuroprotection through regulation of the DLL4/Notch1 signaling pathway.

Histology and histopathology·2026
Same author

Cucurbituril-based anion-conducting membranes with supramolecular nanopores.

Nature·2026
Same author

Integrated effects of geographical origin, fruit color, and cultivation type on quality and bioactive properties of cherry tomato in China.

Food chemistry·2026
Same author

The overlooked promotion of electricity generation by electrochemically active bacteria using chitosan.

Talanta·2026

Related Experiment Video

Updated: May 8, 2025

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

8.1K

Predicting Postoperative Prognosis in Pediatric Malignant Tumor With MRI Radiomics and Deep Learning Models: A

Yao Chen1,2, Xin Hu3, Ting Fan2

  • 1Department of Anesthesiology, Sanbo Brain Hospital, Capital Medical University.

The Journal of Craniofacial Surgery
|May 5, 2025
PubMed
Summary

A new multimodal machine learning model integrating MRI radiomics, deep learning, and clinical data accurately predicts 3-year disease-free survival in pediatric brain tumors, aiding personalized treatment strategies.

Keywords:
Deep learningdisease-free survivalmultimodal modelpediatric brain tumorradiomics

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
Whole-body PET/MRI of Pediatric Patients: The Details That Matter
10:02

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

14.3K

Related Experiment Videos

Last Updated: May 8, 2025

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

8.1K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
Whole-body PET/MRI of Pediatric Patients: The Details That Matter
10:02

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

14.3K

Area of Science:

  • Oncology
  • Radiology
  • Machine Learning
  • Medical Informatics

Background:

  • Pediatric malignant tumors pose significant challenges in predicting long-term outcomes.
  • Accurate prognostication is crucial for tailoring treatment strategies in pediatric oncology.
  • Current predictive models may not fully leverage multimodal data for improved accuracy.

Purpose of the Study:

  • To develop and validate a multimodal machine learning model for predicting 3-year postoperative disease-free survival (DFS) in pediatric brain tumor patients.
  • To integrate magnetic resonance imaging (MRI) radiomics, deep learning features, and clinical indexes into a unified predictive framework.
  • To assess the model's performance and identify key predictive factors for improved prognostic accuracy.

Main Methods:

  • Retrospective analysis of 260 pediatric patients (≤14 years) with brain tumors who underwent R0 resection.
  • Extraction of 1130 radiomics and 511 deep learning features from preoperative MRI, alongside clinical data.
  • Development of six machine learning models, including LightGBM, with dimensionality reduction and Bayesian optimization.

Main Results:

  • The fusion LightGBM model achieved an AUC of 0.859 in the validation set.
  • Integration with clinical indexes improved the final model's AUC to 0.909.
  • Radiomics features (texture heterogeneity) and clinical factors (tumor diameter ≥ 5 cm, low preoperative albumin) were significant prognostic indicators.

Conclusions:

  • The developed multimodal model effectively predicts 3-year DFS in pediatric brain tumors.
  • This approach provides a scientific basis for personalized treatment strategies in pediatric oncology.
  • The integration of diverse data types enhances prognostic accuracy for improved patient management.