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

Enhancing YOLOv11 with Large Kernel Attention and Multi-Scale Fusion for Accurate Small and Multi-Lesion Bone Tumor Detection in Radiographs.

Diagnostics (Basel, Switzerland)·2025
Same author

Artificial Intelligence in Pancreatic Image Analysis: A Review.

Sensors (Basel, Switzerland)·2024
Same author

A Regularization Homotopy Strategy for the Constrained Parameter Inversion of Partial Differential Equations.

Entropy (Basel, Switzerland)·2021
See all related articles

Related Experiment Video

Updated: Sep 18, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.2K

The Teacher-Assistant-Student Collaborative and Competitive Network for Brain Tumor Segmentation with Missing

Junjie Wang1, Huanlan Kang1, Tao Liu1

  • 1School of Mathematics and Statistics, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China.

Diagnostics (Basel, Switzerland)
|June 26, 2025
PubMed
Summary

A novel AI model, TASCCNet, effectively segments brain tumors using limited Magnetic Resonance Imaging (MRI) data. This approach enhances tumor analysis when multiple MRI modalities are unavailable.

Keywords:
brain tumor segmentationcollaboration and competitiondeep learningknowledge distillationmedical image segmentationmissing modalities

More Related Videos

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
08:41

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

8.6K
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

3.0K

Related Experiment Videos

Last Updated: Sep 18, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.2K
Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
08:41

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

8.6K
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

3.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuro-oncology

Background:

  • Magnetic Resonance Imaging (MRI) offers detailed tumor insights via T1, T1ce, T2, and FLAIR modalities.
  • Clinical limitations often restrict MRI analysis to a single modality, hindering tumor segmentation accuracy.
  • Incomplete MRI data significantly impacts the performance of current brain tumor segmentation methods.

Purpose of the Study:

  • To develop an advanced AI model for robust brain tumor segmentation using incomplete MRI data.
  • To overcome the performance degradation caused by the unavailability of multiple MRI modalities.

Main Methods:

  • Proposed the Teacher-Assistant-Student Collaborative and Competitive Net (TASCCNet) based on knowledge distillation.
  • Introduced a Multihead Mixture of Experts (MHMoE) for enhanced fused modality information.
  • Implemented a competitive function for teacher-student network synergy and an assistant module for supplementary structural knowledge.

Main Results:

  • TASCCNet demonstrated robust performance on BraTS 2018 and BraTS 2021 datasets, even with single MRI modality input.
  • The model effectively handles scenarios with incomplete imaging data.

Conclusions:

  • TASCCNet successfully addresses the challenge of incomplete MRI data in brain tumor segmentation.
  • The model leverages collaborative knowledge distillation and competitive learning for improved segmentation outcomes.