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 Videos

PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for 3D Brain Tumor

Haokun Wang1, Shuyi Wang1, Yuqi Li1

  • 1School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.

Brain Sciences
|June 26, 2026
PubMed
Summary
This summary is machine-generated.

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

Waterborne Polyurethane Reinforced with SiO<sub>2</sub>-Modified TiO<sub>2</sub>: Enhanced Mechanical Properties and Retained Hydrostatic Pressure Resistance.

Polymers·2026
Same author

Application of large language models in medical diagnosis: A bibliometric review.

Digital health·2026
Same author

A cholinergic checkpoint controls autoantibody selection via somatic hypermutation in lupus germinal centers.

Cellular & molecular immunology·2026
Same author

Photocatalytic Activation of Alkyl Diazirine Probes for In Situ Drug Profiling and Extracellular Vesicle-Based Diagnostics.

Journal of the American Chemical Society·2026
Same author

Investigating the efficacy of propranolol in treating chronic stress combined with colorectal cancer in mice and its antitumor potential.

European journal of pharmacology·2026
Same author

Zeb2 Controls Retinal Physiological and Pathological Angiogenesis by Regulating Astrocyte Proliferation and Differentiation.

Cell proliferation·2026
Same journal

Anterior Cingulate Cortex Mediates State-Dependent Prioritization of Distressed Conspecifics.

Brain sciences·2026
Same journal

Hemispherotomy for Pediatric Post-Traumatic Epilepsy.

Brain sciences·2026
Same journal

When Robots Learn: Artificial Intelligence and the Next Human-Centered Era of Neurorehabilitation.

Brain sciences·2026
Same journal

The Association Between Changes in White Matter Microstructure and Cognitive Function in Older Adults with Mild Cognitive Impairment.

Brain sciences·2026
Same journal

Beyond Ventricular Enlargement: Multimodal MRI Assessment Improves Surgical Decision-Making in Normal Pressure Hydrocephalus.

Brain sciences·2026
Same journal

The Effects of Personalized Observation, Execution, and Mental Imagery (POEM) Therapy in Logopenic Primary Progressive Aphasia: A Telepractice-Based Single-Case Study.

Brain sciences·2026
See all related articles

This study introduces PF-CMNet, a novel framework for brain tumor segmentation using multimodal MRI. The model demonstrates improved accuracy and robustness, even with incomplete imaging data.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Accurate segmentation of multimodal MRI is crucial for neurosurgery.
  • Existing models struggle with low contrast, ambiguous boundaries, and missing imaging data.

Purpose of the Study:

  • Develop a robust segmentation framework for multimodal MRI.
  • Improve cross-modal learning, boundary recovery, and performance with incomplete data.

Main Methods:

  • Proposed PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation.
  • Utilized Cross-Modal Selective Frequency Attention and Progressive Cross-Scale Detail Fusion.
  • Employed teacher-student distillation for robustness against missing modalities.
Keywords:
brain tumor segmentationcross-modal learningknowledge distillationmissing modalitymultimodal MRI

Related Experiment Videos

Main Results:

  • Achieved 84.3% average Dice score on MSD Task01_BrainTumour.
  • Attained 88.2% average Dice score on BraTS2021, with the lowest Hausdorff distance.
  • Maintained strong performance with missing MRI sequences in stress tests.

Conclusions:

  • PF-CMNet offers a unified framework for multimodal brain tumor segmentation.
  • The model enhances accuracy, boundary consistency, and robustness to incomplete MRI.
  • Achieved a favorable accuracy-efficiency trade-off.