Search research articles

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

Clinical differentiation between pediatric pulmonary tuberculosis and <i>Mycoplasma pneumoniae</i> pneumonia (Review).

Experimental and therapeutic medicine·2026

Same author

Interpretable agentic AI system with localized reasoning for radiology.

NPJ digital medicine·2026

Same author

PIPA: Prior-Driven Prompting with Diagnosis-Oriented Retrieval-Augmentation for 3D Radiology Report Generation.

IEEE transactions on medical imaging·2026

Same author

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection.

Proceedings. IEEE International Conference on Computer Vision·2026

Same author

Brain network construction and analysis for epilepsy: A methodology review.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 24, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Progressive Distillation With Optimal Transport for Federated Incomplete Multi-Modal Learning of Brain Tumor

Qiushi Yang, Meilu Zhu, Peter Y M Woo

IEEE Journal of Biomedical and Health Informatics

|March 3, 2025

Summary

This study introduces Federated Incomplete Multi-modal Learning (FedIML) for brain tumor segmentation, addressing challenges with missing MRI data and distributed training. The proposed Progressive distiLlation with Optimal Transport (PLOT) framework enhances model robustness and accuracy.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 24, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Area of Science:

Medical Imaging
Artificial Intelligence
Machine Learning

Background:

Multi-modal Magnetic Resonance Imaging (MRI) is crucial for brain tumor segmentation but struggles with incomplete data and centralized training limitations.
Existing methods often fail with missing modalities and do not leverage distributed datasets effectively for robust model development.

Purpose of the Study:

To develop a robust brain tumor segmentation model using federated learning under incomplete multi-modal MRI scenarios.
To address challenges of unstable local training and conflicting model parameters in distributed environments.

Main Methods:

Propose the Federated Incomplete Multi-modal Learning (FedIML) framework.
Introduce the Progressive distiLlation with Optimal Transport (PLOT) framework, incorporating Modality Progressive Distillation (MPD) for stable local training and Optimal Transport-guided Model Aggregation (OTMA) for server-side parameter alignment.
MPD uses a routing mechanism for gradual, easy-to-hard learning, while OTMA solves an optimal transport problem for compatible parameter aggregation.

Main Results:

The proposed FedIML framework with the PLOT strategy demonstrates significant effectiveness in brain tumor segmentation.
Experiments on the BraTS-2021 dataset show superior performance compared to state-of-the-art methods, particularly in handling incomplete modalities and distributed data.

Conclusions:

The FedIML framework effectively trains robust brain tumor segmentation models even with incomplete multi-modal MRI data in distributed settings.
The PLOT framework, through MPD and OTMA, successfully overcomes limitations of unstable local training and parameter conflicts, improving overall segmentation accuracy.