Search research articles

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

Home
Ttp-ssfl: Test-time Personalization Self-supervised Federated Learning For Accelerating Mr Image Reconstruction.

Home
Ttp-ssfl: Test-time Personalization Self-supervised Federated Learning For Accelerating Mr Image Reconstruction.

Related Concept Videos

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been developed.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026

Same author

A deep cardiac motion field analysis approach via global 2nd-order kinematic graph modeling.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same author

Diversity-driven MG-MAE: Multi-granularity representation learning for non-salient object segmentation.

Medical image analysis·2026

Same author

S<sup>3</sup>CNet: self-supervised Siamese cooperative network for accelerating magnetic resonance imaging reconstruction.

Medical physics·2026

Same author

[An unsupervised three-dimensional medical image registration method based on shifted window Transformer and convolutional neural network].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2025

Same author

Embedding Tasks Into the Latent Space: Cross-Space Consistency for Multi-Dimensional Analysis in Echocardiography.

IEEE transactions on medical imaging·2024

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

Same journal

Hierarchical Semantic Concept Modeling for Generalizable Myocardial Pathology Segmentation on Multisequence CMR Images.

IEEE transactions on neural networks and learning systems·2026

Same journal

Stability of Time-Varying Impulsive Systems With State-Dependent Delay and Its Application in Complex Networks.

IEEE transactions on neural networks and learning systems·2026

Same journal

Adaptive Learning Control of Uncertain Systems via Weight and Intrinsic Plasticity-Based Neural Networks.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Related Experiment Videos

TTP-SSFL: Test-Time Personalization Self-Supervised Federated Learning for Accelerating MR Image Reconstruction.

Chenghu Geng, Mingfeng Jiang, Dongsheng Ruan

IEEE Transactions on Neural Networks and Learning Systems

|June 23, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces a novel federated learning (FL) method for faster magnetic resonance (MR) image reconstruction. The approach enhances privacy and performance across different clinical sites without needing fully sampled data.

Related Experiment Videos

Area of Science:

Medical Imaging
Artificial Intelligence
Data Science

Background:

Federated learning (FL) accelerates magnetic resonance (MR) image reconstruction and ensures data privacy in multicenter studies.
Current FL methods require fully sampled k-space data for training and suffer from performance drops due to domain shifts.

Purpose of the Study:

To propose a test-time personalization self-supervised FL (TTP-SSFL) method for accelerated MR image reconstruction.
To address the challenges of limited fully sampled data and domain shifts in clinical settings.

Main Methods:

Implemented cross-institutional collaboration without fully sampled data using a Siamese-based self-supervised strategy and a hybrid loss function.
Introduced a low-rank adaptation (LoRA)-based test-time adaptation (TTA) strategy for domain shift mitigation.
Optimized lightweight adapters using only testing data via self-supervision for efficient personalization and generalization.

Main Results:

Achieved state-of-the-art performance among self-supervised methods for MR image reconstruction.
Matched the accuracy of supervised personalized FL (PFL) models.
Demonstrated robust generalization across heterogeneous clinical environments.

Conclusions:

TTP-SSFL offers a practical, privacy-preserving solution for robust MR reconstruction in diverse clinical settings.
The method effectively handles the lack of fully sampled data and mitigates domain shift issues.