Article

Individualized Per-Site Meta-Federated Feature Learning (iPS-MFFL) for Privacy-Preserving Brain Tumor MRI Classification under non-IID Heterogeneity

2026-04-17

Abstract excerpt

<h4>Background</h4> Federated learning (FL) enables collaborative model training across institutions without sharing patient-level data. However, standard FL algorithms such as FedAvg degrade under non-independently and non-identically distributed (non-IID) data, a prevalent condition when patient demographics, scanner hardware, and disease prevalence differ across hospital sites. <h4>Objective</h4> We propose...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 2c5fddbb-1c70-5877-81ed-f9b8b1734755
DOI: 10.64898/2026.04.15.26351000

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Individualized Per-Site Meta-Federated Feature Learning (iPS-MFFL) for Privacy-Preserving Brain Tumor MRI Classification under non-IID HeterogeneityDOI 10.64898/2026.04.15.26351000Read

Federated CT Foundation Models for Multi-Center Detection of Lymph Node Metastasis in Pancreatic CancerSemantic proximity Read

Federated Learning for Multi-Center Imaging Diagnostics: A Study in Cardiovascular DiseaseSemantic proximity Read

Fed-ComBat: A Generalized Federated Framework for Batch Effect Harmonization in Collaborative StudiesSemantic proximity Read

Flexible and Scalable Federated Learning with Deep Feature Prompts for Digital PathologySemantic proximity Read

GlioVision: A Multi-Modal MRI Framework for Non-Invasive Glioma Molecular Biomarkers PredictionSemantic proximity Read

FedIHRAS: A Privacy-Preserving Federated Learning Framework for Multi-Institutional Collaborative Radiological Analysis with Integrated Explainability and Automated Clinical ReportingSemantic proximity Read

SIENNA: Generalizable Lightweight Machine Learning Platform for Brain Tumor DiagnosticsSemantic proximity Read

Federated deep learning enables cancer subtyping by proteomicsSemantic proximity Read

Toward Real-World Deployment of Federated Learning in Healthcare: A Comprehensive Review of Hybrid Models and Data Simulation ToolsSemantic proximity Read

A Simple, Privacy-Preserving Multimodal Stacking System for Clinical Progression Prediction in Low-Resource Rare DiseasesSemantic proximity Read

Federated Learning-Driven Collaborative Diagnostic System for Metastatic Breast CancerSemantic proximity Read

Categorical and phenotypic image synthetic learning as an alternative to federated learning.Semantic proximity Read