.png){kind=icon}
Return
Multitask gated autoencoder-based brain MRI harmonization framework
.png){kind=icon}
PRE
AI
DOI：10.1016/j.bspc.2025.108909.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes a U-shaped multitask-gated autoencoder that eliminates MRI batch effects via adversarial biomarker-preserving learning. • Dynamically suppresses batch effects and artifacts via constrained gating and attention. • Outperforms existing methods in multi-center classification and image quality, validated across independent and cross-pathology cohorts.
Journal
IF:
4.9
Papers:
1.0W
Citations:
2.4W
Organization
Cited Papers
BERNN: Enhancing classification of Liquid Chromatography Mass Spectrometry data with batch effect removal neural networks.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveAssessment of ComBat Harmonization Performance on Structural Magnetic Resonance Imaging MeasurementsHUMAN BRAIN MAPPINGOAAI
HUMAN BRAIN MAPPINGIF3.3
OAAIShareSaveIncreased power by harmonizing structural MRI site differences with the ComBat batch adjustment method in ENIGMANeuroImageOAAI
NeuroImageIF0
OAAIShareSaveShareSaveImUnity: A generalizable VAE-GAN solution for multicenter MR image harmonizationMEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAIShareSaveEffect of acetylcholine deficiency on neural oscillation in a brainstem-thalamus-cortex neurocomputational model related with Alzheimer's diseaseSCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSaveDisentangled latent energy-based style translation: An image-level structural MRI harmonization frameworkNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAIShareSave
View more