New MRI technique enhances T2* mapping accuracy with uncertainty propagation

Researchers have developed CUPA-T2*, a novel framework designed to improve the accuracy of T2* mapping in accelerated magnetic resonance imaging (MRI). This method explicitly propagates voxel-wise uncertainty from Monte Carlo dropout reconstructions to the downstream T2* fitting process. By employing a heteroscedastic MLP and a correlation-based regularizer, CUPA-T2* enhances T2* fitting performance, particularly in white matter at higher acceleration rates. The framework also provides voxel-wise uncertainty maps to aid in the interpretation of quantitative T2* estimates. AI

RANK_REASON The item is an academic paper detailing a new method for T2* mapping in MRI. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• arXiv
• CUPA-T2*
• DagsHub
• Gideon Nicolaas Laurentius Rouwendaal
• Hugging Face
• magnetic resonance imaging
• Monte Carlo
• multilayer perceptron

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →