Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)
The PS-VAE framework rapidly extracts voxelwise multi-parameter posterior distributions from quantitative molecular MRI using a physics-structured variational autoencoder. It addresses uncertainty and bias in AI quantification by approximating the full posterior with a neural network, providing complete covariance information for parameter correlations. This offers fast, trustworthy insights for optimizing imaging protocols.