In this study, we propose a model-based unsupervised learning algorithm to estimate three-component exponential model parameters. The proposed method, model-based T2* autoencoder, is composed of ANN encoder and three-component model decoder. Incorporation of ANN encoder and three-component model decoder provides noise robust estimation of MWF and physically meaningful information at deep latent space.
This abstract and the presentation materials are available to members only; a login is required.