Deep Image Priors for Magnetic Resonance Fingerprinting with pretrained Bloch-consistent denoising autoencoders
This addresses the problem of limited ground truth data in MRF for medical imaging, offering an incremental improvement over existing methods.
The paper tackled the challenge of estimating multi-parametric quantitative maps from compressed sampled Magnetic Resonance Fingerprinting (MRF) acquisitions, which suffer from high undersampling rates and artifacts, by proposing a method that combines a deep image prior (DIP) module with a Bloch consistency enforcing autoencoder, resulting in a faster method with equivalent or better accuracy than DIP-MRF.
The estimation of multi-parametric quantitative maps from Magnetic Resonance Fingerprinting (MRF) compressed sampled acquisitions, albeit successful, remains a challenge due to the high underspampling rate and artifacts naturally occuring during image reconstruction. Whilst state-of-the-art DL methods can successfully address the task, to fully exploit their capabilities they often require training on a paired dataset, in an area where ground truth is seldom available. In this work, we propose a method that combines a deep image prior (DIP) module that, without ground truth and in conjunction with a Bloch consistency enforcing autoencoder, can tackle the problem, resulting in a method faster and of equivalent or better accuracy than DIP-MRF.