Refine
Is part of the Bibliography
- no (8)
Review
- peer-review (6)
- nein (2)
Language
- English (8)
Version
- published (2)
Deep Learning with Synthetic Diffusion MRI Data for Free-Water Elimination in Glioblastoma Cases
(2018)
Magnetic resonance imaging (MRI) has evolved into an outstandingly versatile diagnostic modality, as it has the ability to non-invasively produce detailed information on a tissue’s structure and function. Complementary data is normally obtained in separate measurements, either as contrast-weighted images, which are fast and simple to acquire, or as quantitative parametric maps, which offer an absolute quantification of underlying biophysical effects, such as relaxation times or flow. Here, we demonstrate how to acquire and reconstruct data in a transient-state with a dual purpose: 1 – to generate contrast-weighted images that can be adjusted to emphasise clinically relevant image biomarkers; exemplified with signal modulation according to flow to obtain angiography information, and 2 – to simultaneously infer multiple quantitative parameters with a single, highly accelerated acquisition. This is achieved by introducing three novel elements: a model that accounts for flowing blood, a method for sequence design using smooth flip angle excitation patterns that incorporates both parameter encoding and signal contrast, and the reconstruction of temporally resolved contrast-weighted images. From these images we simultaneously obtain angiography projections and multiple quantitative maps. By doing so, we increase the amount of clinically relevant data without adding measurement time, creating new dimensions for biomarker exploration and adding value to MR examinations for patients and clinicians alike.
Learning a Spatiotemporal Dictionary for Magnetic Resonance Fingerprinting with Compressed Sensing
(2016)
Deep learning-based parameter mapping for joint relaxation and diffusion tensor MR Fingerprinting
(2020)
Deep learning-based parameter mapping for joint relaxation and diffusion tensor MR Fingerprinting
(2020)
Purpose
The compartmental nature of brain tissue microstructure is typically studied by diffusion MRI, MR relaxometry or their correlation. Diffusion MRI relies on signal representations or biophysical models, while MR relaxometry and correlation studies are based on regularized inverse Laplace transforms (ILTs). Here we introduce a general framework for characterizing microstructure that does not depend on diffusion modeling and replaces ill-posed ILTs with blind source separation (BSS). This framework yields proton density, relaxation times, volume fractions, and signal disentanglement, allowing for separation of the free-water component.
Theory and Methods
Diffusion experiments repeated for several different echo times, contain entangled diffusion and relaxation compartmental information. These can be disentangled by BSS using a physically constrained nonnegative matrix factorization.
Results
Computer simulations, phantom studies, together with repeatability and reproducibility experiments demonstrated that BSS is capable of estimating proton density, compartmental volume fractions and transversal relaxations. In vivo results proved its potential to correct for free-water contamination and to estimate tissue parameters.
Conclusion
Formulation of the diffusion-relaxation dependence as a BSS problem introduces a new framework for studying microstructure compartmentalization, and a novel tool for free-water elimination.