An off-the-grid approach to multi-compartment magnetic resonance fingerprinting
This work provides an incremental improvement in multi-compartment MRF for medical imaging researchers by offering a more efficient and precise way to quantify tissue properties.
This paper introduces a new numerical method for multi-compartment magnetic resonance fingerprinting (MRF) that can separate multiple tissue compartments and estimate their NMR properties and mixture fractions without prior knowledge of tissue types or properties. It addresses the scalability and precision challenges of fine-grid discretisation by proposing an off-the-grid approach with sparse group lasso regularisation and approximating Bloch responses with a neural network for efficient gradient back-propagation. The method was tested on simulated and in-vivo healthy brain MRF data, showing effectiveness compared to baseline methods.
We propose a novel numerical approach to separate multiple tissue compartments in image voxels and to estimate quantitatively their nuclear magnetic resonance (NMR) properties and mixture fractions, given magnetic resonance fingerprinting (MRF) measurements. The number of tissues, their types or quantitative properties are not a-priori known, but the image is assumed to be composed of sparse compartments with linearly mixed Bloch magnetisation responses within voxels. Fine-grid discretisation of the multi-dimensional NMR properties creates large and highly coherent MRF dictionaries that can challenge scalability and precision of the numerical methods for (discrete) sparse approximation. To overcome these issues, we propose an off-the-grid approach equipped with an extended notion of the sparse group lasso regularisation for sparse approximation using continuous (non-discretised) Bloch response models. Further, the nonlinear and non-analytical Bloch responses are approximated by a neural network, enabling efficient back-propagation of the gradients through the proposed algorithm. Tested on simulated and in-vivo healthy brain MRF data, we demonstrate effectiveness of the proposed scheme compared to the baseline multicompartment MRF methods.