Myo-regressor Deep Informed Neural NetwOrk (Myo-DINO) for fast MR parameters mapping in neuromuscular disorders.

Magnetic Resonance (MR) parameters mapping in muscle Magnetic Resonance Imaging (mMRI) is predominantly performed using pattern recognition-based algorithms, which are characterised by high computational costs and scalability issues in the context of multi-parametric mapping. Deep Learning (DL) has been demonstrated to be a robust and efficient method for rapid MR parameters mapping. However, its application in mMRI domain to investigate Neuromuscular Disorders (NMDs) has not yet been explored. In addition, data-driven DL models suffered in interpretation and explainability of the learning process. We developed a Physics Informed Neural Network called Myo-Regressor Deep Informed Neural NetwOrk (Myo-DINO) for efficient and explainable Fat Fraction (FF), water-T2 (wT2) and B1 mapping from a cohort of NMDs.A total of 2165 slices (232 subjects) from Multi-Echo Spin Echo (MESE) images were selected as the input dataset for which FF, wT2,B1 ground truth maps were computed using the MyoQMRI toolbox. This toolbox exploits the Extended Phase Graph (EPG) theory with a two-component model (water and fat signal) and slice profile to simulate the signal evolution in the MESE framework. A customized U-Net architecture was implemented as the Myo-DINO architecture. The squared L2 norm loss was complemented by two distinct physics models to define two 'Physics-Informed' loss functions: Cycling Loss 1 embedded a mono-exponential model to describe the relaxation of water protons, while Cycling Loss 2 incorporated the EPG theory with slice profile to model the magnetization dephasing under the effect of gradients and RF pulses. The Myo-DINO was trained with the hyperparameter value of the 'Physics-Informed' component held constant, i.e. λmodel = 1, while different hyperparameter values (λcnn) were applied to the squared L2 norm component in both the cycling loss. In particular, hard (λcnn=10), normal (λcnn=1) and self-supervised (λcnn=0) constraints were applied to gradually decrease the impact of the squared L2 norm component on the 'Physics Informed' term during the Myo-DINO training process. Myo-DINO achieved higher performance with Cycling Loss 2 for FF, wT2 and B1 prediction. In particular, high reconstruction similarity and quality (Structural Similarity Index > 0.92, Peak Signal to Noise ratio > 30.0 db) and small reconstruction error (Normalized Root Mean Squared Error < 0.038) to the reference maps were shown with self-supervised weighting of the Cycling Loss 2. In addition muscle-wise FF, wT2 and B1 predicted values showed good agreement with the reference values. The Myo-DINO has been demonstrated to be a robust and efficient workflow for MR parameters mapping in the context of mMRI. This provides preliminary evidence that it can be an effective alternative to the reference post-processing algorithm. In addition, our results demonstrate that Cycling Loss 2, which incorporates the Extended Phase Graph (EPG) model, provides the most robust and relevant physical constraints for Myo-DINO in this multi-parameter regression task. The use of Cycling Loss 2 with self-supervised constraint improved the explainability of the learning process because the network acquired domain knowledge solely in accordance with the assumptions of the EPG model.

Muscle diffusion tensor imaging in facioscapulohumeral muscular dystrophy.

INTRODUCTION/AIMS: Muscle diffusion tensor imaging has not yet been explored in facioscapulohumeral muscular dystrophy (FSHD). We assessed diffusivity parameters in FSHD subjects compared with healthy controls (HCs), with regard to their ability to precede any fat replacement or edema. METHODS: Fat fraction (FF), water T2 (wT2), mean, radial, axial diffusivity (MD, RD, AD), and fractional anisotropy (FA) of thigh muscles were calculated in 10 FSHD subjects and 15 HCs. All parameters were compared between FSHD and controls, also exploring their gradient along the main axis of the muscle. Diffusivity parameters were tested in a subgroup analysis as predictors of disease involvement in muscle compartments with different degrees of FF and wT2 and were also correlated with clinical severity scores. RESULTS: We found that MD, RD, and AD were significantly lower in FSHD subjects than in controls, whereas we failed to find a difference for FA. In contrast, we found a significant positive correlation between FF and FA and a negative correlation between MD, RD, and AD and FF. No correlation was found with wT2. In our subgroup analysis we found that muscle compartments with no significant fat replacement or edema (FF < 10% and wT2 < 41 ms) showed a reduced AD and FA compared with controls. Less involved compartments showed different diffusivity parameters than more involved compartments. DISCUSSION: Our exploratory study was able to demonstrate diffusivity parameter abnormalities even in muscles with no significant fat replacement or edema. Larger cohorts are needed to confirm these preliminary findings.