Long-term neuroprotective effects of natalizumab and fingolimod in multiple sclerosis: Evidence from real-world clinical data.

BACKGROUND: The long-term effect of high efficacy disease modifying therapy (DMT) on neurodegeneration in people with multiple sclerosis (pwMS) is largely unknown. The aim of this study was to evaluate the long-term effect of natalizumab (NTZ) or fingolimod (FTY) therapy on the evolution of brain atrophy compared to moderate efficacy DMT in a real-world clinical setting. METHODS: A total of 438 pwMS with 2,439 MRI exams during treatment were analyzed: 252 pwMS treated with moderate efficacy DMT, 130 with NTZ and 56 with FTY. Evolution of brain atrophy was analyzed over an average follow-up of 6.6 years after treatment initiation. Brain segmentation was performed on clinical 3D-FLAIRs using SynthSeg and regional brain volume changes over time were compared between the treatment groups. RESULTS: Total brain, white matter and deep gray matter atrophy rates did not differ between moderate efficacy DMTs, NTZ and FTY. Annualized ventricle growth rates were lower in pwMS treated with NTZ (1.1 %/year) compared with moderate efficacy DMT (2.4 %/year, p < 0.001) and similar to FTY (2.0 %/year, p = 0.051). Cortical atrophy rates were lower in NTZ (-0.08 %/year) compared with moderate efficacy DMT (-0.16 %/year, p = 0.048). CONCLUSION: In a real-world clinical setting, pwMS treated with NTZ had slower ventricular expansion and cortical atrophy compared to those treated with moderate efficacy DMT.

Assessment of data consistency through cascades of independently recurrent inference machines for fast and robust accelerated MRI reconstruction.

Objective.Machine Learning methods can learn how to reconstruct magnetic resonance images (MRI) and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varying network architectures is preferred to optimize performance.Approach.We propose a scheme called Cascades of Independently Recurrent Inference Machines (CIRIM) to assess DC through unrolled optimization. Herein we assess DC both implicitly by gradient descent and explicitly by a designed term. Extensive comparison of the CIRIM to compressed sensing as well as other Machine Learning methods is performed: the End-to-End Variational Network (E2EVN), CascadeNet, KIKINet, LPDNet, RIM, IRIM, and UNet. Models were trained and evaluated on T1-weighted and FLAIR contrast brain data, and T2-weighted knee data. Both 1D and 2D undersampling patterns were evaluated. Robustness was tested by reconstructing 7.5× prospectively undersampled 3D FLAIR MRI data of multiple sclerosis (MS) patients with white matter lesions.Main results.The CIRIM performed best when implicitly enforcing DC, while the E2EVN required an explicit DC formulation. Through its cascades, the CIRIM was able to score higher on structural similarity and PSNR compared to other methods, in particular under heterogeneous imaging conditions. In reconstructing MS patient data, prospectively acquired with a sampling pattern unseen during model training, the CIRIM maintained lesion contrast while efficiently denoising the images.Significance.The CIRIM showed highly promising generalization capabilities maintaining a very fair trade-off between reconstructed image quality and fast reconstruction times, which is crucial in the clinical workflow.