Evaluation of Disability Progression in Multiple Sclerosis via Magnetic-Resonance-Based Deep Learning Techniques.

Short-term disability progression was predicted from a baseline evaluation in patients with multiple sclerosis (MS) using their three-dimensional T1-weighted (3DT1) magnetic resonance images (MRI). One-hundred-and-eighty-one subjects diagnosed with MS underwent 3T-MRI and were followed up for two to six years at two sites, with disability progression defined according to the expanded-disability-status-scale (EDSS) increment at the follow-up. The patients' 3DT1 images were bias-corrected, brain-extracted, registered onto MNI space, and divided into slices along coronal, sagittal, and axial projections. Deep learning image classification models were applied on slices and devised as ResNet50 fine-tuned adaptations at first on a large independent dataset and secondly on the study sample. The final classifiers' performance was evaluated via the area under the curve (AUC) of the false versus true positive diagram. Each model was also tested against its null model, obtained by reshuffling patients' labels in the training set. Informative areas were found by intersecting slices corresponding to models fulfilling the disability progression prediction criteria. At follow-up, 34% of patients had disability progression. Five coronal and five sagittal slices had one classifier surviving the AUC evaluation and null test and predicted disability progression (AUC > 0.72 and AUC > 0.81, respectively). Likewise, fifteen combinations of classifiers and axial slices predicted disability progression in patients (AUC > 0.69). Informative areas were the frontal areas, mainly within the grey matter. Briefly, 3DT1 images may give hints on disability progression in MS patients, exploiting the information hidden in the MRI of specific areas of the brain.

A new perspective of molecular diffusion by nuclear magnetic resonance.

The diffusion-weighted NMR signal acquired using Pulse Field Gradient (PFG) techniques, allows for extrapolating microstructural information from porous materials and biological tissues. In recent years there has been a multiplication of diffusion models expressed by parametric functions to fit the experimental data. However, clear-cut criteria for the model selection are lacking. In this paper, we develop a theoretical framework for the interpretation of NMR attenuation signals in the case of Gaussian systems with stationary increments. The full expression of the Stejskal-Tanner formula for normal diffusing systems is devised, together with its extension to the domain of anomalous diffusion. The range of applicability of the relevant parametric functions to fit the PFG data can be fully determined by means of appropriate checks to ascertain the correctness of the fit. Furthermore, the exact expression for diffusion weighted NMR signals pertaining to Brownian yet non-Gaussian processes is also derived, accompanied by the proper check to establish its contextual relevance. The analysis provided is particularly useful in the context of medical MRI and clinical practise where the hardware limitations do not allow the use of narrow pulse gradients.

ABC Epatite Web App: raising health awareness in a mobile world.

BACKGROUND: This paper presents the case study of a health campaign for mobile devices launched in Italy in 2019 aimed at raising viral hepatitis awareness. The research project "ABC epatite. Sviluppo di una app per la prevenzione delle epatiti virali e per la consapevolezza dei comportamenti a rischio", winner of the 2018 Digital Health Program of Gilead Italia, was carried out by the Italian National Research Council. METHODS: The project entailed the development of a free Italian language Progressive Web App (PWA) providing current and scientifically validated information on viral hepatitis (A, B and C). RESULTS: A mobile first PWA health awareness app was implemented (https://epatite.web.app) together with an Android app version. Diversified landing pages cater to two target audiences: general public and schools. An initial campaign was directed toward engaging schools in nine Italian regions. CONCLUSIONS: Preliminary results based on the campaign directed toward Italian schools in just under half of its regions have shown promise on the feasibility of reaching large audiences and encouraging engagement on viral hepatitis prevention. A mobile first approach to health communication is a cost-effective way to help reaching the goal of eradicating viral hepatitis by reducing infections and deaths.