No abstract

Brain function has been investigated via the blood oxygenation level dependent (BOLD) effect using magnetic resonance imaging (MRI) for the past decades. Advances in sodium imaging offer the unique chance to access signal changes directly linked to sodium ions (23Na) flux across the cell membrane, which generates action potentials, hence signal transmission in the brain. During this process 23Na transiently accumulates in the intracellular space. Here we show that quantitative functional sodium imaging (fNaI) at 3T is potentially sensitive to 23Na concentration changes during finger tapping, which can be quantified in gray and white matter regions key to motor function. For the first time, we measured a 23Na concentration change of 0.54 mmol/l in the ipsilateral cerebellum, 0.46 mmol/l in the contralateral primary motor cortex (M1), 0.27 mmol/l in the corpus callosum and -11 mmol/l in the ipsilateral M1, suggesting that fNaI is sensitive to distributed functional alterations. Open issues persist on the role of the glymphatic system in maintaining 23Na homeostasis, the role of excitation and inhibition as well as volume distributions during neuronal activity. Haemodynamic and physiological signal recordings coupled to realistic models of tissue function will be critical to understand the mechanisms of such changes and contribute to meeting the overarching challenge of measuring neuronal activity in vivo.

Among dementia-like diseases, Alzheimer disease (AD) and vascular dementia (VD) are two of the most frequent. AD and VD may share multiple neurological symptoms that may lead to controversial diagnoses when using conventional clinical and MRI criteria. Therefore, other approaches are needed to overcome this issue. Machine learning (ML) combined with magnetic resonance imaging (MRI) has been shown to improve the diagnostic accuracy of several neurodegenerative diseases, including dementia. To this end, in this study, we investigated, first, whether different kinds of ML algorithms, combined with advanced MRI features, could be supportive in classifying VD from AD and, second, whether the developed approach might help in predicting the prevalent disease in subjects with an unclear profile of AD or VD. Three ML categories of algorithms were tested: artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Multiple regional metrics from resting-state fMRI (rs-fMRI) and diffusion tensor imaging (DTI) of 60 subjects (33 AD, 27 VD) were used as input features to train the algorithms and find the best feature pattern to classify VD from AD. We then used the identified VD-AD discriminant feature pattern as input for the most performant ML algorithm to predict the disease prevalence in 15 dementia patients with a "mixed VD-AD dementia" (MXD) clinical profile using their baseline MRI data. ML predictions were compared with the diagnosis evidence from a 3-year clinical follow-up. ANFIS emerged as the most efficient algorithm in discriminating AD from VD, reaching a classification accuracy greater than 84% using a small feature pattern. Moreover, ANFIS showed improved classification accuracy when trained with a multimodal input feature data set (e.g., DTI + rs-fMRI metrics) rather than a unimodal feature data set. Castellazzi et al. Dementia Classification Using Machine Learning When applying the best discriminant pattern to the MXD group, ANFIS achieved a correct prediction rate of 77.33%. Overall, results showed that our approach has a high discriminant power to classify AD and VD profiles. Moreover, the same approach also showed potential in predicting earlier the prevalent underlying disease in dementia patients whose clinical profile is uncertain between AD and VD, therefore suggesting its usefulness in supporting physicians' diagnostic evaluations.