In spite of the worldwide financial and research efforts made, the pathophysiological mechanism at the basis of Alzheimer's disease (AD) is still poorly understood. Previous studies using electroencephalography (EEG) have focused on the slowing of oscillatory brain rhythms, coupled with complexity reduction of the corresponding time-series and their enhanced compressibility. These analyses have been typically carried out on single channels. However, limited investigations have focused on the possibility yielded by computational intelligence methodologies and novel machine learning approaches applied to multichannel schemes. The study at screening level on EEG recordings of subjects at risk could be useful to highlight the emergence of underlying AD progression (or at least support any further clinical investigation). In this work, the representational power of Deep Learning on Convolutional Neural Networks (CNN) is exploited to generate suitable sets of features that are then able to classify EEG patterns of AD from a prodromal version of dementia (Mild Cognitive Impairment, MCI) and from age-matched Healthy Controls (HC). The processing system here used enforces a series of convolutional-subsampling layers in order to derive a multivariate assembly of latent, novel patterns, finally used to categorize sets of EEG from different classes of subjects. The final processor here proposed is able to reach an averaged 80% of correct classification with good performance on both sensitivity and specificity by using a Multilayered Feedforward Perceptron (MLP) of the standard type as a final block of the procedure.

Alzheimer's Disease (AD) is a neurodegenerative disorder that causes a loss of connections between neurons. The goal of the present work was to construct a complex network model of the brain-electrical activity using high-density EEG (HD-EEG) recordings and to compare the network organization in AD, Mild Cognitive Impaired (MCI) and healthy control (CNT) subjects. The HD-EEG of 16 AD, 16 MCI and 12 CNT were recorded during an eye-closed resting state. The Permutation Disalignment Index (PDI) was used to describe the dissimilarity between EEG signals and to construct the connection matrices of the network model. The three groups were found to have significantly different ( $p\lt0.001$ ) Characteristic Path Length (Lambda), average Clustering Coefficient (CC) and Global Efficiency (GE). This is the first time that HD-EEG signals of AD, MCI and CNT have been compared and that PDI has been used to discriminate between the three groups. Considered the large amount of data originating from the HD-EEG acquisition, compared to standard EEG, the aim of the present work was also to assess that compression did not alter the results of the complex network analysis. Compressive sensing was adopted to compress and reconstruct the HD-EEG signals with minimal information loss, achieving an average Structural SIMilarity index (SSIM) of 0.954 (AD), 0.957 (MCI) and 0.959 (CNT). When applied to the reconstructed HD-EEG, the complex network analysis provided a substantially unaltered performance, compared to the analysis of the original signals. Indeed, Lambda, CC, GE and of the three groups were still significantly different ( $p\lt0.001$ ).

The differential diagnosis between radiation necrosis, tumor recurrence and tumor progression is crucial for the evaluation of treatment response and treatment planning. The appearance of treatment-induced tissue necrosis on conventional Magnetic Resonance Imaging (MRI) is similar to brain tumor recurrence and it could be difficult to differentiate the two entities on follow-up MRI examinations. Dynamic Susceptibility Contrast-enhanced (DSC) and Dynamic Contrast-Enhanced (DCE) are MRI perfusion techniques that use an exogenous, intravascular, non-diffusible gadolinium-based contrast agent. The aim of this study was to compare the diagnostic accuracy of DSC and DCE perfusion MRI in the differential diagnosis between radiation necrosis and tumor recurrence, in the follow-up of primary and metastatic intra-axial brain tumors after Stereotactic RadioSurgery (SRS) performed with CyberKnife. A total of 72 enhancing lesions (57 brain metastases and 15 primary brain tumors) were analyzed with DCE and DSC, by means of MRI acquisition performed by 1,5 Tesla MR scanner. The statistical relationship between the diagnosis of tumor recurrence or radiation necrosis, decided according to clinicoradiologically criteria, rCBV and Ktrans was evaluated by the point-biserial correlation coefficient respectively. The statistical analysis showed a correlation between the diagnosis of radiation necrosis or recurrent tumor with Ktrans (rpb = 0.54, p < 0.001) and with rCBV (rpb = 0.37, p = 0.002). The ROC analysis of rCBV values demonstrated a good classification ability in differentiating radiation necrosis from tumour recurrence as well as the Ktrans. The optimal cut-off value for rCBV was k = 1.23 with 0.88 of sensitivity and 0.75 of specificity while for Ktrans was k = 28.76 with 0.89 of sensitivity and 0.97 of specificity. MRI perfusion techniques, particularly DCE, help in the differential diagnosis by tumor recurrence and radiation necrosis during the follow-up after radiosurgery.

Several fMRI studies in migraine assessed resting state functional connectivity in different networks suggesting that this neurological condition was associated with brain functional alteration. The aim of present study was to explore the association between cognitive functions and cerebral functional connectivity, in default mode network, in migraine patients without and with aura, during interictal episodic attack. Twenty-eight migraine patients (14 without and 14 with aura) and 14 matched normal controls, were consecutively recruited. A battery of standardized neuropsychological test was administered to evaluate cognitive functions and all subjects underwent a resting state with high field fMRI examination. Migraine patients did not show abnormalities in neuropsychological evaluation, while, we found a specific alteration in cortical network, if we compared migraine with and without aura. We observed, in migraine with aura, an increased connectivity in left angular gyrus, left supramarginal gyrus, right precentral gyrus, right postcentral gyrus, right insular cortex. Our findings showed in migraine patients an alteration in functional connectivity architecture. We think that our results could be useful to better understand migraine pathogenesis.