This study aimed to develop and evaluate a spatiotemporal deep-neural-network (stDNN) using resting-state fMRI (rs-fMRI) data to identify brain biomarkers associated with isolated REM sleep behavior disorder (iRBD) and Parkinson's disease (PD) and to differentiate these conditions from controls. The final sample included 771 subjects, comprising 423 patients with PD, 144 with iRBD, and 204 healthy controls. stDNN model was applied to mean timeseries extracted for each subject from rs-fMRI data. By integrating spatio-temporal features, the network classified subjects based on distinct neural patterns. Model generalizability was assessed using subject-wise k-fold cross-validation. Explainable artificial intelligence (XAI) methods were applied. stDNN achieved balanced accuracy rates of 71.0% in distinguishing controls from PD and up to 71.9% in middle-stage PD cases. It also demonstrated over 80% accuracy in differentiating healthy controls from iRBD. XAI analysis highlighted the involvement of fronto-parietal and temporal regions, including the dorsolateral prefrontal cortex, and anterior temporal gyri, in distinguishing controls from PD. In the comparison with iRBD, key contributing areas included the bilateral superior and medial frontal gyri, dorsolateral prefrontal cortex, parietal and occipital regions (lingual gyri and cuneus). This study demonstrates the potential of stDNN to differentiate between iRBD, PD, and controls using rs-fMRI data.
S. Basaia, S. Pisano, E. Sarasso et al.· npj Parkinson's Disease· 0 citations
Abstract Converging evidence supports a key pathogenic role of the glymphatic system in the accumulation of pathological aggregates in several central nervous system proteinopathies, including amyotrophic lateral sclerosis and other motor neuron diseases. This study aimed to investigate potential glymphatic impairment using diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) across motor neuron disease phenotypes, to examine its clinical correlates, and to assess its relationship with white matter damage. Fifty-seven patients with motor neuron disease and 32 age- and sex-matched healthy controls underwent a 3 Tesla brain MRI scan, including diffusion tensor imaging sequences. We obtained the DTI-ALPS index from each individual, evaluating its relationship with measures of motor and cognitive disability, site of symptom onset, cognitive status, genetic status and fractional anisotropy of white matter tracts. Comparisons between groups were evaluated using analysis of covariance adjusting for age, sex, local fractional anisotropy and white matter hyperintensity burden. Partial correlations with clinical and cognitive measures were also tested. Patients with motor neuron disease exhibited significantly lower DTI-ALPS index values relative to healthy controls (P = 0.05). Patients with bulbar onset had lower DTI-ALPS values than those with spinal onset (P = 0.017). Comparable DTI-ALPS values were found across patients with classical amyotrophic lateral sclerosis clinical presentation and predominant upper or lower motor neuron clinical presentations, with no effect of cognitive diagnosis or genetic status. DTI-ALPS exhibited a significant correlation with disease duration (r = −0.38, P = 0.01). Motor neuron disease patients presenting insomnia had significantly lower DTI-ALPS values compared to those without sleep disturbances (P = 0.002). Significant positive correlations were found between ALPS index and fractional anisotropy values across major white matter tracts, including the internal and external capsules, superior longitudinal fasciculi, anterior, posterior and superior corona radiata, posterior thalamic radiation, fornix and the genu and body of the corpus callosum. This study confirms the presence of altered interstitial fluid diffusivity dynamics across motor neuron disease phenotypes, with greater impairment observed in bulbar-onset cases, patients with longer disease duration, and those experiencing more pronounced sleep disturbances. These findings may support a potential pathogenic role of glymphatic failure in the accumulation of TAR DNA-binding protein 43 proteinopathy and widespread microstructural axonal damage in motor neuron diseases.
Ilaria Bottale, E. Spinelli, S. Basaia et al.· Brain Communications· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
