Hippocampal, basal ganglia and olfactory connectivity contribute to cognitive impairments in Parkinson's disease

Detection of Marchiafava Bignami disease using distinct deep learning techniques in medical diagnostics

PURPOSE

To detect the Marchiafava Bignami Disease (MBD) using a distinct deep learning technique.

BACKGROUND

Advanced deep learning methods are becoming more crucial in contemporary medical diagnostics, particularly for detecting intricate and uncommon neurological illnesses such as MBD. This rare neurodegenerative disorder, sometimes associated with persistent alcoholism, is characterized by the loss of myelin or tissue death in the corpus callosum. It poses significant diagnostic difficulties owing to its infrequency and the subtle signs it exhibits in its first stages, both clinically and on radiological scans.

METHODS

The novel method of Variational Autoencoders (VAEs) in conjunction with attention mechanisms is used to identify MBD peculiar diseases accurately. VAEs are well-known for their proficiency in unsupervised learning and anomaly detection. They excel at analyzing extensive brain imaging datasets to uncover subtle patterns and abnormalities that traditional diagnostic approaches may overlook, especially those related to specific diseases. The use of attention mechanisms enhances this technique, enabling the model to concentrate on the most crucial elements of the imaging data, similar to the discerning observation of a skilled radiologist. Thus, we utilized the VAE with attention mechanisms in this study to detect MBD. Such a combination enables the prompt identification of MBD and assists in formulating more customized and efficient treatment strategies.

RESULTS

A significant breakthrough in this field is the creation of a VAE equipped with attention mechanisms, which has shown outstanding performance by achieving accuracy rates of over 90% in accurately differentiating MBD from other neurodegenerative disorders.

CONCLUSION

This model, which underwent training using a diverse range of MRI images, has shown a notable level of sensitivity and specificity, significantly minimizing the frequency of false positive results and strengthening the confidence and dependability of these sophisticated automated diagnostic tools.

Cholinergic innervation topography in GBA-associated de novo Parkinson's disease patients

The most common genetic risk factors for Parkinson's disease are GBA1 mutations, encoding the lysosomal enzyme glucocerebrosidase. Patients with GBA1 mutations (GBA-PD) exhibit earlier age of onset and faster disease progression with more severe cognitive impairments, postural instability and gait problems. These GBA-PD features suggest more severe cholinergic system pathologies. PET imaging with the vesicular acetylcholine transporter ligand 18F-F-fluoroethoxybenzovesamicol (18F-FEOBV PET) provides the opportunity to investigate cholinergic changes and their relationship to clinical features in GBA-PD. The study investigated 123 newly diagnosed, treatment-naïve Parkinson's disease subjects-with confirmed presynaptic dopaminergic deficits on PET imaging. Whole-gene GBA1 sequencing of saliva samples was performed to evaluate GBA1 variants. Patients underwent extensive neuropsychological assessment of all cognitive domains, motor evaluation with the Unified Parkinson's Disease Rating Scale, brain MRI, dopaminergic PET to measure striatal-to-occipital ratios of the putamen and 18F-FEOBV PET. We investigated differences in regional cholinergic innervation between GBA-PD carriers and non-GBA1 mutation carriers (non-GBA-PD), using voxel-wise and volume of interest-based approaches. The degree of overlap between t-maps from two-sample t-test models was quantified using the Dice similarity coefficient. Seventeen (13.8%) subjects had a GBA1 mutation. No significant differences were found in clinical features and dopaminergic ratios between GBA-PD and non-GBA-PD at diagnosis. Lower 18F-FEOBV binding was found in both the GBA-PD and non-GBA-PD groups compared to controls. Dice (P < 0.05, cluster size 100) showed good overlap (0.7326) between the GBA-PD and non-GBA-PD maps. GBA-PD patients showed more widespread reduction in 18F-FEOBV binding than non-GBA-PD when compared to controls in occipital, parietal, temporal and frontal cortices (P < 0.05, FDR-corrected). In volume of interest analyses (Bonferroni corrected), the left parahippocampal gyrus was more affected in GBA-PD. De novo GBA-PD show a distinct topography of regional cholinergic terminal ligand binding. Although the Parkinson's disease groups were not distinguishable clinically, in comparison to healthy controls, GBA-PD showed more extensive cholinergic denervation compared to non-GBA-PD. A larger group is needed to validate these findings. Our results suggest that de novo GBA-PD and non-GBA-PD show differential patterns of cholinergic system changes before clinical phenotypic differences between carriers versus non-carrier groups are observable.

Connectome-based predictive modelling estimates individual cognitive status in Parkinson's disease

INTRODUCTION

The progressive nature of Parkinson's disease (PD) affords emphasis on accurate early-stage individual-level assessment of risk and intervention appropriateness. In PD, cognitive impairment (CI) may follow or precede motor symptoms but are generally underdetected. In addition to impeding daily functioning and quality of life, CIs increase the risk for later conversion to dementia, providing a pressing need to develop novel tools to detect and interpret them. Connectome-based predictive modelling (CPM) is an emerging machine-learning approach to individual prediction that holds translational promise due to its noninvasiveness and simple implementation. The aim of this study was to investigate CPM's potential to predict and understand CIs in PD.

METHODS

Resting-state functional connectivity from 58 patients with PD of varying cognitive status was used to train a CPM-model to predict a global cognitive composite (GCC) score. The model was validated using cross-validation, permutation testing, and internal stability analyses. The combined predictive strength of two brain connectivity networks, positive and negative, directly and inversely correlated with GCC, respectively, was assessed.

RESULTS

The model significantly predicted individual GCC scores, r = 0.63, pperm < .05. Separately, the positive and negative networks were similar in performance, rs ≥ .58, ps < .05, but varied in anatomical distribution.

CONCLUSIONS

This study identified a connectome predictive of cognitive scores in PD, with features overlapping with established and emerging evidence on aberrant connectivity in PD-related CIs. Overall, CPM appears promising for clinical translation in this population, but longitudinal studies with out-of-sample validation are needed.

Pathobiology of Cognitive Impairment in Parkinson Disease: Challenges and Outlooks

Cognitive impairment (CI) is a characteristic non-motor feature of Parkinson disease (PD) that poses a severe burden on the patients and caregivers, yet relatively little is known about its pathobiology. Cognitive deficits are evident throughout the course of PD, with around 25% of subtle cognitive decline and mild CI (MCI) at the time of diagnosis and up to 83% of patients developing dementia after 20 years. The heterogeneity of cognitive phenotypes suggests that a common neuropathological process, characterized by progressive degeneration of the dopaminergic striatonigral system and of many other neuronal systems, results not only in structural deficits but also extensive changes of functional neuronal network activities and neurotransmitter dysfunctions. Modern neuroimaging studies revealed multilocular cortical and subcortical atrophies and alterations in intrinsic neuronal connectivities. The decreased functional connectivity (FC) of the default mode network (DMN) in the bilateral prefrontal cortex is affected already before the development of clinical CI and in the absence of structural changes. Longitudinal cognitive decline is associated with frontostriatal and limbic affections, white matter microlesions and changes between multiple functional neuronal networks, including thalamo-insular, frontoparietal and attention networks, the cholinergic forebrain and the noradrenergic system. Superimposed Alzheimer-related (and other concomitant) pathologies due to interactions between α-synuclein, tau-protein and β-amyloid contribute to dementia pathogenesis in both PD and dementia with Lewy bodies (DLB). To further elucidate the interaction of the pathomechanisms responsible for CI in PD, well-designed longitudinal clinico-pathological studies are warranted that are supported by fluid and sophisticated imaging biomarkers as a basis for better early diagnosis and future disease-modifying therapies.