Parkinson disease (PD) is amongst the relatively prevalent neurodegenerative disorders with its course of progression classified as prodromal, stage1, 2, 3 and sever conditions. With all the shortcomings in clinical setting, it is often challenging to identify the stage of PD severity and predict its progression course. Therefore, there appear to be an ever-growing need need to use supervised and unsupervised artificial intelligence and machine learning methods on clinical and paraclinical datasets to accurately diagnose PD, identify its stage and predict its course. In today neuro-medicine practices, MRI-related data are regarded beneficial in detecting various pathologies in the brain. In addition, the field has recently witnessed a growing application of deep learning methods in image processing often with outstanding results. Here, we applied Convolutional Neural Networks (CNN) to propose a model helping to distinguish different stages of PD. The results showed that our current MRI-based CNN model may potentially be employed as a suitable method for the distinction of PD stages at a high accuracy rate (0.94).

Background: A proper explanation for perceptual symptoms in neurodegenerative disorders including Alzheimer’s disease and Parkinson’s disease (PD) is still lacking. Objective: This study aimed at investigating the imbalance between ‘bottom-up’ and ‘top-down’ information flow (IF) and processing in PD in relation with visual hallucination symptoms. Methods: Here, we looked at bottom-up and top-down IF markers using resting state electroencephalographic (EEG) data from PD patients analyzed through three different IF measures (direct Directed Transfer Function (dDTF), full frequency Directed Transfer Function (ff-DTF), and renormalized Partial Directed Coherence (rPDC). Results: We observed an increased gamma band IF and a reduced beta band IF in PD patients compared to healthy controls. Additionally, we noticed a reduced theta band IF in PD patients using dDTF as a measure of IF. By source localizing the EEG activity of the PD patients and healthy controls, we looked at the alterations of IF in the prefrontal cortex of PD patients as well. Conclusion: In line with previous studies, our results suggest that the delicate balance between bottom-up and top-down IF is disrupted in Parkinson’s disease potentially contributing to the cognitive symptoms of PD patients.

Background and Objectives: Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) are the two most common neurodevelopmental disorders often with overlapping symptoms. Misdiagnosis of these disorders is the leading cause of a variety of problems including inappropriate interventions and improper treatment outcome. Over the last few years, resting state functional magnetic Resonance imaging (rs-fMRI) has received clinical attention among other beneficial brain scan techniques to extract functional connectivity in the brain. However, extracting useful information by human observation is prone to errors. Material and Methods: The above unmet need prompted us to design the present investigation to construct a convolutional neural network model with 12 layers architecture in rsFMRI data aiming to differentiate the two conditions. The rs-fMRI data was collected from the ADHD-200 and ABIDE to feed into a convolutional neural network. Over the preprocessing phase, we have removed undesirable data and coordinated the remaining to MSDL atlas to recruit 39 regions of the brain. Results: Ultimately, out results obtained a 0.92 accuracy, an AUC of 0.97 and loss of 0.17 in classification and discrimination of ADHD and ASD. Conclusion: Though cross-validity with larger datasets is deemed required, the results obtained from the present investigation suggest that convolutional neural network may serve as a beneficial tool to differentiate ADHD and ASD from relatively small fMRI datasets. This further highlights the potential application of deep neural networks for serving the above purpose.