Early Prediction of Parkinson’s Disease from Brain MRI Images Using Convolutional Neural Network

2021 ◽  
Vol 11 (12) ◽  
pp. 3103-3109
Author(s):  
G. Prema Arokia Mary ◽  
N. Suganthi ◽  
M. S. Hema
Keyword(s):  
Neural Network ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Human Error ◽  
Brain Mri ◽  
Early Prediction ◽  
Healthy Individuals ◽  
Automatic Feature Extraction ◽  
Sensitivity Specificity ◽  
The Brain

The early diagnosis of Parkinson’s Disease (PD) is a challenging practice for doctors. Currently, there are no separate diagnostics and tests to be done to predict onset PD. However, the PD can be predicted through repeated clinical trials and tests. Sometimes, early prediction of PD can become tedious based on trials and tests. The computer-aided prediction will help medical professionals predict PD accurately during one’s onset stages to improve the PD patients’ quality of life. Hence, early prediction of PD is essential. In this article, Convolution Neural Networks (CNN) is proposed to classify PD patients and healthy individuals. The brain MRI images are given as input for the proposed methodology. The CNN deep neural network will first extract the features from the images. Then, it will classify the PD patients and healthy individuals from the extracted features. The automatic feature extraction will improve the accuracy of the classifier and reduce human error. The brain MRI images are taken from the PPMI dataset for experimentation. The sensitivity, specificity, and accuracy are calculated to assess the performance of the proposed methodology. The loss is also calculated to verify the performance of the classifier. It is observed that the CNN classifier has produced a higher accuracy of more than 98% in classifying PD patients and healthy individuals when compared to multi-layer perceptron deep learning.

Gene expression analysis in modeling Parkinson’s disease

2020 ◽  
pp. 103-104
Author(s):  
М.М. Руденок ◽  
А.Х. Алиева ◽  
А.А. Колачева ◽  
М.В. Угрюмов ◽  
П.А. Сломинский ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Early Stage ◽  
Systemic Disease ◽  
Molecular Genetic ◽  
Presymptomatic Stage ◽  
Whole Transcriptome Analysis ◽  
Whole Transcriptome ◽  
The Brain ◽  
Transcriptome Level

Несмотря на очевидный прогресс, достигнутый в изучении молекулярно-генетических факторов и механизмов патогенеза болезни Паркинсона (БП), в настоящее время стало ясно, что нарушения в структуре ДНК не описывают весь спектр патологических изменений, наблюдаемых при развитии заболевания. В настоящее время показано, что существенное влияние на патогенез БП могут оказывать изменения на уровне транскриптома. В работе были использованы мышиные модели досимптомной стадии БП, поздней досимптомной и ранней симптомной (РСС) стадиями БП. Для полнотранскриптомного анализа пулов РНК тканей черной субстанции и стриатума мозга мышей использовались микрочипы MouseRef-8 v2.0 Expression BeadChip Kit («Illumina», США). Полученные данные указывают на последовательное вовлечение транскриптома в патогенез БП, а также на то, что изменения на транскриптомном уровне процессов транспорта и митохондриального биогенеза могут играть важную роль в нейродегенерации при БП уже на самых ранних этапах. Parkinson’s disease (PD) is a complex systemic disease, mainly associated with the death of dopaminergic neurons. Despite the obvious progress made in the study of molecular genetic factors and mechanisms of PD pathogenesis, it has now become clear that violations in the DNA structure do not describe the entire spectrum of pathological changes observed during the development of the disease. It has now been shown that changes at the transcriptome level can have a significant effect on the pathogenesis of PD. The authors used models of the presymptomatic stage of PD with mice decapitation after 6 hours (6 h-PSS), presymptomatic stage with decapitation after 24 hours (24 h-PSS), advanced presymptomatic (Adv-PSS) and early symptomatic (ESS) stages of PD. For whole transcriptome analysis of RNA pools of the substantia nigra and mouse striatum, the MouseRef-8 v2.0 Expression BeadChip Kit microchips (Illumina, USA) were used. As a result of the analysis of whole transcriptome data, it was shown that, there are a greater number of statistically significant changes in the tissues of the brain and peripheral blood of mice with Adv-PSS and ESS models of PD compared to 6 h-PSS and 24 h-PSS models. In general, the obtained data indicate the sequential involvement of the transcriptome in the pathogenesis of PD, as well as the fact that changes at the transcriptome level of the processes of transport and mitochondrial biogenesis can play an important role in neurodegeneration in PD at an early stage.

Liposomes: Novel Drug Delivery Approach for Targeting Parkinson’s Disease

2020 ◽  
Vol 26 (37) ◽  
pp. 4721-4737 ◽  
Author(s):  
Bhumika Kumar ◽  
Mukesh Pandey ◽  
Faheem H. Pottoo ◽  
Faizana Fayaz ◽  
Anjali Sharma ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Drug Delivery ◽  
Parkinson's Disease ◽  
Side Effects ◽  
Blood Brain Barrier ◽  
Brain Barrier ◽  
Brain Targeting ◽  
Neural Cells ◽  
Blood Brain ◽  
The Brain

Parkinson’s disease is one of the most severe progressive neurodegenerative disorders, having a mortifying effect on the health of millions of people around the globe. The neural cells producing dopamine in the substantia nigra of the brain die out. This leads to symptoms like hypokinesia, rigidity, bradykinesia, and rest tremor. Parkinsonism cannot be cured, but the symptoms can be reduced with the intervention of medicinal drugs, surgical treatments, and physical therapies. Delivering drugs to the brain for treating Parkinson’s disease is very challenging. The blood-brain barrier acts as a highly selective semi-permeable barrier, which refrains the drug from reaching the brain. Conventional drug delivery systems used for Parkinson’s disease do not readily cross the blood barrier and further lead to several side-effects. Recent advancements in drug delivery technologies have facilitated drug delivery to the brain without flooding the bloodstream and by directly targeting the neurons. In the era of Nanotherapeutics, liposomes are an efficient drug delivery option for brain targeting. Liposomes facilitate the passage of drugs across the blood-brain barrier, enhances the efficacy of the drugs, and minimize the side effects related to it. The review aims at providing a broad updated view of the liposomes, which can be used for targeting Parkinson’s disease.

Neurotoxic and Neuroprotective Role of Exosomes in Parkinson’s Disease

2020 ◽  
Vol 25 (42) ◽  
pp. 4510-4522 ◽  
Author(s):  
Biancamaria Longoni ◽  
Irene Fasciani ◽  
Shivakumar Kolachalam ◽  
Ilaria Pietrantoni ◽  
Francesco Marampon ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Potential Role ◽  
Current Knowledge ◽  
Biological Fluids ◽  
Cell Communication ◽  
Target Cells ◽  
Cellular Debris ◽  
The Brain

: Exosomes are extracellular vesicles produced by eukaryotic cells that are also found in most biological fluids and tissues. While they were initially thought to act as compartments for removal of cellular debris, they are now recognized as important tools for cell-to-cell communication and for the transfer of pathogens between the cells. They have attracted particular interest in neurodegenerative diseases for their potential role in transferring prion-like proteins between neurons, and in Parkinson’s disease (PD), they have been shown to spread oligomers of α-synuclein in the brain accelerating the progression of this pathology. A potential neuroprotective role of exosomes has also been equally proposed in PD as they could limit the toxicity of α-synuclein by clearing them out of the cells. Exosomes have also attracted considerable attention for use as drug vehicles. Being nonimmunogenic in nature, they provide an unprecedented opportunity to enhance the delivery of incorporated drugs to target cells. In this review, we discuss current knowledge about the potential neurotoxic and neuroprotective role of exosomes and their potential application as drug delivery systems in PD.

Comparison of Cytocidal Activities of L-DOPA and Dopamine in S. cerevisiae and C. glabrata

2020 ◽  
Vol 16 (1) ◽  
pp. 90-93
Author(s):  
Carmen E. Iriarte ◽  
Ian G. Macreadie
Keyword(s):  
Saccharomyces Cerevisiae ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dopaminergic Neurons ◽  
Candida Glabrata ◽  
High Sensitivity ◽  
Time Dependent ◽  
Colony Forming Units ◽  
Dependent Cell ◽  
The Brain

Background: Parkinson's Disease results from a loss of dopaminergic neurons, and reduced levels of the neurotransmitter dopamine. Parkinson's Disease treatments involve increasing dopamine levels through administration of L-DOPA, which can cross the blood brain barrier and be converted to dopamine in the brain. The toxicity of dopamine has previously studied but there has been little study of L-DOPA toxicity. Methods: We have compared the toxicity of dopamine and L-DOPA in the yeasts, Saccharomyces cerevisiae and Candida glabrata by cell viability assays, measuring colony forming units. Results: L-DOPA and dopamine caused time-dependent cell killing in Candida glabrata while only dopamine caused such effects in Saccharomyces cerevisiae. The toxicity of L-DOPA is much lower than dopamine. Conclusion: Candida glabrata exhibits high sensitivity to L-DOPA and may have advantages for studying the cytotoxicity of L-DOPA.

scholarly journals Neuroinflammation and protein pathology in Parkinson’s disease dementia

2020 ◽  
Vol 8 (1) ◽  
Author(s):  
Antonina Kouli ◽  
Marta Camacho ◽  
Kieren Allinson ◽  
Caroline H. Williams-Gray
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
T Lymphocytes ◽  
Substantia Nigra ◽  
Amyloid Β ◽  
Brain Regions ◽  
Parkinson’S Disease Dementia ◽  
Activated Microglia ◽  
Cell Counts ◽  
The Brain

AbstractParkinson’s disease dementia is neuropathologically characterized by aggregates of α-synuclein (Lewy bodies) in limbic and neocortical areas of the brain with additional involvement of Alzheimer’s disease-type pathology. Whilst immune activation is well-described in Parkinson’s disease (PD), how it links to protein aggregation and its role in PD dementia has not been explored. We hypothesized that neuroinflammatory processes are a critical contributor to the pathology of PDD. To address this hypothesis, we examined 7 brain regions at postmortem from 17 PD patients with no dementia (PDND), 11 patients with PD dementia (PDD), and 14 age and sex-matched neurologically healthy controls. Digital quantification after immunohistochemical staining showed a significant increase in the severity of α-synuclein pathology in the hippocampus, entorhinal and occipitotemporal cortex of PDD compared to PDND cases. In contrast, there was no difference in either tau or amyloid-β pathology between the groups in any of the examined regions. Importantly, we found an increase in activated microglia in the amygdala of demented PD brains compared to controls which correlated significantly with the extent of α-synuclein pathology in this region. Significant infiltration of CD4+ T lymphocytes into the brain parenchyma was commonly observed in PDND and PDD cases compared to controls, in both the substantia nigra and the amygdala. Amongst PDND/PDD cases, CD4+ T cell counts in the amygdala correlated with activated microglia, α-synuclein and tau pathology. Upregulation of the pro-inflammatory cytokine interleukin 1β was also evident in the substantia nigra as well as the frontal cortex in PDND/PDD versus controls with a concomitant upregulation in Toll-like receptor 4 (TLR4) in these regions, as well as the amygdala. The evidence presented in this study show an increased immune response in limbic and cortical brain regions, including increased microglial activation, infiltration of T lymphocytes, upregulation of pro-inflammatory cytokines and TLR gene expression, which has not been previously reported in the postmortem PDD brain.

S-CCCapsule: Pneumonia detection in chest X-ray images using skip-connected convolutions and capsule neural network

2021 ◽  
pp. 1-25
Author(s):  
Kwabena Adu ◽  
Yongbin Yu ◽  
Jingye Cai ◽  
Victor Dela Tattrah ◽  
James Adu Ansere ◽  
...  
Keyword(s):  
Neural Network ◽  
Human Error ◽  
Medical Center ◽  
Confusion Matrix ◽  
Area Under The Curve ◽  
Dynamic Routing ◽  
Sigmoid Function ◽  
Radiological Society ◽  
Chest X Ray ◽  
Sensitivity Specificity

The squash function in capsule networks (CapsNets) dynamic routing is less capable of performing discrimination of non-informative capsules which leads to abnormal activation value distribution of capsules. In this paper, we propose vertical squash (VSquash) to improve the original squash by preventing the activation values of capsules in the primary capsule layer to shrink non-informative capsules, promote discriminative capsules and avoid high information sensitivity. Furthermore, a new neural network, (i) skip-connected convolutional capsule (S-CCCapsule), (ii) Integrated skip-connected convolutional capsules (ISCC) and (iii) Ensemble skip-connected convolutional capsules (ESCC) based on CapsNets are presented where the VSquash is applied in the dynamic routing. In order to achieve uniform distribution of coupling coefficient of probabilities between capsules, we use the Sigmoid function rather than Softmax function. Experiments on Guangzhou Women and Children’s Medical Center (GWCMC), Radiological Society of North America (RSNA) and Mendeley CXR Pneumonia datasets were performed to validate the effectiveness of our proposed methods. We found that our proposed methods produce better accuracy compared to other methods based on model evaluation metrics such as confusion matrix, sensitivity, specificity and Area under the curve (AUC). Our method for pneumonia detection performs better than practicing radiologists. It minimizes human error and reduces diagnosis time.

Sign in / Sign up

Export Citation Format

Share Document