RESUMO

In recent years, Artificial Intelligence has been used to assist healthcare professionals in detecting and diagnosing neurodegenerative diseases. In this study, we propose a methodology to analyze functional Magnetic Resonance Imaging signals and perform classification between Parkinson's disease patients and healthy participants using Machine Learning algorithms. In addition, the proposed approach provides insights into the brain regions affected by the disease. The functional Magnetic Resonance Imaging from the PPMI and 1000-FCP datasets were pre-processed to extract time series from 200 brain regions per participant, resulting in 11,600 features. Causal Forest and Wrapper Feature Subset Selection algorithms were used for dimensionality reduction, resulting in a subset of features based on their heterogeneity and association with the disease. We utilized Logistic Regression and XGBoost algorithms to perform PD detection, achieving 97.6% accuracy, 97.5% F1 score, 97.9% precision, and 97.7%recall by analyzing sets with fewer than 300 features in a population including men and women. Finally, Multiple Correspondence Analysis was employed to visualize the relationships between brain regions and each group (women with Parkinson, female controls, men with Parkinson, male controls). Associations between the Unified Parkinson's Disease Rating Scale questionnaire results and affected brain regions in different groups were also obtained to show another use case of the methodology. This work proposes a methodology to (1) classify patients and controls with Machine Learning and Causal Forest algorithm and (2) visualize associations between brain regions and groups, providing high-accuracy classification and enhanced interpretability of the correlation between specific brain regions and the disease across different groups.

Assuntos

RESUMO

Although social functioning relies on working memory, whether a social-specific mechanism exists remains unclear. This undermines the characterization of neurodegenerative conditions with both working memory and social deficits. We assessed working memory domain-specificity across behavioral, electrophysiological, and neuroimaging dimensions in 245 participants. A novel working memory task involving social and non-social stimuli with three load levels was assessed across controls and different neurodegenerative conditions with recognized impairments in: working memory and social cognition (behavioral-variant frontotemporal dementia); general cognition (Alzheimer's disease); and unspecific patterns (Parkinson's disease). We also examined resting-state theta oscillations and functional connectivity correlates of working memory domain-specificity. Results in controls and all groups together evidenced increased working memory demands for social stimuli associated with frontocinguloparietal theta oscillations and salience network connectivity. Canonical frontal theta oscillations and executive-default mode network anticorrelation indexed non-social stimuli. Behavioral-variant frontotemporal dementia presented generalized working memory deficits related to posterior theta oscillations, with social stimuli linked to salience network connectivity. In Alzheimer's disease, generalized working memory impairments were related to temporoparietal theta oscillations, with non-social stimuli linked to the executive network. Parkinson's disease showed spared working memory performance and canonical brain correlates. Findings support a social-specific working memory and related disease-selective pathophysiological mechanisms.

Assuntos

RESUMO

OBJECTIVE: The aim of this study is to compare a portable ultrasound (US) device and a traditional US for performing transcranial ultrasonography (CCT) in patients with Parkinson's disease (PD). METHODS: This is a cross-sectional, observational, and analytical study. The study recruited a total of 129 individuals from two public hospitals in the city of Rio de Janeiro in a prospective and non-randomized manner between September 2019 and July 2021 as follows: group A with 31 patients with PD, group B with 65 patients with PD, and group C with 64 healthy individuals. Group A was used to collect data to establish the agreement analysis of the TCS measurements between the two devices. Groups B and C provided data for constructing the receiver operating characteristic curve for the handheld US. The subjects underwent the assessment of the transtemporal bone window (TW) quality, the mesencephalon area, the size of the third ventricle, and the substantia nigra (SN) hyperechogenicity area. RESULTS: There was a good agreement between the methods regarding the quality of the TW-Kappa concordance coefficient of 100% for the right TW and 83% for the left, the midbrain area-intraclass correlation coefficient (ICC) of 69%, the SN area ICC = 90% for the right SN and 93% for the left and the size of the third ventricle ICC = 96%. The cutoff point for the SN echogenic area in the handheld US was 0.20 cm2 . CONCLUSIONS: The handheld US is a viable imaging method for performing TCS because it shows good agreement with the measurements performed with traditional equipment, and the measurement of SN echogenic area for PD diagnosis presents good sensitivity and specificity.

Assuntos

RESUMO

INTRODUCTION: Nonspecific areas of brain white matter hyperintensity (WMH) are commonly found in the elderly. Some studies have shown that the presence, quantity, and location of WMHs may be associated with the development of cognitive and motor decline in patients with Parkinson's disease (PD), but the results remain controversial. This study aimed to evaluate the relationship of WMH to motor and non-motor symptoms, including dysautonomia and rapid eye movement sleep behavior disorder (RBD), in patients with PD. METHODS: Brain magnetic resonance images were acquired from 120 patients diagnosed with PD and analyzed for WMH classification and quantification. Motor symptoms were quantified using sub-scores of the Movement Disorder Society-Unified Parkinson Disease Rating Scale (MDS-UPDRS)-III. Dysautonomia was evaluated by autonomic reactivity tests, and polysomnography was used for the diagnosis of RBD. RESULTS: Age, total value of the MDS-UPDRS-III tremor sub-score, and the presence of dysautonomia were found to be linearly positively associated. Specifically, the duration of PD was positively associated with rigidity, bradykinesia, axial symptoms, prevalence of dysautonomia, and RBD sub-scores. However, in the multivariate analysis adjusted for variables of interest, no statistical significance was found for any of the models. CONCLUSION: The presence, quantity, and location of WMH were not associated with the analyzed motor and non-motor manifestations of PD.

Assuntos

RESUMO

The underlying causes of Parkinson's disease are complex, and besides recent advances in elucidating relevant disease mechanisms, no disease-modifying treatments are currently available. One proposed pathophysiological hallmark is mitochondrial dysfunction, and a plethora of evidence points toward the interconnected nature of mitochondria in neuronal homeostasis. This also extends to iron and neuromelanin metabolism, two biochemical processes highly relevant to individual disease manifestation and progression. Modern neuroimaging methods help to gain in vivo insights into these intertwined pathways and may pave the road to individualized medicine in this debilitating disorder. In this narrative review, we will highlight the biological rationale for studying these pathways, how distinct neuroimaging methods can be applied in patients, their respective limitations, and which challenges need to be overcome for successful implementation in clinical studies.

Assuntos

RESUMO

BACKGROUND: the diagnosis of Parkinson's disease (PD) can be challenging, especially in the early stages, albeit its updated and validated clinical criteria. Recent developments on neuroimaging in PD, altogether with its consolidated role of excluding secondary and other neurodegenerative causes of parkinsonism, provide more confidence in the diagnosis across the different stages of the disease. This review highlights current knowledge and major recent advances in magnetic resonance and dopamine transporter imaging in aiding PD diagnosis. OBJECTIVE: This study aims to review current knowledge about the role of magnetic resonance imaging and neuroimaging of the dopamine transporter in diagnosing Parkinson's disease. METHODS: We performed a non-systematic literature review through the PubMed database, using the keywords "Parkinson", "magnetic resonance imaging", "diffusion tensor", "diffusion-weighted", "neuromelanin", "nigrosome-1", "single-photon emission computed tomography", "dopamine transporter imaging". The search was restricted to articles written in English, published between January 2010 and February 2022. RESULTS: The diagnosis of Parkinson's disease remains a clinical diagnosis. However, new neuroimaging biomarkers hold promise for increased diagnostic accuracy, especially in earlier stages of the disease. CONCLUSION: Future validation of new imaging biomarkers bring the expectation of an increased neuroimaging role in the diagnosis of PD in the following years.

Assuntos

RESUMO

OBJECTIVE: Prelemniscal radiation (Raprl) lesions and deep brain stimulation effectively control motor symptoms of Parkinson disease, but individual variations in the stereotactic location of its fiber components constitute a significant concern. The objective of this study was to determine individual variations in the stereotactic location of fiber tracts composing Raprl. METHODS: Raprl fiber composition was determined in a group of 10 Parkinson patients and 10 matched controls using 3T magnetic resonance imaging, brain imaging processed for diffusion-weighted images, tract density imaging, and constrained spherical deconvolution. The stereotactic position of the point of maximal proximity (PMP), which is the point where the most significant number of fibers is concentrated in the smallest volume in the tractography, was evaluated in the right and left hemispheres of the same person, between individuals and between patients and controls for each tract in coordinates "x," "y," and "z." The stereotactic coordinates at which PMP of all tracts meet were statistically determined, representing the recommended aim for this target. RESULTS: Stereotactic coordinates of the 3 fiber tracts composing Raprl, cerebellar-thalamic-cortical, globus pallidus-peduncle-pontine nucleus, and mesencephalic-orbital frontal cortex, did not vary between right and left hemispheres in the same person and between patients and controls. In contrast, PMP variability between individuals was significant, mainly for the mesencephalic-orbitofrontal tract. Therefore, probabilistic tractography can better determine individual variations to plan electrode trajectories. CONCLUSIONS: Individual PMP variations for fiber tracts in Raprl, identified by probabilistic tractography, provide a platform for planning the stereotactic approach to conform volumes for deep brain stimulation and lesions.

Assuntos

RESUMO

Animal models of Parkinson's disease are useful to evaluate new treatments and to elucidate the etiology of the disease. Hence, it is necessary to have methods that allow quantification of their effectiveness. [18 F]FDOPA-PET (FDOPA-PET) imaging is outstanding for this purpose because of its capacity to measure changes in the dopaminergic pathway noninvasively and in vivo. Nevertheless, PET acquisition and quantification is time-consuming making it necessary to find faster ways to quantify FDOPA-PET data. This study evaluated Male Wistar rats by FDOPA, before and after being partially injured with 6-OHDA unilaterally. MicroPET scans with a duration of 120 min were acquired and Patlak reference plots were created to estimate the influx constant Kc in the striatum using the full dynamic scan data. Additionally, simple striatal-to-cerebral ratios (SCR) of short static acquisitions were computed and compared with the Kc values. Good correlation (r > 0.70) was obtained between Kc and SCR, acquired between 80-120 min after FDOPA administration with frames of 10 or 20 min and both methods were able to separate the FDOPA-uptake of healthy controls from that of the PD model (SCR -28%, Kc -71%). The present study concludes that Kc and SCR can be trustfully used to discriminate partially lesioned rats from healthy controls.

Assuntos

Assuntos

RESUMO

BACKGROUND AND OBJECTIVE: Parkinson's disease (PD) is a motor neurodegenerative disease principally manifested by motor disabilities, such as postural instability, bradykinesia, tremor, and stiffness. In clinical practice, there exist several diagnostic rating scales that coarsely allow the measurement, characterization and classification of disease progression. These scales, however, are only based on strong changes in kinematic patterns, and the classification remains subjective, depending on the expertise of physicians. In addition, even for experts, disease analysis based on independent classical motor patterns lacks sufficient sensitivity to establish disease progression. Consequently, the disease diagnosis, stage, and progression could be affected by misinterpretations that lead to incorrect or inefficient treatment plans. This work introduces a multimodal non-invasive strategy based on video descriptors that integrate patterns from gait and eye fixation modalities to assist PD quantification and to support the diagnosis and follow-up of the patient. The multimodal representation is achieved from a compact covariance descriptor that characterizes postural and time changes of both information sources to improve disease classification. METHODS: A multimodal approach is introduced as a computational method to capture movement abnormalities associated with PD. Two modalities (gait and eye fixation) are recorded in markerless video sequences. Then, each modality sequence is represented, at each frame, by primitive features composed of (1) kinematic measures extracted from a dense optical flow, and (2) deep features extracted from a convolutional network. The spatial distributions of these characteristics are compactly coded in covariance matrices, making it possible to map each particular dynamic in a Riemannian manifold. The temporal mean covariance is then computed and submitted to a supervised Random Forest algorithm to obtain a disease prediction for a particular patient. The fusion of the covariance descriptors and eye movements integrating deep and kinematic features is evaluated to assess their contribution to disease quantification and prediction. In particular, in this study, the gait quantification is associated with typical patterns observed by the specialist, while ocular fixation, associated with early disease characterization, complements the analysis. RESULTS: In a study conducted with 13 control subjects and 13 PD patients, the fusion of gait and ocular fixation, integrating deep and kinematic features, achieved an average accuracy of 100% for early and late fusion. The classification probabilities show high confidence in the prediction diagnosis, the control subjects probabilities being lower than 0.27 with early fusion and 0.3 with late fusion, and those of the PD patients, being higher than 0.62 with early fusion and 0.51 with late fusion. Furthermore, it is observed that higher probability outputs are correlated with more advanced stages of the disease, according to the H&Y scale. CONCLUSIONS: A novel approach for fusing motion modalities captured in markerless video sequences was introduced. This multimodal integration had a remarkable discrimination performance in a study conducted with PD and control patients. The representation of compact covariance descriptors from kinematic and deep features suggests that the proposed strategy is a potential tool to support diagnosis and subsequent monitoring of the disease. During fusion it was observed that devoting major attention to eye fixational patterns may contribute to a better quantification of the disease, especially at stage 2.

Assuntos