Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 42.936
Filtrar
2.
Radiographics ; 40(7): 1866-1892, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-33136488

RESUMEN

Infection with severe acute respiratory syndrome coronavirus 2 results in coronavirus disease 2019 (COVID-19), which was declared an official pandemic by the World Health Organization on March 11, 2020. COVID-19 has been reported in most countries, and as of August 15, 2020, there have been over 21 million cases of COVID-19 reported worldwide, with over 800 000 COVID-19-associated deaths. Although COVID-19 predominantly affects the respiratory system, it has become apparent that many other organ systems can also be involved. Imaging plays an essential role in the diagnosis of all manifestations of the disease and its related complications, and proper utilization and interpretation of imaging examinations is crucial. A comprehensive understanding of the diagnostic imaging hallmarks, imaging features, multisystem involvement, and evolution of imaging findings is essential for effective patient management and treatment. In part 1 of this article, the authors described the viral pathogenesis, diagnostic imaging hallmarks, and manifestations of the pulmonary and peripheral and central vascular systems of COVID-19. In part 2 of this article, the authors focus on the key imaging features of the varied pathologic manifestations of COVID-19, involving the cardiac, neurologic, abdominal, dermatologic and ocular, and musculoskeletal systems, as well as the pediatric and pregnancy-related manifestations of the virus. Online supplemental material is available for this article. ©RSNA, 2020.


Asunto(s)
Infecciones por Coronavirus/complicaciones , Infecciones por Coronavirus/diagnóstico por imagen , Neumonía Viral/complicaciones , Neumonía Viral/diagnóstico por imagen , Adolescente , Adulto , Anciano , Enfermedades Asintomáticas , Betacoronavirus , Encéfalo/diagnóstico por imagen , Sistema Cardiovascular/diagnóstico por imagen , Niño , Infecciones por Coronavirus/diagnóstico , Femenino , Tracto Gastrointestinal/diagnóstico por imagen , Humanos , Recién Nacido , Pulmón/diagnóstico por imagen , Imagen por Resonancia Magnética , Masculino , Persona de Mediana Edad , Pandemias , Neumonía Viral/diagnóstico , Embarazo , Complicaciones Infecciosas del Embarazo/diagnóstico por imagen , Radiografía , Evaluación de Síntomas , Tomografía Computarizada por Rayos X
3.
Brain Nerve ; 72(11): 1263-1273, 2020 Nov.
Artículo en Japonés | MEDLINE | ID: mdl-33191304

RESUMEN

Because higher-order cognitive functions are supposed to be executed by the interplay between various brain regions, it is necessary to elucidate the neural communication between brain regions to understand the purpose of understanding the mechanism of such brain functions. Therefor, functional connectivity analysis has been rapidly gaining in importance. This is an analysis that illuminates the spatiotemporal dynamics at the whole-brain level based on the functional or effective connections, defined by a statistical correlation or a causal relation of neural activities between brain regions. The present manuscript primarily provides the basic idea of functional connectivity analysis, and then introduces representative methods. Finally, the approaches to the diagnosis of neurological diseases based on this analysis are introduced.


Asunto(s)
Mapeo Encefálico , Encéfalo , Encéfalo/diagnóstico por imagen , Cognición , Humanos , Imagen por Resonancia Magnética , Vías Nerviosas
4.
Medicine (Baltimore) ; 99(44): e22911, 2020 Oct 30.
Artículo en Inglés | MEDLINE | ID: mdl-33126348

RESUMEN

The aim of this study was to investigate the clinical characteristics of central nervous system (CNS) aspergillosis in immunocompetent patients.This study enrolled six immunocompetent patients diagnosed with CNS aspergillosis. Additionally, we reviewed the clinical profiles for 28 cases reported in the literature. The age, gender, etiology of Aspergillus infection, clinical manifestations, location of the lesion, treatment, and prognosis were analyzed.There were 19 men (average age, 54.6 ±â€Š14.3 years) and 15 women (average age, 47.0 ±â€Š19.4 years). The clinical manifestations included headache (55.9%; n = 19), visual impairment (32.4%; n = 11), diplopia (32.4%; n = 11), hemiplegia (20.6%; n = 7), fever (17.6%; n = 6), and epilepsy (8.8%; n = 3). According to the radiological features, CNS aspergillosis lesions were divided into two subtypes: parenchymal lesions in the cerebral lobes (n = 11), and meningeal lesions in the meninges (n = 23). The patients with meningeal lesions are easy to be complicated with more serious cerebrovascular diseases, such as subarachnoid hemorrhage and massive infarction. Most of the lesions in brain parenchyma were abscess formation, and magnetic resonance imaging showed ring enhancement. The clinical diagnosis of Aspergillus infection was mainly based on brain biopsy (n = 14), autopsy (n = 8), pathological examination of adjacent brain tissues (n = 7), cerebrospinal fluid (CSF) or tissue culture (n = 3), and second-generation sequencing analysis of the CSF (n = 3). Clinical improvement was achieved in 23 cases, and 11 patients succumbed to the disease. Voriconazole treatment was effective in 24 (70.6%) cases.Immunocompetent subjects are also at risk for Aspergillus infections. Concomitant cerebrovascular diseases are common in patients with CNS aspergillosis, especially in patients with meningeal aspergillosis. Parenchymal aspergillosis lesions are usually localized and manifest as brain abscesses with annular enhancement on magnetic resonance imaging. Biopsy, CSF culture, and next-generation sequencing are mainstream diagnostic modalities. Voriconazole is an effective treatment for Aspergillus infection, and early diagnosis and treatment should be highlighted.


Asunto(s)
Absceso Encefálico , Encéfalo , Inmunocompetencia , Meningitis Fúngica , Neuroaspergilosis , Hemorragia Subaracnoidea , Voriconazol/uso terapéutico , Adulto , Antifúngicos/uso terapéutico , Biopsia/métodos , Encéfalo/diagnóstico por imagen , Encéfalo/microbiología , Encéfalo/patología , Absceso Encefálico/diagnóstico , Absceso Encefálico/etiología , Diagnóstico , Femenino , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , Meningitis Fúngica/diagnóstico , Meningitis Fúngica/etiología , Persona de Mediana Edad , Neuroaspergilosis/líquido cefalorraquídeo , Neuroaspergilosis/diagnóstico , Neuroaspergilosis/tratamiento farmacológico , Neuroaspergilosis/fisiopatología , Hemorragia Subaracnoidea/diagnóstico , Hemorragia Subaracnoidea/etiología , Tomografía Computarizada por Rayos X/métodos , Resultado del Tratamiento
5.
Medicine (Baltimore) ; 99(43): e22626, 2020 Oct 23.
Artículo en Inglés | MEDLINE | ID: mdl-33120751

RESUMEN

RATIONALE: Paradoxical reaction/immune reconstitution inflammatory syndrome is common in patients with central nervous system tuberculosis. Management relies on high-dose corticosteroids and surgery when feasible. PATIENT CONCERN: We describe 2 cases of HIV-negative patients with corticosteroid-refractory paradoxical reactions of central nervous system tuberculosis. DIAGNOSES: The 2 patients experienced clinical impairment shortly after starting therapy for TB, and magnetic resonance imaging showed the presence of tuberculomas, leading to the diagnosis of a paradoxical reaction. INTERVENTIONS: We added infliximab, an anti-tumor necrosis factor (TNF)-alpha monoclonal antibody, to the dexamethasone. OUTCOMES: Both patients had favorable outcomes, 1 achieving full recovery but 1 suffering neurologic sequelae. LESSONS: Clinicians should be aware of the risk of paradoxical reactions/immune reconstitution inflammatory syndrome when treating patients with tuberculosis of the central nervous system and should consider the prompt anti-TNF-α agents in cases not responding to corticosteroids.


Asunto(s)
Encéfalo/efectos de los fármacos , Tuberculosis del Sistema Nervioso Central/tratamiento farmacológico , Inhibidores del factor de Necrosis Tumorales/uso terapéutico , Adulto , Encéfalo/diagnóstico por imagen , Encéfalo/inmunología , Encéfalo/patología , Femenino , Humanos , Síndrome Inflamatorio de Reconstitución Inmune/etiología , Síndrome Inflamatorio de Reconstitución Inmune/patología , Masculino , Persona de Mediana Edad , Tuberculosis del Sistema Nervioso Central/complicaciones , Adulto Joven
6.
Artículo en Inglés | MEDLINE | ID: mdl-33017931

RESUMEN

Affective personality traits have been associated with a risk of developing mental and cognitive disorders and can be informative for early detection and management of such disorders. However, conventional personality trait detection is often biased and unreliable, as it depends on the honesty of the subjects when filling out the lengthy questionnaires. In this paper, we propose a method for objective detection of personality traits using physiological signals. Subjects are shown affective images and videos to evoke a range of emotions. The electrical activity of the brain is captured using EEG during this process and the multi-channel EEG data is processed to compute the inter-hemispheric asynchrony of the brainwaves. The most discriminative features are selected and then used to build a machine learning classifier, which is trained to predict 16 personality traits. Our results show high predictive accuracy for both image and video stimuli individually, and an improvement when the two stimuli are combined, achieving a 95.49% accuracy. Most of the selected discriminative features were found to be extracted from the alpha frequency band. Our work shows that personality traits can be accurately detected with EEG data, suggesting possible use in practical applications for early detection of mental and cognitive disorders.


Asunto(s)
Ondas Encefálicas , Electroencefalografía , Encéfalo/diagnóstico por imagen , Aprendizaje Automático , Personalidad
7.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1023-1026, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018159

RESUMEN

Short-duration bursts of spontaneous activity are important markers of maturation in the electroencephalogram (EEG) of premature infants. This paper examines the application of a feature-less machine learning approach for detecting these bursts. EEGs were recorded over the first 3 days of life for infants with a gestational age below 30 weeks. Bursts were annotated on the EEG from 36 infants. In place of feature extraction, the time-series EEG is transformed into a time-frequency distribution (TFD). A gradient boosting machine is then trained directly on the whole TFD using a leave-one-out procedure. TFD kernel parameters, length of the Doppler and lag windows, are selected within a nested cross-validation procedure during training. Results indicate that detection performance is sensitive to Doppler-window length but not lag-window length. Median area under the receiver operator characteristic for detection is 0.881 (inter-quartile range 0.850 to 0.913). Examination of feature importance highlights a critical wideband region <15 Hz in the TFD. Burst detection methods form an important component in any fully-automated brain-health index for the vulnerable preterm infant.


Asunto(s)
Enfermedades del Recién Nacido , Recien Nacido Prematuro , Encéfalo/diagnóstico por imagen , Electroencefalografía , Humanos , Lactante , Recién Nacido , Aprendizaje Automático
8.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1051-1054, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018166

RESUMEN

Oxygen deprivation (hypoxia) and reduced blood supply (ischemia) can occur before, during or shortly after birth and can result in death, brain damage and long-term disability. Assessing neuronal survival after hypoxia-ischemia in the near-term fetal sheep brain model is essential for the development of novel treatment strategies. As manual quantification of neurons in histological images varies between different assessors and is extremely time-consuming, automation of the process is needed and has not been currently achieved. To achieve automation, successfully segmenting the neurons from the background is very important. Due to presence of densely populated overlapping cells and with no prior information of shapes and sizes, the segmentation of neurons from the image is complex. Initially, we segmented the RGB images by using K-means clustering to primarily segment the neurons from the background based on their colour value, a distance transform for seed detection and watershed method for separating overlapping objects. However, this resulted in unsatisfactory sensitivity and performance due to over-segmentation if we use the RGB image directly. In this paper, we propose a semi-automated modified approach to segment neurons that tackles the over-segmentation issue that we encountered. Initially, we separated the red, green and blue colour channel information from the RGB image. We determined that by applying the same segmentation method first to the blue channel image, then by performing segmentation on the green channel for the neurons that remain unsegmented from the blue channel segmentation and finally by performing segmentation on red channel for neurons that were still unsegmented from the green channel segmentation, improved performance results could be achieved. The modified approach increased performance for the healthy and ischemic animal images from 89.7% to 98.08% and from 94.36% to 98.06% respectively as compared to using RGB image directly.


Asunto(s)
Feto , Fenómenos Fisiológicos del Sistema Nervioso , Animales , Encéfalo/diagnóstico por imagen , Femenino , Humanos , Neuronas , Embarazo , Atención Prenatal , Ovinos
9.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1071-1074, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018171

RESUMEN

While Deep Learning methods have been successfully applied to tackle a wide variety of prediction problems, their application has been mostly limited to data structured in a grid-like fashion. However, the study of the human brain "connectome" involves the representation of the brain as a graph with interacting nodes. In this paper, we extend the Graph Attention Network (GAT), a novel neural network (NN) architecture acting on the features of the nodes of a binary graph, to handle a set of graphs provided with node features and non-binary edge weights. We demonstrate the effectiveness of our architecture by training it multimodal data collected from a large homogeneous fMRI dataset (n=1003 individuals with multiple fMRI sessions per subject) made publicly available by the Human Connectome Project (HCP), demonstrating good performance and seamless integration of multimodal neuroimaging data. Our adaptation provides a powerful and flexible deep learning tool to integrate multimodal neuroimaging connectomics data in a predictive context.


Asunto(s)
Encéfalo , Conectoma , Atención , Encéfalo/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética , Neuroimagen
10.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1080-1083, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018173

RESUMEN

Cerebral vascular territories are related to the clinical progression and outcome of ischemic stroke. The vascular territory map (VTM) helps to understand stroke pathophysiology and potentially the clinical prognosis. A VTM can be generated from the bolus arrival time map. However, previous methods require initial seed points to be chosen manually, and the region inferior to the circle of Willis is not included. In this paper, we propose a method to automatically generate a map of the whole cerebral vascular territory from CT perfusion imaging. We applied the proposed method to 19 cases of ischemic stroke to generate VTM for each case.Clinical Relevance- The proposed map may improve the interpretation of the physiological status of collateral flow for ischemic stroke, and aid in treatment decision making.


Asunto(s)
Isquemia Encefálica , Sistema Cardiovascular , Accidente Cerebrovascular , Encéfalo/diagnóstico por imagen , Isquemia Encefálica/diagnóstico por imagen , Mapeo Encefálico , Humanos , Accidente Cerebrovascular/diagnóstico por imagen
11.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1084-1087, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018174

RESUMEN

Recently, more evidences manifest that the subjective cognitive decline (SCD) of unimpaired individual may represent first symptom of Alzheimer's disease (AD). This study investigated the differences of intrinsic glucose metabolic functional connectivity between SCD and healthy subject (HC) groups from the perspective of brain network topology. In this study we attained 18F-Fluorodeoxyglucose positron emission tomography (18F-FDG PET) scans from Xuanwu Hospital, Beijing, China, including 85 SCD subjects (male = 16, mean age = 66, MMSE = 28.4) and 74 HC subjects (male = 37, mean age = 65,MMSE=29.0). Graph theory method has been used in this study. Network parameters, including global efficiency, local efficiency, characteristic path length, clustering coefficient, betweenness centrality, sigma and modularity were calculated and compared between two groups. As a result, both SCD and HC groups showed the small-world property. Meanwhile, SCD showed loss of small-world properties, for example, sigma in SCD was significantly lower than HC (p<0.05). In addition, the clustering coefficient and local efficiency of SCD were both higher than HC significantly (p<0.05). In contrast, the characteristic path length and global efficiency of SCD were lower than HC, which led to the regularization of brain network in SCD group. Furthermore, we found global modularity of SCD was lower than HC and the number of modules also decreased. Our findings suggested that there exist differences in glucose metabolic brain network between two groups, demonstrating that the graph theory analysis method could be useful and helpful to predict risks in the preclinical stage of AD.


Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Encéfalo/diagnóstico por imagen , China , Glucosa , Humanos
12.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1088-1091, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018175

RESUMEN

A unified framework for the analysis of fluorescence data taken by a two-photon imaging system is presented. As in the processing of blood-oxygen-level-dependent signals of functional magnetic resonance imaging, the acquired functional images have to be co-registered with a structural brain atlas before delineating the regions activated by a given stimulus. The voxels whose calcium traces are highly correlated with the predicted responses are demarcated without the need for subjective reasoning. Experimental data acquired while presenting olfactory stimuli are used to demonstrate the efficacy of the proposed schemes. The results indicate that the functional images of a Drosophila individual can be normalized into a standard stereotactic space, and the expected brain regions can be delineated adequately. This framework provides an opportunity to enable the development of a Drosophila functional connectome database.


Asunto(s)
Conectoma , Drosophila , Animales , Encéfalo/diagnóstico por imagen , Imagenología Tridimensional , Imagen por Resonancia Magnética
13.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1092-1095, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018176

RESUMEN

Neuronal-related activity can be estimated from functional magnetic resonance imaging (fMRI) data with no knowledge of the timings of blood oxygenation level-dependent (BOLD) events by means of deconvolution with regularized least-squares. This work proposes two improvements on the deconvolution algorithm of sparse paradigm free mapping (SPFM): a new formulation that enables the estimation of neuronal events with long, sustained activity; and the implementation of a subsampling approach based on stability selection that avoids the choice of any regularization parameter. The proposed method is evaluated on real fMRI data and compared with both the original SPFM algorithm and conventional analysis with a general linear model (GLM) that is aware of the temporal model of the neuronal-related activity. We demonstrate that the novel stability-based SPFM algorithm yields activation maps with higher resemblance to the maps obtained with GLM analyses and offers improved detection of neuronal-related events over SPFM, particularly in scenarios with low contrast-to-noise ratio.


Asunto(s)
Mapeo Encefálico , Encéfalo , Algoritmos , Encéfalo/diagnóstico por imagen , Modelos Lineales , Imagen por Resonancia Magnética
14.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1096-1099, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018177

RESUMEN

Simultaneously resting brain glucose metabolism and intrinsic functional activity, by integrated PET/MRI scans, both reflect nerve actions. Studies showed that there existed relevance between two phenotypes of neuros in normal human brains. However, whether the relevance will change in cognitive dysfunction (CD) brains is still unknown. The aim of this study therefore is to explore the relevance between voxel-wise glucose metabolism and functional connectivity in Chinese CD people. The dataset in this study included two imaging modalities and clinical information of 21 healthy control (HC) individuals and 15 CD patients, from Xuanwu hospital, Beijing, China. Firstly, we calculated the standardized uptake value rate (SUVR) from positron emission tomography (PET), and three parameters for intrinsic functional activity from functional magnetic resonance imaging (fMRI), including amplitude of low frequency fluctuations (ALFF), fractional amplitude of low frequency fluctuations (fALFF) and regional homogeneity (ReHo). Second, the two sample t-test was used to compare each parameter between HC and CD groups respectively. Third, the relevance between SUVR and the three fMRI parameters were measured by Spearman's rank correlation. The results of t-test showed that glucose metabolism consumption decreased in Default Mode Network (DMN) (p < 0.01), and the damage of functional connection also happened DMN area in CD group. The correlation between glucose metabolism and functional activity in CD group was lower than that in HC group in DMN. Especially, the correlation between SUVR and ReHo was significantly reduced (p < 0.05). Above results promoted a deeper understanding on the pathogenesis of cognitive impairment, and providing new biomarkers to discriminate CD and HC subjects.


Asunto(s)
Disfunción Cognitiva , Tomografía de Emisión de Positrones , Encéfalo/diagnóstico por imagen , China , Disfunción Cognitiva/diagnóstico por imagen , Glucosa , Humanos , Imagen por Resonancia Magnética
15.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1104-1107, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018179

RESUMEN

Alzheimer's disease (AD) is progressive neurodegenerative disease. It is important to identify effective biomarkers to explore changes of complex functional brain networks in AD patients based on functional magnetic resonance imaging (fMRI). Recently, four fMRI brain network parameters were frequently used, including regional homogeneity (ReHo), amplitude of low frequency fluctuations (ALFF), fractional amplitude of low frequency fluctuations (f/ALFF) and degree centrality (DC). However, these parameters only present the changes of brain networks in a full time quantum, but ignore changes over a short period of time and lack space information. In this study we propose a new brain network parameter for fMRI, called multilayer network modularity and spatiotemporal network switching rate (stNSR). This parameter is calculated combing Pearson correlation sliding Hamming window and the Louvain algorithm. To verify the efficiency of stNSR, we selected 61 AD patients and 110 healthy controls (HC) from Xuanwu Hospital, Beijing, China. First, we used two-sample t test to identify regions of interest (ROI) between AD patients and HCs. Second, we calculated the stNSR values in these ROIs, and compared them with ReHo, ALFF, f/ALFF, and DC values between AD and HC groups. The results showed that, stNSR values in left calcimine fissure and surrounding cortex, left Lingual gyrus and left cerebellum inferior significantly increased, while stNSR values significantly decreased in left Para hippocampal gyrus, left temporal and superior temporal gyrus. As a comparison, changes in these ROIs could not be observed using ReHo, ALFF, f/ALFF, and DC. The results indicated that stNSR may reflect differences of brain networks between AD patients and HCs.


Asunto(s)
Enfermedad de Alzheimer , Enfermedades Neurodegenerativas , Enfermedad de Alzheimer/diagnóstico por imagen , Encéfalo/diagnóstico por imagen , Mapeo Encefálico , China , Humanos
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1108-1111, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018180

RESUMEN

Reconstructing the perceived faces from brain signals has become a promising work recently. However, the reconstruction accuracies rely on a large number of brain signals collected for training a stable reconstruction model, which is really time consuming, and greatly limits its application. In our current study, we develop a new framework that can efficiently perform high-quality face reconstruction with only a small number of brain signals as training samples. The framework consists of three mathematical models: principle component analysis (PCA), linear regression (LR) and conditional generative adversarial network (cGAN). We conducted a functional Magnetic Resonance Imaging (fMRI) experiment in which two subjects' brain signals were collected to test the efficiency of our proposed method. Results show that we can achieve state-of-the-art reconstruction performance from brain signals with a very limited number of fMRI training samples.


Asunto(s)
Encéfalo , Imagen por Resonancia Magnética , Encéfalo/diagnóstico por imagen , Modelos Lineales , Análisis de Componente Principal
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1116-1119, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018182

RESUMEN

Recent neuroimaging studies have employed graph theory as a data-driven approach to describe topological organization of the brain under different neurological disorders or task conditions and across life span. In this exploratory study, we tested whether subtle differences in interoception related to intravesical fullness can alter brain topological architecture in healthy participants. 17 right-handed women underwent a series of resting state fMRI scans that included catheterization and partial bladder filling. Using a whole brain regions of interest (ROIs), we computed several graph theory metrics to assess the efficiency of brain-wide information exchange. Results showed that brain network's topological properties significantly changed in many brain regions when we binary compared different interoceptive resting state conditions. Notably, we observed changes in global efficiency in the salience network, the central executive network, anterior dorsal attention network and the posterior default-mode network (DMN) as bladder became full and interoceptive signals intensified. Moreover, degree (the number of connections for each node), and betweenness centrality (how connected a particular region is to other regions) differed between the empty bladder, the catheterized empty bladder, and the catheterized and partially filled bladder. Comparing resting state data before and after an interoceptive task (repeated intravesical infusion and drainage) further showed increased average path length for the salience networks and decreased clustering coefficient of the DMN. These results suggest visceral interoception influences brain topological properties of resting state networks.


Asunto(s)
Interocepción , Imagen por Resonancia Magnética , Anatomía Regional , Encéfalo/diagnóstico por imagen , Mapeo Encefálico , Femenino , Humanos
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1120-1123, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018183

RESUMEN

In recent years, the conceptualisation of the brain as a "connectome" as summary measures derived from graph theory analyses, has become increasingly popular. Still, such approaches are inherently limited by the need to condense and simplify temporal fMRI dynamics and architecture into a purely spatial representation. We formulate a novel architecture based on Geometric Deep Learning which is specifically tailored to the one-step integration of spatial relationship between nodes and single-node temporal dynamics. We compare different spatiotemporal modelling mechanisms and demonstrate the effectiveness of our architecture in a binary prediction task based on a large homogeneous fMRI dataset made publicly available by the Human Connectome Project (HCP). As the idea of e.g. a dynamical network connectivity is beginning to make its way into the more mainstream toolset which neuroscientists commonly employ with neuroimaging data, our model can contribute to laying the groundwork for explicitly incorporating spatiotemporal information into every association and prediction problem in neuroscience.


Asunto(s)
Conectoma , Neurociencias , Encéfalo/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1355-1359, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018240

RESUMEN

Volumetric medical image registration has important clinical significance. Traditional registration methods may be time-consuming when processing large volumetric data due to their iterative optimizations. In contrast, existing deep learning-based networks can obtain the registration quickly. However, most of them require independent rigid alignment before deformable registration; these two steps are often performed separately and cannot be end-to-end. Moreover, registration ground-truth is difficult to obtain for supervised learning methods. To tackle the above issues, we propose an unsupervised 3D end-to-end deformable registration network. The proposed network cascades two subnetworks; the first one is for obtaining affine alignment, and the second one is a deformable subnetwork for achieving the non-rigid registration. The parameters of the two subnetworks are shared. The global and local similarity measures are used as loss functions for the two subnetworks, respectively. The trained network can perform end-to-end deformable registration. We conducted experiments on brain MRI datasets (LPBA40, Mindboggle101, and IXI) and experimental results demonstrate the efficacy of the proposed registration network.


Asunto(s)
Encéfalo , Imagen por Resonancia Magnética , Encéfalo/diagnóstico por imagen
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1420-1423, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018256

RESUMEN

Alzheimers disease is characterized by complex changes in brain tissue including the accumulation of tau-containing neurofibrillary tangles (NFTs) and dystrophic neurites (DNs) within neurons. The distribution and density of tau pathology throughout the brain is evaluated at autopsy as one component of Alzheimers disease diagnosis. Deep neural networks (DNN) have been shown to be effective in the quantification of tau pathology when trained on fully annotated images. In this paper, we examine the effectiveness of three DNNs for the segmentation of tau pathology when trained on noisily labeled data. We train FCN, SegNet and U-Net on the same set of training images. Our results show that using noisily labeled data, these networks are capable of segmenting tau pathology as well as nuclei in as few as 40 training epochs with varying degrees of success. SegNet, FCN and U-Net are able to achieve a DICE loss of 0.234, 0.297 and 0.272 respectively on the task of segmenting regions of tau. We also apply these networks to the task of segmenting whole slide images of tissue sections and discuss their practical applicability for processing gigapixel sized images.


Asunto(s)
Enfermedad de Alzheimer , Redes Neurales de la Computación , Enfermedad de Alzheimer/diagnóstico , Encéfalo/diagnóstico por imagen , Humanos , Ovillos Neurofibrilares
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA