1,721,046 research outputs found
Echo state network models for nonlinear Granger causality
No full textWhile Granger causality (GC) has been often employed in network neuroscience, most GC applications are based on linear multivariate autoregressive (MVAR) models. However, real-life systems like biological networks exhibit notable nonlinear behaviour, hence undermining the validity of MVAR-based GC (MVAR-GC). Most nonlinear GC estimators only cater for additive nonlinearities or, alternatively, are based on recurrent neural networks or long short-term memory networks, which present considerable training difficulties and tailoring needs. We reformulate the GC framework in terms of echo-state networks-based models for arbitrarily complex networks, and characterize its ability to capture nonlinear causal relations in a network of noisy Duffing oscillators, showing a net advantage of echo state GC (ES-GC) in detecting nonlinear, causal links. We then explore the structure of ES-GC networks in the human brain employing functional MRI data from 1003 healthy subjects drawn from the human connectome project, demonstrating the existence of previously unknown directed within-brain interactions. In addition, we examine joint brain-heart signals in 15 subjects where we explore directed interaction between brain networks and central vagal cardiac control in order to investigate the so-called central autonomic network in a causal manner. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'
A realistic neuronal network and neurovascular coupling model for the study of multivariate directed connectivity in fMRI data
No full textThe use of Multivariate Granger Causality (MVGC) in estimating directed Blood-Oxygen-Level- Dependant (BOLD) connectivity is still controversial. This is mostly due to the short data Ienghts typically available in func- tional MRI (fMRI) acquisitions, to the very nature of the BOLD acquisition strategy (which yields extremely low signal- to-noise-ratio) and importantly to the fact that neuronal activi- ty is convolved with a slow-varying haemodynamic response function (HRF) which therefore generates a temporal confound which is arduous to account for when basing MVGC estimates on vector autoregressive models (VAR). In this paper, we em- ploy realistic complex network models based on Izhikevich neuronal populations, interlinked by realistic neuronal fiber bundles which exert compounded directed influences and cas- cade into Baloon-model-like neurovascular coupling, to explore and validate the MVGC approach to directed connectivity es- timation in realistic fMRI conditions and in a complex directed network setting. In particular, we show in silico that the top 1 percentile of a BOLD connectivity matrix estimated with MVGC from BOLD data similar to the one provided by the Human Connectome Project (HCP) has a Positive Predictive Value very close to 1, hence corroborating the evidence that the "strongest" connections can be safely studied with this method in fMRI
Multidimensional autonomic nervous system profiles relate to psychiatric disturbances, emotion and personality
No full textLinear and nonlinear Estimates of Autonomic Nervous System (ANS) activity from Heart Rate variability (HRV) have been separately linked to a number of cardiac, psychiatric and metabolic conditions. We employed unsupervised methods to detect clusters within an HRV-derived ANS profile and relate this structure to a vast array of biological and behavioural variables. We found that HRV profiles are able to stratify individuals by a number of biological (e.g. body mass index, blood pressure, endurance) but also behavioral and psychiatric (depression, anxiety, personality) indicators, hence providing a stepping stone for understanding how ANS activity shapes biological functions as well as human behavior and its possible pathological aberrations
Deep computational pathology in breast cancer
No full textdeep learning (DL) algorithms are a set of techniques that exploit large and/or complex real-world datasets for cross-domain and cross-discipline prediction and classification tasks. DL architectures excel in computer vision tasks, and in particular image processing and interpretation. this has prompted a wave of disruptingly innovative applications in medical imaging, where DL strategies have the potential to vastly outperform human experts. this is particularly relevant in the context of histopathology, where whole slide imaging (WSI) of stained tissue in conjuction with DL algorithms for their interpretation, selection and cancer staging are beginning to play an ever increasing role in supporting human operators in visual assessments. this has the potential to reduce everyday workload as well as to increase precision and reproducibility across observers, centers, staining techniques and even pathologies. In this paper we introduce the most common DL architectures used in image analysis, with a focus on histopathological image analysis in general and in breast histology in particular. we briefly review how, state-of-art DL architectures compare to human performance on across a number of critical tasks such as mitotic count, tubules analysis and nuclear pleomorphism analysis. also, the development of DL algorithms specialized to pathology images have been enormously fueled by a number of world-wide challenges based on large, multicentric image databases which are now publicly available. In turn, this has allowed most recent efforts to shift more and more towards semi-supervised learning methods, which provide greater flexibility and applicability. we also review all major repositories of manually labelled pathology images in breast cancer and provide an indepth discussion of the challenges specific to training DL architectures to interpret WSI data, as well as a review of the state-of-the-art methods for interpretation of images generated from immunohistochemical analysis of breast lesions. we finally discuss the future challenges and opportunities which the adoption of DL paradigms is most likely to pose in the field of pathology for breast cancer detection, diagnosis, staging and prognosis. this review is intended as a comprehensive stepping stone into the field of modern computational pathology for a transdisciplinary readership across technical and medical disciplines
Radiomics in breast cancer classification and prediction
No full textBreast Cancer (BC) is the common form of cancer in women. Its diagnosis and screening are usually performed through different imaging modalities such as mammography, magnetic resonance imaging and ultrasound. However, mammography and ultrasound-imaging techniques have limited sensitivity and specificity both in identifying lesions and in differentiating malign from benign lesions, especially in presence of dense breast parenchyma. Due to the higher resolution of magnetic resonance images, MRI represents the method with the higher specificity and sensitivity among all the available tools, in both lesions' identification and diagnosis. However, especially for diagnosis, even MRI has limitations that are only partially solved if combined with mammography. Unfortunately, due to the limits of all these imaging tools, in order to have a certain diagnosis, patients often receive painful and costly bioptics procedures. In this context, several computational approaches have been developed to increase sensitivity, while maintaining the same specificity, in BC diagnosis and screening. Amongst these, radiomics has been increasingly gaining ground in oncology to improve cancer diagnosis, prognosis and treatment. Radiomics derives multiple quantitative features from single or multiple medical imaging modalities, highlighting image traits which are not visible to the naked eye and hence significantly augmenting the discriminatory and predictive potential of medical imaging. This review article aims to summarize the state of the art in radiomics-based BC research. The dominating evidence extracted from the literature points towards a high potential of radiomics in disentangling malignant from benign breast lesions, classifying BC types and grades and also in predicting treatment response and recurrence risk. In the era of personalized medicine, radiomics has the potential to improve diagnosis, prognosis, prediction, monitoring, image-based intervention, and assessment of therapeutic response in BC
A novel multi-branch architecture for state of the art robust detection of pathological phonocardiograms
No full textheart auscultation is an inexpensive and fundamental technique to effectively diagnose cardiovascular disease. however, due to relatively high human error rates even when auscultation is performed by an experienced physician, and due to the not universal availability of qualified personnel, e.g. in developing countries, many efforts are made worldwide to propose computational tools for detecting abnormalities in heart sounds. the large heterogeneity of achievable data quality and devices, the variety of possible heart pathologies, and a generally poor signal-to-noise ratio make this problem very challenging. we present an accurate classification strategy for diagnosing heart sounds based on (1) automatic heart phase segmentation, (2) state-of-the art filters drawn from the field of speech synthesis (mel-frequency cepstral representation) and (3) an ad hoc multi-branch, multi-instance artificial neural network based on convolutional layers and fully connected neuronal ensembles which separately learns from each heart phase hence implicitly leveraging their different physiological significance. we demonstrate that it is possible to train our architecture to reach very high performances, e.g. an area under the curve of 0.87 or a sensitivity of 0.97. our machine-learning-based tool could be employed for heartsound classification, especially as a screening tool in a variety of situations including telemedicine applications. this article is part of the theme issue 'advanced computation in cardiovascular physiology: new challenges and opportunities'
Recurrent neural networks for reconstructing complex directed brain connectivity
No full textWhile Granger Causality(GC)-based approaches have been widely employed in a vast number of problems in network science, the vast majority of GC applications are based on linear multivariate autoregressive (MVAR) models. However, it is well known that real-life system (and biological networks in particular) exhibit notable nonlinear behavior, hence undermining that validity of MVAR-based approaches to estimating GC (MVAR-GC). In this paper, we define a novel approach to estimating nonlinear, directed within-network interactions based on a specific class of recurrent neural networks (RNN) termed echo-state networks (ESN). We reformulate the classical GC framework in terms of ESN-based models for multivariate signals generated by arbitrarily complex networks, and characterize the ability of our ESN-based Granger Causality (ES-GC) to capture nonlinear causal relations by simulating multivariate coupling in a network of nonlinearly interacting, noisy Duffing oscillators operating in a chaotic regime. Synthetic validation shows a net advantage of ES-GC over all other estimators in detecting nonlinear, causal links. We then explore the structure of EC-GC networks in the human brain in functional MRI data from 1003 healthy subjects scanned at rest at 3T, discovering previously unknown between-network interactions. In summary, ES-GC performs significantly better than commonly used and recently developed GC detection tools, making it a superior tool for the analysis of e.g. multivariate biological networks
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Simultaneous estimation of the in-mean and in-variance causal connectomes of the human brain
No full textIn recent years, the study of the human connectome (i.e. of statistical relationships between non spatially contiguous neurophysiological events in the human brain) has been enormously fuelled by technological advances in high-field functional magnetic resonance imaging (fMRI) as well as by coordinated world wide data-collection efforts like the Human Connectome Project (HCP). In this context, Granger Causality (GC) approaches have recently been employed to incorporate information about the directionality of the influence exerted by a brain region on another. However, while fluctuations in the Blood Oxygenation Level Dependent (BOLD) signal at rest also contain important information about the physiological processes that underlie neurovascular coupling and associations between disjoint brain regions, so far all connectivity estimation frameworks have focused on central tendencies, hence completely disregarding so-called in-variance causality (i.e. the directed influence of the volatility of one signal on the volatility of another). In this paper, we develop a framework for simultaneous estimation of both in-mean and invariance causality in complex networks. We validate our approach using synthetic data from complex ensembles of coupled nonlinear oscillators, and successively employ HCP data to provide the very first estimate of the in-variance connectome of the human brain
- …
