Examinando por Autor "Pastor, Luis"

Mostrando 1 - 6 de 6

A Deep Learning-Based Workflow for Dendritic Spine Segmentation
(Frontiers, 2022-03-17) Vidaurre-Gallart, Isabel; Fernaud-Espinosa, Isabel; Cosmin-Toader, Nicusor; Talavera-Martínez, Lidia; Martin-Abadal, Miguel; Benavides-Piccione, Ruth; Gonzalez-Cid, Yolanda; Pastor, Luis; DeFelipe, Javier; García-Lorenzo, M
The morphological analysis of dendritic spines is an important challenge for the neuroscientific community. Most state-of-the-art techniques rely on user-supervised algorithms to segment the spine surface, especially those designed for light microscopy images. Therefore, processing large dendritic branches is costly and time-consuming. Although deep learning (DL) models have become one of the most commonly used tools in image segmentation, they have not yet been successfully applied to this problem. In this article, we study the feasibility of using DL models to automatize spine segmentation from confocal microscopy images. Supervised learning is the most frequently used method for training DL models. This approach requires large data sets of high-quality segmented images (ground truth). As mentioned above, the segmentation of microscopy images is time-consuming and, therefore, in most cases, neuroanatomists only reconstruct relevant branches of the stack. Additionally, some parts of the dendritic shaft and spines are not segmented due to dyeing problems. In the context of this research, we tested the most successful architectures in the DL biomedical segmentation field. To build the ground truth, we used a large and high-quality data set, according to standards in the field. Nevertheless, this data set is not sufficient to train convolutional neural networks for accurate reconstructions. Therefore, we implemented an automatic preprocessing step and several training strategies to deal with the problems mentioned above. As shown by our results, our system produces a high-quality segmentation in most cases. Finally, we integrated several postprocessing user-supervised algorithms in a graphical user interface application to correct any possible artifacts.
A Unified Framework for Neuroscience Morphological Data Visualization
(MDPI, 2021) Pastor, Luis; Bayona, Sofia; Brito, Juan P.; Cuevas, María; Fernaud, Isabel; Galindo, Sergio Emilio; García-Cantero, Juan José; González de Quevedo, Francisco; Mata, Susana; Robles, Oscar David; Rodríguez, Angel; Toharia, Pablo; Zdravkovic, Ana
The complexity of the human brain makes its understanding one of the biggest challenges that science is currently confronting. Due to its complexity, the brain has been studied at many different levels and from many disciplines and points of view, using a diversity of techniques for getting meaningful data at each specific level and perspective, producing sometimes data that are difficult to integrate. In order to advance understanding of the brain, scientists need new tools that can speed up this analysis process and that can facilitate integrating research results from different disciplines and techniques. Visualization has proved to be useful in the analysis of complex data, and this paper focuses on the design of visualization solutions adapted to the specific problems posed by brain research. In this paper, we propose a unified framework that allows the integration of specific tools to work together in a coordinated manner in a multiview environment, displaying information at different levels of abstraction and combining schematic and realistic representations. The two use cases presented here illustrate the capability of this approach for providing a visual environment that supports the exploration of the brain at all its organizational levels.
H-Isoefficiency: Scalability Metric for Heterogeneous Systems
(J. Vigo - Aguiar, 2010-06) Bosque, Jose Luis; Robles, Oscar D.; Toharia, Pablo; Pastor, Luis
Scalability is one of the most important features in exascale computing. Most of this systems are heterogeneous and therefore it becomes necessary to develop models and metrics that take into account this heterogeneity. This paper presents a new expression of the isoefficiency function called H-isoefficiency. This function can be applied for both homogeneous and heterogeneous systems and allows to analyze the scalability of a parallel system. Then, as an example, a theoretical a priori analysis of the scalability of Floyd¿s algorithm is presented. Finally a model evaluation which demonstrate the correlation between the theoretical analysis and the experimental results is showed.
Motor imagery EEG signal classification with a multivariate time series approach
(2023) Velasco, Ivan; Sipols, Ana Elizabeth; Simón de Blas, Clara; Pastor, Luis; Bayona, Sofia
Background: Electroencephalogram (EEG) signals record electrical activity on the scalp. Measured signals, especially EEG motor imagery signals, are often inconsistent or distorted, which compromises their classification accuracy. Achieving a reliable classification of motor imagery EEG signals opens the door to possibilities such as the assessment of consciousness, brain computer interfaces or diagnostic tools. We seek a method that works with a reduced number of variables, in order to avoid overfitting and to improve interpretability. This work aims to enhance EEG signal classification accuracy by using methods based on time series analysis. Previous work on this line, usually took a univariate approach, thus losing the possibility to take advantage of the correlation information existing within the time series provided by the different electrodes. To overcome this problem, we propose a multivariate approach that can fully capture the relationships among the different time series included in the EEG data. To perform the multivariate time series analysis, we use a multi-resolution analysis approach based on the discrete wavelet transform, together with a stepwise discriminant that selects the most discriminant variables provided by the discrete wavelet transform analysis Results: Applying this methodology to EEG data to differentiate between the motor imagery tasks of moving either hands or feet has yielded very good classification results, achieving in some cases up to 100% of accuracy for this 2-class pre-processed dataset. Besides, the fact that these results were achieved using a reduced number of variables (55 out of 22,176) can shed light on the relevance and impact of those variables. Conclusions: This work has a potentially large impact, as it enables classification of EEG data based on multivariate time series analysis in an interpretable way with high accuracy. The method allows a model with a reduced number of features, facilitating its interpretability and improving overfitting. Future work will extend the application of this classification method to help in diagnosis procedures for detecting brain pathologies and for its use in brain computer interfaces. In addition, the results presented here suggest that this method could be applied to other fields for the successful analysis of multivariate temporal data.
SynCoPa: Visualizing Connectivity Paths and Synapses Over Detailed Morphologies
(Frontiers, 2021) Galindo, Sergio E.; Toharia, Pablo; Robles, Oscar D.; Pastor, Luis
Brain complexity has traditionally fomented the division of neuroscience into somehow separated compartments; the coexistence of the anatomical, physiological, and connectomics points of view is just a paradigmatic example of this situation. However, there are times when it is important to combine some of these standpoints for getting a global picture, like for fully analyzing the morphological and topological features of a specific neuronal circuit. Within this framework, this article presents SynCoPa, a tool designed for bridging gaps among representations by providing techniques that allow combining detailed morphological neuron representations with the visualization of neuron interconnections at the synapse level. SynCoPa has been conceived for the interactive exploration and analysis of the connectivity elements and paths of simple to medium complexity neuronal circuits at the connectome level. This has been done by providing visual metaphors for synapses and interconnection paths, in combination with the representation of detailed neuron morphologies. SynCoPa could be helpful, for example, for establishing or confirming a hypothesis about the spatial distributions of synapses, or for answering questions about the way neurons establish connections or the relationships between connectivity and morphological features. Last, SynCoPa is easily extendable to include functional data provided, for example, by any of the morphologically-detailed simulators available nowadays, such as Neuron and Arbor, for providing a deep insight into the circuits features prior to simulating it, in particular any analysis where it is important to combine morphology, network topology, and physiology.
VMetaFlow: A Meta-Framework for Integrating Visualizations in Coordinated View Applications
(IEEE, 2022-08-29) Cosmin-Toader, Nicusor; Trincado-Alonso, Fernando; Pastor, Luis; García-Lorenzo, Marcos
The analysis and exploration of complex data sets are common problems in many areas, including scientific and business domains. This need has led to substantial development of the data visualization field. In this paper, we present VMetaFlow, a graphical meta-framework to design interactive and coordinated views applications for data visualization. Our meta-framework is based on data flow diagrams since they have proved their value in simplifying the design of data visualizations. VMetaFlow operates as an abstraction layer that encapsulates and interconnects visualization frameworks in a web-based environment, providing them with interoperability mechanisms. The only requirement is that the visualization framework must be accessible through a JavaScript API. We propose a novel data flow model that allows users to define both interactions between multiple data views and how the data flows between visualization and data processing modules. In contrast with previous data-flow-based frameworks for visualization, we separate the view interactions from data items, broadening the expressiveness of our model and supporting the most common types of multi-view interactions. Our meta-framework allows visualization and data analysis experts to focus their efforts on creating data representations and transformations for their applications, whereas nonexperts can reuse previously developed components to design their applications through a user-friendly interface. We validate our approach through a critical inspection with visualization experts and two case studies. We have carefully selected these case studies to illustrate its capabilities. Finally, we compare our approach with the subset flow model designed for multiple coordinated views.