A5066236691- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Image and Signal Denoising Methods
- Medical Image Segmentation Techniques
- Electronic Health Records Systems
- Advanced MRI Techniques and Applications
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Functional Brain Connectivity Studies
- Advanced Neuroimaging Techniques and Applications
- Brain Tumor Detection and Classification
- Schizophrenia research and treatment
- Advanced Image Fusion Techniques
- Advanced Database Systems and Queries
- Advanced Image Processing Techniques
- Neuroscience and Music Perception
- Scientific Computing and Data Management
- Service-Oriented Architecture and Web Services
- Business Process Modeling and Analysis
- Data Quality and Management
- Clinical practice guidelines implementation
- Blind Source Separation Techniques
- Traumatic Brain Injury Research
- Distributed and Parallel Computing Systems
- Medical Imaging and Analysis
Universitat Politècnica de València
2011-2022
Centro Tecnológico de Investigación, Desarrollo e Innovación en tecnologías de la Información y las Comunicaciones (TIC)
2011-2014
Hospital de Referencia La Equina
2012
Hospital Clínico Universitario Virgen de la Victoria
2008
Universitat de València
2003-2007
AIA (Spain)
2007
Simón Bolívar University
2004
Functional genomics technologies have been widely adopted in the biological research of both model and non-model species. An efficient functional annotation DNA or protein sequences is a major requirement for successful application these approaches as information on gene products often key to interpretation experimental results. Therefore, there an increasing need bioinformatics resources which are able cope with large amount sequence data, produce valuable results easily accessible...
To adapt the so-called nonlocal means filter to deal with magnetic resonance (MR) images spatially varying noise levels (for both Gaussian and Rician distributed noise).Most filtering techniques assume an equal distribution across image. When this assumption is not met, resulting becomes suboptimal. This case of MR levels, such as those obtained by parallel imaging (sensitivity-encoded), intensity inhomogeneity-corrected images, or surface coil-based acquisitions. We propose a new method...
Diffusion Weighted Images (DWI) normally shows a low Signal to Noise Ratio (SNR) due the presence of noise from measurement process that complicates and biases estimation quantitative diffusion parameters. In this paper, new denoising methodology is proposed takes into consideration multicomponent nature multi-directional DWI datasets such as those employed in imaging. This filter reduces random by locally shrinking less significant Principal Components using an overcomplete approach. The...
Automatic brain tumour segmentation has become a key component for the future of treatment. Currently, most approaches arise from supervised learning standpoint, which requires labelled training dataset to infer models classes. The performance these is directly determined by size and quality corpus, whose retrieval becomes tedious time-consuming task. On other hand, unsupervised avoid limitations but often do not reach comparable results than methods. In this sense, we propose an automated...
Automatic brain tumor classification by MRS has been under development for more than a decade. Nonetheless, to our knowledge, there are no published evaluations of predictive models with unseen cases that subsequently acquired in different centers. The multicenter eTUMOUR project (2004-2009), which builds upon previous expertise from the INTERPRET (2000-2002) allowed such an evaluation take place.A total 253 pairwise classifiers glioblastoma, meningioma, metastasis, and low-grade glial...
In this study, an adaptive multiresolution version of the blockwise non-local (NL)-means filter is presented for three-dimensional (3D) magnetic resonance (MR) images. On basis soft wavelet coefficient mixing, proposed implicitly adapts amount denoising according to spatial and frequency information contained in image. Two versions are described Gaussian Rician noise. Quantitative validation was carried out on BrainWeb datasets by using several quality metrics. The results show that obtained...
In Magnetic Resonance Imaging typical clinical settings, both low- and high-resolution images of different types are routinarily acquired. some cases, the acquired low-resolution have to be upsampled match with other for posterior analysis or postprocessing such as registration multimodal segmentation. However, classical interpolation techniques not able recover high-frequency information lost during acquisition process. present paper, a new superresolution method is proposed reconstruct...
Automatic and accurate methods to estimate normalized regional brain volumes from MRI data are valuable tools which may help obtain an objective diagnosis followup of many neurological diseases. To such volumes, the intracranial cavity volume (ICV) is often used for normalization. However, high variability shape size due normal intersubject variability, changes occurring over lifespan, abnormal disease makes ICV estimation problem challenging. In this paper, we present a new approach perform...
Mobile health (m-health) apps can bring prevention and promotion to the general population. The main purpose of this article is analyze different m-health for a broad spectrum consumers by means three experiences. This goal was defined following strategic documents generated prospective observatories Information Communications Technology health. After exploration app markets, we entries specific themes focused in article: type 2 diabetes, obesity, breast-feeding. user experiences reported...
The objective was to study the correlations and differences in glucose metabolism between thalamus cortical structures a sample of severe traumatic brain injury (TBI) patients with different neurological outcomes. We studied 49 who had suffered TBI 10 healthy control subjects using 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET). were divided into three groups: vegetative or minimally-conscious state (MCS&VS) group (n=17), which included minimally conscious state; an...
Background The secondary use of electronic healthcare records (EHRs) often requires the identification patient cohorts. In this context, an important problem is heterogeneity clinical data sources, which can be overcome with combined standardized information models, virtual health records, and semantic technologies, since each them contributes to solving aspects related interoperability EHR data. Objective To develop methods allowing for a direct cohorts leveraging current standards web...