A5054775009- Functional Brain Connectivity Studies
- Parkinson's Disease Mechanisms and Treatments
- Neurological disorders and treatments
- Dementia and Cognitive Impairment Research
- Gene expression and cancer classification
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- Blind Source Separation Techniques
- Neural dynamics and brain function
- Advanced Neuroimaging Techniques and Applications
- Machine Learning in Healthcare
- Advanced MRI Techniques and Applications
- Machine Learning in Bioinformatics
- Face and Expression Recognition
- Alzheimer's disease research and treatments
- Voice and Speech Disorders
- Artificial Intelligence in Healthcare
- Long-Term Effects of COVID-19
- Chronic Disease Management Strategies
- Handwritten Text Recognition Techniques
- Medical Imaging and Analysis
- Spatial Neglect and Hemispheric Dysfunction
- Anomaly Detection Techniques and Applications
- Face Recognition and Perception
- Neurological Disease Mechanisms and Treatments
Universidad de Granada
2019-2025
Instituto Andaluz de Ciencias de la Tierra
2024-2025
University of Castilla-La Mancha
2023
Instituto de Salud Carlos III
2023
ORCID
2020
Deep Learning (DL), a groundbreaking branch of Machine (ML), has emerged as driving force in both theoretical and applied Artificial Intelligence (AI). DL algorithms, rooted complex non-linear artificial neural systems, excel at extracting high-level features from data. demonstrated human-level performance real-world tasks, including clinical diagnostics, unlocked solutions to previously intractable problems virtual agent design, robotics, genomics, neuroimaging, computer vision, industrial...
The prevalence of dementia is currently increasing worldwide. This syndrome produces a deterioration in cognitive function that cannot be reverted. However, an early diagnosis can crucial for slowing its progress. Clock Drawing Test (CDT) widely used paper-and-pencil test assessment which individual has to manually draw clock on paper. There are lot scoring systems this and most them depend the subjective expert. study proposes computer-aided (CAD) system based artificial intelligence (AI)...
The detection of Alzheimer's Disease in its early stages is crucial for patient care and drugs development. Motivated by this fact, the neuroimaging community has extensively applied machine learning techniques to diagnosis problem with promising results. organization challenges helped address different raised problems standardize approaches problem. In work we use data from international challenge automated prediction MCI MRI multiclass classification We propose a novel approach that...
Abstract INTRODUCTION Adults with Down syndrome (DS) show increased risk for Alzheimer's disease (AD) due to the triplication of chromosome 21 encoding amyloid precursor protein gene. Further, this possibly contributes dysregulation immune system, furthering AD pathophysiology. METHODS Using Olink Explore 3072, we measured ∼3000 proteins in plasma from 73 adults DS and 15 euploid, healthy controls (HC). Analyses differentially expressed (DEP) were carried out, pathway network enrichment...
Abstract Novel features derived from imaging and artificial intelligence systems are commonly coupled to construct computer‐aided diagnosis (CAD) that intended as clinical support tools or for investigation of complex biological patterns. This study used sulcal patterns structural images the brain basis classifying patients with schizophrenia unaffected controls. Statistical, machine learning deep techniques were sequentially applied a demonstration how CAD system might be comprehensively...
Neurodegenerative diseases pose a formidable challenge to medical research, demanding nuanced understanding of their progressive nature. In this regard, latent generative models can effectively be used in data-driven modeling different dimensions neurodegeneration, framed within the context manifold hypothesis. This paper proposes joint framework for multi-modal, common model address need more comprehensive neurodegenerative landscape Parkinson’s disease (PD). The proposed architecture uses...
In the 70s a novel branch of statistics emerged focusing its effort in selecting function pattern recognition problem, which fulfils definite relationship between quality approximation and complexity. These data-driven approaches are mainly devoted to problems estimating dependencies with limited sample sizes comprise all empirical out-of generalization approaches, e.g. cross validation (CV) approaches. Although latter \emph{not designed for testing competing hypothesis or comparing...
Parkinson's Disease (PD) is the second most prevalent neurodegenerative disorder among adults. Although its triggers are still not clear, they may be due to a combination of different types biomarkers measured through medical imaging, metabolomics, proteomics or genetics, others. In this context, we have proposed Computer-Aided Diagnosis (CAD) system that combines structural and functional imaging data from subjects in Progression Markers Initiative dataset by means an Ensemble Learning...
Spatial normalization helps us to compare quantitatively two or more input brain scans. Although using an affine approach preserves the anatomical structures, neuroimaging field is common find works that make use of nonlinear transformations. The main reason they facilitate a voxel-wise comparison, not only when studying functional images but also comparing MRI scans given fit better reference template. However, amount bias introduced by transformations can potentially alter final outcome...
A connection between the General Linear Model (GLM) in combination with classical statistical inference and machine learning (MLE)-based is described this paper. Firstly, estimation of GLM parameters expressed as a Regression (LRM) an indicator matrix, that is, terms inverse problem regressing observations. In other words, both approaches, i.e. LRM, apply to different domains, observation label are linked by normalization value at least-squares solution. Subsequently, from relationship we...
Discriminative analysis in neuroimaging by means of deep/machine learning techniques is usually tested with validation techniques, whereas the associated statistical significance remains largely under-developed due to their computational complexity. In this work, a non-parametric framework proposed that estimates classifications using deep architectures. particular, combination autoencoders (AE) and support vector machines (SVM) applied to: (i) one-condition, within-group designs often...
Regression analysis is a central topic in statistical modeling, aiming to estimate the relationships between dependent variable, commonly referred as response and one or more independent variables, i.e., explanatory variables. Linear regression by far most popular method for performing this task several fields of research, such prediction, forecasting, causal inference. Beyond various classical methods solve linear problems, Ordinary Least Squares, Ridge, Lasso regressions - which are often...
This work proposes the use of 3D convolutional variational autoencoders (CVAEs) to trace changes and symptomatology produced by neurodegeneration in Parkinson's disease (PD). In this work, we present a novel approach detect quantify dopamine transporter (DaT) concentration its spatial patterns using CVAEs on Ioflupane (FPCIT) imaging. Our leverages power deep learning learn low-dimensional representation brain imaging data, which then is linked different symptom categories regression...
Computer-based analysis of neuroimaging data in multisubject studies requires a previous spatial registration procedure, which ensures that the same voxel across different images refers to anatomical position. Several algorithms have been proposed this end and most them perform two steps, an affine transformation followed by non-linear registration. While former applies only translations, rotations, zoom shears neuroimages, step can deform adjust size shape individual regions. Although...