A5046787989- EEG and Brain-Computer Interfaces
- Medical Image Segmentation Techniques
- Functional Brain Connectivity Studies
- Brain Tumor Detection and Classification
- Medical Imaging and Analysis
- Image Retrieval and Classification Techniques
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Face and Expression Recognition
- Advanced Neural Network Applications
- Advanced Neuroimaging Techniques and Applications
- Gaussian Processes and Bayesian Inference
- Radiomics and Machine Learning in Medical Imaging
- Neuroscience and Neural Engineering
- Attention Deficit Hyperactivity Disorder
- Integrated Energy Systems Optimization
- Dementia and Cognitive Impairment Research
- AI in cancer detection
- Reservoir Engineering and Simulation Methods
- Gaze Tracking and Assistive Technology
- ECG Monitoring and Analysis
- Photoacoustic and Ultrasonic Imaging
- Advanced Chemical Sensor Technologies
Technological University of Pereira
2019-2024
Universidad Nacional de Colombia
2012-2019
Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number diversity variety segmentation algorithms, consensus lacking as which automated method works best for certain applications. Segmentation challenges are good approach unbiased evaluation comparison algorithms.In this work, we describe present results Head Neck Auto-Segmentation Challenge 2015, satellite event at Medical Image Computing Computer Assisted Interventions (MICCAI) 2015...
Many approaches for image segmentation rely on a first low-level step, where an is partitioned into homogeneous regions with enforced regularity and adherence to object boundaries. Methods generate these superpixels have gained substantial interest in the last few years, but only made it applications practice, particular because requirements processing time are essential not met by most of them. Here, we propose waterpixels as general strategy generating which relies marker controlled...
Chronic pain leads to not only physical discomfort but also psychological challenges, such as depression and anxiety, which contribute a substantial healthcare burden. Still, detection assessment remains challenge due its subjective nature. Indeed, current clinical methods may be inaccurate or unfeasible for non-verbal patients. Then, Electroencephalography (EEG) has emerged promising non-invasive tool detection. However, EEG-based faces challenges noise, volume conduction effects, high...
An Open Brain-Computer Interface (OpenBCI) provides unparalleled freedom and flexibility through open-source hardware firmware at a low-cost implementation. It exploits robust platforms powerful software development kits to create customized drivers with advanced capabilities. Still, several restrictions may significantly reduce the performance of OpenBCI. These limitations include need for more effective communication between computers peripheral devices fast settings under specific...
The early detection of Alzheimer's disease and quantification its progression poses multiple difficulties for machine learning algorithms. Two the most relevant issues are related to missing data results interpretability. To deal with both issues, we introduce a methodology predict conversion mild cognitive impairment patients from structural brain MRI volumes. First, use morphological measures each structure build an instance-based feature mapping that copes missed follow-up visits. Then,...
Dementia is a growing problem that affects elderly people worldwide. More accurate evaluation of dementia diagnosis can help during the medical examination. Several methods for computer-aided have been proposed using resonance imaging scans to discriminate between patients with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) and healthy controls (NC). Nonetheless, especially challenging because heterogeneous intermediate nature MCI. We address automated by introducing novel...
Peripheral nerve blocking (PNB) is a standard procedure to support regional anesthesia. Still, correct localization of the nerve’s structure needed avoid adverse effects; thereby, ultrasound images are used as an aid approach. In addition, image-based automatic segmentation from deep learning methods has been proposed mitigate attenuation and speckle noise ultrasonography issues. Notwithstanding, complex architectures highlight region interest lacking suitable data interpretability...
As a neurodevelopmental pathology, Attention Deficit Hyperactivity Disorder (ADHD) mainly arises during childhood. Persistent patterns of generalized inattention, impulsivity, or hyperactivity characterize ADHD that may persist into adulthood. The conventional diagnosis relies on clinical observational processes yielding high rates overdiagnosis due to varying interpretations among specialists missing information. Although several studies have designed objective behavioral features overcome...
The recurrent use of databases with categorical variables in different applications demands new alternatives to identify relevant patterns. Classification is an interesting approach for the recognition this type data. However, there are a few amount methods purpose literature. Also, those techniques specifically focused only on kernels, having accuracy problems and high computational cost. For reason, we propose identification using conventional classifiers (LDC-QDC-KNN-SVM) mapping increase...
Motor Imagery (MI) refers to imagining the mental representation of motor movements without overt activity, enhancing physical action execution and neural plasticity with potential applications in medical professional fields like rehabilitation education. Currently, most promising approach for implementing MI paradigm is Brain-Computer Interface (BCI), which uses Electroencephalogram (EEG) sensors detect brain activity. However, MI-BCI control depends on a synergy between user skills EEG...
La enfermedad del Alzheimer es un trastorno neurológico que causa la pérdida de autonomía y memoria en las personas padecen. Debido al aumento casos este padecimiento falta precisión herramientas diagnóstico se da paso desarrollo nuevas capaces disminuir esta problemática. El objetivo principal trabajo investigativo implementar modelo red neuronal convolucional tridimensional con estructura base tipo AlexNet3D para obtener predicción posible (AD) a partir análisis imágenes por resonancia...
Alzheimer's disease (AD) is the kind of dementia that affects most people around world. Therefore, an early identification supporting effective treatments required to increase life quality a wide number patients. Recently, computer-aided diagnosis tools for using Magnetic Resonance Imaging scans have been successfully proposed discriminate between patients with AD, mild cognitive impairment, and healthy controls. Most attention has given clinical data, provided by initiatives as ADNI,...
This paper proposes a new solution for local binary fitting energy minimization based on graph cuts automatic brain structure segmentation magnetic resonance images. The approach establishes an effective way to embed the formulation into directed graph, such that is minimized by maximizing flow. Proposed and conventional solutions are compared segmenting well-known BrainWeb synthetic Magnetic Resonance Imaging database. Achieved results show improvement computational cost (about 10 times...
Brain–computer interface (BCI) systems communicate the human brain and computers by converting electrical activity into commands to use external devices. Such kind of system has become an alternative for interaction with environment people suffering from motor disabilities through imagery (MI) paradigm. Despite being most widespread, electroencephalography (EEG)-based MI are highly sensitive noise artifacts. Further, spatially close sources variability among subjects hampers performance....
Neural oscillations are present in the brain at different spatial and temporal scales, they linked to several cognitive functions. Furthermore, information carried by their phases is fundamental for coordination of anatomically distributed processing brain. The concept phase transfer entropy refers an theory-based measure directed connectivity among neural that allows studying such processes. Phase TE commonly obtained from probability estimations out over data multiple trials, which bars...
A new kernel-based image representation is proposed on this paper aiming to support clustering tasks 3D magnetic resonances images. The approach establishes an effective way encode inter-slice similarities, so that the main shape information kept a lower dimensional space. Additionally, spectral technique employed estimate compact embedding space where natural groups are easily detectable. Proposed outperforms conventional voxel-wise sum of squared differences gender category. pair...
Attention deficit hyperactivity disorder (ADHD), most often present in childhood, may persist adult life, hampering personal development. However, ADHD diagnosis is a real challenge since it highly depends on the clinical observation of patient, parental and scholar information, specialist expertise. Despite demanded objective aids from biosignals, physiological biomarkers lack robustness significance under non-stationary non-linear electroencephalographic dynamics. Therefore, this work...