Álvaro Ángel Orozco

A Kernelized Morphable Model for 3D Brain Tumor Analysis

Abnormal tissue analysis in brain volumes is a difficult task, due to the shape variability that the brain tumors exhibit between patients. The main problem in these processes is that the common techniques use linear representations of the input data which makes unsuitable to model complex shapes as brain tumors. In this paper, we present a kernelized morphable model (3D-KMM) for brain tumor analysis in which the model variations are captured through nonlinear mappings by using kernel principal component analysis. We learn complex shape variations through a high-dimensional representation of the input data. Then from the trained model, we recover the pre-images from the features vectors and perform a non-rigid matching procedure to fit the modeled tumor to a given brain volume. The results show that by using a kernelized morphable model, the non-rigid properties (i.e., nonlinearities and shape variations) of the abnormal tissues can be learned. Finally, our approach proves to be more accurate than the classic morphable model for shape analysis.

Student Desertion Prediction Using Kernel Relevance Analysis

This paper presents a kernel-based relevance analysis to support student desertion prediction. Our approach, termed KRA-SD, is twofold: (i) A feature ranking based on centered kernel alignment to match demographic, academic, and biopsychosocial measures with the output labels (deserter/not deserter), and (ii) classification stage based on k-nearest neighbors and support vector machines to predict the desertion. For concrete testing, the student desertion database of the Universidad Tecnologica de Pereira is employed to assess the KRA-SD under a training, validation, and testing scheme. Attained results show that the proposed approach can recognize the main features related to the student desertion achieving an 85.64% of accuracy. Therefore, the proposed system aims to serve as a handy tool for planning strategies to prevent students from leaving the university without finishing their studies.

Imbalanced Data Classification Using a Relevant Information-Based Sampling Approach

The imbalanced data refer to datasets where the number of samples in one class (majority class) is much higher than the other (minority class) causing biased classifiers in favor of the majority class. Currently, it is difficult to develop an effective model using machine learning algorithms without considering data preprocessing to balance the imbalanced data sets. In this paper, we propose a Relevant Information-based under-sampling (RIS) approach to improve the classification performance for the minority class by selecting the most relevant samples from the majority class as training data. Our RIS approach is based on a self-organizing principle of relevant information, which allows extracting the underlying structure of the majority class preserving different levels of detail of the original data with a smaller number of samples. Additionally, the RIS captures the data structure beyond second order statistics by estimating information theoretic measures which quantify the statistical structure of the majority class accurately, decreasing the consequences of the imbalanced classes distribution problem. We test our methodology on synthetic and real-world imbalanced datasets. Finally, we use a cross-validation scheme to quantify the classifier performance by evaluating the geometric mean. Results show that our proposal outperforms the state of the art methods for imbalanced class distributions regarding classification geometric mean, especially in highly imbalanced datasets.

Multilayer-Based HMM Training to Support Bearing Fault Diagnosis

The bearings are among the most critical components in rotating machinery. For this reason, fault diagnosis in those elements is essential to avoid economic losses and human casualties. Traditionally, the automatic bearing fault diagnosis has been addressed by approaches based on Hidden Markov Models (HMM). However, the efficiency and reliability of the HMM-based diagnostic systems are still relevant topics for many researchers. In this paper, we present a modified training approach based on multilayer partition to support bearing fault diagnosis, that we called MHMM. The proposed strategy seeks to increase the system efficiency by reducing the number of HMM required to perform a proper diagnosis, making it more intelligent and suitable for this application. For concrete testing, the bearing fault databases from the Western Case Reserve University and the Politecnica Salesiana University were employed to assess the MHMM under a training and testing scheme. Attained results show that the proposed approach can effectively reduce the number of models required to perform the diagnosis while keeping high accuracy ratings when we compare the MHMM with the benchmarks. Also, the diagnosis process time is reduced as well.

3D Probabilistic Morphable Models for Brain Tumor Segmentation.

Segmenting abnormal areas in brain volumes is a difficult task, due to the shape variability that the brain tumors exhibit between patients. The main problem in these processes is that the common segmentation techniques used in these tasks, lack of the property of modeling the shape structure that the tumor presents, which leads to an inaccurate segmentation. In this paper, we propose a probabilistic framework in order to model the shape variations related to abnormal tissues relevant in brain tumor segmentation procedures. For this purpose the database of the Brain Tumor Image Segmentation Challenge (Brats) 2015 is used. We use a Probabilistic extension of the 3D morphable model to learn those tumor variations between patients. Then from the trained model, we perform a non-rigid matching to fit the deformed modeled tumor in the medical image. The experimental results show that by using Probabilistic morphable models, the non-rigid properties of the abnormal tissues can be learned and hence improve the segmentation task.

Estimación de la propagación eléctrica cerebral generada por la DBS en pacientes con enfermedad de Parkinson de la región sur-occidente de Colombia

Among the different technologies with important implications today in such areas as education, health and business, videostreaming is highlighted. This considering how this technology facilitates the access to multimedia content remotely, live or offline. The goal of this paper is to propose a test environment for the support of the video streaming service, using open source tools. Moreover, this work proposes, as part of the environment, a stress measurement tool (Hermes), which allows obtaining the response times to establish multiple RTSP connections to streaming servers. The methodology used in this work is divided into four phases: analysis of technologies and tools, configuration of the video streaming environment, design and implementation of Hermes, and finally tests. This methodology allowed the construction of the test environment and its evaluation, through the stress measurement tool Hermes. Finally, in this work we demonstrate how the proposed environment becomes a reference point for different application environments that require the implementation of a video streaming service.Se aplico la mecanica de solidos hiperelasticos al estudio del comportamiento del tubo arterial, ya que es un medio consolidado en la comprension de fenomenos de interes para los profesionales de la medicina y de la ingenieria biomedica. En el caso del organo en cuestion, su estudio se realizo mediante el modelado como un recipiente cilindrico de pared gruesa, donde la funcion de energia empleada permitio considerar aspectos microestructurales como la anisotropia y la dispersion de fibras de colageno. En el problema de equilibrio estatico en el que se implementa esta caracterizacion se representaron las capas media y adventicia de la pared arterial. La solucion expedita del problema de valores en la frontera resultante es posible gracias a la asuncion de un patron de deformacion de simetria axial. Se encontro que el factor de dispersion de fibras y los demas parametros adimensionales del mismo orden de magnitud tienen el rol dominante en la rigidez radial del tubo arterial. Los resultados se presentan utilizando grupos adimensionales, lo cual facilita la interpretacion rapida del efecto de los numerosos parametros que emergen

Estimation of brain electrical propagation generated by the DBS in patients with Parkinson's disease from South-west region of Colombia

Among the different technologies with important implications today in such areas as education, health and business, videostreaming is highlighted. This considering how this technology facilitates the access to multimedia content remotely, live or offline. The goal of this paper is to propose a test environment for the support of the video streaming service, using open source tools. Moreover, this work proposes, as part of the environment, a stress measurement tool (Hermes), which allows obtaining the response times to establish multiple RTSP connections to streaming servers. The methodology used in this work is divided into four phases: analysis of technologies and tools, configuration of the video streaming environment, design and implementation of Hermes, and finally tests. This methodology allowed the construction of the test environment and its evaluation, through the stress measurement tool Hermes. Finally, in this work we demonstrate how the proposed environment becomes a reference point for different application environments that require the implementation of a video streaming service.Se aplico la mecanica de solidos hiperelasticos al estudio del comportamiento del tubo arterial, ya que es un medio consolidado en la comprension de fenomenos de interes para los profesionales de la medicina y de la ingenieria biomedica. En el caso del organo en cuestion, su estudio se realizo mediante el modelado como un recipiente cilindrico de pared gruesa, donde la funcion de energia empleada permitio considerar aspectos microestructurales como la anisotropia y la dispersion de fibras de colageno. En el problema de equilibrio estatico en el que se implementa esta caracterizacion se representaron las capas media y adventicia de la pared arterial. La solucion expedita del problema de valores en la frontera resultante es posible gracias a la asuncion de un patron de deformacion de simetria axial. Se encontro que el factor de dispersion de fibras y los demas parametros adimensionales del mismo orden de magnitud tienen el rol dominante en la rigidez radial del tubo arterial. Los resultados se presentan utilizando grupos adimensionales, lo cual facilita la interpretacion rapida del efecto de los numerosos parametros que emergen

Recognition of Brain Structures from MER-Signals Using Dynamic MFCC Analysis and a HMC Classifier

A novel methodology for the characterization of Microelectrode Recording signals (MER-signals) in Parkinson’s patients in order to recognize basal ganglia in the brain is presented in this work. The most common approach of MER signals analysis consists of time-frequency analysis through Short Time Fourier Transform, Wavelet Transform, or Filters Banks. We present an approach based on MEL-Frequency Cepstral Coefficients (MFCC) and K-means clustering to obtain dynamic features from MER-signals. A Hidden Markov Chain (HMC) with 1, 2, 3, and 4 states was used for the classification of four classes of basal ganglia: Thalamus (Tal), Zone Incerta (ZI), Subthalamic Nucleus (STN) and Substantia Nigra reticulata (SNr), achieving a positive identification over 82%. A performance analysis for each HHM model is presented using ROC curves.

Brain structures recognition using MER signals and medical images - application to brain deep stimulation surgery

Deep brain stimulation (DBS) is the most suitable surgical procedure for patients with Parkinson disease whose symptoms are not well controlled by drug treatment, or who cannot tolerate the side-effects of medication. The success of this surgery procedure, depends on the correct location of the neurostimulator device over the basal ganglia area (i.e. thalamus and globus pallidus). This paper presents a software system DEEPBRAINnav as support tool in Parkinson surgery. This software serves as support to the neurological specialist in DBS surgery. DEEPBRAINnav is composed mainly by two applications. First, it allows to the medical specialist, online recognition of brain structures by the analysis of signals from microelectrode recordings (MER), as well as analyses offline databases allowing the inclusion of new trained classifiers for automatic identification of thalamus location. Secondly, the software includes an interactive application to perform the tracking of the microelectrode device, allowing to the neurosurgeon visualize the path and real location of the microelectrode device implant process. DEEPBRAINnav has been tested for Deep Brain Stimulation surgeries performed at the Institute for Epilepsy and Parkinson of the Eje Cafetero (Colombia). The results shows an accurate tracking of the microelectrode implanting process and achieving positive identifications of the Subthalamic Nucleus (STN) over to 85% using a naive Bayes classifier. Furthermore, develop applications for image and signals guide surgery procedures, allows to the neurologist obtain more support information of a surgery procedure given, with the aim to increase the robustness of the DBS surgery.

Tecnicas de seguimiento de caracteristicas faciales en secuencias de imágenes basadas en metodos de libre modelo.

Facial features play a important role in developmen t of systems on computer vision for different applications such as: the huma n-computer interactive, facial expressions automatic recognition also identify fat igue in car drivers, within these systems, facial features tracking is a signif icant stages that need to be developed, Therefore, this paper focuses on review the different techniques for facial features tracking, such as model-free method s (Kalman filter, particle Filter, among other).