Miguel A. Becerra

Bio: Miguel A. Becerra is an academic researcher from National University of Colombia. The author has contributed to research in topics: Support vector machine & Feature extraction. The author has an hindex of 7, co-authored 48 publications receiving 157 citations.

Speckle Noise Reduction in Ultrasound Images for Improving the Metrological Evaluation of Biomedical applications: an Overview

Abstract: In recent years, many studies have examined filters for eliminating or reducing speckle noise, which is inherent to ultrasound images, in order to improve the metrological evaluation of their biomedical applications. In the case of medical ultrasound images, said noise can produce uncertainty in the diagnosis because details, such as limits and edges, should be preserved. Most algorithms can eliminate speckle noise, but they do not consider the conservation of these details. This paper describes, in detail, 27 techniques that mainly focus on the smoothing or elimination of speckle noise in medical ultrasound images. The aim of this study is to highlight the importance of improving said smoothing and elimination, which are directly related to several processes (such as the detection of regions of interest) described in other articles examined in this study. Furthermore, the description of this collection of techniques facilitates the implementation of evaluations and research with a more specific scope. This study initially covers several classical methods, such as spatial filtering, diffusion filtering, and wavelet filtering. Subsequently, it describes recent techniques in the field of machine learning focused on deep learning, which are not yet well known but greatly relevant, along with some modern and hybrid models in the field of speckle-noise filtering. Finally, five Full-Reference (FR) distortion metrics, common in filter evaluation processes, are detailed along with a compensation methodology between FR and Non-Reference (NR) metrics, which can generate greater certainty in the classification of the filters by considering the information of their behavior in terms of perceptual quality provided by NR metrics.

Dimensionality reduction based on fuzzy rough sets oriented to ischemia detection

Abstract: This paper presents a dimensionality reduction study based on fuzzy rough sets with the aim of increasing the discriminant capability of the representation of normal ECG beats and those that contain ischemic events. A novel procedure is proposed to obtain the fuzzy equivalence classes based on entropy and neighborhood techniques and a modification of the Quick Reduct Algorithm is used to select the relevant features from a large feature space by a dependency function. The tests were carried out on a feature space made up by 840 wavelet features extracted from 900 ECG normal beats and 900 ECG beats with evidence of ischemia. Results of around 99% classification accuracy are obtained. This methodology provides a reduced feature space with low complexity and high representation capability. Additionally, the discriminant strength of entropy in terms of representing ischemic disorders from time-frequency information in ECG signals is highlighted.

Effect of the electrograms density in detecting and ablating the tip of the rotor during chronic atrial fibrillation: an in silico study.

Abstract: Aims Identification in situ of arrhythmogenic mechanisms could improve the rate of ablation success in atrial fibrillation (AF). Our research group reported that rotors could be located through dynamic approximate entropy (DApEn) maps. However, it is unknown how much the spatial resolution of catheter electrodes could affect substrates localization. The present work looked for assessing the electrograms (EGMs) spatial resolution needed to locate the rotor tip using DApEn maps. Methods and results A stable rotor in a two-dimensional computational model of human atrial tissue was simulated using the Courtemanche electrophysiological model and implementing chronic AF features. The spatial resolution is 0.4 mm (150 × 150 EGM). Six different lower resolution arrays were obtained from the initial mesh. For each array, DApEn maps were constructed using the inverse distance weighting (IDW) algorithm. Three simple ablation patterns were applied. The full DApEn map detected the rotor tip and was able to follow the small meander of the tip through the shape of the area containing the tip. Inverse distance weighting was able to reconstruct DApEn maps after applying different spatial resolutions. These results show that spatial resolutions from 0.4 to 4 mm accurately detect the rotor tip position. An ablation line terminates the rotor only if it crosses the tip and ends at a tissue boundary. Conclusion A previous work has shown that DApEn maps successfully detected simulated rotor tips using a high spatial resolution. In this work, it was evinced that DApEn maps could be applied using a spatial resolution similar to that available in commercial catheters, by adding an interpolation stage. This is the first step to translate this tool into medical practice with a view to the detection of ablation targets.

Odor Pleasantness Classification from Electroencephalographic Signals and Emotional States

Abstract: Odor identification refers to the capability of the olfactory sense for discerning odors. The interest in this sense has grown over multiple fields and applications such as multimedia, virtual reality, marketing, among others. Therefore, objective identification of pleasant and unpleasant odors is an open research field. Some studies have been carried out based on electroencephalographic signals (EEG). Nevertheless, these can be considered insufficient due to the levels of accuracy achieved so far. The main objective of this study was to investigate the capability of the classifiers systems for identification pleasant and unpleasant odors from EEG signals. The methodology applied was carried out in three stages. First, an odor database was collected using the signals recorded with an Emotiv Epoc+ with 14 channels of electroencephalography (EEG) and using a survey for establishing the emotion levels based on valence and arousal considering that the odor induces emotions. The registers were acquired from three subjects, each was subjected to 10 different odor stimuli two times. The second stage was the feature extraction which was carried out on 5 sub-bands \(\delta \), \(\theta \), \(\alpha \), \(\beta \), \(\gamma \) of EEG signals using discrete wavelet transform, statistical measures, and other measures such as area, energy, and entropy. Then, feature selection was applied based on Rough Set algorithms. Finally, in the third stage was applied a Support vector machine (SVM) classifier, which was tested with five different kernels. The performance of classifiers was compared using k-fold cross-validation. The best result of 99.9% was achieved using the linear kernel. The more relevant features were obtained from sub-bands \(\beta \) and \(\alpha \). Finally, relations among emotion, EEG, and odors were demonstrated.

Kernel-based framework for spectral dimensionality reduction and clustering formulation: A theoretical study

Abstract: This work outlines a unified formulation to represent spectral approaches for both dimensionality reduction and clustering. Proposed formulation starts with a generic latent variable model in terms of the projected input data matrix.Particularly, such a projection maps data onto a unknown high-dimensional space. Regarding this model, a generalized optimization problem is stated using quadratic formulations and a least-squares support vector machine.The solution of the optimization is addressed through a primal-dual scheme.Once latent variables and parameters are determined, the resultant model outputs a versatile projected matrix able to represent data in a low-dimensional space, as well as to provide information about clusters. Particularly, proposedformulation yields solutions for kernel spectral clustering and weighted-kernel principal component analysis.

Statistical Pattern Recognition

Abstract: This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Spectral Analysis Identifies Sites of High-Frequency Activity Maintaining Atrial Fibrillation in Humans

Abstract: Background— The identification of sites of dominant activation frequency during atrial fibrillation (AF) in humans and the effect of ablation at these sites have not been reported. Methods and Results— Thirty-two patients undergoing AF ablation (19 paroxysmal, 13 permanent) during ongoing arrhythmia were studied. Electroanatomic mapping was performed, acquiring 126±13 points per patient throughout both atria and coronary sinus. At each point, 5-second electrograms were obtained to determine the highest-amplitude frequency on spectral analysis and to construct 3D dominant frequency (DF) maps. The temporal stability of the recording interval was confirmed in a subset. Ablation was performed with the operator blinded to the DF maps. The effect of ablation at sites with or without high-frequency DF sites (maximal frequencies surrounded by a decreasing frequency gradient ≥20%) was evaluated by determining the change in AF cycle length (AFCL) and the termination and inducibility of AF. The spatial distribution ...

Pulmonary Vein Denervation Enhances Long-Term Benefit After Circumferential Ablation for Paroxysmal Atrial Fibrillation

Abstract: Background— There are no data to evaluate the relationship between autonomic nerve function modification and recurrent atrial fibrillation (AF) after circumferential pulmonary vein ablation (CPVA). This study assesses the incremental benefit of vagal denervation by radiofrequency in preventing recurrent AF in a large series of patients undergoing CPVA for paroxysmal AF. Methods and Results— Data were collected on 297 patients undergoing CPVA for paroxysmal AF. Abolition of all evoked vagal reflexes around all pulmonary vein ostia was defined as complete vagal denervation (CVD) and was obtained in 34.3% of patients. Follow-up ended at 12 months. Heart rate variability attenuation, consistent with vagal withdrawal, was detectable for up to 3 months after CPVA, particularly in patients with reflexes and CVD, who were less likely to have recurrent AF than those without reflexes (P=0.0002, log-rank test). Only the percentage area of left atrial isolation and CVD were predictors of AF recurrence after CPVA (P<0...

Catheter Ablation Versus Antiarrhythmic Drugs for Atrial Fibrillation

Abstract: Background—The mainstay of treatment for atrial fibrillation (AF) remains pharmacological; however, catheter ablation has increasingly been used over the last decade. The relative merits of each strategy have not been extensively studied. Methods and Results—We conducted a randomized multicenter comparison of these 2 treatment strategies in patients with paroxysmal AF resistant to at least 1 antiarrhythmic drug. The primary end point was absence of recurrent AF between months 3 and 12, absence of recurrent AF after up to 3 ablation procedures, or changes in antiarrhythmic drugs during the first 3 months. Ablation consisted of pulmonary vein isolation in all cases, whereas additional extrapulmonary vein lesions were at the discretion of the physician. Crossover was permitted at 3 months in case of failure. Echocardiographic data, symptom score, exercise capacity, quality of life, and AF burden were evaluated at 3, 6, and 12 months by the supervising committee. Of 149 eligible patients, 112 (18 women [16%];...