Álvaro A. Orozco

Feature selection for multimodal emotion recognition in the arousal-valence space

Emotion recognition is a challenging research problem with a significant scientific interest. Most of the emotion assessment studies have focused on the analysis of facial expressions. Recently, it has been shown that the simultaneous use of several biosignals taken from the patient may improve the classification accuracy. An open problem in this area is to identify which biosignals are more relevant for emotion recognition. In this paper, we perform Recursive Feature Elimination (RFE) to select a subset of features that allows emotion classification. Experiments are carried out over a multimodal database with arousal and valence annotations, and a diverse range of features extracted from physiological, neurophysiological, and video signals. Results show that several features can be eliminated while still preserving classification accuracy in setups of 2 and 3 classes. Using a small subset of the features, it is possible to reach 70% accuracy for arousal and 60% accuracy for valence in some experiments. Experimentally, it is shown that the Galvanic Skin Response (GSR) is relevant for arousal classification, while the electroencephalogram (EEG) is relevant for valence.

Driving fatigue detection using active shape models

Driver fatigue is a major cause of traffic accidents. The fatigue detection systems based on computer vision have great potential given its property of non-invasiveness. Major challenges that arise are fast movements of eyes and mouth, changes in pose and lighting variations. In this paper an Active Shape Model is presented for facial features detection of features extracted from the parametric model Candide-3. We describe the characterization methodology from parametric model. Also quantitatively evaluated the accuracy for feature detection and estimation of the parameters associated with fatigue, analyzing its robustness to variations in pose and local variations in the regions of interest. The model used and characterization methodology showed efficient to detect fatigue in 100% of the cases.

A Gaussian Process Emulator for Estimating the Volume of Tissue Activated During Deep Brain Stimulation

The volume of tissue activated (VTA) is a well established approach to model the effects of deep brain stimulation (DBS), and previous studies have pointed to its potential benefits in clinical applications. However, the elevated computational cost of the standard technique for VTA estimation limits its suitability for practical use. In this study we developed a novel methodology to reduce the cost of VTA estimation. Our approach combines multicompartment axon models coupled to the stimulating electric field with a Gaussian emulator. We achieved a remarkable reduction in the average time required for VTA estimation, without the loss of accuracy and other limitations entailed by alternative methods used to attain similar benefits, such as activation threshold curves.

A probabilistic framework based on SLIC-superpixel and Gaussian processes for segmenting nerves in ultrasound images

We deal with an important problem in the field of anesthesiology known as automatic segmentation of nerve structures depicted in ultrasound images. This is important to aid the experts in anesthesiology, in order to carry out Peripheral Nerve Blocking (PNB). Ultrasound imaging has gained recent interest for performing PNB procedures since it offers a non-invasive visualization of the nerve and the anatomical structures around it. However, the location of these nerves in ultrasound images is a difficult task for the specialist due to the artifacts (i.e. speckle noise) that affect the intelligibility of a given image. In this paper, we present a probabilistic approach based on Simple Linear Iterative Clustering (SLIC-superpixels) and Gaussian processes for automatic segmentation of peripheral nerves. First, we use Graph cuts segmentation to define a region of interest (ROI). Such a ROI is divided into several correlated regions using SLIC-superpixels, then, a nonlinear Wavelet transform is applied as feature extraction stage. Finally, we use a classification scheme based on Gaussian Processes in order to predict the label of each parametrized superpixel (the label can be “nerve” or “background”). The accuracy of the proposed method is measured in terms of the Dice coefficient. Results obtained show performances with a Dice coefficient of 0.6524±0.0085 which brings accurate performances in nerve segmentation processes.

Peripheral nerve segmentation using Nonparametric Bayesian Hierarchical Clustering

Several cases related to chronic pain, due to accidents, illness or surgical interventions, depend on anesthesiology procedures. These procedures are assisted with ultrasound images. Although, the ultrasound images are a useful instrument in order to guide the specialist in anesthesiology, the lack of intelligibility due to speckle noise, makes the clinical intervention a difficult task. In a similar manner, some artifacts are introduced in the image capturing process, challenging the expertise of anesthesiologists for not confusing the true nerve structures. Accordingly, an assistance methodology using image processing can improve the accuracy in the anesthesia practice. This paper proposes a peripheral nerve segmentation method in medical ultrasound images, based on Nonparametric Bayesian Hierarchical Clustering. The experimental results show segmentation performances with a Mean Squared Error performance of 1.026 ± 0.379 pixels for ulnar nerve, 0.704 ± 0.233 pixels for median nerve and 1.698 ± 0.564 pixels for peroneal nerve. Likewise, the model allows to emphasize other soft structures like muscles and aqueous tissues, that might be useful for an anesthesiologist.

Peripheral Nerves Segmentation in Ultrasound Images Using Non-linear Wavelets and Gaussian Processes

Regional anesthesia is carried out using a technique called peripheral nerve blocking (PNB), which involves the administration of an anesthetic nearby the nerve. Ultrasound images have been widely used for PNB procedure due to their low cost and because they are non-invasive. However, the segmentation of nerve structures in ultrasound images is a challenging task for the specialists since the images are affected by echo perturbations and speckle noise. Automatic or semi-automatic segmentation systems can be developed in order to aid the specialist for locating nerves structures accurately. In this paper we propose a methodology for the semi-automatic segmentation of nerve structures in ultrasound images. We use non-linear Wavelets transform in the feature extraction step and for the classification stage we use a Gaussian Processes classifier. Experimental results show that the implemented methodology can segment nerve structures accurately.

Peripheral Nerve Segmentation Using Speckle Removal and Bayesian Shape Models

In the field of medicine, ultrasound images have become a useful tool for visualizing nerve structures in the process of anesthesiology. Although, these images are commonly used in medical procedures such as peripheral nerve blocks. Their poor intelligibility makes it difficult for the anesthesiologists to perform this process accurately. Therefore, an automated segmentation methodology of the peripheral nerves can assist the experts in improving accuracy. This paper proposes a peripheral nerve segmentation method in medical ultrasound images, based on Speckle removal and Bayesian shape models. The method allows segmenting efficiently a given nerve by performing a Bayesian shape fitting. The experimental results show that performing a speckle removal before fitting the model, improves the accuracy due to the enhancement of the image to segment.

Dynamic physiological signal analysis based on Fisher kernels for emotion recognition

Emotional behavior is an active area of study in the fields of neuroscience and affective computing. This field has the fundamental role of emotion recognition in the maintenance of physical and mental health. Valence/Arousal levels are two orthogonal, independent dimensions of any emotional stimulus and allows an analysis framework in affective research. In this paper we present our framework for emotional regression based on machine learning techniques. Autoregressive coefficients and hidden markov models on physiological signals, based on Fisher Kernels characterization are presented for mapping variable length sequences to new dimension feature vector space. Then, support vector regression is performed over the Fisher Scores for emotional recognition. Also quantitatively we evaluated the accuracy of the proposed model by acomplishing a hold-out cross validation over the dataset. The experimental results show that the proposed model can effectively perform the regression in comparison with static characterization methods.

NEUROZONE: On-line recognition of brain structures in stereotactic surgery - application to Parkinson's disease

The success of stereotactic surgery for Deep Brain Stimulation depends critically on the exact positioning of a microelectrode recording in a target area of the brain. This paper presents the software system NEUROZONE composed of two main applications: first, it allows online recognition of brain structures by the analysis of signals from microelectrode recordings (MER), and second, it processes and analyses off-line databases allowing the inclusion of new trained classifiers for automatic identification. The software serves as a support to the analysis done by a medical specialist during surgery, and seeks to reduce the adverse side effects that may occur because of inadequate identification of the target areas. The software also allows the specialists to label recordings obtained during surgery, in order to generate a new off-line database or increase the amount of records in an already existing off-line database. NEUROZONE has been tested for Deep Brain Stimulation performed at the Institute for Epilepsy and Parkinson of the Eje Cafetero (Colombia), achieving positive identifications of the Subthalamic Nucleus (STN) over to 85% using a naive Bayes classifier.

Multi-patient learning increases accuracy for Subthalamic nucleus identification in deep brain stimulation

Establishing the exact position of basal ganglia is key in several brain surgeries, particularly in deep brain stimulation for patients suffering from Parkinsons disease. There have been recent attempts to introduce automatic systems with the ability to localize, with high accuracy, specific brain regions. These systems usually follow the classical supervised learning paradigm, in which training data from different patients are employed to construct a classifier that is patient-independent. In this paper, we show how by sharing information from different patients, it is possible to increase accuracy for targeting the Subthalamic Nucleus. We do this in the context of multi-task learning, where different but related tasks are used simultaneously to leverage the performance of a learning system. Results show that the multitask framework can outperform the traditional patient-independent scenario in two different real datasets.