César Alexandre Teixeira

Epileptic seizure prediction using relative spectral power features

OBJECTIVE Prediction of epileptic seizures can improve the living conditions for refractory epilepsy patients. We aimed to improve sensitivity and specificity of prediction methods, and to reduce the number of false alarms. METHODS Relative combinations of sub-band spectral powers of electroencephalogram (EEG) recordings across all possible channel pairs were utilized for tracking gradual changes preceding seizures. By using a specifically developed feature selection method, a set of best candidate features were fed to support vector machines in order to discriminate cerebral state as preictal or non-preictal. RESULTS Proposed algorithm was evaluated on continuous long-term multichannel scalp and invasive recordings (183 seizures, 3565 h). The best results demonstrated a sensitivity of 75.8% (66 out of 87 seizures) and a false prediction rate of 0.1h(-1). Performance was validated statistically, and was superior to that of analytical random predictor. CONCLUSION Applying machine learning methods on a reduced subset of proposed features could predict seizure onsets with high performance. SIGNIFICANCE Our method was evaluated on long-term continuous recordings of overall about 5 months, contrary to majority of previous studies using short-term fragmented data. It is of very low computational cost, while providing acceptable levels of alarm sensitivity and specificity.

The EPILEPSIAE database: an extensive electroencephalography database of epilepsy patients.

From the very beginning the seizure prediction community faced problems concerning evaluation, standardization, and reproducibility of its studies. One of the main reasons for these shortcomings was the lack of access to high‐quality long‐term electroencephalography (EEG) data. In this article we present the EPILEPSIAE database, which was made publicly available in 2012. We illustrate its content and scope. The EPILEPSIAE database provides long‐term EEG recordings of 275 patients as well as extensive metadata and standardized annotation of the data sets. It will adhere to the current standards in the field of prediction and facilitate reproducibility and comparison of those studies. Beyond seizure prediction, it may also be of considerable benefit for studies focusing on seizure detection, basic neurophysiology, and other fields.

EPILAB: A software package for studies on the prediction of epileptic seizures

A Matlab®-based software package, EPILAB, was developed for supporting researchers in performing studies on the prediction of epileptic seizures. It provides an intuitive and convenient graphical user interface. Fundamental concepts that are crucial for epileptic seizure prediction studies were implemented. This includes, for example, the development and statistical validation of prediction methodologies in long-term continuous recordings. Seizure prediction is usually based on electroencephalography (EEG) and electrocardiography (ECG) signals. EPILAB is able to process both EEG and ECG data stored in different formats. More than 35 time and frequency domain measures (features) can be extracted based on univariate and multivariate data analysis. These features can be post-processed and used for prediction purposes. The predictions may be conducted based on optimized thresholds or by applying classifications methods such as artificial neural networks, cellular neuronal networks, and support vector machines. EPILAB proved to be an efficient tool for seizure prediction, and aims to be a way to communicate, evaluate, and compare results and data among the seizure prediction community.

Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods

Combining multiple linear univariate features in one feature space and classifying the feature space using machine learning methods could predict epileptic seizures in patients suffering from refractory epilepsy. For each patient, a set of twenty-two linear univariate features were extracted from 6 electroencephalogram (EEG) signals to make a 132 dimensional feature space. Preprocessing and normalization methods of the features, which affect the output of the seizure prediction algorithm, were studied in terms of alarm sensitivity and false prediction rate (FPR). The problem of choosing an optimal preictal time was tackled using 4 distinct values of 10, 20, 30, and 40 min. The seizure prediction problem has traditionally been considered a two-class classification problem, which is also exercised here. These studies have been conducted on the features obtained from 10 patients. For each patient, 48 different combinations of methods are compared to find the best configuration. Normalization by dividing by the maximum and smoothing are found to be the best configuration in most of the patients. The results also indicate that applying machine learning methods on a multidimensional feature space of 22 univariate features predicted seizure onsets with high performance. On average, the seizures were predicted in 73.9% of the cases (34 out of 46 in 737.9h of test data), with a FPR of 0.15 h(-1).

A Soft-Computing Methodology for Noninvasive Time-Spatial Temperature Estimation

The safe and effective application of thermal therapies is restricted due to lack of reliable noninvasive temperature estimators. In this paper, the temporal echo-shifts of backscattered ultrasound signals, collected from a gel-based phantom, were tracked and assigned with the past temperature values as radial basis functions neural networks input information. The phantom was heated using a piston-like therapeutic ultrasound transducer. The neural models were assigned to estimate the temperature at different intensities and points arranged across the therapeutic transducer radial line (60 mm apart from the transducer face). Model inputs, as well as the number of neurons were selected using the multiobjective genetic algorithm (MOGA). The best attained models present, in average, a maximum absolute error less than 0.5 C, which is pointed as the borderline between a reliable and an unreliable estimator in hyperthermia/diathermia. In order to test the spatial generalization capacity, the best models were tested using spatial points not yet assessed, and some of them presented a maximum absolute error inferior to 0.5 C, being ldquoelectedrdquo as the best models. It should be also stressed that these best models present implementational low-complexity, as desired for real-time applications.

Epileptic seizure predictors based on computational intelligence techniques

The ability of computational intelligence methods to predict epileptic seizures is evaluated in long-term EEG recordings of 278 patients suffering from pharmaco-resistant partial epilepsy, also known as refractory epilepsy. This extensive study in seizure prediction considers the 278 patients from the European Epilepsy Database, collected in three epilepsy centres: Hôpital Pitié-là-Salpêtrière, Paris, France; Universitätsklinikum Freiburg, Germany; Centro Hospitalar e Universitário de Coimbra, Portugal. For a considerable number of patients it was possible to find a patient specific predictor with an acceptable performance, as for example predictors that anticipate at least half of the seizures with a rate of false alarms of no more than 1 in 6 h (0.15 h⁻¹). We observed that the epileptic focus localization, data sampling frequency, testing duration, number of seizures in testing, type of machine learning, and preictal time influence significantly the prediction performance. The results allow to face optimistically the feasibility of a patient specific prospective alarming system, based on machine learning techniques by considering the combination of several univariate (single-channel) electroencephalogram features. We envisage that this work will serve as benchmark data that will be of valuable importance for future studies based on the European Epilepsy Database.

Slow modulations of high-frequency activity (40–140 Hz) discriminate preictal changes in human focal epilepsy

Recent evidence suggests that some seizures are preceded by preictal changes that start from minutes to hours before an ictal event. Nevertheless an adequate statistical evaluation in a large database of continuous multiday recordings is still missing. Here, we investigated the existence of preictal changes in long-term intracranial recordings from 53 patients with intractable partial epilepsy (in total 531 days and 558 clinical seizures). We describe a measure of brain excitability based on the slow modulation of high-frequency gamma activities (40–140 Hz) in ensembles of intracranial contacts. In prospective tests, we found that this index identified preictal changes at levels above chance in 13.2% of the patients (7/53), suggesting that results may be significant for the whole group (p < 0.05). These results provide a demonstration that preictal states can be detected prospectively from EEG data. They advance understanding of the network dynamics leading to seizure and may help develop novel seizure prediction algorithms.

Modeling epileptic brain states using EEG spectral analysis and topographic mapping.

Changes in the spatio-temporal behavior of the brain electrical activity are believed to be associated to epileptic brain states. We propose a novel methodology to identify the different states of the epileptic brain, based on the topographic mapping of the time varying relative power of delta, theta, alpha, beta and gamma frequency sub-bands, estimated from EEG. Using normalized-cuts segmentation algorithm, points of interest are identified in the topographic mappings and their trajectories over time are used for finding out relations with epileptogenic propagations in the brain. These trajectories are used to train a Hidden Markov Model (HMM), which models the different epileptic brain states and the transition among them. Applied to 10 patients suffering from focal seizures, with a total of 30 seizures over 497.3h of data, the methodology shows good results (an average point-by-point accuracy of 89.31%) for the identification of the four brain states--interictal, preictal, ictal and postictal. The results suggest that the spatio-temporal dynamics captured by the proposed methodology are related to the epileptic brain states and transitions involved in focal seizures.

Pre-ictal heart rate variability assessment of epileptic seizures by means of linear and non-linear analyses.

OBJECTIVE The purpose of the present study was to analyze the effects of epilepsy on the autonomic control of the heart in pre-ictal phase in order to find an algorithm of early detection of seizure onset. METHODS Overall 133 epileptic seizures were analyzed from 12 patients with epilepsy (seven males and five females; mean age 43.91 years, SD: 10.16) participated in this study. Single lead electrocardiogram recordings of epileptic patients were compiled. 240, 90-30, 30-10 and 5 minutes heart rate variability (HRV) signals of preseizure were chosen for analysis of heart rate. As HRV signals are non-stationary, a set of time and frequency domain features (Mean HR, Triangular Index, LF, HF, LF/HF) and nonlinear parameters (SD1, SD2 and SD2/SD1 indices derived from Poincare plots) extracted from HRV is analyzed. Statistical analysis was performed using paired sample t-test for comparisons of the segments and differences between pre-ictal segments were evaluated by Tukey tests. RESULTS There was slight tachycardia in segments near the seizure (30 minutes before: 85.3517 bpm, 5 minutes before: 119.3630.82 bpm, p=0.0207) which significantly differ from baseline in segments far from seizure (240 minutes before: 66.5211.7 bpm). Also there was significant increase in LF/HF ratio (30 minutes before: 1.10.22, 5 minutes before: 2.120.5, p=0.0332) and SD2/SD1 ratio (30 minutes before: 1.20.15, 5 minutes before: 2.030.55, p=0.0431) when compared to segments far from the seizure (240 minutes before: 0.780.24 and 0.780.14) respectively. Although there was about decrease of triangular index in segments near the seizure the percentage of decrease was not comparable to segments far from the seizure. CONCLUSION Significant changes of HRV parameters in pre-ictal (5 minutes before the seizure) are obviously higher in comparison to interictal baseline. Pre-ictal significant changes of HRV suggesting that this time can be considered as prediction time for designing an algorithm of early detection of seizure onset based on HRV.

On the possibility of non-invasive multilayer temperature estimation using soft-computing methods

OBJECTIVE AND MOTIVATION This work reports original results on the possibility of non-invasive temperature estimation (NITE) in a multilayered phantom by applying soft-computing methods. The existence of reliable non-invasive temperature estimator models would improve the security and efficacy of thermal therapies. These points would lead to a broader acceptance of this kind of therapies. Several approaches based on medical imaging technologies were proposed, magnetic resonance imaging (MRI) being appointed as the only one to achieve the acceptable temperature resolutions for hyperthermia purposes. However, MRI intrinsic characteristics (e.g., high instrumentation cost) lead us to use backscattered ultrasound (BSU). Among the different BSU features, temporal echo-shifts have received a major attention. These shifts are due to changes of speed-of-sound and expansion of the medium. NOVELTY ASPECTS The originality of this work involves two aspects: the estimator model itself is original (based on soft-computing methods) and the application to temperature estimation in a three-layer phantom is also not reported in literature. MATERIALS AND METHODS In this work a three-layer (non-homogeneous) phantom was developed. The two external layers were composed of (in % of weight): 86.5% degassed water, 11% glycerin and 2.5% agar-agar. The intermediate layer was obtained by adding graphite powder in the amount of 2% of the water weight to the above composition. The phantom was developed to have attenuation and speed-of-sound similar to in vivo muscle, according to the literature. BSU signals were collected and cumulative temporal echo-shifts computed. These shifts and the past temperature values were then considered as possible estimators inputs. A soft-computing methodology was applied to look for appropriate multilayered temperature estimators. The methodology involves radial-basis functions neural networks (RBFNN) with structure optimized by the multi-objective genetic algorithm (MOGA). In this work 40 operating conditions were considered, i.e. five 5-mm spaced spatial points and eight therapeutic intensities (I(SATA)): 0.3, 0.5, 0.7, 1.0, 1.3, 1.5, 1.7 and 2.0W/cm(2). Models were trained and selected to estimate temperature at only four intensities, then during the validation phase, the best-fitted models were analyzed in data collected at the eight intensities. This procedure leads to a more realistic evaluation of the generalisation level of the best-obtained structures. RESULTS AND DISCUSSION At the end of the identification phase, 82 (preferable) estimator models were achieved. The majority of them present an average maximum absolute error (MAE) inferior to 0.5 degrees C. The best-fitted estimator presents a MAE of only 0.4 degrees C for both the 40 operating conditions. This means that the gold-standard maximum error (0.5 degrees C) pointed for hyperthermia was fulfilled independently of the intensity and spatial position considered, showing the improved generalisation capacity of the identified estimator models. As the majority of the preferable estimator models, the best one presents 6 inputs and 11 neurons. In addition to the appropriate error performance, the estimator models present also a reduced computational complexity and then the possibility to be applied in real-time. CONCLUSIONS A non-invasive temperature estimation model, based on soft-computing technique, was proposed for a three-layered phantom. The best-achieved estimator models presented an appropriate error performance regardless of the spatial point considered (inside or at the interface of the layers) and of the intensity applied. Other methodologies published so far, estimate temperature only in homogeneous media. The main drawback of the proposed methodology is the necessity of a-priory knowledge of the temperature behavior. Data used for training and optimisation should be representative, i.e., they should cover all possible physical situations of the estimation environment.