Vasileios G. Kanas

Chimera States in Networks of Nonlocally Coupled Hindmarsh–Rose Neuron Models

We have identified the occurrence of chimera states for various coupling schemes in networks of two-dimensional and three-dimensional Hindmarsh–Rose oscillators, which represent realistic models of neuronal ensembles. This result, together with recent studies on multiple chimera states in nonlocally coupled FitzHugh–Nagumo oscillators, provide strong evidence that the phenomenon of chimeras may indeed be relevant in neuroscience applications. Moreover, our work verifies the existence of chimera states in coupled bistable elements, whereas to date chimeras were known to arise in models possessing a single stable limit cycle. Finally, we have identified an interesting class of mixed oscillatory states, in which desynchronized neurons are uniformly interspersed among the remaining ones that are either stationary or oscillate in synchronized motion.

Investigating machine learning techniques for MRI-based classification of brain neoplasms

PurposeDiagnosis and characterization of brain neoplasms appears of utmost importance for therapeutic management. The emerging of imaging techniques, such as Magnetic Resonance (MR) imaging, gives insight into pathology, while the combination of several sequences from conventional and advanced protocols (such as perfusion imaging) increases the diagnostic information. To optimally combine the multiple sources and summarize the information into a distinctive set of variables however remains difficult. The purpose of this study is to investigate machine learning algorithms that automatically identify the relevant attributes and are optimal for brain tumor differentiation.MethodsDifferent machine learning techniques are studied for brain tumor classification based on attributes extracted from conventional and perfusion MRI. The attributes, calculated from neoplastic, necrotic, and edematous regions of interest, include shape and intensity characteristics. Attributes subset selection is performed aiming to remove redundant attributes using two filtering methods and a wrapper approach, in combination with three different search algorithms (Best First, Greedy Stepwise and Scatter). The classification frameworks are implemented using the WEKA software.ResultsThe highest average classification accuracy assessed by leave-one-out (LOO) cross-validation on 101 brain neoplasms was achieved using the wrapper evaluator in combination with the Best First search algorithm and the KNN classifier and reached 96.9% when discriminating metastases from gliomas and 94.5% when discriminating high-grade from low-grade neoplasms.ConclusionsA computer-assisted classification framework is developed and used for differential diagnosis of brain neoplasms based on MRI. The framework can achieve higher accuracy than most reported studies using MRI.

Chimera states in a two–population network of coupled pendulum–like elements

AbstractMore than a decade ago, a surprising coexistence of synchronous and asynchronous behavior called the chimera state was discovered in networks of nonlocally coupled identical phase oscillators. In later years, chimeras were found to occur in a variety of theoretical and experimental studies of chemical and optical systems, as well as models of neuron dynamics. In this work, we study two coupled populations of pendulum-like elements represented by phase oscillators with a second derivative term multiplied by a mass parameter m and treat the first order derivative terms as dissipation with parameter ∊ > 0. We first present numerical evidence showing that chimeras do exist in this system for small mass values 0 < m ≪ 1. We then proceed to explain these states by reducing the coherent population to a single damped pendulum equation driven parametrically by oscillating averaged quantities related to the incoherent population.

Learning MRI-based classification models for MGMT methylation status prediction in glioblastoma

BACKGROUND AND OBJECTIVE The O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation has been shown to be associated with improved outcomes in patients with glioblastoma (GBM) and may be a predictive marker of sensitivity to chemotherapy. However, determination of the MGMT promoter methylation status requires tissue obtained via surgical resection or biopsy. The aim of this study was to assess the ability of quantitative and qualitative imaging variables in predicting MGMT methylation status noninvasively. METHODS A retrospective analysis of MR images from GBM patients was conducted. Multivariate prediction models were obtained by machine-learning methods and tested on data from The Cancer Genome Atlas (TCGA) database. RESULTS The status of MGMT promoter methylation was predicted with an accuracy of up to 73.6%. Experimental analysis showed that the edema/necrosis volume ratio, tumor/necrosis volume ratio, edema volume, and tumor location and enhancement characteristics were the most significant variables in respect to the status of MGMT promoter methylation in GBM. CONCLUSIONS The obtained results provide further evidence of an association between standard preoperative MRI variables and MGMT methylation status in GBM.

A low cost approach for brain tumor segmentation based on intensity modeling and 3D Random Walker

Abstract Objective Magnetic resonance imaging (MRI) is the primary imaging technique for evaluation of the brain tumor progression before and after radiotherapy or surgery. The purpose of the current study is to exploit conventional MR modalities in order to identify and segment brain images with neoplasms. Methods Four conventional MR sequences, namely, T1-weighted, gadolinium-enhanced T1-weighted, T2-weighted and fluid attenuation inversion recovery, are combined with machine learning techniques to extract global and local information of brain tissues and model the healthy and neoplastic imaging profiles. Healthy tissue clustering, outlier detection and geometric and spatial constraints are applied to perform a first segmentation which is further improved by a modified multiparametric Random Walker segmentation method. The proposed framework is applied on clinical data from 57 brain tumor patients (acquired by different scanners and acquisition parameters) and on 25 synthetic MR images with tumors. Assessment is performed against expert-defined tissue masks and is based on sensitivity analysis and Dice coefficient. Results The results demonstrate that the proposed multiparametric framework differentiates neoplastic tissues with accuracy similar to most current approaches while it achieves lower computational cost and higher degree of automation. Conclusion This study might provide a decision-support tool for neoplastic tissue segmentation, which can assist in treatment planning for tumor resection or focused radiotherapy.

Joint Spatial-Spectral Feature Space Clustering for Speech Activity Detection from ECoG Signals

Brain-machine interfaces for speech restoration have been extensively studied for more than two decades. The success of such a system will depend in part on selecting the best brain recording sites and signal features corresponding to speech production. The purpose of this study was to detect speech activity automatically from electrocorticographic signals based on joint spatial-frequency clustering of the ECoG feature space. For this study, the ECoG signals were recorded while a subject performed two different syllable repetition tasks. We found that the optimal frequency resolution to detect speech activity from ECoG signals was 8 Hz, achieving 98.8% accuracy by employing support vector machines as a classifier. We also defined the cortical areas that held the most information about the discrimination of speech and nonspeech time intervals. Additionally, the results shed light on the distinct cortical areas associated with the two syllables repetition tasks and may contribute to the development of portable ECoG-based communication.

Combining Outlier Detection with Random Walker for Automatic Brain Tumor Segmentation

The diagnosis of brain neoplasms has been facilitated by the emerging of high-quality imaging techniques, such as Magnetic Resonance Imaging (MRI), while the combination of several sequences from conventional and advanced protocols has increased the diagnostic information. Treatment planning and therapy follow-up require the detection of neoplastic and edematous tissue boundaries, a very time consuming task when manually performed by medical experts based on the 3D MRI data. Automating the detection process is challenging, due to the high diversity in appearance of neoplastic tissue among different patients and, in many cases, similarity between neoplastic and normal tissue. In this paper, we propose an automatic brain tumor segmentation method based on a multilabel multiparametric random walks approach initialized by an outlier detection scheme. Segmentation assessment is performed by measuring spatial overlap between automatic segmentation and manual segmentation performed by medical experts. Good agreement is observed in most of the 26 cases for both neoplastic and edematous tissue. The highest achieved overlapping values were 0.74 and 0.79 for neoplastic and edematous tissue, respectively.

EEG-based Classification of Epileptic and Non-Epileptic Events using Multi-Array Decomposition

In this paper, the classification of epileptic and non-epileptic events from EEG is investigated based on temporal and spectral analysis and two different schemes for the formulation of the training set. Although matrix representation which treats features as concatenated vectors allows capturing dependencies across channels, it leads to significant increase of feature vector dimensionality and lacks a means of modeling dependencies between features. Thus, the authors compare the commonly used matrix representation with a tensor-based scheme. TUCKER decomposition is applied to learn the essence of original, high-dimensional domain of feature space. In contrast to other relevant studies, the authors extend the non-epileptic class to both psychogenic non-epileptic seizure and vasovagal syncope. The classification schemes were evaluated on EEG epochs from 11 subjects. The proposed tensor scheme achieved an accuracy of 97,7% which is better compared to the spatiotemporal model even after trying to improve the latter by dimensionality reduction through principal component analysis and feature selection.

Real-time voice activity detection for ECoG-based speech brain machine interfaces

In this article, we investigated the performance of a real-time voice activity detection module exploiting different time-frequency methods for extracting signal features in a subject with implanted electrocorticographic (ECoG) electrodes. We used ECoG signals recorded while the subject performed a syllable repetition task. The voice activity detection module used, as input, ECoG data streams, on which it performed feature extraction and classification. With this approach we were able to detect voice activity (speech onset and offset) from ECoG signals with high accuracy. The results demonstrate that different time-frequency representations carried complementary information about voice activity, with the S-transform achieving 92% accuracy using the 86 best features and support vector machines as the classifier. The proposed real-time voice activity detector may be used as a part of an automated natural speech BMI system for rehabilitating individuals with communication deficits.

Existence and control of chimera states in networks of nonlocally coupled models of neuron oscillators

In a recent work, we have studied networks of two-dimensional and three-dimensional Hindmarsh-Rose oscillators and have discovered some very interesting oscillatory phenomena, called chimera states, in which synchronized neuronal ensembles coexist with completely asynchronous ones. In this paper, we summarize our work in connection with other studies on nonlocally coupled FitzHugh-Nagumo oscillators, examine the occurrence of chimera states in coupled bistable elements and point out that mixed oscillatory states also exist, in which desynchronized neurons are interspersed among neurons that oscillate in synchronous fashion. We also demonstrate, by a preliminary study, that it is possible to control these states by varying an external current parameter applied to the main potential variable in order to observe new phenomena that may be relevant in neuroscience applications.