Gerard Forzy

Multi-channel analysis of the EEG signals and statistic particularities for epileptic seizure forecast

In France, 5 to 8 people in 1000 suffer from epilepsy. An epileptic seizure is sudden, impressive, and is often followed by a loss of consciousness by the patient. The clinical studies have demonstrated that neuronal activity is responsible for these seizures. The electroencephalograms recorded by the doctors allow the visualization of the very beginning of the crises. The aim of our previous studies was to determine characteristics of the EEG signals that will allow us to forecast the seizures (Peyrodie et al., 2001). We reached the conclusion that using that using principal components analysis, we were able to find out some grapho-elements in the 2 first principal components that where leading us to highlight a state were patients are likely to make a seizure. A new challenge consists in trying to provide an interpretation of these grapho-elements. The first part is concerned in the explanation of the principal components analysis and the results it gave us. The second part is concerned with a statistical study of the principal components using a log-likelihood method. The third part is concerned with the use of independent component analysis to filter the EEG signals.

Improvements of Adaptive Filtering by Optimal Projection to filter different artifact types on long duration EEG recordings

Adaptive Filtering by Optimal Projection (AFOP) is an automatic method for reducing ocular and muscular artifacts on electro-encephalographic (EEG) recordings. This paper presents two additions to this method: an improvement of the stability of ocular artifact filtering and an adaptation of the method for filtering electrode artifacts. With these improvements, it is possible to reduce almost all the current types of artifacts, while preserving brain signals, particularly those characterising epilepsy. This generalised method consists of dividing the signal into several time-frequency windows, and in applying different spatial filters to each. Two steps are required to define one of these spatial filters: the first step consists of defining artifact spatial projection using the Common Spatial Pattern (CSP) method and the second consists of defining EEG spatial projection via regression. For this second step, a progressive orthogonalisation process is proposed to improve stability. This method has been tested on long-duration EEG recordings of epileptic patients. A neurologist quantified the ratio of removed artifacts and the ratio of preserved EEG. Among the 330 artifacted pages used for evaluation, readability was judged better for 78% of pages, equal for 20% of pages, and worse for 2%. Artifact amplitudes were reduced by 80% on average. At the same time, brain sources were preserved in amplitude from 70% to 95% depending on the type of waves (alpha, theta, delta, spikes, etc.). A blind comparison with manual Independent Component Analysis (ICA) was also realised. The results show that this method is competitive and useful for routine clinical practice.

BioSigPlot: An opensource tool for the visualization of multi-channel biomedical signals with Matlab

This paper presents a Matlab-based software (MathWorks inc.) called BioSigPlot for the visualization of multi-channel biomedical signals, particularly for the EEG. This tool is designed for researchers on both engineering and medicine who have to collaborate to visualize and analyze signals. It aims to provide a highly customizable interface for signal processing experimentation in order to plot several kinds of signals while integrating the common tools for physician. The main advantages compared to other existing programs are the multi-dataset displaying, the synchronization with video and the online processing. On top of that, this program uses object oriented programming, so that the interface can be controlled by both graphic controls and command lines. It can be used as EEGlab plug-in but, since it is not limited to EEG, it would be distributed separately. BioSigPlot is distributed free of charge (http://biosigplot.sourceforge.net), under the terms of GNU Public License for non-commercial use and open source development.

Texture segmentation using globally active contours model and Cauchy-Schwarz distance

We present a new unsupervised segmentation based active contours model and local region texture descriptor. The proposed local region texture descriptor intrinsically describes the geometry of textural regions using the shape operator defined in Beltrami framework. The local texture descriptor is incorporated in the active contours using the Cauchy-Schwarz distance. The texture is discriminated by maximizing distance between the probability density functions which leads to distinguish textural objects of interest and background. We propose a fast Bregman split implementation of our segmentation algorithm based on the dual formulation of the Total Variation norm. Finally, we show results on some challenging images to illustrate segmentations that are possible.

Semi-automated image analysis of gel electrophoresis of cerebrospinal fluid for oligoclonal band detection

Detection of oligoclonal electrophoretic bands in cerebrospinal fluid (CSF) is an important diagnostic tool for Multiple Sclerosis (MS). Electrophoretic profiles are difficult to interpret due to low contrast and artefacts. A semi-automated method to ease analysis and to reduce subjectivity is presented. The method sequentially converts color images to grayscale, realigns bands, removes artifacts, then converts 2D images to a signal, before detecting, thresholding and editing peaks to optimize profiles. Such treated profiles (21 positive and 15 negative) are compared to ground truth analysis of an expert biologist. 16 profiles over 21 are well detected positive and 12 profiles over 15 are detected negative, results seem similar to inter-experts variability reported in literature.Detection of oligoclonal electrophoretic bands in cerebrospinal fluid (CSF) is an important diagnostic tool for Multiple Sclerosis (MS). Electrophoretic profiles are difficult to interpret due to low contrast and artefacts. A semi-automated method to ease analysis and to reduce subjectivity is presented. The method sequentially converts color images to grayscale, realigns bands, removes artifacts, then converts 2D images to a signal, before detecting, thresholding and editing peaks to optimize profiles. Such treated profiles (21 positive and 15 negative) are compared to ground truth analysis of an expert biologist. 16 profiles over 21 are well detected positive and 12 profiles over 15 are detected negative, results seem similar to inter-experts variability reported in literature.

Prostate contours delineation using interactive directional active contours model and parametric shape prior model

Prostate contours delineation on Magnetic Resonance (MR) images is a challenging and important task in medical imaging with applications of guiding biopsy, surgery and therapy. While a fully automated method is highly desired for this application, it can be a very difficult task due to the structure and surrounding tissues of the prostate gland. Traditional active contours-based delineation algorithms are typically quite successful for piecewise constant images. Nevertheless, when MR images have diffuse edges or multiple similar objects (e.g. bladder close to prostate) within close proximity, such approaches have proven to be unsuccessful. In order to mitigate these problems, we proposed a new framework for bi-stage contours delineation algorithm based on directional active contours (DAC) incorporating prior knowledge of the prostate shape. We first explicitly addressed the prostate contour delineation problem based on fast globally DAC that incorporates both statistical and parametric shape prior model. In doing so, we were able to exploit the global aspects of contour delineation problem by incorporating a user feedback in contours delineation process where it is shown that only a small amount of user input can sometimes resolve ambiguous scenarios raised by DAC. In addition, once the prostate contours have been delineated, a cost functional is designed to incorporate both user feedback interaction and the parametric shape prior model. Using data from publicly available prostate MR datasets, which includes several challenging clinical datasets, we highlighted the effectiveness and the capability of the proposed algorithm. Besides, the algorithm has been compared with several state-of-the-art methods.

Fast globally supervised segmentation by active contours with shape and texture descriptors

We present a new globally supervised segmentation method in the characteristic function framework based on an active contours (AC) model incorporating both shape prior and texture descriptors. The shape prior descriptor is formulated as the traditional Legendre moment and the texture descriptor as a linear combination of local inside/outside texture descriptor. Using these two descriptors, the AC energy incorporates both learned textures and training shapes. This formulation has two main advantages: 1) by discriminating independently the foreground/background textures. 2) by incorporating both the learned inside/outside texture and the training shape. The trade-off between inside and outside texture descriptor is ensured by balancing descriptor. We illustrate the performance of our segmentation algorithm using some challenging textured images.

Fast Unsupervised Segmentation Using Active Contours and Belief Functions

In this paper, we study Active Contours AC based globally segmentation for vector valued images using evidential Kullback-Leibler KL distance. We investigate the evidential framework to fuse multiple features issued from vector-valued images. This formulation has two main advantages: 1 by the combination of foreground/background issued from the multiple channels in the same framework. 2 the incorporation of the heterogeneous knowledge and the reduction of the imprecision due to the noise. The statistical relation between the image channels is ensured by the Dempster-Shafer rule. We illustrate the performance of our segmentation algorithm using some challenging color and textured images.

Binary Active Contours using both inside and outside texture descriptors

In this paper, we propose a new framework for Binary Active Contours (AC) that incorporates a new texture descriptor. The texture descriptor is split into inside/ outside region descriptors. Both the inside and outside texture descriptors discriminate the texture using Kullback-Leibler distance. Using these two descriptors, the AC incorporates both learned textures. This formulation has two main advantages. Firstly, by discriminating independently the foreground/background textures. Secondly, by incorporating both the learned inside/outside texture. Our segmentation model based AC model is formulated in Total variation framework using characteristic function framework. We propose a fast Bregman split implementation of our segmentation algorithm based on the primal-dual formulation. Finally, we show results on some challenging images to illustrate texture segmentations that are possible.

Segmentation of prostate using interactive finsler active contours and shape prior

We present a new interactive segmentation framework to segment the prostate from MR prostate imagery. We first explicitly address the segmentation problem based on fast globally Finsler Active Contours (FAC) by incorporating both statistical and geometric shape prior knowledge. In doing so, we are able to exploit the more global aspects of segmentation by incorporating user feedback in segmentation process. In addition, once the prostate shape has been segmented, a cost functional is designed to incorporate both the local image statistics as user feedback and the learned shape prior. We provide experimental results, which include several challenging clinical data sets, to highlight the algorithms capability of robustly handling supine/prone prostate segmentation task.