Oldrich Vysata

Symptoms and signs of posterior circulation ischemia in the new England medical center posterior circulation registry.

OBJECTIVE To evaluate the frequencies of symptoms and signs in patients with posterior circulation ischemia in a large case series of prospectively collected patients. DESIGN Case series. SETTING Outpatient and inpatient setting at the New England Medical Center, a tertiary care referral center in Boston, Massachusetts. PATIENTS Consecutive sample of 407 adult patients who had stroke and/or transient ischemic attacks in the posterior circulation within 6 months of study inclusion. All patients were examined by senior stroke neurologists. All patients had either computed tomography or magnetic resonance imaging of the brain as well as vascular imaging of the head and neck. The study included 256 men (63%) and 151 women (37%). MAIN OUTCOME MEASURES Frequencies of posterior circulation ischemic symptoms and signs. These outcome measures were planned before data collection began. Correlations between symptoms and signs with separate vascular territories of the posterior circulation were then analyzed. RESULTS The most frequent posterior circulation symptoms were dizziness (47%), unilateral limb weakness (41%), dysarthria (31%), headache (28%), and nausea or vomiting (27%). The most frequent signs were unilateral limb weakness (38%), gait ataxia (31%), unilateral limb ataxia (30%), dysarthria (28%), and nystagmus (24%). Logistic regression analysis reveals that the clinical features dysphagia (P = .004; 95% CI, 1.8-24.4), nausea or vomiting (P = .002; 95% CI, 1.6-8.2), dizziness (P = .047; 95% CI, 1.0-5.4), and Horner syndrome (P = .001; 95% CI, 2.4-26.6) were positively correlated with the proximal vascular territory. Unilateral limb weakness (P = .001; 95% CI, 1.7-8.7) and cranial nerve VII deficits (P = .02; 95% CI, 1.1-5.3) were positively correlated with the middle territory. Limb sensory deficit (P = .001; 95% CI, 1.8-7.8), lethargy (P = .001; 95% CI, 2.3-12.4), and visual field loss (P = .001; 95% CI, 5.3-23.9) were positively correlated with the distal territory. CONCLUSIONS We report the most frequent symptoms and signs in the largest published registry, the New England Medical Center Posterior Circulation Registry, of patients with posterior circulation ischemia who had complete neurological examinations and extensive cerebrovascular imaging. Knowledge of the vascular territory involved aids in the diagnosis of the causative vascular lesion and stroke mechanism.

Wavelet transform use for feature extraction and EEG signal segments classification

Segmentation, feature extraction and classification of signal components belong to very common problems in various engineering, economical and biomedical applications. The paper is devoted to the use of discrete wavelet transform (DWT) both for signal preprocessing and signal segments feature extraction as an alternative to the commonly used discrete Fourier transform (DFT). Feature vectors belonging to separate signal segments are then classified by a competitive neural network as one of methods of cluster analysis and processing. The paper provides a comparison of classification results using different methods of feature extraction most appropriate for EEG signal components detection. Problems of multichannel segmentation are mentioned in this connection as well.

Multi-Dimensional Biomedical Image De-Noising using Haar Transform

Image de-noising and enhancement form two fundamental problems in many engineering and biomedical applications. The paper is devoted to the study of the multi-resolution approach to this topic employing the Haar wavelet transform and its application to processing of volumetric magnetic resonance image sets corrupted with additional noise. The resulting coefficients are thresholded and exploited for subsequent reconstruction. The Haar transform is evaluated using both the two-dimensional approach applied individually to each image layer, and the three-dimensional technique performed on the image volume as a whole. In noise reduction, the latter approach profits from similarities between the neighbouring image layers and shows a considerable improvement over the former method. Results are presented in numerical and graphical forms using three-dimensional visualization tools.

The MS kinect image and depth sensors use for gait features detection

Movement disorders, problems with motion and gait stability related to aging form a very intensively studied research area. The paper presents a contribution to these topics through the use of data acquired by motion sensors and namely image and depth sensors of the MS Kinect. While video sequences obtained by complex camera systems can be used for the precise gait features evaluation, it is possible to use much cheaper devices for diagnostic purposes accurate enough in many cases. The experimental part of the study presents video sequences and depth sensors data acquisition for 18 individuals with the Parkinsons disease and 18 healthy age-matched controls using the proposed graphical user interface in the clinical environment. Results presented include the estimation of gait features to distinguish gait disorders and to classify individuals in the early stage of possible serious diseases. The accuracy achieved was higher then 90 % for given sets of individuals.

Wavelet use for reduction of watershed transform over-segmentation in biomedical images processing

Problems of multi-dimensional signal enhancement, segmentation, feature extraction and components classification is essential in many engineering and biomedical applications. The paper is devoted to the use of watershed transform and wavelet transform for MR image components detection and discussion of over-segmentation problems. The goal of the paper is in (i) analysis of image de-noising, (ii) discussion of image enhancement, and (iii) multi-resolutional approach application for reduction of over-segmentation problems. Proposed algorithms include the use of wavelet transform and gradient methods in the preprocessing stage and application of the watershed transform for enhanced images. Resulting algorithms are verified for simulated images and applied for a selected MR biomedical images containing different structures.

Challenges and trends in Ambient Assisted Living and intelligent tools for disabled and elderly people

In this review article, we present some challenges and opportunities in Ambient Assisted Living (AAL) for disabled and elderly people addressing various state of the art and recent approaches particularly in artificial intelligence, biomedical engineering, and body sensor networking.

Linear and Nonlinear EEG Synchronization in Alzheimer’s Disease

As is known, Alzheimer’s disease (AD) is associated with cognitive deficits due to significant neuronal loss. Reduced connectivity might be manifested as changes in the synchronization of electrical activity of collaborating parts of the brain. We used wavelet coherence to estimate linear/nonlinear synchronization between EEG samples recorded from different leads. Mutual information was applied to the complex wavelet coefficients in wavelet scales to estimate nonlinear synchronization. Synchronization rates for a group of 110 patients with moderate AD (MMSE score 10 to 19) and a group of 110 healthy control subjects were compared. The most significant decrease in mutual information in AD patients was observed on the third scale in the fronto-temporal area and for wavelet coherence within the same areas as for mutual information; these areas are preferentially affected by atrophy in AD. The new method used utilizes mutual information in wavelet scales and demonstrates larger discriminatory values in AD compared to wavelet coherence.

Physiological and GPS data fusion

The paper deals with fusion of physiological and GPS data acquired during cycling and their analysis using general methods of multichannel signal processing. Experimental data were acquired during 17 identical cycling routes each about 12 km long including more then 1100 segments of the length 60 s recorded with the varying sampling period. The proposed algorithm includes their initial analysis, de-nosing using selected digital filters, interpolation and resampling in the first stage followed by evaluation of the cross-correlation between the heart rate and the altitude gradient of positioning data recorded by the GPS system. Results obtained present (i) relation between the heart rate and the slope with the positive regression coefficient 6.04 and (ii) the heart rate and speed with the negative regression coefficient -1.67 over all segments analyzed.

Functional transforms in MR image segmentation

Image segmentation, feature extraction and image components classification form a fundamental problem in many applications of multi-dimensional signal processing. The paper is devoted to the use of watershed transform for image segmentation in connection with wavelet transform allowing image de-noising and image components feature extraction. Proposed methods are applied for biomedical image analysis and processing. The study of MR image segmentation devoted to the detection of its specific components results in the proposal of the appropriate image preprocessing to reduce problems of its oversegmentation. Resulting algorithms include the use of wavelet transform and gradient methods in the preprocessing stage. Proposed algorithms are verified for simulated images and applied for a selected MR biomedical images containing different structures.

Breathing Analysis Using Thermal and Depth Imaging Camera Video Records

The paper is devoted to the study of facial region temperature changes using a simple thermal imaging camera and to the comparison of their time evolution with the pectoral area motion recorded by the MS Kinect depth sensor. The goal of this research is to propose the use of video records as alternative diagnostics of breathing disorders allowing their analysis in the home environment as well. The methods proposed include (i) specific image processing algorithms for detecting facial parts with periodic temperature changes; (ii) computational intelligence tools for analysing the associated videosequences; and (iii) digital filters and spectral estimation tools for processing the depth matrices. Machine learning applied to thermal imaging camera calibration allowed the recognition of its digital information with an accuracy close to 100% for the classification of individual temperature values. The proposed detection of breathing features was used for monitoring of physical activities by the home exercise bike. The results include a decrease of breathing temperature and its frequency after a load, with mean values −0.16 °C/min and −0.72 bpm respectively, for the given set of experiments. The proposed methods verify that thermal and depth cameras can be used as additional tools for multimodal detection of breathing patterns.