Aleš Procházka

Signal Analysis and Prediction

This book surveys the latest information concerning methods of time-frequency and time-scale signal analysis, higher order statistics in signal processing, selected methods of signal identification, nonlinear modeling by neural networks, fuzzy-rule based systems, and methods of signal prediction and noise rejection. Many chapters include Matlab examples and visualizations.

Possibility of reconstruction of dental plaster cast from 3D digital study models

ObjectivesTo compare traditional plaster casts, digital models and 3D printed copies of dental plaster casts based on various criteria. To determine whether 3D printed copies obtained using open source system RepRap can replace traditional plaster casts in dental practice. To compare and contrast the qualities of two possible 3D printing options – open source system RepRap and commercially available 3D printing.Design and settingsA method comparison study on 10 dental plaster casts from the Orthodontic department, Department of Stomatology, 2nd medical Faulty, Charles University Prague, Czech Republic.Material and methodsEach of 10 plaster casts were scanned by inEos Blue scanner and the printed on 3D printer RepRap [10 models] and ProJet HD3000 3D printer [1 model]. Linear measurements between selected points on the dental arches of upper and lower jaws on plaster casts and its 3D copy were recorded and statistically analyzed.Results3D printed copies have many advantages over traditional plaster casts. The precision and accuracy of the RepRap 3D printed copies of plaster casts were confirmed based on the statistical analysis. Although the commercially available 3D printing enables to print more details than the RepRap system, it is expensive and for the purpose of clinical use can be replaced by the cheaper prints obtained from RepRap printed copies.ConclusionsScanning of the traditional plaster casts to obtain a digital model offers a pragmatic approach. The scans can subsequently be used as a template to print the plaster casts as required. Using 3D printers can replace traditional plaster casts primarily due to their accuracy and price.

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.

Microsoft Kinect Visual and Depth Sensors for Breathing and Heart Rate Analysis

This paper is devoted to a new method of using Microsoft (MS) Kinect sensors for non-contact monitoring of breathing and heart rate estimation to detect possible medical and neurological disorders. Video sequences of facial features and thorax movements are recorded by MS Kinect image, depth and infrared sensors to enable their time analysis in selected regions of interest. The proposed methodology includes the use of computational methods and functional transforms for data selection, as well as their denoising, spectral analysis and visualization, in order to determine specific biomedical features. The results that were obtained verify the correspondence between the evaluation of the breathing frequency that was obtained from the image and infrared data of the mouth area and from the thorax movement that was recorded by the depth sensor. Spectral analysis of the time evolution of the mouth area video frames was also used for heart rate estimation. Results estimated from the image and infrared data of the mouth area were compared with those obtained by contact measurements by Garmin sensors (www.garmin.com). The study proves that simple image and depth sensors can be used to efficiently record biomedical multidimensional data with sufficient accuracy to detect selected biomedical features using specific methods of computational intelligence. The achieved accuracy for non-contact detection of breathing rate was 0.26% and the accuracy of heart rate estimation was 1.47% for the infrared sensor. The following results show how video frames with depth data can be used to differentiate different kinds of breathing. The proposed method enables us to obtain and analyse data for diagnostic purposes in the home environment or during physical activities, enabling efficient human–machine interaction.

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.

Towards an inclusive Parkinson's screening system

In this study, brain, and gait dynamic information were combined and used for diagnosis and monitoring of Parkinsons disease (the most important Neurodegenerative Disorder). Analysis of the information corresponding to a prescribed movement involving tremor, and the related changes in brain connectivity is novel and original. Analytically, developing a space-time nonlinear adaptive system which fuses brain and gait information algorithmically is proposed here for the first time. The overall dynamic system will be constrained by the clinical impressions of the patient symptoms embedded in a knowledge-based system. The entire complex constrained problem were solved to enable a powerful model for recognition and monitoring of Parkinsons disease and establishing appropriate rules for its clinical following up.

Change in the Characteristics of EEG Color Noise in Alzheimer’s Disease

Neurophysiological experiments support the hypothesis of the presence of critical dynamics of brain activity. This is also manifested by power law of electroencephalography (EEG) power spectra, which can be described by the relation 1/fα. This dependence is a result of internal interactions between parts of the brain and is probably required for optimal processing of information. In Alzheimer’s disease, changes in the functional organization of the brain occur, which may be manifested by changes in the α coefficient. We compared the average values of α for 19 electrodes in the resting EEG record in 110 patients with moderate to severe Alzheimer’s disease (Mini-Mental State Examination [MMSE] score = 10-19) with 110 healthy controls. Statistically, the most significant differences are present in the prefrontal areas. In addition to the prefrontal and frontal areas, the largest separation value in the evaluation of receiver operating characteristic (ROC) curves was recorded in the temporal area. The coefficient alpha has few false-positive results in the optimal operating point of the ROC curve, and is thereby highly specific for Alzheimer’s disease.

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 transform in image recognition

Texture segmentation and classification form a very important topic of the interdisciplinarg area of signal processing with many applications in diflerent areas including satellite image processing, biomedical image analysis and microscopic image processing. The paper presents selected mathematical methods used for image segmentation and the following segments classification using multiresolution decomposition of segments boundary szgnals. The wavelet transform has been applied here for feature extraction and image de-noising. Results of feature extraction obtained by the discrete wavelet transform are compared with that evaluated by the discrete Fourier transform. For the following feature classification the self-organizing neural networks are applied. Proposed methods have been verified for simulated structures and then used for analysis of microscopic images of crystals of diflerent shapes and sizes.

Biomedical Image Volumes Denoising via the Wavelet Transform

Image denoising represents a crucial initial step in biomedical image processing and analysis. Denoising belongs to the family of image enhancement methods (Bovik, 2009) which comprise also blur reduction, resolution enhancement, artefacts suppression, and edge enhancement. The motivation for enhancing the biomedical image quality is twofold. First, improving the visual quality may yield more accurate medical diagnostics, and second, analytical methods, such as segmentation and content recognition, require image preprocessing on the input. Gradually, noise reduction methods developed in other research fields find their usage in biomedical applications. However, biomedical images, such as images obtained from computed tomography (CT) scanners, are quite specific. Modelling noise based on the first principles of image acquisition and transmission is a too complex task (Borsdorf et al., 2009), and moreover, the noise component characteristics depend on the measurement conditions (Bovik, 2009). Additionally, noise reduction must be carried out with extreme care to avoid suppression of the important image content. For this reason, the results of biomedical image denoising should be consulted with medical experts.