Mohamed I. Owis

Study of features based on nonlinear dynamical modeling in ECG arrhythmia detection and classification

We present a study of the nonlinear dynamics of electrocardiogram (ECG) signals for arrhythmia characterization. The correlation dimension and largest Lyapunov exponent are used to model the chaotic nature of five different classes of ECG signals. The model parameters are evaluated for a large number of real ECG signals within each class and the results are reported. The presented algorithms allow automatic calculation of the features. The statistical analysis of the calculated features indicates that they differ significantly between normal heart rhythm and the different arrhythmia types and, hence, can be rather useful in ECG arrhythmia detection. On the other hand, the results indicate that the discrimination between different arrhythmia types is difficult using such features. The results of this work are supported by statistical analysis that provides a clear outline for the potential uses and limitations of these features.

Characterisation of electrocardiogram signals based on blind source separation

Blind source separation assumes that the acquired signal is composed of a weighted sum of a number of basic components corresponding to a number of limited sources. This work poses the problem of ECG signal diagnosis in the form of a blind source separation problem. In particular, a large number of ECG signals undergo two of the most commonly used blind source separation techniques, namely, principal component analysis (PCA) and independent component analysis (ICA), so that the basic components underlying this complex signal can be identified. Given that such techniques are sensitive to signal shift, a simple transformation is used that computes the magnitude of the Fourier transformation of ECG signals. This allows the phase components corresponding to such shifts to be removed. Using the magnitude of the projection of a given ECG signal onto these basic components as features, it was shown that accurate arrhythmia detection and classification were possible. The proposed strategies were applied to a large number of independent 3s intervals of ECG signals consisting of 320 training samples and 160 test samples from the MIT-BIH database. The samples equally represent five different ECG signal types, including normal, ventricular couplet, ventricular tachycardia, ventricular bigeminy and ventricular fibrillation. The intervals analysed were windowed using either a rectangular or a Hamming window. The methods demonstrated a detection rate of sensitivity 98% at specificity of 100% using nearest neighbour classification of features from ICA and a rectangular window. Lower classification rates were obtained using the same classifier with features from either PCA or ICA and a rectangular window. The results demonstrate the potential of the new method for clinical use.

A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines

A method for arrhythmia classification based on spectral correlation is proposed.Statistical features for the spectral correlation coefficients were calculated.Features were subjected to principal component analysis and fisher score.Raw spectral correlation data, PCA data and FS data were classified using SVM.The best performance is achieved using raw spectral correlation data. Cardiac disorders are one of the main causes leading to death. Therefore, they require continuous and efficient detection techniques. ECG is one of the main tools to diagnose cardiovascular disorders such as arrhythmias. Computer aided diagnosis (CAD) systems play a very important role in early detection and diagnosis of cardiac arrhythmias. In this work, we propose a CAD system for classifying five beat types including: normal (N), Premature Ventricular Contraction (PVC), Premature Atrial Contraction (APC), Left Bundle Branch Block (LBBB) and Right Bundle Branch Block (RBBB). The proposed system is based on cyclostationary signal analysis approach, which explores hidden periodicities in the signal of interest and thus it is able to detect hidden features. In order to study the cyclostationarity properties of the signal, we utilized the spectral correlation as a nonlinear statistical transformation inspecting the periodicity of the correlation. Three experiments were investigated in our study; raw spectral correlation data were used in the first experiment while the other two experiments utilized statistical features for the raw spectral data followed by principal component analysis (PCA) and fisher score for feature space reduction purposes respectively. As for the classification task, support vector machine (SVM) with linear kernel was employed for all experiments. The experimental results showed that the approach that uses the raw spectral correlation data is superior compared to several state of the art methods. This approach achieved sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 99.20%, 99.70%, 98.60%, 99.90% and 97.60% respectively.

Robust feature extraction from ECG signals based on nonlinear dynamical modeling

The early detection of abnormal heart conditions is vital for intensive care unit patients. The detection of such conditions is possible through continuous monitoring of electrocardiographic (ECG) signals to detect the presence of arrhythmia. Conventional methods of arrhythmia detection rely on observing morphological features of the signal in the time domain or after applying a certain transformation. Even though these techniques have been fairly successful in detecting such conditions, they are limited by the fact that they treat the heart as a linear system. In this paper, we present a comprehensive study of the nonlinear dynamics of ECG signals. The correlation dimension and largest Lyapunov exponent are used to model the chaotic nature of five different classes of ECG signals. The model parameters are evaluated for a large number of real ECG signals within each class and the results are reported. The proposed algorithms allow automatic calculation of the features. The statistical analysis of the calculated features indicates that they differ significantly among different arrhythmia types and hence can be rather useful in ECG signal classification. The results of this work show the potential of such features for use in arrhythmia detection in clinical cardiac monitoring.

GPU acceleration for digitally reconstructed radiographs using bindless texture objects and CUDA/OpenGL interoperability.

This paper features an advanced implementation of the X-ray rendering algorithm that harnesses the giant computing power of the current commodity graphics processors to accelerate the generation of high resolution digitally reconstructed radiographs (DRRs). The presented pipeline exploits the latest features of NVIDIA Graphics Processing Unit (GPU) architectures, mainly bindless texture objects and dynamic parallelism. The rendering throughput is substantially improved by exploiting the interoperability mechanisms between CUDA and OpenGL. The benchmarks of our optimized rendering pipeline reflect its capability of generating DRRs with resolutions of 20482 and 40962 at interactive and semi interactive frame-rates using an NVIDIA GeForce 970 GTX device.

Accelerating DRR generation using Fourier slice theorem on the GPU.

Digitally Reconstructed Radiographs (DRRs) play a vital role in medical imaging procedures and radiotherapy applications. They allow the continuous monitoring of patient positioning during image guided therapies using multi-dimensional image registration. Conventional generation of DRRs using spatial domain algorithms such as ray casting is associated with computational complexity of O(N3). Fourier slice theorem is an alternative approach for generating the DRRs in the k-space with reduced time complexity. In this work, we present a high performance, scalable, and optimized DRR generation pipeline on the Graphics Processing Unit (GPU). The strong scaling performance of the presented pipeline is investigated and demonstrated using two contemporary GPUs. Our pipeline is capable of generating DRRs for 5123 volumes in less than a milli-second.

Parallel generation of digitally reconstructed radiographs on heterogeneous multi-GPU workstations

The growing importance of three-dimensional radiotherapy treatment has been associated with the active presence of advanced computational workflows that can simulate conventional x-ray films from computed tomography (CT) volumetric data to create digitally reconstructed radiographs (DRR). These simulated x-ray images are used to continuously verify the patient alignment in image-guided therapies with 2D-3D image registration. The present DRR rendering pipelines are quite limited to handle huge imaging stacks generated by recent state-of-the-art CT imaging modalities. We present a high performance x-ray rendering pipeline that is capable of generating high quality DRRs from large scale CT volumes. The pipeline is designed to harness the immense computing power of all the heterogeneous computing platforms that are connected to the system relying on OpenCL. Load-balancing optimization is also addressed to equalize the rendering load across the entire system. The performance benchmarks demonstrate the capability of our pipeline to generate high quality DRRs from relatively large CT volumes at interactive frame rates using cost-effective multi-GPU workstations. A 5122 DRR frame can be rendered from 1024 × 2048 × 2048 CT volumes at 85 frames per second.

Patient adaptable ventricular arrhythmia classifier using template matching

In this paper we propose a real-time method for discrimination of ventricular ectopic and normal beats in the electrocardiogram (ECG). The heartbeat waveforms were evaluated within a fixed-length window around the fiducial points (100 ms before, 100 ms after) after being normalized. Our algorithm was designed to operate with no expert assistance; the operator is not required to initially select any known beat templates which makes it applicable in real-time. It is based on the dominancy of normal beats during the first several seconds for most of records which mostly match the real cases. In addition to R-R intervals, we extract other features as beat width, P wave existence for each beat. Also we apply template matching between the learned template and the unknown beat where template beats are created for each beat shape on runtime. Template matching not only classifies normal dominant beat but also multi-form ventricular ectopic beats where each form is classified separately so as doctors and medical stuff could take the better decision. Our proposed algorithm was tested on MIT-BIH ECG database records with normal and ventricular ectopic beat classes defined in AAMI standard while other records are excluded. Our results show 97.24% overall accuracy with 98.93% and 94.54% sensitivities for normal and ventricular ectopic beats respectively.

Novel Bayesian classifier discriminant function optimization strategies for arrhythmia classification

Cardiac arrhythmia is considered to be one of the most critical addressed problems leading to death. Thus, Computer Aided Diagnosis (CAD) systems are essential for early arrhythmia detection and diagnosis. In this paper, we propose a classification system for arrhythmia diagnosis based on Bayesian classifier. The system employs one-versus-one approach, used in the classification methodology of several multi-class classifiers such as the support Vector Machine (SVM). The proposed idea is mainly based on introducing new algorithms for optimizing the classifiers parameters in order to improve the overall classification system performance, using the Space Search (SS) and the One-versus-One Error Minimization (OOEM) approaches. The SS approach boosted system accuracy over the conventional Bayes (CB) by 1.14%, 2.5% and 3.33% for 3, 5 and 6-classes arrhythmia problems respectively while OOEM showed less superiority than SS as it boosted accuracy by 0.7% and 2.44% for the 5 and 6-classes problems respectively and attained same accuracy achieved by CB for the 3-class problem. The learning and testing times were calculated for both approaches. The results show that the SS based system offers the best possible accuracy, however it has the longest learning time.

Retrospective screening of microarray data to identify candidate IFN-inducible genes in a HTLV-1 transformed model

HuT-102 cells are considered one of the most representable human T-lymphotropic virus 1 (HTLV-1)-infected cell lines for studying adult T-cell lymphoma (ATL). In our previous studies, genome-wide screening was performed using the GeneChip system with Human Genome Array U133 Plus 2.0 for transforming growth factor-β-activated kinase 1 (TAK1)-, interferon regulatory factor 3 (IRF3)- and IRF4-regulated genes to demonstrate the effects of interferon-inducible genes in HuT-102 cells. Our previous findings demonstrated that TAK1 induced interferon inducible genes via an IRF3-dependent pathway and that IRF4 has a counteracting effect. As our previous data was performed by manual selection of common interferon-related genes mentioned in the literature, there has been some obscure genes that have not been considered. In an attempt to maximize the outcome of those microarrays, the present study reanalyzed the data collected in previous studies through a set of computational rules implemented using ‘R’ software, to identify important candidate genes that have been missed in the previous two studies. The final list obtained consisted of ten genes that are highly recommend as potential candidate for therapies targeting the HTLV-1 infected cancer cells. Those genes are ATM, CFTR, MUC4, PARP14, QK1, UBR2, CLEC7A (Dectin-1), L3MBTL, SEC24D and TMEM140. Notably, PARP14 has gained increased attention as a promising target in cancer cells.