Kuang Chua

Automated Diagnosis of Glaucoma Using Texture and Higher Order Spectra Features

Glaucoma is the second leading cause of blindness worldwide. It is a disease in which fluid pressure in the eye increases continuously, damaging the optic nerve and causing vision loss. Computational decision support systems for the early detection of glaucoma can help prevent this complication. The retinal optic nerve fiber layer can be assessed using optical coherence tomography, scanning laser polarimetry, and Heidelberg retina tomography scanning methods. In this paper, we present a novel method for glaucoma detection using a combination of texture and higher order spectra (HOS) features from digital fundus images. Support vector machine, sequential minimal optimization, naive Bayesian, and random-forest classifiers are used to perform supervised classification. Our results demonstrate that the texture and HOS features after z-score normalization and feature selection, and when combined with a random-forest classifier, performs better than the other classifiers and correctly identifies the glaucoma images with an accuracy of more than 91%. The impact of feature ranking and normalization is also studied to improve results. Our proposed novel features are clinically significant and can be used to detect glaucoma accurately.

Computer-aided diagnosis of diabetic retinopathy: A review

Diabetes mellitus may cause alterations in the retinal microvasculature leading to diabetic retinopathy. Unchecked, advanced diabetic retinopathy may lead to blindness. It can be tedious and time consuming to decipher subtle morphological changes in optic disk, microaneurysms, hemorrhage, blood vessels, macula, and exudates through manual inspection of fundus images. A computer aided diagnosis system can significantly reduce the burden on the ophthalmologists and may alleviate the inter and intra observer variability. This review discusses the available methods of various retinal feature extractions and automated analysis.

APPLICATION OF EMPIRICAL MODE DECOMPOSITION (EMD) FOR AUTOMATED DETECTION OF EPILEPSY USING EEG SIGNALS

Epilepsy is a global disease with considerable incidence due to recurrent unprovoked seizures. These seizures can be noninvasively diagnosed using electroencephalogram (EEG), a measure of neuronal electrical activity in brain recorded along scalp. EEG is highly nonlinear, nonstationary and non-Gaussian in nature. Nonlinear adaptive models such as empirical mode decomposition (EMD) provide intuitive understanding of information present in these signals. In this study a novel methodology is proposed to automatically classify EEG of normal, inter-ictal and ictal subjects using EMD decomposition. EEG decomposition using EMD yields few intrinsic mode functions (IMF), which are amplitude and frequency modulated (AM and FM) waves. Hilbert transform of these IMF provides AM and FM frequencies. Features such as spectral peaks, spectral entropy and spectral energy in each IMF are extracted and fed to decision tree classifier for automated diagnosis. In this work, we have compared the performance of classification using two types of decision trees (i) classification and regression tree (CART) and (ii) C4.5. We have obtained the highest average accuracy of 95.33%, average sensitivity of 98%, and average specificity of 97% using C4.5 decision tree classifier. The developed methodology is ready for clinical validation on large databases and can be deployed for mass screening.

Application of Higher Order Spectra for the Identification of Diabetes Retinopathy Stages

Diabetic retinopathy (DR) is a condition where the retina is damaged due to fluid leaking from the blood vessels into the retina. In extreme cases, the patient will become blind. Therefore, early detection of diabetic retinopathy is crucial to prevent blindness. Various image processing techniques have been used to identify the different stages of diabetes retinopathy. The application of non-linear features of the higher-order spectra (HOS) was found to be efficient as it is more suitable for the detection of shapes. The aim of this work is to automatically identify the normal, mild DR, moderate DR, severe DR and prolific DR. The parameters are extracted from the raw images using the HOS techniques and fed to the support vector machine (SVM) classifier. This paper presents classification of five kinds of eye classes using SVM classifier. Our protocol uses, 300 subjects consisting of five different kinds of eye disease conditions. We demonstrate a sensitivity of 82% for the classifier with the specificity of 88%.

Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach

Human eye is one of the most sophisticated organ, with retina, pupil, iris cornea, lens and optic nerve. Automatic retinal image analysis is emerging as an important screening tool for early detection of eye diseases. Uncontrolled diabetes retinopathy (DR) and glaucoma may lead to blindness. DR is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of DR are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources used for mass screening of DR. We present an automatic screening system for the detection of normal and DR stages (NPDR and PDR). The proposed systems involves processing of fundus images for extraction of abnormal signs, such as area of hard exudates, area of blood vessels, bifurcation points, texture and entropies. Our protocol uses total of 156 subjects consisting of two stages of DR and normal. In this work, we have fed thirteen statistically significant (p<0.0001) features for Probabilistic Neural Network (PNN), Decision Tree (DT) C4.5, and Support Vector Machine (SVM) to select the best classifier. The best model parameter (@s) for which the PNN classifier performed best was identified using global optimization techniques such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). We demonstrated an average classification accuracy of 96.15%, sensitivity of 96.27% and specificity of 96.08% for @s=0.0104 using threefold cross validation using PNN classifier. The computer-aided diagnosis (CAD) results were validated by comparing with expert ophthalmologists. The proposed automated system can aid clinicians to make a faster DR diagnosis during the mass screening of normal/DR images.

AUTOMATIC IDENTIFICATION OF EPILEPTIC EEG SIGNALS USING NONLINEAR PARAMETERS

Epilepsy is a brain disorder causing people to have recurring seizures. Electroencephalogram (EEG) is the electrical activity of the brain signals that can be used to diagnose the epilepsy. The EEG signal is highly nonlinear and nonstationary in nature and may contain indicators of current disease, or warnings about impending diseases. The chaotic measures like correlation dimension (CD), Hurst exponent (H), and approximate entropy (ApEn) can be used to characterize the signal. These features extracted can be used for automatic diagnosis of seizure onsets which would help the patients to take appropriate precautions. These nonlinear features have been reported to be a promising approach to differentiate among normal, pre-ictal (background), and epileptic EEG signals. In this work, these features were used to train both Gaussian mixture model (GMM) and support vector machine (SVM) classifiers. The performance of the two classifiers were evaluated using the receiver operating characteristics (ROC) curves. Our results show that the GMM classifier performed better with average classification efficiency of 95%, sensitivity and specificity of 92.22% and 100%, respectively.

APPLICATION OF INTRINSIC TIME-SCALE DECOMPOSITION (ITD) TO EEG SIGNALS FOR AUTOMATED SEIZURE PREDICTION

Intrinsic time-scale decomposition (ITD) is a new nonlinear method of time-frequency representation which can decipher the minute changes in the nonlinear EEG signals. In this work, we have automatically classified normal, interictal and ictal EEG signals using the features derived from the ITD representation. The energy, fractal dimension and sample entropy features computed on ITD representation coupled with decision tree classifier has yielded an average classification accuracy of 95.67%, sensitivity and specificity of 99% and 99.5%, respectively using 10-fold cross validation scheme. With application of the nonlinear ITD representation, along with conceptual advancement and improvement of the accuracy, the developed system is clinically ready for mass screening in resource constrained and emerging economy scenarios.

Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network

Coronary artery disease (CAD) is caused due by the blockage of inner walls of coronary arteries by plaque. This constriction reduces the blood flow to the heart muscles resulting in myocardial infarction (MI). The electrocardiogram (ECG) is commonly used to screen the cardiac health. The ECG signals are nonstationary and nonlinear in nature whereby the transient disease indicators may appear randomly on the time scale. Therefore, the procedure to diagnose the abnormal beat is arduous, time consuming and prone to human errors. The automated diagnosis system overcomes these problems. In this study, convolutional neural network (CNN) structures comprising of four convolutional layers, four max pooling layers and three fully connected layers are proposed for the diagnosis of CAD using two and five seconds durations of ECG signal segments. Deep CNN is able to differentiate between normal and abnormal ECG with an accuracy of 94.95%, sensitivity of 93.72%, and specificity of 95.18% for Net 1 (two seconds) and accuracy of 95.11%, sensitivity of 91.13% and specificity of 95.88% for Net 2 (5 s). The proposed system can help the clinicians in their accurate and reliable decision making of CAD using ECG signals.

Automated detection and localization of myocardial infarction using electrocardiogram

Identification and timely interpretation of changes occurring in the 12 electrocardiogram (ECG) leads is crucial to identify the types of myocardial infarction (MI). However, manual annotation of this complex nonlinear ECG signal is not only cumbersome and time consuming but also inaccurate. Hence, there is a need of computer aided techniques to be applied for the ECG signal analysis process. Going further, there is a need for incorporating this computerized software into the ECG equipment, so as to enable automated detection of MIs in clinics. Therefore, this paper proposes a novel method of automated detection and localization of MI by using ECG signal analysis. In our study, a total of 200 twelve lead ECG subjects (52 normal and 148 with MI) involving 611,405 beats (125,652 normal beats and 485,753 beats of MI ECG) are segmented from the 12 lead ECG signals. Firstly, ECG signal obtained from 12 ECG leads are subjected to discrete wavelet transform (DWT) up to four levels of decomposition. Then, 12 nonlinear features namely, approximate entropy ( E a x ), signal energy (?x), fuzzy entropy ( E f x ), Kolmogorov-Sinai entropy ( E k s x ), permutation entropy ( E p x ), Renyi entropy ( E r x ), Shannon entropy ( E s h x ), Tsallis entropy ( E t s x ), wavelet entropy ( E w x ), fractal dimension ( F D x ), Kolmogorov complexity ( C k x ), and largest Lyapunov exponent ( E L L E x ) are extracted from these DWT coefficients. The extracted features are then ranked based on the t value. Then these features are fed into the k-nearest neighbor (KNN) classifier one by one to get the highest classification performance by using minimum number of features. Our proposed method has achieved the highest average accuracy of 98.80%, sensitivity of 99.45% and specificity of 96.27% in classifying normal and MI ECG (two classes), by using 47 features obtained from lead 11 (V5). We have also obtained the highest average accuracy of 98.74%, sensitivity of 99.55% and specificity of 99.16% in differentiating the 10 types of MI and normal ECG beats (11 class), by using 25 features obtained from lead 9 (V3). In addition, our study results achieved an accuracy of 99.97% in locating inferior posterior infarction by using only lead 9 (V3) ECG signal. Our proposed method can be used as an automated diagnostic tool for (i) the detection of different (10 types of) MI by using 12 lead ECG signal, and also (ii) to locate the MI by analyzing only one lead without the need to analyze other leads. Thus, our proposed algorithm and computerized system software (incorporated into the ECG equipment) can aid the physicians and clinicians in accurate and faster location of MIs, and thereby providing adequate time available for the requisite treatment decision.

Application of higher order statistics for atrial arrhythmia classification

Abstract Atrial fibrillation (AF) and atrial flutter (AFL) are the two common atrial arrhythmia encountered in the clinical practice. In order to diagnose these abnormalities the electrocardiogram (ECG) is widely used. The conventional linear time and frequency domain methods cannot decipher the hidden complexity present in these signals. The ECG is inherently a non-linear, non-stationary and non-Gaussian signal. The non-linear models can provide improved results and capture minute variations present in the time series. Higher order spectra (HOS) is a non-linear dynamical method which is highly rugged to noise. In the present study, the performances of two methods are compared: (i) 3rd order HOS cumulants and (ii) HOS bispectrum. The 3rd order cumulant and bispectrum coefficients are subjected to dimensionality reduction using independent component analysis (ICA) and classified using classification and regression tree (CART), random forest (RF), artificial neural network (ANN) and k -nearest neighbor (KNN) classifiers to select the best classifier. The ICA components of cumulant coefficients have provided the average accuracy, sensitivity, specificity and positive predictive value of 99.50%, 100%, 99.22% and 99.72% respectively using KNN classifier. Similarly, the ICA components of HOS bispectrum coefficients have yielded the average accuracy, sensitivity, specificity and PPV of 97.65%, 98.16%, 98.75% and 99.53% respectively using KNN. So, the ICA performed on the 3rd order HOS cumulants coupled with KNN classifier performed better than the HOS bispectrum method. The proposed methodology is robust and can be used in mass screening of cardiac patients.