Vidya K. Sudarshan

A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals.

Depression is a mental disorder characterized by persistent occurrences of lower mood states in the affected person. The electroencephalogram (EEG) signals are highly complex, nonlinear, and nonstationary in nature. The characteristics of the signal vary with the age and mental state of the subject. The signs of abnormality may be invisible to the naked eyes. Even when they are visible, deciphering the minute changes indicating abnormality is tedious and time consuming for the clinicians. This paper presents a novel method for automated EEG-based diagnosis of depression using nonlinear methods: fractal dimension, largest Lyapunov exponent, sample entropy, detrended fluctuation analysis, Hursts exponent, higher order spectra, and recurrence quantification analysis. A novel Depression Diagnosis Index (DDI) is presented through judicious combination of the nonlinear features. The DDI calculated automatically based on the EEG recordings can be used to diagnose depression objectively using just one numeric value. Also, these features extracted from nonlinear methods are ranked using the t value and fed to the support vector machine (SVM) classifier. The SVM classifier yielded the highest classification performance with an average accuracy of about 98%, sensitivity of about 97%, and specificity of about 98.5%.

An integrated index for detection of Sudden Cardiac Death using Discrete Wavelet Transform and nonlinear features

Display Omitted Novel Sudden Cardiac Death Index (SCDI) is proposed using ECG signals.Nonlinear features are extracted from DWT coefficients.SCDI is formulated using nonlinear features.SCDI predicts accurately SCD 4min before its onset. Early prediction of person at risk of Sudden Cardiac Death (SCD) with or without the onset of Ventricular Tachycardia (VT) or Ventricular Fibrillation (VF) still remains a continuing challenge to clinicians. In this work, we have presented a novel integrated index for prediction of SCD with a high level of accuracy by using electrocardiogram (ECG) signals. To achieve this, nonlinear features (Fractal Dimension (FD), Hursts exponent (H), Detrended Fluctuation Analysis (DFA), Approximate Entropy (ApproxEnt), Sample Entropy (SampEnt), and Correlation Dimension (CD)) are first extracted from the second level Discrete Wavelet Transform (DWT) decomposed ECG signal. The extracted nonlinear features are ranked using t-value and then, a combination of highly ranked features are used in the formulation and employment of an integrated Sudden Cardiac Death Index (SCDI). This calculated novel SCDI can be used to accurately predict SCD (four minutes before the occurrence) by using just one numerical value four minutes before the SCD episode. Also, the nonlinear features are fed to the following classifiers: Decision Tree (DT), k-Nearest Neighbour (KNN), and Support Vector Machine (SVM). The combination of DWT and nonlinear analysis of ECG signals is able to predict SCD with an accuracy of 92.11% (KNN), 98.68% (SVM), 93.42% (KNN) and 92.11% (SVM) for first, second, third and fourth minutes before the occurrence of SCD, respectively. The proposed SCDI will constitute a valuable tool for the medical professionals to enable them in SCD prediction.

Computer-Aided Diagnosis of Depression Using EEG Signals

The complex, nonlinear and non-stationary electroencephalogram (EEG) signals are very tedious to interpret visually and highly difficult to extract the significant features from them. The linear and nonlinear methods are effective in identifying the changes in EEG signals for the detection of depression. Linear methods do not exhibit the complex dynamical variations in the EEG signals. Hence, chaos theory and nonlinear dynamic methods are widely used in extracting the EEG signal features for computer-aided diagnosis (CAD) of depression. Hence, this article presents the recent efforts on CAD of depression using EEG signals with a focus on using nonlinear methods. Such a CAD system is simple to use and may be used by the clinicians as a tool to confirm their diagnosis. It should be of a particular value to enable the early detection of depression.

Automated Identification of Infarcted Myocardium Tissue Characterization Using Ultrasound Images: A Review

Myocardial infarction (MI) or acute myocardial infarction commonly known as heart attack is one of the major causes of cardiac death worldwide. It occurs when the blood supply to the portion of the heart muscle is blocked or stopped causing death of heart muscle cells. Early detection of MI will help to prevent the infarct expansion leading to left ventricle (LV) remodeling and further damage to the cardiac muscles. Timely identification of MI and the extent of LV remodeling are crucial to reduce the time taken for further tests, and save the cost due to early treatment. Echocardiography images are widely used to assess the differential diagnosis of normal and infarcted myocardium. The reading of ultrasound images is subjective due to interobserver variability and may lead to inconclusive findings which may increase the anxiety for patients. Hence, a computer-aided diagnostic (CAD) technique which uses echocardiography images of the heart coupled with pattern recognition algorithms can accurately classify normal and infarcted myocardium images. In this review paper, we have discussed the various components that are used to develop a reliable CAD system.

Sudden cardiac death (SCD) prediction based on nonlinear heart rate variability features and SCD index

SCD is predicated using SVM classifier and sudden cardiac death index (SCDI).Nonlinear features are extracted from HRV signals.SVM predicts SCD with 94.7% accuracy four minutes before its onset.SCDI predicts SCD accurately. In our previous work, we have developed a sudden cardiac death index (SCDI) using electrocardiogram (ECG) signals that could effectively predict the occurrence of SCD four minutes before the onset. Thus, the prediction of SCD before its onset by using heart rate variability (HRV) signals is a worthwhile task for further investigation. Therefore, in this paper, a new novel methodology to automatically classify the HRV signals of normal and subjects at risk of SCD by using nonlinear techniques has been presented. In this study, we have predicted SCD by analyzing four-minutes of HRV signals (separately for each one-minute interval) prior to SCD occurrence by using nonlinear features such as Renyi entropy (REnt), fuzzy entropy (FE), Hjorths parameters (activity, mobility and complexity), Tsallis entropy (TEnt), and energy features of discrete wavelet transform (DWT) coefficients. All the clinically significant features obtained are ranked using their t-value and fed to classifiers such as K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM). In this work, we have achieved an accuracy of 97.3%, 89.4%, 89.4%, and 94.7% for prediction of SCD one, two, three, and four minutes prior to the SCD onset respectively using SVM classifier. Furthermore, we have also developed a novel SCD Index (SCDI) by using nonlinear HRV signal features to classify the normal and SCD prone HRV signals. Our proposed technique is able to identify the person at risk of developing SCD four minutes earlier, thereby providing sufficient time for the clinicians to respond with treatment in Intensive Care Units (ICU). Thus, this proposed technique can thus serve as a valuable tool for increasing the survival rate of many cardiac patients.

Data mining framework for identification of myocardial infarction stages in ultrasound

Early expansion of infarcted zone after Acute Myocardial Infarction (AMI) has serious short and long-term consequences and contributes to increased mortality. Thus, identification of moderate and severe phases of AMI before leading to other catastrophic post-MI medical condition is most important for aggressive treatment and management. Advanced image processing techniques together with robust classifier using two-dimensional (2D) echocardiograms may aid for automated classification of the extent of infarcted myocardium. Therefore, this paper proposes novel algorithms namely Curvelet Transform (CT) and Local Configuration Pattern (LCP) for an automated detection of normal, moderately infarcted and severely infarcted myocardium using 2D echocardiograms. The methodology extracts the LCP features from CT coefficients of echocardiograms. The obtained features are subjected to Marginal Fisher Analysis (MFA) dimensionality reduction technique followed by fuzzy entropy based ranking method. Different classifiers are used to differentiate ranked features into three classes normal, moderate and severely infarcted based on the extent of damage to myocardium. The developed algorithm has achieved an accuracy of 98.99%, sensitivity of 98.48% and specificity of 100% for Support Vector Machine (SVM) classifier using only six features. Furthermore, we have developed an integrated index called Myocardial Infarction Risk Index (MIRI) to detect the normal, moderately and severely infarcted myocardium using a single number. The proposed system may aid the clinicians in faster identification and quantification of the extent of infarcted myocardium using 2D echocardiogram. This system may also aid in identifying the person at risk of developing heart failure based on the extent of infarcted myocardium.

Longitudinal Changes in Tear Evaporation Rates After Eyelid Warming Therapies in Meibomian Gland Dysfunction

PURPOSE Lid warming is the major treatment for meibomian gland dysfunction (MGD). The purpose of the study was to determine the longitudinal changes of tear evaporation after lid warming in patients with MGD. METHODS Ninety patients with MGD were enrolled from a dry eye clinic at Singapore National Eye Center in an interventional trial. Participants were treated with hot towel (n = 22), EyeGiene (n = 22), or Blephasteam (n = 22) twice daily or a single 12-minute session of Lipiflow (n = 24). Ocular surface infrared thermography was performed at baseline and 4 and 12 weeks after the treatment, and image features were extracted from the captured images. RESULTS The baseline of conjunctival tear evaporation (TE) rate (n = 90) was 66.1 ± 21.1 W/min. The rates were not significantly different between sexes, ages, symptom severities, tear breakup times, Schirmer test, corneal fluorescein staining, or treatment groups. Using a general linear model (repeat measures), the conjunctival TE rate was reduced with time after treatment. A higher baseline evaporation rate (≥ 66 W/min) was associated with greater reduction of evaporation rate after treatment. Seven of 10 thermography features at baseline were predictive of reduction in irritative symptoms after treatment. CONCLUSIONS Conjunctival TE rates can be effectively reduced by lid warming treatment in some MGD patients. Individual baseline thermography image features can be predictive of the response to lid warming therapy. For patients that do not have excessive TE, additional therapy, for example, anti-inflammatory therapy, may be required.

Computer aided diagnosis of Coronary Artery Disease, Myocardial Infarction and carotid atherosclerosis using ultrasound images: A review

The diagnosis of Coronary Artery Disease (CAD), Myocardial Infarction (MI) and carotid atherosclerosis is of paramount importance, as these cardiovascular diseases may cause medical complications and large number of death. Ultrasound (US) is a widely used imaging modality, as it captures moving images and image features correlate well with results obtained from other imaging methods. Furthermore, US does not use ionizing radiation and it is economical when compared to other imaging modalities. However, reading US images takes time and the relationship between image and tissue composition is complex. Therefore, the diagnostic accuracy depends on both time taken to read the images and experience of the screening practitioner. Computer support tools can reduce the inter-operator variability with lower subject specific expertise, when appropriate processing methods are used. In the current review, we analysed automatic detection methods for the diagnosis of CAD, MI and carotid atherosclerosis based on thoracic and Intravascular Ultrasound (IVUS). We found that IVUS is more often used than thoracic US for CAD. But for MI and carotid atherosclerosis IVUS is still in the experimental stage. Furthermore, thoracic US is more often used than IVUS for computer aided diagnosis systems.

Automated diagnosis of congestive heart failure using dual tree complex wavelet transform and statistical features extracted from 2s of ECG signals

Identification of alarming features in the electrocardiogram (ECG) signal is extremely significant for the prediction of congestive heart failure (CHF). ECG signal analysis carried out using computer-aided techniques can speed up the diagnosis process and aid in the proper management of CHF patients. Therefore, in this work, dual tree complex wavelets transform (DTCWT)-based methodology is proposed for an automated identification of ECG signals exhibiting CHF from normal. In the experiment, we have performed a DTCWT on ECG segments of 2s duration up to six levels to obtain the coefficients. From these DTCWT coefficients, statistical features are extracted and ranked using Bhattacharyya, entropy, minimum redundancy maximum relevance (mRMR), receiver-operating characteristics (ROC), Wilcoxon, t-test and reliefF methods. Ranked features are subjected to k-nearest neighbor (KNN) and decision tree (DT) classifiers for automated differentiation of CHF and normal ECG signals. We have achieved 99.86% accuracy, 99.78% sensitivity and 99.94% specificity in the identification of CHF affected ECG signals using 45 features. The proposed method is able to detect CHF patients accurately using only 2s of ECG signal length and hence providing sufficient time for the clinicians to further investigate on the severity of CHF and treatments.

An integrated index for automated detection of infarcted myocardium from cross-sectional echocardiograms using texton-based features (Part 1)

Cross-sectional view echocardiography is an efficient non-invasive diagnostic tool for characterizing Myocardial Infarction (MI) and stages of expansion leading to heart failure. An automated computer-aided technique of cross-sectional echocardiography feature assessment can aid clinicians in early and more reliable detection of MI patients before subsequent catastrophic post-MI medical conditions. Therefore, this paper proposes a novel Myocardial Infarction Index (MII) to discriminate infarcted and normal myocardium using features extracted from apical cross-sectional views of echocardiograms. The cross-sectional view of normal and MI echocardiography images are represented as textons using Maximum Responses (MR8) filter banks. Fractal Dimension (FD), Higher-Order Statistics (HOS), Hus moments, Gabor Transform features, Fuzzy Entropy (FEnt), Energy, Local binary Pattern (LBP), Renyis Entropy (REnt), Shannons Entropy (ShEnt), and Kapurs Entropy (KEnt) features are extracted from textons. These features are ranked using t-test and fuzzy Max-Relevancy and Min-Redundancy (mRMR) ranking methods. Then, combinations of highly ranked features are used in the formulation and development of an integrated MII. This calculated novel MII is used to accurately and quickly detect infarcted myocardium by using one numerical value. Also, the highly ranked features are subjected to classification using different classifiers for the characterization of normal and MI LV ultrasound images using a minimum number of features. Our current technique is able to characterize MI with an average accuracy of 94.37%, sensitivity of 91.25% and specificity of 97.50% with 8 apical four chambers view features extracted from only single frame per patient making this a more reliable and accurate classification.