Rahul Kher

CT Image Compression Using Compressive Sensing and Wavelet Transform

Compressive sensing (CS) technique addresses the issue of compressing the sparse signal with a rate below Nyquist rate of sampling. For medical images there are always issues of acquisition time and compression, the compressive sensing is found to be a better technique that works in a manner that it first acquires samples less than signal dimensionality and reconstructs the same signal. In this paper Wavelet transform is applied along with compressive sensing on CT images. Three various measurements (for three compression ratio values) have been taken and calculated PSNR, CoC, and RMSE. As measurements are increased PSNR, CoC and visual quality increases and RMSE decreases. The main observation is that only 60% measurements can reproduce image with PSNR of more than 25 dB and with CoC more than 0.99.

A Comparative Analysis of Multimodality Medical Image Fusion Methods

Medical image fusion has been used to derive useful information from multimodality medical image data. The idea is to improve the image content by fusing images like computer tomography (CT) and magnetic resonance imaging (MRI) images, magnetic resonance imaging (MRI) provides better information on soft tissue whereas computed tomography (CT) provides better information about denser tissue. Fusing these two types of images creates a composite image which is more informative than any of the input signals provided by a single modality. For this reason, image fusion has become a common process used within medical diagnostics and treatment. In this paper, Fast Discrete Curvelet Transform using Wrapper algorithm based image fusion technique, has been implemented, analyzed and compared with Wavelet based Fusion Technique. Fusion of images taken at different resolutions, intensity and by different techniques helps physicians to extract the features that may not be normally visible in a single image by different modalities. This work aims at fusion of registered CT and MRI Images. This fused image can significantly benefit medical diagnosis and also the further image processing such as, visualization (colorization), segmentation, classification and computer-aided diagnosis (CAD). The fusion performance is evaluated on the basis of the root mean square error (RMSE) and peak signal to noise ratio (PSNR).

Analysis of CT and MRI Image Fusion Using Wavelet Transform

Medical image fusion has been used to derive useful information from multimodality medical image data. The idea is to improve the image content by fusing images like computer tomography (CT) and magnetic resonance imaging (MRI) images, so as to provide more information to the doctor and clinical treatment planning system. This paper aims to demonstrate the application of wavelet transformation to multi-modality medical image fusion. This work covers the selection of wavelet function, the use of wavelet based fusion algorithms on medical image fusion of CT and MRI, implementation of fusion rules and the fusion image quality evaluation. The fusion performance is evaluated on the basis of the root mean square error (RMSE) and peak signal to noise ratio (PSNR).

ECG signal compression using Compressive Sensing and wavelet transform

Compressed Sensing (CS) is a novel approach of reconstructing a sparse signal much below the significant Nyquist rate of sampling. Due to the fact that ECG signals can be well approximated by the few linear combinations of wavelet basis, this work introduces a comparison of the reconstructed 10 ECG signals based on different wavelet families, by evaluating the performance measures as MSE (Mean Square Error), PSNR (Peak Signal To Noise Ratio), PRD (Percentage Root Mean Square Difference) and CoC (Correlation Coefficient). Reconstruction of the ECG signal is a linear optimization process which considers the sparsity in the wavelet domain. L1 minimization is used as the recovery algorithm. The reconstruction results are comprehensively analyzed for three compression ratios, i.e. 2:1, 4:1, and 6:1. The results indicate that reverse biorthogonal wavelet family can give better results for all CRs compared to other families.

Physical activities recognition from ambulatory ECG signals using neuro-fuzzy classifiers and support vector machines

Abstract The use of wearable recorders for long-term monitoring of physiological parameters has increased in the last few years. The ambulatory electrocardiogram (A-ECG) signals of five healthy subjects with four body movements or physical activities (PA)—left arm up down, right arm up down, waist twisting and walking—have been recorded using a wearable ECG recorder. The classification of these four PAs has been performed using neuro-fuzzy classifier (NFC) and support vector machines (SVM). The PA classification is based on the distinct, time-frequency features of the extracted motion artifacts contained in recorded A-ECG signals. The motion artifacts in A-ECG signals have been separated first by the discrete wavelet transform (DWT) and the time–frequency features of these motion artifacts have then been extracted using the Gabor transform. The Gabor energy feature vectors have been fed to the NFC and SVM classifiers. Both the classifiers have achieved a PA classification accuracy of over 95% for all subjects.

Selecting the Most Favorable Wavelet for Compressing ECG Signals Using Compressive Sensing Approach

Compressed Sensing (CS) is a novel approach of reconstructing a sparse signal much below the significant Nyquist rate of sampling. Due to the fact that ECG signals can be well approximated by the few linear combinations of wavelet basis, this work introduces a comparison of the reconstructed ECG signal based on different wavelet families, by evaluating the performance measures as MSE (Mean Square Error), PSNR (Peak Signal To Noise Ratio), PRD (Percentage Root Mean Square Difference) and CoC (Correlation Coefficient). Reconstruction of the ECG signal is a linear optimization process which consider the sparsity in the wavelet domain, perceived by the fact that higher the sparsity, more better the recovery. L1 minimization is used as the recovery algorithm. The reconstruction results are comprehensively analyzed for five compression ratios, i.e. 2:1, 4:1, 6:1, 8:1 and 10:1. The results indicate that reverse biorthogonal wavelet family can give better results for all (Compression Ratios)CRs compared to other families.

Motion artifacts extraction using dwt from ambulatory ECG (A-ECG)

Ambulatory ECG signal monitoring is useful when long term cardiac monitoring of a patient is necessary. Ambulatory ECG (A-ECG) monitoring provides electrical activity of the heart while a person is involved in doing his or her normal routine activities. Thus, the recorded ECG signal consists of cardiac signal along with motion artifacts introduced due to persons body movements during routine activities. This motion artifact has spectral overlap with cardiac signal in 1-10 Hz which corresponds to ECG features like P wave and T wave. Detection of motion artifacts due to different physical activities (PA) might help in further cardiac diagnosis. Ambulatory ECG signal analysis for detection of various motion artifacts using discrete wavelet transform (DWT) approach is addressed in this paper. The ECG signals of healthy subjects (aged of 19 to 16 years) were recorded while the person performs various body movements activity like (i) up and down movement of left hand, (ii) up and down movement of right hand, (iii) waist twisting movement while standing and (iv) change in position from sitting down on chair to standing up movement in lead I configuration by using BIOPAC MP 36 signal acquiring system.

Implementation of derivative based QRS complex detection methods

In this paper QRS complex detection algorithms based on the first and second derivatives have been studied and implemented. The threshold values for detecting R-peak candidate points mentioned in previous work have been modified for accuracy point of view. The derivative based QRS detection algorithms have been found not only computationally simple but exceptionally effective also on variety of ECG database that includes highly noisy and arrhythmic ECG signals. This is indicated by an average detection rate of over 98% obtained through the modified threshold values even for the challenging ECG test sets.

Adaptive filtering based artifact removal from electroencephalogram (EEG) signals

The electroencephalogram (EEG) is an important bioelectric signal for studying human brain characteristics as well as detection of abnormalities like epilepsy. However, the EEG recorded from frontal channels, often contain strong artifacts produced by eye movements. Existing regression-based methods for removing artifacts require various procedures for pre-processing and calibration that are inconvenient and time consuming. This paper describes a method for removing the EOG artifacts contained in EEG signal based on adaptive filtering. The method uses separately recorded noisy EEG and clean EEG as two reference inputs. The noisy EEG signals with three types of EOG artifacts-horizontal eye movement, vertical eye movement and eye blinks have been recorded for five subjects. The adaptive filter, based on a least mean square (LMS) algorithm, adapts its coefficients to produce an output which matches the reference input.

Face Recognition Using 2DPCA and ANFIS Classifier

With the growth of information technology coupled with the need for high security, the application of biometric as identification and recognition process has received special attention. The biometric authentication systems are gaining importance, and in particular, face biometric is more preferred for person authentication because of its easy and non-intrusive method during acquisition procedure. Face recognition is considered to be one of the most reliable biometric, when security issues are taken into concern. Various methods are used for face recognition. To recognize the face, feature extraction becomes a critical problem. In this paper, two-dimensional principle component analysis (2D-PCA) has been applied for feature extraction. The feature vectors are then applied to adaptive neuro-fuzzy inference system (ANFIS) classifier. The result indicates that ANFIS classifier yields 97.1 % of classification accuracy.