Tiwari, Anil Kumar

Automatic diagnosis of the heart valve diseases generally requires the segmentation of heart sound signal. Henceforth, in this paper a novel algorithm for automatic segmentation of the heart sound signal is proposed. The heart sound signal is acquired using seismocardiography (SCG), which uses a sensor called accelerometer. The accelerometer is of small size and low weight and thus convenient to wear. The proposed algorithm performs in three steps. First, the signal is filtered using the developed denoising algorithm based on discrete wavelet transform. The computational complexity of this algorithm is reduced by processing only two levels, which are expected to have heart sound signal, and other levels are discarded. To improve the performance of denoising, an adaptive threshold is obtained for both the levels separately, and applied. Then, the denoised signal is obtained by reconstructing the thresholded coefficients. In the second step, peaks are detected in the denoised signal using an adaptive threshold, obtained using Otsu's method. Then, false detected peaks and noise contaminated parts of the signal are identified and discarded from further analyses. In the third step, the heart sound components are identified as S1, and S2 based on the energy of the particular component and segmentation is performed. The results of denoising, show that the developed algorithm outperforms the existing method. Further, the segmentation results show that the developed algorithm is able to identify the heart sound components, accurately, even in the presence of noise.

In this paper we investigate the prediction scheme of Context Based Adaptive Lossless Image Coding (CALIC), the standard for lossless/near lossless image compression for continuous-tone finger-print images. We show that it is not sufficient to consider the prediction technique in a single direction for a fingerprint image as a whole for Gradient Adjusted Predictor (GAP). As a result, we propose an additional GAP scheme to achieve better speed and better prediction accuracy as and hence provide potential for further improvements in Lossless Image Compression. Experimental results indicate that the proposed scheme outperforms the existing GAP prediction for all the finger-print images tested, while the complexity of the prediction algorithm is improved by more than four times with the help of parallel implementation. ©2010 IEEE.

Hypertensive Retinopathy (HR) is a retinal manifestation caused due to persistently raised blood pressure. Computer-aided diagnosis (CAD) plays an important role in the early identification of HR with high diagnostic accuracy, which is time-efficient and demands fewer resources. At present, there are very few computerized systems available for HR detection. Nonetheless, because of the limited number of datasets, there is still room for significant advancement in HR detection. Recently, deep learning has drawn a lot of interest, mainly due to its efficiency has been significantly enhanced. In this work, we develop a novel approach for HR detection based on few-shot learning using a pretrained initial baseline model in which transferable knowledge is obtained for feature embedding on few-shot prediction (limited number of images). It is used to avoid overfitting and to improve generalization on smaller datasets. The proposed baseline model consists of a CNN and LSTM-based HR detection model that can recognize base categories and dynamically generate classification weight vectors for few-shot datasets. The pretrained baseline classifier maximizes the reuse of feature embedding on few-shot datasets, which is comparatively more suitable for smaller datasets than other deep-learning models. In addition, the similarity-based cosine distance classifier followed by the softmax function is used for a few-shot dataset classification. Our experimental findings indicate the effectiveness of the proposed method in HR detection, evaluated on publicly available datasets (including recently released datasets). Therefore, the proposed system can effectively detect HR and can be used by clinicians for referral as well as to facilitate mass screening.

In this paper, we propose a new reversible watermarking algorithm based on additive prediction-error expansion which can recover original image after extracting the hidden data. Embedding capacity of such algorithms depend on the prediction accuracy of the predictor. We observed that the performance of a predictor based on full context prediction is preciser as compared to that of partial context prediction. In view of this observation, we propose an efficient adaptive prediction (EAP) method based on full context, that exploits local characteristics of neighboring pixels much effectively than other prediction methods reported in literature. Experimental results demonstrate that the proposed algorithm has a better embedding capacity and also gives better Peak Signal to Noise Ratio (PSNR) as compared to state-of-the-art reversible watermarking schemes. © 2013 IEEE.

In this paper, we propose a novel method for image watermarking which can recover the original image after extracting the embedded data without effecting the original cover image. The proposed embedding algorithm runs in two pass. The watermarked image after first pass works as a cover image for second pass. In each pass, embedded data utilizes different prediction algorithm. First pass uses a highly effective method for prediction whether in second pass a simpler and less complex method is used in our work. Moreover, the proposed algorithm has simple decoder complexity. Our algorithm gives better embedding capacity and Peak Signal to Noise Ratio (PSNR) than various One Pass algorithms. We also modified our two pass algorithm which increases PSNR value by sacrificing payload capacity. © 2012 Institute of Telecommunica.

Purpose: Diabetic Retinopathy (DR) is a progressive retinal disease caused by long-term diabetes. Non-proliferative Diabetic Retinopathy (NPDR), an early stage of DR, damages retinal blood vessels, often leads to swelling and leakage of blood. This results in the formation of microaneurysms (MAs) and hemorrhages (HAMs). These changes in the retina can cause vision problems, and an early diagnosis and management are crucial to prevent the progression of the disease. Methods: This paper presents a reliable method for severity grading of NPDR into normal, mild, moderate, and severe classes using fundus images. The proposed method consists of image enhancement, masking out the optic disc region and blood vessel elimination for initial candidate extraction of MAs and HAMs, features extraction, and classification. Fundus image enhancement includes denoising, contrast enhancement, shade correction, and image normalization. In this study, we construct a hybrid feature set based on multiple descriptors, including shape, color, texture, and statistics, to enhance the classification process. For texture-based information, the performance of the gray-level co-occurrence matrix (GLCM) and Gabor-based feature descriptor is thoroughly analyzed. The proposed method is evaluated using two datasets APTOS and MESSIDOR, which are divided into four NPDR classes, each of which suffers from class imbalance, where the number of samples in one class significantly outweighs the other. Such an imbalance can adversely affect machine learning classification models, as they tend to over-predict the majority class and under-predict the minority class. To address this issue, the synthetic minority oversampling technique (SMOTE) is utilized. To grade the images into one of the severity classes (normal, mild, moderate, and severe) and to further improve the performance for class imbalance, we present an ensemble learning-based random forest (RF) classifier. Results: The proposed method achieved a weighted average accuracy of 98.6%, a sensitivity of 97.2%, a specificity of 98.3%, an F1-score of 97.2%, and a precision of 97.2% on the MESSIDOR dataset. For the APTOS dataset, the proposed method achieved an average accuracy of 98.9%, a sensitivity of 97.6%, a specificity of 98.8%, an F1-score of 97.6%, and a precision of 97.6%. Conclusion: The performance evaluation results demonstrate the effectiveness of the proposed method, which will aid in the early diagnosis, regular screening, and effective management of NPDR.

In this paper, we present an additive prediction error expansion (PEE) based reversible data hiding scheme that gives overall low distortion and relatively high embedding capacity. Recently reported interpolation based PEE method uses fixed order predictor that fails to exploit the correlation between the neighborhood pixels and the unknown pixel (to be interpolated).We observed that embedding capacity and distortion of PEE based algorithm depends on the prediction accuracy of the predictor. In view of this observation, we propose an interpolation based method that predicts pixels using predictors of different structure and order. Moreover, we use only original pixels for interpolation. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art algorithms both in terms of embedding capacity and Peak Signal to Noise Ratio.

Background: Automatic detection of epileptic seizures is critical in the paradigm of epilepsy diagnosis and in relieving the cumbersome visual inspection of electroencephalogram (EEG) recordings. A speedy algorithm could help in more reliable monitoring and detection of seizures. Methods and materials: In this study, we aim to provide an EEG-based seizure detection system with computational efficiency and improved performance. In the proposed work, many features including temporal, spectral, and non-linear features from each intrinsic mode function (IMF) of empirical mode decomposition (EMD) have been used. Barnes–Hut approximation-based t-stochastic neighborhood embedding (bh t-SNE) was explored for the first time to observe the reduction in computational time (CT) period in the automatic seizure detection system. Three classes of widely-used EEG Bonn datasets were used to assess the performance of the proposed method. Results: The proposed Barnes–Hut-based accelerating t-SNE along with SVM and KNN reduced more than half of the classification time with the same accuracy. The classifier takes 2.147±0.1 s for SVM and 1.216±0.1 s for KNN without the proposed t-SNE and 1.31±0.1 s for SVM and 0.736±0.1 s for KNN (at the trade-off parameter θ=0.5) with the proposed Barnes–hut based t-SNE (bh t-SNE) at an accuracy of 100%. Conclusions: The findings of the experimental work indicate that the proposed method is effective in reducing the computational time while maintaining the required efficacy. As a result, the inclusion of these algorithms in hardware might prove to be effective in assisting neurologists in detecting seizures.

Fundus image enhancement is an essential and challenging pre-processing step for automated diagnosis of ocular disorders. The enhancement works reported earlier were developed for the distortions such as additive white Gaussian noise and salt-and-pepper noise. However, this poses a significant limitation for the applicability of these methods, as occurrences of such distortions are least likely. In this work, the five most common distortions are identified, and algorithms are proposed to create distortions resembling the same. Thereafter, a residual dense connection based UNet (RDC-UNet) architecture is proposed for the enhancement task. The residual dense connections incorporated in the UNet effectively captures both local and global information from the images beneficial for the enhancement task. The RDC-UNet was trained individually for each of the five distortions and then applied to the synthetic degraded fundus images. The experimental results show that the visual quality and quantitative results are, on average, 8% better than the state-of-the-art methods reported in the literature. Furthermore, in case of naturally degraded images, the type of distortion is not known apriori. Additionally, multiple such distortions can be present at a time. An ensemble model architecture is proposed using the RDC-UNet trained individually for each degradation to address this challenge. Experiments conducted over naturally degraded fundus images demonstrate that the proposed model effectively enhances the visual quality of fundus images. In addition, the effectiveness of the proposed method is also shown with the application of blood vessel segmentation.

Fetal phonocardiography is a simple and noninvasive diagnostic technique for surveillance of fetal well-being. The fetal phonocardiographic (fPCG) signals carry valuable information about the anatomical and physiological states of the fetal heart. This article is concerned with a study of continuous wavelet transform (CWT)-based scalogram in analyzing the fPCG signals. The scalogram has both spatial and frequency resolution powers, whereas traditional spectral estimation methods only have the frequency resolution ability. The fPCG signals are acquired by a specially developed data recording system. Segmentation of these signals into fundamental components of fetal heart sound (S1 & S2) is carried out through envelope detection and thresholding techniques. CWT-based scalogram is used for time-frequency characterization of the segmented fPCG signals. It has been shown that the wavelet scalogram provides enough features of the fPCG signals that will help to obtain qualitative and quantitative measurements of the time-frequency characteristics of the fPCG signals and consequently, assist in diagnosis. The proposed method for time-frequency analysis (TFA) and the associated pre-processing have been shown to be suitable for the characterization of fPCG signals, yielding relatively good and robust results in the experimental evaluation. © 2011 World Scientific Publishing Company.