Department of Biomedical Engineering

In medical imaging, image denoising has become a very essential exercise all through the diagnosis. Compromise between the preservation of useful diagnostic information and noise suppression must be respected in medical images. One of the ultimate goals of an imaging modality is to provide the clinician with the best possible information needed to make an accurate diagnosis. Ultrasound images suffer from an intrinsic artifact called speckle. Speckle degrades spatial and contrast resolution and obscures the underlying anatomy. Thus, it seems sensible to reduce speckle artifacts before performing image analysis, provided the image that might distinguish one tissue from another is preserved. The main goal of this thesis was the development of novel methods for suppression of speckle in medical ultrasound images in the wavelet domain. We have adopted weighted variance for estimating the threshold and multiscale product scheme for thresholding the coefficients. To employ the wavelet interscale dependencies, the adjacent wavelet subbands are multiplied. Multiplying the adjacent wavelet scales would sharpen the important structures while reducing noise. In the multiscale products, edges can be efficiently discriminated from noise. Then, an adaptive threshold was calculated and imposed on the products, instead of on the wavelet coefficients, to identify important features. Fundamentally speckle noise is a signal-dependent one, and so weighted variance of each background pixel was taken into account while calculating threshold. Experiments show that the proposed scheme better suppresses noise and preserves edges than other wavelet-denoising methods. Experiments with synthetic and real ultrasound imagery show that the proposed method improves the signal-to-noise ratio and preserves edge clarity.

EEG recording are used to analyze the electrical signals generated by the brain. It is used in diagnosing and monitoring process of neurological disorder such as Epilepsy. Epilepsy cannot be controlled by available medical treatments. Its major manifestation is epilepsy seizure. Lifting Based Discrete Wavelet Transform (LBDWT) an efficient toll for representing electroencephalogram signals. EEG changes will be classified by Multilayer perceptron Neural Network (MLPNN). The classification rules were extracted from EEG that were reordered from healthy volunteers , epilepsy patients during seizure free interval and epilepsy patients during epileptic seizure.EEG signals were used as input of the MLPNNs trained with Back propagation and Levenberg -Marquadrant algorithm. Decision making was done in two stages: feature extraction by using LBDWT and classification using MLPNNs trained with the BP and LM algorithms .In this paper, we present an algorithm for classification of EEG (normal and Epilepsy) signals based on lifting based Discrete Wavelet Transformation and patterns recognize techniques.

In medical image processing, image denoising has become a very essential exercise all through the diagnose. Negotiation between the preservation of useful diagnostic information and noise suppression must be treasured in medical images. In certain cases, for instance in Ultrasound images, the noise can restrain information which is valuable for the general practitioner. The success of ultrasonic examination depends on the Image quality. In case of ultrasonic images a special type of acoustic noise, technically known as speckle noise, is the major factor of image quality degradation. Many denoising techniques have been proposed for effective suppression of speckle noise. This paper presents the performance analysis of various schemes for suppressing speckle noise in Ultrasound images in terms of the assessment parameters PSNR and Equivalent Number of Looks (ENL).

and-conditions-of-access.pdf This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, redistribution , reselling , loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material.

Image compression is significant in the medical industry. The sequence of images produced is of great importance which requires lossless compression technique. Among the several lossless image compression algorithms JPEG-LS becomes a promising technique to compress the medical image sequences which gives the best performance both in terms of compression ratio and compression speed.JPEG-LS compress only a single picture with intracoding. To enhance the compression with medical image sequences we have combined JPEG-LS with interframecoding. This combination has provided the compression ratio of 4.8.To further increase the compression ratio we propose a new scheme Head Code Compression.Experimental results of our proposed algorithm achieve 20% more reduction than the prior arts.

Medical image security can be enhanced using the reversible watermarking technique, it allows us to embed the relevant information with the image, which provides confidentiality, integrity and authentication by embedding RSA encrypted digital signature with the image. Protection of Medical Image content is very much important for tele-diagnosis and telesurgery. Our work proposes a novel algorithms AHF (Additive Hash Function) and RSA for the production of DS (Digital Signature) to achieve high confidentiality and Authentication. An image is compressed using JPEG2000 (DWT) algorithm and EPR (Electronic Patient Record) is embedded in RONI (Region of Non Interest) of compressed image using Lossless Watermarking Technique then shared through the open network. The PSNR (peak Signal to Noise ratio) value is up to 72dBs for 512×512 US(Ultrasonic) images. Increase in Authentication can be achieved when medical expert's access secured medical images from the web servers using Kerberos technique.

Medical image content authentication is very important, since medical image contents are more and more widely distributed. Reversible watermarking becomes a promising technique to embed the information into medical images. In this paper, we define the Region of Interest (ROI) in an image and trying to embed data in Region of Non Interest. When medical image shared through network, for the compression purpose we proposed the JPEG2000 algorithm and to improve the integrity and Authenticity hash value of the image is found by using MD5 and encrypted using RSA to form the DS (Digital Signature). DS and patient information is embedded into DICOM images. Strict authentication can be achieved by providing high security in accessing the secured medical images by medical experts which are available in the websites using Kerberos technique.

The necessity in medical image compression continuously grows during the last decade. In advanced medical life large number of medical images is processed in hospitals and medical centers around the world. These images are in the form of sequences which are much correlated and are of great importance. Hence lossless image compression is needed to reproduce the original quality of the image without any loss of information. To exploit the correlation a new algorithm is proposed in this paper. The proposed compression method combines Super-Spatial Structure Prediction with motion estimation and motion compensation to achieve higher compression ratio. This is applied with a simple blockmatching process Binary Tree Search. Results are compared in terms of Compression Ratio and Peak Signal-to-Noise Ratio. The proposed methodology provides better CR and PSNR than the other state-of-the-art algorithm.

In multimedia environment many videos have been introduced which occupies more memory space, especially in the medical field. In this paper, a new low complexity and lossless image compression system for capsule endoscopy (CE) is approached. The compressor consists of a low-cost YCbCr color space converter and variable-length predictive with a combination and unary encoding. All these components have been heavily optimized for low-power and low-cost and lossless in nature. As a result, the entire compression system does not incur any loss of image information. Unlike transform based algorithms, the compressor can be interfaced with commercial image sensors which send pixel data in raster-scan fashion that eliminates the need of having large buffer memory. The results shows increase in PSNR value of 54db the proposed algorithm offers a solution to wireless capsule endoscopy with lossless and yet acceptable level of compression.

Human action recognition has a wide range of promising applications like video surveillance, intelligent interface, and video retrieval. The objective of this project is to recognize and annotate different human activities present in digital videos taken from both constrained and unconstrained environment. This work extended the use of the techniques existing in object recognition in 2D images to video sequences by determining the Spatio-temporal Interest points using the extension of Harris operator in the time dimension. Features descriptors are computed on the cuboids around these interest points and further they are clustered and bag of features is built .SVM is used to classify the different classes of action present in the video. The recognition rate is further improved by using Adaboost SVM wherein number of weak classifier is weighted to form a strong classifier. The result shows that the proposed method using adaboost SVM classifier, the mean accuracy rate of recognition of KTH dataset is 89.13%.

Medical image sequences are produced in enormous amount which requires a large storage capacity. These image sequences are of great importance, hence it is necessary to develop a system that produces high degree of compression while preserving the medical information. Lossless compression Technique is required to reduce the number of bits to store these image sequences and take less time to transmit over the network. This paper proposes a method that combines SPIHT with HCC to enhance the compression ratio. Inter-frame coding is used to exploit the correlation among image sequences. Initially SPIHT is applied with fast block matching process, Diamond Search. To enhance the efficiency of compression ratio a new scheme Head Code Compression is introduced. Results are compared in terms of Compression Ratio and Peak Signal-to-Noise Ratio with other state of art coding. Experimental results of our proposed methodology achieves 25% more reduction than the other state-of-the-art algorithms.

Protection of Medical image contents becomes the important issue in computer network security. Digital Watermarking has becomes a promising technique for medical content authentication, it allows to embed relevant information with the image, which provides confidentiality, integrity and authentication by embedding Digital Signature (DS) with the Medical image. In this paper we focus on need for reversible watermarking, Medical Image Compression and security related problems in medical images, it comparing the performances of various lossless watermarking techniques for various medical image modalities like MRI (Magnetic Resonance Imaging), US (Ultrasonic), CT (Computed Tomography), Endoscopic and Angiographic images. Region of Interest (ROI) supporting lossless watermarking systems only considered for discussions. Performance of all lossless watermarking with Digital Signature is analyzed by means of four parameters Capacity Rate, PSNR (Peak Signal to Noise ratio), NPCR (Number of P...

Protection of Medical image contents becomes the important issue in computer network security. Digital Watermarking has becomes a promising technique for medical content authentication, it allows to embed relevant information with the image, which provides confidentiality, integrity and authentication by embedding Digital Signature (DS) with the Medical image. In this paper we focus on need for reversible watermarking, Medical Image Compression and security related problems in medical images, it comparing the performances of various lossless watermarking techniques for various medical image modalities like MRI (Magnetic Resonance Imaging), US (Ultrasonic), CT (Computed Tomography), Endoscopic and Angiographic images. Region of Interest (ROI) supporting lossless watermarking systems only considered for discussions. Performance of all lossless watermarking with Digital Signature is analyzed by means of four parameters Capacity Rate, PSNR (Peak Signal to Noise ratio), NPCR (Number of P...

The demand to preserve raw image data for further processing has been increased with the hasty growth of digital technology. In medical industry the images are generally in the form of sequences which are much correlated. These images are very important and hence lossless compression Technique is required to reduce the number of bits to store these image sequences and take less time to transmit over the network The proposed compression method combines Super-Spatial Structure Prediction with inter-frame coding that includes Motion Estimation and Motion Compensation to achieve higher compression ratio. Motion Estimation and Motion Compensation is made with the fast block-matching process Inverse Diamond Search method. To enhance the compression ratio we propose a new scheme Bose, Chaudhuri and Hocquenghem (BCH). Results are compared in terms of compression ratio and Bits per pixel to the prior arts. Experimental results of our proposed algorithm for medical image sequences achieve 30%...

In mammograms, a cluster of micro calcifications shows an early sign of breast cancer. An accurate and efficient classification scheme is needed for detection of tumour in mammograms. A Computer-Aided-Detection (CAD) system for automatic detection of tumour of micro calcification clusters on mammograms is discussed in this paper. The approach is very helpful for radiologist to diagnose the tumour and performs faster than typical screening programs. The images are collected from the Mammographic Image Analysis Society (MIAS) databases for implementation. The feature is extracted by Local Binary Pattern and classified using ANN. The proposed scheme provides high accuracy in classification of micro calcifications.

Background: Stress has become an integrated part of our life. Stress was modelled as four stages by Hans Selye’s in his General Adaptation Syndrome (GAS) model. Objective: The main objective of this work is to design an efficient laboratory Group Stroop Colour Word Test (GSCWT) to induce distinct four levels of stress that is, no stress, low, medium and high stress, which mimics a real time working memory (WM) load for the subject and thus cause stress for the subject. Subjects and Method: Healthy and normal 50 subject’s Heart Rate Variability (HRV) is considered for analysis. GSCWT is developed using software Matlab 2013 and is validated by recording ECG both at rest and while performing the different levels of stroop task. The time domain, frequency domain parameters of HRV is determined using kubios software and the influence of GSCWT between the different levels of stress is analysed using statistical t-test to compare the features between each state and one-way Anova test is us...