Suvojit Acharjee

Shape-Based Approach for Coronary Calcium Lesion Volume Measurement on Intravascular Ultrasound Imaging and Its Association With Carotid Intima-Media Thickness

Coronary calcification plays an important role in diagnostic classification of lesion subsets. According to histopathologic studies, vulnerable atherosclerotic plaque contains calcified deposits, and there can be considerable variation in the extent and degree of calcification. Intravascular ultrasound (IVUS) has demonstrated its role in imaging coronary arteries, thereby displaying calcium lesions. The aim of this work was to develop a fully automated system for detection, area and volume measurement, and characterization of the largest calcium deposits in coronary arteries. Furthermore, we demonstrate the correlation between the coronary calcium IVUS volume and the neurologic risk biomarker B‐mode carotid intima‐media thickness (IMT).

Ant Weight Lifting algorithm for image segmentation

Image segmentation forms a quintessential concept and is one of the most in-demand arenas of research in the field of image processing. Throughout the years several techniques like k-means clustering, watershed segmentation and quad tree segmentation have been devised to properly segment an image into well-defined classes. Segmentation techniques can be broadly classified as thresholding techniques, edge detection techniques, clustering, region based and matching. Image segmentation may be the ultimate output desired and may also be a penultimate step in the algorithm. In either case it becomes essential to get an accurately segmented image which is often not the case with the existing algorithms since each algorithm has its own drawback. In our paper we have proposed a novel segmentation technique that is bio-inspired from the behavioral nature of ants and is hence called the Ant Weight Lifting (AWL) segmentation algorithm. Our segmentation algorithm has generated optimum results on a wide range of test cases imposed by us with a high correlation factor between the original and segmented image and also an added perk in the form of a low time complexity.

A novel Block Matching Algorithmic Approach with smaller block size for motion vector estimation in video compression

The most computationally expensive operation in entire video compression process is Motion Estimation. The challenge is to reduce the computational complexity and time of Exhaustive Search Algorithm without losing too much quality at the output. The proposed work is to implement a novel block matching algorithm for Motion Vector Estimation which performs better than other conventional Block Matching Algorithms such as Three Step Search (TSS), New Three Step Search (NTSS), and Four Step Search (FSS) etc.

Electrocardiogram Feature Based Inter-human Biometric Authentication System

Biometrics integrates various technologies to identify an individual by exploiting their physiological and behavioral characteristics, which are unique and measurable. This paper proposes a novel technique for the development of a robust and secure biometric authentication system. In this current work, an interhuman ECG-Hash code is generated by performing an inner product between the Electrocardiogram (ECG) feature matrices of two different individuals located remotely. The individuals will have each others ECG features, stored in their database. The accuracy of the system increases as the authentication mechanism requires traits from both the individuals, amongst whom the transmission is taking place. Moreover, the use of ECG features as a biometric trait enhances the security aspects of the system as traits like fingerprints or facial features maybe compromised with age or otherwise.

Watermarking in motion vector for security enhancement of medical videos

With the advancement in technology, it becomes easy for some individuals to use digital data without the permission of the owner. To increase authentication and security of copyrights, digital watermarking was introduced. Medical videos contain very significant information about the condition of the patient. A good watermarking scheme should always contain very less distortion. Videos generally contain huge temporal redundancy, which demands the use of motion vector estimation technique in order to remove the temporal redundancy. In this work, an image was watermarked inside the motion vector of two consecutive frames of an echo-cardiograph video. Quality analysis of the recovered video with the original video proves the robustness of the proposed scheme.

Performance Evaluation of Different Cost Functions in Motion Vector Estimation

Video is an important medium in terms of information sharing in this present era. The tremendous growth of video use can be seen in the traditional multimedia application as well as in many other applications like medical videos, surveillance video etc. Raw video data is usually large in size, which demands for video compression. In different video compressing schemes, motion vector is a very important step to remove the temporal redundancy. A frame is first divided into small blocks and then motion vector for each block is computed. The difference between two blocks is evaluated by different cost functions (i.e. mean absolute difference (MAD), mean square error (MSE) etc).In this paper the performance of different cost functions was evaluated and also the most suitable cost function for motion vector estimation was found.

Highly Secured Multilayered Motion Vector Watermarking

With the recent development in multimedia, video has become a powerful medium of information. To exploit the temporal redundancy during video compression, motion vector estimation is required. Now-a-days internet and digital media has become very popular, which made data authentication and data security a challenging task. Digital watermarking was introduced to provide data authentication. Though, it was not enough to prevent the unauthorized access of data by third parties. To prevent unauthorized access, data is encrypted using a secret key known only to the user. This process is known as cryptography. In this paper, an algorithm has been proposed to embed the watermark inside calculated motion vector. The position of watermark bit inside the motion vector will depend on a key provided by user. The correlation values between the four original and recovered experimental video frames are 0.97, 0.98, 0.98 and 0.91 respectively whereas structural similarity index metric (SSIM) between them are 0.97, 0.87, 0.90 and 0.68, respectively. The high correlation values and SSIM shows the effectiveness of the proposed method.

Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners

BACKGROUND AND OBJECTIVES Standardization of the carotid IMT requires a reference marker in ultrasound scans. It has been shown previously that manual reference marker and manually created carotid segments are used for measuring IMT in these segments. Manual methods are tedious, time consuming, subjective, and prone to errors. Bulb edge can be considered as a reference marker for measurements of the cIMT. However, bulb edge can be difficult to locate in ultrasound scans due to: (a) low signal to noise ratio in the bulb region as compared to common carotid artery region; (b) uncertainty of bulb location in craniocaudal direction; and (c) variability in carotid bulb shape and size. This paper presents an automated system (a class of AtheroEdge™ system from AtheroPoint™, Roseville, CA, USA) for locating the bulb edge as a reference marker and further develop segmental-IMT (sIMT) which measures IMT in 10mm segments (namely: s1, s2 and s3) proximal to the bulb edge. METHODS The patented methodology uses an integrated approach which combines carotid geometry and pixel-classification paradigms. The system first finds the bulb edge and then measures the sIMT proximal to the bulb edge. The system also estimates IMT in bulb region (bIMT). The 649 image database consists of varying plaque (light, moderate to heavy), image resolutions, shapes, sizes and ethnicity. RESULTS Our results show that the IMT contributions in different carotid segments are as follows: bulb-IMT 34%, s1-IMT 29.46%, s2-IMT 11.48%, and s3-IMT 12.75%, respectively. We compare our automated results against readers tracings demonstrating the following performance: mean lumen-intima error: 0.01235 ± 0.01224mm, mean media-adventitia error: 0.020933 ± 0.01539mm and mean IMT error: 0.01063 ± 0.0031mm. Our systems Precision of Merit is: 98.23%, coefficient of correlation between automated and Readers IMT is: 0.998 (p-value < 0.0001). These numbers are improved compared to previous publications by Suris group which is automated multi-resolution conventional cIMT. CONCLUSIONS Our fully automated bulb detection system reports 92.67% precision against ideal bulb edge locations as marked by the reader in the bulb transition zone.

Effect of watermarking in vector quantization based image compression

In the modern era of health care and medical diagnostics, medical image contents are needed to be transported through the internet, in a safe and secured way, within time. Image compression is a process of reducing the size of an image without affecting the quality. Image compression reduces the size and helps in quick transportation. Digital watermarking is a process of embedding some secret data in an image for copyright protection, authentication, and channel reliability detection, done without affecting its look. In this work, vector quantization based compression technique is used. It follows LBG clustering algorithm. For watermarking, DCT-DWT based embedding and extraction technique is adopted. At first, retina image was compressed and BPP, SNR, MSE, PSNR values were compared, before and after compression. Later, a binary EPR logo image was embedded into compressed and uncompressed images. Correlation values of original watermark and extracted watermark images were computed and compared for further study.

Solving 0/1 knapsack problem using ant weight lifting algorithm

0/1 knapsack problem is a combinatorial optimization problem. Different approaches like dynamic programming, GA, PSO, ACO etc. have been taken by researchers to solve this problem. In this proposed paper, Ant Weight Lifting algorithm (AWL) is used to solve this problem. An ant can carry food heavier than their own weight. This bio-inspired behavior is taken into consideration and is applied to solve 0/1 Knapsack problem. Obtained results clearly show an improvement in performance and time complexity with respect to popular genetic algorithm based approach.