{"title":"A Robust Compressive Sampling Method for MR Images Based on Partial Scanning and Apodization","authors":"Henry Kiragu, E. Mwangi, G. Kamucha","doi":"10.1109/ISSPIT.2018.8642640","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642640","url":null,"abstract":"This paper proposes a robust, fast Magnetic Resonance Imaging (MRI) reconstruction algorithm. The method is based on Compressive Sampling (CS), profile of the k-space coefficients and sparsity in the wavelet transform domain. It commences with partial acquisition of the k-space of the image followed by random sampling prior to reconstruction in the wavelet transform domain using a greedy algorithm. The reconstructed wavelet coefficients vector is transformed into the full k-space vector of the image by determining its Inverse Discrete Wavelet Transform (IDWT) domain. The vectorized form of the k-space reveals the reconstruction artifacts which makes it easy to design a denoising filter. The artifacts are then suppressed using an apodization function. The denoised coefficients are then reshaped into a k-space matrix prior to being transformed into the reconstructed image using two-dimensional Inverse Discrete Fourier Transform (2D-IDFT). The Structural SIMilarity (SSIM) and the Peak Signal to Noise Ratio (PSNR) quality metrics are used for quality assessment of the output images. Experimental results show that the proposed method yields an average PSNR improvement of 1.4 dB over the Orthogonal Matching Pursuit (OMP) method at 40% measurements. The improvement implies reduction in scan time by approximately 10% for a given image quality.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126742037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Omar Dekhil, F. Taher, F. Khalifa, G. Beache, Adel Said Elmaghraby, A. El-Baz
{"title":"A Novel Fully Automated CAD System for Left Ventricle Volume Estimation","authors":"Omar Dekhil, F. Taher, F. Khalifa, G. Beache, Adel Said Elmaghraby, A. El-Baz","doi":"10.1109/ISSPIT.2018.8642754","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642754","url":null,"abstract":"Left ventricular (LV) volumes, and emptying and filling function remain important indices in conditions such as heart failure. These parameters are derived from the volume curve contained by the inner border of the LV of the heart, throughout the emptying and filling phases of the cardiac cycle, and the peak emptying and filling rates. The gold standard uses the Simpson rule to estimate volume from stacks of short axis images acquired using cine MRI. In this study, a deep learning, automated supervised approach to estimate ventricular volumes is introduced. Unlike prior methods that required hand-crafted image features to segment the inner contour, the proposed approach uses an automatically selected region of interest (ROI), and intelligently determines the optimum features directly from the ROI information. These derived features are then inputted into a deep learning regression model, with the estimated volume as the output results.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"29 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116621580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using Unsupervised Anomaly Detection to Analyze Physiological Signals for Emotion Recognition","authors":"G. Popoola, C. Graves, Phyllis Ford-Booker","doi":"10.1109/ISSPIT.2018.8642690","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642690","url":null,"abstract":"An increase in the collection of physiological signals, whether done implicitly in wearable or IoT device or explicitly in experimental and laboratory environments, creates the need for development of smart systems and tools capable of data analysis with limited expert knowledge. For instances in which an expert is absolutely necessary, a method for filtering out uninteresting data is necessary to reduce the amount of data storage necessary as well as reduce the amount of data the expert will have to analyze. Anomaly detection, specifically unsupervised anomaly detection can be used to design a tool or even as a tool to help remedy these issues. This paper will focus on how unsupervised anomaly detection can be utilized for the development of such systems. A systematic, robust, and customizable approach will be presented and preliminary results will be shown that open the door for future research and algorithm development.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128388743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extraction of Fetal Electrocardiogram signals using Blind Source Extraction Based Parallel Linear Predictor Filter","authors":"L. Taha, E. Abdel-Raheem","doi":"10.1109/ISSPIT.2018.8642620","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642620","url":null,"abstract":"The aim of this paper is to apply the blind source extraction (BSE) parallel linear predictor filter (PLP) algorithm to extract Fetal Electrocardiogram (ECG) signals. First, the ECG signals are modelled using the linear mixture model. Then, the BSE-PLP algorithm is applied to extract both the maternal and fetal ECG signals. Simulation results show that the model is successfully extracting all the unknown FECG and MECG signals, for both synthesized and real ECG data. The algorithm is also tested using the sensitivity and accuracy R-peak extraction metrics. The recorded values for the two metrics are 95.652% and 91.667%, respectively, and show considerable improvements as compared to PCA, FastICA, and SOBI algorithms.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121617092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Pixel-wise Illumination Correction Algorithms for Relative Color Constancy Under the Spectral Domain","authors":"Yunfeng Zhao, C. Elliott, Huiyu Zhou, K. Rafferty","doi":"10.1109/ISSPIT.2018.8642759","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642759","url":null,"abstract":"Achieving color constancy between and within images, i.e., minimizing the color difference between the same object imaged under nonuniform and varied illuminations is crucial for computer vision tasks such as colorimetric analysis and object recognition. Most current methods attempt to solve this by illumination correction on perceptual color spaces. In this paper, we proposed two pixel-wise algorithms to achieve relative color constancy by working under the spectral domain. That is, the proposed algorithms map each pixel to the reflectance ratio of objects appeared in the scene and perform illumination correction in this spectral domain. Also, we proposed a camera calibration technique that calculates the characteristics of a camera without the need of a standard reference. We show that both of the proposed algorithms achieved the best performance on nonuniform illumination correction and relative illumination matching respectively compared to the benchmarked algorithms.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128030507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michael Kronmueller, Dar-jen Chang, Hanqing Hu, A. Desoky
{"title":"A Graph Database of Yelp Dataset Challenge 2018 and Using Cypher for Basic Statistics and Graph Pattern Exploration","authors":"Michael Kronmueller, Dar-jen Chang, Hanqing Hu, A. Desoky","doi":"10.1109/ISSPIT.2018.8642700","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642700","url":null,"abstract":"In this paper, we use Neo4j, a popular graph database, to store the Yelp Dataset for 2018 Challenge, which is a real-world dataset. The graph database provides persistent availability for users to retrieve data using Neo4j Graph Query Language called cypher, for many applications. Users can use Neo4j clients such as Python and R together with cypher and server plugins such as APOC and graph algorithm library to explore the dataset. We explain the basic concepts and applications of cypher graph pattern language. To demonstrate how the database can be used, we use cypher to obtain basic statistics of the dataset and use cypher with graph algorithm library to explore interesting graph patterns such as bipartite and connected components.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115789574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Connor S. Centner, E. Murphy, Caroline M. Stivers, Marie S. Burns, Mariah C. Priddy, Brett R. Janis, M. Menze, Jonathan A. Kopechek
{"title":"Development of a high-performance ultrasonic flow system for cell transformation","authors":"Connor S. Centner, E. Murphy, Caroline M. Stivers, Marie S. Burns, Mariah C. Priddy, Brett R. Janis, M. Menze, Jonathan A. Kopechek","doi":"10.1109/ISSPIT.2018.8705103","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8705103","url":null,"abstract":"Cell transformation is an important process utilized in a wide variety of research and medical applications. Current methods for cell transformation generally depend on viral delivery or other methods which are often limited by inefficiency and/or toxicity. An alternative approach known as sonoporation may avoid these issues. Sonoporation can occur when ultrasound pulses induce microbubble oscillation near cellular membranes causing formation of transient pores. Sonoporation has been shown to enhance molecular delivery to cells. To improve the efficiency and consistency of molecular delivery via sonoporation, we have developed a high-performance ultrasonic flow system which integrates ultrasound and microfluidic technology. One particular application of interest involves loading red blood cells (RBCs) with trehalose for dry preservation. Storage of RBCs is limited by a short shelf-life of 42 days when refrigerated, and frozen storage is limited by the complex process that is required which involves adding and removing glycerol from RBCs before and after freezing them for storage at -80 oC. A technology that enables dry storage of blood at ambient temperature would have significant global impact. A potential solution to achieve this goal is to load RBCs with trehalose which can form a protective barrier around cell membranes during freezing and drying. Trehalose is a sugar molecule found in many organisms that survive freezing and desiccation, but mammalian cells are impermeable to trehalose. Therefore, trehalose must be actively loaded into human cells. In this study we have evaluated the performance of our ultrasonic flow system to load trehalose into RBCs. In addition, this platform technology can potentially be utilized to transform other cell types for a variety of different applications.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131218051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automated Foveal Detection in OCT Scans","authors":"Bilal Hassan, Ramsha Ahmed, Bo Li","doi":"10.1109/ISSPIT.2018.8642788","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642788","url":null,"abstract":"Fovea is a minor area about 1.5 millimeter in diameter located at the center of human retina. It is responsible for permitting 100% visual acuity and is also an important biomarker for analyzing the different retina syndromes. Fovea is dislocated in most of the retina syndromes depending upon the severity of disease progression. Optical Coherence Tomography (OCT) is a modern practice for acquisition of eye scans and visualizing the retinal changes. Usually OCT scan is acquired with fovea at the center but since OCT scan acquisition is a manual process, it is prone to errors in alignment of fovea at the center of the scan. This misaligned OCT scan creates difficulty for ophthalmologists in locating fovea especially when the disease is severely progressed. In this research, we report a computerized algorithm for detecting fovea in OCT scans. Our algorithm examines the thickness vector between the two retina layers. We analyzed three different retinal pathologies in our studies and our algorithm achieved the overall accuracy of 97.5% in localization of fovea.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132784505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Resampling with less than 1/100th Hz Difference Accuracy through On Demand Sample Creation","authors":"Andreas Falkenberg","doi":"10.1109/ISSPIT.2018.8642688","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642688","url":null,"abstract":"This document provides a highly efficient algorithm for resampling sounds and other digitally recorded signals. Specifically very minor changes often require large upsampling and downsampling rates, which consequently lead to very high intermediate sample rates combined with large filter components, which are computationally challenging. Herein we provide a very resource efficient resampling solution, which can be implemented in software, without the need for special hardware by generating samples on demand.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133447389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. E. El-Gamal, M. Elmogy, A. Khalil, M. Ghazal, Hassan H. Soliman, A. Atwan, R. Keynton, G. Barnes, A. El-Baz
{"title":"A Significant Regional-based Diagnosis System for Early Detection of Alzheimer’s Disease Using sMRI Scans","authors":"F. E. El-Gamal, M. Elmogy, A. Khalil, M. Ghazal, Hassan H. Soliman, A. Atwan, R. Keynton, G. Barnes, A. El-Baz","doi":"10.1109/ISSPIT.2018.8642665","DOIUrl":"https://doi.org/10.1109/ISSPIT.2018.8642665","url":null,"abstract":"Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder that targets the central nervous system causing a significant degradation that affects the patient’s life. The early diagnosis of the disease is highly recommended due to a number of factors that can assist in improving the quality of patients’ life. The main aim of this paper is to present a personalized-based computer-aided diagnosis (CAD) system to serve the early diagnosis of AD. This system aims to visualize the disease’s effect in each of the brain regions to provide more assistance in the diagnosis and consequently the treatment procedures. To achieve better performance and precise diagnosis results, the statistical analysis has been applied to define a subset of brain regions that show significant influence by the disease. Evaluating the system’s performance shows an accuracy, specificity, and sensitivity of 96%, 100%, and 93.1%, respectively. These results were validated with the related work and showed promising results in addressing the classification problem of the early diagnosis of AD.","PeriodicalId":361288,"journal":{"name":"2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132175704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}