Xiaobo Thou, Honghui Wang, Jun Wang, G. Hoehn, J. Azok, M. Brennan, S. Hazen, King C. Li, Stephen T. C. Wong
{"title":"Biomarker Discovery for Risk Stratification of Cardiovascular Events using an Improved Genetic Algorithm","authors":"Xiaobo Thou, Honghui Wang, Jun Wang, G. Hoehn, J. Azok, M. Brennan, S. Hazen, King C. Li, Stephen T. C. Wong","doi":"10.1109/LSSA.2006.250393","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250393","url":null,"abstract":"Detection of an optimal panel of biomarkers capable of predicting a patient's risk of major adverse cardiac events (MACE) is of clinical significance. Due to the high dynamic range of the protein concentration in human blood, applying proteomics techniques for protein profiling can generate large arrays of data for development of optimized clinical biomarker panels. The objective of this study is to discover a panel of biomarkers for predicting risk of MACE in subjects reliably. The development of immunoassay can only tolerate the complexity of the prediction model with less than ten selected biomarkers. Hence, traditional optimization methods, such as genetic algorithm, cannot be used to derive a solution in such a high-dimensional space. In this paper, we propose an improved genetic algorithm with the local floating searching technique to discover a subset of biomarkers with improved prognostic values for prediction of MACE. The proposed method has been compared with standard genetic algorithm and other feature selection approaches based on the MACE prediction experiments","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121329244","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":"Robust Bioinformatics Recognition with VLSI Biochip Microsystem","authors":"Jaw-Chyng L. Lue, W. Fang","doi":"10.1109/LSSA.2006.250384","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250384","url":null,"abstract":"A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR) amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122460245","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}
Jianfeng Lu, Tianming Liu, Jingxin Nie, Jie Ding, Jinmin Zhu, Jingyu Yang, Lei Guo, W. Xia, Stephen T. C. Wong
{"title":"Automated Quantitation of Zebrafish Somites in High-Throughput Screens","authors":"Jianfeng Lu, Tianming Liu, Jingxin Nie, Jie Ding, Jinmin Zhu, Jingyu Yang, Lei Guo, W. Xia, Stephen T. C. Wong","doi":"10.1109/LSSA.2006.250389","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250389","url":null,"abstract":"With the availability of high-throughput imaging machines and large number of zebrafish embryos, zebrafish is by far one of the most cost-effective vertebrate systems for high-throughput or high-content screens. With the tremendous amount of images generated from large numbers of zebrafish, computerized image analysis for accurate and efficient data interpretation becomes essential. This paper presents an automated algorithm for quantitation of zebrafish somite in high-throughput screen. Preliminary evaluation results are shown to demonstrate the performance of the algorithm. This algorithm has been integrated into our CBI platform","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124813105","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":"Bio-inspired Systems in Speech Perception: An overview and a study case","authors":"P. Gómez, R. Martínez, V. Rodellar, J. Ferrández","doi":"10.1109/LSSA.2006.250388","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250388","url":null,"abstract":"Bio-inspired systems and methods have pervaded the life of modern technology during the last twenty years at a steady but faster stroll. Bio-inspiration dates from long, although it has been during the last fifty years with the better knowledge of the nervous systems functions, components and structures when it has come to a state where its influence in recent developments is more complex everyday. Nevertheless bio-inspiration is not free from controversy. Through this paper its fundamentals, characteristics and development is analyzed in relation with modern tendencies in cognitive audio processing","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"435 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123867366","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}
G. Laevsky, W. Warger, M. Rajadhyaksha, C. DiMarzio
{"title":"Multi-Modal Microscope for Biomedical Research","authors":"G. Laevsky, W. Warger, M. Rajadhyaksha, C. DiMarzio","doi":"10.1109/LSSA.2006.250433","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250433","url":null,"abstract":"Microscopists often use different instruments to exploit the different types of contrast available in complicated biological media. A new multi-modal microscope makes it possible to acquire the different images nearly simultaneously, without moving the specimen. Rather than simply observing different contrast mechanisms in a specimen which has been moved, the user can now obtain registered images in different modes for image fusion or data fusion. The first application area is imaging of embryo health","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123587861","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":"High-speed three-dimensional fluorescence imaging of neural activity","authors":"T. Holy, T.F. Holekam, D. Turaga","doi":"10.1109/LSSA.2006.250367","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250367","url":null,"abstract":"Our progress in understanding the function of the nervous system is, in many ways, limited by our ability to record neural activity. While there has been considerable progress in imaging at the extremes of length scales (e.g., whole brain imaging by fMRI and sub-cellular resolution by two-photon microscopy), there is a need for optical techniques to record the individual activities of large populations of neurons in intact circuits. Current techniques such as epifluorescence microscopy have reasonable time resolution but suffer from signal-to-background problems when viewing thick samples, while confocal techniques are limited in time resolution and/or photon efficiency. To address some of these limitations, we have developed a novel form of microscopy for high-speed three-dimensional fluorescence imaging. Using this technique, entire stacks of high signal-to-noise images can be acquired in seconds. We are currently using this technique to record the activity of populations of sensory neurons in the mouse olfactory system","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122779476","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":"Comparative Evaluation of classifiers and Feature Selection Methods for Mass Screening in Digitized Mammograms","authors":"Chuin-Mu Wang, Sheng-Chih Yang, P. Chung","doi":"10.1109/LSSA.2006.250418","DOIUrl":"https://doi.org/10.1109/LSSA.2006.250418","url":null,"abstract":"In this paper, three groups of characteristics related to mass texture are adopted, namely, SGLD (spatial gray level dependence), TS (texture spectrum) and TFCM (texture feature coding method) to describe the characteristics of masses and normal textures on digitized mammograms. Next, under the testing by classifiers, three feature selection methods - SBS (sequential backward selection), SFS (sequential forward selection) and SFSM (sequential floating search method) are used to find out suboptimal subset from 19 features in order to improve the performance of mass detection. Finally, two classifiers PNN (probabilistic neural network) and SVM (support vector machine) are applied and their performances are compared","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133638557","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}
M. Mollazadeh, K. Murari, C. Sauer, M. Stanaćević, N. Thakor, G. Cauwenberghs
{"title":"Wireless Integrated Voltametric and Amperometric Biosensing","authors":"M. Mollazadeh, K. Murari, C. Sauer, M. Stanaćević, N. Thakor, G. Cauwenberghs","doi":"10.1109/lssa.2006.250372","DOIUrl":"https://doi.org/10.1109/lssa.2006.250372","url":null,"abstract":"Central nervous system (CNS) uses the interplay between signals of different modalities to transfer and process information. Neurological events are characterized by changes in both neurochemical concentrations and the electrical activity of neurons. Electrophysiological and neurochemical events are highly correlated as one causes the other and vice-versa. The ability to simultaneously record electrical and chemical activity is of considerable research and diagnostic importance. Here, we present a hardware implementation for wireless power and clock transfer to and serial transmission of digitized neurochemical and electrophysiological data from sensors over one RF link. The idea can be extended to sensors of different modalities having widely different data rates. Neurochemical data are acquired in real-time from a custom multichannel very large scale integrated (VLSI) potentiostat chip at 5 Hz. Field potential data were sampled at 400 Hz. A custom VLSI chip powers up and supplies clocks to the potentiostat and telemeters the multiplexed data. All the chips were fabricated in AMI 3M-2P 0.5mu CMOS process. We demonstrate successful operation of the system with wireless powering and telemetry of the multiplexed data","PeriodicalId":360097,"journal":{"name":"2006 IEEE/NLM Life Science Systems and Applications Workshop","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127664196","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}