In standard analysis of cardiac models, typically one variable - usually the trans-membrane potential - is used in the generation of visualizations. However, all but the most basic models have many state variables at each node, information that is not used when visualizing the output of the model. In this paper, we present a novel approach to visualizing the entire state of a 2D cardiac virtual tissue
{"title":"Multi-Variate Visualization of Cardiac Virtual Tissue","authors":"J. Handley, K. Brodlie, R. Clayton","doi":"10.1109/CBMS.2006.120","DOIUrl":"https://doi.org/10.1109/CBMS.2006.120","url":null,"abstract":"In standard analysis of cardiac models, typically one variable - usually the trans-membrane potential - is used in the generation of visualizations. However, all but the most basic models have many state variables at each node, information that is not used when visualizing the output of the model. In this paper, we present a novel approach to visualizing the entire state of a 2D cardiac virtual tissue","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122759303","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}
A. Tsymbal, Mykola Pechenizkiy, P. Cunningham, S. Puuronen
In the real world concepts and data distributions are often not stable but change with time. This problem, known as concept drift, complicates the task of learning a model from data and requires special approaches, different from commonly used techniques, which treat arriving instances as equally important contributors to the target concept. Among the most popular and effective approaches to handle concept drift is ensemble learning, where a set of models built over different time periods is maintained and the best model is selected or the predictions of models are combined. In this paper we consider the use of an ensemble integration technique that helps to better handle concept drift at the instance level. Our experiments with real-world antibiotic resistance data demonstrate that dynamic integration of classifiers built over small time intervals can be more effective than globally weighted voting which is currently the most commonly used integration approach for handling concept drift with ensembles
{"title":"Handling Local Concept Drift with Dynamic Integration of Classifiers: Domain of Antibiotic Resistance in Nosocomial Infections","authors":"A. Tsymbal, Mykola Pechenizkiy, P. Cunningham, S. Puuronen","doi":"10.1109/CBMS.2006.94","DOIUrl":"https://doi.org/10.1109/CBMS.2006.94","url":null,"abstract":"In the real world concepts and data distributions are often not stable but change with time. This problem, known as concept drift, complicates the task of learning a model from data and requires special approaches, different from commonly used techniques, which treat arriving instances as equally important contributors to the target concept. Among the most popular and effective approaches to handle concept drift is ensemble learning, where a set of models built over different time periods is maintained and the best model is selected or the predictions of models are combined. In this paper we consider the use of an ensemble integration technique that helps to better handle concept drift at the instance level. Our experiments with real-world antibiotic resistance data demonstrate that dynamic integration of classifiers built over small time intervals can be more effective than globally weighted voting which is currently the most commonly used integration approach for handling concept drift with ensembles","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"70 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131748417","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}
Advances in proteomics and protein expression techniques have lead to the elucidation of large amounts of protein data. Various data mining algorithms and mathematical models provide methods for analyzing this data; however, there are two issues that need to be addressed: (1) the need for standards for defining protein data description and exchange formats so they can be exchanged across the World Wide Web, and also read into data mining software in a consistent format and (2) eliminating errors which arise with the data integration methodologies for complex queries. Protein ontology is designed to meet these needs by providing a structured protein data specification for protein data representation. Protein ontology is a standard for representing protein data in a way that helps in defining data integration and data mining models for protein structure and function. In this paper we summarize the structure of protein ontology we developed earlier, its current applications to various protein families, and its future development
{"title":"Advances in Protein Ontology Project","authors":"A. Sidhu, T. Dillon, E. Chang","doi":"10.1109/CBMS.2006.35","DOIUrl":"https://doi.org/10.1109/CBMS.2006.35","url":null,"abstract":"Advances in proteomics and protein expression techniques have lead to the elucidation of large amounts of protein data. Various data mining algorithms and mathematical models provide methods for analyzing this data; however, there are two issues that need to be addressed: (1) the need for standards for defining protein data description and exchange formats so they can be exchanged across the World Wide Web, and also read into data mining software in a consistent format and (2) eliminating errors which arise with the data integration methodologies for complex queries. Protein ontology is designed to meet these needs by providing a structured protein data specification for protein data representation. Protein ontology is a standard for representing protein data in a way that helps in defining data integration and data mining models for protein structure and function. In this paper we summarize the structure of protein ontology we developed earlier, its current applications to various protein families, and its future development","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121475660","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}
Much of the data in bioinformatics and data relationships can be represented by graphs. General purpose graph drawing tools are available, but not all are adequate for bioinformatics graphs as these tend to grow quite large. The specific purpose for our research was to investigate the applicability of existing graph drawing tools for visualization of very large phylogenetic trees. In this paper we describe some of the general functions and features that are required for exploring and comparing graphs in bioinformatics. We include a description of a selection of existing tools, to give an overview of the current abilities of graph drawing software and to analyze their advantages and drawbacks in the bioinformatics domain
{"title":"Graph Drawing Tools for Bioinformatics Research: An Overview","authors":"K. Wiese, Christina Eicher","doi":"10.1109/CBMS.2006.92","DOIUrl":"https://doi.org/10.1109/CBMS.2006.92","url":null,"abstract":"Much of the data in bioinformatics and data relationships can be represented by graphs. General purpose graph drawing tools are available, but not all are adequate for bioinformatics graphs as these tend to grow quite large. The specific purpose for our research was to investigate the applicability of existing graph drawing tools for visualization of very large phylogenetic trees. In this paper we describe some of the general functions and features that are required for exploring and comparing graphs in bioinformatics. We include a description of a selection of existing tools, to give an overview of the current abilities of graph drawing software and to analyze their advantages and drawbacks in the bioinformatics domain","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114973413","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}
Luciano Silva, O. Bellon, Rubisley de P. Lemes, J. Meira, M. Cat
The FootScanAge is a non-invasive, more accurate novel approach to automatically estimate the gestational age of newborns. This task is performed by the computational analysis of the features from the newborn plantar surface. The FootScanAge system is composed by two main tools: (1) image processing and (2) data mining. In this paper, we present the image processing tool that extract features of the plantar surface by applying image processing techniques developed to work on the footprint of the newborns, which present some singular characteristics. We included the results that support the determination of an adequate gestational age score by using the data mining tool
{"title":"An Image Processing Tool to Support Gestational Age Determination","authors":"Luciano Silva, O. Bellon, Rubisley de P. Lemes, J. Meira, M. Cat","doi":"10.1109/CBMS.2006.38","DOIUrl":"https://doi.org/10.1109/CBMS.2006.38","url":null,"abstract":"The FootScanAge is a non-invasive, more accurate novel approach to automatically estimate the gestational age of newborns. This task is performed by the computational analysis of the features from the newborn plantar surface. The FootScanAge system is composed by two main tools: (1) image processing and (2) data mining. In this paper, we present the image processing tool that extract features of the plantar surface by applying image processing techniques developed to work on the footprint of the newborns, which present some singular characteristics. We included the results that support the determination of an adequate gestational age score by using the data mining tool","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133776791","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}
Previous studies have shown that the photoplethysmogram (PPG) may be a useful tool for the noninvasive detection of hypovolemia. The focus has been on determining if frequency analysis of the respiratory induced variations of the PPG can be used as an indicator of blood volume. In this preliminary study, we evaluate these frequency analysis techniques for two subjects undergoing lower body negative pressure (LBNP) induced hypovolemia. Using Matlabreg-based software the power of the respiratory component and heart rate component were calculated using the periodogram method for spectral estimation. Consistent with other studies our algorithms were able to automatically detect changes in the respiratory variations. We found a significant increase in the respiratory variations in the PPG during simulated hypovolemia. By taking the ratio of the respiratory power to the heart rate power we consistently detected hypovolemia in subjects corresponding to sequestration of approximately 2 liters of blood (LBNP >70 mm Hg). The increase in this ratio occurred before significant change in blood pressure or tachycardia were observed
{"title":"A Preliminary Study of Respiratory Variations in the Photoplethysmogram during Lower Body Negative Pressure","authors":"S. Wendelken, S. P. Linder, Sue McGrath","doi":"10.1109/CBMS.2006.23","DOIUrl":"https://doi.org/10.1109/CBMS.2006.23","url":null,"abstract":"Previous studies have shown that the photoplethysmogram (PPG) may be a useful tool for the noninvasive detection of hypovolemia. The focus has been on determining if frequency analysis of the respiratory induced variations of the PPG can be used as an indicator of blood volume. In this preliminary study, we evaluate these frequency analysis techniques for two subjects undergoing lower body negative pressure (LBNP) induced hypovolemia. Using Matlabreg-based software the power of the respiratory component and heart rate component were calculated using the periodogram method for spectral estimation. Consistent with other studies our algorithms were able to automatically detect changes in the respiratory variations. We found a significant increase in the respiratory variations in the PPG during simulated hypovolemia. By taking the ratio of the respiratory power to the heart rate power we consistently detected hypovolemia in subjects corresponding to sequestration of approximately 2 liters of blood (LBNP >70 mm Hg). The increase in this ratio occurred before significant change in blood pressure or tachycardia were observed","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128287670","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}
A. D. Luz, D. Abdala, A. V. Wangenheim, E. Comunello
This paper presents a hybrid approach to perform content-based retrieval on medical image databases. It takes advantage of a pre-processed case base that is batch updated. DICOM information is used to perform pre-filtering to speed up the retrieval process and an image processing knowledge base is used to dynamically reconfigure the most appropriated image processing procedures to perform the image feature extraction. It shows that pre-filtering can speed up considerably the retrieval process and also that some image features produce very similar results what leads to future work on defining the needed digital image processing knowledge base
{"title":"Analyzing DICOM and non-DICOM Features in Content-Based Medical Image Retrieval: A Multi-Layer Approach","authors":"A. D. Luz, D. Abdala, A. V. Wangenheim, E. Comunello","doi":"10.1109/CBMS.2006.45","DOIUrl":"https://doi.org/10.1109/CBMS.2006.45","url":null,"abstract":"This paper presents a hybrid approach to perform content-based retrieval on medical image databases. It takes advantage of a pre-processed case base that is batch updated. DICOM information is used to perform pre-filtering to speed up the retrieval process and an image processing knowledge base is used to dynamically reconfigure the most appropriated image processing procedures to perform the image feature extraction. It shows that pre-filtering can speed up considerably the retrieval process and also that some image features produce very similar results what leads to future work on defining the needed digital image processing knowledge base","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906199","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}
There currently is no clinically accepted noninvasive technique for detecting moderate blood loss. Clinicians instead normally rely on lagging indicators such as blood pressure and tachycardia. We propose to use changes in the morphology of the respiratory induced variation in the photoplethysmogram (PPG) to detect moderate hypovolemia in non-ventilated subjects. These changes were characterized by two statistically robust metrics that were developed to characterize the top and bottom envelope of the PPG. The first metric detects when the height of the top envelope becomes greater than the difference between the minimum of the top envelope and the maximum of the bottom envelope. The second metric robustly detects when the upper and lower envelopes synchronously rise or fall. The use of these metrics was then validated in nonintubated healthy volunteers with a lower-body negative pressure (LBNP) chamber which induces central hypovolemia by sequestering blood in the hips and lower extremities. Hypovolemia corresponding to sequestration of more than 1 liter of blood (LBNP > 60 mmHg) was consistently detected using these metrics before significant change in blood pressure, or tachycardia are observed
{"title":"Using the Morphology of the Photoplethysmogram Envelope to Automatically Detect Hypovolemia","authors":"S. P. Linder, S. Wendelken","doi":"10.1109/CBMS.2006.167","DOIUrl":"https://doi.org/10.1109/CBMS.2006.167","url":null,"abstract":"There currently is no clinically accepted noninvasive technique for detecting moderate blood loss. Clinicians instead normally rely on lagging indicators such as blood pressure and tachycardia. We propose to use changes in the morphology of the respiratory induced variation in the photoplethysmogram (PPG) to detect moderate hypovolemia in non-ventilated subjects. These changes were characterized by two statistically robust metrics that were developed to characterize the top and bottom envelope of the PPG. The first metric detects when the height of the top envelope becomes greater than the difference between the minimum of the top envelope and the maximum of the bottom envelope. The second metric robustly detects when the upper and lower envelopes synchronously rise or fall. The use of these metrics was then validated in nonintubated healthy volunteers with a lower-body negative pressure (LBNP) chamber which induces central hypovolemia by sequestering blood in the hips and lower extremities. Hypovolemia corresponding to sequestration of more than 1 liter of blood (LBNP > 60 mmHg) was consistently detected using these metrics before significant change in blood pressure, or tachycardia are observed","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446651","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}
This paper reports the construction of an agent-based model that has been used to study humanitarian assistance policies executed by governments and non-governmental organizations (NGOs) in a synthetic environment. We create intelligent agents representing institutions, organizations, individuals, infrastructure, and governments. The resulting interactions and emergent behaviors are analyzed using a central composite design of experiments with five factors. The results indicate that the introduction of actions on NGOs leads to a change in the peripheral/regional environment and refugee wellbeing. This is due to the changes produced in refugees' perception of basic needs, social needs, and security, as well as the fluctuations in the supply of medical and personnel resources
{"title":"Modeling the Health of Refugee Camps: An Agent-Based Computational Approach","authors":"James Anderson, A. Chaturvedi, Mike Cibulskis","doi":"10.1109/CBMS.2006.118","DOIUrl":"https://doi.org/10.1109/CBMS.2006.118","url":null,"abstract":"This paper reports the construction of an agent-based model that has been used to study humanitarian assistance policies executed by governments and non-governmental organizations (NGOs) in a synthetic environment. We create intelligent agents representing institutions, organizations, individuals, infrastructure, and governments. The resulting interactions and emergent behaviors are analyzed using a central composite design of experiments with five factors. The results indicate that the introduction of actions on NGOs leads to a change in the peripheral/regional environment and refugee wellbeing. This is due to the changes produced in refugees' perception of basic needs, social needs, and security, as well as the fluctuations in the supply of medical and personnel resources","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133708556","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}
L. Long, Sameer Kiran Antani, J. Jeronimo, M. Schiffman, M. Bopf, Leif Neve, Carl Cornwell, S. Budihas, G. Thoma
The Communications Engineering Branch of the National Library of Medicine is collaborating with the National Cancer Institute (NCI) in developing applications for medical education, research, and disease screening for precancer detection in the uterine cervix. These applications include (1) expert marking/labeling of tissue regions, (2) Web viewing/interpretation of histology images, (3) image database/retrieval, and (4) training/testing in clinical image interpretation. Initial NCI studies have been conducted in expert cervicography marking and histology evaluation. We are working toward making cervix images searchable by content-based image retrieval (CBIR). Image pre-processing to remove specular reflection artifacts has achieved 90% success (120 images). Similar results have been obtained for automated location of cervix regions, using Gaussian mixture modeling (GMM) with Lab color and one geometric feature. We describe initial classification experiments to discriminate clinically significant tissue, using RGB, HSV, Lab, and YCbCr color models, texture measures, and GMM, fuzzy C-means, and deterministic annealing algorithms
{"title":"Technology for Medical Education, Research, and Disease Screening by Exploitation of Biomarkers in a Large Collection of Uterine Cervix Images","authors":"L. Long, Sameer Kiran Antani, J. Jeronimo, M. Schiffman, M. Bopf, Leif Neve, Carl Cornwell, S. Budihas, G. Thoma","doi":"10.1109/CBMS.2006.154","DOIUrl":"https://doi.org/10.1109/CBMS.2006.154","url":null,"abstract":"The Communications Engineering Branch of the National Library of Medicine is collaborating with the National Cancer Institute (NCI) in developing applications for medical education, research, and disease screening for precancer detection in the uterine cervix. These applications include (1) expert marking/labeling of tissue regions, (2) Web viewing/interpretation of histology images, (3) image database/retrieval, and (4) training/testing in clinical image interpretation. Initial NCI studies have been conducted in expert cervicography marking and histology evaluation. We are working toward making cervix images searchable by content-based image retrieval (CBIR). Image pre-processing to remove specular reflection artifacts has achieved 90% success (120 images). Similar results have been obtained for automated location of cervix regions, using Gaussian mixture modeling (GMM) with Lab color and one geometric feature. We describe initial classification experiments to discriminate clinically significant tissue, using RGB, HSV, Lab, and YCbCr color models, texture measures, and GMM, fuzzy C-means, and deterministic annealing algorithms","PeriodicalId":208693,"journal":{"name":"19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442084","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：