C. Fuchsberger, H. Hübl, G. Schäfer, A. Pelzer, G. Bartsch, H. Klocker, Nicola Barbarini, R. Bellazzi, W. Wieder, G. Bonn
Spatial proteomic profiling of tissue sections provides in situ molecular analysis of proteins and peptides. Analysis and visualization of these high-dimensional data cubes is challenging. We present a methodology for this task based on a novel developed algorithm for the feature identification and reduction step. To show the validity of our approach, we analyzed prostate cancer tissue sections with an adapted kernel-density based clustering algorithm.
{"title":"Analysis and Visualization of Spatial Proteomic Data for Tissue Characterization","authors":"C. Fuchsberger, H. Hübl, G. Schäfer, A. Pelzer, G. Bartsch, H. Klocker, Nicola Barbarini, R. Bellazzi, W. Wieder, G. Bonn","doi":"10.1109/CBMS.2008.119","DOIUrl":"https://doi.org/10.1109/CBMS.2008.119","url":null,"abstract":"Spatial proteomic profiling of tissue sections provides in situ molecular analysis of proteins and peptides. Analysis and visualization of these high-dimensional data cubes is challenging. We present a methodology for this task based on a novel developed algorithm for the feature identification and reduction step. To show the validity of our approach, we analyzed prostate cancer tissue sections with an adapted kernel-density based clustering algorithm.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127537775","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. Bubak, T. Gubała, M. Malawski, B. Baliś, W. Funika, Tomasz Bartyński, Eryk Ciepiela, D. Harezlak, M. Kasztelnik, J. Kocot, Dariusz Król, P. Nowakowski, M. Pelczar, J. Wach, M. Assel, Alfredo Tirado-Ramos
The ViroLab Virtual Laboratory is a collaborative platform for scientists representing multiple fields of expertise while working together on common scientific goals. This environment makes it possible to combine efforts of computer scientists, virology and epidemiology experts and experienced physicians to support future advances in HIV-related research and treatment. The paper explains the challenges involved in building a modern, inter-organizational platform to support science and gives an overview of solutions to these challenges. Examples of real-world problems applied in the presented environment are also described to prove the feasibility of the solution.
{"title":"Virtual Laboratory for Development and Execution of Biomedical Collaborative Applications","authors":"M. Bubak, T. Gubała, M. Malawski, B. Baliś, W. Funika, Tomasz Bartyński, Eryk Ciepiela, D. Harezlak, M. Kasztelnik, J. Kocot, Dariusz Król, P. Nowakowski, M. Pelczar, J. Wach, M. Assel, Alfredo Tirado-Ramos","doi":"10.1109/CBMS.2008.47","DOIUrl":"https://doi.org/10.1109/CBMS.2008.47","url":null,"abstract":"The ViroLab Virtual Laboratory is a collaborative platform for scientists representing multiple fields of expertise while working together on common scientific goals. This environment makes it possible to combine efforts of computer scientists, virology and epidemiology experts and experienced physicians to support future advances in HIV-related research and treatment. The paper explains the challenges involved in building a modern, inter-organizational platform to support science and gives an overview of solutions to these challenges. Examples of real-world problems applied in the presented environment are also described to prove the feasibility of the solution.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126003282","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}
The performance of a classification system is sometimes unsatisfactory for the needs of real applications. In these cases, the measure of classification reliability should be useful since it takes into account the many issues that influence the achievement of satisfactory results. The most common choice for confidence evaluation consists in using the confusion matrix estimated during the learning phase. As a consequence, the same reliability value is associated with every decision attributing a sample to the same class. In this respect, this paper proposes and compares three different reliability estimators of each classification act of classification systems that belong to the one-per-class framework. They are based on the reliabilities provided by each dichotomizer and are independent of the binary module design. Their performance have been assessed and ranked on private and public medical datasets, showing that one of the estimators outperforms the others.
{"title":"Reliability Estimators for Classification by Decomposition Method: Experiments in the Medical Domain","authors":"P. Soda, G. Iannello","doi":"10.1109/CBMS.2008.142","DOIUrl":"https://doi.org/10.1109/CBMS.2008.142","url":null,"abstract":"The performance of a classification system is sometimes unsatisfactory for the needs of real applications. In these cases, the measure of classification reliability should be useful since it takes into account the many issues that influence the achievement of satisfactory results. The most common choice for confidence evaluation consists in using the confusion matrix estimated during the learning phase. As a consequence, the same reliability value is associated with every decision attributing a sample to the same class. In this respect, this paper proposes and compares three different reliability estimators of each classification act of classification systems that belong to the one-per-class framework. They are based on the reliabilities provided by each dichotomizer and are independent of the binary module design. Their performance have been assessed and ranked on private and public medical datasets, showing that one of the estimators outperforms the others.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"425 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122800352","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}
Shuai Zhang, S. McClean, B. Scotney, Xin Hong, C. Nugent, M. Mulvenna
Assistive technology in smart homes for elderly people with Alzheimer's disease is needed to support 'aging in place'. In this paper, we propose a probabilistic learning approach to characterise behavioural patterns for multi-inhabitants in smart homes. Decision support is then provided to monitor and assist patients to complete activities of daily living (ADL). Reasoning is based on the learned profiles and partially observed low-level sensors information. Data are stored in the proposed snow-flake schema based on homeML (an XML based schema for representation of information within smart homes). A laboratory has been developed for studying activities of 'making drinks' for multiple users. Evaluations of our learning and decision support approach are carried out on both real and simulated data. The potential of our approach to support assistive living and home-health monitoring of Alzheimer's patients is demonstrated.
{"title":"Decision Support for Alzheimer's Patients in Smart Homes","authors":"Shuai Zhang, S. McClean, B. Scotney, Xin Hong, C. Nugent, M. Mulvenna","doi":"10.1109/CBMS.2008.16","DOIUrl":"https://doi.org/10.1109/CBMS.2008.16","url":null,"abstract":"Assistive technology in smart homes for elderly people with Alzheimer's disease is needed to support 'aging in place'. In this paper, we propose a probabilistic learning approach to characterise behavioural patterns for multi-inhabitants in smart homes. Decision support is then provided to monitor and assist patients to complete activities of daily living (ADL). Reasoning is based on the learned profiles and partially observed low-level sensors information. Data are stored in the proposed snow-flake schema based on homeML (an XML based schema for representation of information within smart homes). A laboratory has been developed for studying activities of 'making drinks' for multiple users. Evaluations of our learning and decision support approach are carried out on both real and simulated data. The potential of our approach to support assistive living and home-health monitoring of Alzheimer's patients is demonstrated.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"95 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113975268","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}
The LENUS [LE08] master patient index in combination with the electronic patient record and a healthcare service bus enables the implementation of a small lean reference system for patient management. Via a modern client all ADT functionalities can be applied without a leading administrative software system. Based on service oriented architecture the index is used in combination with a preconfigured open source healthcare bus. It uses the association based search engine of the LENUS HCM software suite [LE06] to reach a high re-identification rate of existing patients. Only few cases must be processed manually in the LENUS clearing component.
{"title":"The LENUS Master Patient Index: Combining Hospital Content Management with a Healthcare Service Bus","authors":"D. Krechel, Markus Hartbauer","doi":"10.1109/CBMS.2008.107","DOIUrl":"https://doi.org/10.1109/CBMS.2008.107","url":null,"abstract":"The LENUS [LE08] master patient index in combination with the electronic patient record and a healthcare service bus enables the implementation of a small lean reference system for patient management. Via a modern client all ADT functionalities can be applied without a leading administrative software system. Based on service oriented architecture the index is used in combination with a preconfigured open source healthcare bus. It uses the association based search engine of the LENUS HCM software suite [LE06] to reach a high re-identification rate of existing patients. Only few cases must be processed manually in the LENUS clearing component.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128116323","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}
S. Wurst, Gregor Lamla, J. Schlundt, Randi Karlsen, K. Kuhn
Integration of data from heterogeneous sources has been a problem in medicine over decades. In the post genomicera, new opportunities have emerged and created new challenges, e.g. when genotypes and phenotypes have to be associated. We have developed a concept for integrating data from systems in clinical and in research environments, with a specific focus on process support. Our solution is following a mediator based approach, realized in a service-oriented architecture using web services. In order to cope with complexity and changing requirements, and to make early user feedback possible, a tool-based agile software development process has been carried out for building a prototype. Open-source technology has been used for the implementation.
{"title":"A Service-Oriented Architectural Framework for the Integration of Information Systems in Clinical Research","authors":"S. Wurst, Gregor Lamla, J. Schlundt, Randi Karlsen, K. Kuhn","doi":"10.1109/CBMS.2008.91","DOIUrl":"https://doi.org/10.1109/CBMS.2008.91","url":null,"abstract":"Integration of data from heterogeneous sources has been a problem in medicine over decades. In the post genomicera, new opportunities have emerged and created new challenges, e.g. when genotypes and phenotypes have to be associated. We have developed a concept for integrating data from systems in clinical and in research environments, with a specific focus on process support. Our solution is following a mediator based approach, realized in a service-oriented architecture using web services. In order to cope with complexity and changing requirements, and to make early user feedback possible, a tool-based agile software development process has been carried out for building a prototype. Open-source technology has been used for the implementation.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132540776","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}
In this paper, we present a random effects approach to modelling of patient pathways with an application to the neonatal unit of a large metropolitan hospital. This approach could be used to identify pathways such as those resulting in high probabilities of death/survival, and to estimate cost of care or length of stay. Patient-specific discharge probabilities could also be predicted as a function of the random effect. We also investigate the sensitivity of our modelling results to random effects distribution assumptions.
{"title":"A Random Effects Sensitivity Analysis for Patient Pathways Model","authors":"Shola Adeyemi, T. Chaussalet","doi":"10.1109/CBMS.2008.49","DOIUrl":"https://doi.org/10.1109/CBMS.2008.49","url":null,"abstract":"In this paper, we present a random effects approach to modelling of patient pathways with an application to the neonatal unit of a large metropolitan hospital. This approach could be used to identify pathways such as those resulting in high probabilities of death/survival, and to estimate cost of care or length of stay. Patient-specific discharge probabilities could also be predicted as a function of the random effect. We also investigate the sensitivity of our modelling results to random effects distribution assumptions.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130717702","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 computerized classification based on morphologic and texture features is proposed to increase the accuracy of the ultrasonic diagnosis of breast tumors. Firstly, tumor boundaries are obtained with the gray-level threshold segmentation algorithm and the dynamic programming method. Then five morphologic features and two texture features are extracted. Finally, an artificial neural network with the error back propagation algorithm is applied to classify breast tumors as benign or malignant. Experiments on 168 cases show that the proposed system yields the high accuracy, sensitivity and specificity. Therefore, it is concluded that this system performs well in the ultrasonic classification of breast tumors.
{"title":"Computerized Classification of Breast Tumors with Morphologic and Texture Features of Ultrasonic Images","authors":"Yuanyuan Wang, Jialin Shen, Yi Guo, Wen Wang","doi":"10.1109/CBMS.2008.10","DOIUrl":"https://doi.org/10.1109/CBMS.2008.10","url":null,"abstract":"A computerized classification based on morphologic and texture features is proposed to increase the accuracy of the ultrasonic diagnosis of breast tumors. Firstly, tumor boundaries are obtained with the gray-level threshold segmentation algorithm and the dynamic programming method. Then five morphologic features and two texture features are extracted. Finally, an artificial neural network with the error back propagation algorithm is applied to classify breast tumors as benign or malignant. Experiments on 168 cases show that the proposed system yields the high accuracy, sensitivity and specificity. Therefore, it is concluded that this system performs well in the ultrasonic classification of breast tumors.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132571503","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}
Interactomics is the study of the Interactome, i.e. the whole set of macromolecular interactions within a cell. Proteins interact among them and different interactions are represented as graphs named Protein to Protein Interaction (PPI) networks. The interest in analyzing PPI networks is related to the possibility of predicting PPI properties on the basis of global properties of the graph (e.g. verify if homology among species involves PPI similarity), or to find set of protein interactions that has a biological meaning. The prediction of protein complexes has been faced in the last years by using different clustering algorithms. The Markov Clustering algorithm (MCL) is a method that presents one of the best performance but is currently available only as a stand alone application with a simple command-line interface available only on Linux platforms. Following a trend in bioinformatics, we provide a web portal (myMCL) allowing remote users to access MCL functions through the Internet. myMCL enables user to submit a job and stores results in a local database for further processing.
{"title":"myMCL: A Web Portal for Protein Complexes Prediction","authors":"M. Cannataro, P. Guzzi, P. Veltri","doi":"10.1109/CBMS.2008.113","DOIUrl":"https://doi.org/10.1109/CBMS.2008.113","url":null,"abstract":"Interactomics is the study of the Interactome, i.e. the whole set of macromolecular interactions within a cell. Proteins interact among them and different interactions are represented as graphs named Protein to Protein Interaction (PPI) networks. The interest in analyzing PPI networks is related to the possibility of predicting PPI properties on the basis of global properties of the graph (e.g. verify if homology among species involves PPI similarity), or to find set of protein interactions that has a biological meaning. The prediction of protein complexes has been faced in the last years by using different clustering algorithms. The Markov Clustering algorithm (MCL) is a method that presents one of the best performance but is currently available only as a stand alone application with a simple command-line interface available only on Linux platforms. Following a trend in bioinformatics, we provide a web portal (myMCL) allowing remote users to access MCL functions through the Internet. myMCL enables user to submit a job and stores results in a local database for further processing.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131399683","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}
Soontharee Koompairojn, A. Petkova, K. Hua, Pichest Metarugcheep
In this paper, a semi-automatic segmentation technique for brain mass-like lesions in magnetic resonance (MR) image sequences is proposed. With the graphical user interface of ImageJ, the user can interactively determine the lesion volume. The user needs to only provide the tumor contour on one MR slice using LiveWire, after which the system automatically segments and determines the gross lesion volume. Our experimental results, based on MR image sequences from Prasat Neurological Institute, indicate that the proposed system is effective.
{"title":"Semi-Automatic Segmentation and Volume Determination of Brain Mass-Like Lesion","authors":"Soontharee Koompairojn, A. Petkova, K. Hua, Pichest Metarugcheep","doi":"10.1109/CBMS.2008.115","DOIUrl":"https://doi.org/10.1109/CBMS.2008.115","url":null,"abstract":"In this paper, a semi-automatic segmentation technique for brain mass-like lesions in magnetic resonance (MR) image sequences is proposed. With the graphical user interface of ImageJ, the user can interactively determine the lesion volume. The user needs to only provide the tumor contour on one MR slice using LiveWire, after which the system automatically segments and determines the gross lesion volume. Our experimental results, based on MR image sequences from Prasat Neurological Institute, indicate that the proposed system is effective.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133859665","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：