Content-based image retrieval (CBIR) for medical images has received a significant research interest over the past decade as a promising approach to address the data management challenges posed by the rapidly increasing volume of medical image data in use. Articles published in the literature detail the benefits and present impressive results to substantiate potential impact of the technology. However, the benefits have yet to make it to mainstream clinical, biomedical research, or educational use. No major commercial software tools are available for use in medical imaging products, although several are available for commercial stock photo collections. CBIR has had some success in isolated instances in applications on limited data sets addressing specialized medical problems and at biomedical research laboratories and hospitals that are tightly coupled with software developers. This article explores some possible causes of this "gap" in the lack of translation of research into widespread biomedical use and provides some directions to alleviate the problem.
{"title":"Bridging the Gap: Enabling CBIR in Medical Applications","authors":"Sameer Kiran Antani, L. Long, G. Thoma","doi":"10.1109/CBMS.2008.133","DOIUrl":"https://doi.org/10.1109/CBMS.2008.133","url":null,"abstract":"Content-based image retrieval (CBIR) for medical images has received a significant research interest over the past decade as a promising approach to address the data management challenges posed by the rapidly increasing volume of medical image data in use. Articles published in the literature detail the benefits and present impressive results to substantiate potential impact of the technology. However, the benefits have yet to make it to mainstream clinical, biomedical research, or educational use. No major commercial software tools are available for use in medical imaging products, although several are available for commercial stock photo collections. CBIR has had some success in isolated instances in applications on limited data sets addressing specialized medical problems and at biomedical research laboratories and hospitals that are tightly coupled with software developers. This article explores some possible causes of this \"gap\" in the lack of translation of research into widespread biomedical use and provides some directions to alleviate the problem.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"135 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":"122906052","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}
P. Staccini, S. Vessiere, S. Jullien, C. Bordonado, J. Quaranta, P. Roussel, J. Cabaud, P. Rouger
In order to manage a nationwide assessment program for certifying professional competence in blood transfusion throughout France, the National Institute of Blood Transfusion and the University of Nice-Sophia Antipolis developed a Web-based and tutored portfolio. The structure of this e-portfolio is based on a matrix of actions defined according to standards of practice. For each action, elements of proof are uploaded by the physician and peer reviewed by an expert before being validated. The electronic portfolio stores all the history of the actions done by users. This tracking feature generates alerts emailed to users according to a list of monitored events. After one year of design and development, the application is used in routine. Based on open-source components, we forecast integration with the CME system in blood transfusion handled by INTS.
{"title":"Evaluation of Professional Practices in Transfusion Medicine: Design and Implementation of a Web-Based and Tutored ePortfolio","authors":"P. Staccini, S. Vessiere, S. Jullien, C. Bordonado, J. Quaranta, P. Roussel, J. Cabaud, P. Rouger","doi":"10.1109/CBMS.2008.79","DOIUrl":"https://doi.org/10.1109/CBMS.2008.79","url":null,"abstract":"In order to manage a nationwide assessment program for certifying professional competence in blood transfusion throughout France, the National Institute of Blood Transfusion and the University of Nice-Sophia Antipolis developed a Web-based and tutored portfolio. The structure of this e-portfolio is based on a matrix of actions defined according to standards of practice. For each action, elements of proof are uploaded by the physician and peer reviewed by an expert before being validated. The electronic portfolio stores all the history of the actions done by users. This tracking feature generates alerts emailed to users according to a list of monitored events. After one year of design and development, the application is used in routine. Based on open-source components, we forecast integration with the CME system in blood transfusion handled by INTS.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"23 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":"131568294","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 increasing body of distributed and heterogeneous information and the autonomous, heterogeneous and dynamic nature of information resources are important issues hindering effective and efficient data access, retrieval and knowledge sharing. The importance of ontologies has been recognised within the biomedical domain and work has begun on developing and sharing biomedical ontologies. In this paper, we define ontology and ontology commitments and explain the main characteristics and representations of ontology models. Ontologies are highly expressive knowledge models and as such increase expressiveness and intelligence of a system. We highlight the significance of ontologies in a variety of semi-automatic and automatic tasks, and provide an illustrative example of an ontology-based multi-agent system designed to intelligently retrieve information about human diseases from a number of heterogeneous and dispersed information resources.
{"title":"Ontology Support for Biomedical Information Resources","authors":"T. Dillon, E. Chang, M. Hadzic","doi":"10.1109/CBMS.2008.21","DOIUrl":"https://doi.org/10.1109/CBMS.2008.21","url":null,"abstract":"The increasing body of distributed and heterogeneous information and the autonomous, heterogeneous and dynamic nature of information resources are important issues hindering effective and efficient data access, retrieval and knowledge sharing. The importance of ontologies has been recognised within the biomedical domain and work has begun on developing and sharing biomedical ontologies. In this paper, we define ontology and ontology commitments and explain the main characteristics and representations of ontology models. Ontologies are highly expressive knowledge models and as such increase expressiveness and intelligence of a system. We highlight the significance of ontologies in a variety of semi-automatic and automatic tasks, and provide an illustrative example of an ontology-based multi-agent system designed to intelligently retrieve information about human diseases from a number of heterogeneous and dispersed information resources.","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":"130763345","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. Brochhausen, G. Weiler, Cristian Cocos, H. Stenzhorn, N. Graf, M. Doerr, M. Tsiknakis
We present a new source of terminology for transnational data exchange in oncology, emphasizing the integration of both clinical and molecular data. In order to achieve best results in semantic interoperability, the ACGT project provides an ontology on cancer research and management. Besides examining pre-existing sources of terminology, were view methods of ontology development, and present best practices to be employed in the development of the ACGT Master Ontology. The clinical trial management system that is currently developed within ACGT constitutes a central use of the ontology at this point.
{"title":"The ACGT Master Ontology on Cancer – A New Terminology Source for Oncological Practice","authors":"M. Brochhausen, G. Weiler, Cristian Cocos, H. Stenzhorn, N. Graf, M. Doerr, M. Tsiknakis","doi":"10.1109/CBMS.2008.17","DOIUrl":"https://doi.org/10.1109/CBMS.2008.17","url":null,"abstract":"We present a new source of terminology for transnational data exchange in oncology, emphasizing the integration of both clinical and molecular data. In order to achieve best results in semantic interoperability, the ACGT project provides an ontology on cancer research and management. Besides examining pre-existing sources of terminology, were view methods of ontology development, and present best practices to be employed in the development of the ACGT Master Ontology. The clinical trial management system that is currently developed within ACGT constitutes a central use of the ontology at this point.","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":"128140493","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}
Optical measurements are fast and convenient mode to obtain information from human skin. However, the complicated interactions of light with skin may overwhelm our understanding of the measurements. Moreover, the high remittance from the surface of the skin may be often an obstacle for making measurements regarding deeper layers of skin. In this research, we have constructed a simulation model to show from which depths the remittance is coming from. Using this model we have studied the effects of light source shape and location to measure the remittance originating deeper. According to the model, the ring-shaped light source more than doubles the measurement depth, compared with the diffuse light. In fiber-based measurements, increase of the fiber separation increases the measurement depth.
{"title":"The Effect of the Shape and Location of the Light Source in Diffuse Reflectance Measurements","authors":"P. Välisuo, J. Alander","doi":"10.1109/CBMS.2008.29","DOIUrl":"https://doi.org/10.1109/CBMS.2008.29","url":null,"abstract":"Optical measurements are fast and convenient mode to obtain information from human skin. However, the complicated interactions of light with skin may overwhelm our understanding of the measurements. Moreover, the high remittance from the surface of the skin may be often an obstacle for making measurements regarding deeper layers of skin. In this research, we have constructed a simulation model to show from which depths the remittance is coming from. Using this model we have studied the effects of light source shape and location to measure the remittance originating deeper. According to the model, the ring-shaped light source more than doubles the measurement depth, compared with the diffuse light. In fiber-based measurements, increase of the fiber separation increases the measurement depth.","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":"128179060","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}
D. D. J. D. Macedo, H. W. G. Perantunes, Rafael Andrade, A. V. Wangenheim, M. Dantas
Telemedicine systems currently have increased the volume of information stored in their databases. A centralized telemedicine system project covers datasets that ranges from personal patient's information, physicians and institutions to all images of examinations performed. As they store large amounts of examinations, the medical databases can reach several terabytes of volume. This paper presents a contribution characterized by an asynchronous replication model for medical distributed databases. The model, called postgresreplication, is an extension to the relational database postgreSQL. In our experiment, an engine has been created to manage all integration operations and information replication for the medical databases. The early results indicate that the model and its implementation have successfully reached a good performance level and interoperability.
{"title":"Asynchronous Data Replication: A National Integration Strategy for Databases on Telemedicine Network","authors":"D. D. J. D. Macedo, H. W. G. Perantunes, Rafael Andrade, A. V. Wangenheim, M. Dantas","doi":"10.1109/CBMS.2008.76","DOIUrl":"https://doi.org/10.1109/CBMS.2008.76","url":null,"abstract":"Telemedicine systems currently have increased the volume of information stored in their databases. A centralized telemedicine system project covers datasets that ranges from personal patient's information, physicians and institutions to all images of examinations performed. As they store large amounts of examinations, the medical databases can reach several terabytes of volume. This paper presents a contribution characterized by an asynchronous replication model for medical distributed databases. The model, called postgresreplication, is an extension to the relational database postgreSQL. In our experiment, an engine has been created to manage all integration operations and information replication for the medical databases. The early results indicate that the model and its implementation have successfully reached a good performance level and interoperability.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"3 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":"114281628","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}
Computed tomography (CT) images are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies and the 3D volume rendering of the abdominal organs. The first and fundamental step in all these studies is the automatic organs segmentation, that is still an open problem. In this paper we propose a fully automatic gray level based segmentation framework that employs a fast marching technique; the proposed segmentation scheme is general, and employs only established and not critical anatomical knowledge. For this reason, it can be easily adapted to separately segment different abdominal organs, by overcoming problems due to the high inter and intra patient gray level and shape variabilities; the extracted volumes are then combined to achieve robust results. The system performance has been evaluated on the data of 40 patients, by comparing the automatically detected organ volumes to the organ boundaries manually traced by three experts. The good quality of the achieved results is proved by the fact that they are comparable to the inter and intra personal variability of the manual segmentation produced by experts.
{"title":"Fully Automatic Segmentation of Abdominal Organs from CT Images Using Fast Marching Methods","authors":"P. Campadelli, E. Casiraghi, Stella Pratissoli","doi":"10.1109/CBMS.2008.9","DOIUrl":"https://doi.org/10.1109/CBMS.2008.9","url":null,"abstract":"Computed tomography (CT) images are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies and the 3D volume rendering of the abdominal organs. The first and fundamental step in all these studies is the automatic organs segmentation, that is still an open problem. In this paper we propose a fully automatic gray level based segmentation framework that employs a fast marching technique; the proposed segmentation scheme is general, and employs only established and not critical anatomical knowledge. For this reason, it can be easily adapted to separately segment different abdominal organs, by overcoming problems due to the high inter and intra patient gray level and shape variabilities; the extracted volumes are then combined to achieve robust results. The system performance has been evaluated on the data of 40 patients, by comparing the automatically detected organ volumes to the organ boundaries manually traced by three experts. The good quality of the achieved results is proved by the fact that they are comparable to the inter and intra personal variability of the manual segmentation produced by experts.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"60 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":"122089335","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. Guarracino, Salvatore Cuciniello, Davide Feminiano
In this study, we present incremental learning and decremented characterization of regularized generalized eigenvalue classification (ILDC-ReGEC), a novel algorithm to train a generalized eigenvalue classifier with a substantially smaller subset of points and features of the original data. The proposed method provides a constructive way to understand the influence of new training data on an existing classification model and the grouping of features that determine the class of samples. The proposed algorithm is compared with other well known solutions. Experimental results are conducted on publicly available datasets and standard parameters are used for evaluation.
{"title":"Incremental Learning and Decremented Characterization of Gene Expression Data Analysis","authors":"M. Guarracino, Salvatore Cuciniello, Davide Feminiano","doi":"10.1109/CBMS.2008.63","DOIUrl":"https://doi.org/10.1109/CBMS.2008.63","url":null,"abstract":"In this study, we present incremental learning and decremented characterization of regularized generalized eigenvalue classification (ILDC-ReGEC), a novel algorithm to train a generalized eigenvalue classifier with a substantially smaller subset of points and features of the original data. The proposed method provides a constructive way to understand the influence of new training data on an existing classification model and the grouping of features that determine the class of samples. The proposed algorithm is compared with other well known solutions. Experimental results are conducted on publicly available datasets and standard parameters are used for evaluation.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"13 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":"115672402","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}
B. Calster, S. Huffel, D. Timmerman, E. Kirk, T. Bourne, G. Condous
This paper presents our activities towards the development of a clinical decision support (CDS) system for the early diagnosis of pregnancies of unknown location (PULs). PULs are pregnancies that are not visualized on ultrasound. Generally, they turn out to be failing, normal intra-uterine, or ectopic pregnancies. Using 856 PULs collected at a London hospital, we developed probabilistic multi-class models. At the moment, a large multi-center data set is being collected. Data are entered using stand-alone software, and are sent to the database server by ftp. These data will be used to prospectively test existing models, and to build new, hopefully more robust, models. The ultimate aim is to select one model for implementation in a CDS system that is easy to use in routine clinical practice.
{"title":"Towards a Clinical Decision Support System for Pregnancies of Unknown Location","authors":"B. Calster, S. Huffel, D. Timmerman, E. Kirk, T. Bourne, G. Condous","doi":"10.1109/CBMS.2008.123","DOIUrl":"https://doi.org/10.1109/CBMS.2008.123","url":null,"abstract":"This paper presents our activities towards the development of a clinical decision support (CDS) system for the early diagnosis of pregnancies of unknown location (PULs). PULs are pregnancies that are not visualized on ultrasound. Generally, they turn out to be failing, normal intra-uterine, or ectopic pregnancies. Using 856 PULs collected at a London hospital, we developed probabilistic multi-class models. At the moment, a large multi-center data set is being collected. Data are entered using stand-alone software, and are sent to the database server by ftp. These data will be used to prospectively test existing models, and to build new, hopefully more robust, models. The ultimate aim is to select one model for implementation in a CDS system that is easy to use in routine clinical practice.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"27 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":"129081920","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. Zillner, T. Hauer, D. Rogulin, A. Tsymbal, M. Huber, T. Solomonides
Clinical practice and research rely increasingly on analytic approaches to patient data. Visualization enables the comparative exploration of similar patients, a key requirement in certain clinical decision support systems. Patient data is complex and heterogeneous, may have different formats, reside in various structures and carry different semantics. This makes the comparison and analysis of clinical data a challenging task. Most medical applications visualize patient data without integrating additional semantic information to structure the analysis. Our objective is to map patient data onto relevant fragments of ontologies and inferred ontological structures as a basis for improved patient data visualization, comparison, and analysis. Two visualization scenarios that we have implemented using the patient data acquired in the Health-e-Child project will be presented and their clinical evaluation will be provided.
{"title":"Semantic Visualization of Patient Information","authors":"S. Zillner, T. Hauer, D. Rogulin, A. Tsymbal, M. Huber, T. Solomonides","doi":"10.1109/CBMS.2008.11","DOIUrl":"https://doi.org/10.1109/CBMS.2008.11","url":null,"abstract":"Clinical practice and research rely increasingly on analytic approaches to patient data. Visualization enables the comparative exploration of similar patients, a key requirement in certain clinical decision support systems. Patient data is complex and heterogeneous, may have different formats, reside in various structures and carry different semantics. This makes the comparison and analysis of clinical data a challenging task. Most medical applications visualize patient data without integrating additional semantic information to structure the analysis. Our objective is to map patient data onto relevant fragments of ontologies and inferred ontological structures as a basis for improved patient data visualization, comparison, and analysis. Two visualization scenarios that we have implemented using the patient data acquired in the Health-e-Child project will be presented and their clinical evaluation will be provided.","PeriodicalId":377855,"journal":{"name":"2008 21st IEEE International Symposium on Computer-Based Medical Systems","volume":"80 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":"130130199","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：