Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596425
J. A. Ware, I. Ciuca
The paper outlines an integrated image processing environment that uses neural networks for object recognition and classification. The image processing environment which is Windows based, encapsulates a multiple-document interface (MDI) and is menu driven. Object (shape) parameter extraction is focused on features that are invariant in terms of translation, rotation and scale transformations. The neural network models incorporated into the environment allow both clustering and classification of objects from the analysed image. Mapping neural networks perform input sensitivity analysis on the extracted feature measurements and thus facilitates the removal of irrelevant features and improvements in the degree of generalisation.
{"title":"A neural network based integrated image processing environment for object recognition in medical applications","authors":"J. A. Ware, I. Ciuca","doi":"10.1109/CBMS.1997.596425","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596425","url":null,"abstract":"The paper outlines an integrated image processing environment that uses neural networks for object recognition and classification. The image processing environment which is Windows based, encapsulates a multiple-document interface (MDI) and is menu driven. Object (shape) parameter extraction is focused on features that are invariant in terms of translation, rotation and scale transformations. The neural network models incorporated into the environment allow both clustering and classification of objects from the analysed image. Mapping neural networks perform input sensitivity analysis on the extracted feature measurements and thus facilitates the removal of irrelevant features and improvements in the degree of generalisation.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129038614","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596440
W. Zagler, P. Panek, Christian Flachberger
Up from a certain degree of impairment, motor and multiple disabled children are rarely able to use conventional environmental control and augmentative communication systems. To attain this ability, in many cases customer-tailored user interfaces plus a long training process is necessary. Even learning the relation between reason and effect and experiencing self effectiveness (being able to make something happen in the environment) is the first big challenge and often an entire new experience. Hence, a technical system able to meet the needs of these users has to fulfill three criteria: (1) give optimal support to the training process; (2) support the facilitators with a tool to easily adapt the system to the rapidly changing user needs; (3) be able to grow from the first experience of self effectiveness up to a multi functional, multi purpose technical aid. The paper discusses an innovative technical assistance system developed at the Vienna University of Technology which is especially for multiple impairments and the training process. The authors look back on one and a half years of practical evaluation of the technical assistance system in a support center for motor and multiple impaired persons. After introducing the concept of the technical assistance system and pointing out its special features, two case studies illustrate the practical application of the system.
{"title":"Technical assistance for severely motor- and multiple impaired children","authors":"W. Zagler, P. Panek, Christian Flachberger","doi":"10.1109/CBMS.1997.596440","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596440","url":null,"abstract":"Up from a certain degree of impairment, motor and multiple disabled children are rarely able to use conventional environmental control and augmentative communication systems. To attain this ability, in many cases customer-tailored user interfaces plus a long training process is necessary. Even learning the relation between reason and effect and experiencing self effectiveness (being able to make something happen in the environment) is the first big challenge and often an entire new experience. Hence, a technical system able to meet the needs of these users has to fulfill three criteria: (1) give optimal support to the training process; (2) support the facilitators with a tool to easily adapt the system to the rapidly changing user needs; (3) be able to grow from the first experience of self effectiveness up to a multi functional, multi purpose technical aid. The paper discusses an innovative technical assistance system developed at the Vienna University of Technology which is especially for multiple impairments and the training process. The authors look back on one and a half years of practical evaluation of the technical assistance system in a support center for motor and multiple impaired persons. After introducing the concept of the technical assistance system and pointing out its special features, two case studies illustrate the practical application of the system.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132504078","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596417
G. Krell, H. Tizhoosh, T. Lilienblum, C. Moore, B. Michaelis
The Electronic Portal Imaging Device (EPID) uses a high-energy treatment beam to project the body interior of a patient on to a fluorescent screen that is scanned by a camera. Because of the imaging physics, the unprocessed images are very poor in quality. This paper presents an approach that combines an associative restoration algorithm with a fuzzy image enhancement technique. By fusing the electronic portal image with a pre-treatment captured simulator image, a higher image quality than by conventional techniques is achieved.
{"title":"Enhancement and associative restoration of electronic portal images in radiotherapy","authors":"G. Krell, H. Tizhoosh, T. Lilienblum, C. Moore, B. Michaelis","doi":"10.1109/CBMS.1997.596417","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596417","url":null,"abstract":"The Electronic Portal Imaging Device (EPID) uses a high-energy treatment beam to project the body interior of a patient on to a fluorescent screen that is scanned by a camera. Because of the imaging physics, the unprocessed images are very poor in quality. This paper presents an approach that combines an associative restoration algorithm with a fuzzy image enhancement technique. By fusing the electronic portal image with a pre-treatment captured simulator image, a higher image quality than by conventional techniques is achieved.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123416043","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596439
Dominique Dieng
The aim of the paper is to outline the keys to success of the implementation of a specific computer based medical system, the Health Card. The advice suggested is issued from the experience of 9 European and Canadian health card projects. The advice applies to national or local health card projects. No real distinction is made in consideration of the scale of the project: some of the recommendations are more specific to large scale projects, and depend on the government. However, most of the advice can apply to national or local projects. Our concern is "health cards", but a lot of recommendations can also apply to telematics, particularly to the computerized medical record.
{"title":"The keys of success of a health card project: the lessons learned from 9 health cards project","authors":"Dominique Dieng","doi":"10.1109/CBMS.1997.596439","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596439","url":null,"abstract":"The aim of the paper is to outline the keys to success of the implementation of a specific computer based medical system, the Health Card. The advice suggested is issued from the experience of 9 European and Canadian health card projects. The advice applies to national or local health card projects. No real distinction is made in consideration of the scale of the project: some of the recommendations are more specific to large scale projects, and depend on the government. However, most of the advice can apply to national or local projects. Our concern is \"health cards\", but a lot of recommendations can also apply to telematics, particularly to the computerized medical record.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126300984","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596400
H. Eich, C. Ohmann, K. Lang
This paper describes a knowledge-based system for the diagnosis of acute abdominal pain, in which scores and rule sets are integrated. The system is linked to a documentation program via a medical data dictionary and allows an on-line application of knowledge modules to clinical data. Different rule sets were generated by automatic rule generation (C4.5) from a prospective database. The rule sets and two published diagnostic scores were evaluated on a test set, resulting in a diagnostic accuracy of 57% for a general knowledge module and between 44 and 88% for specific knowledge modules. The program is fully functioning and has been evaluated carefully in 14 German hospitals.
{"title":"Decision support in acute abdominal pain using an expert system for different knowledge bases","authors":"H. Eich, C. Ohmann, K. Lang","doi":"10.1109/CBMS.1997.596400","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596400","url":null,"abstract":"This paper describes a knowledge-based system for the diagnosis of acute abdominal pain, in which scores and rule sets are integrated. The system is linked to a documentation program via a medical data dictionary and allows an on-line application of knowledge modules to clinical data. Different rule sets were generated by automatic rule generation (C4.5) from a prospective database. The rule sets and two published diagnostic scores were evaluated on a test set, resulting in a diagnostic accuracy of 57% for a general knowledge module and between 44 and 88% for specific knowledge modules. The program is fully functioning and has been evaluated carefully in 14 German hospitals.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123294715","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596426
B. Novak, G. Bunc
Neuroimaging provides a neurosurgeon with the most important information about pathology concerning a particular patient. The amount of such information is enormous and is still growing with the introduction of new equipment. The problem is the choice of the exact details of interest from this huge amount of information, how to make it more visible, and how to store it etc. in order to enable the physician to make better and quicker decisions about exact diagnosis and localization of the pathology for further medical interventions. In such cases computer based intelligent support can help a physician to acquire more important information from X-ray images. This is very important for drawing proper conclusions and taking appropriate action. The authors are developing a prototype of a computer based intelligent support for neuroimaging (CBISN). Some practical examples are presented.
{"title":"Intelligent support for the neuroimaging","authors":"B. Novak, G. Bunc","doi":"10.1109/CBMS.1997.596426","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596426","url":null,"abstract":"Neuroimaging provides a neurosurgeon with the most important information about pathology concerning a particular patient. The amount of such information is enormous and is still growing with the introduction of new equipment. The problem is the choice of the exact details of interest from this huge amount of information, how to make it more visible, and how to store it etc. in order to enable the physician to make better and quicker decisions about exact diagnosis and localization of the pathology for further medical interventions. In such cases computer based intelligent support can help a physician to acquire more important information from X-ray images. This is very important for drawing proper conclusions and taking appropriate action. The authors are developing a prototype of a computer based intelligent support for neuroimaging (CBISN). Some practical examples are presented.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127534718","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596406
Margaret G. E. Peterson, P. Williams-Russo, Alex Bernardin, N. Sharrock
During an operation, data is collected on operative events including start and stop times and on continuous data distributions such as heart rate, and blood pressure. This means that records from different operations are of different lengths since the amount of data collected depends on the length of the operation. Padding all records to the same length is a waste of disk space and processing time. In general statistical software packages require constant length records and much of the data is redundant and will not be used in the analysis. This paper discusses a method using a statistics package to format the operation records into one file.
{"title":"Interfacing anesthesiology operating room data with statistics software packages","authors":"Margaret G. E. Peterson, P. Williams-Russo, Alex Bernardin, N. Sharrock","doi":"10.1109/CBMS.1997.596406","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596406","url":null,"abstract":"During an operation, data is collected on operative events including start and stop times and on continuous data distributions such as heart rate, and blood pressure. This means that records from different operations are of different lengths since the amount of data collected depends on the length of the operation. Padding all records to the same length is a waste of disk space and processing time. In general statistical software packages require constant length records and much of the data is redundant and will not be used in the analysis. This paper discusses a method using a statistics package to format the operation records into one file.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129820188","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596404
W. Zagler, Georg Edelmayer, P. Mayer
This paper describes the development of functions and tests for the prototype of a vision enhancement system within the TIDE Project 1211-"POVES". POVES is the acronym for Portable Optoelectronic Vision Enhancement System. It addresses such kinds of visual impairments which cannot or only insufficiently be compensated by conventional means like eye glasses, contact lenses, drugs or surgical intervention. POVES consists of a battery operated portable image processing system and a head-worn spectacle part carrying CCD cameras and LCD displays. The results of the technical and clinical tests with a prototype are discussed. As a first overcome of this project a device called NiViS to tackle night vision problems is expected to be put on the market within 1997.
{"title":"Studies on vision enhancement with optoelectronical devices","authors":"W. Zagler, Georg Edelmayer, P. Mayer","doi":"10.1109/CBMS.1997.596404","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596404","url":null,"abstract":"This paper describes the development of functions and tests for the prototype of a vision enhancement system within the TIDE Project 1211-\"POVES\". POVES is the acronym for Portable Optoelectronic Vision Enhancement System. It addresses such kinds of visual impairments which cannot or only insufficiently be compensated by conventional means like eye glasses, contact lenses, drugs or surgical intervention. POVES consists of a battery operated portable image processing system and a head-worn spectacle part carrying CCD cameras and LCD displays. The results of the technical and clinical tests with a prototype are discussed. As a first overcome of this project a device called NiViS to tackle night vision problems is expected to be put on the market within 1997.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129640621","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596423
M. Köhle, D. Merkl, J. Kastner
Clinical gait analysis is an area aimed at the provision of support for diagnoses and therapy considerations, the development of bio-feedback systems to train patients, and the recognition of effects of multiple diseases and still active compensation. The data recorded with ground reaction force measurement platforms is a convenient starting point for gait analysis. The authors argue in favor of using the raw data from such force platforms and apply artificial neural networks for gait malfunction identification. They discuss their latest results in this line of research by using a supervised learning rule. The employed classification approach is learning vector quantization which proved to be highly robust in the training process yielding a remarkably high recognition accuracy of gait patterns.
{"title":"Clinical gait analysis by neural networks: issues and experiences","authors":"M. Köhle, D. Merkl, J. Kastner","doi":"10.1109/CBMS.1997.596423","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596423","url":null,"abstract":"Clinical gait analysis is an area aimed at the provision of support for diagnoses and therapy considerations, the development of bio-feedback systems to train patients, and the recognition of effects of multiple diseases and still active compensation. The data recorded with ground reaction force measurement platforms is a convenient starting point for gait analysis. The authors argue in favor of using the raw data from such force platforms and apply artificial neural networks for gait malfunction identification. They discuss their latest results in this line of research by using a supervised learning rule. The employed classification approach is learning vector quantization which proved to be highly robust in the training process yielding a remarkably high recognition accuracy of gait patterns.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123973482","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}
Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596434
I. Pilih, D. Mladenić, N. Lavrač, T. Prevec
The paper presents an application of decision tree induction to the problem of the prediction of outcome after a severe head injury. The study shows that induced decision trees are useful for the analysis of the importance of clinical parameters and of their combinations for the evaluation of the severity of brain injury and for outcome prediction.
{"title":"Using machine learning for outcome prediction of patients with severe head injury","authors":"I. Pilih, D. Mladenić, N. Lavrač, T. Prevec","doi":"10.1109/CBMS.1997.596434","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596434","url":null,"abstract":"The paper presents an application of decision tree induction to the problem of the prediction of outcome after a severe head injury. The study shows that induced decision trees are useful for the analysis of the importance of clinical parameters and of their combinations for the evaluation of the severity of brain injury and for outcome prediction.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705528","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：