Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128981
M. Poliac, John M. Zanetty, David Salerno, G. Wilcox
Exercise seismocardiograms (SCG) were recorded in a population of 114 patients, 57 of which were diagnosed as having coronary artery disease. The remaining 57 were diagnosed as low-risk normals. Three 60-s SCG recordings were performed at rest, immediately after exercise, and after recovery. A multilayered neural network has been developed to accept the 48 input parameters derived from the three SCG recordings, and to produce an output value of zero is the input parameters correspond to a normal patient and an output value of one if the input parameters correspond to a diseased patient. Three SCG parameters have been identified as most sensitive indicators of heart disease. The relative performance of several neural-network architectures in detecting heart disease based on the selected SCG parameters is discussed. Optimal learning and overlearning issues are discussed. The work suggests that using artificial neural networks can be a useful tool in the interpretation of subtle changes in exercise SCGs necessary for the early detection of heart disease.<>
{"title":"Seismocardiogram (SCG) interpretation using neural networks","authors":"M. Poliac, John M. Zanetty, David Salerno, G. Wilcox","doi":"10.1109/CBMS.1991.128981","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128981","url":null,"abstract":"Exercise seismocardiograms (SCG) were recorded in a population of 114 patients, 57 of which were diagnosed as having coronary artery disease. The remaining 57 were diagnosed as low-risk normals. Three 60-s SCG recordings were performed at rest, immediately after exercise, and after recovery. A multilayered neural network has been developed to accept the 48 input parameters derived from the three SCG recordings, and to produce an output value of zero is the input parameters correspond to a normal patient and an output value of one if the input parameters correspond to a diseased patient. Three SCG parameters have been identified as most sensitive indicators of heart disease. The relative performance of several neural-network architectures in detecting heart disease based on the selected SCG parameters is discussed. Optimal learning and overlearning issues are discussed. The work suggests that using artificial neural networks can be a useful tool in the interpretation of subtle changes in exercise SCGs necessary for the early detection of heart disease.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127283552","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128988
Wei Lin, Jian-Xong Tang
DiagFH, a consultation system for the diagnosis of fulminant hepatitis (FH) is presented. The expert's knowledge is represented by a tree-like structure which is divided into two classes of facts; certain and uncertain facts. The inferences on the facts is implemented by using logical and probabilistic strategies. The entire design is based on the simulation of clinical practice. DiagFH consists of user interface, knowledge base, database, and inference engine. The system is implemented in TURBO PROLOG, and runs on IBM-PC or compatible. DiagFH has been tested by approximately 100 patients who had been suspected FH-infected and had liver biopsy. The DiagFH's diagnostic conclusions coincided with pathological reports.<>
{"title":"DiagFH: an expert system for diagnosis of fulminant hepatitis","authors":"Wei Lin, Jian-Xong Tang","doi":"10.1109/CBMS.1991.128988","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128988","url":null,"abstract":"DiagFH, a consultation system for the diagnosis of fulminant hepatitis (FH) is presented. The expert's knowledge is represented by a tree-like structure which is divided into two classes of facts; certain and uncertain facts. The inferences on the facts is implemented by using logical and probabilistic strategies. The entire design is based on the simulation of clinical practice. DiagFH consists of user interface, knowledge base, database, and inference engine. The system is implemented in TURBO PROLOG, and runs on IBM-PC or compatible. DiagFH has been tested by approximately 100 patients who had been suspected FH-infected and had liver biopsy. The DiagFH's diagnostic conclusions coincided with pathological reports.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132135368","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128966
N. Tavakoli
Lossless compression of magnetic resonance images is reviewed using both the theoretical and implementation models. The compression level of selected algorithms (Lempel-Ziv and Huffman) are compared against the first-order, second-order, and conditional entropies. It is found that the compression upper limit for Huffman is the first-order entropy and for Lempel-Ziv, the second-order or first-order conditional entropies. The experiments showed that the second-order and conditional entropies were lower per pixel than the first-order, suggesting a certain amount of dependencies between the adjacent pixels. As a result, the Lempel-Ziv achieved more compression than the Huffman. The first transformation (difference coding) improves the compression level by 6% for Huffman and 1% for Lempel-Ziv. In a second transformation, where images are split by their upper and lower bytes of each pixel, Lempel-Ziv performs better on the higher byte and Huffman performs better on the lower byte.<>
{"title":"Lossless compression of medical images","authors":"N. Tavakoli","doi":"10.1109/CBMS.1991.128966","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128966","url":null,"abstract":"Lossless compression of magnetic resonance images is reviewed using both the theoretical and implementation models. The compression level of selected algorithms (Lempel-Ziv and Huffman) are compared against the first-order, second-order, and conditional entropies. It is found that the compression upper limit for Huffman is the first-order entropy and for Lempel-Ziv, the second-order or first-order conditional entropies. The experiments showed that the second-order and conditional entropies were lower per pixel than the first-order, suggesting a certain amount of dependencies between the adjacent pixels. As a result, the Lempel-Ziv achieved more compression than the Huffman. The first transformation (difference coding) improves the compression level by 6% for Huffman and 1% for Lempel-Ziv. In a second transformation, where images are split by their upper and lower bytes of each pixel, Lempel-Ziv performs better on the higher byte and Huffman performs better on the lower byte.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129976707","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128940
Robert F. Roggio
A prototype number discrimination test system (NDTS) is described. The NDTS is a computer-based medical application system designed to gather data in support of the hypothesis that fatigue and sleep deprivation adversely affect motor skills and hence clinical effectiveness in surgical resident programs. The computer system measures hand-eye coordination. A series (50) of three three-digit numbers are positioned in random locations on a typical computer monitor. The subject chooses the largest of the three as quickly as possible by using a light pen or mouse. The computer software records both the accuracy and the elapsed time for each of the selections. The test results can be analyzed locally, supplemented with additional on-call parameters, and input into a standard statistical package for follow-on correlation activities.<>
{"title":"Performance resource profiling using a computer-based number discrimination test system","authors":"Robert F. Roggio","doi":"10.1109/CBMS.1991.128940","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128940","url":null,"abstract":"A prototype number discrimination test system (NDTS) is described. The NDTS is a computer-based medical application system designed to gather data in support of the hypothesis that fatigue and sleep deprivation adversely affect motor skills and hence clinical effectiveness in surgical resident programs. The computer system measures hand-eye coordination. A series (50) of three three-digit numbers are positioned in random locations on a typical computer monitor. The subject chooses the largest of the three as quickly as possible by using a light pen or mouse. The computer software records both the accuracy and the elapsed time for each of the selections. The test results can be analyzed locally, supplemented with additional on-call parameters, and input into a standard statistical package for follow-on correlation activities.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131696711","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128953
R. Dayhoff, P. Kuzmak, D. Maloney, B. Shepard
An integrated image system to provide high-quality image data from cardiology, pulmonary and gastrointestinal endoscopy, pathology, radiology, hematology, and nuclear medicine for hospital information systems has been developed. Images and associated text data are presented to clinicians throughout the hospital on high-resolution workstations which are interfaced to the main hospital system in a client-server architecture. The system's architecture is described, and experience in the first six months of operation is discussed. Initial use has validated the approach and has indicated a number of unanticipated benefits for patient care and teaching.<>
{"title":"Experience with an architecture for integrating images into a hospital information system","authors":"R. Dayhoff, P. Kuzmak, D. Maloney, B. Shepard","doi":"10.1109/CBMS.1991.128953","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128953","url":null,"abstract":"An integrated image system to provide high-quality image data from cardiology, pulmonary and gastrointestinal endoscopy, pathology, radiology, hematology, and nuclear medicine for hospital information systems has been developed. Images and associated text data are presented to clinicians throughout the hospital on high-resolution workstations which are interfaced to the main hospital system in a client-server architecture. The system's architecture is described, and experience in the first six months of operation is discussed. Initial use has validated the approach and has indicated a number of unanticipated benefits for patient care and teaching.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114403409","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128961
E. Rogers, R. Arkin, M. Baron
The concept of visual interaction is introduced as the process which links perception and problem solving such that problem solving is affected by what is seen, and conversely, what is seen and perceived is affected by the current state of the problem-solving process. The development of a cognitively based model of the visual interaction process in diagnostic radiology is described. It is shown how aspects of this model are being incorporated into the design and implementation of an intelligent computer-based radiological assistant. In order to achieve this, it is necessary to extract information about the nature and type of knowledge involved in this process, and then to determine how the knowledge is used to accomplish the task of radiological diagnosis. This work may provide new directions for clinically useful interactive radiological systems. It is also seen as a useful radiological teaching tool, providing hands-on experience with a clinical aid, and further, it may prove to be effective tool for studying the radiological process.<>
{"title":"Visual interaction in diagnostic radiology","authors":"E. Rogers, R. Arkin, M. Baron","doi":"10.1109/CBMS.1991.128961","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128961","url":null,"abstract":"The concept of visual interaction is introduced as the process which links perception and problem solving such that problem solving is affected by what is seen, and conversely, what is seen and perceived is affected by the current state of the problem-solving process. The development of a cognitively based model of the visual interaction process in diagnostic radiology is described. It is shown how aspects of this model are being incorporated into the design and implementation of an intelligent computer-based radiological assistant. In order to achieve this, it is necessary to extract information about the nature and type of knowledge involved in this process, and then to determine how the knowledge is used to accomplish the task of radiological diagnosis. This work may provide new directions for clinically useful interactive radiological systems. It is also seen as a useful radiological teaching tool, providing hands-on experience with a clinical aid, and further, it may prove to be effective tool for studying the radiological process.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127493597","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128957
R. Reilly, Mohammed Reza Amirinia, R. Soames
A novel approach to implementing a clinical walkway for imaging foot placement with high resolution in two dimensions and in time over several steps is discussed. It uses a novel principle for sensing and data gathering through an array of magnetostrictive delay lines made of amorphous magnetic alloy. Foot/ground contact images are read by a computer in real time. Software has been developed for rapid analysis and presentation of spatial and temporal gait parameters, based on two-dimensional foot placement. The sensing array is simple and robust and it should be possible for reliable systems to be built at a low enough cost to be widely used in the clinical environment with minimal technical support. Progress has also been made towards achieving proportional pressure mapping by means of a similar structure.<>
{"title":"A two-dimensional imaging walkway for gait analysis","authors":"R. Reilly, Mohammed Reza Amirinia, R. Soames","doi":"10.1109/CBMS.1991.128957","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128957","url":null,"abstract":"A novel approach to implementing a clinical walkway for imaging foot placement with high resolution in two dimensions and in time over several steps is discussed. It uses a novel principle for sensing and data gathering through an array of magnetostrictive delay lines made of amorphous magnetic alloy. Foot/ground contact images are read by a computer in real time. Software has been developed for rapid analysis and presentation of spatial and temporal gait parameters, based on two-dimensional foot placement. The sensing array is simple and robust and it should be possible for reliable systems to be built at a low enough cost to be widely used in the clinical environment with minimal technical support. Progress has also been made towards achieving proportional pressure mapping by means of a similar structure.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126448465","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128971
Chong-woo Woo, M. Evens, J. Michael, A. Rovick
An intelligent tutoring system (ITS) that will assist first-year medical students in learning the causal relationships between the parameters of the circulatory system and in solving problems of disturbances to the system is discussed. The central component of the ITS, the instructional planner, is responsible for determining what to do next at each point during a tutoring session. The approach taken is to build the planner by combining the capabilities of lesson planning and discourse planning in order to provide globally coherent and adaptive instruction. The planner consists of two parts: a lesson planner and a discourse planner. The lesson planner generates lesson plans, which the discourse planner carries out. A sample dialogue, extracted from the transcript of an actual human tutor-student interaction, is used to provide a framework for the development of the overall system, especially from the planner's point of view.<>
{"title":"Dynamic instructional planning for an intelligent physiology tutoring system","authors":"Chong-woo Woo, M. Evens, J. Michael, A. Rovick","doi":"10.1109/CBMS.1991.128971","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128971","url":null,"abstract":"An intelligent tutoring system (ITS) that will assist first-year medical students in learning the causal relationships between the parameters of the circulatory system and in solving problems of disturbances to the system is discussed. The central component of the ITS, the instructional planner, is responsible for determining what to do next at each point during a tutoring session. The approach taken is to build the planner by combining the capabilities of lesson planning and discourse planning in order to provide globally coherent and adaptive instruction. The planner consists of two parts: a lesson planner and a discourse planner. The lesson planner generates lesson plans, which the discourse planner carries out. A sample dialogue, extracted from the transcript of an actual human tutor-student interaction, is used to provide a framework for the development of the overall system, especially from the planner's point of view.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122962540","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128965
C. Kurak
Adaptive histogram equalization (AHE) is computationally expensive, and therefore time-consuming. A parallel method implemented with commercially available hardware is discussed. The implementation and testing conducted supports the hypothesis that multiple instruction/multiple data (MIMD) parallelism will improve the performance of the AHE algorithm. A method for handling border regions has been developed and implemented. The application of a look-up table served well to reduce the number of required computations. Whereas this probably did not affect the outcome of the testing, as both the sequential and parallel versions utilized this method, it did serve as an improvement to the overall implementation.<>
{"title":"Adaptive histogram equalization: a parallel implementation","authors":"C. Kurak","doi":"10.1109/CBMS.1991.128965","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128965","url":null,"abstract":"Adaptive histogram equalization (AHE) is computationally expensive, and therefore time-consuming. A parallel method implemented with commercially available hardware is discussed. The implementation and testing conducted supports the hypothesis that multiple instruction/multiple data (MIMD) parallelism will improve the performance of the AHE algorithm. A method for handling border regions has been developed and implemented. The application of a look-up table served well to reduce the number of required computations. Whereas this probably did not affect the outcome of the testing, as both the sequential and parallel versions utilized this method, it did serve as an improvement to the overall implementation.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116736918","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 : 1991-05-12DOI: 10.1109/CBMS.1991.128951
M. MacAulay, J. Scrimger, D. Riordan, A. Foyle, H. Cheng
An interactive graphics package with standard images and exemplar rules to assist physicians in the grading of breast cancer in a standardized way is presented. Pictures obtained from microscopic slide examples of standards for the Bloom-Richardson grading method have been visually classified by an expert, digitized, and input into a computer display system. These are presented together with a knowledge base (exemplars) of some underlying commonalities in a user-friendly, graphical image-display system that will run on personal computer with EGA or VGA graphics capabilities. The physician can inspect and enhance the standard images, and by using the exemplars can be guided to a diagnosis of new cases. The exemplars also include rules that advise on the use of the image analyzer.<>
{"title":"An interactive graphics package with standard examples of the Bloom and Richardson histological grading technique","authors":"M. MacAulay, J. Scrimger, D. Riordan, A. Foyle, H. Cheng","doi":"10.1109/CBMS.1991.128951","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128951","url":null,"abstract":"An interactive graphics package with standard images and exemplar rules to assist physicians in the grading of breast cancer in a standardized way is presented. Pictures obtained from microscopic slide examples of standards for the Bloom-Richardson grading method have been visually classified by an expert, digitized, and input into a computer display system. These are presented together with a knowledge base (exemplars) of some underlying commonalities in a user-friendly, graphical image-display system that will run on personal computer with EGA or VGA graphics capabilities. The physician can inspect and enhance the standard images, and by using the exemplars can be guided to a diagnosis of new cases. The exemplars also include rules that advise on the use of the image analyzer.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125504998","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：