Pub Date : 1992-06-14DOI: 10.1109/CBMS.1992.245039
Jonathan Michel, G. Mirchandani, S. Wald
The authors report on several techniques for feature selection utilized in the development of a prognostic tool of predicting recovery for patients with head trauma injuries. The database was examined for features, which were extracted using statistical techniques. ANN (artificial neural network) models were built based on the feature selection of the statistical techniques. These models were trained and tested. Results showed that the ability of the ANN to generalize was dependent on three factors: method of data representation, number of outcome classes, and specific features in the data set. The ANN architecture was kept constant for all the cases. Of the statistical techniques used, the backward selection applied to RA (regression analysis) and stepwise selection applied to LDA (linear disciminant analysis) feature models yielded the best generalizations.<>
{"title":"Prognosis with neural networks using statistically based feature sets","authors":"Jonathan Michel, G. Mirchandani, S. Wald","doi":"10.1109/CBMS.1992.245039","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245039","url":null,"abstract":"The authors report on several techniques for feature selection utilized in the development of a prognostic tool of predicting recovery for patients with head trauma injuries. The database was examined for features, which were extracted using statistical techniques. ANN (artificial neural network) models were built based on the feature selection of the statistical techniques. These models were trained and tested. Results showed that the ability of the ANN to generalize was dependent on three factors: method of data representation, number of outcome classes, and specific features in the data set. The ANN architecture was kept constant for all the cases. Of the statistical techniques used, the backward selection applied to RA (regression analysis) and stepwise selection applied to LDA (linear disciminant analysis) feature models yielded the best generalizations.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"15 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120990147","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 : 1992-06-14DOI: 10.1109/CBMS.1992.244941
M. Bilgen, W. Brockman
An image restoration model is given to restore images blurred by a random medium. The overall distortion process caused by the random medium is represented by a stochastic point spread function. To estimate the original images degraded by this model, two restoration algorithms are formulated based on the Wiener filter and the constrained least-squares filter. Computer simulations are included to compare the performances of the proposed algorithms with the conventional ones.<>
{"title":"Restoration of noisy images blurred by a random medium","authors":"M. Bilgen, W. Brockman","doi":"10.1109/CBMS.1992.244941","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244941","url":null,"abstract":"An image restoration model is given to restore images blurred by a random medium. The overall distortion process caused by the random medium is represented by a stochastic point spread function. To estimate the original images degraded by this model, two restoration algorithms are formulated based on the Wiener filter and the constrained least-squares filter. Computer simulations are included to compare the performances of the proposed algorithms with the conventional ones.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127282029","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 : 1992-06-14DOI: 10.1109/CBMS.1992.244967
C. D. Graaf, A. Koster, K. Vincken, M. Viergever
A validation methodology for image segmentation methods is explored that is based on quality constrained cost analysis. In this methodology a segmentation method is evaluated by the cost reduction it provides relative to the cost of a full-interactive (manual) segmentation. This cost is constrained by a quality threshold, so that less-than-perfect segmentations are allowed. In this way, segmentation methods which are entirely different in nature can be compared objectively. The validation methodology is presented in its most general form, along with an example of its application to the comparison of segmentation methods.<>
{"title":"A methodology for the validation of image segmentation methods","authors":"C. D. Graaf, A. Koster, K. Vincken, M. Viergever","doi":"10.1109/CBMS.1992.244967","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244967","url":null,"abstract":"A validation methodology for image segmentation methods is explored that is based on quality constrained cost analysis. In this methodology a segmentation method is evaluated by the cost reduction it provides relative to the cost of a full-interactive (manual) segmentation. This cost is constrained by a quality threshold, so that less-than-perfect segmentations are allowed. In this way, segmentation methods which are entirely different in nature can be compared objectively. The validation methodology is presented in its most general form, along with an example of its application to the comparison of segmentation methods.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114462484","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 : 1992-06-14DOI: 10.1109/CBMS.1992.245033
X. Zhou, P. Engler, M. Coblentz
A hybrid adaptive algorithm for canceling the maternal electrocardiogram (MECG) component in abdominal fetal electrocardiography (FECG) is described. Three limb (1,2,3) lead ECG recordings and one abdominal ECG recording are taken from 6 pregnant women. The three limb ECG recordings are orthogonalized through the Gram-Schmidt procedure, and are input to a multichannel adaptive filter. After processing by the adaptive algorithm, these three orthogonal ECG recordings will be put together to simulate the MECG component in the abdominal FECG. The ideal output of the hybrid adaptive filter will be an MECG-component-free fetal ECG signal, which can provide valuable clinical data to the obstetrician.<>
{"title":"Adaptive filter application in fetal electrocardiography","authors":"X. Zhou, P. Engler, M. Coblentz","doi":"10.1109/CBMS.1992.245033","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245033","url":null,"abstract":"A hybrid adaptive algorithm for canceling the maternal electrocardiogram (MECG) component in abdominal fetal electrocardiography (FECG) is described. Three limb (1,2,3) lead ECG recordings and one abdominal ECG recording are taken from 6 pregnant women. The three limb ECG recordings are orthogonalized through the Gram-Schmidt procedure, and are input to a multichannel adaptive filter. After processing by the adaptive algorithm, these three orthogonal ECG recordings will be put together to simulate the MECG component in the abdominal FECG. The ideal output of the hybrid adaptive filter will be an MECG-component-free fetal ECG signal, which can provide valuable clinical data to the obstetrician.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128413580","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 : 1992-06-14DOI: 10.1109/CBMS.1992.245025
Kent Wreder, Dong-Chul Park, M. Adjouadi, S. Gonzalez-Arias
Recent research into different artificial neural network structures and topologies suggests the possibility of implementing a particular application. The goal is for the neural network to represent the input function in a natural manner. The authors describe such an implementation in the field of neurosurgical planning, where a set of neural networks represents the lesion to be treated as well as the different functional regions of the brain. It is shown that this neural network structure can actively and effectively assist in the surgical planning. Emphasis is on stereotactic radiosurgery, whereby a high dose of radiation is delivered to the lesion. This modality allows for extensive implementation of the neural network features in a natural way, using Gaussian potential functions for the neural activation. The goal of decreasing the procedural risk factor in stereotactic surgery is accomplished by implementing the visual interface and a framework of artificial neural networks.<>
{"title":"Stereotactic surgical planning using three dimensional reconstruction and artificial neural networks","authors":"Kent Wreder, Dong-Chul Park, M. Adjouadi, S. Gonzalez-Arias","doi":"10.1109/CBMS.1992.245025","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245025","url":null,"abstract":"Recent research into different artificial neural network structures and topologies suggests the possibility of implementing a particular application. The goal is for the neural network to represent the input function in a natural manner. The authors describe such an implementation in the field of neurosurgical planning, where a set of neural networks represents the lesion to be treated as well as the different functional regions of the brain. It is shown that this neural network structure can actively and effectively assist in the surgical planning. Emphasis is on stereotactic radiosurgery, whereby a high dose of radiation is delivered to the lesion. This modality allows for extensive implementation of the neural network features in a natural way, using Gaussian potential functions for the neural activation. The goal of decreasing the procedural risk factor in stereotactic surgery is accomplished by implementing the visual interface and a framework of artificial neural networks.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124603063","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 : 1992-06-14DOI: 10.1109/CBMS.1992.244951
Santina Franchi, Mario A. Imperato, F. Prampolini
The design of a multimedia medical information system implies an extension of the issues previously described for PAC (picture archiving and communications) systems. Database structures must be defined to describe the physical features and the clinical contents of each kind of multimedia clinical data. Mass storage requirements dramatically increase to archive audio and/or video sequences. As for PACS, high-speed networking is necessary. Moreover, the transfer of multimedia information implies further requirements for the network subsystem, e.g. the capability to support isochronous traffic. In order to achieve a richer interaction of the radiologist with the system, the user workstation must be properly equipped to allow access and presentation of multimedia data. At a higher level, the hypertext model can be exploited for effective consultation of clinical data. All these issues have been considered in the design of a multimedia system under development at IBM Rome Scientific Center. The system addresses multimedia information management and can provide the basis of an advanced PAC system.<>
{"title":"Multimedia perspectives for next generation PAC systems","authors":"Santina Franchi, Mario A. Imperato, F. Prampolini","doi":"10.1109/CBMS.1992.244951","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244951","url":null,"abstract":"The design of a multimedia medical information system implies an extension of the issues previously described for PAC (picture archiving and communications) systems. Database structures must be defined to describe the physical features and the clinical contents of each kind of multimedia clinical data. Mass storage requirements dramatically increase to archive audio and/or video sequences. As for PACS, high-speed networking is necessary. Moreover, the transfer of multimedia information implies further requirements for the network subsystem, e.g. the capability to support isochronous traffic. In order to achieve a richer interaction of the radiologist with the system, the user workstation must be properly equipped to allow access and presentation of multimedia data. At a higher level, the hypertext model can be exploited for effective consultation of clinical data. All these issues have been considered in the design of a multimedia system under development at IBM Rome Scientific Center. The system addresses multimedia information management and can provide the basis of an advanced PAC system.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129532220","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 : 1992-06-14DOI: 10.1109/CBMS.1992.245015
Ru-Charn Chang, M. Evens, A. Rovick, J. Michael
Presents a surface generator for an intelligent tutoring system based on analysis of human tutoring sessions. The tutoring system is designed to help first-year medical students understand the negative feedback system that regulates blood pressure. The authors illustrate the generation of appropriate natural language output using Lexical Functional Grammar based on a study of the cardiovascular sublanguage.<>
{"title":"Surface generation in a tutorial dialogue based on analysis of human tutoring sessions","authors":"Ru-Charn Chang, M. Evens, A. Rovick, J. Michael","doi":"10.1109/CBMS.1992.245015","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245015","url":null,"abstract":"Presents a surface generator for an intelligent tutoring system based on analysis of human tutoring sessions. The tutoring system is designed to help first-year medical students understand the negative feedback system that regulates blood pressure. The authors illustrate the generation of appropriate natural language output using Lexical Functional Grammar based on a study of the cardiovascular sublanguage.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116268684","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 : 1992-06-14DOI: 10.1109/CBMS.1992.244959
N. Botros
The author presents an algorithm and instrumentation for ultrasound classification of simulated human-liver tissue abnormalities. The tissue is simulated by a liver phantom that mimics the tissue acoustically. The instrumentation used is a 50 MHz microcomputer-based data acquisition and analysis system. The system digitizes the ultrasound backscattered signal from selected regions of the phantom and processes the digitized data for feature measurement. The algorithm is based on a three-layer backpropagation artificial neural network. The network is trained to differentiate between simulated normal and abnormal tissue and to classify three types of simulated abnormalities. The results of this study show that out of twenty-eight cases the system classifies twenty five correctly and fails to classify three cases. The reasons for this are discussed along with recommendations to increase the accuracy of classification.<>
{"title":"A PC-based system for soft tissue classification","authors":"N. Botros","doi":"10.1109/CBMS.1992.244959","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244959","url":null,"abstract":"The author presents an algorithm and instrumentation for ultrasound classification of simulated human-liver tissue abnormalities. The tissue is simulated by a liver phantom that mimics the tissue acoustically. The instrumentation used is a 50 MHz microcomputer-based data acquisition and analysis system. The system digitizes the ultrasound backscattered signal from selected regions of the phantom and processes the digitized data for feature measurement. The algorithm is based on a three-layer backpropagation artificial neural network. The network is trained to differentiate between simulated normal and abnormal tissue and to classify three types of simulated abnormalities. The results of this study show that out of twenty-eight cases the system classifies twenty five correctly and fails to classify three cases. The reasons for this are discussed along with recommendations to increase the accuracy of classification.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116510356","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 : 1992-06-14DOI: 10.1109/CBMS.1992.245001
C. Chang, H. Chan, L. Niklason, J. Crabbe, J. Mathews, M. Cobby, R. Adler
A computer algorithm has been developed to detect and possibly stage subperiosteal resorption from digitized hand radiographs for patients with primary or secondary hyperparathyroidism. The method can quantify the severity of bony resorption by analyzing the roughness of the radial phalangeal margins as projected on the hand radiographs. This margin is detected by a model-guided boundary-tracking scheme and its roughness is quantified by the mean-square variation and the first moment of the power spectrum. The preliminary results indicate that the computer-aided diagnosis system if accurately trained, may assist radiologists in detection and staging of hyperparathyroidism by providing reproducible and consistent analysis of bony erosion.<>
{"title":"Computer-aided detection and characterization of hyperparathyroidism in digital hand radiographs","authors":"C. Chang, H. Chan, L. Niklason, J. Crabbe, J. Mathews, M. Cobby, R. Adler","doi":"10.1109/CBMS.1992.245001","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245001","url":null,"abstract":"A computer algorithm has been developed to detect and possibly stage subperiosteal resorption from digitized hand radiographs for patients with primary or secondary hyperparathyroidism. The method can quantify the severity of bony resorption by analyzing the roughness of the radial phalangeal margins as projected on the hand radiographs. This margin is detected by a model-guided boundary-tracking scheme and its roughness is quantified by the mean-square variation and the first moment of the power spectrum. The preliminary results indicate that the computer-aided diagnosis system if accurately trained, may assist radiologists in detection and staging of hyperparathyroidism by providing reproducible and consistent analysis of bony erosion.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132895963","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 : 1992-06-14DOI: 10.1109/CBMS.1992.245014
R. Bellazzi, S. Quaglini, C. Berzuini
The authors describe GAMEES II (Graphical Modeling Environment for Expert Systems II), a computer system built to manage arrays of Bayesian belief networks (BBNs). With regard to biomedical applications, the system makes it possible to represent probabilistic knowledge both for the individual patient and for population, enlarging the class of problems actually represented through BBNs. In addition, mathematical models can be represented through the BBN formalism. These characteristics were exploited to perform model-based patient monitoring and population pharmacokinetic/pharmacodynamic studies. BBNs are built within GAMEES II through a graphical interface which is provided with some statistical knowledge, in order to facilitate the construction of sound statistical models. Probabilistic inference is performed by stochastic simulation algorithms that do not give rise to computational problems when dealing with complex networks.<>
{"title":"GAMEES II: an environment for building probabilistic expert systems based on arrays of Bayesian belief networks","authors":"R. Bellazzi, S. Quaglini, C. Berzuini","doi":"10.1109/CBMS.1992.245014","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245014","url":null,"abstract":"The authors describe GAMEES II (Graphical Modeling Environment for Expert Systems II), a computer system built to manage arrays of Bayesian belief networks (BBNs). With regard to biomedical applications, the system makes it possible to represent probabilistic knowledge both for the individual patient and for population, enlarging the class of problems actually represented through BBNs. In addition, mathematical models can be represented through the BBN formalism. These characteristics were exploited to perform model-based patient monitoring and population pharmacokinetic/pharmacodynamic studies. BBNs are built within GAMEES II through a graphical interface which is provided with some statistical knowledge, in order to facilitate the construction of sound statistical models. Probabilistic inference is performed by stochastic simulation algorithms that do not give rise to computational problems when dealing with complex networks.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114372720","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：