Pub Date : 1997-03-11DOI: 10.1109/CBMS.1997.596420
A. Sarvazyan
Mechanical imaging (MI) is a new modality of medical imaging, mimicking palpatory diagnostics. MI provides a 3D reconstruction of the internal structures of body soft tissues using measurements of stress patterns on the surface of the investigated tissue. In contrast to other, existing methods of medical imaging which use sophisticated hardware such as superconductive magnets, expensive X-ray equipment and complex ultrasonic phased arrays, MI hardware consists of inexpensive mechanical sensors and a positioning system connected to a PC. The results of our pilot studies have proven the feasibility of the MI technology. Currently, devices for the MI of the prostate gland and breast are being developed. Recently, the first 3D MI of in-vivo prostate has been obtained. Preliminary data strongly suggest that MI technology is an efficient means of objectively evaluating and imaging the prostate, and of detecting prostate cancer.
{"title":"Knowledge-based mechanical imaging","authors":"A. Sarvazyan","doi":"10.1109/CBMS.1997.596420","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596420","url":null,"abstract":"Mechanical imaging (MI) is a new modality of medical imaging, mimicking palpatory diagnostics. MI provides a 3D reconstruction of the internal structures of body soft tissues using measurements of stress patterns on the surface of the investigated tissue. In contrast to other, existing methods of medical imaging which use sophisticated hardware such as superconductive magnets, expensive X-ray equipment and complex ultrasonic phased arrays, MI hardware consists of inexpensive mechanical sensors and a positioning system connected to a PC. The results of our pilot studies have proven the feasibility of the MI technology. Currently, devices for the MI of the prostate gland and breast are being developed. Recently, the first 3D MI of in-vivo prostate has been obtained. Preliminary data strongly suggest that MI technology is an efficient means of objectively evaluating and imaging the prostate, and of detecting prostate cancer.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"44 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":"114866838","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.1997.596411
M. Kukar, Ciril Groselj, I. Kononenko, J. Fettich
Ischaemic heart disease is one of the world's most important causes of mortality, so improvements and rationalization of diagnostic procedures would be very useful. The four diagnostic levels consist of evaluation of signs and symptoms of the disease and ECG (electrocardiogram) at rest, sequential ECG testing during the controlled exercise, myocardial scintigraphy and finally coronary angiography. The diagnostic process is stepwise and the results are interpreted hierarchically, i.e, the next step is necessary only if the results of the former are inconclusive. Because suggestibility is possible, the results of each step are interpreted individually and only the results of the highest step are valid. On the other hand, machine learning methods may be capable of objective interpretation of all available results for the same patient and in this way increase the diagnostic accuracy, sensitivity and specificity of each step. In the usual setting, the machine learning algorithms are tuned to maximize classification accuracy. In our case, the sensitivity and specificity were much more important, so we generalized the algorithms to take in account the variable misclassification costs. The costs can be tuned in order to bias the algorithms towards higher sensitivity or specificity. We conducted many experiments with four learning algorithms and different variations of our dataset (327 patients with completed diagnostic procedures). Our results show that improvements using machine learning techniques are reasonable and might find good use in practice.
{"title":"An application of machine learning in the diagnosis of ischaemic heart disease","authors":"M. Kukar, Ciril Groselj, I. Kononenko, J. Fettich","doi":"10.1109/CBMS.1997.596411","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596411","url":null,"abstract":"Ischaemic heart disease is one of the world's most important causes of mortality, so improvements and rationalization of diagnostic procedures would be very useful. The four diagnostic levels consist of evaluation of signs and symptoms of the disease and ECG (electrocardiogram) at rest, sequential ECG testing during the controlled exercise, myocardial scintigraphy and finally coronary angiography. The diagnostic process is stepwise and the results are interpreted hierarchically, i.e, the next step is necessary only if the results of the former are inconclusive. Because suggestibility is possible, the results of each step are interpreted individually and only the results of the highest step are valid. On the other hand, machine learning methods may be capable of objective interpretation of all available results for the same patient and in this way increase the diagnostic accuracy, sensitivity and specificity of each step. In the usual setting, the machine learning algorithms are tuned to maximize classification accuracy. In our case, the sensitivity and specificity were much more important, so we generalized the algorithms to take in account the variable misclassification costs. The costs can be tuned in order to bias the algorithms towards higher sensitivity or specificity. We conducted many experiments with four learning algorithms and different variations of our dataset (327 patients with completed diagnostic procedures). Our results show that improvements using machine learning techniques are reasonable and might find good use in practice.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"41 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":"115920377","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.1997.596427
S. Badjou, G. Powers, M. Tanas
The study of postural sway is of special interest because of its applications in clinical medicine. Currently, the most accurate device used to study postural sway is the force platform. It is however costly and nonportable. The authors introduce an alternative system that consists of a computer-interfaced ultrasonic device. Ultrasound is emitted by sonar and bounces back from the subject's body. The amplitude of motion of the center of gravity is calculated and displayed graphically in real time. They, and several researchers, have determined that the mean speed of sway is a parameter that could be used to quantify postural sway. They developed software to filter system noise and calculate the mean speed of sway accurately. They tested the sensitivity and reliability by performing measurements of a fixed distance, and of the anterior-posterior and medical-lateral sways of thirty young healthy subjects, 15 males and 15 females. The error on the mean speed of sway was found to be less than 1%. This is no less accurate than the best sway instruments they know of. The results are consistent with force-platform measurements, and demonstrate the reliability of the system, as a means to study accurately postural control.
{"title":"Ultrasonic measurement of postural stability and control","authors":"S. Badjou, G. Powers, M. Tanas","doi":"10.1109/CBMS.1997.596427","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596427","url":null,"abstract":"The study of postural sway is of special interest because of its applications in clinical medicine. Currently, the most accurate device used to study postural sway is the force platform. It is however costly and nonportable. The authors introduce an alternative system that consists of a computer-interfaced ultrasonic device. Ultrasound is emitted by sonar and bounces back from the subject's body. The amplitude of motion of the center of gravity is calculated and displayed graphically in real time. They, and several researchers, have determined that the mean speed of sway is a parameter that could be used to quantify postural sway. They developed software to filter system noise and calculate the mean speed of sway accurately. They tested the sensitivity and reliability by performing measurements of a fixed distance, and of the anterior-posterior and medical-lateral sways of thirty young healthy subjects, 15 males and 15 females. The error on the mean speed of sway was found to be less than 1%. This is no less accurate than the best sway instruments they know of. The results are consistent with force-platform measurements, and demonstrate the reliability of the system, as a means to study accurately postural control.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"295 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":"115394951","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.1997.596410
P. Merialdo, F. Bilotta, L. Fiorani, G. Gigante
Myocardial perfusion information is crucial in the clinical evaluation of patients with coronary artery disease. A software tool dedicated to the automated analysis of contrast echocardiographic images for the evaluation of myocardial perfusion is presented in this paper. The system recognizes the internal border of the heart during the transit of an ultrasound contrast bolus injection and draws regions of interest. For each region of interest, time intensity curves are derived in order to quantify segmental perfusion.
{"title":"Automated recognition of cardiac structures in echocontrast perfusion studies","authors":"P. Merialdo, F. Bilotta, L. Fiorani, G. Gigante","doi":"10.1109/CBMS.1997.596410","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596410","url":null,"abstract":"Myocardial perfusion information is crucial in the clinical evaluation of patients with coronary artery disease. A software tool dedicated to the automated analysis of contrast echocardiographic images for the evaluation of myocardial perfusion is presented in this paper. The system recognizes the internal border of the heart during the transit of an ultrasound contrast bolus injection and draws regions of interest. For each region of interest, time intensity curves are derived in order to quantify segmental perfusion.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"115 1 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":"117221805","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.1997.596408
A. Mehuys
The project "Patient en Dossier" is subsidized by the IWT through the Actionprogramme Informationtechnology for Telenet Vlaanderen. The project examines the influence of the "Law for the Protection of the Personal Privacy"/sup 2/ on the electronic medical record (EMR) and the increase of the involvement of the patient in his own health care process. The project started on 1.1.96 and will run for three years.
{"title":"The project \"Patient en Dossier\"","authors":"A. Mehuys","doi":"10.1109/CBMS.1997.596408","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596408","url":null,"abstract":"The project \"Patient en Dossier\" is subsidized by the IWT through the Actionprogramme Informationtechnology for Telenet Vlaanderen. The project examines the influence of the \"Law for the Protection of the Personal Privacy\"/sup 2/ on the electronic medical record (EMR) and the increase of the involvement of the patient in his own health care process. The project started on 1.1.96 and will run for three years.","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":"134537097","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.1997.596438
D. Pager
We describe the design and implementation of an automatic computer controlled infusion pump for administering oxytocin to a woman in labor, with emphasis on the hardware and software safety issues. The infusion is applied by means of timed pulses, as opposed to the more usual continuous infusion method. The basic study of the system and its efficiency was described by R.J. Willcourt et al. (1894), while the mathematical algorithms employed were described by D. Pager and R.J. Willcourt (1995), and a patent for the system was granted earlier this year (D. Pager and R.J. Willcourt, 1996). The software safety issues encompass the detection by the system of various kinds of undesirable patient parameters, such as excessively high intrauterine pressure, constant intrauterine pressure, the occurrence of series of contractions closely following each other whose amplitudes are all exceedingly high. The hardware safety issues relate to the reliability of the system, and measures for ensuring that malfunctions are intercepted without the possibility of inappropriate infusion actions.
{"title":"The design and implementation of an automatic computer-controlled infusion pump","authors":"D. Pager","doi":"10.1109/CBMS.1997.596438","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596438","url":null,"abstract":"We describe the design and implementation of an automatic computer controlled infusion pump for administering oxytocin to a woman in labor, with emphasis on the hardware and software safety issues. The infusion is applied by means of timed pulses, as opposed to the more usual continuous infusion method. The basic study of the system and its efficiency was described by R.J. Willcourt et al. (1894), while the mathematical algorithms employed were described by D. Pager and R.J. Willcourt (1995), and a patent for the system was granted earlier this year (D. Pager and R.J. Willcourt, 1996). The software safety issues encompass the detection by the system of various kinds of undesirable patient parameters, such as excessively high intrauterine pressure, constant intrauterine pressure, the occurrence of series of contractions closely following each other whose amplitudes are all exceedingly high. The hardware safety issues relate to the reliability of the system, and measures for ensuring that malfunctions are intercepted without the possibility of inappropriate infusion actions.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"48 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":"116236337","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.1997.596403
V. Cerný, R. Zajac
A computer support system works in our sonography laboratory providing essential services like the data-base for medical findings combined with the image data-base. The system is based on the digitization of the video-signal output of the sonograph. We have studied the possibility of easing various picture processing methods to further support the diagnosis-making process. We report here on our experience with three particular methods. So far the most successful method we have developed was the quasi-tomographical processing of images. We take up to 16 scans of the same section plane from different positions of the ultrasonic probe. The final image is obtained as a suitable average of the matched images. The method proved to be very helpful in the diagnostic process and is used on an everyday basis. On a somewhat more academic level we are studying the use of simple neural net classifiers to evaluate textural content in the images. The nets are trained on sets of texture patterns and then used to classify the testing samples. We present here two particular examples: classifying malignant tissue in testes and segmentation (sinus vs parenchyma) in kidney. Our experience with these methods is still limited. However, our conjecture is that the texture information can be used as a supportive tool in clinical praxis.
{"title":"Computer aided ultrasound laboratory","authors":"V. Cerný, R. Zajac","doi":"10.1109/CBMS.1997.596403","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596403","url":null,"abstract":"A computer support system works in our sonography laboratory providing essential services like the data-base for medical findings combined with the image data-base. The system is based on the digitization of the video-signal output of the sonograph. We have studied the possibility of easing various picture processing methods to further support the diagnosis-making process. We report here on our experience with three particular methods. So far the most successful method we have developed was the quasi-tomographical processing of images. We take up to 16 scans of the same section plane from different positions of the ultrasonic probe. The final image is obtained as a suitable average of the matched images. The method proved to be very helpful in the diagnostic process and is used on an everyday basis. On a somewhat more academic level we are studying the use of simple neural net classifiers to evaluate textural content in the images. The nets are trained on sets of texture patterns and then used to classify the testing samples. We present here two particular examples: classifying malignant tissue in testes and segmentation (sinus vs parenchyma) in kidney. Our experience with these methods is still limited. However, our conjecture is that the texture information can be used as a supportive tool in clinical praxis.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"262 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113997837","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.1997.596443
D. Luzi, F. Ricci, L. Serbanati
The first step in understanding information systems in health care units (HCUs) is to develop a conceptual model of HCU able to gather data and knowledge used by the management staff in order to plan, execute, control and evaluate the patient care process. An approach to HCU management modelling is presented in the paper. Our approach is centred on the use of guidelines for all activities which are carried out in HCU environments. Various guidelines may exist. Some of them are clinical, others are managerial. Among the most important managerial guidelines are the communication guidelines. They govern all communication activities inside or between HCUs. A model of guideline-based inter-HCUs communication is presented.
{"title":"Integrating clinical and managerial activities of health care units","authors":"D. Luzi, F. Ricci, L. Serbanati","doi":"10.1109/CBMS.1997.596443","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596443","url":null,"abstract":"The first step in understanding information systems in health care units (HCUs) is to develop a conceptual model of HCU able to gather data and knowledge used by the management staff in order to plan, execute, control and evaluate the patient care process. An approach to HCU management modelling is presented in the paper. Our approach is centred on the use of guidelines for all activities which are carried out in HCU environments. Various guidelines may exist. Some of them are clinical, others are managerial. Among the most important managerial guidelines are the communication guidelines. They govern all communication activities inside or between HCUs. A model of guideline-based inter-HCUs communication is presented.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"59 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":"133915275","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.1997.596444
M. Crudele, G. Clapworthy, M. Krokos, G. Salcito, Nickos Vasilonikolidakis
We describe a research project for the development of a system for cataloguing, retrieval and interactive manipulation of 3D models of pathological human organs from a distributed WWW database. The project aims to provide transmission and rendering of three-dimensional models of human pathologies (constructed mainly from MRI and CT slices), enhanced manipulation and fly-through functionality on the models, as well as 3D animation sequences of virtual endoscopy. The system supports standard PC platforms without specialised hardware, thereby allowing accessibility to the widest possible audience. The system will provide the end users with advanced imaging capabilities such as models derived from multi-modal inputs (CT and MRI), stereoscopic display and will incorporate a number of features such as model warping. In addition to interactive utilisation, the service will provide interactive platforms for education, incorporating monitoring and assessment, as well as for information and/or counselling exchange between users.
{"title":"A distributed database on the Internet of 3D models of human pathological organs","authors":"M. Crudele, G. Clapworthy, M. Krokos, G. Salcito, Nickos Vasilonikolidakis","doi":"10.1109/CBMS.1997.596444","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596444","url":null,"abstract":"We describe a research project for the development of a system for cataloguing, retrieval and interactive manipulation of 3D models of pathological human organs from a distributed WWW database. The project aims to provide transmission and rendering of three-dimensional models of human pathologies (constructed mainly from MRI and CT slices), enhanced manipulation and fly-through functionality on the models, as well as 3D animation sequences of virtual endoscopy. The system supports standard PC platforms without specialised hardware, thereby allowing accessibility to the widest possible audience. The system will provide the end users with advanced imaging capabilities such as models derived from multi-modal inputs (CT and MRI), stereoscopic display and will incorporate a number of features such as model warping. In addition to interactive utilisation, the service will provide interactive platforms for education, incorporating monitoring and assessment, as well as for information and/or counselling exchange between users.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"20 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":"132832418","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.1997.596421
D. Kovacevic, S. Lončarić
The paper presents a novel method for CT head image automatic segmentation. The images are obtained from patients having a spontaneous intra-cerebral brain hemorrhage (ICH). The results of the segmentation are images partitioned into five regions of interest corresponding to four tissue classes (skull, brain, calcifications and ICH) and background. Once the images are segmented it is possible to calculate various hemorrhage region parameters such as size, position, etc. The segmentation is performed in three major steps. In the first phase feature extraction and normalization is performed using a receptive field (RF). Experiments were performed to determine the optimal RF structure. Pixels are classified in the second phase using the radial basis function (RBF) artificial neural network. Experiments with different RBF network topologies were performed in order to determine the optimal basis functions, network size and a training algorithm. The segmentation results obtained using the RBF network were compared with results obtained by multi-layer perceptron neural network (MLP). In the third phase the image regions obtained by the RBF network were labeled using an expert system. Experiments have shown that the proposed method successfully performs image segmentation.
{"title":"Radial basis function-based image segmentation using a receptive field","authors":"D. Kovacevic, S. Lončarić","doi":"10.1109/CBMS.1997.596421","DOIUrl":"https://doi.org/10.1109/CBMS.1997.596421","url":null,"abstract":"The paper presents a novel method for CT head image automatic segmentation. The images are obtained from patients having a spontaneous intra-cerebral brain hemorrhage (ICH). The results of the segmentation are images partitioned into five regions of interest corresponding to four tissue classes (skull, brain, calcifications and ICH) and background. Once the images are segmented it is possible to calculate various hemorrhage region parameters such as size, position, etc. The segmentation is performed in three major steps. In the first phase feature extraction and normalization is performed using a receptive field (RF). Experiments were performed to determine the optimal RF structure. Pixels are classified in the second phase using the radial basis function (RBF) artificial neural network. Experiments with different RBF network topologies were performed in order to determine the optimal basis functions, network size and a training algorithm. The segmentation results obtained using the RBF network were compared with results obtained by multi-layer perceptron neural network (MLP). In the third phase the image regions obtained by the RBF network were labeled using an expert system. Experiments have shown that the proposed method successfully performs image segmentation.","PeriodicalId":292377,"journal":{"name":"Proceedings of Computer Based Medical Systems","volume":"11 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":"124963015","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：