Dongying Qin, B. Houchins, M. Parten, Nicole Parker, R. Homan, A. Petrosian
{"title":"A comparison of techniques for the prediction of epileptic seizures","authors":"Dongying Qin, B. Houchins, M. Parten, Nicole Parker, R. Homan, A. Petrosian","doi":"10.1109/CBMS.1995.465436","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465436","url":null,"abstract":"EEG signal analysis has been proposed for early warning of an epileptic seizure. A number of different signal analysis techniques are examined and compared using an example EEG signal. The objective of this comparison is to determine which analysis technique to use in an automatic, real time early warning system for epileptic patients.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117276774","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}
G. Rovetta, P. Monteforte, G. Bianchi, S. Rovetta, R. Zunino
{"title":"Validation of a large medical database","authors":"G. Rovetta, P. Monteforte, G. Bianchi, S. Rovetta, R. Zunino","doi":"10.1109/CBMS.1995.465447","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465447","url":null,"abstract":"Complex clinical problems involving huge experimental evidence require a preliminary validation of observed data. This may avoid biasing due to incorrect sampling and clarify the sample distribution by showing data-inherent regularities. The paper describes the application of unsupervised models of neural networks to the analysis of a very large set of clinical records for the study of osteoporosis. The main result obtained lies in showing the overall uniformity of the data distribution, which indicates a correct unbiased sampling of the considered population.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130834649","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}
{"title":"In-vivo tissue characterization of brain by synthetic MR proton relaxation and statistical chisquares parameter maps","authors":"K. Cheng, J. Hazle, E. Jackson, R. Price, K. Ang","doi":"10.1109/CBMS.1995.465406","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465406","url":null,"abstract":"Proton spin density (N[H])- and relaxation time (T1 and T2)-weighted magnetic resonance (MR) images at different anatomical sections and/or orientations of the brain are routinely used for clinical MR diagnosis of various types of intracranial disorders and injuries. However, numerical information pertaining to the relaxation behavior of water in the brain is very difficult to be extracted and quantified form these conventional MR images. Using Carr-Purcell-Meiboom-Gill spin echo imaging sequences, multiple raw MR images of human and animal brains with selected values of repetition and echo times were acquired using a clinical 1.5-Tesla MR scanner. Using a non-interactive nonlinear regression algorithm, first-order (N[H], T1 and T2) and higher order (biexponential and distribution) T2 proton relaxation parameter maps, as well as a new set of statistical chi-square parameter maps of the brains were calculated from the raw MR images pixel-by-pixel. We propose that the use of calculated relaxation and chi-square maps may further improve the capability of MRI in clinical diagnosis and staging of intercranial disorders and injuries.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130856069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Kokol, J. Završnik, K. Kancler, M. Bigec, I. Malcic, D. Ivancevic, B. Tepes
{"title":"Diagnostic process optimisation: a two levelled approach [paediatric cardiology]","authors":"P. Kokol, J. Završnik, K. Kancler, M. Bigec, I. Malcic, D. Ivancevic, B. Tepes","doi":"10.1109/CBMS.1995.465423","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465423","url":null,"abstract":"Every-day routine responsibilities of medical staff can be enormous. The appearance of new computer-based information technology has eased these activities enormously and enabled medical staff to perform their work more efficiently and effectively. One possible application of computer technology in paediatric cardiology, where examinations can be very expensive, is the optimisation of the diagnostic process in a manner to minimise the number of examinations, and to reduce costs and the risk to the patients. In this paper, we present an information system which supports diagnostic process optimisation (DIAPRO) and the approach used to design it.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121604283","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}
{"title":"Prostate ultrasound image analysis: localization of cancer lesions to assist biopsy","authors":"A. Houston, S. Premkumar, D. Pitts, R. Babaian","doi":"10.1109/CBMS.1995.465441","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465441","url":null,"abstract":"Prostate cancer is the most commonly diagnosed cancer and second cause of cancer deaths in American men. Transrectal ultrasound imaging has been an acclaimed choice for systematic analysis of the internal architecture of the prostate gland and also for guiding the selection of biopsy tissue cores from suspicious lesions. The current accuracy of visual interpretation for identifying the presence of cancer from prostate ultrasound images is low. The present study addresses the statistical distribution of digital gray scale values to compare cancerous and noncancerous biopsy sites within a gland. Analyses of selected features from these data, for a limited number of cases, indicate significant differences between cancerous and non-cancerous biopsies with a retrospective biopsy classification accuracy of approximately 80%. This approach therefore shows promise for objective interpretation with improved accuracy.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"7 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116789742","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}
{"title":"Simple cyropreservation techniques to preserve cellular ultrastructure of freeze fracture or sectioning prior to image analysis","authors":"C. Haigler, M. Grimson","doi":"10.1109/CBMS.1995.465445","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465445","url":null,"abstract":"Summary form only given. Computer-assisted computer imaging techniques are limited in their value by the extent to which the structure being analyzed deviates from its native state. For intracellular structures, traditional chemical fixations have been well established to leave substantial room for deviation from reality. For example, membrane-bound vesicles can be relocated or abnormally fused and molecules can be extracted. In addition, traditional techniques can substantially diminish antigenicity in immunocytochemical localization protocols. Although the alternative of freeze-substitution and ultra-low temperature embedding are established in the literature, many people have not switched to these techniques. For structures deep within a tissue (up to about 25 /spl mu/m), these techniques will require an expensive high-pressure freezer (approximately $150,000.000). However, for structures on the surface of a tissue block, small organisms, or single cells in suspension, we describe fairly simple apparatus and reliable techniques to achieve ultra-rapid freezing routinely ( up to about 30 /spl mu/m). In addition, we describe preliminary efforts to use computer-assisted electron tomography to reconstruct three dimensional structures from freeze fracture and sectioned images.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129877321","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}
{"title":"Remote respiratory monitor","authors":"R. Peters","doi":"10.1109/CBMS.1995.465427","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465427","url":null,"abstract":"A new approach to respiration monitoring is made possible by the invention of a broad new class of patent-pending sensors that are labeled 'symmetric differential capacitive' (SDC). A pressure transducer of SDC type is used in the described remote respiratory monitor. It is similar to others that use a diaphragm, but its improved electrical symmetry permits greater sensitivity than was previously possible in inexpensive devices. As developed and employed, the SDC sensors have been routinely part of automated systems. Used with a personal computer, they are opening up new vistas in physics, both in research and in pedagogy. Thus, it is expected that their impact in medical areas along similar lines could also be significant.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128828249","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}
J. Keller, P. Gader, O. Sjahputera, C. Caldwell, T. Huang
{"title":"A fuzzy logic rule-based system for chromosome recognition","authors":"J. Keller, P. Gader, O. Sjahputera, C. Caldwell, T. Huang","doi":"10.1109/CBMS.1995.465438","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465438","url":null,"abstract":"One of the longest standing problems in medical image analysis is that of the automated recognition of chromosomes from images of a metaphase spread of a cell. This process of visualizing and categorizing the chromosomes within a cell, called karyotyping, is a key factor in many medical procedures. It is a labor intensive activity, and hence, is a great candidate for automation. However, there are many sources of uncertainty in this problem domain, making complete karyotyping a difficult problem. We describe how fuzzy logic is being inserted into a complete karyotyping system to deal with uncertainty in similar chromosome classes.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129843954","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}
{"title":"Multiresolution wavelet decomposition and neuro-fuzzy clustering for segmentation of radiographic images","authors":"S. Pemmaraju, S. Mitra, Y. Shieh, G. H. Roberson","doi":"10.1109/CBMS.1995.465430","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465430","url":null,"abstract":"Segmentation of medical images is a challenging problem in the field of image analysis. Several diagnostics are based on proper segmentation of the digitized image. Segmentation of medical images is needed for applications involving estimation of the boundary of an object, classification of tissue abnormalities, shape analysis, contour detection and texture segmentation. Despite the existence of several techniques, segmentation of specific medical images still remains a crucial problem due to the complex nature of most medical images. A multiresolution image representation approach is used for better analyzing the information present in an image. We use multiresolution wavelet decomposition to reconstruct the original image such that it contains all the salient features relevant to segmentation and is devoid of the low frequency noise and texture information that can be ignored while segmenting the image. An unsupervised neural network with fuzzy learning rules is then used to segment the reconstructed image.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127414809","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}
{"title":"Choosing the right RIS to survive the health care reform","authors":"Y. Shieh, G. H. Roberson","doi":"10.1109/CBMS.1995.465446","DOIUrl":"https://doi.org/10.1109/CBMS.1995.465446","url":null,"abstract":"Health care reform is rapidly taking place. Cost-effectiveness is one of the key factors that determine who will survive and prosper. Under such a competitive business climate, information technology plays an extremely important role in the operation of tomorrow's radiology department. Radiology information system (RIS) technology has been around for many years. In spite of its promise to maximize the utilization of resources and to boost productivity, only one third of all US hospitals currently have an RIS. One of the reasons that delayed the installation of RIS is the great confusion arising from the potential promised by new technologies and the fear of incompatibility with existing equipment. The University Medical Center Computer Department in collaboration with IDX has developed an in-house RIS over the past few years. For several months, an extensive survey of the commercial RIS products to replace this system has been conducted. With experience in in-house development and exposure to commercial products, this paper discusses the necessary functions that a good RIS should have and a checklist of important features in the process of selecting a good RIS.<<ETX>>","PeriodicalId":254366,"journal":{"name":"Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133122579","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}