{"title":"A phoneme recognition system using modular construction of time-delay neural networks","authors":"Thomas C. Wendell, K. Abdelhamied","doi":"10.1109/CBMS.1992.245041","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245041","url":null,"abstract":"Research on alternative approaches of representing phoneme data to be input into an artificial neural network and alterations that can be made in the network to reduce training time without sacrificing recognition rate is described. A modularly constructed time-delay neural network (TDNN) trained to identify English stop consonant phonemes under speaker-independent, continuous speech conditions was used. Samples of continuous speech were recorded from ten male speakers and phonemes were manually extracted. Extracted phonemes were less than the maximum input size for the TDNN, so data were shifted within the input window to allow recognition of the phoneme regardless of where the phoneme was presented within the input window. The TDNN contained 490 processing elements and over 12000 connections and was constructed in a modular fashion, allowing future expansion. Recognition rates as high as 98.8% were obtained for individual phonemes within modules, and overall recognition rates as high as 79.4% for all stop consonant phonemes were obtained.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"10 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":"129495431","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":"Local motion identification and correction schemes for ultrafast CT flow studies","authors":"C. Wolfkiel","doi":"10.1109/CBMS.1992.245019","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245019","url":null,"abstract":"Analysis of flow studies with ultrafast CT (computed tomography) generally assumes registration of a sequence of images acquired to measure time density curves produced by contrast medium enhancement. However, only under strict experimental conditions is registration possible for the heart and lungs. The author preliminary develops a method to detect local motion shifts from an unenhanced image and correct subsequent images as the contrast medium enhances different regions. This preliminary research shows that local motion correction algorithms may be applicable to ultrafast CT flow studies.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"73 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":"113965914","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":"Rectification of distortion in MRI for stereotaxy","authors":"S. Dong, J. Fitzpatrick, R. Maciunas","doi":"10.1109/CBMS.1992.244949","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244949","url":null,"abstract":"It is shown that it is possible to provide an effective, patient-specific correction to geometrical distortion in MRI (magnetic resonance imaging) for use in stereotaxy. The authors examine two correction techniques, each based on the acquisition of an additional image of the patient utilizing a reversed readout gradient. Information from the additional image is combined with that of the standard image to provide geometrically corrected coordinates for targets identified by a neurosurgeon. They have applied the technique retrospectively to images of a patient who has undergone stereotaxic surgery, and they show that large geometrical errors are corrected.<<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":"130106890","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":"An image computing system for the estimation and reconstruction of diffuse volume of an anti-cancer drug in liver tumours","authors":"H. Ip, S. Lam, M. Arnold, L. Kreel","doi":"10.1109/CBMS.1992.244924","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244924","url":null,"abstract":"Presents a medical image computing system which has been designed to extract and analyze quantitative information from a spatial sequence of CT (computed tomography) images. In particular, it has been applied to the quantitation and 3D reconstruction of the diffuse pattern of a radio-opaque anti-cancer drug, lipiodol-doxorubicin, in hepatocellular carcinoma. The PC-based system computes quantitative measures which can be used to assess the effectiveness of the chemotherapeutic treatment and to study the histology of the tumour. The system can provide a visualization of the tumour volume and quantification of drug absorption using 3D surface reconstruction and graphics techniques.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"143 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":"131843665","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":"A system for detecting chemically-induced changes in cerebral blood flow using transcranial Doppler sonography in a dog model","authors":"M. Drues, D. Hopper, D. N. Lange","doi":"10.1109/CBMS.1992.245004","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245004","url":null,"abstract":"An experiment designed to develop a computer-based system capable of detecting chemically induced changes in cerebral blood flow (CBF) in a dog before the onset of overt clinical or behavioral symptoms is discussed. The system uses transcranial Doppler sonography (TCD) to noninvasively measure changes in CBF after low-level exposure to deltamethrin. Since changes in CBF often occur before other clinical signs, a method of detecting these changes could be used to detect exposures to potentially hazardous chemicals. Initial results indicate that TCD does seem to be sensitive enough to detect changes in blood flow velocity caused by deltamethrin, but improvements in the methodology need to be made and more data need to be collected to try to obtain more consistent results.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"443 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":"132932241","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. Sundaramoorthy, W. Higgins, J. Hoford, E. Hoffman
{"title":"Graphical user interface system for automatic 3-D medical image analysis","authors":"G. Sundaramoorthy, W. Higgins, J. Hoford, E. Hoffman","doi":"10.1109/CBMS.1992.244920","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244920","url":null,"abstract":"Describes a graphical user interface system for constructing automatic image-segmentation processes for 3D medical-imaging applications. The system provides a user-friendly environment for prototyping, testing, and executing complex image-analysis processes and can interact with a graphics-based 3D medical image-analysis package. The interface links to a library of 1D, 2D, and 3D image-processing functions and can easily link to other functions created by the user. Demonstrations of the system are given for 3D left-ventricular chamber extraction and 3D upper-airway analysis.<<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":"114166548","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":"SPECT reconstruction using a backpropagation neural network implemented on a massively parallel SIMD computer","authors":"J. Kerr, E. Bartlett","doi":"10.1109/CBMS.1992.245026","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245026","url":null,"abstract":"The feasibility of reconstructing a single photon emission computed tomography (SPECT) image via the parallel implementation of a backpropagation neural network is shown. The MasPar MP-1 is a single-instruction multiple-data (SIMD) massively parallel machine, composed of a 128*128 array of 4-bit processors. The neural network is distributed on the array by dedicating a processor to each node and each interconnection of the network. An 8*8 SPECT image slice section is projected into eight planes. It is shown that, based on the projections, the neural network can produce the original SPECT slice image exactly. Likewise, when trained on two parallel slices, separated by one slice, the neural network is able to reproduce the center, untrained image to an RMS (root mean square) error of 0.001928.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"12 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":"122832666","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":"Visualization of wave propagation through a 3D strand of myocardium","authors":"Naim Alper, A. Pang, B. Kogan","doi":"10.1109/CBMS.1992.245034","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245034","url":null,"abstract":"The authors present recent results obtained from simulating the action potential generation and propagation through a thin 3-D cylindrical heart muscle bundle. These results represent the first step towards obtaining a more accurate understanding of wave propagation properties through striated muscles. Using a 3-D computational grid of 32*32*128 cells, a single muscle bundle was modeled. The individual fibers and inter-fiber matter making up the bundle were treated homogeneously. Using a modified FitzHugh-Nagumo equation called the Epsilon-4 model, the authors obtained the relationship of propagation speed as a function of cross-sectional depth. The variations in speed that were observed can be explained in terms of the different wave curvatures arising from different types of boundary conditions and the geometry of the pathway. From these observations, the authors construct experiments where unidirectional blocks can occur in geometries with low excitability and no flux borders.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"13 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":"129389426","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":"Design and implementation of a clinical MSI workstation","authors":"J. Sanders, W. Orrison","doi":"10.1109/CBMS.1992.244953","DOIUrl":"https://doi.org/10.1109/CBMS.1992.244953","url":null,"abstract":"It is noted that magnetic source imaging (MSI) has unique processing and presentation requirements that must be addressed for it to become incorporated into clinical practice. As the combination of multislice medical imaging, particularly magnetic resonance imaging (MRI), and magnetoencephalography (MEG) functional localization, MSI is heavily computer-dependent for data preparation and evaluation as well as for data generation. The general issues of volumetric display and manipulation are compounded by the necessity for geometric accuracy and for interactive preparation of the data to be clinically evaluated. The authors discuss the design and implementation of a workstation-based system for processing MRI and MEG data and generating the combination of functional/anatomical images.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"55 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":"132168678","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}
R. Hermida, F. Aguado, J. Fernández, D. Ayala, J. Rodríguez-Cervilla, J. M. Fraga
{"title":"Estimation of a neonatal cardiovascular risk score by biomedical discriminant analysis","authors":"R. Hermida, F. Aguado, J. Fernández, D. Ayala, J. Rodríguez-Cervilla, J. M. Fraga","doi":"10.1109/CBMS.1992.245003","DOIUrl":"https://doi.org/10.1109/CBMS.1992.245003","url":null,"abstract":"Genetics is a primary factory for the predisposition of a newborn to elevated blood pressure (BP) later in life. The search for an index for this factor, needed to assess, on the neonate, the success of failure of preventive interventions instituted on pregnant women, is discussed. This index could be based on characteristics of BP and heart rate (HR) variability during the first days after birth. In the search for such an index, the systolic and diastolic BP and HR of 150 newborns were automatically monitored at about 30-min intervals for 48 h starting early after birth. The newborns were assigned to a group of either a negative or positive family history of high BP. Circadian characteristics and descriptive statistics for the three circulatory variables were used for classification by a 'monotest', an all-subsets variable selection technique for biomedical discriminate analysis. The monotest is discussed in detail. When the 90% range of systolic BP was used as classifier, the monotest yielded a 69% total classification equivalent to prior criteria.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"85 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":"127131597","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}