{"title":"Echocardiographic myocardial edge detection using an optimization protocol","authors":"N. Friedland, D. Adam","doi":"10.1109/CIC.1989.130572","DOIUrl":"https://doi.org/10.1109/CIC.1989.130572","url":null,"abstract":"The definition of the ventricular myocardial shape in echocardiographic ultrasound cross-sectional images is a difficult task due to the low quality of these images and the high noise levels present. An automatic protocol has been developed for high-speed detection of cavity boundaries in sequential 2-D echocardiograms. A 1-D cyclic Markov random field is defined, where the field's random variables are radii emanating from the cavity's center of gravity. An optimization using simulated annealing is performed upon an energy function defined by these random variables. This energy function is composed of a linear combination of elements which represent optimal edge detection, cavity wall smoothness, temporal continuity, and cavity volume maximization. The improved decision rule, which results from this optimization, produced highly encouraging results.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128168405","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":"Expert system for automatic phono-mechanocardiographic diagnosis","authors":"S. Khoor, E. Kékes, E. Berentey","doi":"10.1109/CIC.1989.130576","DOIUrl":"https://doi.org/10.1109/CIC.1989.130576","url":null,"abstract":"An expert system has been created for collecting, controlling, and categorizing phonomechanocardiographic data. LV (left ventricle) contraction, ejection, relaxation, and ventricular filling is detected by means of an apexcardiogram. The various forms and combinations of valvular heart disease are characterized by the phonospectra of the auscultation areas. The expert system Mechano has rule-based knowledge representation, backward chaining, uncertainty handling and explanation facilities. The database consists of data on 200 patients with ischemic heart disease and 140 patients with valvular heart disease. By using question nets the digitalized knowledge elements of the apex (amplitude-time intervals) and the phonomap (location, duration, amplitude of sounds, and murmurs) are automatically collected. The diagnosis of N different forms of valvular heart disease and the evaluation of LV functions are based on diagnosis rules containing values of possibilities determined by multiple statistical models (regression, factor, and cluster). The program, implemented on a PC, is written in Turbo Prolog.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"62 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129943309","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. Bortolan, C. Cavaggion, R. Degani, M. Bressan, P. Marinato
{"title":"The role of patient history in a decision support system","authors":"G. Bortolan, C. Cavaggion, R. Degani, M. Bressan, P. Marinato","doi":"10.1109/CIC.1989.130565","DOIUrl":"https://doi.org/10.1109/CIC.1989.130565","url":null,"abstract":"The management of the temporal information contained in patient histories is investigated. The problems connected with the use of patient histories in both information systems and decision support systems are taken into account. An adequate formalization based on time intervals is suggested in order to capture both precise and imprecise information. An example of the use of patient history in the context of the management of cardiac arrhythmias is described. The information system under development is based on the ORACLE relational database management system, while the decision support system uses the knowledge engineering tool ART-Inference (Automated Reasoning Tool).<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124581462","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":"MRI estimation of turbulent abnormalities in blood flow by improved multiparametric encoding gradients","authors":"D. Kwiat, S. Einav, D. Elad","doi":"10.1109/CIC.1989.130526","DOIUrl":"https://doi.org/10.1109/CIC.1989.130526","url":null,"abstract":"A novel magnetic resonance approach to imaging turbulence in the velocity profiles in major blood vessels is presented. A nuclear magnetic resonance (NMR) image, in general, is dependent on parameters like r, v, a, which represent deterministic parameters of motion. In addition, spins undergo random motion such as diffusion and turbulence, which cannot be described by a predetermined set of parameters of motion. The differentiation between turbulent and nonturbulent flow is based on the deterministic or indeterministic nature of the flow as a function of time. A method of building up a general gradient from a basic set of gradients is investigated here. Image blurring due to the nondeterministic behavior of spins (e.g. diffusion and turbulence) is not removed by this technique of a composite gradient encoding field. This fact is the key to the possibility of identifying regions of turbulent flow. Because of its random nature, elimination of turbulent effects by use of a deterministic method is bound to fail. On the other hand, regions of turbulent flow may be identified owing to signal decrease from those regions.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133188993","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. Coppini, S. Cagnoni, M. Demi, A. L'Abbate, P. Marraccini, G. Valli
{"title":"A knowledge-based method for 3-D coronary imaging","authors":"G. Coppini, S. Cagnoni, M. Demi, A. L'Abbate, P. Marraccini, G. Valli","doi":"10.1109/CIC.1989.130510","DOIUrl":"https://doi.org/10.1109/CIC.1989.130510","url":null,"abstract":"A knowledge-based method for the 3-D reconstruction of coronary arteries using biplane angiography is described. The reconstruction problem was divided into two subproblems: (1) reconstruction of the tree skeleton and (2) reconstruction of the arterial cross section. Only the solution of the first subproblem is discussed here. Basically, the reconstruction of the tree skeleton was achieved by matching the projections of each vessel segment and subsequently backprojecting the coupled projections. As regards the matching phase, both imaging geometry and anatomical knowledge were used. In particular, owing to the allocation of epicardial vessels on a well-behaved ellipsoidlike surface, the projections of a given vessel segment must satisfy a set of geometrical conditions. These depend on the position of the vessel on the heart surface with respect to the X-ray sources. As for reconstruction of the coronary tree skeleton, an algorithm based on the imaging geometry, the bounding of the backprojection error, and a contiguity criterion was developed.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131413294","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":"Heart sound analysis using neural and statistical classifiers: a comparison","authors":"B. Dieter, Albert E. Bothe, U. Rengshausen","doi":"10.1109/CIC.1989.130582","DOIUrl":"https://doi.org/10.1109/CIC.1989.130582","url":null,"abstract":"The results of a classical pattern recognition approach to heart sound analysis are compared with those of a trained neural network classifier. Noise not correlated with the specific heart operation is reduced by use of adaptive digital online filtering. The results, indicating the advantages of learning neural classifiers, are regarded as being transferable to other applications.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124002563","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}
C. Burrell, A. McDonald, M. Rothman, R.I. Kitnev, K. Straughan, L. Moura, D. Giddens
{"title":"3-D computer visualization of arteries and blood flow-in vitro and in vivo","authors":"C. Burrell, A. McDonald, M. Rothman, R.I. Kitnev, K. Straughan, L. Moura, D. Giddens","doi":"10.1109/CIC.1989.130475","DOIUrl":"https://doi.org/10.1109/CIC.1989.130475","url":null,"abstract":"An extension to previously described work on the representation of arterial structures using three-dimensional solid modeling is presented. Data acquired using a special-purpose catheter-mounted ultrasound probe are used to reconstruct 3-D computer models of arterial sections in vitro and in vivo. The images are reconstructed in full voxel space, which allows powerful software manipulation. Preliminary work on tissue differentiation using arterial models and color coding of the image is included. In addition to 3-D arterial visualization, early work on 3-D flow field representation is presented. It is concluded that the combining 3-D visualization of an artery with the presentation of the associated 3-D flow field will result in significant clinical benefit in the assessment of arterial disease.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115427419","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 real-time personal computer based system for analysis of electrocardiograms","authors":"F. Jager, A. Jaklic, I. Koren, L. Gyergyek","doi":"10.1109/CIC.1989.130604","DOIUrl":"https://doi.org/10.1109/CIC.1989.130604","url":null,"abstract":"The authors have developed a real-time personal-computer-based system for analysis of single-lead electrocardiograms running on an IBM PC/AT personal computer or compatibles. It converts an analog ECG (electrocardiographic) signal coming from the ECG acquisition unit into digital form, monitors it on a video display, detects each incoming beat, displays heart rate, and recognizes some simple rhythm disorders (arrest, bradycardia, tachycardia). Each beat is classified into one of three different categories: normal, supraventricular (SVC), or ventricular ectopic (VEC). The system also computes average beats and from them determines some diagnostic parameters (R-wave amplitude, R/R1 ratio, J point level, ST slope, and ST integral). The results of the analysis are displayed and periodically updated. At the end of the analysis, histograms which show trends of global changes for heart rate, VECs/min, SVCs/min, R-wave amplitude, R/R1 ratio, J point level, ST slope, and ST integral can be viewed.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116819115","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":"Analysis of 24 hour heart rate variability in post-infarction patients","authors":"P. Albrecht, J. Bigger, R. Steinman, L. Rolnitzky","doi":"10.1109/CIC.1989.130478","DOIUrl":"https://doi.org/10.1109/CIC.1989.130478","url":null,"abstract":"Summary form only given. The 24-h heart rate variability (HRV) in 40 Holter tapes from the Multicenter Post-Infarction Research Group Study was examined. The first 20 Holters were part of a preliminary study which analyzed various time- and frequency-domain measures of HRV. The time-domain measures were based on the RR intervals and included the 24-h standard deviations of RR/sub n/ and RR/sub n-1/-RR/sub n/. The frequency-domain measures were based on a single 24-h HR spectrum and included the LO (0.01-0.15-Hz) power, HI (0.15-0.50-Hz) power, and the alpha , which characterized the low-frequency 1/f/sup alpha / tail of the power spectrum. The other 20 Holter tapes were used to see whether the HRV measures could be used as predictors of mortality. It was found that HI power and total HRV power clearly separated the 20 patients into two distinct groups of 10 patients each. However, belonging to a group was completely unrelated to mortality: half the members of each group died.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127490596","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":"DECGAP: an automatic ECG analysis program","authors":"F. Gritzali, G. Frangakis, G. Papakonstantinou","doi":"10.1109/CIC.1989.130485","DOIUrl":"https://doi.org/10.1109/CIC.1989.130485","url":null,"abstract":"A description is given of DECGAP (Democritos ElectroCardioGram Analysis Program), a program for the automatic ECG (electrocardiographic) analysis developed at the NRCPS 'Democritos'. The methods and algorithms used by DECGAP in the stages of preprocessing, detection-recognition, and parameter extraction of the ECG waves are described. Experimental and evaluation results are also given, with an actual ECG taken from the standard CSE ECG library. The DECGAP program uses a general transformation for the detection of all cardiac waves, which is valid for single and multichannel ECG. Only one threshold is used, which is automatically determined. The boundary recognition phase is avoided, since it is executed at the same time as detection and is obtained as a by-product. Correct boundary recognition makes the recognition of the waves, as well as the baseline drift correction, easy and precise, resulting in precise measurements of the waves.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"47 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130272810","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}