INTELLIGENT DECISION SUPPORT SYSTEM FOR FUNCTIONAL DIAGNOSTICS WITH GAMMA CAMERA
Науковий журнал «Радіоелектроніка, інформатика, управління»
Переглянути архів Інформація| Поле | Співвідношення | |
| ##plugins.schemas.marc.fields.042.name## |
dc |
|
| ##plugins.schemas.marc.fields.245.name## |
INTELLIGENT DECISION SUPPORT SYSTEM FOR FUNCTIONAL DIAGNOSTICS WITH GAMMA CAMERA |
|
| ##plugins.schemas.marc.fields.720.name## |
Moskalenko, V. V.; Sumy State University, Sumy Rizhova, A. S.; Sumy State University, Sumy Dovbysh, A. S.; Sumy State University, Sumy |
|
| ##plugins.schemas.marc.fields.653.name## |
segmentation, cluster-analysis, information-extreme intellectual technology, set of classes, feature set, radionuclide diagnostics, gamma-camera, optimization, swarm algorithm. |
|
| ##plugins.schemas.marc.fields.520.name## |
Method of information synthesis of a decision support system for radionuclide diagnostics of human organs during dynamic observation<br />on gamma camera is proposed. By way of example, the process of diagnosis kidneys’ functional state is considered. Segmentation algorithm series of scintigrams based on information-extreme cluster analysis of time-spatial vectors of pixel brightness changing, algorithm of recognition functional state of kidneys using renogram curves based on information-extreme machine learning are developed. The developed information-extreme algorithms based on adaptive binary coding of feature values and on optimization of geometrical parameters of feature space partitioning into classes equivalence during the process of maximizing of decision support system’s information ability. The modified information criterion for estimate efficiency of machine learning which expressed in terms of false omission rate and positive predictive value is proposed. The results of parameters optimization of decision rules using the particle swarm algorithm are analyzed. The result of the automatic segmentation of scintigraphic data intended to highlight regions of interests, result of automatic classification of renogram curves intended to make-diagnosis are shown. Set of classes characterized three functional states of kidneys. The first class characterizes the normal state of renal function without any apparent violations. The second class characterizes renal parenchymal disease. The third class characterizes a impaired impaired urinary dynamics. It was concluded about the accuracy of the decision rules. |
|
| ##plugins.schemas.marc.fields.260.name## |
Zaporizhzhya National Technical University 2016-01-25 15:28:44 |
|
| ##plugins.schemas.marc.fields.856.name## |
application/pdf http://ric.zntu.edu.ua/article/view/60382 |
|
| ##plugins.schemas.marc.fields.786.name## |
Radio Electronics, Computer Science, Control; No 4 (2015): Radio Electronics, Computer Science, Control |
|
| ##plugins.schemas.marc.fields.546.name## |
uk |
|
| ##plugins.schemas.marc.fields.540.name## |
Copyright (c) 2016 V. V. Moskalenko, A. S. Rizhova, A. S. Dovbysh |
|