DocumentCode :
948088
Title :
Neural network and fuzzy clustering approach for automatic diagnosis of coronary artery disease in nuclear medicine
Author :
Bagher-Ebadian, Hassan ; Soltanian-Zadeh, Hamid ; Setayeshi, Saeed ; Smith, Stephen T.
Author_Institution :
Phys. Dept., Amir-Kabir Univ. of Technol., Tehran, Iran
Volume :
51
Issue :
1
fYear :
2004
Firstpage :
184
Lastpage :
192
Abstract :
We investigated feasibility of using fuzzy clustering and artificial neural network to predict coronary artery disease (CAD) in acute phase from planar and gated SPECT nuclear medicine images. We developed an automatic computerized scheme that helps physicians diagnose coronary artery disease based on 99Tc-Sestamibi myocardial perfusion images. Our study consisted of two separate studies with respect to patient population and imaging method. The first study included 58 subjects (30 male, 28 female) studies using planar rest and stress imaging and a second patient subset of 115 subjects (61 male, 54 female) using gated rest/stress SPECT imaging. After the myocardial perfusion scans, patients also had coronary angiography within three months of the imaging. Signal-to-noise ratio was improved by segmentation of myocardium from its background in both studies using fuzzy clustering with the Picard iteration algorithm. We extracted a set of adaptive features consistent with nature of nuclear medicine imaging and myocardium anatomy. Features were optimized and selected based on maximum separation in multidimensional feature space. A back-propagation artificial neural network (ANN) classifier was trained and tested for each study using the optimal features and the results of coronary angiographies as input and outputs, respectively. ANNs were trained, optimized, and tested using leave-one-out and Poh´s Implementation of Weigned-Rumelhart-Huberman (PIWRH) methods, to diagnose the normal and abnormal patients based on their coronary angiograms. The performances of the optimal ANNs were analyzed by receiver operator characteristic (ROC) method. Results of ANN in the first study were compared to those of the physicians in nuclear medicine ward and two other physicians using ROC method. Results of ANN for the second study were compared to those of the nuclear medicine ward using ROC method. Both subsets demonstrate that the proposed method outperforms visual diagnosis and is therefore a useful adjunct for CAD diagnosis from planar and gated SPECT images.
Keywords :
angiocardiography; iterative methods; neural nets; single photon emission computed tomography; 99Tc-Sestamibi myocardial perfusion images; Picard iteration algorithm; Poh implementation of Weigned-Rumelhart-Huberman methods; acute phase; artificial neural network; automatic computerized scheme; automatic diagnosis; back-propagation artificial neural network; coronary angiography; coronary artery disease; fuzzy clustering approach; gated SPECT nuclear medicine images; imaging method; multidimensional feature space; myocardial perfusion scans; myocardium anatomy; myocardium segmentation; nuclear medicine; patient population; planar SPECT nuclear medicine images; planar rest imaging; receiver operator characteristic method; signal-to-noise ratio; stress imaging; Angiography; Artificial neural networks; Coronary arteriosclerosis; Fuzzy neural networks; Myocardium; Neural networks; Nuclear medicine; Physics computing; Stress; Testing;
fLanguage :
English
Journal_Title :
Nuclear Science, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9499
Type :
jour
DOI :
10.1109/TNS.2003.823047
Filename :
1282081
Link To Document :
بازگشت