IDENTIFICATION OF A HYPOPERFUSED SEGMENT IN BULLS-EYE MYOCARDIAL PERFUSION IMAGES USING A FEED FORWARD NEURAL-NETWORK

Artificial neural networks are computer systems which can be trained t o recognize similarities in patterns and which learn by example; one o f the more straightforward types being the feed forward neural network (FFNN). We previously reported the use of FFNNs for classification of hypoperfusion patterns in bull's-eye representation of Tl-201 Single photon emission tomography myocardial perfusion studies and showed tha t, when such an image was divided into 24 segments, FFNNs could detect perfusion defects without direct comparison to a normal data base. Th is has been extended in this investigation to assess the ability of an FFNN, trained on data in which only a single segment was hypoperfused , to detect this abnormal segment when the hypoperfusion pattern of th e other segments in the image varied. The results indicated that the n etwork could reliably determine whether a segment was normally or unde r perfused, with accuracies of 99% and 100%, respectively, if all othe r segments were normally perfused. It could also reliably detect a nor mally perfused segment, even if other segments were hypoperfused, with accuracies of 95% and 98%. The network was less reliable, however, in detecting a hypoperfused segment when other segments were also hypope rfused. showing accuracies of only 74% and 88%.