A Neural Network that Learns to Interpret Myocardial Planar Thallium Scintigrams

Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)

Bibtex Metadata Paper

Authors

Charles Rosenberg, Jacob Erel, Henri Atlan

Abstract

The planar thallium-201 myocardial perfusion scintigram is a widely used diagnostic technique for detecting and estimating the risk of coronary artery disease. Neural networks learned to interpret 100 thallium scinti(cid:173) grams as determined by individual expert ratings. Standard error back(cid:173) propagation was compared to standard LMS, and LMS combined with one layer of RBF units. Using the "leave-one-out" method, generaliza(cid:173) tion was tested on all 100 cases. Training time was determined automati(cid:173) cally from cross-validation perfonnance. Best perfonnance was attained by the RBF/LMS network with three hidden units per view and compares favorably with human experts.