ARTIFICIAL NEURAL NETWORKS FOR SINGLE-PHOTON EMISSION COMPUTED-TOMOGRAPHY - A STUDY OF COLD LESION DETECTION AND LOCALIZATION

RATIONALE AND OBJECTIVES. An artificial neural network was developed f or cold lesion detection and localization in single photon emission co mputed tomography (SPECT) images. METHODS. The network was trained for several noise levels and lesion sizes to identify lesions located in the center of small image neighborhoods. When scrolled across an image the trained network was able to identify cold abnormalities. The diag nostic performance of the technique was evaluated at two noise levels (50,000 and 100,000 counts/slice) and for two lesion sizes (radius: 1. 0 cm and 1.5 cm) using the free-response operating characteristic (FRO C) analysis. Furthermore, the same network was tested on a situation i t was not trained on (80,000 counts/slice and a different reconstructi on filter). RESULTS. The neural network showed high sensitivity and sm all false-positive rates per image for all test situations. These resu lts suggest that neural networks are promising tools for computer-aide d clinical diagnosis in SPECT.