DETECTION OF LUNG NODULES IN DIGITAL CHEST RADIOGRAPHS USING ARTIFICIAL NEURAL NETWORKS - A PILOT-STUDY

Radiologists can fail to detect up to 30% of pulmonary nodules in chest radiographs. A back-propagation neural network was used to detect lung nodules in digital chest radiographs to assist radiologists in the diagnosis of lung cancer. Regions of interest (ROls) that contained nodules and normal tissues in the lung were selected from digitized chest radiographs by a previously developed computer-aided diagnosis (CAD) scheme. Different preprocessing techniques were used to produce input data to the neural network. The performance of the neural network was evaluated by receiver operating characteristic (ROC) analysis. We found that subsampling of original 64- x 64-pixel ROls to smaller 8- x 8-pixel ROls provides the optimal preprocessing for the neural network to distinguish ROls containing nodules from false-positive ROls containing normal regions, The neural network was able to detect obvious nodules very well with an A, value (area under ROC curve) of 0.93, but was unable to detect subtle nodules. However, with a training method that uses different orientations of the original ROls, we were able to improve the performance of the neural network to detect subtle nodules. Artificial neural networks have the potential to serve as a useful classifier to help to eliminate the false-positive detections of the CAD scheme. (C) 1995 by W.B. Saunders Company