Computer-aided diagnosis for pneumoconiosis using neural network

A computer-aided diagnosis system for pneumoconiosis using a neural network is presented. The rounded opacities on the pneumoconiosis X-ray photographs are picked up quickly through a backpropagation (BP) neural network with several typical training patterns. Training patterns from 0.6 to 4.0 mm in diameter are made as simple circles. The main problem for automatic pneumoconiosis diagnosis in the past has been to reject unnecessary parts, like ribs and blood vessel shadows. In this paper, such unnecessary parts are rejected well by a special technique called “moving normalization”. This new technique has been developed in order to make an appropriate bi-level region-of-interest (ROI) image. The total evaluation is done from the size and figure categorization. Many simulation examples show that the proposed method gives much more reliable results than the traditional methods do