Computer-aided diagnosis for pneumoconiosis using neural network

Computer-aided diagnosis for pneumoconiosis using Meural Network is presented The rounded opacities on the pneumoconiosis X-ray, photo are picked up quickly through a buck propagation (BP) neural network with several topical training patterns. The training patterns fi-om 0.6 mm(null set) to 4.0 mm(null set) are made cis simple circles. The neck problem for an automatic pneumoconiosis diagnosis has been to reject the unnecessary, part like ribs and vessel shades, In this paper such unnecessary parts are rejected well by the special technique called "moving normalization".. The new technique called moving normalization is developed here in order to made an appropriate bi-level RO1 image. The total evaluation is done from the size and figure categorization, Mary, simulation examples show that the proposed method gives much reliable result than traditional ones.