Pulmonary nodule clarification method using two-dimensional cellular automaton

摘要

PROBLEM TO BE SOLVED: To extract a faint lung nodule shadow from a binary error diffusion image with respect to a lung nodule clarification image by using a two-dimensional cellular automaton and clarify it by an adaptive rank filter. SOLUTION: The lung nodule clarification method of the present invention is a stage of creating a lung nodule clarification image from a chest X-ray image, a stage of creating a background noise suppression image, and an error diffusion method for a pulmonary nodule clarification image. Is applied to create a binary error diffusion image, and an image in the initial state is created based on the rank of the pixel values in a predetermined region obtained by using a rank filter for the binary error diffusion image. The stage of creating and the stage of creating a binary point image by extracting a pale lung nodule shadow as a set of binary points by performing state transition by a two-dimensional cell automaton, and the stage of creating a binary point image and lungs. It has a stage of creating an adaptive rank lung nodule clarification image by synthesizing a nodule clarification image and a background noise suppression image, and a stage of outputting an adaptive rank pulmonary nodule clarification image. [Selection diagram] Fig. 2