Automatic detection method of lung cancers including ground-glass opacities from chest x-ray CT images

In this paper, we described an algorithm of automatic detection of ground glass opacities (GGO) from X-ray CT images. In this algorithm, at first, pathological shadow candidates are extracted by our variable N-Quoit filter which is a kind of mathematical morphology filter. Next, shadow candidates are classified into some classes using feature values calculated from the shadow candidates. By using discriminate functions, at last, shadow candidates are discriminated between normal shadows and abnormal ones. This method was examined by 38 samples (including GGO's shadows) of chest CT images, and proved to be very effective.