Extraction of tumor regions keeping boundary shape information from chest X-ray CT images and benign/malignant discrimination

Abstract

In this paper, we propose a new method to extract tumor regions from thin-slice chest X-ray CT images. The tumor regions that are used for benign/malignant discrimination must keep boundary shape information as exactly as possible because the tumor regions specify the regions for which features are calculated. The proposed method is based on the thresholding of CT values and distance. Since the change of CT values suggest the existence of tumors, it is reasonable to use thresholding of CT values for extraction of tumor regions. We assume that the position of tumors are known beforehand because the thin-slice chest X-ray CT images are taken with the view to be used in the close medical examination. We applied the method to 78 practical CT images, and 67 tumors were extracted properly. Furthermore, the benign/malignant discrimination was carried out suitably using the tumor regions extracted by the proposed method. The correct classification rate was improved from 0.84 to 0.91. This shows the usefulness of the method developed here.