Automated Extraction of the Essential Region in Computer-Aided Diagnosis of Helicobacter Pylori Infection Using Gastric X-ray Images

Abstract

To design a computer-aided diagnosis of helicobacter pylori infection, this paper presents a method for extracting the essential region for diagnosing the infection from gastric X-ray images automatically. Although the automated extraction has a core role as a pre-processing method in the diagnosis, all the existing systems for diagnosing the infection or gastric cancer using X-ray images have never contained the extraction into the systems due to difficulty of the extraction. In the proposed method, first, two objects of the barium-pool and the spinal column are extracted. Next, with the clue of these objects and difference of density distributions between the gastric area and its outer area, the essential region is extracted by detecting the contour of gastric area. Experimental results for the proposed method using 106 images have shown that the proposed method correctly extracted the essential region from 87 images.