Features for Evaluating Gastric Atrophy Using X-ray Images

Abstract

This paper presents image features for evaluating progression of gastric atrophy from gastric X-ray images. In the proposed method, after the target area for the diagnosis is determined and the gastric folds are extracted, the features are extracted from the area based on the diagnostic index for reading the atrophy from the X-ray images. Concretely, the features measure quantity of the folds and parallelism of the folds. In experiments for examining performance of the proposed features, classifications of normal, moderate, and severe cases were conducted to 117 gastric X-ray images by regarding the features as variables of discriminant machines, and experimental results have shown that the proposed features are effective well to measure the progression.