Pseudo-normal Image Synthesis from Chest Radiograph Database for Lung Nodule Detection

Abstract

The purpose of this study is to develop a new computer aided diagnosis (CAD) system for a plain chest radiograph. It is difficult to distinguish lung nodules from a chest radiograph. Therefore, CAD systems enhancing the lung nodules have been actively studied. The most notable achievements are temporal subtraction (TS) based systems. The TS method can suppress false alarms comparatively because it uses the chest radiograph of the same person. However, the TS method cannot be applied to initial visitors because it requires the past chest radiograph of themselves. In this study, to overcome the absence of past image for a patient himself, a pseudo-normal image is synthesized from a database containing other patient’s chest radiographs that have already been diagnosed as normal by medical specialists. And then, the lung nodules are emphasized by subtracting the synthesized normal image from the target image.