Clinical Decision Support System for Patients with Cardiopulmonary Function Using Image Processing

Abstract

Clinical decision support system for chest X-ray images was proposed in this paper, which is based on image processing and analysis methods to evaluate the normality of X-ray images. To segment lung regions from the chest X-ray images, threshold and morphological methods were applied. The feature selection and image measurement were performed to evaluate the normality of chest X-ray images. The results demonstrate that the segmentation results differ only marginally from the actual contours of lung regions and provide similar results with actual lung regions. Moreover, based on the measurement and feature selection, the interpretation of normality was facilitated, and the results of interpretation were similar with the diagnosis made by clinical experts.