Segmentation and Feature Extraction of Endoscopic Images for Making Diagnosis of Acute Appendicitis

Abstract

In recent years, digital endoscopy has established as key technology for medical screenings and minimally invasive surgery. Endoscopy image processing techniques have been applied to the diagnosis of diseases. In this paper, an effective approach is proposed to process endoscopic images to detect acute appendicitis. For this purpose, we first introduced image enhancement techniques that allow us to improve quality of endoscopic image for further processing. A simple and effective image segmentation technique was developed to detect vessels and vermiform appendix. The hierarchical set of features have been extracted for detecting acute appendicitis. It includes geometrical, colorimetric, densitometric, and topological features. For each appendicitis feature discriminant indexes have been introduced for diagnosis. This method has achieved good results in clinical application.