Automatic digital colon cleansing in CT scan images

Abstract

In Thailand, cancer is one of the most important leading causes of fidelity sickness in Thai people have died from cancer more and more and the death rate tends to increase every year. Cancer can be found in several organs and among them, colon cancer is one of the most deadly diseases. However, people's lives can be saved if cancers can be detected at an early stage. The system called Virtual Colonoscopy (VC) which requires a patient to take CT scan images from abdominal to anus, is a technique used to help doctor diagnose colon to find or detect polyps inside the colon. Virtual colonoscopy consists of patient preparation, electronic colon cleansing, 3D reconstruction of colon. Virtual colonoscopy gives 3D view inside the colon that enables a doctor to diagnose more easily and navigate inside the colon along the center line to measure the distance from the anus to a suspicious volume and mark it as polyp(before becoming tumor) or discard it. The patient will feel less invasive and less painful from passing the colonoscopy optical camera through their anus and colon. Electronic colon cleansing (ECC) presented in this thesis is an alternative method that can be used to remove remaining tagged fecal material (stools) from abdominal CT-scan image during colon cancer screening in virtual colonoscopy (VC) after inflating CO₂ to extend the colon diameter and to take CT scan images. This thesis presents a new method for automatic electronic colon cleansing using gradient magnitude and similarity measure to detect and remove tagged material from colon in CTC images which is a method in Virtual colonoscopy system.