Wireless Capsule Endoscopy is a non-invasive diagnostic tool very considerate to the patient. It has enabled, for the first time, a painless diagnosis inside the gastrointestinal tract including the small bowel.
It has enabled, for the first time, a painless diagnosis inside the gastrointestinal (GI) tract including the small bowel. The pioneer company in this field of research was Given Imaging, which brought WCE into clinical practice in 2001 and filed a patent application in 2006. Over time, it has been successfully applied in detection of small bowel bleeding sources, Crohns disease, complications of coeliac disease, tumors and NSAID(Nonsteroidal Anti-Inflammatory Drugs) induced enteropathy.
The patient swallows a cylindrical plastic capsule. The capsule travels through the GI tract by peristaltic contractions, captures the images and transmits them in real time wirelessly to an external console worn by the patient. The images are recorded and stored in the console memory and can be uploaded to a computer for a visual inspection or automatic analysis immediately after the monitoring has been completed.
This method has expanded greatly in the past decade and new capsules have appeared. One of them is the PillCam ESO (Given Imaging), which was developed for the imaging of the esophagus. It has a faster frame rate (18fps) and images are acquired in a shorter time; 25 minutes until the capsule automatically turned off.
The capsule typically consists of an optical window and an imaging system for obtaining images. The imaging system includes a white LED illumination source, a CMOS imaging camera, and an optical system. The capsule further includes a transmitter and an antenna for transmitting the video signal, and a power source. The size of the capsule depends on the manufacturer and is usually about 10x25 mm. Internal batteries are powerful enough to supply the light source and complete the acquisition and transmission process, lasting up to 10 hours. Current capsules take frames at a rate between two and six per second on average, which results in many thousands of images; typically over 60,000. The image resolution is mostly 256x256 pixels.
It should be noted there are patients for whom WCE is not appropriate. It is not recommended to use WCE in those with known motility disorders, swallowing disorders or dementia. On the other hand, we can label WCE as an extraordinarily safe device to be used. Over 340,000 capsules have been deployed worldwide with no reported deaths and with a few side effects, published in 2006 by Pannezio. If there is suspicion of retention of the capsule in the GI tract, the check is carried out by normal X-ray and after the confirmation surgery is performed. For this reason, WCE is suitable only for patients who are medically fit for surgery.
The main obstacle in the massive usage of WCE is that the visual evaluation of the video is very time-consuming. It is supposed to be done by a trained endoscopist. Even if the software provided by the capsule producers offers certain supporting tools to simplify and speed up the process, it still takes at least one hour of a full concentration of the evaluator; in many cases over two hours. This led to the research of new algorithms for blood, ulcer, and tumor detection in the bowel.
Since the bleeding detection is a very frequent requirement and appears to be easily achievable, the largest group of papers has dealt with this challenge. The problem here is that the blood spots and traces do not have any typical texture and shape, and the blood color may vary in a wide range from light red through dark red to brown. This diversity in color is depending on types of disease, bleeding time, the position of the capsule and the surrounding conditions. The approaches, adopted by various authors differ from one another only in the color space they are working in. Traditional color spaces such as RGB and HSV have been commonly used but some authors proposed also specialized color spaces. Most of the methods extract the features at the pixel level, others use image blocks and some methods work with the image as a whole.
