A review of machine-vision-based analysis of wireless capsule endoscopy video

Wireless capsule endoscopy (WCE) enables a physician to diagnose a patient's digestive system without surgical procedures. However, it takes 1-2 hours for a gastroenterologist to examine the video. To speed up the review process, a number of analysis techniques based on machine vision have been proposed by computer science researchers. In order to train a machine to understand the semantics of an image, the image contents need to be translated into numerical form first. The numerical form of the image is known as image abstraction. The process of selecting relevant image features is often determined by the modality of medical images and the nature of the diagnoses. For example, there are radiographic projection-based images (e.g., X-rays and PET scans), tomography-based images (e.g., MRT and CT scans), and photography-based images (e.g., endoscopy, dermatology, and microscopic histology). Each modality imposes unique image-dependent restrictions for automatic and medically meaningful image abstraction processes. In this paper, we review the current development of machine-vision-based analysis of WCE video, focusing on the research that identifies specific gastrointestinal (GI) pathology and methods of shot boundary detection.