Sequential Image Analysis for Computer-Aided Wireless Endoscopy

Michal Drozdzal

Dr. Petia Ivanova Radeva

Medical Imaging Laboratory (MILab)

Wireless Capsule Endoscopy (WCE) is a technique for inner-visualization of the entire small intestine and, thus, offers an interesting perspective on intestinal motility. The two major drawbacks of this technique are: 1) huge amount of data acquired by WCE makes the motility analysis tedious and 2) since the capsule is the first tool that offers complete inner-visualization of the small intestine, the exact importance of the observed events is still an open issue. Therefore, in this thesis, a novel computer-aided system for intestinal motility analysis is presented. The goal of the system is to provide an easily-comprehensible visual description of motility-related intestinal events to a physician. In order to do so, several tools based either on computer vision concepts or on machine learning techniques are presented. A method for transforming 3D video signal to a holistic image of intestinal motility, called motility bar, is proposed. The method calculates the optimal mapping from video into image from the intestinal motility point of view. To characterize intestinal motility, methods for automatic extraction of motility information from WCE are presented. Two of them are based on the motility bar and two of them are based on frame-per-frame analysis. In particular, four algorithms dealing with the problems of intestinal contraction detection, lumen size estimation, intestinal content characterization and wrinkle frame detection are proposed and validated. The results of the algorithms are converted into sequential features using an online statistical test. This test is designed to work with multivariate data streams. To this end, we propose a novel formulation of concentration inequality that is introduced into a robust adaptive windowing algorithm for multivariate data streams. The algorithm is used to obtain robust representation of segments with constant intestinal motility activity. The obtained sequential features are shown to be discriminative in the problem of abnormal motility characterization. Finally, we tackle the problem of efficient labeling. To this end, we incorporate active learning concepts to the problems present in WCE data and propose two approaches. The first one is based the concepts of sequential learning and the second one adapts the partition-based active learning to an error-free labeling scheme. All these steps are sufficient to provide an extensive visual description of intestinal motility that can be used by an expert as decision support system.

In summation, the development of Wireless Capsule Endoscopy opened a new filed of intestinal motility analysis that uses computational approach to video analysis. In the last 10 years this approach has proven its value making the field sufficiently mature for large-scale visual analysis of motility data. My thesis on computational approach to video analysis sits on the ridge of current trends in both computer vision and intestinal motility analysis. The novelty of the research was proven by numerous publications and the importance of the work for industrial applications was proven by variety of patent applications. Moreover, the fact that the methods developed during the thesis are about to become a part of the software that will be used on daily basis by medical doctors is a strong indicator of commercial interest of the research.

Wireless Capsule Endoscopy (WCE); Small Intestine; Intestinal Motility; Motility Analysis; Computer-Aided System; Easily-Comprehensible Visual Description; Motility-Related Intestinal Events; Physician; Computer Vision Concepts; Machine Learning Techniques; 3D Video Signal; Holistic Image; Motility Bar; Optimal Mapping; Video to Image; Automatic Extraction; Motility Information; Frame-Per-Frame Analysis; Intestinal Contraction Detection; Lumen Size Estimation; Intestinal Content Characterization; Wrinkle Frame Detection; Algorithms; Validation; Sequential Features; Online Statistical Test; Multivariate Data Streams; Concentration Inequality; Robust Adaptive Windowing Algorithm; Robust Representation; Segments; Constant Intestinal Motility Activity; Discriminative Features; Abnormal Motility Characterization; Efficient Labeling; Active Learning Concepts; WCE Data; Sequential Learning; Partition-Based Active Learning; Error-Free Labeling Scheme; Extensive Visual Description; Expert System; Decision Support System