Smart Videocapsule for Early Diagnosis of Colorectal Cancer: Toward Embedded Image Analysis

Abstract

International audienceFor the last 20 years, wireless videocapsule technology has triggered alot of interest in the gastroenterologist community for the non-invasive early detectionof various gastrointestinal pathologies (ulcers, Chrones disease, polyp detection,etc.). Nevertheless, in most of the European countries videocapsules are notyet considered as a systematic valid alternative to classic endoscopies and colonoscopies.Main reasons are in the existing technological limitations of videocapsulesthat are of two kinds: (i) A limited battery life-time (8 hours usually ensured bythe manufacturer) that does not allow a complete imaging of the gastro intestinaltract, and (ii) the limited performance of the device in terms of detection rate of particularstructures like polyps for instance which degenerations are at the origin ofcolorectal cancer. To overpass these limitations, main idea of our work is to developa generation of smart videocapsules that takes advantage of the constant progress inelectronics and most precisely in embedded signal processing tasks. In this Chapter,we give first a detailed overview of the most recent state-of-the-art related tovideocapsules from the technological perspective in order to clearly positioned ourwork among the existing products and on going projects. In a second time, we proposea synthetic recall of the Cyclope project in the framework of which we arestudying different strategies to improve the performance of current videocapsules inthe particular context of the early diagnosis of colorectal cancer (polyp detection).We then propose a particular focus on the design optimization of the proposed algorithms from an electronic perspective. Most precisely, we give concrete elementsand quantitative estimation (time processing, embedding performance, etc.) to showthat embedding of the signal processing IP inside the videocapsule is feasible consideringthe most recent FPGA-platform performance, and that such an integrationcan bring a positive balance in terms of energy consumption by drastically reducingthe amount of transmitted data

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

“…• Finally, embedding the image analysis part within capsule endoscopy imaging systems [70,77] is an exciting research area which will enable the gastroenterologists to make real-time decisions. However, there are a lot of challenges that remain for essential progress [78].…”

Bleeding detection in wireless capsule endoscopy videos — Color versus texture features

“…Composition of WCE and data acquisition setup. 5 have any typical shape and texture, and the color of blood might vary from light red to dark intense red and brown, which makes the blood challenging to differentiate from the intestinal content or other objects present in the intestine. This diversity of color might depend on the position of the camera capsule, the bleeding timing 9 and the surrounding condition of the intestinal content.…”

Survey of Computer Vision and Machine Learning in Gastrointestinal Endoscopy

“…In [5], [6], texture features using GLCM are compared with LBP using SVM for classification. [7] proposed using edges, followed by a hough transform of the image before using GLCM for texture features detection. They employed an adaboost classifier.…”