Abstract
Wireless Capsule Endoscopy (WCE) is a noninvasive diagnostic technique enabling the inspection of the whole gastrointestinal (GI) tract by capturing and wirelessly transmitting thousands of color images. Proprietary software “stitches” the images into videos for examination by accredited readers. However, the videos produced are of large length and consequently the reading task becomes harder and more prone to human errors. Automating the WCE reading process could contribute in both the reduction of the examination time and the improvement of its diagnostic accuracy. In this paper, we present a novel feature extraction methodology for automated WCE image analysis. It aims at discriminating various kinds of abnormalities from the normal contents of WCE images, in a machine learning-based classification framework. The extraction of the proposed features involves an unsupervised color-based saliency detection scheme which, unlike current approaches, combines both point and region-level saliency information and the estimation of local and global image color descriptors. The salient point detection process involves estimation of DIstaNces On Selective Aggregation of chRomatic image Components (DINOSARC). The descriptors are extracted from superpixels by coevaluating both point and region-level information. The main conclusions of the experiments performed on a publicly available dataset of WCE images are (a) the proposed salient point detection scheme results in significantly less and more relevant salient points; (b) the proposed descriptors are more discriminative than relevant state-of-the-art descriptors, promising a wider adoption of the proposed approach for computer-aided diagnosis in WCE.
Highlights
Wireless Capsule Endoscopy (WCE) has been established as a first-line diagnostic tool for small bowel diseases [1]
Local and Global Color Image Descriptors. Another novel contribution of this work is that both DINOSARC salient regions and points are represented by a local color feature vector. e local feature vectors are subsequently used for the formation of feature vectors globally representing the WCE images. e feature extraction process presented in this paper is an extension of the approach we originally proposed in [6] for only local representation of square WCE image patches along with their central point
Prior to the application of DINOSARC algorithm, we performed a series of experiments to determine its optimal parameters. e criterion considered for this tuning process was the number of false negative images, that is, the number of images that were containing abnormalities, but no salient points were detected on these abnormalities
Summary
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy. Automating the WCE reading process could contribute in both the reduction of the examination time and the improvement of its diagnostic accuracy. We present a novel feature extraction methodology for automated WCE image analysis. It aims at discriminating various kinds of abnormalities from the normal contents of WCE images, in a machine learning-based classification framework. E extraction of the proposed features involves an unsupervised color-based saliency detection scheme which, unlike current approaches, combines both point and region-level saliency information and the estimation of local and global image color descriptors. E salient point detection process involves estimation of DIstaNces On Selective Aggregation of chRomatic image Components (DINOSARC). It aims at discriminating various kinds of abnormalities from the normal contents of WCE images, in a machine learning-based classification framework. e extraction of the proposed features involves an unsupervised color-based saliency detection scheme which, unlike current approaches, combines both point and region-level saliency information and the estimation of local and global image color descriptors. e salient point detection process involves estimation of DIstaNces On Selective Aggregation of chRomatic image Components (DINOSARC). e descriptors are extracted from superpixels by coevaluating both point and region-level information. e main conclusions of the experiments performed on a publicly available dataset of WCE images are (a) the proposed salient point detection scheme results in significantly less and more relevant salient points; (b) the proposed descriptors are more discriminative than relevant state-of-the-art descriptors, promising a wider adoption of the proposed approach for computer-aided diagnosis in WCE
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
