Honghan Chen, Junzhou Chen, Qiang Peng, Ganglu Sun, Tao Gan
{"title":"Automatic hookworm image detection for wireless capsule endoscopy using hybrid color gradient and contourlet transform","authors":"Honghan Chen, Junzhou Chen, Qiang Peng, Ganglu Sun, Tao Gan","doi":"10.1109/BMEI.2013.6746918","DOIUrl":null,"url":null,"abstract":"Wireless Capsule Endoscopy (WCE) is a relative novel technology, which can view entire gastrointestinal (GI) tract without invasiveness and sedation. The main disadvantage associated with WCE is that the huge number of recorded images must be examined by clinicians. It is a tedious and time consuming task. Developing an automatic computer-aided detection system to alleviate the burden of clinicians is required. In this paper, we proposed a new hookworm image detection algorithm. A new gradient space, named Hybrid Color Gradient (HCG) for hookworm detection is developed by analyzing the characteristics of hookworm infection images. Contourlet transformation is introduced to construct the final features. Real experiments using SVM show that reasonable classification results can be obtained. Moreover, according to our literature survey, this is the first work on automatic hookworm detection of WCE images.","PeriodicalId":163211,"journal":{"name":"2013 6th International Conference on Biomedical Engineering and Informatics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"21","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 6th International Conference on Biomedical Engineering and Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BMEI.2013.6746918","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 21
Abstract
Wireless Capsule Endoscopy (WCE) is a relative novel technology, which can view entire gastrointestinal (GI) tract without invasiveness and sedation. The main disadvantage associated with WCE is that the huge number of recorded images must be examined by clinicians. It is a tedious and time consuming task. Developing an automatic computer-aided detection system to alleviate the burden of clinicians is required. In this paper, we proposed a new hookworm image detection algorithm. A new gradient space, named Hybrid Color Gradient (HCG) for hookworm detection is developed by analyzing the characteristics of hookworm infection images. Contourlet transformation is introduced to construct the final features. Real experiments using SVM show that reasonable classification results can be obtained. Moreover, according to our literature survey, this is the first work on automatic hookworm detection of WCE images.