Lesion Detection in Wireless Capsule Endoscopy Images Using Texture and Color Features

被引：0
|
作者：
Jia, Zhiwei [1 ]
Liu, Yong [1 ]
Zhang, Liming [1 ]
机构：
[1] Changsha Univ Sci & Technol, Coll Elect & Informat Engn, Changsha 410012, Hunan, Peoples R China
来源：
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS | 2018年 / 8卷 / 07期
基金：
中国国家自然科学基金;
关键词：
Color Information Feature; Texture Feature; Texture Primitive Dictionary; The k-Nearest Neighbors Method; Wireless Capsule Endoscopy;
D O I：
10.1166/jmihi.2018.2446
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
Distinguishing lesions from normal images quickly is the most challenging work during the review of wireless capsule endoscopy (WCE) videos owing to the large number of images and poor resolution. A novel method based on texture primitive histogram and image block dictionary (IBD) was proposed in this study. Each texture primitive contained 32 dimensions of color information features and 52 dimensions of texture features, which were generated using vector quantization and local binary patterns (LBP) and Leung and Malik (LM) filter bank, respectively. The power of this method was demonstrated by distinguishing 4 kinds of lesions (25 of each kind) from 400 normal images. This method was advantageous over the existing methods, which use the color feature or texture feature alone, with a recall of 93% and a specificity of 92.25%.
引用
收藏
页码：1397 / 1401
页数：5
相关论文
共 50 条
  • [21] BLEEDING DETECTION IN WIRELESS CAPSULE ENDOSCOPY BASED ON COLOR FEATURES FROM HISTOGRAM PROBABILITY
    Sainju, Sonu
    Bui, Francis M.
    Wahid, Khan
    2013 26TH ANNUAL IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2013, : 539 - 542
  • [22] Automatic polyp detection for wireless capsule endoscopy images
    Li, Baopu
    Meng, Max Q. -H.
    EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (12) : 10952 - 10958
  • [23] Detection of Hookworm Infection in the Wireless Capsule Endoscopy Images
    Sri, R. Sneha
    Oliver, A. Sheryl
    Shanthini, S.
    2017 IEEE INTERNATIONAL CONFERENCE ON ELECTRICAL, INSTRUMENTATION AND COMMUNICATION ENGINEERING (ICEICE), 2017,
  • [24] Detection of Uninformative Regions in Wireless Capsule Endoscopy Images
    Alizadeh, Mandi
    Sharzehi, Kaveh
    Talebpour, Alireza
    Soltanian-Zadeh, Hamid
    Eskandari, Hoda
    Maghsoudi, Omid Haji
    2015 41ST ANNUAL NORTHEAST BIOMEDICAL ENGINEERING CONFERENCE (NEBEC), 2015,
  • [25] Automatic Hookworm Detection in Wireless Capsule Endoscopy Images
    Wu, Xiao
    Chen, Honghan
    Gan, Tao
    Chen, Junzhou
    Ngo, Chong-Wah
    Peng, Qiang
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (07) : 1741 - 1752
  • [26] New features for wireless capsule endoscopy polyp detection
    Souaidi, Meryem
    Charfi, Said
    Ait Abdelouahad, Abdelkaher
    El Ansari, Mohamed
    2018 INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND COMPUTER VISION (ISCV2018), 2018,
  • [27] Design of the color vector similarity coefficient classifier for bleeding detection in wireless capsule endoscopy images
    School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai 200240, China
    Shanghai Jiaotong Daxue Xuebao, 2009, 11 (1715-1719):
  • [28] Lymphangiectasia Detection in Wireless Capsule Endoscopy images Using Fisher Transform Method
    Alizadeh, Mahdi
    Eskandari, Hoda
    Sharzehi, Kaveh
    2015 41ST ANNUAL NORTHEAST BIOMEDICAL ENGINEERING CONFERENCE (NEBEC), 2015,
  • [29] Ulcer Detection and Classification of Wireless Capsule Endoscopy Images Using RGB Masking
    Suman, Shipra
    Hussin, Fawnizu Azmadi
    Nicolas, Walter
    Malik, Aamir Saeed
    ADVANCED SCIENCE LETTERS, 2016, 22 (10) : 2764 - 2768
  • [30] Detection of a polypoid lesion inside a Meckel's diverticulum using wireless capsule endoscopy
    Mavrogenis, G.
    Coumaros, D.
    Bellocq, J. -P.
    Leroy, J.
    ENDOSCOPY, 2011, 43 : E115 - E116
12345