A decision fusion strategy for polyp detection in capsule endoscopy

Qian Zhao, Themistocles Dassopoulos, Gerard E. Mullin, Max Q.H. Meng, Rajesh Kumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations


Wireless capsule endoscopy (CE) is now routinely used for non-invasive diagnosis of small bowel diseases. But, it still requires manual assessment of the approximately 50,000 study images. Literature has recently investigated automated methods to detect and analyze various anomalies in CE images to improve reading efficiency and reduce variability. We propose such a computer aided diagnosis (CAD) approach to detect small bowel polyps. For supervised classification of polyps, we investigated fusing multiple statistical classifiers based on color, texture and edge features. The combined boosted classifier when evaluated using 1200 CE images outperformed all individual classifiers and achieved a ∼90% classification accuracy.

Original languageEnglish (US)
Title of host publicationMedicine Meets Virtual Reality 19
Subtitle of host publicationNextMed, MMVR 2012
PublisherIOS Press
Number of pages7
ISBN (Print)9781614990215
StatePublished - 2012
EventMedicine Meets Virtual Reality 19: NextMed, MMVR 2012 - Newport Beach, CA, United States
Duration: Feb 9 2012Feb 11 2012

Publication series

NameStudies in Health Technology and Informatics
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365


OtherMedicine Meets Virtual Reality 19: NextMed, MMVR 2012
Country/TerritoryUnited States
CityNewport Beach, CA


  • Capsule endoscopy
  • Computer aided diagnosis
  • Statistical classification

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management


Dive into the research topics of 'A decision fusion strategy for polyp detection in capsule endoscopy'. Together they form a unique fingerprint.

Cite this