Skip to main content
Presentation
Cable Footprint History: Spatio-Temporal Technique for Instrument Detection in Gastrointestinal Endoscopic Procedures
Proceedings of WorldComp International Conference on Image Processing, Computer Vision & Pattern Recognition
  • Chuanhai Zhang, Iowa State University
  • Wallapak Tavanapong, Iowa State University
  • Johnny S. Wong, Iowa State University
  • Piet C. de Groen, Mayo Clinic College of Medicine
  • JungHwan Oh, University of North Texas
Document Type
Conference Proceeding
Conference
International Conference on Image Processing, Computer Vision & Pattern Recognition
Publication Version
Published Version
Publication Date
7-1-2015
Conference Title
IPCV'15 - The 19th International Conference on Image Processing, Computer Vision, & Pattern Recognition
Conference Date
July 27-30, 2015
Geolocation
(36.1699412, -115.13982959999998)
Abstract

We propose a new fast spatio-temporal technique that detects an operation scene---a video segment corresponding to a single purpose diagnosis action or a single purpose therapeutic action. The technique utilizes (1) color contrast of the cable region and the background, (2) the new area-based coordinate system to compute spatial features, and (3) the history of locations of detected cables of the instrument in a video to discard false regions. The proposed technique and software are useful for (1) automatic documentation of diagnostic or therapeutic operations at the end of the procedure, (2) a second review for causes of complications due to these operations, and (3) a building block for an effective content-based retrieval system to facilitate endoscopic research and education. On 38 fulllength colonoscopy and upper endoscopy video files with different cable colors and four different insertion directions of the instruments, the average percentage of false positive duration is small at 2.23%. The average percentage of true positive duration is high at 92.9%. The average analysis time per image is 13 milliseconds on an inexpensive off-the-shelf PC.

Comments

This is from IPCV'15 - The 19th International Conference on Image Processing, Computer Vision, & Pattern Recognition, July 2015, pp.308-314. Posted with permission.

Language
en
File Format
application/pdf
Citation Information
Chuanhai Zhang, Wallapak Tavanapong, Johnny S. Wong, Piet C. de Groen, et al.. "Cable Footprint History: Spatio-Temporal Technique for Instrument Detection in Gastrointestinal Endoscopic Procedures" Las Vegas, NEProceedings of WorldComp International Conference on Image Processing, Computer Vision & Pattern Recognition (2015) p. 308 - 314
Available at: http://works.bepress.com/johnny-wong/2/