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 full-length 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.
|Original language||English (US)|
|Title of host publication||Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015|
|Editors||Hamid R. Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, George Jandieri, Gerald Schaefer, Ashu M. G. Solo|
|Number of pages||7|
|ISBN (Electronic)||1601324049, 9781601324047|
|State||Published - 2015|
|Event||2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015 - Las Vegas, United States|
Duration: Jul 27 2015 → Jul 30 2015
|Name||Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015|
|Conference||2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015|
|Period||7/27/15 → 7/30/15|
Bibliographical noteFunding Information:
This work is partially supported by Iowa Regent Innovation Funds and EndoMetric Corp. Johnny Wong, Wallapak Tavanapong, and JungHwan Oh hold positions in EndoMetric Corporation, Ames, IA 50014, U.S.A, a for profit company that markets endoscopy-related software. De Groen is the medical advisor of EndoMetric.
© International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015.All right reserved.
- Image analysis
- Image features