EFFECTIVE AND ACCELERATED INFORMATIVE FRAME FILTERING IN COLONOSCOPY VIDEOS USING GRAPHICS PROCESSING UNIT

Venkata Praveen Karri, JungHwan Oh, Wallapak Tavanapong, Johnny Wong, Piet C. de Groen

Abstract

Colonoscopy is an endoscopic technique that allows a physician to inspect the mucosa of the human colon. It has contributed to a marked decline in the number of colorectal cancer related deaths. However, recent data suggest that there is a significant (4-12%) miss-rate for the detection of even large polyps and cancers. To address this, we have investigated automated post-procedure and real-time quality measurements by analyzing colonoscopy videos. One of the fundamental steps is separating informative frames from non-informative frames, a process called Informative Frame Filtering (IFF). Non-informative frames comprise out-of-focus frames and frames lacking typical features of the colon. We introduce a new IFF algorithm in this paper, which is much more accurate than our previous one. Also, we exploit the many-core GPU (Graphics Processing Unit) to create an IFF software module for High Performance Computing (HPC). Code optimizations embedded in the many-core GPU resulted in a 40-fold acceleration compared to CPU-only implementation for our IFF software module.

References

  1. American Cancer Society, 2008. “Colorectal Cancer Facts and Figures” http://www.cancer.org/docroot/ STT/content/STT_1x_Cancer_Facts_and_Figures_200 8.asp.
  2. Johnson, D., Fletcher, J., MacCarty, R., et al. 2007. “Effect of slice thickness and primary 2D versus 3D virtual dissection on colorectal lesion detection at CT colonography in 452 asymptomatic adults”, American Journal of Roentgenology, 189(3):672-80.
  3. Pabby, A., Schoen, R., Weissfeld, J., Burt, R., Kikendall, J., Lance, P., Lanza, E., Schatzkin, A., 2005. “Analysis of colorectal cancer occurrence during surveillance colonoscopy in the dietary prevention trial". Gastrointestinal Endoscopy, 61(3): p.385-391.
  4. Oh, J., Hwang, S., Lee, J., Tavanapong, W., de Groen, P., Wong, J., 2007. “Informative Frame Classification for Endoscopy Video”. J. Medical Image Analysis, 11(2):110-27.
  5. Canny, J., 1986. “A Computational Approach to Edge Detection". IEEE Trans. Pattern Analysis and Machine Intelligence, 8:679-698.
  6. NVIDIA CUDA Programming Guide 3.0-beta1, 2009. www.nvidia.com.
  7. CUDA Programming Best Practices Guide 3.0-beta1, 2009. www.nvidia.com.
  8. CUDA Technical Training, 2008. Vol. I: Introduction to CUDA Programming, www.nvidia.com.
Download


Paper Citation


in Harvard Style

Karri V., Oh J., Tavanapong W., Wong J. and de Groen P. (2011). EFFECTIVE AND ACCELERATED INFORMATIVE FRAME FILTERING IN COLONOSCOPY VIDEOS USING GRAPHICS PROCESSING UNIT . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011) ISBN 978-989-8425-35-5, pages 119-124. DOI: 10.5220/0003123401190124


in Bibtex Style

@conference{biosignals11,
author={Venkata Praveen Karri and JungHwan Oh and Wallapak Tavanapong and Johnny Wong and Piet C. de Groen},
title={EFFECTIVE AND ACCELERATED INFORMATIVE FRAME FILTERING IN COLONOSCOPY VIDEOS USING GRAPHICS PROCESSING UNIT},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011)},
year={2011},
pages={119-124},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003123401190124},
isbn={978-989-8425-35-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011)
TI - EFFECTIVE AND ACCELERATED INFORMATIVE FRAME FILTERING IN COLONOSCOPY VIDEOS USING GRAPHICS PROCESSING UNIT
SN - 978-989-8425-35-5
AU - Karri V.
AU - Oh J.
AU - Tavanapong W.
AU - Wong J.
AU - de Groen P.
PY - 2011
SP - 119
EP - 124
DO - 10.5220/0003123401190124