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

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

5 Citations (Scopus)

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.

Original languageEnglish (US)
Title of host publicationBIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing
Pages119-124
Number of pages6
StatePublished - 2011
EventInternational Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2011 - Rome, Italy
Duration: Jan 26 2011Jan 29 2011

Other

OtherInternational Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2011
CountryItaly
CityRome
Period1/26/111/29/11

Fingerprint

Program processors
Graphics processing unit
Mucous Membrane

Keywords

  • Colonoscopy
  • CPU multi-threading
  • CUDA
  • GPU
  • Informative frame filtering

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering

Cite this

Karri, V. P., Oh, J., Tavanapong, W., Wong, J., & De Groen, P. C. (2011). Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit. In BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing (pp. 119-124)

Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit. / Karri, Venkata Praveen; Oh, JungHwan; Tavanapong, Wallapak; Wong, Johnny; De Groen, Piet C.

BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2011. p. 119-124.

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

Karri, VP, Oh, J, Tavanapong, W, Wong, J & De Groen, PC 2011, Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit. in BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. pp. 119-124, International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2011, Rome, Italy, 1/26/11.
Karri VP, Oh J, Tavanapong W, Wong J, De Groen PC. Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit. In BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2011. p. 119-124
Karri, Venkata Praveen ; Oh, JungHwan ; Tavanapong, Wallapak ; Wong, Johnny ; De Groen, Piet C. / Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit. BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2011. pp. 119-124
@inproceedings{58adbfd8940f4036ab231a359da98e69,
title = "Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit",
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.",
keywords = "Colonoscopy, CPU multi-threading, CUDA, GPU, Informative frame filtering",
author = "Karri, {Venkata Praveen} and JungHwan Oh and Wallapak Tavanapong and Johnny Wong and {De Groen}, {Piet C.}",
year = "2011",
language = "English (US)",
isbn = "9789898425355",
pages = "119--124",
booktitle = "BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing",

}

TY - GEN

T1 - Effective and accelerated informative frame filtering in colonoscopy videos using graphics processing unit

AU - Karri, Venkata Praveen

AU - Oh, JungHwan

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - De Groen, Piet C.

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

KW - Colonoscopy

KW - CPU multi-threading

KW - CUDA

KW - GPU

KW - Informative frame filtering

UR - http://www.scopus.com/inward/record.url?scp=79960246734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960246734&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79960246734

SN - 9789898425355

SP - 119

EP - 124

BT - BIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

ER -