Automatic polyp detection from learned boundaries

Nima Tajbakhsh, Changching Chi, Suryakanth R. Gurudu, Jianming Liang

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

12 Citations (Scopus)

Abstract

Colonoscopy is the primary method for detecting and removing polyps-precursors to colon cancer, but during colonoscopy, a significant number of polyps are missed-the pooled miss-rate for all polyps is 22% (95% CI, 19%-26%). This paper presents an automatic polyp detection system for colonoscopy, aiming to alert colonoscopists to possible polyps during the procedures. Given an input image, our method first collects a crude set of edge pixels, then refines this edge map by effectively removing many non-polyp boundary edges through a classification scheme, and finally localizes polyps based on the retained edges with a novel voting scheme. This paper makes three original contributions: (1) a fast and discriminative patch descriptor for precisely characterizing image appearance, (2) a new 2-stage classification pipeline for accurately excluding undesired edges, and (3) a novel voting scheme for robustly localizing polyps from fragmented edge maps. Evaluations demonstrate that our method outperforms the state-of-the-art.

Original languageEnglish (US)
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages97-100
Number of pages4
ISBN (Print)9781467319591
StatePublished - Jul 29 2014
Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duration: Apr 29 2014May 2 2014

Other

Other2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
CountryChina
CityBeijing
Period4/29/145/2/14

Fingerprint

Polyps
Colonoscopy
Pipelines
Pixels
Politics
Colonic Neoplasms

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Tajbakhsh, N., Chi, C., Gurudu, S. R., & Liang, J. (2014). Automatic polyp detection from learned boundaries. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 97-100). [6867818] Institute of Electrical and Electronics Engineers Inc..

Automatic polyp detection from learned boundaries. / Tajbakhsh, Nima; Chi, Changching; Gurudu, Suryakanth R.; Liang, Jianming.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 97-100 6867818.

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

Tajbakhsh, N, Chi, C, Gurudu, SR & Liang, J 2014, Automatic polyp detection from learned boundaries. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6867818, Institute of Electrical and Electronics Engineers Inc., pp. 97-100, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 4/29/14.
Tajbakhsh N, Chi C, Gurudu SR, Liang J. Automatic polyp detection from learned boundaries. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 97-100. 6867818
Tajbakhsh, Nima ; Chi, Changching ; Gurudu, Suryakanth R. ; Liang, Jianming. / Automatic polyp detection from learned boundaries. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 97-100
@inproceedings{245b0f8c7b7644f2af863565d1b758d4,
title = "Automatic polyp detection from learned boundaries",
abstract = "Colonoscopy is the primary method for detecting and removing polyps-precursors to colon cancer, but during colonoscopy, a significant number of polyps are missed-the pooled miss-rate for all polyps is 22{\%} (95{\%} CI, 19{\%}-26{\%}). This paper presents an automatic polyp detection system for colonoscopy, aiming to alert colonoscopists to possible polyps during the procedures. Given an input image, our method first collects a crude set of edge pixels, then refines this edge map by effectively removing many non-polyp boundary edges through a classification scheme, and finally localizes polyps based on the retained edges with a novel voting scheme. This paper makes three original contributions: (1) a fast and discriminative patch descriptor for precisely characterizing image appearance, (2) a new 2-stage classification pipeline for accurately excluding undesired edges, and (3) a novel voting scheme for robustly localizing polyps from fragmented edge maps. Evaluations demonstrate that our method outperforms the state-of-the-art.",
author = "Nima Tajbakhsh and Changching Chi and Gurudu, {Suryakanth R.} and Jianming Liang",
year = "2014",
month = "7",
day = "29",
language = "English (US)",
isbn = "9781467319591",
pages = "97--100",
booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatic polyp detection from learned boundaries

AU - Tajbakhsh, Nima

AU - Chi, Changching

AU - Gurudu, Suryakanth R.

AU - Liang, Jianming

PY - 2014/7/29

Y1 - 2014/7/29

N2 - Colonoscopy is the primary method for detecting and removing polyps-precursors to colon cancer, but during colonoscopy, a significant number of polyps are missed-the pooled miss-rate for all polyps is 22% (95% CI, 19%-26%). This paper presents an automatic polyp detection system for colonoscopy, aiming to alert colonoscopists to possible polyps during the procedures. Given an input image, our method first collects a crude set of edge pixels, then refines this edge map by effectively removing many non-polyp boundary edges through a classification scheme, and finally localizes polyps based on the retained edges with a novel voting scheme. This paper makes three original contributions: (1) a fast and discriminative patch descriptor for precisely characterizing image appearance, (2) a new 2-stage classification pipeline for accurately excluding undesired edges, and (3) a novel voting scheme for robustly localizing polyps from fragmented edge maps. Evaluations demonstrate that our method outperforms the state-of-the-art.

AB - Colonoscopy is the primary method for detecting and removing polyps-precursors to colon cancer, but during colonoscopy, a significant number of polyps are missed-the pooled miss-rate for all polyps is 22% (95% CI, 19%-26%). This paper presents an automatic polyp detection system for colonoscopy, aiming to alert colonoscopists to possible polyps during the procedures. Given an input image, our method first collects a crude set of edge pixels, then refines this edge map by effectively removing many non-polyp boundary edges through a classification scheme, and finally localizes polyps based on the retained edges with a novel voting scheme. This paper makes three original contributions: (1) a fast and discriminative patch descriptor for precisely characterizing image appearance, (2) a new 2-stage classification pipeline for accurately excluding undesired edges, and (3) a novel voting scheme for robustly localizing polyps from fragmented edge maps. Evaluations demonstrate that our method outperforms the state-of-the-art.

UR - http://www.scopus.com/inward/record.url?scp=84927946589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927946589&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781467319591

SP - 97

EP - 100

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -