A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos

Nima Tajbakhsh, Suryakanth R. Gurudu, Jianming Liang

Research output: Contribution to journalArticle

Abstract

Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.

Original languageEnglish (US)
Pages (from-to)327-338
Number of pages12
JournalInformation processing in medical imaging : proceedings of the ... conference
Volume24
StatePublished - 2015
Externally publishedYes

Fingerprint

Colonoscopy
Polyps
Politics
Color
Sensitivity and Specificity

ASJC Scopus subject areas

  • Medicine(all)

Cite this

A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos. / Tajbakhsh, Nima; Gurudu, Suryakanth R.; Liang, Jianming.

In: Information processing in medical imaging : proceedings of the ... conference, Vol. 24, 2015, p. 327-338.

Research output: Contribution to journalArticle

@article{edffc89d7b9f453ba48ce55014ecde7e,
title = "A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos",
abstract = "Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.",
author = "Nima Tajbakhsh and Gurudu, {Suryakanth R.} and Jianming Liang",
year = "2015",
language = "English (US)",
volume = "24",
pages = "327--338",
journal = "Information processing in medical imaging : proceedings of the ... conference",
issn = "1011-2499",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos

AU - Tajbakhsh, Nima

AU - Gurudu, Suryakanth R.

AU - Liang, Jianming

PY - 2015

Y1 - 2015

N2 - Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.

AB - Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.

UR - http://www.scopus.com/inward/record.url?scp=84942610820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942610820&partnerID=8YFLogxK

M3 - Article

C2 - 26221684

VL - 24

SP - 327

EP - 338

JO - Information processing in medical imaging : proceedings of the ... conference

JF - Information processing in medical imaging : proceedings of the ... conference

SN - 1011-2499

ER -