Surface normal overlap: A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT

David S. Paik, Christopher F. Beaulieu, Geoffrey D. Rubin, Burak Acar, R. Brooke Jeffrey, Judy Yee, Joyoni Dey, Sandy Napel

Research output: Contribution to journalArticle

211 Citations (Scopus)

Abstract

We developed a novel computer-aided detection (CAD) algorithm called the surface normal overlap method that we applied to colonic polyp detection and lung nodule detection in helical computed tomography (CT) images. We demonstrate some of the theoretical aspects of this algorithm using a statistical shape model. The algorithm was then optimized on simulated CT data and evaluated using a per-lesion cross-validation on 8 CT colonography datasets and on 8 chest CT datasets. It is able to achieve 100% sensitivity for colonic polyps 10 mm and larger at 7.0 false positives (FPs)/dataset and 90% sensitivity for solid lung nodules 6 mm and larger at 5.6 FP/dataset.

Original languageEnglish (US)
Pages (from-to)661-675
Number of pages15
JournalIEEE Transactions on Medical Imaging
Volume23
Issue number6
DOIs
StatePublished - Jun 1 2004
Externally publishedYes

Fingerprint

Colonic Polyps
Spiral Computed Tomography
Tomography
Lung
Statistical Models
Thorax
Datasets

Keywords

  • Colonic polyp
  • Computed tomography colonography (CTC)
  • Computer-aided detection (CAD)
  • Cross-validation
  • Lung nodule
  • Statistical shape model

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Surface normal overlap : A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT. / Paik, David S.; Beaulieu, Christopher F.; Rubin, Geoffrey D.; Acar, Burak; Jeffrey, R. Brooke; Yee, Judy; Dey, Joyoni; Napel, Sandy.

In: IEEE Transactions on Medical Imaging, Vol. 23, No. 6, 01.06.2004, p. 661-675.

Research output: Contribution to journalArticle

Paik, David S. ; Beaulieu, Christopher F. ; Rubin, Geoffrey D. ; Acar, Burak ; Jeffrey, R. Brooke ; Yee, Judy ; Dey, Joyoni ; Napel, Sandy. / Surface normal overlap : A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT. In: IEEE Transactions on Medical Imaging. 2004 ; Vol. 23, No. 6. pp. 661-675.
@article{d8d55e7a847d423bba35fa8df9f86d21,
title = "Surface normal overlap: A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT",
abstract = "We developed a novel computer-aided detection (CAD) algorithm called the surface normal overlap method that we applied to colonic polyp detection and lung nodule detection in helical computed tomography (CT) images. We demonstrate some of the theoretical aspects of this algorithm using a statistical shape model. The algorithm was then optimized on simulated CT data and evaluated using a per-lesion cross-validation on 8 CT colonography datasets and on 8 chest CT datasets. It is able to achieve 100{\%} sensitivity for colonic polyps 10 mm and larger at 7.0 false positives (FPs)/dataset and 90{\%} sensitivity for solid lung nodules 6 mm and larger at 5.6 FP/dataset.",
keywords = "Colonic polyp, Computed tomography colonography (CTC), Computer-aided detection (CAD), Cross-validation, Lung nodule, Statistical shape model",
author = "Paik, {David S.} and Beaulieu, {Christopher F.} and Rubin, {Geoffrey D.} and Burak Acar and Jeffrey, {R. Brooke} and Judy Yee and Joyoni Dey and Sandy Napel",
year = "2004",
month = "6",
day = "1",
doi = "10.1109/TMI.2004.826362",
language = "English (US)",
volume = "23",
pages = "661--675",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Surface normal overlap

T2 - A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT

AU - Paik, David S.

AU - Beaulieu, Christopher F.

AU - Rubin, Geoffrey D.

AU - Acar, Burak

AU - Jeffrey, R. Brooke

AU - Yee, Judy

AU - Dey, Joyoni

AU - Napel, Sandy

PY - 2004/6/1

Y1 - 2004/6/1

N2 - We developed a novel computer-aided detection (CAD) algorithm called the surface normal overlap method that we applied to colonic polyp detection and lung nodule detection in helical computed tomography (CT) images. We demonstrate some of the theoretical aspects of this algorithm using a statistical shape model. The algorithm was then optimized on simulated CT data and evaluated using a per-lesion cross-validation on 8 CT colonography datasets and on 8 chest CT datasets. It is able to achieve 100% sensitivity for colonic polyps 10 mm and larger at 7.0 false positives (FPs)/dataset and 90% sensitivity for solid lung nodules 6 mm and larger at 5.6 FP/dataset.

AB - We developed a novel computer-aided detection (CAD) algorithm called the surface normal overlap method that we applied to colonic polyp detection and lung nodule detection in helical computed tomography (CT) images. We demonstrate some of the theoretical aspects of this algorithm using a statistical shape model. The algorithm was then optimized on simulated CT data and evaluated using a per-lesion cross-validation on 8 CT colonography datasets and on 8 chest CT datasets. It is able to achieve 100% sensitivity for colonic polyps 10 mm and larger at 7.0 false positives (FPs)/dataset and 90% sensitivity for solid lung nodules 6 mm and larger at 5.6 FP/dataset.

KW - Colonic polyp

KW - Computed tomography colonography (CTC)

KW - Computer-aided detection (CAD)

KW - Cross-validation

KW - Lung nodule

KW - Statistical shape model

UR - http://www.scopus.com/inward/record.url?scp=2942577813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942577813&partnerID=8YFLogxK

U2 - 10.1109/TMI.2004.826362

DO - 10.1109/TMI.2004.826362

M3 - Article

C2 - 15191141

AN - SCOPUS:2942577813

VL - 23

SP - 661

EP - 675

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 6

ER -