Increasing computer-aided detection specificity by projection features for CT colonography

Hongbin Zhu, Zhengrong Liang, Perry J. Pickhardt, Matthew A. Barish, Jiangsheng You, Yi Fan, Hongbing Lu, Erica J. Posniak, Robert J. Richards, Harris Cohen

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Purpose: A large number of false positives (FPs) generated by computer-aided detection (CAD) schemes is likely to distract radiologists' attention and decrease their interpretation efficiency. This study aims to develop projection-based features which characterize true and false positives to increase the specificity while maintaining high sensitivity in detecting colonic polyps. Methods: In this study, two-dimensional projection images are obtained from each initial polyp candidate or volume of interest, and features are extracted from both the gray and color projection images to differentiate FPs from true positives. These projection features were tested to exclude different types of FPs, such as haustral folds, rectal tubes, and residue stool using a database of 325 patient studies (from two different institutions), which includes 556 scans at supine and/or prone positions with 347 polyps and masses sized from 5 to 60 mm. For comparison, several well-established features were used to generate a baseline reference. The experimental evaluation was conducted for large polyps (10 mm) and medium-sized polyps (5-9 mm) separately. Results: For large polyps, the additional usage of the projection features reduces the FP rate from 5.31 to 1.92 per scan at the comparable by-polyp sensitivity level of 93.1%. For medium-sized polyps, the FP rate is reduced from 8.89 to 5.23 at the sensitivity level of 80.6%. The percentages of FP reduction are 63.9% and 41.2% for the large and medium-sized polyps, respectively, without sacrificing detection sensitivity. Conclusions: The results have demonstrated that the new projection features can effectively reduce the FPs and increase the detection specificity without sacrificing the sensitivity. CAD of colonic polyps is supposed to help radiologists to improve their performance in interpreting computed tomographic colonography images.

Original languageEnglish (US)
Pages (from-to)1468-1481
Number of pages14
JournalMedical Physics
Volume37
Issue number4
DOIs
StatePublished - Jan 1 2010
Externally publishedYes

Fingerprint

Computed Tomographic Colonography
Polyps
Colonic Polyps
Prone Position
Supine Position
Color
Databases

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Increasing computer-aided detection specificity by projection features for CT colonography. / Zhu, Hongbin; Liang, Zhengrong; Pickhardt, Perry J.; Barish, Matthew A.; You, Jiangsheng; Fan, Yi; Lu, Hongbing; Posniak, Erica J.; Richards, Robert J.; Cohen, Harris.

In: Medical Physics, Vol. 37, No. 4, 01.01.2010, p. 1468-1481.

Research output: Contribution to journalArticle

Zhu, H, Liang, Z, Pickhardt, PJ, Barish, MA, You, J, Fan, Y, Lu, H, Posniak, EJ, Richards, RJ & Cohen, H 2010, 'Increasing computer-aided detection specificity by projection features for CT colonography', Medical Physics, vol. 37, no. 4, pp. 1468-1481. https://doi.org/10.1118/1.3302833
Zhu H, Liang Z, Pickhardt PJ, Barish MA, You J, Fan Y et al. Increasing computer-aided detection specificity by projection features for CT colonography. Medical Physics. 2010 Jan 1;37(4):1468-1481. https://doi.org/10.1118/1.3302833
Zhu, Hongbin ; Liang, Zhengrong ; Pickhardt, Perry J. ; Barish, Matthew A. ; You, Jiangsheng ; Fan, Yi ; Lu, Hongbing ; Posniak, Erica J. ; Richards, Robert J. ; Cohen, Harris. / Increasing computer-aided detection specificity by projection features for CT colonography. In: Medical Physics. 2010 ; Vol. 37, No. 4. pp. 1468-1481.
@article{9844d7f70f6e4f3ea806aa3ab78c79f7,
title = "Increasing computer-aided detection specificity by projection features for CT colonography",
abstract = "Purpose: A large number of false positives (FPs) generated by computer-aided detection (CAD) schemes is likely to distract radiologists' attention and decrease their interpretation efficiency. This study aims to develop projection-based features which characterize true and false positives to increase the specificity while maintaining high sensitivity in detecting colonic polyps. Methods: In this study, two-dimensional projection images are obtained from each initial polyp candidate or volume of interest, and features are extracted from both the gray and color projection images to differentiate FPs from true positives. These projection features were tested to exclude different types of FPs, such as haustral folds, rectal tubes, and residue stool using a database of 325 patient studies (from two different institutions), which includes 556 scans at supine and/or prone positions with 347 polyps and masses sized from 5 to 60 mm. For comparison, several well-established features were used to generate a baseline reference. The experimental evaluation was conducted for large polyps (10 mm) and medium-sized polyps (5-9 mm) separately. Results: For large polyps, the additional usage of the projection features reduces the FP rate from 5.31 to 1.92 per scan at the comparable by-polyp sensitivity level of 93.1{\%}. For medium-sized polyps, the FP rate is reduced from 8.89 to 5.23 at the sensitivity level of 80.6{\%}. The percentages of FP reduction are 63.9{\%} and 41.2{\%} for the large and medium-sized polyps, respectively, without sacrificing detection sensitivity. Conclusions: The results have demonstrated that the new projection features can effectively reduce the FPs and increase the detection specificity without sacrificing the sensitivity. CAD of colonic polyps is supposed to help radiologists to improve their performance in interpreting computed tomographic colonography images.",
author = "Hongbin Zhu and Zhengrong Liang and Pickhardt, {Perry J.} and Barish, {Matthew A.} and Jiangsheng You and Yi Fan and Hongbing Lu and Posniak, {Erica J.} and Richards, {Robert J.} and Harris Cohen",
year = "2010",
month = "1",
day = "1",
doi = "10.1118/1.3302833",
language = "English (US)",
volume = "37",
pages = "1468--1481",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "4",

}

TY - JOUR

T1 - Increasing computer-aided detection specificity by projection features for CT colonography

AU - Zhu, Hongbin

AU - Liang, Zhengrong

AU - Pickhardt, Perry J.

AU - Barish, Matthew A.

AU - You, Jiangsheng

AU - Fan, Yi

AU - Lu, Hongbing

AU - Posniak, Erica J.

AU - Richards, Robert J.

AU - Cohen, Harris

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Purpose: A large number of false positives (FPs) generated by computer-aided detection (CAD) schemes is likely to distract radiologists' attention and decrease their interpretation efficiency. This study aims to develop projection-based features which characterize true and false positives to increase the specificity while maintaining high sensitivity in detecting colonic polyps. Methods: In this study, two-dimensional projection images are obtained from each initial polyp candidate or volume of interest, and features are extracted from both the gray and color projection images to differentiate FPs from true positives. These projection features were tested to exclude different types of FPs, such as haustral folds, rectal tubes, and residue stool using a database of 325 patient studies (from two different institutions), which includes 556 scans at supine and/or prone positions with 347 polyps and masses sized from 5 to 60 mm. For comparison, several well-established features were used to generate a baseline reference. The experimental evaluation was conducted for large polyps (10 mm) and medium-sized polyps (5-9 mm) separately. Results: For large polyps, the additional usage of the projection features reduces the FP rate from 5.31 to 1.92 per scan at the comparable by-polyp sensitivity level of 93.1%. For medium-sized polyps, the FP rate is reduced from 8.89 to 5.23 at the sensitivity level of 80.6%. The percentages of FP reduction are 63.9% and 41.2% for the large and medium-sized polyps, respectively, without sacrificing detection sensitivity. Conclusions: The results have demonstrated that the new projection features can effectively reduce the FPs and increase the detection specificity without sacrificing the sensitivity. CAD of colonic polyps is supposed to help radiologists to improve their performance in interpreting computed tomographic colonography images.

AB - Purpose: A large number of false positives (FPs) generated by computer-aided detection (CAD) schemes is likely to distract radiologists' attention and decrease their interpretation efficiency. This study aims to develop projection-based features which characterize true and false positives to increase the specificity while maintaining high sensitivity in detecting colonic polyps. Methods: In this study, two-dimensional projection images are obtained from each initial polyp candidate or volume of interest, and features are extracted from both the gray and color projection images to differentiate FPs from true positives. These projection features were tested to exclude different types of FPs, such as haustral folds, rectal tubes, and residue stool using a database of 325 patient studies (from two different institutions), which includes 556 scans at supine and/or prone positions with 347 polyps and masses sized from 5 to 60 mm. For comparison, several well-established features were used to generate a baseline reference. The experimental evaluation was conducted for large polyps (10 mm) and medium-sized polyps (5-9 mm) separately. Results: For large polyps, the additional usage of the projection features reduces the FP rate from 5.31 to 1.92 per scan at the comparable by-polyp sensitivity level of 93.1%. For medium-sized polyps, the FP rate is reduced from 8.89 to 5.23 at the sensitivity level of 80.6%. The percentages of FP reduction are 63.9% and 41.2% for the large and medium-sized polyps, respectively, without sacrificing detection sensitivity. Conclusions: The results have demonstrated that the new projection features can effectively reduce the FPs and increase the detection specificity without sacrificing the sensitivity. CAD of colonic polyps is supposed to help radiologists to improve their performance in interpreting computed tomographic colonography images.

UR - http://www.scopus.com/inward/record.url?scp=77949721458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949721458&partnerID=8YFLogxK

U2 - 10.1118/1.3302833

DO - 10.1118/1.3302833

M3 - Article

VL - 37

SP - 1468

EP - 1481

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 4

ER -