Micronodule detection and false-positive elimination from 3D chest CT

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

1 Citation (Scopus)

Abstract

Computed Tomography (CT) is generally accepted as the most sensitive way for lung cancer screening. Its high contrast resolution allows the detection of small nodules and, thus, lung cancer at a very early stage. In this paper, we propose a method for automating nodule detection from high-resolution 3D chest CT images. Our method focuses on the detection of both calcified (high-contrast) and noncalcified (low-contrast) granulomatous nodules less than 5mm in diameter, using a series of 3D filters including a filter for vessels and noise suppression, a filter for nodule enhancement, and a filter for false-positive elimination based on local skeletonization of suspicious nodule areas. We also present promising results of applying our method to various clinical chest CT datasets with over 90% detection rate.

Original languageEnglish (US)
Title of host publicationWMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings
Pages254-259
Number of pages6
Volume5
StatePublished - 2005
Event9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005 - Orlando, FL, United States
Duration: Jul 10 2005Jul 13 2005

Other

Other9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005
CountryUnited States
CityOrlando, FL
Period7/10/057/13/05

Fingerprint

Tomography
Screening

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Chang, S. (2005). Micronodule detection and false-positive elimination from 3D chest CT. In WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings (Vol. 5, pp. 254-259)
Chang, Sukmoon. / Micronodule detection and false-positive elimination from 3D chest CT. WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. Vol. 5 2005. pp. 254-259
@inproceedings{3a400f50664945088da01cf5137feefe,
title = "Micronodule detection and false-positive elimination from 3D chest CT",
abstract = "Computed Tomography (CT) is generally accepted as the most sensitive way for lung cancer screening. Its high contrast resolution allows the detection of small nodules and, thus, lung cancer at a very early stage. In this paper, we propose a method for automating nodule detection from high-resolution 3D chest CT images. Our method focuses on the detection of both calcified (high-contrast) and noncalcified (low-contrast) granulomatous nodules less than 5mm in diameter, using a series of 3D filters including a filter for vessels and noise suppression, a filter for nodule enhancement, and a filter for false-positive elimination based on local skeletonization of suspicious nodule areas. We also present promising results of applying our method to various clinical chest CT datasets with over 90{\%} detection rate.",
author = "Sukmoon Chang",
year = "2005",
language = "English (US)",
isbn = "9806560574",
volume = "5",
pages = "254--259",
booktitle = "WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings",

}

Chang, S 2005, Micronodule detection and false-positive elimination from 3D chest CT. in WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. vol. 5, pp. 254-259, 9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005, Orlando, FL, United States, 7/10/05.

Micronodule detection and false-positive elimination from 3D chest CT. / Chang, Sukmoon.

WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. Vol. 5 2005. p. 254-259.

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

TY - GEN

T1 - Micronodule detection and false-positive elimination from 3D chest CT

AU - Chang, Sukmoon

PY - 2005

Y1 - 2005

N2 - Computed Tomography (CT) is generally accepted as the most sensitive way for lung cancer screening. Its high contrast resolution allows the detection of small nodules and, thus, lung cancer at a very early stage. In this paper, we propose a method for automating nodule detection from high-resolution 3D chest CT images. Our method focuses on the detection of both calcified (high-contrast) and noncalcified (low-contrast) granulomatous nodules less than 5mm in diameter, using a series of 3D filters including a filter for vessels and noise suppression, a filter for nodule enhancement, and a filter for false-positive elimination based on local skeletonization of suspicious nodule areas. We also present promising results of applying our method to various clinical chest CT datasets with over 90% detection rate.

AB - Computed Tomography (CT) is generally accepted as the most sensitive way for lung cancer screening. Its high contrast resolution allows the detection of small nodules and, thus, lung cancer at a very early stage. In this paper, we propose a method for automating nodule detection from high-resolution 3D chest CT images. Our method focuses on the detection of both calcified (high-contrast) and noncalcified (low-contrast) granulomatous nodules less than 5mm in diameter, using a series of 3D filters including a filter for vessels and noise suppression, a filter for nodule enhancement, and a filter for false-positive elimination based on local skeletonization of suspicious nodule areas. We also present promising results of applying our method to various clinical chest CT datasets with over 90% detection rate.

UR - http://www.scopus.com/inward/record.url?scp=84867346081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867346081&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9806560574

SN - 9789806560574

VL - 5

SP - 254

EP - 259

BT - WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings

ER -

Chang S. Micronodule detection and false-positive elimination from 3D chest CT. In WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. Vol. 5. 2005. p. 254-259