Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter

Atsushi Teramoto, Hiroshi Fujita

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

Purpose: Existing computer-aided detection schemes for lung nodule detection require a large number of calculations and tens of minutes per case; there is a large gap between image acquisition time and nodule detection time. In this study, we propose a fast detection scheme of lung nodule in chest CT images using cylindrical nodule-enhancement filter with the aim of improving the workflow for diagnosis in CT examinations. Methods: Proposed detection scheme involves segmentation of the lung region, preprocessing, nodule enhancement, further segmentation, and false-positive (FP) reduction. As a nodule enhancement, our method employs a cylindrical shape filter to reduce the number of calculations. False positives (FPs) in nodule candidates are reduced using support vector machine and seven types of characteristic parameters. Results: The detection performance and speed were evaluated experimentally using Lung Image Database Consortium publicly available image database. A 5-fold cross-validation result demonstrates that our method correctly detects 80 % of nodules with 4.2 FPs per case, and detection speed of proposed method is also 4-36 times faster than existing methods. Conclusion: Detection performance and speed indicate that our method may be useful for fast detection of lung nodules in CT images.

Original languageEnglish
Pages (from-to)193-205
Number of pages13
JournalInternational journal of computer assisted radiology and surgery
Volume8
Issue number2
DOIs
Publication statusPublished - 01-01-2013

Fingerprint

Thorax
Lung
Image acquisition
Support vector machines
Databases
Workflow

All Science Journal Classification (ASJC) codes

  • Surgery
  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

@article{d4630bb09778429fbe29d05318d53225,
title = "Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter",
abstract = "Purpose: Existing computer-aided detection schemes for lung nodule detection require a large number of calculations and tens of minutes per case; there is a large gap between image acquisition time and nodule detection time. In this study, we propose a fast detection scheme of lung nodule in chest CT images using cylindrical nodule-enhancement filter with the aim of improving the workflow for diagnosis in CT examinations. Methods: Proposed detection scheme involves segmentation of the lung region, preprocessing, nodule enhancement, further segmentation, and false-positive (FP) reduction. As a nodule enhancement, our method employs a cylindrical shape filter to reduce the number of calculations. False positives (FPs) in nodule candidates are reduced using support vector machine and seven types of characteristic parameters. Results: The detection performance and speed were evaluated experimentally using Lung Image Database Consortium publicly available image database. A 5-fold cross-validation result demonstrates that our method correctly detects 80 {\%} of nodules with 4.2 FPs per case, and detection speed of proposed method is also 4-36 times faster than existing methods. Conclusion: Detection performance and speed indicate that our method may be useful for fast detection of lung nodules in CT images.",
author = "Atsushi Teramoto and Hiroshi Fujita",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/s11548-012-0767-5",
language = "English",
volume = "8",
pages = "193--205",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "2",

}

Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter. / Teramoto, Atsushi; Fujita, Hiroshi.

In: International journal of computer assisted radiology and surgery, Vol. 8, No. 2, 01.01.2013, p. 193-205.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter

AU - Teramoto, Atsushi

AU - Fujita, Hiroshi

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Purpose: Existing computer-aided detection schemes for lung nodule detection require a large number of calculations and tens of minutes per case; there is a large gap between image acquisition time and nodule detection time. In this study, we propose a fast detection scheme of lung nodule in chest CT images using cylindrical nodule-enhancement filter with the aim of improving the workflow for diagnosis in CT examinations. Methods: Proposed detection scheme involves segmentation of the lung region, preprocessing, nodule enhancement, further segmentation, and false-positive (FP) reduction. As a nodule enhancement, our method employs a cylindrical shape filter to reduce the number of calculations. False positives (FPs) in nodule candidates are reduced using support vector machine and seven types of characteristic parameters. Results: The detection performance and speed were evaluated experimentally using Lung Image Database Consortium publicly available image database. A 5-fold cross-validation result demonstrates that our method correctly detects 80 % of nodules with 4.2 FPs per case, and detection speed of proposed method is also 4-36 times faster than existing methods. Conclusion: Detection performance and speed indicate that our method may be useful for fast detection of lung nodules in CT images.

AB - Purpose: Existing computer-aided detection schemes for lung nodule detection require a large number of calculations and tens of minutes per case; there is a large gap between image acquisition time and nodule detection time. In this study, we propose a fast detection scheme of lung nodule in chest CT images using cylindrical nodule-enhancement filter with the aim of improving the workflow for diagnosis in CT examinations. Methods: Proposed detection scheme involves segmentation of the lung region, preprocessing, nodule enhancement, further segmentation, and false-positive (FP) reduction. As a nodule enhancement, our method employs a cylindrical shape filter to reduce the number of calculations. False positives (FPs) in nodule candidates are reduced using support vector machine and seven types of characteristic parameters. Results: The detection performance and speed were evaluated experimentally using Lung Image Database Consortium publicly available image database. A 5-fold cross-validation result demonstrates that our method correctly detects 80 % of nodules with 4.2 FPs per case, and detection speed of proposed method is also 4-36 times faster than existing methods. Conclusion: Detection performance and speed indicate that our method may be useful for fast detection of lung nodules in CT images.

UR - http://www.scopus.com/inward/record.url?scp=84878889029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878889029&partnerID=8YFLogxK

U2 - 10.1007/s11548-012-0767-5

DO - 10.1007/s11548-012-0767-5

M3 - Article

C2 - 22684487

AN - SCOPUS:84878889029

VL - 8

SP - 193

EP - 205

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 2

ER -