Automated lung nodule detection using positron emission tomography/computed tomography

Atsushi Teramoto, Hiroshi Fujita

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

Lung cancer is a leading cause of death in human globally. Owing to the low survival rates among lung cancer patients, it is essential to detect and treat cancer at an early stage. In some countries, positron emission tomography (PET)/X-ray computed tomography (CT) examination is also used for the cancer screening in addition to diagnosis and follow-up of treatment. PET/CT images provide both anatomical and functional information of the lung cancer. However, radiologists must examine a large number of these images and therefore, support tools for the localization of lung nodule are desired. This chapter highlights our recent contributions to a hybrid detection scheme of lung nodules in PET/CT images. In the CT image, a massive region is first detected using a cylindrical nodule enhancement filter (CNEF), which is a cylindrical kernel shaped by contrast enhancement filter. Subsequently, high-uptake regions detected by the PET images are merged with the region detected by the CT image. False positives (FPs) among the leading candidates are eliminated by a rule-based classifier and three support vector machines based on the characteristic features obtained from CT and PET images. Experimentally, the detection capability was evaluated using 100 cases of PET/CT images. As a result, the sensitivity in detecting candidates was 83%, with 5 FPs/case. These results indicate that the proposed hybrid method may be useful for the computer-aided detection of lung cancer in clinical practice.

Original languageEnglish
Title of host publicationIntelligent Systems Reference Library
PublisherSpringer Science and Business Media Deutschland GmbH
Pages87-110
Number of pages24
DOIs
Publication statusPublished - 01-01-2018

Publication series

NameIntelligent Systems Reference Library
Volume140
ISSN (Print)1868-4394
ISSN (Electronic)1868-4408

Fingerprint

Positron emission tomography
Tomography
cancer
candidacy
Lung
Computed tomography
cause of death
Support vector machines
Screening
Classifiers
X rays
examination
Lung cancer

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Information Systems and Management
  • Library and Information Sciences

Cite this

Teramoto, A., & Fujita, H. (2018). Automated lung nodule detection using positron emission tomography/computed tomography. In Intelligent Systems Reference Library (pp. 87-110). (Intelligent Systems Reference Library; Vol. 140). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-68843-5_4
Teramoto, Atsushi ; Fujita, Hiroshi. / Automated lung nodule detection using positron emission tomography/computed tomography. Intelligent Systems Reference Library. Springer Science and Business Media Deutschland GmbH, 2018. pp. 87-110 (Intelligent Systems Reference Library).
@inbook{847b927b63434123911f9b9178a568b6,
title = "Automated lung nodule detection using positron emission tomography/computed tomography",
abstract = "Lung cancer is a leading cause of death in human globally. Owing to the low survival rates among lung cancer patients, it is essential to detect and treat cancer at an early stage. In some countries, positron emission tomography (PET)/X-ray computed tomography (CT) examination is also used for the cancer screening in addition to diagnosis and follow-up of treatment. PET/CT images provide both anatomical and functional information of the lung cancer. However, radiologists must examine a large number of these images and therefore, support tools for the localization of lung nodule are desired. This chapter highlights our recent contributions to a hybrid detection scheme of lung nodules in PET/CT images. In the CT image, a massive region is first detected using a cylindrical nodule enhancement filter (CNEF), which is a cylindrical kernel shaped by contrast enhancement filter. Subsequently, high-uptake regions detected by the PET images are merged with the region detected by the CT image. False positives (FPs) among the leading candidates are eliminated by a rule-based classifier and three support vector machines based on the characteristic features obtained from CT and PET images. Experimentally, the detection capability was evaluated using 100 cases of PET/CT images. As a result, the sensitivity in detecting candidates was 83{\%}, with 5 FPs/case. These results indicate that the proposed hybrid method may be useful for the computer-aided detection of lung cancer in clinical practice.",
author = "Atsushi Teramoto and Hiroshi Fujita",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-68843-5_4",
language = "English",
series = "Intelligent Systems Reference Library",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "87--110",
booktitle = "Intelligent Systems Reference Library",
address = "Germany",

}

Teramoto, A & Fujita, H 2018, Automated lung nodule detection using positron emission tomography/computed tomography. in Intelligent Systems Reference Library. Intelligent Systems Reference Library, vol. 140, Springer Science and Business Media Deutschland GmbH, pp. 87-110. https://doi.org/10.1007/978-3-319-68843-5_4

Automated lung nodule detection using positron emission tomography/computed tomography. / Teramoto, Atsushi; Fujita, Hiroshi.

Intelligent Systems Reference Library. Springer Science and Business Media Deutschland GmbH, 2018. p. 87-110 (Intelligent Systems Reference Library; Vol. 140).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Automated lung nodule detection using positron emission tomography/computed tomography

AU - Teramoto, Atsushi

AU - Fujita, Hiroshi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Lung cancer is a leading cause of death in human globally. Owing to the low survival rates among lung cancer patients, it is essential to detect and treat cancer at an early stage. In some countries, positron emission tomography (PET)/X-ray computed tomography (CT) examination is also used for the cancer screening in addition to diagnosis and follow-up of treatment. PET/CT images provide both anatomical and functional information of the lung cancer. However, radiologists must examine a large number of these images and therefore, support tools for the localization of lung nodule are desired. This chapter highlights our recent contributions to a hybrid detection scheme of lung nodules in PET/CT images. In the CT image, a massive region is first detected using a cylindrical nodule enhancement filter (CNEF), which is a cylindrical kernel shaped by contrast enhancement filter. Subsequently, high-uptake regions detected by the PET images are merged with the region detected by the CT image. False positives (FPs) among the leading candidates are eliminated by a rule-based classifier and three support vector machines based on the characteristic features obtained from CT and PET images. Experimentally, the detection capability was evaluated using 100 cases of PET/CT images. As a result, the sensitivity in detecting candidates was 83%, with 5 FPs/case. These results indicate that the proposed hybrid method may be useful for the computer-aided detection of lung cancer in clinical practice.

AB - Lung cancer is a leading cause of death in human globally. Owing to the low survival rates among lung cancer patients, it is essential to detect and treat cancer at an early stage. In some countries, positron emission tomography (PET)/X-ray computed tomography (CT) examination is also used for the cancer screening in addition to diagnosis and follow-up of treatment. PET/CT images provide both anatomical and functional information of the lung cancer. However, radiologists must examine a large number of these images and therefore, support tools for the localization of lung nodule are desired. This chapter highlights our recent contributions to a hybrid detection scheme of lung nodules in PET/CT images. In the CT image, a massive region is first detected using a cylindrical nodule enhancement filter (CNEF), which is a cylindrical kernel shaped by contrast enhancement filter. Subsequently, high-uptake regions detected by the PET images are merged with the region detected by the CT image. False positives (FPs) among the leading candidates are eliminated by a rule-based classifier and three support vector machines based on the characteristic features obtained from CT and PET images. Experimentally, the detection capability was evaluated using 100 cases of PET/CT images. As a result, the sensitivity in detecting candidates was 83%, with 5 FPs/case. These results indicate that the proposed hybrid method may be useful for the computer-aided detection of lung cancer in clinical practice.

UR - http://www.scopus.com/inward/record.url?scp=85040516856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040516856&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-68843-5_4

DO - 10.1007/978-3-319-68843-5_4

M3 - Chapter

T3 - Intelligent Systems Reference Library

SP - 87

EP - 110

BT - Intelligent Systems Reference Library

PB - Springer Science and Business Media Deutschland GmbH

ER -

Teramoto A, Fujita H. Automated lung nodule detection using positron emission tomography/computed tomography. In Intelligent Systems Reference Library. Springer Science and Business Media Deutschland GmbH. 2018. p. 87-110. (Intelligent Systems Reference Library). https://doi.org/10.1007/978-3-319-68843-5_4