Automated detection of lung tumors in PET/CT images using active contour filter

Atsushi Teramoto, Hayato Adachi, Masakazu Tsujimoto, Hiroshi Fujita, Katsuaki Takahashi, Osamu Yamamuro, Tsuneo Tamaki, Masami Nishio, Toshiki Kobayashi

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

4 Citations (Scopus)

Abstract

In a previous study, we developed a hybrid tumor detection method that used both computed tomography (CT) and positron emission tomography (PET) images. However, similar to existing computer-aided detection (CAD) schemes, it was difficult to detect low-contrast lesions that touch to the normal organs such as the chest wall or blood vessels in the lung. In the current study, we proposed a novel lung tumor detection method that uses active contour filters to detect the nodules deemed »difficult» in previous CAD schemes. The proposed scheme detects lung tumors using both CT and PET images. As for the detection in CT images, the massive region was first enhanced using an active contour filter (ACF), which is a type of contrast enhancement filter that has a deformable kernel shape. The kernel shape involves closed curves that are connected by several nodes that move iteratively in order to enclose the massive region. The final output of ACF is the difference between the maximum pixel value on the deformable kernel, and pixel value on the center of the filter kernel. Subsequently, the PET images were binarized to detect the regions of increased uptake. The results were integrated, followed by the false positive reduction using 21 characteristic features and three support vector machines. In the experiment, we evaluated the proposed method using 100 PET/CT images. More than half of nodules missed using previous methods were accurately detected. The results indicate that our method may be useful for the detection of lung tumors using PET/CT images.

Original languageEnglish
Title of host publicationMedical Imaging 2015
Subtitle of host publicationComputer-Aided Diagnosis
EditorsLubomir M. Hadjiiski, Lubomir M. Hadjiiski, Georgia D. Tourassi, Georgia D. Tourassi
PublisherSPIE
ISBN (Electronic)9781628415049, 9781628415049
DOIs
Publication statusPublished - 01-01-2015
EventSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis - Orlando, United States
Duration: 22-02-201525-02-2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9414
ISSN (Print)1605-7422

Other

OtherSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis
CountryUnited States
CityOrlando
Period22-02-1525-02-15

Fingerprint

Positron emission tomography
lungs
Tomography
Tumors
positrons
tumors
tomography
filters
Lung
Neoplasms
Pixels
nodules
Blood vessels
Touch
Thoracic Wall
Positron-Emission Tomography
Support vector machines
Blood Vessels
pixels
Positron Emission Tomography Computed Tomography

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Teramoto, A., Adachi, H., Tsujimoto, M., Fujita, H., Takahashi, K., Yamamuro, O., ... Kobayashi, T. (2015). Automated detection of lung tumors in PET/CT images using active contour filter. In L. M. Hadjiiski, L. M. Hadjiiski, G. D. Tourassi, & G. D. Tourassi (Eds.), Medical Imaging 2015: Computer-Aided Diagnosis [94142V] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9414). SPIE. https://doi.org/10.1117/12.2081680
Teramoto, Atsushi ; Adachi, Hayato ; Tsujimoto, Masakazu ; Fujita, Hiroshi ; Takahashi, Katsuaki ; Yamamuro, Osamu ; Tamaki, Tsuneo ; Nishio, Masami ; Kobayashi, Toshiki. / Automated detection of lung tumors in PET/CT images using active contour filter. Medical Imaging 2015: Computer-Aided Diagnosis. editor / Lubomir M. Hadjiiski ; Lubomir M. Hadjiiski ; Georgia D. Tourassi ; Georgia D. Tourassi. SPIE, 2015. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{b2b0c0ad544041ea847c591768cb14ca,
title = "Automated detection of lung tumors in PET/CT images using active contour filter",
abstract = "In a previous study, we developed a hybrid tumor detection method that used both computed tomography (CT) and positron emission tomography (PET) images. However, similar to existing computer-aided detection (CAD) schemes, it was difficult to detect low-contrast lesions that touch to the normal organs such as the chest wall or blood vessels in the lung. In the current study, we proposed a novel lung tumor detection method that uses active contour filters to detect the nodules deemed »difficult» in previous CAD schemes. The proposed scheme detects lung tumors using both CT and PET images. As for the detection in CT images, the massive region was first enhanced using an active contour filter (ACF), which is a type of contrast enhancement filter that has a deformable kernel shape. The kernel shape involves closed curves that are connected by several nodes that move iteratively in order to enclose the massive region. The final output of ACF is the difference between the maximum pixel value on the deformable kernel, and pixel value on the center of the filter kernel. Subsequently, the PET images were binarized to detect the regions of increased uptake. The results were integrated, followed by the false positive reduction using 21 characteristic features and three support vector machines. In the experiment, we evaluated the proposed method using 100 PET/CT images. More than half of nodules missed using previous methods were accurately detected. The results indicate that our method may be useful for the detection of lung tumors using PET/CT images.",
author = "Atsushi Teramoto and Hayato Adachi and Masakazu Tsujimoto and Hiroshi Fujita and Katsuaki Takahashi and Osamu Yamamuro and Tsuneo Tamaki and Masami Nishio and Toshiki Kobayashi",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2081680",
language = "English",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Hadjiiski, {Lubomir M.} and Hadjiiski, {Lubomir M.} and Tourassi, {Georgia D.} and Tourassi, {Georgia D.}",
booktitle = "Medical Imaging 2015",
address = "United States",

}

Teramoto, A, Adachi, H, Tsujimoto, M, Fujita, H, Takahashi, K, Yamamuro, O, Tamaki, T, Nishio, M & Kobayashi, T 2015, Automated detection of lung tumors in PET/CT images using active contour filter. in LM Hadjiiski, LM Hadjiiski, GD Tourassi & GD Tourassi (eds), Medical Imaging 2015: Computer-Aided Diagnosis., 94142V, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9414, SPIE, SPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis, Orlando, United States, 22-02-15. https://doi.org/10.1117/12.2081680

Automated detection of lung tumors in PET/CT images using active contour filter. / Teramoto, Atsushi; Adachi, Hayato; Tsujimoto, Masakazu; Fujita, Hiroshi; Takahashi, Katsuaki; Yamamuro, Osamu; Tamaki, Tsuneo; Nishio, Masami; Kobayashi, Toshiki.

Medical Imaging 2015: Computer-Aided Diagnosis. ed. / Lubomir M. Hadjiiski; Lubomir M. Hadjiiski; Georgia D. Tourassi; Georgia D. Tourassi. SPIE, 2015. 94142V (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9414).

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

TY - GEN

T1 - Automated detection of lung tumors in PET/CT images using active contour filter

AU - Teramoto, Atsushi

AU - Adachi, Hayato

AU - Tsujimoto, Masakazu

AU - Fujita, Hiroshi

AU - Takahashi, Katsuaki

AU - Yamamuro, Osamu

AU - Tamaki, Tsuneo

AU - Nishio, Masami

AU - Kobayashi, Toshiki

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In a previous study, we developed a hybrid tumor detection method that used both computed tomography (CT) and positron emission tomography (PET) images. However, similar to existing computer-aided detection (CAD) schemes, it was difficult to detect low-contrast lesions that touch to the normal organs such as the chest wall or blood vessels in the lung. In the current study, we proposed a novel lung tumor detection method that uses active contour filters to detect the nodules deemed »difficult» in previous CAD schemes. The proposed scheme detects lung tumors using both CT and PET images. As for the detection in CT images, the massive region was first enhanced using an active contour filter (ACF), which is a type of contrast enhancement filter that has a deformable kernel shape. The kernel shape involves closed curves that are connected by several nodes that move iteratively in order to enclose the massive region. The final output of ACF is the difference between the maximum pixel value on the deformable kernel, and pixel value on the center of the filter kernel. Subsequently, the PET images were binarized to detect the regions of increased uptake. The results were integrated, followed by the false positive reduction using 21 characteristic features and three support vector machines. In the experiment, we evaluated the proposed method using 100 PET/CT images. More than half of nodules missed using previous methods were accurately detected. The results indicate that our method may be useful for the detection of lung tumors using PET/CT images.

AB - In a previous study, we developed a hybrid tumor detection method that used both computed tomography (CT) and positron emission tomography (PET) images. However, similar to existing computer-aided detection (CAD) schemes, it was difficult to detect low-contrast lesions that touch to the normal organs such as the chest wall or blood vessels in the lung. In the current study, we proposed a novel lung tumor detection method that uses active contour filters to detect the nodules deemed »difficult» in previous CAD schemes. The proposed scheme detects lung tumors using both CT and PET images. As for the detection in CT images, the massive region was first enhanced using an active contour filter (ACF), which is a type of contrast enhancement filter that has a deformable kernel shape. The kernel shape involves closed curves that are connected by several nodes that move iteratively in order to enclose the massive region. The final output of ACF is the difference between the maximum pixel value on the deformable kernel, and pixel value on the center of the filter kernel. Subsequently, the PET images were binarized to detect the regions of increased uptake. The results were integrated, followed by the false positive reduction using 21 characteristic features and three support vector machines. In the experiment, we evaluated the proposed method using 100 PET/CT images. More than half of nodules missed using previous methods were accurately detected. The results indicate that our method may be useful for the detection of lung tumors using PET/CT images.

UR - http://www.scopus.com/inward/record.url?scp=84948799417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948799417&partnerID=8YFLogxK

U2 - 10.1117/12.2081680

DO - 10.1117/12.2081680

M3 - Conference contribution

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2015

A2 - Hadjiiski, Lubomir M.

A2 - Hadjiiski, Lubomir M.

A2 - Tourassi, Georgia D.

A2 - Tourassi, Georgia D.

PB - SPIE

ER -

Teramoto A, Adachi H, Tsujimoto M, Fujita H, Takahashi K, Yamamuro O et al. Automated detection of lung tumors in PET/CT images using active contour filter. In Hadjiiski LM, Hadjiiski LM, Tourassi GD, Tourassi GD, editors, Medical Imaging 2015: Computer-Aided Diagnosis. SPIE. 2015. 94142V. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2081680