Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique

Atsushi Teramoto, Hiroshi Fujita, Osamu Yamamuro, Tsuneo Tamaki

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using an active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2%, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1%, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors ensemble FP-reduction method eliminated 93% of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images.

Original languageEnglish
Pages (from-to)2821-2827
Number of pages7
JournalMedical Physics
Volume43
Issue number6
DOIs
Publication statusPublished - 01-06-2016

Fingerprint

Lung
Tomography
Solitary Pulmonary Nodule
Positron Emission Tomography Computed Tomography
Early Detection of Cancer
Positron-Emission Tomography

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

@article{83767e358a534bdfbb12e58fb114b34e,
title = "Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique",
abstract = "Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using an active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2{\%}, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1{\%}, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors ensemble FP-reduction method eliminated 93{\%} of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images.",
author = "Atsushi Teramoto and Hiroshi Fujita and Osamu Yamamuro and Tsuneo Tamaki",
year = "2016",
month = "6",
day = "1",
doi = "10.1118/1.4948498",
language = "English",
volume = "43",
pages = "2821--2827",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

Automated detection of pulmonary nodules in PET/CT images : Ensemble false-positive reduction using a convolutional neural network technique. / Teramoto, Atsushi; Fujita, Hiroshi; Yamamuro, Osamu; Tamaki, Tsuneo.

In: Medical Physics, Vol. 43, No. 6, 01.06.2016, p. 2821-2827.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated detection of pulmonary nodules in PET/CT images

T2 - Ensemble false-positive reduction using a convolutional neural network technique

AU - Teramoto, Atsushi

AU - Fujita, Hiroshi

AU - Yamamuro, Osamu

AU - Tamaki, Tsuneo

PY - 2016/6/1

Y1 - 2016/6/1

N2 - Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using an active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2%, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1%, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors ensemble FP-reduction method eliminated 93% of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images.

AB - Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using an active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2%, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1%, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors ensemble FP-reduction method eliminated 93% of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images.

UR - http://www.scopus.com/inward/record.url?scp=84969776874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969776874&partnerID=8YFLogxK

U2 - 10.1118/1.4948498

DO - 10.1118/1.4948498

M3 - Article

C2 - 27277030

AN - SCOPUS:84969776874

VL - 43

SP - 2821

EP - 2827

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -