Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction

Atsushi Teramoto, Hiroshi Fujita, Yoya Tomita, Katsuaki Takahashi, Osamu Yamamuro, Tsuneo Tamaki

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

3 Citations (Scopus)

Abstract

In this study, an automated scheme for detecting pulmonary nodules in PET/CT images has been proposed using combined detection and hybrid false-positive (FP) reduction techniques. The initial nodule candidates were detected separately from CT and PET images. FPs were then eliminated in the initial candidates by using support vector machine with characteristic values obtained from CT and PET images. In the experiment, we evaluated proposed method using 105 cases of PET/CT images that were obtained in the cancer-screening program. We evaluated true positive fraction (TPF) and FP/case. As a result, TPFs of CT and PET detections were 0.76 and 0.44, respectively. However, by integrating the both results, TPF was reached to 0.82 with 5.14 FPs/case. These results indicate that our method may be of practical use for the detection of pulmonary nodules using PET/CT images.

Original languageEnglish
Title of host publicationMedical Imaging 2012
Subtitle of host publicationComputer-Aided Diagnosis
Volume8315
DOIs
Publication statusPublished - 01-12-2012
EventMedical Imaging 2012: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: 07-02-201209-02-2012

Other

OtherMedical Imaging 2012: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period07-02-1209-02-12

Fingerprint

nodules
Support vector machines
Screening
Lung
Experiments
Early Detection of Cancer
screening
cancer
Positron Emission Tomography Computed Tomography

All Science Journal Classification (ASJC) codes

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

Cite this

Teramoto, A., Fujita, H., Tomita, Y., Takahashi, K., Yamamuro, O., & Tamaki, T. (2012). Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction. In Medical Imaging 2012: Computer-Aided Diagnosis (Vol. 8315). [83152V] https://doi.org/10.1117/12.912102
Teramoto, Atsushi ; Fujita, Hiroshi ; Tomita, Yoya ; Takahashi, Katsuaki ; Yamamuro, Osamu ; Tamaki, Tsuneo. / Pulmonary nodule detection in PET/CT images : Improved approach using combined nodule detection and hybrid FP reduction. Medical Imaging 2012: Computer-Aided Diagnosis. Vol. 8315 2012.
@inproceedings{a1f82fdccbea433c84c9372427db39da,
title = "Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction",
abstract = "In this study, an automated scheme for detecting pulmonary nodules in PET/CT images has been proposed using combined detection and hybrid false-positive (FP) reduction techniques. The initial nodule candidates were detected separately from CT and PET images. FPs were then eliminated in the initial candidates by using support vector machine with characteristic values obtained from CT and PET images. In the experiment, we evaluated proposed method using 105 cases of PET/CT images that were obtained in the cancer-screening program. We evaluated true positive fraction (TPF) and FP/case. As a result, TPFs of CT and PET detections were 0.76 and 0.44, respectively. However, by integrating the both results, TPF was reached to 0.82 with 5.14 FPs/case. These results indicate that our method may be of practical use for the detection of pulmonary nodules using PET/CT images.",
author = "Atsushi Teramoto and Hiroshi Fujita and Yoya Tomita and Katsuaki Takahashi and Osamu Yamamuro and Tsuneo Tamaki",
year = "2012",
month = "12",
day = "1",
doi = "10.1117/12.912102",
language = "English",
isbn = "9780819489647",
volume = "8315",
booktitle = "Medical Imaging 2012",

}

Teramoto, A, Fujita, H, Tomita, Y, Takahashi, K, Yamamuro, O & Tamaki, T 2012, Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction. in Medical Imaging 2012: Computer-Aided Diagnosis. vol. 8315, 83152V, Medical Imaging 2012: Computer-Aided Diagnosis, San Diego, CA, United States, 07-02-12. https://doi.org/10.1117/12.912102

Pulmonary nodule detection in PET/CT images : Improved approach using combined nodule detection and hybrid FP reduction. / Teramoto, Atsushi; Fujita, Hiroshi; Tomita, Yoya; Takahashi, Katsuaki; Yamamuro, Osamu; Tamaki, Tsuneo.

Medical Imaging 2012: Computer-Aided Diagnosis. Vol. 8315 2012. 83152V.

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

TY - GEN

T1 - Pulmonary nodule detection in PET/CT images

T2 - Improved approach using combined nodule detection and hybrid FP reduction

AU - Teramoto, Atsushi

AU - Fujita, Hiroshi

AU - Tomita, Yoya

AU - Takahashi, Katsuaki

AU - Yamamuro, Osamu

AU - Tamaki, Tsuneo

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this study, an automated scheme for detecting pulmonary nodules in PET/CT images has been proposed using combined detection and hybrid false-positive (FP) reduction techniques. The initial nodule candidates were detected separately from CT and PET images. FPs were then eliminated in the initial candidates by using support vector machine with characteristic values obtained from CT and PET images. In the experiment, we evaluated proposed method using 105 cases of PET/CT images that were obtained in the cancer-screening program. We evaluated true positive fraction (TPF) and FP/case. As a result, TPFs of CT and PET detections were 0.76 and 0.44, respectively. However, by integrating the both results, TPF was reached to 0.82 with 5.14 FPs/case. These results indicate that our method may be of practical use for the detection of pulmonary nodules using PET/CT images.

AB - In this study, an automated scheme for detecting pulmonary nodules in PET/CT images has been proposed using combined detection and hybrid false-positive (FP) reduction techniques. The initial nodule candidates were detected separately from CT and PET images. FPs were then eliminated in the initial candidates by using support vector machine with characteristic values obtained from CT and PET images. In the experiment, we evaluated proposed method using 105 cases of PET/CT images that were obtained in the cancer-screening program. We evaluated true positive fraction (TPF) and FP/case. As a result, TPFs of CT and PET detections were 0.76 and 0.44, respectively. However, by integrating the both results, TPF was reached to 0.82 with 5.14 FPs/case. These results indicate that our method may be of practical use for the detection of pulmonary nodules using PET/CT images.

UR - http://www.scopus.com/inward/record.url?scp=84874886051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874886051&partnerID=8YFLogxK

U2 - 10.1117/12.912102

DO - 10.1117/12.912102

M3 - Conference contribution

AN - SCOPUS:84874886051

SN - 9780819489647

VL - 8315

BT - Medical Imaging 2012

ER -

Teramoto A, Fujita H, Tomita Y, Takahashi K, Yamamuro O, Tamaki T. Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction. In Medical Imaging 2012: Computer-Aided Diagnosis. Vol. 8315. 2012. 83152V https://doi.org/10.1117/12.912102