Value of a computer-Aided detection system based on chest tomosynthesis imaging for the detection of pulmonary nodules

Yoshitake Yamada, Eisuke Shiomi, Masahiro Hashimoto, Takayuki Abe, Masaki Matsusako, Yukihisa Saida, Kenji Ogawa

研究成果: Article

1 引用 (Scopus)

抄録

Purpose: To assess the value of a computer-Aided detection (CAD) system for the detection of pulmonary nodules on chest tomosynthesis images. Materials and Methods: Fifty patients with and 50 without pulmonary nodules underwent both chest tomosynthesis and multidetector computed tomography (CT) on the same day. Fifteen observers (five interns and residents, five chest radiologists, and five abdominal radiologists) independently evaluated tomosynthesis images of 100 patients for the presence of pulmonary nodules in a blinded and randomized manner, first without CAD, then with the inclusion of CAD marks. Multidetector CT images served as the reference standard. Free-response receiver operating characteristic analysis was used for the statistical analysis. Results: The pooled diagnostic performance of 15 observers was significantly better with CAD than without CAD (figure of merit [FOM], 0.74 vs 0.71, respectively; P = .02). The average true-positive fraction and false-positive rate per all cases with CAD were 0.56 and 0.26, respectively, whereas those without CAD were 0.47 and 0.20, respectively. Subanalysis showed that the diagnostic performance of interns and residents was significantly better with CAD than without CAD (FOM, 0.70 vs 0.62, respectively; P = .001), whereas for chest radiologists and abdominal radiologists, the FOM with CAD values were greater but not significantly: 0.80 versus 0.78 (P = .38) and 0.74 versus 0.73 (P = .65), respectively. Conclusion: CAD significantly improved diagnostic performance in the detection of pulmonary nodules on chest tomosynthesis images for interns and residents, but provided minimal benefit for chest radiologists and abdominal radiologists.

元の言語English
ページ(範囲)333-339
ページ数7
ジャーナルRadiology
287
発行部数1
DOI
出版物ステータスPublished - 2018 4 1
外部発表Yes

Fingerprint

Thorax
Lung
Multidetector Computed Tomography
ROC Curve
Radiologists

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

これを引用

Value of a computer-Aided detection system based on chest tomosynthesis imaging for the detection of pulmonary nodules. / Yamada, Yoshitake; Shiomi, Eisuke; Hashimoto, Masahiro; Abe, Takayuki; Matsusako, Masaki; Saida, Yukihisa; Ogawa, Kenji.

:: Radiology, 巻 287, 番号 1, 01.04.2018, p. 333-339.

研究成果: Article

Yamada, Yoshitake ; Shiomi, Eisuke ; Hashimoto, Masahiro ; Abe, Takayuki ; Matsusako, Masaki ; Saida, Yukihisa ; Ogawa, Kenji. / Value of a computer-Aided detection system based on chest tomosynthesis imaging for the detection of pulmonary nodules. :: Radiology. 2018 ; 巻 287, 番号 1. pp. 333-339.
@article{aa1b567c3c4d4a8fac5951b61b237d3d,
title = "Value of a computer-Aided detection system based on chest tomosynthesis imaging for the detection of pulmonary nodules",
abstract = "Purpose: To assess the value of a computer-Aided detection (CAD) system for the detection of pulmonary nodules on chest tomosynthesis images. Materials and Methods: Fifty patients with and 50 without pulmonary nodules underwent both chest tomosynthesis and multidetector computed tomography (CT) on the same day. Fifteen observers (five interns and residents, five chest radiologists, and five abdominal radiologists) independently evaluated tomosynthesis images of 100 patients for the presence of pulmonary nodules in a blinded and randomized manner, first without CAD, then with the inclusion of CAD marks. Multidetector CT images served as the reference standard. Free-response receiver operating characteristic analysis was used for the statistical analysis. Results: The pooled diagnostic performance of 15 observers was significantly better with CAD than without CAD (figure of merit [FOM], 0.74 vs 0.71, respectively; P = .02). The average true-positive fraction and false-positive rate per all cases with CAD were 0.56 and 0.26, respectively, whereas those without CAD were 0.47 and 0.20, respectively. Subanalysis showed that the diagnostic performance of interns and residents was significantly better with CAD than without CAD (FOM, 0.70 vs 0.62, respectively; P = .001), whereas for chest radiologists and abdominal radiologists, the FOM with CAD values were greater but not significantly: 0.80 versus 0.78 (P = .38) and 0.74 versus 0.73 (P = .65), respectively. Conclusion: CAD significantly improved diagnostic performance in the detection of pulmonary nodules on chest tomosynthesis images for interns and residents, but provided minimal benefit for chest radiologists and abdominal radiologists.",
author = "Yoshitake Yamada and Eisuke Shiomi and Masahiro Hashimoto and Takayuki Abe and Masaki Matsusako and Yukihisa Saida and Kenji Ogawa",
year = "2018",
month = "4",
day = "1",
doi = "10.1148/radiol.2017170405",
language = "English",
volume = "287",
pages = "333--339",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "1",

}

TY - JOUR

T1 - Value of a computer-Aided detection system based on chest tomosynthesis imaging for the detection of pulmonary nodules

AU - Yamada, Yoshitake

AU - Shiomi, Eisuke

AU - Hashimoto, Masahiro

AU - Abe, Takayuki

AU - Matsusako, Masaki

AU - Saida, Yukihisa

AU - Ogawa, Kenji

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Purpose: To assess the value of a computer-Aided detection (CAD) system for the detection of pulmonary nodules on chest tomosynthesis images. Materials and Methods: Fifty patients with and 50 without pulmonary nodules underwent both chest tomosynthesis and multidetector computed tomography (CT) on the same day. Fifteen observers (five interns and residents, five chest radiologists, and five abdominal radiologists) independently evaluated tomosynthesis images of 100 patients for the presence of pulmonary nodules in a blinded and randomized manner, first without CAD, then with the inclusion of CAD marks. Multidetector CT images served as the reference standard. Free-response receiver operating characteristic analysis was used for the statistical analysis. Results: The pooled diagnostic performance of 15 observers was significantly better with CAD than without CAD (figure of merit [FOM], 0.74 vs 0.71, respectively; P = .02). The average true-positive fraction and false-positive rate per all cases with CAD were 0.56 and 0.26, respectively, whereas those without CAD were 0.47 and 0.20, respectively. Subanalysis showed that the diagnostic performance of interns and residents was significantly better with CAD than without CAD (FOM, 0.70 vs 0.62, respectively; P = .001), whereas for chest radiologists and abdominal radiologists, the FOM with CAD values were greater but not significantly: 0.80 versus 0.78 (P = .38) and 0.74 versus 0.73 (P = .65), respectively. Conclusion: CAD significantly improved diagnostic performance in the detection of pulmonary nodules on chest tomosynthesis images for interns and residents, but provided minimal benefit for chest radiologists and abdominal radiologists.

AB - Purpose: To assess the value of a computer-Aided detection (CAD) system for the detection of pulmonary nodules on chest tomosynthesis images. Materials and Methods: Fifty patients with and 50 without pulmonary nodules underwent both chest tomosynthesis and multidetector computed tomography (CT) on the same day. Fifteen observers (five interns and residents, five chest radiologists, and five abdominal radiologists) independently evaluated tomosynthesis images of 100 patients for the presence of pulmonary nodules in a blinded and randomized manner, first without CAD, then with the inclusion of CAD marks. Multidetector CT images served as the reference standard. Free-response receiver operating characteristic analysis was used for the statistical analysis. Results: The pooled diagnostic performance of 15 observers was significantly better with CAD than without CAD (figure of merit [FOM], 0.74 vs 0.71, respectively; P = .02). The average true-positive fraction and false-positive rate per all cases with CAD were 0.56 and 0.26, respectively, whereas those without CAD were 0.47 and 0.20, respectively. Subanalysis showed that the diagnostic performance of interns and residents was significantly better with CAD than without CAD (FOM, 0.70 vs 0.62, respectively; P = .001), whereas for chest radiologists and abdominal radiologists, the FOM with CAD values were greater but not significantly: 0.80 versus 0.78 (P = .38) and 0.74 versus 0.73 (P = .65), respectively. Conclusion: CAD significantly improved diagnostic performance in the detection of pulmonary nodules on chest tomosynthesis images for interns and residents, but provided minimal benefit for chest radiologists and abdominal radiologists.

UR - http://www.scopus.com/inward/record.url?scp=85044281101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044281101&partnerID=8YFLogxK

U2 - 10.1148/radiol.2017170405

DO - 10.1148/radiol.2017170405

M3 - Article

C2 - 29206596

AN - SCOPUS:85044281101

VL - 287

SP - 333

EP - 339

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 1

ER -