Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization

Feng Li, Hidetaka Arimura, Kenji Suzuki, Junji Shiraishi, Qiang Li, Hiroyuki Abe, Roger Engelmann, Shusuke Sone, Heber MacMahon, Kunio Doi

Research output: Contribution to journalArticle

91 Citations (Scopus)

Abstract

PURPOSE: To retrospectively evaluate whether a difference-image computer-aided detection (CAD) scheme can help radiologists detect peripheral lung cancers missed at low-dose computed tomography (CT). MATERIALS AND METHODS: Institutional review board approval and informed patient and observer consent were obtained. Seventeen patients (eight men and nine women; mean age, 60 years) with a missed peripheral lung cancer and 10 control subjects (five men and five women; mean age, 63 years) without cancer at low-dose CT were included in an observer study. Fourteen radiologists were divided into two groups on the basis of different image display formats: Six radiologists (group 1) reviewed CT scans with a multiformat display, and eight radiologists (group 2) reviewed images with a "stacked" cine-mode display. The radiologists, first without and then with the CAD scheme, indicated their confidence level regarding the presence (or absence) of cancer and the most likely position of a lesion on each CT scan. Receiver operating characteristic (ROC) curves were calculated without and with localization to evaluate the observers' performance. RESULTS: With the CAD scheme, the average area under the ROC curve improved from 0.763 to 0.854 for all radiologists (P = .002), from 0.757 to 0.862 for group 1 (P = .04), and from 0.768 to 0.848 for group 2 (P = .01). The average sensitivity in the detection of 17 cancers improved from 52% (124 of 238 observations) to 68% (163 of 238 observations) for all radiologists (P < .001), from 49% (50 of 102 observations) to 71% (72 of 102 observations) for group 1 (P = .02), and from 54% (74 of 136 observations) to 67% (91 of 136 observations) for group 2 (P = .006). The localization ROC curve also improved. CONCLUSION: Lung cancers missed at low-dose CT were very difficult to detect, even in an observer study. The use of CAD, however, can improve radiologists' performance in the detection of these subtle cancers.

Original languageEnglish
Pages (from-to)684-690
Number of pages7
JournalRadiology
Volume237
Issue number2
DOIs
Publication statusPublished - Nov 1 2005

Fingerprint

ROC Curve
Lung Neoplasms
Tomography
Neoplasms
Radiologists
Research Ethics Committees

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

Computer-aided detection of peripheral lung cancers missed at CT : ROC analyses without and with localization. / Li, Feng; Arimura, Hidetaka; Suzuki, Kenji; Shiraishi, Junji; Li, Qiang; Abe, Hiroyuki; Engelmann, Roger; Sone, Shusuke; MacMahon, Heber; Doi, Kunio.

In: Radiology, Vol. 237, No. 2, 01.11.2005, p. 684-690.

Research output: Contribution to journalArticle

Li, F, Arimura, H, Suzuki, K, Shiraishi, J, Li, Q, Abe, H, Engelmann, R, Sone, S, MacMahon, H & Doi, K 2005, 'Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization', Radiology, vol. 237, no. 2, pp. 684-690. https://doi.org/10.1148/radiol.2372041555
Li, Feng ; Arimura, Hidetaka ; Suzuki, Kenji ; Shiraishi, Junji ; Li, Qiang ; Abe, Hiroyuki ; Engelmann, Roger ; Sone, Shusuke ; MacMahon, Heber ; Doi, Kunio. / Computer-aided detection of peripheral lung cancers missed at CT : ROC analyses without and with localization. In: Radiology. 2005 ; Vol. 237, No. 2. pp. 684-690.
@article{4c455beef3304e5b8588634786bd49b5,
title = "Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization",
abstract = "PURPOSE: To retrospectively evaluate whether a difference-image computer-aided detection (CAD) scheme can help radiologists detect peripheral lung cancers missed at low-dose computed tomography (CT). MATERIALS AND METHODS: Institutional review board approval and informed patient and observer consent were obtained. Seventeen patients (eight men and nine women; mean age, 60 years) with a missed peripheral lung cancer and 10 control subjects (five men and five women; mean age, 63 years) without cancer at low-dose CT were included in an observer study. Fourteen radiologists were divided into two groups on the basis of different image display formats: Six radiologists (group 1) reviewed CT scans with a multiformat display, and eight radiologists (group 2) reviewed images with a {"}stacked{"} cine-mode display. The radiologists, first without and then with the CAD scheme, indicated their confidence level regarding the presence (or absence) of cancer and the most likely position of a lesion on each CT scan. Receiver operating characteristic (ROC) curves were calculated without and with localization to evaluate the observers' performance. RESULTS: With the CAD scheme, the average area under the ROC curve improved from 0.763 to 0.854 for all radiologists (P = .002), from 0.757 to 0.862 for group 1 (P = .04), and from 0.768 to 0.848 for group 2 (P = .01). The average sensitivity in the detection of 17 cancers improved from 52{\%} (124 of 238 observations) to 68{\%} (163 of 238 observations) for all radiologists (P < .001), from 49{\%} (50 of 102 observations) to 71{\%} (72 of 102 observations) for group 1 (P = .02), and from 54{\%} (74 of 136 observations) to 67{\%} (91 of 136 observations) for group 2 (P = .006). The localization ROC curve also improved. CONCLUSION: Lung cancers missed at low-dose CT were very difficult to detect, even in an observer study. The use of CAD, however, can improve radiologists' performance in the detection of these subtle cancers.",
author = "Feng Li and Hidetaka Arimura and Kenji Suzuki and Junji Shiraishi and Qiang Li and Hiroyuki Abe and Roger Engelmann and Shusuke Sone and Heber MacMahon and Kunio Doi",
year = "2005",
month = "11",
day = "1",
doi = "10.1148/radiol.2372041555",
language = "English",
volume = "237",
pages = "684--690",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "2",

}

TY - JOUR

T1 - Computer-aided detection of peripheral lung cancers missed at CT

T2 - ROC analyses without and with localization

AU - Li, Feng

AU - Arimura, Hidetaka

AU - Suzuki, Kenji

AU - Shiraishi, Junji

AU - Li, Qiang

AU - Abe, Hiroyuki

AU - Engelmann, Roger

AU - Sone, Shusuke

AU - MacMahon, Heber

AU - Doi, Kunio

PY - 2005/11/1

Y1 - 2005/11/1

N2 - PURPOSE: To retrospectively evaluate whether a difference-image computer-aided detection (CAD) scheme can help radiologists detect peripheral lung cancers missed at low-dose computed tomography (CT). MATERIALS AND METHODS: Institutional review board approval and informed patient and observer consent were obtained. Seventeen patients (eight men and nine women; mean age, 60 years) with a missed peripheral lung cancer and 10 control subjects (five men and five women; mean age, 63 years) without cancer at low-dose CT were included in an observer study. Fourteen radiologists were divided into two groups on the basis of different image display formats: Six radiologists (group 1) reviewed CT scans with a multiformat display, and eight radiologists (group 2) reviewed images with a "stacked" cine-mode display. The radiologists, first without and then with the CAD scheme, indicated their confidence level regarding the presence (or absence) of cancer and the most likely position of a lesion on each CT scan. Receiver operating characteristic (ROC) curves were calculated without and with localization to evaluate the observers' performance. RESULTS: With the CAD scheme, the average area under the ROC curve improved from 0.763 to 0.854 for all radiologists (P = .002), from 0.757 to 0.862 for group 1 (P = .04), and from 0.768 to 0.848 for group 2 (P = .01). The average sensitivity in the detection of 17 cancers improved from 52% (124 of 238 observations) to 68% (163 of 238 observations) for all radiologists (P < .001), from 49% (50 of 102 observations) to 71% (72 of 102 observations) for group 1 (P = .02), and from 54% (74 of 136 observations) to 67% (91 of 136 observations) for group 2 (P = .006). The localization ROC curve also improved. CONCLUSION: Lung cancers missed at low-dose CT were very difficult to detect, even in an observer study. The use of CAD, however, can improve radiologists' performance in the detection of these subtle cancers.

AB - PURPOSE: To retrospectively evaluate whether a difference-image computer-aided detection (CAD) scheme can help radiologists detect peripheral lung cancers missed at low-dose computed tomography (CT). MATERIALS AND METHODS: Institutional review board approval and informed patient and observer consent were obtained. Seventeen patients (eight men and nine women; mean age, 60 years) with a missed peripheral lung cancer and 10 control subjects (five men and five women; mean age, 63 years) without cancer at low-dose CT were included in an observer study. Fourteen radiologists were divided into two groups on the basis of different image display formats: Six radiologists (group 1) reviewed CT scans with a multiformat display, and eight radiologists (group 2) reviewed images with a "stacked" cine-mode display. The radiologists, first without and then with the CAD scheme, indicated their confidence level regarding the presence (or absence) of cancer and the most likely position of a lesion on each CT scan. Receiver operating characteristic (ROC) curves were calculated without and with localization to evaluate the observers' performance. RESULTS: With the CAD scheme, the average area under the ROC curve improved from 0.763 to 0.854 for all radiologists (P = .002), from 0.757 to 0.862 for group 1 (P = .04), and from 0.768 to 0.848 for group 2 (P = .01). The average sensitivity in the detection of 17 cancers improved from 52% (124 of 238 observations) to 68% (163 of 238 observations) for all radiologists (P < .001), from 49% (50 of 102 observations) to 71% (72 of 102 observations) for group 1 (P = .02), and from 54% (74 of 136 observations) to 67% (91 of 136 observations) for group 2 (P = .006). The localization ROC curve also improved. CONCLUSION: Lung cancers missed at low-dose CT were very difficult to detect, even in an observer study. The use of CAD, however, can improve radiologists' performance in the detection of these subtle cancers.

UR - http://www.scopus.com/inward/record.url?scp=27144509110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27144509110&partnerID=8YFLogxK

U2 - 10.1148/radiol.2372041555

DO - 10.1148/radiol.2372041555

M3 - Article

C2 - 16244277

AN - SCOPUS:27144509110

VL - 237

SP - 684

EP - 690

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 2

ER -