Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system

Shingo Kakeda, Yukunori Korogi, Hidetaka Arimura, Toshinori Hirai, Shigehiko Katsuragawa, Takatoshi Aoki, Kunio Doi

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

OBJECTIVE. The objective of our study was to determine whether the use of a computer-aided diagnosis (CAD) system can shorten the reading time while maintaining the diagnostic performance of MR angiography for the detection of intracranial aneurysms. MATERIALS AND METHODS. Fifty maximum-intensity- projection MR angiograms in 50 patients (16 intracranial aneurysms and 34 negative cases) were used for this observer performance study. Sixteen radiologists - eight neuroradiologists and eight less experienced radiologists - participated in the observer studies and interpreted the MR angiograms without and with CAD output images using an independent test method. The reading times without and with CAD were compared separately for the aneurysm and negative cases. The observers' performances were evaluated using receiver operating characteristic (ROC) analysis. We analyzed separately the data obtained from neuroradiologists and from less experienced radiologists. RESULTS. For all observers, the mean area under the ROC curve (Az) with CAD was improved compared with that without CAD (0.903 vs 0.851, respectively; p = 0.109), and the mean reading time per case was reduced significantly by 18.1 seconds (28.5%) (from 63.4 to 45.3 seconds, p < 0.05). When CAD output images were available, the mean Az for the less experienced radiologists was significantly improved (0.911 vs 0.787, p < 0.05), but not for the neuroradiologists. The mean reading time of the less experienced radiologists with CAD was significantly shorter than that of the neuroradiologists without CAD (39.8 vs 54.5 seconds, p < 0.05). CONCLUSION. The use of a CAD system for the detection of intracranial aneurysms on MR angiography can shorten the reading time while improving diagnostic performance for less experienced radiologists.

Original languageEnglish
Pages (from-to)459-465
Number of pages7
JournalAmerican Journal of Roentgenology
Volume190
Issue number2
DOIs
Publication statusPublished - Feb 1 2008

Fingerprint

Intracranial Aneurysm
Reading
Angiography
ROC Curve
Aneurysm
Radiologists

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system. / Kakeda, Shingo; Korogi, Yukunori; Arimura, Hidetaka; Hirai, Toshinori; Katsuragawa, Shigehiko; Aoki, Takatoshi; Doi, Kunio.

In: American Journal of Roentgenology, Vol. 190, No. 2, 01.02.2008, p. 459-465.

Research output: Contribution to journalArticle

Kakeda, Shingo ; Korogi, Yukunori ; Arimura, Hidetaka ; Hirai, Toshinori ; Katsuragawa, Shigehiko ; Aoki, Takatoshi ; Doi, Kunio. / Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system. In: American Journal of Roentgenology. 2008 ; Vol. 190, No. 2. pp. 459-465.
@article{996b70da671f4c5e9c0e70f8a311131f,
title = "Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system",
abstract = "OBJECTIVE. The objective of our study was to determine whether the use of a computer-aided diagnosis (CAD) system can shorten the reading time while maintaining the diagnostic performance of MR angiography for the detection of intracranial aneurysms. MATERIALS AND METHODS. Fifty maximum-intensity- projection MR angiograms in 50 patients (16 intracranial aneurysms and 34 negative cases) were used for this observer performance study. Sixteen radiologists - eight neuroradiologists and eight less experienced radiologists - participated in the observer studies and interpreted the MR angiograms without and with CAD output images using an independent test method. The reading times without and with CAD were compared separately for the aneurysm and negative cases. The observers' performances were evaluated using receiver operating characteristic (ROC) analysis. We analyzed separately the data obtained from neuroradiologists and from less experienced radiologists. RESULTS. For all observers, the mean area under the ROC curve (Az) with CAD was improved compared with that without CAD (0.903 vs 0.851, respectively; p = 0.109), and the mean reading time per case was reduced significantly by 18.1 seconds (28.5{\%}) (from 63.4 to 45.3 seconds, p < 0.05). When CAD output images were available, the mean Az for the less experienced radiologists was significantly improved (0.911 vs 0.787, p < 0.05), but not for the neuroradiologists. The mean reading time of the less experienced radiologists with CAD was significantly shorter than that of the neuroradiologists without CAD (39.8 vs 54.5 seconds, p < 0.05). CONCLUSION. The use of a CAD system for the detection of intracranial aneurysms on MR angiography can shorten the reading time while improving diagnostic performance for less experienced radiologists.",
author = "Shingo Kakeda and Yukunori Korogi and Hidetaka Arimura and Toshinori Hirai and Shigehiko Katsuragawa and Takatoshi Aoki and Kunio Doi",
year = "2008",
month = "2",
day = "1",
doi = "10.2214/AJR.07.2642",
language = "English",
volume = "190",
pages = "459--465",
journal = "American Journal of Roentgenology",
issn = "0361-803X",
publisher = "American Roentgen Ray Society",
number = "2",

}

TY - JOUR

T1 - Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system

AU - Kakeda, Shingo

AU - Korogi, Yukunori

AU - Arimura, Hidetaka

AU - Hirai, Toshinori

AU - Katsuragawa, Shigehiko

AU - Aoki, Takatoshi

AU - Doi, Kunio

PY - 2008/2/1

Y1 - 2008/2/1

N2 - OBJECTIVE. The objective of our study was to determine whether the use of a computer-aided diagnosis (CAD) system can shorten the reading time while maintaining the diagnostic performance of MR angiography for the detection of intracranial aneurysms. MATERIALS AND METHODS. Fifty maximum-intensity- projection MR angiograms in 50 patients (16 intracranial aneurysms and 34 negative cases) were used for this observer performance study. Sixteen radiologists - eight neuroradiologists and eight less experienced radiologists - participated in the observer studies and interpreted the MR angiograms without and with CAD output images using an independent test method. The reading times without and with CAD were compared separately for the aneurysm and negative cases. The observers' performances were evaluated using receiver operating characteristic (ROC) analysis. We analyzed separately the data obtained from neuroradiologists and from less experienced radiologists. RESULTS. For all observers, the mean area under the ROC curve (Az) with CAD was improved compared with that without CAD (0.903 vs 0.851, respectively; p = 0.109), and the mean reading time per case was reduced significantly by 18.1 seconds (28.5%) (from 63.4 to 45.3 seconds, p < 0.05). When CAD output images were available, the mean Az for the less experienced radiologists was significantly improved (0.911 vs 0.787, p < 0.05), but not for the neuroradiologists. The mean reading time of the less experienced radiologists with CAD was significantly shorter than that of the neuroradiologists without CAD (39.8 vs 54.5 seconds, p < 0.05). CONCLUSION. The use of a CAD system for the detection of intracranial aneurysms on MR angiography can shorten the reading time while improving diagnostic performance for less experienced radiologists.

AB - OBJECTIVE. The objective of our study was to determine whether the use of a computer-aided diagnosis (CAD) system can shorten the reading time while maintaining the diagnostic performance of MR angiography for the detection of intracranial aneurysms. MATERIALS AND METHODS. Fifty maximum-intensity- projection MR angiograms in 50 patients (16 intracranial aneurysms and 34 negative cases) were used for this observer performance study. Sixteen radiologists - eight neuroradiologists and eight less experienced radiologists - participated in the observer studies and interpreted the MR angiograms without and with CAD output images using an independent test method. The reading times without and with CAD were compared separately for the aneurysm and negative cases. The observers' performances were evaluated using receiver operating characteristic (ROC) analysis. We analyzed separately the data obtained from neuroradiologists and from less experienced radiologists. RESULTS. For all observers, the mean area under the ROC curve (Az) with CAD was improved compared with that without CAD (0.903 vs 0.851, respectively; p = 0.109), and the mean reading time per case was reduced significantly by 18.1 seconds (28.5%) (from 63.4 to 45.3 seconds, p < 0.05). When CAD output images were available, the mean Az for the less experienced radiologists was significantly improved (0.911 vs 0.787, p < 0.05), but not for the neuroradiologists. The mean reading time of the less experienced radiologists with CAD was significantly shorter than that of the neuroradiologists without CAD (39.8 vs 54.5 seconds, p < 0.05). CONCLUSION. The use of a CAD system for the detection of intracranial aneurysms on MR angiography can shorten the reading time while improving diagnostic performance for less experienced radiologists.

UR - http://www.scopus.com/inward/record.url?scp=38849194784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38849194784&partnerID=8YFLogxK

U2 - 10.2214/AJR.07.2642

DO - 10.2214/AJR.07.2642

M3 - Article

VL - 190

SP - 459

EP - 465

JO - American Journal of Roentgenology

JF - American Journal of Roentgenology

SN - 0361-803X

IS - 2

ER -