Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting

I. L. Štepán-Buksakowska, J. M. Accurso, F. E. Diehn, John III Huston, Timothy J Kaufmann, Patrick H Luetmer, C. P. Wood, X. Yang, D. J. Blezek, Rickey E. Carter, C. Hagen, D. Hořínek, A. Hejčl, M. Rǒcek, Bradley J Erickson

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

BACKGROUND AND PURPOSE: MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.

MATERIALS AND METHODS: Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean=3.12 mm, median=2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.

RESULTS: For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F1,47 = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.

CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.

Original languageEnglish (US)
Pages (from-to)1897-1902
Number of pages6
JournalAmerican Journal of Neuroradiology
Volume35
Issue number10
DOIs
StatePublished - Oct 1 2014

Fingerprint

Intracranial Aneurysm
Aneurysm
Cross-Over Studies
Radiologists

ASJC Scopus subject areas

  • Clinical Neurology
  • Radiology Nuclear Medicine and imaging

Cite this

Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting. / Štepán-Buksakowska, I. L.; Accurso, J. M.; Diehn, F. E.; Huston, John III; Kaufmann, Timothy J; Luetmer, Patrick H; Wood, C. P.; Yang, X.; Blezek, D. J.; Carter, Rickey E.; Hagen, C.; Hořínek, D.; Hejčl, A.; Rǒcek, M.; Erickson, Bradley J.

In: American Journal of Neuroradiology, Vol. 35, No. 10, 01.10.2014, p. 1897-1902.

Research output: Contribution to journalArticle

Štepán-Buksakowska, IL, Accurso, JM, Diehn, FE, Huston, JIII, Kaufmann, TJ, Luetmer, PH, Wood, CP, Yang, X, Blezek, DJ, Carter, RE, Hagen, C, Hořínek, D, Hejčl, A, Rǒcek, M & Erickson, BJ 2014, 'Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting', American Journal of Neuroradiology, vol. 35, no. 10, pp. 1897-1902. https://doi.org/10.3174/ajnr.A3996
Štepán-Buksakowska, I. L. ; Accurso, J. M. ; Diehn, F. E. ; Huston, John III ; Kaufmann, Timothy J ; Luetmer, Patrick H ; Wood, C. P. ; Yang, X. ; Blezek, D. J. ; Carter, Rickey E. ; Hagen, C. ; Hořínek, D. ; Hejčl, A. ; Rǒcek, M. ; Erickson, Bradley J. / Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting. In: American Journal of Neuroradiology. 2014 ; Vol. 35, No. 10. pp. 1897-1902.
@article{215a19402f0f4ad4a9c10ea2ce4e9e95,
title = "Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting",
abstract = "BACKGROUND AND PURPOSE: MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.MATERIALS AND METHODS: Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean=3.12 mm, median=2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.RESULTS: For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95{\%} CI, 0.03-0.18), which was statistically significant (F1,47 = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.",
author = "Štep{\'a}n-Buksakowska, {I. L.} and Accurso, {J. M.} and Diehn, {F. E.} and Huston, {John III} and Kaufmann, {Timothy J} and Luetmer, {Patrick H} and Wood, {C. P.} and X. Yang and Blezek, {D. J.} and Carter, {Rickey E.} and C. Hagen and D. Hoř{\'i}nek and A. Hejčl and M. Rǒcek and Erickson, {Bradley J}",
year = "2014",
month = "10",
day = "1",
doi = "10.3174/ajnr.A3996",
language = "English (US)",
volume = "35",
pages = "1897--1902",
journal = "American Journal of Neuroradiology",
issn = "0195-6108",
publisher = "American Society of Neuroradiology",
number = "10",

}

TY - JOUR

T1 - Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting

AU - Štepán-Buksakowska, I. L.

AU - Accurso, J. M.

AU - Diehn, F. E.

AU - Huston, John III

AU - Kaufmann, Timothy J

AU - Luetmer, Patrick H

AU - Wood, C. P.

AU - Yang, X.

AU - Blezek, D. J.

AU - Carter, Rickey E.

AU - Hagen, C.

AU - Hořínek, D.

AU - Hejčl, A.

AU - Rǒcek, M.

AU - Erickson, Bradley J

PY - 2014/10/1

Y1 - 2014/10/1

N2 - BACKGROUND AND PURPOSE: MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.MATERIALS AND METHODS: Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean=3.12 mm, median=2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.RESULTS: For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F1,47 = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.

AB - BACKGROUND AND PURPOSE: MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.MATERIALS AND METHODS: Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean=3.12 mm, median=2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.RESULTS: For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F1,47 = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.

UR - http://www.scopus.com/inward/record.url?scp=84907741946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907741946&partnerID=8YFLogxK

U2 - 10.3174/ajnr.A3996

DO - 10.3174/ajnr.A3996

M3 - Article

C2 - 24924543

AN - SCOPUS:84907741946

VL - 35

SP - 1897

EP - 1902

JO - American Journal of Neuroradiology

JF - American Journal of Neuroradiology

SN - 0195-6108

IS - 10

ER -