Computer-aided detection of intracranial aneurysms in MR angiography

Xiaojiang Yang, Daniel J. Blezek, Lionel T E Cheng, William J. Ryan, David F Kallmes, Bradley J Erickson

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Intracranial aneurysms represent a significant cause of morbidity and mortality. While the risk factors for aneurysm formation are known, the detection of aneurysms remains challenging. Magnetic resonance angiography (MRA) has recently emerged as a useful non-invasive method for aneurysm detection. However, even for experienced neuroradiologists, the sensitivity to small (<5 mm) aneurysms in MRA images is poor, on the order of 30~60% in recent, large series. We describe a fully automated computer-aided detection (CAD) scheme for detecting aneurysms on 3D time-of-flight (TOF) MRA images. The scheme locates points of interest (POIs) on individual MRA datasets by combining two complementary techniques. The first technique segments the intracranial arteries automatically and finds POIs from the segmented vessels. The second technique identifies POIs directly from the raw, unsegmented image dataset. This latter technique is useful in cases of incomplete segmentation. Following a series of feature calculations, a small fraction of POIs are retained as candidate aneurysms from the collected POIs according to predetermined rules. The CAD scheme was evaluated on 287 datasets containing 147 aneurysms that were verified with digital subtraction angiography, the accepted standard of reference for aneurysm detection. For two different operating points, the CAD scheme achieved a sensitivity of 80% (71% for aneurysms less than 5 mm) with three mean false positives per case, and 95% (91% for aneurysms less than 5 mm) with nine mean false positives per case. In conclusion, the CAD scheme showed good accuracy and may have application in improving the sensitivity of aneurysm detection on MR images.

Original languageEnglish (US)
Pages (from-to)86-95
Number of pages10
JournalJournal of Digital Imaging
Volume24
Issue number1
DOIs
StatePublished - Feb 2011

Fingerprint

Angiography
Intracranial Aneurysm
Aneurysm
Magnetic resonance
Magnetic Resonance Angiography
Digital Subtraction Angiography
Arteries
Morbidity

Keywords

  • aneurysm detection
  • Computer-aided detection (CAD)
  • intracranial aneurysm
  • magnetic resonance angiography (MRA)

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Medicine(all)

Cite this

Computer-aided detection of intracranial aneurysms in MR angiography. / Yang, Xiaojiang; Blezek, Daniel J.; Cheng, Lionel T E; Ryan, William J.; Kallmes, David F; Erickson, Bradley J.

In: Journal of Digital Imaging, Vol. 24, No. 1, 02.2011, p. 86-95.

Research output: Contribution to journalArticle

Yang, Xiaojiang ; Blezek, Daniel J. ; Cheng, Lionel T E ; Ryan, William J. ; Kallmes, David F ; Erickson, Bradley J. / Computer-aided detection of intracranial aneurysms in MR angiography. In: Journal of Digital Imaging. 2011 ; Vol. 24, No. 1. pp. 86-95.
@article{b4a9e1d490f5423099f1ed2e3637a318,
title = "Computer-aided detection of intracranial aneurysms in MR angiography",
abstract = "Intracranial aneurysms represent a significant cause of morbidity and mortality. While the risk factors for aneurysm formation are known, the detection of aneurysms remains challenging. Magnetic resonance angiography (MRA) has recently emerged as a useful non-invasive method for aneurysm detection. However, even for experienced neuroradiologists, the sensitivity to small (<5 mm) aneurysms in MRA images is poor, on the order of 30~60{\%} in recent, large series. We describe a fully automated computer-aided detection (CAD) scheme for detecting aneurysms on 3D time-of-flight (TOF) MRA images. The scheme locates points of interest (POIs) on individual MRA datasets by combining two complementary techniques. The first technique segments the intracranial arteries automatically and finds POIs from the segmented vessels. The second technique identifies POIs directly from the raw, unsegmented image dataset. This latter technique is useful in cases of incomplete segmentation. Following a series of feature calculations, a small fraction of POIs are retained as candidate aneurysms from the collected POIs according to predetermined rules. The CAD scheme was evaluated on 287 datasets containing 147 aneurysms that were verified with digital subtraction angiography, the accepted standard of reference for aneurysm detection. For two different operating points, the CAD scheme achieved a sensitivity of 80{\%} (71{\%} for aneurysms less than 5 mm) with three mean false positives per case, and 95{\%} (91{\%} for aneurysms less than 5 mm) with nine mean false positives per case. In conclusion, the CAD scheme showed good accuracy and may have application in improving the sensitivity of aneurysm detection on MR images.",
keywords = "aneurysm detection, Computer-aided detection (CAD), intracranial aneurysm, magnetic resonance angiography (MRA)",
author = "Xiaojiang Yang and Blezek, {Daniel J.} and Cheng, {Lionel T E} and Ryan, {William J.} and Kallmes, {David F} and Erickson, {Bradley J}",
year = "2011",
month = "2",
doi = "10.1007/s10278-009-9254-0",
language = "English (US)",
volume = "24",
pages = "86--95",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - Computer-aided detection of intracranial aneurysms in MR angiography

AU - Yang, Xiaojiang

AU - Blezek, Daniel J.

AU - Cheng, Lionel T E

AU - Ryan, William J.

AU - Kallmes, David F

AU - Erickson, Bradley J

PY - 2011/2

Y1 - 2011/2

N2 - Intracranial aneurysms represent a significant cause of morbidity and mortality. While the risk factors for aneurysm formation are known, the detection of aneurysms remains challenging. Magnetic resonance angiography (MRA) has recently emerged as a useful non-invasive method for aneurysm detection. However, even for experienced neuroradiologists, the sensitivity to small (<5 mm) aneurysms in MRA images is poor, on the order of 30~60% in recent, large series. We describe a fully automated computer-aided detection (CAD) scheme for detecting aneurysms on 3D time-of-flight (TOF) MRA images. The scheme locates points of interest (POIs) on individual MRA datasets by combining two complementary techniques. The first technique segments the intracranial arteries automatically and finds POIs from the segmented vessels. The second technique identifies POIs directly from the raw, unsegmented image dataset. This latter technique is useful in cases of incomplete segmentation. Following a series of feature calculations, a small fraction of POIs are retained as candidate aneurysms from the collected POIs according to predetermined rules. The CAD scheme was evaluated on 287 datasets containing 147 aneurysms that were verified with digital subtraction angiography, the accepted standard of reference for aneurysm detection. For two different operating points, the CAD scheme achieved a sensitivity of 80% (71% for aneurysms less than 5 mm) with three mean false positives per case, and 95% (91% for aneurysms less than 5 mm) with nine mean false positives per case. In conclusion, the CAD scheme showed good accuracy and may have application in improving the sensitivity of aneurysm detection on MR images.

AB - Intracranial aneurysms represent a significant cause of morbidity and mortality. While the risk factors for aneurysm formation are known, the detection of aneurysms remains challenging. Magnetic resonance angiography (MRA) has recently emerged as a useful non-invasive method for aneurysm detection. However, even for experienced neuroradiologists, the sensitivity to small (<5 mm) aneurysms in MRA images is poor, on the order of 30~60% in recent, large series. We describe a fully automated computer-aided detection (CAD) scheme for detecting aneurysms on 3D time-of-flight (TOF) MRA images. The scheme locates points of interest (POIs) on individual MRA datasets by combining two complementary techniques. The first technique segments the intracranial arteries automatically and finds POIs from the segmented vessels. The second technique identifies POIs directly from the raw, unsegmented image dataset. This latter technique is useful in cases of incomplete segmentation. Following a series of feature calculations, a small fraction of POIs are retained as candidate aneurysms from the collected POIs according to predetermined rules. The CAD scheme was evaluated on 287 datasets containing 147 aneurysms that were verified with digital subtraction angiography, the accepted standard of reference for aneurysm detection. For two different operating points, the CAD scheme achieved a sensitivity of 80% (71% for aneurysms less than 5 mm) with three mean false positives per case, and 95% (91% for aneurysms less than 5 mm) with nine mean false positives per case. In conclusion, the CAD scheme showed good accuracy and may have application in improving the sensitivity of aneurysm detection on MR images.

KW - aneurysm detection

KW - Computer-aided detection (CAD)

KW - intracranial aneurysm

KW - magnetic resonance angiography (MRA)

UR - http://www.scopus.com/inward/record.url?scp=79751524098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79751524098&partnerID=8YFLogxK

U2 - 10.1007/s10278-009-9254-0

DO - 10.1007/s10278-009-9254-0

M3 - Article

C2 - 19937083

AN - SCOPUS:79751524098

VL - 24

SP - 86

EP - 95

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

IS - 1

ER -