Rapid Automated Quantification of Cerebral Leukoaraiosis on CT Images: A Multicenter Validation Study

被引：19

作者：

Chen, Liang ^{[1
,2
]}

Jones, Anoma Lalani Carlton ^{[2
]}

Mair, Grant ^{[3
]}

Patel, Rajiv ^{[4
]}

Gontsarova, Anastasia ^{[2
]}

Ganesalingam, Jeban ^{[2
]}

Math, Nikhil ^{[2
]}

Dawson, Angela ^{[2
]}

Aweid, Basaam ^{[2
]}

Cohen, David ^{[4
]}

Mehta, Amrish ^{[2
]}

Wardlaw, Joanna ^{[3
]}

Rueckert, Daniel ^{[1
]}

Bentley, Paul ^{[2
]}

机构：

[1] Imperial Coll London, Charing Cross Hosp, Biomed Imaging Anal Grp, Comp Sci, Fulham Palace Rd,10L21, London W6 8RF, England

[2] Imperial Coll London, Charing Cross Hosp, Div Brain Sci, Fulham Palace Rd,10L21, London W6 8RF, England

[3] Univ Edinburgh, Ctr Clin Brain Sci, Edinburgh, Midlothian, Scotland

[4] London North West Healthcare NHS Trust, Northwick Pk Hosp, Dept Radiol, London, England

来源：

RADIOLOGY | 2018年 / 288卷 / 02期

基金：

美国国家卫生研究院;

关键词：

ACUTE ISCHEMIC-STROKE; WHITE-MATTER CHANGES; TISSUE-PLASMINOGEN ACTIVATOR; RANDOMIZED CONTROLLED-TRIAL; TRAUMATIC BRAIN-INJURY; VISUAL RATING-SCALES; INTRAVENOUS THROMBOLYSIS; MR-IMAGES; HEMORRHAGE; SEGMENTATION;

D O I：

10.1148/radiol.2018171567

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Purpose: To validate a random forest method for segmenting cerebral white matter lesions (WMLs) on computed tomographic (CT) images in a multicenter cohort of patients with acute ischemic stroke, by comparison with fluid-attenuated recovery (FLAIR) magnetic resonance (MR) images and expert consensus. Materials and Methods: A retrospective sample of 1082 acute ischemic stroke cases was obtained that was composed of unselected patients who were treated with thrombolysis or who were undergoing contemporaneous MR imaging and CT, and a subset of International Stroke Thrombolysis-3 trial participants. Automated delineations of WML on images were validated relative to experts' manual tracings on CT images, and co-registered FLAIR MR imaging, and ratings were performed by using two conventional ordinal scales. Analyses included correlations between CT and MR imaging volumes, and agreements between automated and expert ratings. Results: Automated WML volumes correlated strongly with expert-delineated WML volumes at MR imaging and CT (r(2) = 0.85 and 0.71 respectively; P<.001). Spatial-similarity of automated maps, relative to WML MR imaging, was not significantly different to that of expert WML tracings on CT images. Individual expert WML volumes at CT correlated well with each other (r(2) = 0.85), but varied widely (range, 91% of mean estimate; median estimate, 11 mL; range of estimated ranges, 0.2-68 mL). Agreements (kappa) between automated ratings and consensus ratings were 0.60 (Wahlund system) and 0.64 (van Swieten system) compared with agreements between individual pairs of experts of 0.51 and 0.67, respectively, for the two rating systems (P < .01 for Wahlund system comparison of agreements). Accuracy was unaffected by established infarction, acute ischemic changes, or atrophy (P>.05). Automated preprocessing failure rate was 4%; rating errors occurred in a further 4%. Total automated processing time averaged 109 seconds (range, 79-140 seconds). Conclusion: An automated method for quantifying CT cerebral white matter lesions achieves a similar accuracy to experts in unselected and multicenter cohorts. (c) RSNA, 2018

引用

页码：573 / 581

页数：9

共 33 条

[1] Neuroimaging in dementia: how best to use the guidelines? [J].