Imperial College London
Portrait Picture

DrPaulBentley

Faculty of Medicine, Department of Brain Sciences

Senior Clinical Research Fellow
 
 
 
//

Contact

 

p.bentley

 
 
//

Location

 

10L21Charing Cross HospitalCharing Cross Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Chen:2018:10.1148/radiol.2018171567,
author = {Chen, L and Carlton, Jones AL and Mair, G and Patel, R and Gontsarova, A and Ganesalingam, J and Math, N and Dawson, A and Basaam, A and Cohen, D and Mehta, A and Wardlaw, J and Rueckert, D and Bentley, P},
doi = {10.1148/radiol.2018171567},
journal = {Radiology},
pages = {573--581},
title = {Rapid automated quantification of cerebral leukoaraiosis on CT: a multicentre validation study},
url = {http://dx.doi.org/10.1148/radiol.2018171567},
volume = {288},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Purpose - To validate a fully-automated, machine-learning method (random forest) for segmenting cerebral white matter lesions (WML) on computerized tomography (CT). Materials and Methods – A retrospective sample of 1082 acute ischemic stroke cases was obtained, comprising unselected patients: 1) treated with thrombolysis; or 2) undergoing contemporaneous MR imaging and CT; and 3) a subset of IST-3 trial participants. Automated (‘Auto’) WML images were validated relative to experts’ manual tracings on CT, and co-registered FLAIR-MRI; and ratings using two conventional ordinal scales. Analyses included correlations between CT and MR imaging volumes, and agreements between Auto and expert ratings.Results - Auto WML volumes correlated strongly with expert-delineated WML volumes on MR imaging and on CT (r2=0.85, 0.71 respectively; p<0.001). Spatial-similarity of Auto-maps, relative to MRI-WML, was not significantly different to that of expert CT-WML tracings. Individual expert CT-WML volumes correlated well with each other (r2=0.85), but varied widely (range: 91% of mean estimate; median 11 cc; range: 0.2 – 68 cc). Agreements between Auto and consensus-expert ratings were superior or similar to agreements between individual pairs of experts (kappa: 0.60, 0.64 vs. 0.51, 0.67 for two score systems; p<0.01 for first comparison). Accuracy was unaffected by established infarction, acute ischemic changes, or atrophy (p>0.05). Auto preprocessing failure rate was 4%; rating errors occurred in a further 4%. Total Auto processing time averaged 109s (range: 79 -  140 s).  Conclusion - An automated method for quantifying CT cerebral white matter lesions achieves a similar accuracy to experts in unselected and multicenter cohorts.
AU  - Chen,L
AU  - Carlton,Jones AL
AU  - Mair,G
AU  - Patel,R
AU  - Gontsarova,A
AU  - Ganesalingam,J
AU  - Math,N
AU  - Dawson,A
AU  - Basaam,A
AU  - Cohen,D
AU  - Mehta,A
AU  - Wardlaw,J
AU  - Rueckert,D
AU  - Bentley,P
DO  - 10.1148/radiol.2018171567
EP  - 581
PY  - 2018///
SN  - 0033-8419
SP  - 573
TI  - Rapid automated quantification of cerebral leukoaraiosis on CT: a multicentre validation study
T2  - Radiology
UR  - http://dx.doi.org/10.1148/radiol.2018171567
UR  - http://hdl.handle.net/10044/1/57261
VL  - 288
ER  -
Download