Publications

BibTex format

@article{Davies:2022:10.1186/s12968-022-00846-4,
author = {Davies, RH and Augusto, JB and Bhuva, A and Xue, H and Treibel, TA and Ye, Y and Hughes, RK and Bai, W and Lau, C and Shiwani, H and Fontana, M and Kozor, R and Herrey, A and Lopes, LR and Maestrini, V and Rosmini, S and Petersen, SE and Kellman, P and Rueckert, D and Greenwood, JP and Captur, G and Manisty, C and Schelbert, E and Moon, JC},
doi = {10.1186/s12968-022-00846-4},
journal = {Journal of Cardiovascular Magnetic Resonance},
title = {Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning},
url = {http://dx.doi.org/10.1186/s12968-022-00846-4},
volume = {24},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundMeasurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis.MethodsA fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm (‘machine’) performance was compared to three clinicians (‘human’) and a commercial tool (cvi42, Circle Cardiovascular Imaging).FindingsMachine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint.ConclusionWe present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.
AU  - Davies,RH
AU  - Augusto,JB
AU  - Bhuva,A
AU  - Xue,H
AU  - Treibel,TA
AU  - Ye,Y
AU  - Hughes,RK
AU  - Bai,W
AU  - Lau,C
AU  - Shiwani,H
AU  - Fontana,M
AU  - Kozor,R
AU  - Herrey,A
AU  - Lopes,LR
AU  - Maestrini,V
AU  - Rosmini,S
AU  - Petersen,SE
AU  - Kellman,P
AU  - Rueckert,D
AU  - Greenwood,JP
AU  - Captur,G
AU  - Manisty,C
AU  - Schelbert,E
AU  - Moon,JC
DO  - 10.1186/s12968-022-00846-4
PY  - 2022///
SN  - 1097-6647
TI  - Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning
T2  - Journal of Cardiovascular Magnetic Resonance
UR  - http://dx.doi.org/10.1186/s12968-022-00846-4
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000767200300001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://jcmr-online.biomedcentral.com/articles/10.1186/s12968-022-00846-4#Sec16
UR  - http://hdl.handle.net/10044/1/97531
VL  - 24
ER  -

Download

ProfessorDanielRueckert

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)