Publications

BibTex format

@article{Sharkey:2022:10.3389/fcvm.2022.983859,
author = {Sharkey, MJ and Taylor, JC and Alabed, S and Dwivedi, K and Karunasaagarar, K and Johns, CS and Rajaram, S and Garg, P and Alkhanfar, D and Metherall, P and O'Regan, DP and van, der Geest RJ and Condliffe, R and Kiely, DG and Mamalakis, M and Swift, AJ},
doi = {10.3389/fcvm.2022.983859},
journal = {Frontiers in Cardiovascular Medicine},
pages = {1--18},
title = {Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning},
url = {http://dx.doi.org/10.3389/fcvm.2022.983859},
volume = {9},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Introduction: Computed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected pulmonary vascular disease including pulmonary hypertension and pulmonary embolism. Cardiac and great vessel assessments on CTPA are based on visual assessment and manual measurements which are known to have poor reproducibility. The primary aim of this study was to develop an automated whole heart segmentation (four chamber and great vessels) model for CTPA.Methods: A nine structure semantic segmentation model of the heart and great vessels was developed using 200 patients (80/20/100 training/validation/internal testing) with testing in 20 external patients. Ground truth segmentations were performed by consultant cardiothoracic radiologists. Failure analysis was conducted in 1,333 patients with mixed pulmonary vascular disease. Segmentation was achieved using deep learning via a convolutional neural network. Volumetric imaging biomarkers were correlated with invasive haemodynamics in the test cohort.Results: Dice similarity coefficients (DSC) for segmented structures were in the range 0.58–0.93 for both the internal and external test cohorts. The left and right ventricle myocardium segmentations had lower DSC of 0.83 and 0.58 respectively while all other structures had DSC >0.89 in the internal test cohort and >0.87 in the external test cohort. Interobserver comparison found that the left and right ventricle myocardium segmentations showed the most variation between observers: mean DSC (range) of 0.795 (0.785–0.801) and 0.520 (0.482–0.542) respectively. Right ventricle myocardial volume had strong correlation with mean pulmonary artery pressure (Spearman's correlation coefficient = 0.7). The volume of segmented cardiac structures by deep learning had higher or equivalent correlation with invasive haemodynamics than by manual segmentations. The model demonstrated good generalisability to different vendors and hospitals with similar
AU  - Sharkey,MJ
AU  - Taylor,JC
AU  - Alabed,S
AU  - Dwivedi,K
AU  - Karunasaagarar,K
AU  - Johns,CS
AU  - Rajaram,S
AU  - Garg,P
AU  - Alkhanfar,D
AU  - Metherall,P
AU  - O'Regan,DP
AU  - van,der Geest RJ
AU  - Condliffe,R
AU  - Kiely,DG
AU  - Mamalakis,M
AU  - Swift,AJ
DO  - 10.3389/fcvm.2022.983859
EP  - 18
PY  - 2022///
SN  - 2297-055X
SP  - 1
TI  - Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning
T2  - Frontiers in Cardiovascular Medicine
UR  - http://dx.doi.org/10.3389/fcvm.2022.983859
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000874203500001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
UR  - https://www.frontiersin.org/articles/10.3389/fcvm.2022.983859/full
UR  - http://hdl.handle.net/10044/1/101026
VL  - 9
ER  -

Download

ProfessorDeclanO'Regan

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)