Tools
Tools
Sharkey, Michael J., Taylor, Jonathan C., Alabed, Samer, Dwivedi, Krit, Karunasaagarar, Kavitasagary, Johns, Christopher S., Rajaram, Smitha, Garg, Pankaj 
ORCID: https://orcid.org/0000-0002-5483-169X, Alkhanfar, Dheyaa, Metherall, Peter, O'Regan, Declan P., van der Geest, Rob J., Condliffe, Robin, Kiely, David G., Mamalakis, Michail and Swift, Andrew J.
(2022)
Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning.
Frontiers in Cardiovascular Medicine, 9.
ISSN 2297-055X
Preview |
PDF (fcvm-09-983859)
- Published Version
Available under License Creative Commons Attribution. Download (4MB) | Preview |
Abstract
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 performance in the external test cohort. The failure rates in mixed pulmonary vascular disease were low (<3.9%) indicating good generalisability of the model to different diseases. Conclusion: Fully automated segmentation of the four cardiac chambers and great vessels has been achieved in CTPA with high accuracy and low rates of failure. DL volumetric biomarkers can potentially improve CTPA cardiac assessment and invasive haemodynamic prediction.
| Item Type: | Article |
|---|---|
| Additional Information: | Funding Information: This work was supported by an NIHR AI Award, AI_AWARD01706. AS was supported by a Wellcome Trust Fellowship Grant 205188/Z/16/Z which provides the open access publication fees for this manuscript. DO'R was supported by the Medical Research Council (MC-A658-5QEB0) and British Heart Foundation Grants (RG/19/6/34387 and RE/18/4/34215). |
| Uncontrolled Keywords: | computed tomography pulmonary angiography (ctpa),deep-learning (dl),pulmonary vascular disease (pvd),semantic segmentation and labelling,whole heart segmentation,cardiology and cardiovascular medicine ,/dk/atira/pure/subjectarea/asjc/2700/2705 |
| Faculty \ School: | Faculty of Medicine and Health Sciences > Norwich Medical School |
| UEA Research Groups: | Faculty of Medicine and Health Sciences > Research Centres > Metabolic Health |
| Related URLs: | |
| Depositing User: | LivePure Connector |
| Date Deposited: | 21 Oct 2022 08:33 |
| Last Modified: | 19 Oct 2023 03:27 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/89256 |
| DOI: | 10.3389/fcvm.2022.983859 |
Downloads
Downloads per month over past year
Actions (login required)
 |
View Item |