Fully automated measurement of aortic pulse wave velocity from routine cardiac MRI studies.
Authors
Affiliations (9)
Affiliations (9)
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom; Royal Free Hospital, London NW3 2PF, United Kingdom. Electronic address: [email protected].
- Barts Heart Centre, St. Bartholomew's Hospital, London EC1A 7BE, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom. Electronic address: [email protected].
- Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom; Barts Heart Centre, St. Bartholomew's Hospital, London EC1A 7BE, United Kingdom. Electronic address: [email protected].
Abstract
Aortic pulse wave velocity (PWV) is a prognostic biomarker for cardiovascular disease, which can be measured by dividing the aortic path length by the pulse transit time. However, current MRI techniques require special sequences and time-consuming manual analysis. We aimed to fully automate the process using deep learning to measure PWV from standard sequences, facilitating PWV measurement in routine clinical and research scans. A deep learning (DL) model was developed to generate high-resolution 3D aortic segmentations from routine 2D trans-axial SSFP localizer images, and the centerlines of the resulting segmentations were used to estimate the aortic path length. A further DL model was built to automatically segment the ascending and descending aorta in phase contrast images, and pulse transit time was estimated from the sampled flow curves. Quantitative comparison with trained observers was performed for path length, aortic flow segmentation and transit time, either using an external clinical dataset with both localizers and paired 3D images acquired or on a sample of UK Biobank subjects. Potential application to clinical research scans was evaluated on 1053 subjects from the UK Biobank. Aortic path length measurement was accurate with no major difference between the proposed method (125 ± 19 mm) and manual measurement by a trained observer (124 ± 19 mm) (P = 0.88). Automated phase contrast image segmentation was similar to that of a trained observer for both the ascending (Dice vs manual: 0.96) and descending (Dice 0.89) aorta with no major difference in transit time estimation (proposed method = 21 ± 9 ms, manual = 22 ± 9 ms; P = 0.15). 966 of 1053 (92 %) UK Biobank subjects were successfully analyzed, with a median PWV of 6.8 m/s, increasing 27 % per decade of age and 6.5 % higher per 10 mmHg higher systolic blood pressure. We describe a fully automated method for measuring PWV from standard cardiac MRI localizers and a single phase contrast imaging plane. The method is robust and can be applied to routine clinical scans, and could unlock the potential of measuring PWV in large-scale clinical and population studies. All models and deployment codes are available online.