Skip to main content

A deep learning pipeline for automatic analysis of multi-scan cardiovascular magnetic resonance.

Fadil, H., Totman, J. J., Hausenloy, D., Ho, H-H., Joseph, P., Low, A.F-H., Richards, A.M., Chan, M.Y. and Marchesseau, S., 2021. A deep learning pipeline for automatic analysis of multi-scan cardiovascular magnetic resonance. Journal of Cardiovascular Magnetic Resonance, 23 (1), 47.

Full text available as:

A deep learning pipeline for automatic analysis of multi-scan cardiovascular magnetic resonance.pdf - Published Version
Available under License Creative Commons Attribution.


DOI: 10.1186/s12968-020-00695-z


BACKGROUND: Cardiovascular magnetic resonance (CMR) sequences are commonly used to obtain a complete description of the function and structure of the heart, provided that accurate measurements are extracted from images. New methods of extraction of information are being developed, among them, deep neural networks are powerful tools that showed the ability to perform fast and accurate segmentation. Iq1n order to reduce the time spent by reading physicians to process data and minimize intra- and inter-observer variability, we propose a fully automatic multi-scan CMR image analysis pipeline. METHODS: Sequence specific U-Net 2D models were trained to perform the segmentation of the left ventricle (LV), right ventricle (RV) and aorta in cine short-axis, late gadolinium enhancement (LGE), native T1 map, post-contrast T1, native T2 map and aortic flow sequences depending on the need. The models were trained and tested on a set of data manually segmented by experts using semi-automatic and manual tools. A set of parameters were computed from the resulting segmentations such as the left ventricular and right ventricular ejection fraction (EF), LGE scar percentage, the mean T1, T1 post, T2 values within the myocardium, and aortic flow. The Dice similarity coefficient, Hausdorff distance, mean surface distance, and Pearson correlation coefficient R were used to assess and compare the results of the U-Net based pipeline with intra-observer variability. Additionally, the pipeline was validated on two clinical studies. RESULTS: The sequence specific U-Net 2D models trained achieved fast (≤ 0.2 s/image on GPU) and precise segmentation over all the targeted region of interest with high Dice scores (= 0.91 for LV, = 0.92 for RV, = 0.93 for Aorta in average) comparable to intra-observer Dice scores (= 0.86 for LV, = 0.87 for RV, = 0.95 for aorta flow in average). The automatically and manually computed parameters were highly correlated (R = 0.91 in average) showing results superior to the intra-observer variability (R = 0.85 in average) for every sequence presented here. CONCLUSION: The proposed pipeline allows for fast and robust analysis of large CMR studies while guaranteeing reproducibility, hence potentially improving patient's diagnosis as well as clinical studies outcome.

Item Type:Article
Additional Information:Funding HF is funded by the National Medical Research Council NUHS Centre Grant Medical Image Analysis Core. NMRC/CG/013/2013). SM is partially funded by the NMRC Open-Fund Young Investigator Research Grant NMRC/OFYIRG/0059/2017. MYC is supported by a Clinician-Scientist award from the NMRC, Singapore (NMRC/CSA/028/2011) and AMR is supported by a Singapore Translational Research Investigator award (NMRC/STaR/0022/2014). DJH was supported by the British Heart Foundation (CS/14/3/31002), the National Institute for Health Research University College London Hospitals Biomedical Research Centre, Duke-National University Singapore Medical School, Singapore Ministry of Health’s National Medical Research Council under its Clinician Scientist-Senior Investigator scheme (NMRC/CSA-SI/0011/2017) and Collaborative Centre Grant scheme (NMRC/CGAug16C006), and the Singapore Ministry of Education Academic Research Fund Tier 2 (MOE2016-T2-2-021). This article is based upon work from COST Action EU-CARDIOPROTECTION CA16225 supported by COST (European Cooperation in Science and Technology).
Uncontrolled Keywords:Aortic flow ; Automatic analysis ; Cine short-axis ; Deep learning ; Segmentation ; T1 mapping ; T2 mapping ; Automation ; Case-Control Studies ; Deep Learning ; Heart Diseases ; Humans ; Image Interpretation, Computer-Assisted ; Magnetic Resonance Imaging, Cine ; Myocardium ; Observer Variation ; Predictive Value of Tests ; Reproducibility of Results ; Stroke Volume ; Ventricular Function, Left ; Ventricular Function, Right
Group:Faculty of Health & Social Sciences
ID Code:36362
Deposited By: Symplectic RT2
Deposited On:13 Dec 2021 08:51
Last Modified:14 Mar 2022 14:31


Downloads per month over past year

More statistics for this item...
Repository Staff Only -