Fully automated segmentation of the left ventricle in cine cardiac magnetic resonance imaging / Tan Li Kuo

Tan, Li Kuo (2018) Fully automated segmentation of the left ventricle in cine cardiac magnetic resonance imaging / Tan Li Kuo. PhD thesis, University of Malaya.

	PDF (The Candidate's Agreement) Restricted to Repository staff only Download (1700Kb)
Preview	PDF (Thesis PhD) Download (3365Kb) | Preview

Abstract

Cardiovascular diseases (CVD) are the primary cause of death globally, accounting for approximately 31% of all deaths worldwide. Cardiac magnetic resonance imaging (MRI) is the reference standard for the medical assessment of cardiac volumes and regional functions due to its accuracy and reproducibility. Most standard cardiac MRI protocols begin with assessing the left ventricle (LV) structure and functions due to the LVs’ role in supplying most of the body with oxygenated blood. In standard clinical practice, quantification of LV function is performed via manual delineation of the LV myocardium within the MR images, for the end-diastole (ED) and end-systole (ES) cardiac phases. This enables the evaluation of standard diagnostic clinical measurements such as LV ED and ES blood volumes, ejection fraction, and LV mass. Despite delineating only two cardiac phases, such manual tracing can take up to 20 minutes by a radiologist. Full delineation across all cardiac phases would enable useful quantification of motion parameters to identify regional LV dysfunction. However, the excessive effort required for manual full delineation makes it impractical for clinical adoption. In this thesis, two fully automatic algorithms for cardiac MRI were presented: the first for localization of the LV blood pool – a sub-problem for enabling subsequent automatic segmentation; and the second for segmentation of the LV with full coverage from base to apex across all cardiac phases. The novel use of neural network regression for image segmentation was introduced, whereby multiple independent networks were designed and trained for the inference of LV landmarks, LV centrepoints, and myocardial contours, respectively. A large range of data sources was utilized for training and validation, including both in-house and publicly available databases, representing a heterogeneous mix of scanner types, imaging protocols, and parameters. Tested against the public 2011 Left Ventricle Segmentation Challenge (LVSC) database, a final Jaccard index result of 0.77 ± 0.11 was obtained for segmentation accuracy. This represents the best published LVSC performance to date for a fully automated algorithm. Tested against the public 2016 Kaggle Second Annual Data Science Bowl challenge, a final result of +7.2 ± 13.0 mL and −19.8 ± 18.8 mL was obtained for clinical blood volume measurement accuracy in the ES and ED phases, respectively. This performance is comparable to published inter-reader variability values for multiple independent expert readers. The execution speed is approximately 12 s per case. In conclusion, two algorithms were developed and tested leading to fully automatic segmentation of LV in cardiac cine MRI. These were validated against a diverse set of publicly available and in-house cardiac cine MRI data. The strong performance overall is suggestive of practical clinical utility.

Actions (For repository staff only : Login required)