Hyperparameter optimisation and validation of registration algorithms for measuring regional ventricular deformation using retrospective gated computed tomography images

Abstract

Recent dose reduction techniques have made retrospective computed tomography (CT) scans more applicable and extracting myocardial function from cardiac computed tomography (CCT) images feasible. However, hyperparameters of generic image intensity-based registration techniques, which are used for tracking motion, have not been systematically optimised for this modality. There is limited work on their validation for measuring regional strains from retrospective gated CCT images and open-source software for motion analysis is not widely available. We calculated strain using our open-source platform by applying an image registration warping field to a triangulated mesh of the left ventricular endocardium. We optimised hyperparameters of two registration methods to track the wall motion. Both methods required a single semi-automated segmentation of the left ventricle cavity at end-diastolic phase. The motion was characterised by the circumferential and longitudinal strains, as well as local area change throughout the cardiac cycle from a dataset of 24 patients. The derived motion was validated against manually annotated anatomical landmarks and the calculation of strains were verified using idealised problems. Optimising hyperparameters of registration methods allowed tracking of anatomical measurements with a mean error of 6.63% across frames, landmarks, and patients, comparable to an intra-observer error of 7.98%. Both registration methods differentiated between normal and dyssynchronous contraction patterns based on circumferential strain ($$p_1=0.0065$$ p 1 = 0.0065 , $$p_2=0.0011$$ p 2 = 0.0011 ). To test whether a typical 10 temporal frames sampling of retrospective gated CCT datasets affects measuring cardiac mechanics, we compared motion tracking results from 10 and 20 frames datasets and found a maximum error of $$8.51\pm 0.8\%$$ 8.51 ± 0.8 % . Our findings show that intensity-based registration techniques with optimal hyperparameters are able to accurately measure regional strains from CCT in a very short amount of time. Furthermore, sufficient sensitivity can be achieved to identify heart failure patients and left ventricle mechanics can be quantified with 10 reconstructed temporal frames. Our open-source platform will support increased use of CCT for quantifying cardiac mechanics.

Are There Differences and Complementarities between Senior and Young Entrepreneurs? An Intergenerational Perspective

“…This result means that a reasonable margin of error [104][105][106][107] is borne in mind for the results presented below.…”

Deep learning automates detection of wall motion abnormalities via measurement of longitudinal strain from ECG-gated CT images

“…Solving for endocardial displacement is computationally intensive and delineating the endocardial surface throughout the chamber can be time-intensive. However, recent work aims to avoid these limitations ( 39 ). Therefore, our streamlined, automated approach could serve as an initial check to determine whether more extensive assessment is needed.…”

A three-dimensional left atrial motion estimation from retrospective gated computed tomography: application in heart failure patients with atrial fibrillation

“…The TSFFD method was utilised in this study as it is based on the widely used free form deformation method ( 31 ) with additional control point (CP) sparsity and temporal cyclicity constraints that make it appropriate for the estimation of physiologically realistic cardiac motion. Furthermore, TSFFD has previously been validated for LV feature tracking in RGCT images using expert-chosen landmarks ( 18 ) that served as a baseline configuration prior to the LA chamber–specific optimisation.…”

“…Regional LV myocardial shortening has been measured using non-rigid surface registration between LV endocardial surfaces from end-diastole (ED) to end-systole (ES) and applied to strain measurement ( 15 ) and mechanical activation time estimation ( 16 ). LV systolic strain synchrony, measured using the temporal sparse free form deformation (TSFFD) non-rigid image registration method ( 17 ), found more dyssynchronous LV mechanics in patients with heart failure (HF) than in control subjects ( 18 ).…”

“…In this study, we present the results of the estimated 3D LA motion and calculated the strain using the TSFFD method to track LA features in RGCT images in a cohort of patients with heart failure with reduced ejection fraction (HFrEF). The TSFFD image registration method was chosen since it enables strain calculation using only a single segmentation of the LA blood pool at the ED time frame, and has previously been optimised using manual landmarks for LV motion estimation ( 18 ). In this study, the TSFFD configuration was optimised specifically for LA FT in RGCT.…”