Performance assessment of displacement-field estimation of the human left atrium from 4D-CT images using the coherent point drift algorithm

Background: Cardiac four-dimensional computed tomography (4D-CT) imaging is a standard approach used to visualize left atrium (LA) deformation for clinical diagnosis. However, the quantitative evaluation of LA deformation from 4D-CT images is still a challenging task. We assess the performance of LA displacement-field estimation from 4D-CT images using the coherent point drift (CPD) algorithm, which is a robust point set alignment method based on the expectation–maximization (EM) algorithm. Method: Subject-specific LA surfaces at 20 phases/cardiac cycles were reconstructed from 4D-CT images and expressed as sets of triangular elements. The LA surface at the phase that maximized the LA surface area was assigned as the control LA surface and those at the other 19 phases were assigned as observed LA surfaces. The LA displacement-field was estimated by solving the alignment between the control and observation LA surfaces using CPD. Results: Global correspondences between the estimated and observed LA surfaces were successfully confirmed by quantitative evaluations using the Dice similarity coefficient and differences of surface area for all phases. The surface distances between the estimated and observed LA surfaces ranged within 2 mm, except at the left atrial appendage and boundaries, where incomplete data, such as missing or false detections, were included on the observed LA surface. We confirmed that the estimated LA surface displacement and its spatial distribution were anisotropic, which is consistent with existing clinical observations. Conclusion: These results highlight that the LA displacement field estimated by CPD robustly tracks global LA surface deformation observed in 4D-CT images