Wall Thickness Estimation from Short Axis Ultrasound Images via Temporal Compatible Deformation Learning

Abstract

Structural parameters of the heart, such as left ventricular wall thickness (LVWT), have important clinical significance for cardiac disease. In clinical practice, it requires tedious labor work to be obtained manually from ultrasound images and results in large variations between experts. Great challenges exist to automatize this procedure: the myocardium boundary is sensitive to heavy noise and can lead to irregular boundaries; the temporal dynamics in the ultrasound video are not well retained. In this paper, we propose a Temporally Compatible Deformation learning network, named TC-Deformer, to detect the myocardium boundaries and estimate LVWT automatically. Specifically, we first propose a two-stage deformation learning network to estimate the myocardium boundaries by deforming a prior myocardium template. A global affine transformation is first learned to shift and scale the template. Then a dense deformation field is learned to adjust locally the template to match the myocardium boundaries. Second, to make the deformation learning of different frames become compatible in the temporal dynamics, we adopt the mean parameters of affine transformation for all frames and propose a bi-direction deformation learning to guarantee that the deformation fields across the whole sequences can be applied to both the myocardium boundaries and the ultrasound images. Experimental results on an ultrasound dataset of 201 participants show that the proposed method can achieve good boundary detection of basal, middle, and apical myocardium, and lead to accurate estimation of the LVWT, with a mean absolute error of less than 1.00 mm. When compared with human methods, our TC-Deformer performs better than the junior cardiologists and is on par with the middle-level cardiologists.