Preserving the border and curvature of fetal heart chambers through TDyWT perspective geometry wrap segmentation

Congenital heart defect leads to the structural abnormality in neonatal. Congenital heart defect (CHD) is the major cause for 20% perinatal mortality and 50% infant mortality. However, the fetal cardiac screening plays a vital role to diagnose the CHD during second –trimester. Evaluation of fetal cardiac chamber structure is difficult due to small in size and movement. Four-chamber view has become the first and foremost view of echocardiography to detect structural malformations in the fetal heart. Furthermore, trained obstetricians, Pediatric cardiologists, maternal-fetal medicine specialists, and radiologists need proper knowledge and skills to identify the chamber structure from echocardiography. In addition, the effective diagnosis of fetal heart four-chamber view consumes more time and needs extremely skilled radiologists owing to their low quality, small signal to noise ratio and rapid movement of fetal heart ultrasound images. Thus, the diagnosis of CHD is the most challenging task. In this paper, we propose the Transverse Dyadic Wavelet Transform (TDyWT) algorithm to preserve the border and curvature of four chambers from 18 to 22 weeks ultrasound fetal heart image. We validate the proposed TDyWT algorithm with normal and abnormal images from Mediscan radiological centre. The performance of the TDyWT algorithm analyses qualitatively and quantitatively to prove border and curvature of the chambers is superior to other conventional methods.