View Planes Recognition For Fetal Echocardiography With Unbalanced Samples

Congenital heart disease (CHD) is the most common fetal birth defect disease, which can seriously threaten the health and life of children. Echocardiography is the most commonly used diagnostic method for fetal CHD. The standard cardiac view planes of the fetus are used for the diagnosis of CHD on echocardiography. Recently deep learning methods were used for standard cardiac view planes recognition of fetuses. However, these studies did not consider the impact of imbalanced sample size on recognition. The recognition performance of fetal heart view planes using different deep learning models is compared. Specifically, the dataset used includes samples of congenital heart disease. An improved method for fetal cardiac view planes classification with unbalanced samples is proposed. It adopts a two-stage training method with weight decay and maximum norm restriction techniques. The experimental results validate the performance of the method proposed.