Deep Atlas Network for Efficient 3D Left Ventricle Segmentation on Echocardiography.

We proposed a novel efficient method for 3D left ventricle (LV) segmentation on echocardiography, which is important for cardiac disease diagnosis. The proposed method effectively overcame the 3D echocardiography's challenges: high dimensional data, complex anatomical environments, and limited annotation data. First, we proposed a deep atlas network, which integrated LV atlas into the deep learning framework to address the 3D LV segmentation problem on echocardiography for the first time, and improved the performance based on limited annotation data. Second, we proposed a novel information consistency constraint to enhance the model's performance from different levels simultaneously, and finally achieved effective optimization for 3D LV segmentation on complex anatomical environments. Finally, the proposed method was optimized in an end-to-end back propagation manner and it achieved high inference efficiency even with high dimensional data, which satisfies the efficiency requirement of clinical practice. The experiments proved that the proposed method achieved better segmentation results and a higher inference speed compared with state-of-the-art methods. The mean surface distance, mean hausdorff surface distance, and mean dice index were 1.52 mm, 5.6 mm and 0.97 respectively. What's more, the method is efficient and its inference time is 0.02s. The experimental results proved that the proposed method has a potential clinical application for 3D LV segmentation on echocardiography.