Abstract: To address the problem of difficult and inaccurate segmentation of left ventricle due to high noise and fuzzy edge in echocardiography, we propose a left ventricle segmentation algorithm HeartNet that combines Transformer and CNN. First, we use two network architectures to efficiently capture global features and local details. Second, we design a feature fusion module using convolutional attention to adaptively fuse features from Transformer and CNN branches. Finally, we introduce a bridge attention module and calculate attention feature maps based on three-layer fusion features to obtain more accurate segmentation results. To validate the performance of HeartNet, we train, validate and test it on a large-scale cardiac image dataset EchoNet-Dynamic, achieving a Dice Coefficient of 92.41%, which outperforms six other algorithms involved in comparison. We test it on clinical patients’ ultrasound images, and the visualization and blind review results by clinical doctors demonstrate the effectiveness of this algorithm. The experimental results show that HeartNet can accurately segment left ventricle, providing reliable computer assistance for cardiac disease diagnosis.