Radiological imaging offers effective measurement of anatomy, which is useful in disease diagnosis and assessment. Previous study has shown that the left atrial wall remodeling can provide information to predict treatment outcome in atrial fibrillation. Nevertheless, the seg-mentation of the left atrial structures from medical images is still very time-consuming. Current advances in neural network may help creating automatic segmentation models that reduce the workload for clini-cians. In this preliminary study, we propose automated, two-stage, three-dimensional U-Nets with convolutional neural network, for the challenging task of left atrial segmentation. Unlike previous two-dimensional image segmentation methods, we use 3D U-Nets to obtain the heart cavity directly in 3D. The dual 3D U-Net structure consists of, a first U-Net to coarsely segment and locate the left atrium, and a second U-Net to accurately segment the left atrium under higher resolution. In addition, we introduce a loss function based on additional distance information to adjust the final segmentation. We randomly split the data into training datasets (80 subjects) and validation datasets (20 subjects). Experiments show that the average Dice coefficient for validation datasets is 0.924, the sensitivity is 0.92 and the specificity 0.99. We also compare the prediction results using the two loss functions, Dice coefficient loss and proposed weighted Dice/Contour distance loss, in a 3D view.