Least-squares reverse time migration (LSRTM) has the potential to reconstruct a high-resolution image of subsurface reflectivity. However, the current data-domain LSRTM approach, which iteratively updates the subsurface reflectivity by minimizing the data residuals, is a computationally expensive task. To alleviate this problem and improve imaging quality, we have developed an LSRTM approach using convolutional neural networks (CNNs), which is referred to as CNN-LSRTM. Specifically, the LSRTM problem can be implemented via a gradient-like iterative scheme, in which the updating component in each iteration is learned via a CNN model. To make the most of the observation data and migration velocity model at hand, we use the common-source reverse time migration (RTM) image, the stacked RTM image, and the migration velocity model rather than only the stacked RTM image as the input data of CNN. We have successfully trained the constructed CNN model on the training data sets with a total of 5000 randomly layered and fault models. Based on the well-trained CNN model, we have proved that our approach can efficiently recover the high-resolution reflection image for the layered, fault, and overthrust models. Through a marine field data experiment, we can determine the benefit of our constructed CNN model in terms of its computational efficiency. In addition, we analyze the influence of input data of the constructed CNN model on the reconstruction quality of the reflection image.