Pursuing better imaging quality and miniaturizing imaging devices are two trends in the current development of ultrasound imaging. While the first one leads to more complex and expensive imaging equipment, poor image quality is a common problem of portable ultrasound imaging systems. In this paper, an image reconstruction method was proposed to break through the imaging quality limitation of portable devices by introducing generative adversarial network (GAN) model into the field of ultrasound image reconstruction. We combined two GAN generator models, the encoder-decoder model and the U-Net model to build a sparse skip connection U-Net (SSC U-Net) to tackle this problem. To produce more realistic output, stabilize the training procedure, and improve spatial resolution in the reconstructed ultrasound images, a new loss function which combines adversarial loss, L1 loss, and differential loss was proposed. Three datasets including 50 pairs of simulation, 40 pairs of phantom, and 72 pairs of in vivo images were used to evaluate the reconstruction performance. Experimental results show that our SSC U-Net is able to reconstruct ultrasound images with improved quality. Compared with U-Net, our SSC U-Net is able to preserve more details in the reconstructed images and improve full width at half maximum (FWHM) of point targets by 3.23%.

追求更好的成像质量和使成像设备小型化是当前超声成像发展的两个趋势。尽管第一个导致更复杂和昂贵的成像设备，但是图像质量差是便携式超声成像系统的普遍问题。本文提出了一种图像重建方法，通过将生成的对抗网络（GAN）模型引入超声图像重建领域，突破了便携式设备的成像质量限制。我们结合了两种GAN生成器模型（编码器-解码器模型和U-Net模型）来构建稀疏跳过连接U-Net（SSC U-Net）来解决此问题。为了产生更真实的输出，稳定训练过程并提高重建超声图像中的空间分辨率，提出了一种将对抗性损失，L1损失和微分损失相结合的新损失函数。使用包括50对模拟，40对幻像和72对体内图像的三个数据集来评估重建性能。实验结果表明，我们的SSC U-Net能够以更高的质量重建超声图像。与U-Net相比，我们的SSC U-Net能够在重建的图像中保留更多细节，并将点目标的半高全宽（FWHM）提高了3.23％。