Deep learning has recently attracted widespread interest as a means of reducing noise in low-dose CT (LDCT) images. Deep convolutional neural networks (CNNs) are typically trained to transfer high-quality image features of normal-dose CT (NDCT) images to LDCT images. However, existing deep learning approaches for denoising LDCT images often overlook the statistical property of CT images. In this paper, we propose an approach to statistical image restoration for LDCT using deep learning. We introduce a loss function to incorporate the noise property in image domain derived from the noise statistics in sinogram domain. In order to capture the spatially-varying statistics of CT images, we increase the receptive fields of the neural network to cover full-size CT slices. In addition, the proposed network utilizes $z$-directional correlation by taking multiple consecutive CT slices as input. For performance evaluation, the proposed networks are trained and validated with a public dataset consisting of LDCT-NDCT image pairs. We also perform a retrospective study by testing the networks with clinical LDCT images. The experimental results show that the denoising networks successfully reduce the noise level and restore the image details without adding artifacts. This study demonstrates that the statistical deep learning approach can restore the image quality of LDCT without loss of anatomical information.

中文翻译：

---

StatNet：使用深度学习对低剂量 CT 进行统计图像恢复

深度学习最近作为一种降低低剂量 CT (LDCT) 图像中的噪声的手段引起了广泛的兴趣。通常训练深度卷积神经网络 (CNN) 以将正常剂量 CT (NDCT) 图像的高质量图像特征传输到 LDCT 图像。然而，现有的用于去噪 LDCT 图像的深度学习方法往往忽略了 CT 图像的统计特性。在本文中，我们提出了一种使用深度学习对 LDCT 进行统计图像恢复的方法。我们引入了一个损失函数来合并从正弦图域中的噪声统计得出的图像域中的噪声属性。为了捕获 CT 图像的空间变化统计信息，我们增加了神经网络的感受野以覆盖全尺寸 CT 切片。此外，提议的网络通过将多个连续 CT 切片作为输入来利用 $z$ 方向相关性。对于性能评估，建议的网络使用由 LDCT-NDCT 图像对组成的公共数据集进行训练和验证。我们还通过使用临床 LDCT 图像测试网络来进行回顾性研究。实验结果表明，去噪网络成功地降低了噪声水平，并在不添加伪影的情况下恢复了图像细节。这项研究表明，统计深度学习方法可以在不丢失解剖信息的情况下恢复 LDCT 的图像质量。我们还通过使用临床 LDCT 图像测试网络来进行回顾性研究。实验结果表明，去噪网络成功地降低了噪声水平，并在不添加伪影的情况下恢复了图像细节。这项研究表明，统计深度学习方法可以在不丢失解剖信息的情况下恢复 LDCT 的图像质量。我们还通过使用临床 LDCT 图像测试网络来进行回顾性研究。实验结果表明，去噪网络成功地降低了噪声水平并恢复了图像细节，而不会添加伪影。这项研究表明，统计深度学习方法可以在不丢失解剖信息的情况下恢复 LDCT 的图像质量。