IEEE Trans Biomed Eng. 2021 Jun;68(6):1751-1758. doi: 10.1109/TBME.2020.3011119. Epub 2021 May 21.
The purpose of this work is to investigate the feasibility of using deep convolutional neural network (CNN) to improve the image quality of a grating-based X-ray differential phase contrast imaging (XPCI) system.
In this work, a novel deep CNN based phase signal extraction and image noise suppression algorithm (named as XP-NET) is developed. The numerical phase phantom, the ex vivo biological specimen and the ACR breast phantom are evaluated via the numerical simulations and experimental studies, separately. Moreover, images are also evaluated under different low radiation levels to verify its dose reduction capability.
Compared with the conventional analytical method, the novel XP-NET algorithm is able to reduce the bias of large DPC signals and hence increasing the DPC signal accuracy by more than 15%. Additionally, the XP-NET is able to reduce DPC image noise by about 50% for low dose DPC imaging tasks.
This proposed novel end-to-end supervised XP-NET has a great potential to improve the DPC signal accuracy, reduce image noise, and preserve object details.
We demonstrate that the deep CNN technique provides a promising approach to improve the grating-based XPCI performance and its dose efficiency in future biomedical applications.
本工作旨在研究利用深度卷积神经网络（CNN）提高基于光栅的 X 射线差分相位对比成像（XPCI）系统图像质量的可行性。
本工作开发了一种基于深度 CNN 的相位信号提取和图像噪声抑制算法（命名为 XP-NET）。通过数值模拟和实验研究，分别对数值相位体模、离体生物样本和 ACR 乳腺体模进行了评估。此外，还在不同低辐射水平下评估了图像，以验证其降低剂量的能力。
与传统的解析方法相比，新的 XP-NET 算法能够降低大 DPC 信号的偏差，从而将 DPC 信号精度提高 15%以上。此外，XP-NET 能够将低剂量 DPC 成像任务的 DPC 图像噪声降低约 50%。
本研究提出的新型端到端监督 XP-NET 有望提高 DPC 信号的准确性、降低图像噪声并保留物体细节。
我们证明了深度 CNN 技术为未来生物医学应用中提高基于光栅的 XPCI 性能及其剂量效率提供了一种有前途的方法。
