Application of machine-learning models to improve the image quality of photon-counting CT images
Application of machine-learning models to improve the image quality of photon-counting CT images
复制标题
应用机器学习模型提高光子计数CT图像质量
DOI：
10.1088/1748-0221/16/05/p05021
复制
发表时间：
2021
影响因子：
1.3
通讯作者：
T. Toyoda;S. Sato;H. Kiji;J. Kataoka;J. Kotoku;M. Taki
中科院分区：
文献类型：
--
作者：
T. Toyoda;S. Sato;H. Kiji;J. Kataoka;J. Kotoku;M. Taki
X射线计算机断层扫描（CT）已广泛应用于医学诊断成像。然而，传统的能量积分CT需要较高的辐射剂量，并且只能提供单色图像，无法消除各种伪影。相比之下，光子计数 CT (PC-CT) 提供低剂量多色 CT 成像，能够识别多种造影剂。然而，在PC-CT系统中，由于有限能带内的图像重建而导致光子统计的缺乏，严重影响了图像质量。在本研究中，我们应用了三种类型的机器学习（ML）技术来提高 PC-CT 的图像质量，即字典学习、U-Net 和 Noise2Noise。这些机器学习模型使用通过简单步骤创建的低剂量和高剂量图像对进行训练。将训练好的 ML 模型应用于模拟数据以及临床实践中使用的对比剂的实验 PC-CT 图像。因此，在模拟数据中，峰值信噪比 (PSNR) 值从输入的 21.3 分别提高到字典学习、U-Net 和 Noise2Noise 的 26.6、33.3 和 30.1。此外，在实际的 PC-CT 图像中，我们成功地再现了具有高 PSNR 的 PC-CT 图像，从而能够同时成像多种造影剂，并提高了浓度估计的准确性。展望未来，我们将开发一种可应用于体内 CT 图像的处理技术。
X-ray computed tomography (CT) has been widely used in medical diagnostic imaging. However, conventional, energy-integrated CT requires a high radiation dose and can only provide monochromatic images that cannot eliminate various artifacts. In contrast, photon-counting CT (PC-CT) provides low-dose multicolor CT imaging, which enables the identification of multiple contrast agents. However, in the PC-CT system, the lack of photon statistics, which is also caused by image reconstruction in the limited energy band, severely affects the image quality. In this study, we applied three types of machine-learning (ML) techniques to improved the image quality of PC-CT, that is, dictionary learning, U-Net, and Noise2Noise. These ML models were trained using low- and high-dose image pairs created in simple steps. The trained ML models were applied to simulated data, and experimental PC-CT images of contrast agents used in clinical practice. Consequently, in the simulated data, the peak signal-to-noise ratio (PSNR) value improved from 21.3 for the input to 26.6, 33.3, and 30.1 for dictionary learning, U-Net, and Noise2Noise, respectively. Furthermore, in the actual PC-CT images, we successfully reproduced PC-CT images with high PSNR, which enabled simultaneous imaging of multiple contrast agents with improved accuracy of concentration estimation. As a future perspective, we will develop a processing technique that can be applied to in vivo CT images.