The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo 182-8585, Japan.
The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo 182-8585, Japan.
Comput Med Imaging Graph. 2021 Jun;90:101920. doi: 10.1016/j.compmedimag.2021.101920. Epub 2021 Apr 20.
Since the development of deep learning methods, many researchers have focused on image quality improvement using convolutional neural networks. They proved its effectivity in noise reduction, single-image super-resolution, and segmentation. In this study, we apply stacked U-Net, a deep learning method, for X-ray computed tomography image reconstruction to generate high-quality images in a short time with a small number of projections. It is not easy to create highly accurate models because medical images have few training images due to patients' privacy issues. Thus, we utilize various images from the ImageNet, a widely known visual database. Results show that a cross-sectional image with a peak signal-to-noise ratio of 27.93 db and a structural similarity of 0.886 is recovered for a 512 × 512 image using 360-degree rotation, 512 detectors, and 64 projections, with a processing time of 0.11 s on the GPU. Therefore, the proposed method has a shorter reconstruction time and better image quality than the existing methods.
自深度学习方法发展以来，许多研究人员专注于使用卷积神经网络来提高图像质量。他们证明了其在降噪、单图像超分辨率和分割方面的有效性。在这项研究中，我们应用堆叠 U-Net，一种深度学习方法，进行 X 射线计算机断层扫描图像重建，以便在短时间内使用少量投影生成高质量图像。由于医疗图像由于患者的隐私问题，训练图像很少，因此创建高度精确的模型并不容易。因此，我们利用来自 ImageNet 的各种图像，这是一个广为人知的视觉数据库。结果表明，对于 512×512 的图像，使用 360 度旋转、512 个探测器和 64 个投影，可以恢复峰值信噪比为 27.93dB 和结构相似性为 0.886 的横截面图像，在 GPU 上的处理时间为 0.11s。因此，与现有方法相比，该方法具有更短的重建时间和更好的图像质量。
