A geometry-guided multi-beamlet deep learning technique for CT reconstruction.
A geometry-guided multi-beamlet deep learning technique for CT reconstruction.
复制标题
DOI：
10.1088/2057-1976/ac6d12
复制
发表时间：
2022-05-13
影响因子：
1.4
通讯作者：
中科院分区：
文献类型：
--
作者：
以前的研究已经提出了深度学习技术来从正弦图重建CT图像。然而，这些技术采用大的全连接（FC）层的投影到图像域变换，产生需要大量的计算能力，可能超过计算内存限制的大型模型。我们之前的工作提出了一种用于CBCT重建的几何引导深度学习（GDL）技术，可以减少模型大小和GPU内存消耗。这项研究进一步发展了这项技术，并提出了一种新的多波束深度学习（GMDL）技术，提高了性能。该研究通过低剂量真实患者CT图像重建将所提出的技术与基于FC层的深度学习（FCDL）方法和GDL技术进行了比较。GMDL技术不是使用大的FC层，而是通过构造许多小的FC层来学习投影到图像域的变换。除了像GDL那样将投影域中的每个像素连接到图像域中沿着中心子束沿着的子束点之外，GMDL中的这些较小FC层基于CT投影几何形状将每个像素连接到中心子束外围的子束。我们比较地面真实图像与低剂量图像重建的GMDL，FCDL，GDL，和传统的FBP方法。通过峰值信噪比（PSNR）、结构相似性指数（SSIM）和均方根误差（RMSE）对图像进行了定量分析。与其他方法相比，GMDL重建的低剂量CT图像在PSNR、SSIM和RMSE方面显示出改善的图像质量。用于GMDL技术的外围子束的最佳数量是在中心子束的每一侧上的两个子束。GMDL模型的模型大小和内存消耗小于FCDL模型的1/100。与FCDL方法相比，GMDL技术被证明能够重建真实的患者低剂量CT图像，图像质量得到改善，模型大小和GPU内存需求显著降低。
Previous studies have proposed deep-learning techniques to reconstruct CT images from sinograms. However, these techniques employ large fully-connected (FC) layers for projection-to-image domain transformation, producing large models requiring substantial computation power, potentially exceeding the computation memory limit. Our previous work proposed a geometry-guided-deep-learning (GDL) technique for CBCT reconstruction that reduces model size and GPU memory consumption. This study further develops the technique and proposes a novel multi-beamlet deep learning (GMDL) technique of improved performance. The study compares the proposed technique with the FC layer-based deep learning (FCDL) method and the GDL technique through low-dose real-patient CT image reconstruction. Instead of using a large FC layer, the GMDL technique learns the projection-to-image domain transformation by constructing many small FC layers. In addition to connecting each pixel in the projection domain to beamlet points along the central beamlet in the image domain as GDL does, these smaller FC layers in GMDL connect each pixel to beamlets peripheral to the central beamlet based on the CT projection geometry. We compare ground truth images with low-dose images reconstructed with the GMDL, the FCDL, the GDL, and the conventional FBP methods. The images are quantitatively analyzed in terms of peak-signal-to-noise-ratio (PSNR), structural-similarity-index-measure (SSIM), and root-mean-square-error (RMSE). Compared to other methods, the GMDL reconstructed low-dose CT images show improved image quality in terms of PSNR, SSIM, and RMSE. The optimal number of peripheral beamlets for the GMDL technique is two beamlets on each side of the central beamlet. The model size and memory consumption of the GMDL model is less than 1/100 of the FCDL model. Compared to the FCDL method, the GMDL technique is demonstrated to be able to reconstruct real patient low-dose CT images of improved image quality with significantly reduced model size and GPU memory requirement.