Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior.
Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior.
复制标题
DOI：
10.1109/tmi.2021.3120913
复制
发表时间：
2022-03
影响因子：
10.6
通讯作者：
Li Q
中科院分区：
文献类型：
--
作者：
Gong K;Catana C;Qi J;Li Q
直接重建方法已被开发，估计参数图像直接从所测量的PET正弦图相结合的PET成像模型和示踪剂动力学在一个集成的框架。由于接收到的计数有限，由直接重建框架产生的参数图像的信噪比（SNR）和分辨率仍然有限。最近，当有大量高质量的训练标签可用时，监督式深度学习方法已成功应用于医学成像去噪/重建。对于静态PET成像，可以通过延长扫描时间来获取高质量的训练标签。然而，这对于扫描时间已经足够长的动态PET成像是不可行的。在这项工作中，我们提出了一个无监督的深度学习框架，用于从动态PET直接进行参数重建，并在Patlak模型和相对平衡Logan模型上进行了测试。训练目标函数基于PET统计模型。患者的解剖学先验图像，这是很容易从PET/CT或PET/MR扫描，被提供作为网络输入，以提供一个流形约束，也被用来构建一个内核层，以执行非局部特征去噪。线性动力学模型以1 × 1 × 1卷积层嵌入网络结构中。基于18F-FDG和11 C-PiB示踪剂动态数据集的评估表明，该框架可以优于传统的和基于核方法的直接重建方法。
Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received, signal-to-noise-ratio (SNR) and resolution of parametric images produced by direct reconstruction frameworks are still limited. Recently supervised deep learning methods have been successfully applied to medical imaging denoising/reconstruction when large number of high-quality training labels are available. For static PET imaging, high-quality training labels can be acquired by extending the scanning time. However, this is not feasible for dynamic PET imaging, where the scanning time is already long enough. In this work, we proposed an unsupervised deep learning framework for direct parametric reconstruction from dynamic PET, which was tested on the Patlak model and the relative equilibrium Logan model. The training objective function was based on the PET statistical model. The patient’s anatomical prior image, which is readily available from PET/CT or PET/MR scans, was supplied as the network input to provide a manifold constraint, and also utilized to construct a kernel layer to perform non-local feature denoising. The linear kinetic model was embedded in the network structure as a 1 × 1 × 1 convolution layer. Evaluations based on dynamic datasets of 18F-FDG and 11C-PiB tracers show that the proposed framework can outperform the traditional and the kernel method-based direct reconstruction methods.
参数图像的直接四维重建结合了函数联合熵。
影响因子：
3.5
作者：
Tang J;Kuwabara H;Wong DF;Rahmim A
通讯作者：
Rahmim A
影响因子：
3.5
作者：
Rahmim A;Zhou Y;Tang J;Lu L;Sossi V;Wong DF
通讯作者：
Wong DF