Anatomically aided PET image reconstruction using deep neural networks.
Anatomically aided PET image reconstruction using deep neural networks.
复制标题
使用深度神经网络的解剖学辅助正电子发射断层成像（PET）图像重建
DOI：
10.1002/mp.15051
复制
发表时间：
2021-09
期刊：
影响因子：
3.8
通讯作者：
Qi J
中科院分区：
文献类型：
--
作者：
Xie Z;Li T;Zhang X;Qi W;Asma E;Qi J
PET/CT和PET/MR扫描仪的发展为利用解剖信息提高PET图像质量提供了机会。在本文中，我们提出了一种新的协同学习3D卷积神经网络（CNN），从PET/CT图像对中提取模态特定的特征，并将互补特征集成到迭代重建框架中，以改善PET图像重建。我们使用预先训练的深度神经网络来表示PET图像。该网络使用低计数PET和CT图像对作为输入，高计数PET图像作为标签进行训练。然后将该网络纳入约束最大似然框架中，以正则化PET图像重建。两种不同的网络结构进行了研究，从CT图像的解剖信息的集成。一个是多通道CNN，它将PET和CT体积作为输入的单独通道。另一个是多分支CNN，它为PET和CT图像实现了单独的编码器来提取潜在特征，并将组合的潜在特征输入解码器。使用基于计算机的Monte Carlo模拟和两个真实的患者数据集，所提出的方法与现有的方法进行了比较，包括最大似然期望最大化（MLEM）重建，基于核的重建和基于CNN的深度惩罚方法，有和没有解剖指导。重建图像表明，所提出的约束ML重建方法产生的图像质量高于竞争方法。肺部区域中的肿瘤在所提出的约束ML重建中具有比在基于CNN的深度惩罚重建中更高的对比度。通过结合解剖信息进一步提高了图像质量。此外，在匹配的病变对比度下，所提出的方法中的肝脏标准差低于所有竞争方法。有监督的协同学习策略可以提高约束最大似然重建的性能。与现有技术相比，该方法产生了更好的病变对比度与背景标准差的权衡曲线，这可能会提高病变检测。
The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning 3D convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction. We used a pre-trained deep neural network to represent PET images. The network was trained using low-count PET and CT image pairs as inputs and high-count PET images as labels. This network was then incorporated into a constrained maximum likelihood framework to regularize PET image reconstruction. Two different network structures were investigated for the integration of anatomical information from CT images. One was a multi-channel CNN, which treated PET and CT volumes as separate channels of the input. The other one was multi-branch CNN, which implemented separate encoders for PET and CT images to extract latent features and fed the combined latent features into a decoder. Using computer-based Monte Carlo simulations and two real patient datasets, the proposed method has been compared with existing methods, including the maximum likelihood expectation maximization (MLEM) reconstruction, a kernel-based reconstruction and a CNN-based deep penalty method with and without anatomical guidance. Reconstructed images showed that the proposed constrained ML reconstruction approach produced higher quality images than the competing methods. The tumors in the lung region have higher contrast in the proposed constrained ML reconstruction than in the CNN-based deep penalty reconstruction. The image quality was further improved by incorporating the anatomical information. Moreover, the liver standard deviation was lower in the proposed approach than all the competing methods at a matched lesion contrast. The supervised co-learning strategy can improve the performance of constrained maximum likelihood reconstruction. Compared with existing techniques, the proposed method produced a better lesion contrast vs. background standard deviation trade-off curve, which can potentially improve lesion detection.
登录
查看更多内容
影响因子：
3.2
作者：
Kaneta T;Ogawa M;Motomura N;Iizuka H;Arisawa T;Hino-Shishikura A;Yoshida K;Inoue T
通讯作者：
Inoue T
影响因子：
4.9
作者：
Bai B;Li Q;Leahy RM
通讯作者：
Leahy RM
DOI：
10.1073/pnas.1907377117
发表时间：
2020-12-01
影响因子：
11.1
作者：
Antun, Vegard;Renna, Francesco;Hansen, Anders C.
通讯作者：
Hansen, Anders C.
影响因子：
10.6
作者：
Kumar, Ashnil;Fulham, Michael;Kim, Jinman
通讯作者：
Kim, Jinman
影响因子：
20.6
作者：
Gong, Kuang;Berg, Eric;Qi, Jinyi
通讯作者：
Qi, Jinyi