Single-Modality Supervised Joint PET-MR Image Reconstruction
Single-Modality Supervised Joint PET-MR Image Reconstruction
复制标题
DOI：
10.1109/trpms.2023.3283786
复制
发表时间：
2023-09-01
影响因子：
4.4
通讯作者：
Reader, Andrew J.
中科院分区：
文献类型：
--
作者：
Corda-D'Incan, Guillaume;Schnabel, Julia A.;Reader, Andrew J.
在传统协同方法的启发下，提出了一种基于联合正则化器的深度学习联合PET-MR图像重建新方法。PET的最大后验期望最大化算法和MR的Landweber算法通过深度学习的联合正则化步骤展开并相互连接。联合U-Net正则化器的参数和各自的正则化强度被学习并在所有迭代中共享。在引入该框架的同时，我们提出了损失函数选择对网络性能影响的研究。我们探讨了网络在单模态或联合模态损失训练时的表现。最后，我们通过使用不同的欠采样因素，探讨了在哪些设置下联合重建有利于MR重建。在二维模拟数据上得到的结果表明，联合网络优于传统的协同方法和独立的深度学习重建方法。对于PET，仅使用PET损失训练的网络比使用PET和MR损失项加权和训练的网络具有更好的全局重建精度。更重要的是，前者进一步改善了pet特异性特征的重建，而mri引导方法显示出其局限性。因此，在我们提出的框架中，使用单模态损失来监督训练，同时仍然并行重建两个模态，可以更好地重建和改进模态特有的损伤恢复。对于MR，虽然观察到相同的效果，但关节重建增益仅发生在高度欠采样的数据中。单模态损失的关节重建结果也在3-D临床PET-MR数据集上得到证实。
We present a new approach for deep learned joint PET-MR image reconstruction inspired by conventional synergistic methods using a joint regularizer. The maximum a posteriori expectation-maximization algorithm for PET and the Landweber algorithm for MR are unrolled and interconnected through a deep learned joint regularization step. The parameters of the joint U-Net regularizer and the respective regularization strengths are learned and shared across all the iterations. Along with introducing this framework, we propose an investigation of the impact of the loss function selection on network performance. We explored how the network performs when trained with a single or a joint-modality loss. Finally, we explored under which settings a joint reconstruction was beneficial for MR reconstruction by using various undersampling factors. The results obtained on 2-D simulated data show that the joint networks outperform conventional synergistic methods and independent deep learned reconstruction methods. For PET, the network trained with only a PET loss achieves a better global reconstruction accuracy than the version trained with a weighted sum of PET and MR loss terms. More importantly, the former further improves the reconstruction of PET-specific features where MR-guided methods show their limit. Therefore, using a single-modality loss to supervise the training while still reconstructing the two modalities in parallel leads to better reconstructions and improved modality-unique lesion recovery in our proposed framework. For MR, while the same effect is observed, joint reconstruction gains only occur in the presence of highly undersampled data. Single-modality loss joint reconstruction results are also demonstrated on 3-D clinical PET-MR datasets.