A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis
A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis
复制标题
DOI：
10.48550/arxiv.2204.03804
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Wanyu Bian;Qingchao Zhang;X. Ye;Yunmei Chen
中科院分区：
文献类型：
--
作者：
Wanyu Bian;Qingchao Zhang;X. Ye;Yunmei Chen
生成同一解剖结构的多对比/模态MRI丰富了诊断信息，但由于数据采集时间过长，在实践中受到限制。在本文中，我们提出了一种新的深度学习模型，用于联合重建和综合多模态MRI，使用多个源模态的不完整k空间数据作为输入。该模型的输出包括源模态的重建图像和目标模态合成的高质量图像。我们提出的模型是一个变分问题，它利用了几个可学习的特定于模态的特征提取器和一个多模态综合模块。我们提出了一种可学习的优化算法来求解该模型，该算法诱导出一个多阶段网络，该网络的参数可以使用多模态MRI数据进行训练。此外，采用双层优化框架进行鲁棒参数训练。我们通过大量的数值实验证明了我们方法的有效性。
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extractors and a multimodal synthesis module. We propose a learnable optimization algorithm to solve this model, which induces a multi-phase network whose parameters can be trained using multi-modal MRI data. Moreover, a bilevel-optimization framework is employed for robust parameter training. We demonstrate the effectiveness of our approach using extensive numerical experiments.