论文标题
联合多模式MRI重建和合成的可学习变分模型
A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis
论文作者
论文摘要
产生相同解剖结构的多对比度/模态MRI丰富了诊断信息，但由于数据获取时间过多而在实践中受到限制。在本文中，我们提出了一种新型的深入学习模型，用于使用几种源模态的不完整的k空间数据作为输入。我们模型的输出包括源模式的重建图像和目标模式中合成的高质量图像。我们提出的模型被公式化为一个变异问题，该问题利用了几个可学习的特定特征提取器和多模式合成模块。我们提出了一种可学习的优化算法来求解该模型，该算法可以使用多模式MRI数据来培训其参数的多相网络。此外，采用了二线优化框架进行鲁棒参数训练。我们使用广泛的数值实验证明了方法的有效性。
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.
