National Heart and Lung Institute, Imperial College London, London, SW7 2AZ, UK.
Cardiovascular Research Centre, Royal Brompton Hospital, London, SW7 2AZ, UK.
Sci Rep. 2024 Mar 7;14(1):5658. doi: 10.1038/s41598-024-55880-2.
In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the microstructure of myocardial tissue in living hearts, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice poses challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and prolonged scanning times. In this study, we investigated and implemented three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluated the performance of these models based on the reconstruction quality assessment, the diffusion tensor parameter assessment as well as the computational cost assessment. Our results indicate that the models discussed in this study can be applied for clinical use at an acceleration factor (AF) of and , with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference from the reference for all diffusion tensor parameters at AF or most DT parameters at AF , and the quality of most diffusion tensor parameter maps is visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF and AF . However, we believe that the models discussed in this study are not yet ready for clinical use at a higher AF. At AF , the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.
体内心脏扩散张量成像 (cDTI) 是一种很有前途的磁共振成像 (MRI) 技术，可用于评估活体心脏心肌组织的微观结构，深入了解心脏功能，并为创新治疗策略的发展提供依据。然而，由于采集过程中的技术障碍，如信噪比低和扫描时间长，将 cDTI 整合到常规临床实践中具有挑战性。在这项研究中，我们研究并实现了三种不同类型的基于深度学习的 MRI 重建模型，用于 cDTI 重建。我们根据重建质量评估、扩散张量参数评估以及计算成本评估来评估这些模型的性能。我们的结果表明，本研究中讨论的模型可以在加速因子 (AF) 为 和 的情况下应用于临床，其中 D5C5 模型在重建保真度方面表现出色，而 SwinMR 模型在感知得分方面更高。在 AF 或大多数 DT 参数在 AF 时，所有扩散张量参数都没有统计学差异，并且大多数扩散张量参数图的质量在视觉上是可以接受的。SwinMR 被推荐为 AF 和 AF 时的最佳重建方法。然而，我们认为，本研究中讨论的模型在更高的 AF 下还不能用于临床。在 AF 时，所有讨论的模型的性能仍然有限，只有一半的扩散张量参数恢复到与参考值无统计学差异的水平。一些扩散张量参数图甚至提供了错误和误导性的信息。
