Fujita Naoto, Yokosawa Suguru, Shirai Toru, Terada Yasuhiko
Institute of Applied Physics, University of Tsukuba.
FUJIFILM Corporation, Medical Systems Research & Development Center.
Magn Reson Med Sci. 2024 Oct 1;23(4):460-478. doi: 10.2463/mrms.mp.2023-0031. Epub 2023 Jul 28.
Deep neural networks (DNNs) for MRI reconstruction often require large datasets for training. Still, in clinical settings, the domains of datasets are diverse, and how robust DNNs are to domain differences between training and testing datasets has been an open question. Here, we numerically and clinically evaluate the generalization of the reconstruction networks across various domains under clinically practical conditions and provide practical guidance on what points to consider when selecting models for clinical application.
We compare the reconstruction performance between four network models: U-Net, the deep cascade of convolutional neural networks (DC-CNNs), Hybrid Cascade, and variational network (VarNet). We used the public multicoil dataset fastMRI for training and testing and performed a single-domain test, where the domains of the dataset used for training and testing were the same, and cross-domain tests, where the source and target domains were different. We conducted a single-domain test (Experiment 1) and cross-domain tests (Experiments 2-4), focusing on six factors (the number of images, sampling pattern, acceleration factor, noise level, contrast, and anatomical structure) both numerically and clinically.
U-Net had lower performance than the three model-based networks and was less robust to domain shifts between training and testing datasets. VarNet had the highest performance and robustness among the three model-based networks, followed by Hybrid Cascade and DC-CNN. Especially, VarNet showed high performance even with a limited number of training images (200 images/10 cases). U-Net was more robust to domain shifts concerning noise level than the other model-based networks. Hybrid Cascade showed slightly better performance and robustness than DC-CNN, except for robustness to noise-level domain shifts. The results of the clinical evaluations generally agreed with the results of the quantitative metrics.
In this study, we numerically and clinically evaluated the robustness of the publicly available networks using the multicoil data. Therefore, this study provided practical guidance for clinical applications.
用于磁共振成像（MRI）重建的深度神经网络（DNN）通常需要大量数据集进行训练。然而，在临床环境中，数据集的领域是多样的，并且DNN对训练和测试数据集之间的领域差异的鲁棒性如何一直是一个悬而未决的问题。在此，我们在临床实际条件下对重建网络在不同领域的泛化能力进行了数值和临床评估，并为临床应用选择模型时应考虑的要点提供了实用指导。
我们比较了四种网络模型的重建性能：U-Net、深度卷积神经网络级联（DC-CNN）、混合级联和变分网络（VarNet）。我们使用公开的多线圈数据集fastMRI进行训练和测试，并进行了单域测试（其中用于训练和测试的数据集领域相同）和跨域测试（其中源域和目标域不同）。我们进行了单域测试（实验1）和跨域测试（实验2 - 4），在数值和临床上重点关注六个因素（图像数量、采样模式、加速因子、噪声水平、对比度和解剖结构）。
U-Net的性能低于基于模型的三个网络，并且对训练和测试数据集之间的领域转移的鲁棒性较差。在基于模型的三个网络中，VarNet具有最高的性能和鲁棒性，其次是混合级联和DC-CNN。特别是，即使训练图像数量有限（200张图像/10例），VarNet仍表现出高性能。与其他基于模型的网络相比，U-Net对噪声水平的领域转移更具鲁棒性。除了对噪声水平领域转移的鲁棒性外，混合级联的性能和鲁棒性略优于DC-CNN。临床评估结果总体上与定量指标结果一致。
在本研究中，我们使用多线圈数据对公开可用网络的鲁棒性进行了数值和临床评估。因此，本研究为临床应用提供了实用指导。
