Faculty of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
Faculty of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
Comput Med Imaging Graph. 2023 Jul;107:102240. doi: 10.1016/j.compmedimag.2023.102240. Epub 2023 May 9.
Estimating T relaxation time distributions from multi-echo T-weighted MRI (TW) data can provide valuable biomarkers for assessing inflammation, demyelination, edema, and cartilage composition in various pathologies, including neurodegenerative disorders, osteoarthritis, and tumors. Deep neural network (DNN) based methods have been proposed to address the complex inverse problem of estimating T distributions from MRI data, but they are not yet robust enough for clinical data with low Signal-to-Noise ratio (SNR) and are highly sensitive to distribution shifts such as variations in echo-times (TE) used during acquisition. Consequently, their application is hindered in clinical practice and large-scale multi-institutional trials with heterogeneous acquisition protocols. We propose a physically-primed DNN approach, called PT, that incorporates the signal decay forward model in addition to the MRI signal into the DNN architecture to improve the accuracy and robustness of T distribution estimation. We evaluated our PT model in comparison to both DNN-based methods and classical methods for T distribution estimation using 1D and 2D numerical simulations along with clinical data. Our model improved the baseline model's accuracy for low SNR levels (SNR<80) which are common in the clinical setting. Further, our model achieved a ∼35% improvement in robustness against distribution shifts in the acquisition process compared to previously proposed DNN models. Finally, Our PT model produces the most detailed Myelin-Water fraction maps compared to baseline approaches when applied to real human MRI data. Our PT model offers a reliable and precise means of estimating T distributions from MRI data and shows promise for use in large-scale multi-institutional trials with heterogeneous acquisition protocols. Our source code is available at: https://github.com/Hben-atya/P2T2-Robust-T2-estimation.git.
从多回波 T 加权磁共振成像（TW）数据估计 T 弛豫时间分布可以为评估炎症、脱髓鞘、水肿和软骨成分提供有价值的生物标志物，这些病变包括神经退行性疾病、骨关节炎和肿瘤。已经提出了基于深度神经网络（DNN）的方法来解决从 MRI 数据估计 T 分布的复杂逆问题，但它们对于信噪比（SNR）低的临床数据还不够稳健，并且对分布偏移（如采集过程中使用的回波时间（TE）变化）非常敏感。因此，它们在临床实践和具有异质采集协议的大型多机构试验中的应用受到了阻碍。我们提出了一种物理引导的 DNN 方法，称为 PT，它将信号衰减正向模型与 MRI 信号一起纳入 DNN 架构中，以提高 T 分布估计的准确性和稳健性。我们使用 1D 和 2D 数值模拟以及临床数据，将我们的 PT 模型与基于 DNN 的方法和经典的 T 分布估计方法进行了比较评估。我们的模型提高了基线模型在临床环境中常见的低 SNR 水平（SNR<80）的准确性。此外，与之前提出的 DNN 模型相比，我们的模型在采集过程中的分布偏移方面的稳健性提高了约 35%。最后，当应用于真实的人体 MRI 数据时，与基线方法相比，我们的 PT 模型生成的髓鞘水分数图最详细。我们的 PT 模型为从 MRI 数据估计 T 分布提供了一种可靠和精确的方法，并有望在具有异质采集协议的大型多机构试验中使用。我们的源代码可在以下网址获得：https://github.com/Hben-atya/P2T2-Robust-T2-estimation.git。
