Deep learning-based parameter estimation in fetal diffusion-weighted MRI.
Deep learning-based parameter estimation in fetal diffusion-weighted MRI.
复制标题
DOI：
10.1016/j.neuroimage.2021.118482
复制
发表时间：
2021-11
期刊：
影响因子：
5.7
通讯作者：
Gholipour A
中科院分区：
文献类型：
--
作者：
Karimi D;Jaimes C;Machado-Rivas F;Vasung L;Khan S;Warfield SK;Gholipour A
磁共振弥散加权成像(DW-MRI)胎儿脑成像存在胎儿运动频繁、信噪比远低于非胎儿图像的问题。因此，在胎儿DW-MRI中准确和稳健的参数估计仍然是一个悬而未决的问题。最近，深度学习技术被成功地用于非胎儿受试者的DW-MRI参数估计。然而，这些先前的工作都没有涉及到胎儿大脑，因为获得可靠的胎儿训练数据是具有挑战性的。为了解决这个问题，在这项工作中，我们提出了一种新的方法，利用胎儿扫描以及早产婴儿的扫描。高质量的新生儿扫描被用来估计感兴趣参数的准确地图。然后使用这些参数图生成与胎儿数据特有的测量方案和噪声分布相匹配的DW-MRI数据。为了验证所提出的数据生成流水线的有效性和可靠性，我们使用生成的数据来训练卷积神经网络(CNN)来估计颜色分数各向异性(CFA)。我们在重建准确性、精确度和重建质量的专家评估方面评估了训练好的CNN对独立的胎儿数据集的影响。结果表明，与标准估计方法相比，所提出的机器学习流水线的重建误差显著降低(n=100，p<；0.001)，重建精度(n=20，p<；0.001)显著提高。对20个胎儿测试扫描的专家评估表明，该方法的总体重建质量(P<；0.001)和11个感兴趣区域(P<；0.001)的重建更加准确。
Diffusion-weighted magnetic resonance imaging (DW-MRI) of fetal brain is challenged by frequent fetal motion and signal to noise ratio that is much lower than non-fetal imaging. As a result, accurate and robust parameter estimation in fetal DW-MRI remains an open problem. Recently, deep learning techniques have been successfully used for DW-MRI parameter estimation in non-fetal subjects. However, none of those prior works has addressed the fetal brain because obtaining reliable fetal training data is challenging. To address this problem, in this work we propose a novel methodology that utilizes fetal scans as well as scans from prematurely-born infants. High-quality newborn scans are used to estimate accurate maps of the parameter of interest. These parameter maps are then used to generate DW-MRI data that match the measurement scheme and noise distribution that are characteristic of fetal data. In order to demonstrate the effectiveness and reliability of the proposed data generation pipeline, we used the generated data to train a convolutional neural network (CNN) to estimate color fractional anisotropy (CFA). We evaluated the trained CNN on independent sets of fetal data in terms of reconstruction accuracy, precision, and expert assessment of reconstruction quality. Results showed significantly lower reconstruction error (n = 100, p < 0.001) and higher reconstruction precision (n = 20, p < 0.001) for the proposed machine learning pipeline compared with standard estimation methods. Expert assessments on 20 fetal test scans showed significantly better overall reconstruction quality (p < 0.001) and more accurate reconstruction of 11 regions of interest (p < 0.001) with the proposed method.
登录
查看更多内容
影响因子：
10.9
作者：
Karimi D;Vasung L;Jaimes C;Machado-Rivas F;Khan S;Warfield SK;Gholipour A
通讯作者：
Gholipour A
影响因子：
5.7
作者：
Jakab, Andras;Kasprian, Gregor;Langs, Georg
通讯作者：
Langs, Georg
影响因子：
3.3
作者：
Chang, LC;Jones, DK;Pierpaoli, C
通讯作者：
Pierpaoli, C
影响因子：
2.2
作者：
Koay, Cheng Guan;Chang, Lin-Ching;Basser, Peter J.
通讯作者：
Basser, Peter J.
影响因子：
11.2
作者：
Baldoli, C;Righini, A;Triulzi, F
通讯作者：
Triulzi, F