当前位置: X-MOL 学术 › Magn Reson Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A deep learning approach to estimation of subject-level bias and variance in high angular resolution diffusion imaging.
Magnetic resonance imaging Pub Date : 2019-03-26 , DOI: 10.1016/j.mri.2019.03.021
Allison E Hainline 1 , Vishwesh Nath 2 , Prasanna Parvathaneni 3 , Kurt G Schilling 4 , Justin A Blaber 2 , Adam W Anderson 4 , Hakmook Kang 5 , Bennett A Landman 6
Affiliation  

The ability to evaluate empirical diffusion MRI acquisitions for quality and to correct the resulting imaging metrics allows for improved inference and increased replicability. Previous work has shown promise for estimation of bias and variance of generalized fractional anisotropy (GFA) but comes at the price of computational complexity. This paper aims to provide methods for estimating GFA, bias of GFA and standard deviation of GFA quickly and accurately. In order to provide a method for bias and variance estimation that can return results faster than the previously studied statistical techniques, three deep, fully-connected neural networks are developed for GFA, bias of GFA, and standard deviation of GFA. The results of these networks are compared to the observed values of the metrics as well as those fit from the statistical techniques (i.e. Simulation Extrapolation (SIMEX) for bias estimation and wild bootstrap for variance estimation). Our GFA network provides predictions that are closer to the true GFA values than a Q-ball fit of the observed data (root-mean-square error (RMSE) 0.0077 vs 0.0082, p < .001). The bias network also shows statistically significant improvement in comparison to the SIMEX-estimated error of GFA (RMSE 0.0071 vs. 0.01, p < .001).

中文翻译:

一种估计高角分辨率扩散成像中主体级偏差和方差的深度学习方法。

评估经验扩散 MRI 采集的质量并校正所得成像指标的能力可以改进推理并提高可复制性。先前的工作已经显示出估计广义分数各向异性 (GFA) 的偏差和方差的希望,但是以计算复杂性为代价的。本文旨在提供快速、准确地估算建筑面积、建筑面积偏差和建筑面积标准差的方法。为了提供一种比先前研究的统计技术更快地返回结果的偏差和方差估计方法,针对 GFA、GFA 偏差和 GFA 标准偏差开发了三个深度、全连接的神经网络。将这些网络的结果与度量的观测值以及统计技术(即用于偏差估计的模拟外推法(SIMEX)和用于方差估计的野生引导法)拟合的值进行比较。我们的 GFA 网络提供的预测比观测数据的 Q 球拟合更接近真实的 GFA 值(均方根误差 (RMSE) 0.0077 与 0.0082,p < .001)。与 GFA 的 SIMEX 估计误差相比,偏差网络还显示出统计上显着的改进(RMSE 0.0071 与 0.01,p < .001)。
更新日期:2019-03-26
down
wechat
bug