Department of Biomedical Engineering, University of California, Davis, California, USA.
Department of Radiology, University of California, Davis, California, USA.
Magn Reson Med. 2023 Aug;90(2):583-595. doi: 10.1002/mrm.29674. Epub 2023 Apr 24.
To reduce the total scan time of multiple postlabeling delay (multi-PLD) pseudo-continuous arterial spin labeling (pCASL) by developing a hierarchically structured 3D convolutional neural network (H-CNN) that estimates the arterial transit time (ATT) and cerebral blow flow (CBF) maps from the reduced number of PLDs as well as averages.
A total of 48 subjects (38 females and 10 males), aged 56-80 years, compromising a training group (n = 45) and a validation group (n = 3) underwent MRI including multi-PLD pCASL. We proposed an H-CNN to estimate the ATT and CBF maps using a reduced number of PLDs and a separately reduced number of averages. The proposed method was compared with a conventional nonlinear model fitting method using the mean absolute error (MAE).
The H-CNN provided the MAEs of 32.69 ms for ATT and 3.32 mL/100 g/min for CBF estimations using a full data set that contains six PLDs and six averages in the 3 test subjects. The H-CNN also showed that the smaller number of PLDs can be used to estimate both ATT and CBF without significant discrepancy from the reference (MAEs of 231.45 ms for ATT and 9.80 mL/100 g/min for CBF using three of six PLDs).
The proposed machine learning-based ATT and CBF mapping offers substantially reduced scan time of multi-PLD pCASL.
通过开发一种分层结构的 3D 卷积神经网络(H-CNN),从减少的标记延迟(PLD)数量和平均值中估计动脉转运时间(ATT)和脑血流量(CBF)图,从而减少多次后标记延迟(multi-PLD)伪连续动脉自旋标记(pCASL)的总扫描时间。
共有 48 名受试者(38 名女性和 10 名男性),年龄 56-80 岁,分为训练组(n=45)和验证组(n=3),进行了包括 multi-PLD pCASL 的 MRI 检查。我们提出了一种 H-CNN,使用减少的 PLD 数量和单独减少的平均值来估计 ATT 和 CBF 图。使用平均绝对误差(MAE)比较了所提出的方法与传统的非线性模型拟合方法。
H-CNN 使用包含 3 名测试对象的 6 个 PLD 和 6 个平均值的完整数据集,提供了 ATT 的 MAE 为 32.69ms 和 CBF 的 MAE 为 3.32mL/100g/min 的估计值。H-CNN 还表明,可以使用较少的 PLD 数量来估计 ATT 和 CBF,而不会与参考值有明显差异(使用 6 个 PLD 中的 3 个,ATT 的 MAE 为 231.45ms,CBF 的 MAE 为 9.80mL/100g/min)。
基于机器学习的 ATT 和 CBF 映射提供了大幅度减少 multi-PLD pCASL 的扫描时间。