Suppr超能文献

使用三维卷积神经网络进行参数化脑血流和动脉传输时间图。

Parametric cerebral blood flow and arterial transit time mapping using a 3D convolutional neural network.

机构信息

Department of Biomedical Engineering, University of California, Davis, California, USA.

Department of Radiology, University of California, Davis, California, USA.

出版信息

Magn Reson Med. 2023 Aug;90(2):583-595. doi: 10.1002/mrm.29674. Epub 2023 Apr 24.

Abstract

PURPOSE

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.

METHODS

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).

RESULTS

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).

CONCLUSION

The proposed machine learning-based ATT and CBF mapping offers substantially reduced scan time of multi-PLD pCASL.

摘要

目的

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。

方法

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。

结果

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)。

结论

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。

相似文献

1
Parametric cerebral blood flow and arterial transit time mapping using a 3D convolutional neural network.
Magn Reson Med. 2023 Aug;90(2):583-595. doi: 10.1002/mrm.29674. Epub 2023 Apr 24.
2
Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin-labeled MRI.
Magn Reson Med. 2022 Jul;88(1):406-417. doi: 10.1002/mrm.29193. Epub 2022 Feb 19.
3
Multi-phase 3D arterial spin labeling brain MRI in assessing cerebral blood perfusion and arterial transit times in children at 3T.
Clin Imaging. 2019 Jan-Feb;53:210-220. doi: 10.1016/j.clinimag.2018.11.001. Epub 2018 Nov 6.
6
Evaluation of cerebral blood flow using multi-phase pseudo continuous arterial spin labeling at 3-tesla.
Magn Reson Imaging. 2015 Dec;33(10):1338-1344. doi: 10.1016/j.mri.2015.07.016. Epub 2015 Aug 8.
8
Test-retest reliability and reproducibility of long-label pseudo-continuous arterial spin labeling.
Magn Reson Imaging. 2020 Nov;73:111-117. doi: 10.1016/j.mri.2020.07.010. Epub 2020 Jul 25.

本文引用的文献

1
Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin-labeled MRI.
Magn Reson Med. 2022 Jul;88(1):406-417. doi: 10.1002/mrm.29193. Epub 2022 Feb 19.
3
Relationship Between Cerebrovascular Reactivity and Cognition Among People With Risk of Cognitive Decline.
Front Physiol. 2021 May 31;12:645342. doi: 10.3389/fphys.2021.645342. eCollection 2021.
4
Comparison of convolutional neural network training strategies for cone-beam CT image segmentation.
Comput Methods Programs Biomed. 2021 Aug;207:106192. doi: 10.1016/j.cmpb.2021.106192. Epub 2021 May 20.
5
Denoising arterial spin labeling perfusion MRI with deep machine learning.
Magn Reson Imaging. 2020 May;68:95-105. doi: 10.1016/j.mri.2020.01.005. Epub 2020 Jan 15.
6
Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning.
NMR Biomed. 2022 Apr;35(4):e4224. doi: 10.1002/nbm.4224. Epub 2019 Dec 22.
7
MR image reconstruction using deep learning: evaluation of network structure and loss functions.
Quant Imaging Med Surg. 2019 Sep;9(9):1516-1527. doi: 10.21037/qims.2019.08.10.
8
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening.
IEEE Trans Med Imaging. 2020 Apr;39(4):1184-1194. doi: 10.1109/TMI.2019.2945514. Epub 2019 Oct 7.
9
Increasing cerebral blood flow improves cognition into late stages in Alzheimer's disease mice.
J Cereb Blood Flow Metab. 2020 Jul;40(7):1441-1452. doi: 10.1177/0271678X19873658. Epub 2019 Sep 7.
10
Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches.
IEEE Trans Med Imaging. 2019 Aug;38(8):1777-1787. doi: 10.1109/TMI.2019.2894349. Epub 2019 Jan 23.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验