Volume 57, Issue 5 pp. 1477-1489

Research Article

Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi-Delay Arterial Spin Labeling MRI Using a Simulation-Based Supervised Deep Neural Network

Shota Ishida PhD,

Corresponding Author

Shota Ishida PhD

[email protected]

orcid.org/0000-0002-0728-8057

Department of Radiological Technology, Faculty of Medical Sciences, Kyoto College of Medical Science, Kyoto, Japan

Address reprint requests to: S.I., 1-3 Imakita, Oyama-higashi, Sonobe, Nantan, Kyoto 622-0041, Japan.

E-mail: [email protected]

Search for more papers by this author

Makoto Isozaki MD, PhD,

Makoto Isozaki MD, PhD

Department of Neurosurgery, Division of Medicine, Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Search for more papers by this author

Yasuhiro Fujiwara PhD,

Yasuhiro Fujiwara PhD

Department of Medical Image Sciences, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan

Search for more papers by this author

Naoyuki Takei MS,

Naoyuki Takei MS

GE Healthcare, Tokyo, Japan

Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan

Search for more papers by this author

Masayuki Kanamoto PhD,

Masayuki Kanamoto PhD

Radiological Center, University of Fukui Hospital, Fukui, Japan

Search for more papers by this author

Hirohiko Kimura MD, PhD,

Hirohiko Kimura MD, PhD

Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Radiology Section, National Health Insurance Echizen-cho Ota Hospital, Fukui, Japan

Search for more papers by this author

Tetsuya Tsujikawa MD, PhD,

Tetsuya Tsujikawa MD, PhD

orcid.org/0000-0002-8980-1044

Department of Radiology, Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Search for more papers by this author

Shota Ishida PhD,

Corresponding Author

Shota Ishida PhD

[email protected]

orcid.org/0000-0002-0728-8057

Department of Radiological Technology, Faculty of Medical Sciences, Kyoto College of Medical Science, Kyoto, Japan

Address reprint requests to: S.I., 1-3 Imakita, Oyama-higashi, Sonobe, Nantan, Kyoto 622-0041, Japan.

E-mail: [email protected]

Search for more papers by this author

Makoto Isozaki MD, PhD,

Makoto Isozaki MD, PhD

Department of Neurosurgery, Division of Medicine, Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Search for more papers by this author

Yasuhiro Fujiwara PhD,

Yasuhiro Fujiwara PhD

Department of Medical Image Sciences, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan

Search for more papers by this author

Naoyuki Takei MS,

Naoyuki Takei MS

GE Healthcare, Tokyo, Japan

Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan

Search for more papers by this author

Masayuki Kanamoto PhD,

Masayuki Kanamoto PhD

Radiological Center, University of Fukui Hospital, Fukui, Japan

Search for more papers by this author

Hirohiko Kimura MD, PhD,

Hirohiko Kimura MD, PhD

Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Radiology Section, National Health Insurance Echizen-cho Ota Hospital, Fukui, Japan

Search for more papers by this author

Tetsuya Tsujikawa MD, PhD,

Tetsuya Tsujikawa MD, PhD

orcid.org/0000-0002-8980-1044

Department of Radiology, Faculty of Medical Sciences, University of Fukui, Fukui, Japan

Search for more papers by this author

First published: 28 September 2022

https://doi.org/10.1002/jmri.28433

Citations: 3

Share a link

Email
Wechat
Bluesky

Abstract

Background

An inherently poor signal-to-noise ratio (SNR) causes inaccuracy and less precision in cerebral blood flow (CBF) and arterial transit time (ATT) when using arterial spin labeling (ASL). Deep neural network (DNN)-based parameter estimation can solve these problems.

Purpose

To reduce the effects of Rician noise on ASL parameter estimation and compute unbiased CBF and ATT using simulation-based supervised DNNs.

Study Type

Retrospective.

Population

One million simulation test data points, 17 healthy volunteers (five women and 12 men, 33.2 ± 14.6 years of age), and one patient with moyamoya disease.

Field Strength/Sequence

3.0 T/Hadamard-encoded pseudo-continuous ASL with a three-dimensional fast spin-echo stack of spirals.

Assessment

Performances of DNN and conventional methods were compared. For test data, the normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) between the ground truth and predicted values were evaluated. For in vivo data, baseline CBF and ATT and their relative changes with respect to SNR using artificial noise-added images were assessed.

Statistical Tests

One-way analysis of variance with post-hoc Tukey's multiple comparison test, paired t-test, and the Bland–Altman graphical analysis. Statistical significance was defined as P < 0.05.

Results

For both CBF and ATT, NMAE and NRMSE were lower with DNN than with the conventional method. The baseline values were significantly smaller with DNN than with the conventional method (CBF in gray matter, 66 ± 10 vs. 71 ± 12 mL/100 g/min; white matter, 45 ± 6 vs. 46 ± 7 mL/100 g/min; ATT in gray matter, 1424 ± 201 vs. 1471 ± 154 msec). CBF and ATT increased with decreasing SNR; however, their change rates were smaller with DNN than were those with the conventional method. Higher CBF in the prolonged ATT region and clearer contrast in ATT were identified by DNN in a clinical case.

Data Conclusion

DNN outperformed the conventional method in terms of accuracy, precision, and noise immunity.

Evidence Level: 3

Technical Efficacy: Stage 1

Supporting Information

References

1Detre JA, Leigh JS, Williams DS, Koretsky AP. Perfusion imaging. Magn Reson Med 1992; 23: 37-45.
10.1002/mrm.1910230106
CAS PubMed Web of Science® Google Scholar
2Alsop DC, Detre JA, Golay X, et al. Recommended implementation of arterial spin-labeled perfusion MRI for clinical applications: A consensus of the ISMRM perfusion study group and the European consortium for ASL in dementia. Magn Reson Med 2015; 73: 102-116.
10.1002/mrm.25197
PubMed Web of Science® Google Scholar
3Ishida S, Kimura H, Takei N, et al. Separating spin compartments in arterial spin labeling using delays alternating with nutation for tailored excitation (DANTE) pulse: A validation study using T2 -relaxometry and application to arterial cerebral blood volume imaging. Magn Reson Med 2022; 87: 1329-1345.
10.1002/mrm.29052
PubMed Web of Science® Google Scholar
4Yoo RE, Choi SH, Cho HR, et al. Tumor blood flow from arterial spin labeling perfusion MRI: A key parameter in distinguishing high-grade gliomas from primary cerebral lymphomas, and in predicting genetic biomarkers in high-grade gliomas. J Magn Reson Imaging 2013; 38: 852-860.
10.1002/jmri.24026
CAS PubMed Web of Science® Google Scholar
5Tsujikawa T, Kimura H, Matsuda T, et al. Arterial transit time mapping obtained by pulsed continuous 3D ASL imaging with multiple post-label delay acquisitions: Comparative study with PET-CBF in patients with chronic occlusive cerebrovascular disease. PLoS One 2016; 11:e0156005.
10.1371/journal.pone.0156005
PubMed Web of Science® Google Scholar
6Suo X, Lei D, Cheng L, et al. Multidelay multiparametric arterial spin labeling perfusion MRI and mild cognitive impairment in early stage Parkinson's disease. Hum Brain Mapp 2019; 40: 1317-1327.
10.1002/hbm.24451
PubMed Web of Science® Google Scholar
7Takeuchi K, Isozaki M, Higashino Y, et al. The utility of arterial transit time measurement for evaluating the hemodynamic perfusion state of patients with chronic cerebrovascular stenosis or occlusive disease: Correlative study between MR imaging and (15)O-labeled H2O positron emission tomography. Magn Reson Med Sci 2022.
10.2463/mrms.mp.2020-0123
PubMed Google Scholar
8Guo J, Holdsworth SJ, Fan AP, et al. Comparing accuracy and reproducibility of sequential and Hadamard-encoded multidelay pseudocontinuous arterial spin labeling for measuring cerebral blood flow and arterial transit time in healthy subjects: A simulation and in vivo study. J Magn Reson Imaging 2018; 47: 1119-1132.
10.1002/jmri.25834
PubMed Web of Science® Google Scholar
9Ishida S, Kimura H, Isozaki M, et al. Robust arterial transit time and cerebral blood flow estimation using combined acquisition of Hadamard-encoded multi-delay and long-labeled long-delay pseudo-continuous arterial spin labeling: A simulation and in vivo study. NMR Biomed 2020; 33:e4319.
10.1002/nbm.4319
CAS PubMed Web of Science® Google Scholar
10Woods JG, Chappell MA, Okell TW. A general framework for optimizing arterial spin labeling MRI experiments. Magn Reson Med 2019; 81: 2474-2488.
10.1002/mrm.27580
PubMed Web of Science® Google Scholar
11Woods JG, Chappell MA, Okell TW. Designing and comparing optimized pseudo-continuous arterial spin labeling protocols for measurement of cerebral blood flow. Neuroimage 2020; 223:117246.
10.1016/j.neuroimage.2020.117246
PubMed Web of Science® Google Scholar
12Dai W, Robson PM, Shankaranarayanan A, Alsop DC. Reduced resolution transit delay prescan for quantitative continuous arterial spin labeling perfusion imaging. Magn Reson Med 2012; 67: 1252-1265.
10.1002/mrm.23103
CAS PubMed Web of Science® Google Scholar
13Wang DJ, Alger JR, Qiao JX, et al. Multi-delay multi-parametric arterial spin-labeled perfusion MRI in acute ischemic stroke - comparison with dynamic susceptibility contrast enhanced perfusion imaging. Neuroimage Clin 2013; 3: 1-7.
10.1016/j.nicl.2013.06.017
PubMed Web of Science® Google Scholar
14Wang R, Yu S, Alger JR, et al. Multi-delay arterial spin labeling perfusion MRI in moyamoya disease--comparison with CT perfusion imaging. Eur Radiol 2014; 24: 1135-1144.
10.1007/s00330-014-3098-9
PubMed Web of Science® Google Scholar
15Amemiya S, Watanabe Y, Takei N, et al. Arterial transit time-based multidelay combination strategy improves arterial spin labeling cerebral blood flow measurement accuracy in severe steno-occlusive diseases. J Magn Reson Imaging 2022; 55: 178-187.
10.1002/jmri.27823
PubMed Web of Science® Google Scholar
16Dai W, Shankaranarayanan A, Alsop DC. Volumetric measurement of perfusion and arterial transit delay using hadamard encoded continuous arterial spin labeling. Magn Reson Med 2013; 69: 1014-1022.
10.1002/mrm.24335
PubMed Web of Science® Google Scholar
17Positano V, Meloni A, Santarelli MF, et al. Deep learning staging of liver iron content from multiecho MR images. J Magn Reson Imaging 2022.
10.1002/jmri.28300
PubMed Web of Science® Google Scholar
18Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv 2014;1409.1556.
Google Scholar
19Bertleff M, Domsch S, Weingartner S, et al. Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T. NMR Biomed 2017; 30:e3833.
10.1002/nbm.3833
Web of Science® Google Scholar
20Barbieri S, Gurney-Champion OJ, Klaassen R, Thoeny HC. Deep learning how to fit an intravoxel incoherent motion model to diffusion-weighted MRI. Magn Reson Med 2020; 83: 312-321.
10.1002/mrm.27910
PubMed Web of Science® Google Scholar
21Kaandorp MPT, Barbieri S, Klaassen R, et al. Improved unsupervised physics-informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients. Magn Reson Med 2021; 86: 2250-2265.
10.1002/mrm.28852
PubMed Web of Science® Google Scholar
22Zhou XX, Wang XY, Liu EH, et al. An unsupervised deep learning approach for dynamic-exponential Intravoxel incoherent motion MRI modeling and parameter estimation in the liver. J Magn Reson Imaging 2022; 56(3): 848-859.
10.1002/jmri.28074
PubMed Web of Science® Google Scholar
23Gong E, Guo J, Liu J, et al. Deep learning and multi-contrast based denoising for low-SNR arterial spin labeling (ASL) MRI. In Proceedings of SPIE, Medical Imaging. 2020; 11313.
Google Scholar
24Xie D, Li Y, Yang H, et al. Denoising arterial spin labeling perfusion MRI with deep machine learning. Magn Reson Imaging 2020; 68: 95-105.
10.1016/j.mri.2020.01.005
PubMed Web of Science® Google Scholar
25Guo J, Gong E, Fan AP, Goubran M, Khalighi MM, Zaharchuk G. Predicting (15)O-Water PET cerebral blood flow maps from multi-contrast MRI using a deep convolutional neural network with evaluation of training cohort bias. J Cereb Blood Flow Metab 2020; 40: 2240-2253.
10.1177/0271678X19888123
PubMed Web of Science® Google Scholar
26Shyna A, Ushadevi Amma C, Ansamma J, Kesavadas C, Thomas B. Deep-ASL enhancement technique in arterial spin labeling MRI – A novel approach for the error reduction of partial volume correction technique with linear regression algorithm. J Comp Sci 2022; 58: 101546.
10.1016/j.jocs.2021.101546
Web of Science® Google Scholar
27Luciw NJ, Shirzadi Z, Black SE, Goubran M, MacIntosh BJ. Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin-labeled MRI. Magn Reson Med 2022; 88: 406-417.
10.1002/mrm.29193
PubMed Web of Science® Google Scholar
28Fantini S, Sassaroli A, Tgavalekos KT, Kornbluth J. Cerebral blood flow and autoregulation: Current measurement techniques and prospects for noninvasive optical methods. Neurophotonics 2016; 3:031411.
10.1117/1.NPh.3.3.031411
PubMed Web of Science® Google Scholar
29Clevert DA, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). arXiv 2016;1511.07289.
Google Scholar
30Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv 2017;1412.6980.
Google Scholar
31He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. arXiv 2015;1502.01852.
Google Scholar
32Dai W, Garcia D, de Bazelaire C, Alsop DC. Continuous flow-driven inversion for arterial spin labeling using pulsed radio frequency and gradient fields. Magn Reson Med 2008; 60: 1488-1497.
10.1002/mrm.21790
CAS PubMed Web of Science® Google Scholar
33Donahue MJ, Achten E, Cogswell PM, et al. Consensus statement on current and emerging methods for the diagnosis and evaluation of cerebrovascular disease. J Cereb Blood Flow Metab 2018; 38: 1391-1417.
10.1177/0271678X17721830
PubMed Web of Science® Google Scholar
34Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geosci Model Dev 2014; 7: 1247-1250.
10.5194/gmd-7-1247-2014
Web of Science® Google Scholar
35MacIntosh BJ, Lindsay AC, Kylintireas I, et al. Multiple inflow pulsed arterial spin-labeling reveals delays in the arterial arrival time in minor stroke and transient ischemic attack. AJNR Am J Neuroradiol 2010; 31: 1892-1894.
10.3174/ajnr.A2008
CAS PubMed Web of Science® Google Scholar
36Fujiwara Y, Matsuda T, Kanamoto M, et al. Comparison of long-labeled pseudo-continuous arterial spin labeling (ASL) features between young and elderly adults: Special reference to parameter selection. Acta Radiol 2017; 58: 84-90.
10.1177/0284185116632387
PubMed Web of Science® Google Scholar
37Wang J, Alsop DC, Li L, et al. Comparison of quantitative perfusion imaging using arterial spin labeling at 1.5 and 4.0 tesla. Magn Reson Med 2002; 48: 242-254.
10.1002/mrm.10211
CAS PubMed Web of Science® Google Scholar
38Matsuda T, Kimura H, Kabasawa H, Kanamoto M. Three-dimensional arterial spin labeling imaging with a DANTE preparation pulse. Magn Reson Imaging 2018; 49: 131-137.
10.1016/j.mri.2018.02.001
CAS PubMed Web of Science® Google Scholar
39Fujiwara Y, Kimura H, Ishida S, et al. Intravascular signal suppression and microvascular signal mapping using delays alternating with nutation for tailored excitation (DANTE) pulse for arterial spin labeling perfusion imaging. Magma 2020; 33: 367-376.
10.1007/s10334-019-00785-9
PubMed Google Scholar
40Chappell MA, MacIntosh BJ, Donahue MJ, Gunther M, Jezzard P, Woolrich MW. Separation of macrovascular signal in multi-inversion time arterial spin labelling MRI. Magn Reson Med 2010; 63: 1357-1365.
10.1002/mrm.22320
PubMed Web of Science® Google Scholar

Citing Literature

Volume57, Issue5

May 2023

Pages 1477-1489

Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi-Delay Arterial Spin Labeling MRI Using a Simulation-Based Supervised Deep Neural Network

Abstract

Background

Purpose

Study Type

Population

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Supporting Information

References

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi-Delay Arterial Spin Labeling MRI Using a Simulation-Based Supervised Deep Neural Network

Abstract

Background

Purpose

Study Type

Population

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Supporting Information

References

Citing Literature

References

Related

Information