TY - JOUR
T1 - Predicting PET cerebrovascular reserve with deep learning by using baseline MRI
T2 - A pilot investigation of a drug-free brain stress test
AU - Chen, David Y.T.
AU - Ishii, Yosuke
AU - Fan, Audrey P.
AU - Guo, Jia
AU - Zhao, Moss Y.
AU - Steinberg, Gary K.
AU - Zaharchuk, Greg
N1 - Funding Information:
Supported by the National Institutes of Health (R01-EB025220) and GE Healthcare.
Publisher Copyright:
© RSNA, 2020
PY - 2020/9
Y1 - 2020/9
N2 - Background: Cerebrovascular reserve (CVR) may be measured by using an acetazolamide test to clinically evaluate patients with cerebrovascular disease. However, acetazolamide use may be contraindicated and/or undesirable in certain clinical settings. Purpose: To predict CVR images generated from acetazolamide vasodilation with a deep learning network by using only images before acetazolamide administration. Materials and Methods: Simultaneous oxygen 15 (15O)–labeled water PET/MRI before and after acetazolamide injection were retrospectively analyzed for patients with Moyamoya disease and healthy control participants from April 2017 to May 2019. Inputs to deep learning models were perfusion-based images (arterial spin labeling [ASL]), structural scans (T2 fluid-attenuated inversion-recovery, T1), and brain location. Two models, that is, 15O-labeled water PET cerebral blood flow (CBF) and MRI (PET-plus-MRI model) before acetazolamide administration and only MRI (MRI-only model) before acetazolamide administration, were trained and tested with sixfold cross-validation. The models learned to predict a voxelwise relative CBF change (r∆CBF) map by using r∆CBF measured with PET due to acetazolamide as ground truth. Quantitative analysis included image quality metrics (peak signal-to-noise ratio, root mean square error, and structural similarity index), as well as comparison between the various methods by using correlation and Bland-Altman analyses. Identification of vascular territories with impaired r∆CBF was evaluated by using receiver operating characteristic metrics. Results: Thirty-six participants were included: 24 patients with Moyamoya disease (mean age 6 standard deviation, 41 years 6 12; 17 women) and 12 age-matched healthy control participants (mean age, 39 years 6 16; nine women). The r∆CBF maps predicted by both deep learning models demonstrated better image quality metrics than did ASL (all P , .001 in patients) and higher correlation coefficient with PET than with ASL (PET-plus-MRI model, 0.704; MRI-only model, 0.690 vs ASL, 0.432; both P , .001 in patients). Both models also achieved high diagnostic performance in identifying territories with impaired r∆CBF (area under receiver operating characteristic curve, 0.95 for PET-plus-MRI model [95% confidence interval: 0.90, 0.99] and 0.95 for MRI-only model [95% confidence interval: 0.91, 0.98]). Conclusion: By using only images before acetazolamide administration, PET-plus-MRI and MRI-only deep learning models predicted cerebrovascular reserve images without the need for vasodilator injection.
AB - Background: Cerebrovascular reserve (CVR) may be measured by using an acetazolamide test to clinically evaluate patients with cerebrovascular disease. However, acetazolamide use may be contraindicated and/or undesirable in certain clinical settings. Purpose: To predict CVR images generated from acetazolamide vasodilation with a deep learning network by using only images before acetazolamide administration. Materials and Methods: Simultaneous oxygen 15 (15O)–labeled water PET/MRI before and after acetazolamide injection were retrospectively analyzed for patients with Moyamoya disease and healthy control participants from April 2017 to May 2019. Inputs to deep learning models were perfusion-based images (arterial spin labeling [ASL]), structural scans (T2 fluid-attenuated inversion-recovery, T1), and brain location. Two models, that is, 15O-labeled water PET cerebral blood flow (CBF) and MRI (PET-plus-MRI model) before acetazolamide administration and only MRI (MRI-only model) before acetazolamide administration, were trained and tested with sixfold cross-validation. The models learned to predict a voxelwise relative CBF change (r∆CBF) map by using r∆CBF measured with PET due to acetazolamide as ground truth. Quantitative analysis included image quality metrics (peak signal-to-noise ratio, root mean square error, and structural similarity index), as well as comparison between the various methods by using correlation and Bland-Altman analyses. Identification of vascular territories with impaired r∆CBF was evaluated by using receiver operating characteristic metrics. Results: Thirty-six participants were included: 24 patients with Moyamoya disease (mean age 6 standard deviation, 41 years 6 12; 17 women) and 12 age-matched healthy control participants (mean age, 39 years 6 16; nine women). The r∆CBF maps predicted by both deep learning models demonstrated better image quality metrics than did ASL (all P , .001 in patients) and higher correlation coefficient with PET than with ASL (PET-plus-MRI model, 0.704; MRI-only model, 0.690 vs ASL, 0.432; both P , .001 in patients). Both models also achieved high diagnostic performance in identifying territories with impaired r∆CBF (area under receiver operating characteristic curve, 0.95 for PET-plus-MRI model [95% confidence interval: 0.90, 0.99] and 0.95 for MRI-only model [95% confidence interval: 0.91, 0.98]). Conclusion: By using only images before acetazolamide administration, PET-plus-MRI and MRI-only deep learning models predicted cerebrovascular reserve images without the need for vasodilator injection.
UR - http://www.scopus.com/inward/record.url?scp=85089711452&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089711452&partnerID=8YFLogxK
U2 - 10.1148/radiol.2020192793
DO - 10.1148/radiol.2020192793
M3 - Article
C2 - 32662761
AN - SCOPUS:85089711452
SN - 0033-8419
VL - 296
SP - 627
EP - 637
JO - Radiology
JF - Radiology
IS - 3
ER -