Myocardial blood flow (MBF) provides important diagnostic information for myocardial ischemia. However, dynamic computed tomography perfusion (CTP) needed for MBF involves multiple exposures, leading to high radiation doses.
Objectives:
This study investigated synthesizing MBF from simulated static myocardial CTP to explore dose reduction potential, bypassing the traditional dynamic input function.
Methods:
The study included 253 subjects with intermediate-to-high pretest probabilities of obstructive coronary artery disease (CAD). MBF was reconstructed from dynamic myocardial CTP. A deep neural network (DNN) converted simulated static CTP into synthetic MBF. Beyond the usual image quality evaluation, the synthetic MBF was segmented and a clinical functional assessment was conducted, with quantitative analysis for consistency and correlation.
Results:
Synthetic MBF closely matched the referenced MBF, with an average structure similarity (SSIM) of 0.87. ROC analysis of ischemic segments showed an area under curve (AUC) of 0.915 for synthetic MBF. This method can theoretically reduce the radiation dose for MBF significantly, provided satisfactory static CTP is obtained, reducing reliance on high time resolution of dynamic CTP.
Conclusions:
The proposed method is feasible, with satisfactory clinical functionality of synthetic MBF. Further investigation and validation are needed to confirm actual dose reduction in clinical settings.
KnuutiJWijnsWSarasteA, et al.2019 ESC guidelines for the diagnosis and management of chronic coronary syndromes: the Task Force for the diagnosis and management of chronic coronary syndromes of the European Society of Cardiology (ESC). European Heart Journal2019; 41: 407–477.
2.
BenjaminEJViraniSSCallawayCW, et al.Heart disease and stroke statistics-2018 update: a report from the American Heart Association. Circulation2018; 137: e67–e492.
3.
PijlsNHDe BruyneBPeelsK, et al.Measurement of fractional flow reserve to assess the functional severity of coronary-artery stenoses. N Engl J Med1996; 334: 1703–1708.
4.
KnuutiJBalloHJuarez-OrozcoLE, et al.The performance of non-invasive tests to rule-in and rule-out significant coronary artery stenosis in patients with stable angina: a meta-analysis focused on post-test disease probability. Eur Heart J2018; 39: 3322–3330.
5.
KoBSCameronJDMeredithIT, et al.Computed tomography stress myocardial perfusion imaging in patients considered for revascularization: a comparison with fractional flow reserve. Eur Heart J2012; 33: 67–77.
6.
BambergFMarcusRPBeckerA, et al.Dynamic myocardial CT perfusion imaging for evaluation of myocardial ischemia as determined by MR imaging. JACC Cardiovasc Imaging2014; 7: 267–277.
7.
LiYDaiXLuZ, et al.Diagnostic performance of quantitative, semi-quantitative, and visual analysis of dynamic CT myocardial perfusion imaging: a validation study with invasive fractional flow reserve. Eur Radiol2021; 31: 525–534.
8.
LiYYuMDaiX, et al.Detection of hemodynamically significant coronary stenosis: cT myocardial perfusion versus machine learning CT fractional flow reserve. Radiology2019; 293: 305–314.
9.
PatelARBambergFBranchK, et al.Society of cardiovascular computed tomography expert consensus document on myocardial computed tomography perfusion imaging. J Cardiovasc Comput Tomogr2020; 14: 87–100.
10.
TanabeYKurataAMatsudaT, et al.Computed tomographic evaluation of myocardial ischemia. Jpn J Radiol2020; 38: 411–433.
11.
KurataAMochizukiTKoyamaY, et al.Myocardial perfusion imaging using adenosine triphosphate stress multi-slice spiral computed tomography: alternative to stress myocardial perfusion scintigraphy. Circ J2005; 69: 550–557.
12.
BambergFKlotzEFlohrT, et al.Dynamic myocardial stress perfusion imaging using fast dual-source CT with alternating table positions: initial experience. Eur Radiol2010; 20: 1168–1173.
13.
HashimotoFKakimotoAOtaN, et al.Automated segmentation of 2D low-dose CT images of the psoas-major muscle using deep convolutional neural networks. Radiol Phys Technol2019; 12: 210–215.
14.
HuangZChenZQuanG, et al.Deep Cascade Residual Networks (DCRNs): optimizing an encoder–decoder convolutional neural network for low-dose CT imaging. IEEE Trans Radiat Plasma Med Sci2022; 6: 829–840.
15.
HuangZLiuZHeP, et al.Segmentation-guided denoising network for low-dose CT imaging. Comput Methods Programs Biomed2022; 227: 107199.
16.
RonnebergerOFischerPBroxT. U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, proceedings, Part III. Springer, 2015, pp.234–241.
17.
IsolaPZhuJ-YZhouT,et al.Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, pp.1125–1134.
18.
HuangZWuYFuF, et al.Parametric image generation with the uEXPLORER total-body PET/CT system through deep learning. Eur J Nucl Med Mol Imaging2022; 49: 2482–2492.
19.
SikkaAPeriSVBathulaDR. MRI To FDG-PET: cross-modal synthesis using 3D U-net for multi-modal Alzheimer’s classification. In: Simulation and Synthesis in Medical Imaging: Third International Workshop, SASHIMI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings 3. Springer, 2018, pp.80–89.
20.
WangHWuYHuangZ, et al.Deep learning-based dynamic PET parametric K(i) image generation from lung static PET. Eur Radiol.2023; 33(4): 2676–2685.
21.
McCommisKSGoldsteinTAAbendscheinDR, et al.Roles of myocardial blood volume and flow in coronary artery disease: an experimental MRI study at rest and during hyperemia. Eur Radiol2010; 20: 2005–2012.
22.
ChenZZengDHuangZ, et al.Temporal feature prior-aided separated reconstruction method for low-dose dynamic myocardial perfusion computed tomography. Phys Med Biol2021; 66: 045012.
23.
CuiJGongKGuoN, et al.PET Image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging2019; 46: 2780–2789.
24.
GongKCatanaCQiJ,et al.PET Image reconstruction using deep image prior. IEEE Trans Med Imaging2019; 38: 1655–1665.
25.
GongKGuanJLiuCC,et al.PET Image denoising using a deep neural network through fine tuning. IEEE Trans Radiat Plasma Med Sci2019; 3: 153–161.
26.
HuangZLiuXWangR, et al.Considering anatomical prior information for low-dose CT image enhancement using attribute-augmented wasserstein generative adversarial networks. Neurocomputing2021; 428: 104–115.
27.
HuangZLiuXWangR, et al.Learning a deep CNN denoising approach using anatomical prior information implemented with attention mechanism for low-dose CT imaging on clinical patient data from multiple anatomical sites. IEEE J Biomed Health Inform2021; 25: 3416–3427.
28.
UlyanovDVedaldiALempitskyV. Deep image prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018, pp.9446–9454.
29.
Huynh-ThuQGhanbariM. Scope of validity of PSNR in image/video quality assessment. Electronics Letters2008; 44: 800–801.
30.
WangZBovikACSheikhHR,et al.Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process2004; 13: 600–612.
31.
BambergFBeckerASchwarzF, et al.Detection of hemodynamically significant coronary artery stenosis: incremental diagnostic value of dynamic CT-based myocardial perfusion imaging. Radiology2011; 260: 689–698.
32.
RossiAWraggAKlotzE, et al.Dynamic Computed Tomography Myocardial Perfusion Imaging: Comparison of Clinical Analysis Methods for the Detection of Vessel-Specific Ischemia. Circ Cardiovasc Imaging2017; 10(4): e005505.
33.
KonoAKCoenenALubbersM, et al.Relative myocardial blood flow by dynamic computed tomographic perfusion imaging predicts hemodynamic significance of coronary stenosis better than absolute blood flow. Invest Radiol2014; 49: 801–807.
34.
DanadISzymonifkaJSchulman-MarcusJ,et al.Static and dynamic assessment of myocardial perfusion by computed tomography. Eur Heart J Cardiovasc Imaging2016; 17: 836–844.
35.
CerqueiraMDWeissmanNJDilsizianV, et al.Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the cardiac imaging committee of the council on clinical cardiology of the American Heart Association. Circulation2002; 105: 539–542.
36.
BlandJMAltmanDG. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet1986; 1: 307–310.
37.
SliwickaOSechopoulosIBaggianoA, et al.Dynamic myocardial CT perfusion imaging-state of the art. Eur Radiol2023; 33: 5509–5525.
38.
van AssenMPelgrimGJSlagerE, et al.Low CT temporal sampling rates result in a substantial underestimation of myocardial blood flow measurements. Int J Cardiovasc Imaging2019; 35: 539–547.
39.
YiYXuCWuW, et al.Low-dose CT perfusion with combined use of CTP and CTP-derived coronary CT angiography at 70 kVp: validation with invasive fractional flow reserve. Eur Radiol2021; 31: 1119–1129.
40.
MorikawaTYoshidaKTanabeY, et al.Direct comparison between static CTP and dynamic CTP for detecting obstructive coronary artery disease. J Cardiovasc Comput Tomogr2023; 17: S30.
41.
MaiWSuranJNCáceresAV,et al.Comparison between bolus tracking and timing-bolus techniques for renal computed tomographic angiography in normal cats. Vet Radiol Ultrasound2013; 54: 343–350.
