AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance

被引:3
作者
Scannell, Cian M. [1 ,2 ]
Alskaf, Ebraham [1 ]
Sharrack, Noor [3 ]
Razavi, Reza [1 ]
Ourselin, Sebastien [1 ]
Young, Alistair A. [1 ]
Plein, Sven [1 ,3 ]
Chiribiri, Amedeo [1 ]
机构
[1] Kings Coll London, St Thomas Hosp, Sch Biomed Engn & Imaging Sci, 4th Floor Lambeth Wing, London SE1 7EH, England
[2] Eindhoven Univ Technol, Dept Biomed Engn, Groene Loper 5, NL-5612 Eindhoven, Netherlands
[3] Univ Leeds, Leeds Inst Cardiovasc & Metab Med, Dept Biomed Imaging Sci, Clarendon Way, Leeds LS2 9JT, England
来源
EUROPEAN HEART JOURNAL - DIGITAL HEALTH | 2023年 / 4卷 / 01期
基金
英国惠康基金; 英国工程与自然科学研究理事会;
关键词
Artificial intelligence; Arterial input function; Quantitative myocardial perfusion; Cardiac magnetic resonance; EMISSION COMPUTED-TOMOGRAPHY; MYOCARDIAL-PERFUSION; CE-MARC; DISEASE; HEART; QUANTIFICATION; COUNCIL; RESERVE;
D O I
10.1093/ehjdh/ztac074
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
AimsOne of the major challenges in the quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) is the estimation of the arterial input function (AIF). This is due to the non-linear relationship between the concentration of gadolinium and the MR signal, which leads to signal saturation. In this work, we show that a deep learning model can be trained to predict the unsaturated AIF from standard images, using the reference dual-sequence acquisition AIFs (DS-AIFs) for training.Methods and resultsA 1D U-Net was trained, to take the saturated AIF from the standard images as input and predict the unsaturated AIF, using the data from 201 patients from centre 1 and a test set comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n = 44). Fully-automated MBF was compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis. There was no statistical difference between the MBF quantified with the DS-AIF [2.77 mL/min/g (1.08)] and predicted with the AI-AIF (2.79 mL/min/g (1.08), P = 0.33. Bland-Altman analysis shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF (bias of -0.11 mL/min/g). Additionally, the MBF diagnosis classification of the AI-AIF matched the DS-AIF in 669/704 (95%) of myocardial segments.ConclusionQuantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF. Graphical Abstract
引用
收藏
页码:12 / 21
页数:10
相关论文
共 47 条
[1]   Comparison of the Diagnostic Performance of Four Quantitative Myocardial Perfusion Estimation Methods Used in Cardiac MR Imaging: CE-MARC Substudy [J].
Biglands, John D. ;
Magee, Derek R. ;
Sourbron, Steven P. ;
Plein, Sven ;
Greenwood, John P. ;
Radjenovic, Aleksandra .
RADIOLOGY, 2015, 275 (02) :393-402
[2]   Sensitivity of quantitative myocardial dynamic contrast-enhanced MRI to saturation pulse efficiency, noise and t1 measurement error: Comparison of nonlinearity correction methods [J].
Broadbent, David A. ;
Biglands, John D. ;
Ripley, David P. ;
Higgins, David M. ;
Greenwood, John P. ;
Plein, Sven ;
Buckley, David L. .
MAGNETIC RESONANCE IN MEDICINE, 2016, 75 (03) :1290-1300
[3]   Fully automated, inline quantification of myocardial blood flow with cardiovascular magnetic resonance: repeatability of measurements in healthy subjects [J].
Brown, Louise A. E. ;
Onciul, Sebastian C. ;
Broadbent, David A. ;
Johnson, Kerryanne ;
Fent, Graham J. ;
Foley, James R. J. ;
Garg, Pankaj ;
Chew, Pei G. ;
Knott, Kristopher ;
Dall'Armellina, Erica ;
Swoboda, Peter P. ;
Xue, Hui ;
Greenwood, John P. ;
Moon, James C. ;
Kellman, Peter ;
Plein, Sven .
JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE, 2018, 20
[4]   Theory-based signal calibration with single-point T1 measurements for first-pass quantitative perfusion MRI studies [J].
Cernicanu, Alexandru ;
Axel, Leon .
ACADEMIC RADIOLOGY, 2006, 13 (06) :686-693
[5]   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 [J].
Cerqueira, MD ;
Weissman, NJ ;
Dilsizian, V ;
Jacobs, AK ;
Kaul, S ;
Laskey, WK ;
Pennell, DJ ;
Rumberger, JA ;
Ryan, T ;
Verani, MS .
CIRCULATION, 2002, 105 (04) :539-542
[6]  
Doeblin P., 2022, Front Cardiovasc Med, V9, P7
[7]  
El-Rewaidy H, 2021, Arxiv, DOI arXiv:2104.00143
[8]   Rapid Cardiovascular Magnetic Resonance for Ischemic Heart Disease Investigation (RAPID-IHD) [J].
Foley, James R. J. ;
Richmond, Caroline ;
Fent, Graham J. ;
Bissell, Malenka ;
Levelt, Eylem ;
'armellina, Erica Dall ;
Swoboda, Peter P. ;
Plein, Sven ;
Greenwood, John P. .
JACC-CARDIOVASCULAR IMAGING, 2020, 13 (07) :1632-1634
[9]   Accurate assessment of the arterial input function during high-dose myocardial perfusion cardiovascular magnetic resonance [J].
Gatehouse, PD ;
Elkington, AG ;
Ablitt, NA ;
Yang, GZ ;
Pennell, DJ ;
Firmin, DN .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2004, 20 (01) :39-45
[10]   Effect of Care Guided by Cardiovascular Magnetic Resonance, Myocardial Perfusion Scintigraphy, or NICE Guidelines on Subsequent Unnecessary Angiography Rates The CE-MARC 2 Randomized Clinical Trial [J].
Greenwood, John P. ;
Ripley, David P. ;
Berry, Colin ;
McCann, Gerry P. ;
Plein, Sven ;
Bucciarelli-Ducci, Chiara ;
Dall'Armellina, Erica ;
Prasad, Abhiram ;
Bijsterveld, Petra ;
Foley, James R. ;
Mangion, Kenneth ;
Sculpher, Mark ;
Walker, Simon ;
Everett, Colin C. ;
Cairns, David A. ;
Sharples, Linda D. ;
Brown, Julia M. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2016, 316 (10) :1051-1060