Abstract
Objectives
This study was conducted to establish and validate a non-contrast T1 map–based radiomic nomogram for predicting major adverse cardiac events (MACEs) in patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI).
Methods
This retrospective study included 157 consecutive patients (training sets, 109 patients; test sets, 48 patients) with acute STEMI undergoing PCI. An open-source radiomics software was used to segment the myocardium on the non-contrast T1 mapping and extract features. A radiomic signature was constructed to predict MACEs using the least absolute shrinkage and selection operator method. The performance of the radiomic nomogram for predicting MACEs in both the training and test sets was evaluated by its discrimination, calibration, and clinical usefulness.
Results
The radiomic signature showed a good prognostic ability in the training sets with an AUC of 0.94 (95% CI, 0.86 to 1.00) and F1 score of 0.71, which was confirmed in the test sets with an AUC of 0.90 (95% CI, 0.74 to 1.00) and F1 score of 0.62. The nomogram consisting of the radiomic scores and cardiac troponin I showed good discrimination ability in the training and test sets with AUCs of 0.96 (95% CI, 0.91 to 1.00; F1 score, 0.71) and 0.94 (95% CI, 0.83 to 1.00; F1 score, 0.70), respectively.
Conclusions
The non-contrast T1 map–based radiomic nomogram is a useful tool for the prediction of MACEs in patients with acute STEMI undergoing PCI that can assist clinicians for optimised risk stratification of individual patients.
Key Points
• Radiomic signature improved MACE prediction in acute STEMI patients.
• T1 mapping–derived radiomic signature outperformed conventional cardiac MRI parameters in predicting MACEs in acute STEMI patients.
• The non-contrast T1 mapping–based radiomic nomogram can be used for prediction of MACEs and improvement of risk stratification in acute STEMI.
Similar content being viewed by others
Abbreviations
- AAR:
-
Area at risk
- AUC:
-
Area under the curve
- CI:
-
Confidence interval
- CMR:
-
Cardiac magnetic resonance
- cTnI:
-
Cardiac troponin I
- DCA:
-
Decision curve analysis
- GBCA:
-
Gadolinium-based contrast agent
- IQR:
-
Interquartile range
- IS:
-
Infarct size
- LASSO:
-
Least absolute shrinkage and selection operator
- LGE:
-
Late gadolinium enhancement
- LV:
-
Left ventricle
- LVEF:
-
Left ventricular ejection fraction
- MACE:
-
Major adverse cardiovascular event
- MI:
-
Myocardial infarction
- MOLLI:
-
Modified look-locker inversion recovery
- MVO:
-
Microvascular obstruction
- PCI:
-
Percutaneous coronary intervention
- Rad-score:
-
Radiomic score
- ROC:
-
Receiver operator characteristic
- ROI:
-
Region of interest
- STEMI:
-
ST-segment elevation myocardial infarction
References
Rodriguez-Palomares JF, Gavara J, Ferreira-González I et al (2019) Prognostic value of initial left ventricular remodeling in patients with reperfused STEMI. JACC Cardiovasc Imaging 12:2445–2456
Roger VL, Go AS, Lloyd-Jones DM et al (2011) Heart disease and stroke statistics--2011 update: a report from the American Heart Association. Circulation 123:e18–e209
Izquierdo M, Ruiz-Granell R, Bonanad C et al (2013) Value of early cardiovascular magnetic resonance for the prediction of adverse arrhythmic cardiac events after a first noncomplicated ST-segment-elevation myocardial infarction. Circ Cardiovasc Imaging 6:755–761
Eitel I, de Waha S, Wöhrle J et al (2014) Comprehensive prognosis assessment by CMR imaging after ST-segment elevation myocardial infarction. J Am Coll Cardiol 64:1217–1226
Steg PG, James SK, Atar D et al (2012) ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation. Eur Heart J 33:2569–2619
O’Gara PT, Kushner FG, Ascheim DD et al (2013) 2013 ACCF/AHA guideline for the management of ST-elevation myocardial infarction: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. J Am Coll Cardiol 61:e78–e140
Symons R, Pontone G, Schwitter J et al (2018) Long-term incremental prognostic value of cardiovascular magnetic resonance after ST-segment elevation myocardial infarction: a study of the collaborative registry on CMR in STEMI. JACC Cardiovasc Imaging 11:813–825
Carrick D, Haig C, Rauhalammi S et al (2016) Prognostic significance of infarct core pathology revealed by quantitative non-contrast in comparison with contrast cardiac magnetic resonance imaging in reperfused ST-elevation myocardial infarction survivors. Eur Heart J 37:1044–1059
Ugander M, Oki AJ, Hsu L-Y et al (2012) Extracellular volume imaging by magnetic resonance imaging provides insights into overt and sub-clinical myocardial pathology. Eur Heart J 33:1268–1278
Carrick D, Haig C, Rauhalammi S et al (2015) Pathophysiology of LV remodeling in survivors of STEMI: inflammation, remote myocardium, and prognosis. JACC Cardiovasc Imaging 8:779–789
Reinstadler SJ, Stiermaier T, Liebetrau J et al (2018) Prognostic significance of remote myocardium alterations assessed by quantitative noncontrast T1 mapping in ST-segment elevation myocardial infarction. JACC Cardiovasc Imaging 11:411–419
Yip SS, Aerts HJWL (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166
Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762
Nie P, Yang G, Wang Z et al (2019) A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma. Eur Radiol 30:1274–1284
Ji G-W, Zhu F-P, Zhang Y-D et al (2019) A radiomics approach to predict lymph node metastasis and clinical outcome of intrahepatic cholangiocarcinoma. Eur Radiol 29:3725–3735
Wang Y, Liu W, Yu Y et al (2019) CT radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer. Eur Radiol 30:976–986
Larroza A, Materka A, López-Lereu MP, Monmeneu JV, Bodí V, Moratal D (2017) Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging. Eur J Radiol 92:78–83
Baessler B, Mannil M, Oebel S, Maintz D, Alkadhi H, Manka R (2018) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 286:103–112
Schulz-Menger J, Bluemke DA, Bremerich J et al (2013) Standardized image interpretation and post processing in cardiovascular magnetic resonance: Society for Cardiovascular Magnetic Resonance (SCMR) board of trustees task force on standardized post processing. J Cardiovasc Magn Reson 15:35
Bondarenko O, Beek AM, Hofman MBM et al (2005) Standardizing the definition of hyperenhancement in the quantitative assessment of infarct size and myocardial viability using delayed contrast-enhanced CMR. J Cardiovasc Magn Reson 7:481–485
Puntmann VO, Peker E, Chandrashekhar Y, Nagel E (2016) T1 Mapping in characterizing myocardial disease: a comprehensive review. Circ Res 119:277–299
Szczypinski PM, Strzelecki M, Materka A, Klepaczko A (2009) MaZda--a software package for image texture analysis. Comput Methods Programs Biomed 94:66–76
Strzelecki M, Szczypinski P, Materka A, Klepaczko A (2013) A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl Instrum Methods Phys Res Sect A 702:137–140
Benjamini Y, Hochberg Y (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc Ser B Methodol 57:289–300
Dastidar AG, Rodrigues JCL, Baritussio A, Bucciarelli-Ducci C (2016) MRI in the assessment of ischaemic heart disease. Heart Br Card Soc 102:239–252
Stone GW, Selker HP, Thiele H et al (2016) Relationship between infarct size and outcomes following primary PCI: patient-level analysis from 10 randomized trials. J Am Coll Cardiol 67:1674–1683
Reinstadler SJ, Thiele H, Eitel I (2015) Risk stratification by cardiac magnetic resonance imaging after ST-elevation myocardial infarction. Curr Opin Cardiol 30:681–689
Messroghli DR, Moon JC, Ferreira VM et al (2017) Clinical recommendations for cardiovascular magnetic resonance mapping of T1, T2, T2* and extracellular volume: a consensus statement by the Society for Cardiovascular Magnetic Resonance (SCMR) endorsed by the European Association for Cardiovascular Imaging (EACVI). J Cardiovasc Magn Reson 19:75
Ide S, Riesenkampff E, Chiasson DA et al (2017) Histological validation of cardiovascular magnetic resonance T1 mapping markers of myocardial fibrosis in paediatric heart transplant recipients. J Cardiovasc Magn Reson 19:10
Diao KY, Yang ZG, Xu HY et al (2016) Histologic validation of myocardial fibrosis measured by T1 mapping: a systematic review and meta-analysis. J Cardiovasc Magn Reson 18:92
Aerts HJWL (2016) The potential of radiomic-based phenotyping in precision medicine: a review. JAMA Oncol 2:1636–1642
Castellano G, Bonilha L, Li LM, Cendes F (2004) Texture analysis of medical images. Clin Radiol 59:1061–1069
Kanda T, Fukusato T, Matsuda M et al (2015) Gadolinium-based contrast agent accumulates in the brain even in subjects without severe renal dysfunction: evaluation of autopsy brain specimens with inductively coupled plasma mass spectroscopy. Radiology 276:228–232
Grobner T, Prischl FC (2007) Gadolinium and nephrogenic systemic fibrosis. Kidney Int 72:260–264
Hammer-Hansen S, Ugander M, Hsu LY et al (2014) Distinction of salvaged and infarcted myocardium within the ischaemic area-at-risk with T2 mapping. Eur Heart J Cardiovasc Imaging 15:1048–1053
Vabalas A, Gowen E, Poliakoff E, Casson AJ (2019) Machine learning algorithm validation with a limited sample size. PLoS One 14:e0224365
Ogundimu EO, Altman DG, Collins GS (2016) Adequate sample size for developing prediction models is not simply related to events per variable. J Clin Epidemiol 76:175–182
Teixeira T, Hafyane T, Stikov N, Greiser A, Friedrich MG, Akdeniz C (2016) Comparison of different cardiovascular magnetic resonance sequences for native myocardial T1 mapping at 3T. J Cardiovasc Magn Reson 18:65
Acknowledgements
We thank Yan Guo for her expert opinion and helpful comments.
Funding
This study has received funding from the 345 Talent Project in Shengjing Hospital of China Medical University.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Guarantor
The scientific guarantor of this publication is Yang Hou.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
Yan Guo kindly provided statistical advice for this manuscript.
Informed consent
Written informed consent was waived by the institutional review board.
Ethical approval
Institutional review board approval was obtained.
Methodology
• retrospective
• Diagnostic or prognostic study / observational
• performed at one institution
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
ESM 1
(DOCX 487 kb)
Rights and permissions
About this article
Cite this article
Ma, Q., Ma, Y., Wang, X. et al. A radiomic nomogram for prediction of major adverse cardiac events in ST-segment elevation myocardial infarction. Eur Radiol 31, 1140–1150 (2021). https://doi.org/10.1007/s00330-020-07176-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-020-07176-y