Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Radiomics of Non-Contrast-Enhanced T1 Mapping: Diagnostic and Predictive Performance for Myocardial Injury in Acute ST-Segment-Elevation Myocardial Infarction

  • Quanmei Ma (Department of Radiology, Shengjing Hospital of China Medical University) ;
  • Yue Ma (Department of Radiology, Shengjing Hospital of China Medical University) ;
  • Tongtong Yu (Department of Cardiology, Shengjing Hospital of China Medical University) ;
  • Zhaoqing Sun (Department of Cardiology, Shengjing Hospital of China Medical University) ;
  • Yang Hou (Department of Radiology, Shengjing Hospital of China Medical University)
  • Received : 2019.12.23
  • Accepted : 2020.08.16
  • Published : 2021.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To evaluate the feasibility of texture analysis on non-contrast-enhanced T1 maps of cardiac magnetic resonance (CMR) imaging for the diagnosis of myocardial injury in acute myocardial infarction (MI). Materials and Methods: This study included 68 patients (57 males and 11 females; mean age, 55.7 ± 10.5 years) with acute ST-segment-elevation MI who had undergone 3T CMR after a percutaneous coronary intervention. Forty patients of them also underwent a 6-month follow-up CMR. The CMR protocol included T2-weighted imaging, T1 mapping, rest first-pass perfusion, and late gadolinium enhancement. Radiomics features were extracted from the T1 maps using open-source software. Radiomics signatures were constructed with the selected strongest features to evaluate the myocardial injury severity and predict the recovery of left ventricular (LV) longitudinal systolic myocardial contractility. Results: A total of 1088 segments of the acute CMR images were analyzed; 103 (9.5%) segments showed microvascular obstruction (MVO), and 557 (51.2%) segments showed MI. A total of 640 segments were included in the 6-month follow-up analysis, of which 160 (25.0%) segments showed favorable recovery of LV longitudinal systolic myocardial contractility. Combined radiomics signature and T1 values resulted in a higher diagnostic performance for MVO compared to T1 values alone (area under the curve [AUC] in the training set; 0.88, 0.72, p = 0.031: AUC in the test set; 0.86, 0.71, p = 0.002). Combined radiomics signature and T1 values also provided a higher predictive value for LV longitudinal systolic myocardial contractility recovery compared to T1 values (AUC in the training set; 0.76, 0.55, p < 0.001: AUC in the test set; 0.77, 0.60, p < 0.001). Conclusion: The combination of radiomics of non-contrast-enhanced T1 mapping and T1 values could provide higher diagnostic accuracy for MVO. Radiomics also provides incremental value in the prediction of LV longitudinal systolic myocardial contractility at six months.

Keywords

Acknowledgement

We thank Yan Guo and Jianqing Sun for their expert opinion and helpful comments.

References

  1. Symons R, Masci PG, Goetschalckx K, Doulaptsis K, Janssens S, Bogaert J. Effect of infarct severity on regional and global left ventricular remodeling in patients with successfully reperfused ST segment elevation myocardial infarction. Radiology 2015;274:93-102
  2. Yamashita Y, Shiomi H, Morimoto T, Yaku H, Furukawa Y, Nakagawa Y, et al. Cardiac and noncardiac causes of long-term mortality in ST-segment-elevation acute myocardial infarction patients who underwent primary percutaneous coronary intervention. Circ Cardiovasc Qual Outcomes 2017;10:e002790
  3. Dagres N, Hindricks G. Risk stratification after myocardial infarction: is left ventricular ejection fraction enough to prevent sudden cardiac death? Eur Heart J 2013;34:1964-1971
  4. Baritussio A, Scatteia A, Bucciarelli-Ducci C. Role of cardiovascular magnetic resonance in acute and chronic ischemic heart disease. INT J Cardiovasc Imaging 2018;34:67-80
  5. Masci PG, Pavon AG, Pontone G, Symons R, Lorenzoni V, Francone M, et al. Early or deferred cardiovascular magnetic resonance after ST-segment-elevation myocardial infarction for effective risk stratification. Eur Heart J Cardiovasc Imaging 2020;21:632-639
  6. Ibanez B, Aletras AH, Arai AE, Arheden H, Bax J, Berry C, et al. Cardiac MRI endpoints in myocardial infarction experimental and clinical trials: JACC scientific expert panel. J Am Coll Cardiol 2019;74:238-256
  7. Larroza A, Bodi V, Moratal D. Texture analysis in magnetic resonance imaging: review and considerations for future applications. In: Constantinides C, ed. Assessment of cellular and organ function and dysfunction using direct and derived MRI methodologies. London: IntechOpen, 2016.
  8. Baessler B, Mannil M, Oebel S, Maintz D, Alkadhi H, Manka R. Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 2018;286:103-112
  9. Larroza A, Materka A, Lopez-Lereu MP, Monmeneu JV, Bodi V, Moratal D. 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 2017;92:78-83
  10. Bulluck H, White SK, Rosmini S, Bhuva A, Treibel TA, Fontana M, et al. T1 mapping and T2 mapping at 3T for quantifying the area-at-risk in reperfused STEMI patients. J Cardiovasc Magn Reson 2015;17:73
  11. Garg P, Broadbent DA, Swoboda PP, Foley JRJ, Fent GJ, Musa TA, et al. Acute infarct extracellular volume mapping to quantify myocardial area at risk and chronic infarct size on cardiovascular magnetic resonance imaging. Circ Cardiovasc Imaging 2017;10:e006182
  12. Carrick D, Haig C, Rauhalammi S, Ahmed N, Mordi I, McEntegart M, et al. Pathophysiology of LV remodeling in survivors of STEMI: inflammation, remote myocardium, and prognosis. JACC Cardiovasc Imaging 2015;8:779-789
  13. Reinstadler SJ, Stiermaier T, Liebetrau J, Fuernau G, Eitel C, de Waha S, et al. Prognostic significance of remote myocardium alterations assessed by quantitative noncontrast T1 mapping in ST-segment elevation myocardial infarction. JACC Cardiovasc Imaging 2018;11:411-419
  14. Carrick D, Haig C, Rauhalammi S, Ahmed N, Mordi I, McEntegart M, et al. 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 2016;37:1044-1059
  15. Ferreira VM, Piechnik SK, Dall'Armellina E, Karamitsos TD, Francis JM, Choudhury RP, et al. Non-contrast T1-mapping detects acute myocardial edema with high diagnostic accuracy: a comparison to T2-weighted cardiovascular magnetic resonance. J Cardiovasc Magn Reson 2012;14:42
  16. Dall'Armellina E, Piechnik SK, Ferreira VM, Si QL, Robson MD, Francis JM, et al. Cardiovascular magnetic resonance by noncontrast T1-mapping allows assessment of severity of injury in acute myocardial infarction. J Cardiovasc Magn Reson 2012;14:15
  17. Liu D, Borlotti A, Viliani D, Jerosch-Herold M, Alkhalil M, De Maria GL, et al. CMR native T1 mapping allows differentiation of reversible versus irreversible myocardial damage in ST-segment-elevation myocardial infarction: an OxAMI Study (Oxford Acute Myocardial Infarction). Circ Cardiovasc Imaging 2017;10:e005986
  18. Hu LW, Liu XR, Wang Q, Barton GP, Ouyang RZ, Sun AM, et al. Systemic ventricular strain and torsion are predictive of elevated serum NT-proBNP in Fontan patients: a magnetic resonance study. Quant Imaging Med Surg 2020;10:485-495
  19. Schulz-Menger J, Bluemke DA, Bremerich J, Flamm SD, Fogel MA, Friedrich MG, et al. Standardized image interpretation and postprocessing in cardiovascular magnetic resonance: Society for Cardiovascular Magnetic Resonance (SCMR) board of trustees task force on standardized post processing. J Cardiovasc Magn Reson 2013;15:35
  20. Carberry J, Carrick D, Haig C, Rauhalammi SM, Ahmed N, Mordi I, et al. Remote zone extracellular volume and left ventricular remodeling in survivors of ST-elevation myocardial infarction. Hypertension 2016;68:385-391
  21. Bulluck H, Rosmini S, Abdel-Gadir A, Bhuva AN, Treibel TA, Fontana M, et al. Diagnostic performance of T1 and T2 mapping to detect intramyocardial hemorrhage in reperfused ST-segment elevation myocardial infarction (STEMI) patients. J Magn Reson Imaging 2017;46:877-886
  22. Szczypinski PM, Strzelecki M, Materka A, Klepaczko A. MaZda--a software package for image texture analysis. Comput Methods Programs Biomed 2009;94:66-76
  23. Strzelecki M, Szczypinski P, Materka A, Klepaczko A. A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl Instrum Methods Phys Res A 2013;702:137-140
  24. Baessler B, Luecke C, Lurz J, Klingel K, von Roeder M, de Waha S, et al. Cardiac MRI texture analysis of T1 and T2 maps in patients with infarctlike acute myocarditis. Radiology 2018;289:357-365
  25. Baessler B, Mannil M, Maintz D, Alkadhi H, Manka R. Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-preliminary results. Eur J Radiol 2018;102:61-67
  26. Dastidar AG, Harries I, Pontecorboli G, Bruno VD, De Garate E, Moret C, et al. Native T1 mapping to detect extent of acute and chronic myocardial infarction: comparison with late gadolinium enhancement technique. INT J Cardiovasc Imaging 2019;35:517-527
  27. Diao KY, Yang ZG, Xu HY, Liu X, Zhang Q, Shi K, et al. Histologic validation of myocardial fibrosis measured by T1 mapping: a systematic review and meta-analysis. J Cardiovasc Magn Reson 2016;18:92
  28. Ide S, Riesenkampff E, Chiasson DA, Dipchand AI, Kantor PF, Chaturvedi RR, et al. Histological validation of cardiovascular magnetic resonance T1 mapping markers of myocardial fibrosis in paediatric heart transplant recipients. J Cardiovasc Magn Reson 2017;19:10
  29. Castellano G, Bonilha L, Li LM, Cendes F. Texture analysis of medical images. Clin Radiol 2004;59:1061-1069
  30. Hammer-Hansen S, Ugander M, Hsu LY, Taylor J, Thune JJ, Kober L, et al. Distinction of salvaged and infarcted myocardium within the ischaemic area-at-risk with T2 mapping. Eur Heart J Cardiovasc Imaging 2014;15:1048-1053
  31. Kotu LP, Engan K, Eftestol T, Orn S, Woie L. Segmentation of scarred and non-scarred myocardium in LG enhanced CMR images using intensity-based textural analysis. Annu Int Conf IEEE Eng Med Biol Soc 2011;2011:5698-5701
  32. Eftestol T, Woie L, Engan K, Kvaloy JT, Nilsen DWT, Orn S. Texture analysis to assess risk of serious arrhythmias after myocardial infarction. Computing in Cardiology IEEE 2012;2012:365-368