Skip to main content

Advertisement

SpringerLink
Log in

Radiomics-based detection of acute myocardial infarction on noncontrast enhanced midventricular short-axis cine CMR images

  • Original Paper
  • Published:
The International Journal of Cardiovascular Imaging Aims and scope Submit manuscript

Abstract

Cardiac magnetic resonance cine images are primarily used to evaluate functional consequences, whereas limited information is extracted from the noncontrast pixel-wise myocardial signal intensity pattern. In this study we want to assess whether characterizing this inherent contrast pattern of noncontrast-enhanced short axis (SAX) cine images via radiomics is sufficient to distinguish subjects with acute myocardial infarction (AMI) from controls. Cine balanced steady-state free-precession images acquired at 1.5 T from 99 AMI and 49 control patients were included. First, radiomic feature extraction of the left ventricular myocardium of end-diastolic (ED) and end-systolic (ES) frames was performed based on automated (AUTO) or manually corrected (MAN) segmentations. Next, top features were selected based on optimal classification results using a support vector machine (SVM) approach. The classification performances of the four radiomics models (using AUTO or MAN segmented ED or ES images), were measured by AUC, classification accuracy (CA), F1-score, sensitivity and specificity. The most accurate model was found when combining the features RunLengthNonUniformity, ClusterShade and Median obtained from the manually segmented ES images (CA = 0.846, F1 score = 0.847). ED analysis performed worse than ES, with lower CA and F1 scores (0.769 and 0.770, respectively). Manual correction of automated contours resulted in similar model features as the automated segmentations and did not improve classification results. A radiomics analysis can capture the inherent contrast in noncontrast mid-ventricular SAX cine images to distinguishing AMI from healthy subjects. The ES radiomics model was more accurate than the ED model. Manual correction of the autosegmentation did not provide significant classification improvements.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Abbreviations

AMI:

Acute myocardial infarct

AUC:

Area under the curve

AUTO:

Automated

bSSFP:

Balanced steady-state free-precession

CC:

Pearson correlation coefficient

Cx:

Circumflex artery

EDV:

End-diastolic volume

ESV:

End-systolic volume

GLCM:

Gray level co-occurrence matrix

GLDLM:

Gray level dependence matrix

GLRLM:

Gray level run length matrix

GLSZM:

Gray level size zone matrix

HR:

Heart rate

IMH:

Intramyocardial hemorrhage

LAD:

Left anterior descending

LASSO:

Least absolute shrinkage and selection operator

LV:

Left ventricle

LVEF:

Left ventricular ejection fraction

MI:

Myocardial infarction

MAN:

Manual

MR:

Magnetic resonance

MVO:

Microvascular obstruction

RCA:

Right coronary artery

ROC:

Receiver operating characteristic

SV:

Stroke volume

SVM:

Support vector machine

References

  1. Khan JN, McCann GP (2017) Cardiovascular magnetic resonance imaging assessment of outcomes in acute myocardial infarction. World J Cardiol 9:109–133. https://doi.org/10.4330/wjc.v9.i2.109

    Article  PubMed  PubMed Central  Google Scholar 

  2. Kramer CM, Barkhausen J, Bucciarelli-Ducci C, Flamm SD, Kim RJ, Nagel E (2020) Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J Cardiovasc Magn Reson 22(1):17. https://doi.org/10.1186/s12968-020-00607-1

    Article  PubMed  PubMed Central  Google Scholar 

  3. Brünjes R, Hofmann T (2020) Anthropogenic gadolinium in freshwater and drinking water systems. Water Res 182:115966. https://doi.org/10.1016/j.watres.2020.115966

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169

    Article  PubMed  Google Scholar 

  5. Raisi-Estabragh Z, Izquierdo C, Campello VM et al (2020) Cardiac magnetic resonance radiomics: basic principles and clinical perspectives. Eur Heart J CVI 21:349–356. https://doi.org/10.1186/s12968-017-0325-y

    Article  Google Scholar 

  6. Nordlund D, Kanski M, Jablonowski R et al (2017) Experimental validation of contrast-enhanced SSFP cine CMR for quantification of myocardium at risk in acute myocardial infarction. J Cardiovasc Magn Reason 19:12. https://doi.org/10.1186/s12968-017-0325-y

    Article  Google Scholar 

  7. Abdulkareem M, Kenawy AA, Rauseo E et al (2022) Predicting post-contrast information from contrast agent free cardiac MRI using machine learning: challenges and methods. Front Cardiovasc Med 9:894503. https://doi.org/10.1016/j.compbiomed.2021.105145

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Avard E, Shiri I, Hajianfar G et al (2022) Noncontrast cine cardiac magnetic resonance image radiomics features and machine learning algorithms for myocardial infarction detection. Comput Biol Med 141:105145

    Article  PubMed  Google Scholar 

  9. 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(1):103–112. https://doi.org/10.1148/radiol.2017170213

    Article  PubMed  Google Scholar 

  10. 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. https://doi.org/10.1016/j.ejrad.2017.04.024

    Article  PubMed  Google Scholar 

  11. Larroza A, López-Lereu MP, Monmeneu JV, Gavara J, Chorro FJ, Bodí V, Moratal D (2018) Texture analysis of cardiac cine magnetic resonance imaging to detect nonviable segments in patients with chronic myocardial infarction. Med Phys 45:1471–1480. https://doi.org/10.1002/mp.12783

    Article  CAS  PubMed  Google Scholar 

  12. Durmaz E S, Karabacak M, Ozkara B B, et al. Radiomics-based machine learning models in STEMI: a promising tool for the prediction of major adverse cardiac events. Eur Radiol 2023. https://doi.org/10.1007/s00330-023-09394-6.

  13. Alis D, Yergin M, Asmakutlu O, Topel C, Karaarslan E (2021) The influence of cardiac motion on radiomics features: radiomics features of non-enhanced CMR cine images greatly vary through the cardiac cycle. Eur Radiol 31(5):2706–2715. https://doi.org/10.1007/s00330-020-07370-y

    Article  PubMed  Google Scholar 

  14. Laube A, Ivantsits M, Hüllebrand M et al (2023) Influence of temporal sampling on reproducibility of radiomics features in cardiac cine MRI. In: Proceedings of the 32nd joint annual ISMRM & SMRT meeting, Toronto (abstract 4460)

  15. Jang J, El-Rewaidy H, Ngo LH et al (2021) Sensitivity of myocardial radiomic features to imaging parameters in cardiac MR imaging. J Magn Reson Imaging 54:787–794. https://doi.org/10.1002/jmri.27581

    Article  PubMed  PubMed Central  Google Scholar 

  16. Raisi-Estabragh Z, Gkontra P, Jaggi A et al (2020) Repeatability of cardiac magnetic resonance radiomics: a multi-centre multi-vendor test-retest study. Front Cardiovasc Med 7:586236. https://doi.org/10.3389/fcvm.2020.586236

    Article  PubMed  PubMed Central  Google Scholar 

  17. Fedorov A, Beichel R, Kalpathy-Cramer J et al (2012) 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging 30(9):1323–1341. https://doi.org/10.1016/j.mri.2012.05.001

    Article  PubMed  PubMed Central  Google Scholar 

  18. van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In: Fawcett T, Mishra N (eds) Proceedings of the 20th international conference on machine learning (ICML-03). The AAAI Press, Menlo Park, pp 856–863

  20. Demsar J, Curk T, Erjavec A et al (2013) Orange: data mining toolbox in Python. J Mach Learn Res 14:2349–2353

    Google Scholar 

  21. Papalini EI, Polte CL, Bobbio E, Lagerstrand KM (2022) Diagnosis of acute myocarditis using texture-based cardiac magnetic resonance, with CINE imaging as a novel tissue characterization technique. Diagnostics (Basel) 12(12):3187. https://doi.org/10.3390/diagnostics12123187

    Article  PubMed  Google Scholar 

  22. Steen H, Voss F, André F et al (2012) Clinical feasibility study for detection of myocardial oedema by a cine SSFP sequence in comparison to a conventional T2-weighted sequence. Clin Res Cardiol 101(2):125–131. https://doi.org/10.1007/s00392-011-0373-5

    Article  PubMed  Google Scholar 

  23. Kumar A, Beohar N, Arumana JM et al (2011) CMR imaging of edema in myocardial infarction using cine balanced steady-state free precession. JACC Cardiovasc Imaging 4(12):1265–1273. https://doi.org/10.1016/j.jcmg.2011.04.024

    Article  PubMed  PubMed Central  Google Scholar 

  24. Goldfarb JW, McLaughlin J, Gray CA, Han J (2011) Cyclic CINE-balanced steady-state free precession image intensity variations: implications for the detection of myocardial edema. J Magn Reson Imaging 33:573–581. https://doi.org/10.1002/jmri.22368

    Article  PubMed  Google Scholar 

  25. Peng Y, Wu K, Wang YXJ, Gong J (2022) Association between cine CMR-based radiomics signature and microvascular obstruction in patients with ST-segment elevation myocardial infarction. J Thorac Dis 14(4):969–978. https://doi.org/10.21037/jtd-21-1706

    Article  PubMed  PubMed Central  Google Scholar 

  26. Hassani C, Saremi F, Varghese BA, Duddalwar V (2020) Myocardial radiomics in cardiac MRI. Am J Roentgen 214:536–545. https://doi.org/10.2214/AJR.19.21986

    Article  Google Scholar 

Download references

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Department of Radiology, University Hospitals Leuven, Herestraat 49, 3000, Leuven, Belgium

    Baptiste Vande Berg, Frederik De Keyzer, Pier Giorgio Masci, Jan Bogaert & Tom Dresselaers

  2. Department of Imaging and Pathology KU Leuven, Herestraat 49, 3000, Leuven, Belgium

    Frederik De Keyzer, Pier Giorgio Masci, Jan Bogaert & Tom Dresselaers

  3. Philips Benelux, Eindhoven, The Netherlands

    Alexandru Cernicanu

  4. Department of Cardiovascular Sciences, KU Leuven, Herestraat 49, 3000, Leuven, Belgium

    Piet Claus

  5. School of Biomedical Engineering and Imaging Sciences, King’s College London, St Thomas Hospital, London, UK

    Pier Giorgio Masci

Authors
  1. Baptiste Vande Berg
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frederik De Keyzer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alexandru Cernicanu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Piet Claus
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pier Giorgio Masci
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jan Bogaert
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tom Dresselaers
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Baptiste Vande Berg, Frederik De Keyzer, Jan Bogaert and Tom Dresselaers. The first draft of the manuscript was written by Baptiste Vande Berg and Tom Dresselaers and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Tom Dresselaers.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethical approval

This study was approved was granted by the UZ/KU Leuven institutional review board and ethics committee (date: 12/10/2021/No: MP017960).

Informed consent

Given the retrospective study design the need for informed consents was waived.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 764 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vande Berg, B., De Keyzer, F., Cernicanu, A. et al. Radiomics-based detection of acute myocardial infarction on noncontrast enhanced midventricular short-axis cine CMR images. Int J Cardiovasc Imaging (2024). https://doi.org/10.1007/s10554-024-03089-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10554-024-03089-9

Keywords

Search

Navigation