Skip to main content
SpringerLink
Log in

Automatic machine learning based on native T1 mapping can identify myocardial fibrosis in patients with hypertrophic cardiomyopathy

  • Cardiac
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To investigate the feasibility of automatic machine learning (autoML) based on native T1 mapping to predict late gadolinium enhancement (LGE) status in hypertrophic cardiomyopathy (HCM).

Methods

Ninety-one HCM patients and 44 healthy controls who underwent cardiovascular MRI were enrolled. The native T1 maps of HCM patients were classified as LGE ( +) or LGE (-) based on location-matched LGE images. An autoML pipeline was implemented using the tree-based pipeline optimization tool (TPOT) for 3 binary classifications: LGE ( +) and LGE (-), LGE (-) and control, and HCM and control. TPOT modeling was repeated 10 times to obtain the optimal model for each classification. The diagnostic performance of the best models by slice and by case was evaluated using sensitivity, specificity, accuracy, and microaveraged area under the curve (AUC).

Results

Ten prediction models were generated by TPOT for each of the 3 binary classifications. The diagnostic accuracy obtained with the best pipeline in detecting LGE status in the testing cohort of HCM patients was 0.80 by slice and 0.79 by case. In addition, the TPOT model also showed discriminability between LGE (-) patients and control (accuracy: 0.77 by slice; 0.78 by case) and for all HCM patients and controls (accuracy: 0.88 for both).

Conclusions

Native T1 map analysis based on autoML correlates with LGE ( +) or (-) status. The TPOT machine learning algorithm could be a promising method for predicting myocardial fibrosis, as reflected by the presence of LGE in HCM patients without the need for late contrast-enhanced MRI sequences.

Key Points

• The tree-based pipeline optimization tool (TPOT) is a machine learning algorithm that could help predict late gadolinium enhancement (LGE) status in patients with hypertrophic cardiomyopathy.

• The TPOT could serve as an adjuvant method to detect LGE by using information from native T1 maps, thus avoiding the need for contrast agent.

• The TPOT also detects native T1 map alterations in LGE-negative patients with hypertrophic cardiomyopathy.

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
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Bogaert J, Olivotto I (2014) MR imaging in hypertrophic cardiomyopathy: from magnet to bedside. Radiology 273(2):329–348

    Article  Google Scholar 

  2. Maron BJ, Ommen SR, Semsarian C, Spirito P, Olivotto I, Maron MS (2014) Hypertrophic cardiomyopathy: present and future, with translation into contemporary cardiovascular medicine. J Am Coll Cardiol 64(1):83–99

    Article  Google Scholar 

  3. Mentias A, Raeisi-Giglou P, Smedira NG et al (2018) Late gadolinium enhancement in patients with hypertrophic cardiomyopathy and preserved systolic function. J Am Coll Cardiol 72(8):857–870

    Article  Google Scholar 

  4. Hashimura H, Kimura F, Ishibashi-Ueda H et al (2017) Radiologic-pathologic correlation of primary and secondary cardiomyopathies: MR imaging and histopathologic findings in hearts from autopsy and transplantation. Radiographics 37(3):719–736

    Article  Google Scholar 

  5. McDonald RJ, Levine D, Weinreb J et al (2018) Gadolinium retention: a research roadmap from the 2018 NIH/ACR/RSNA workshop on gadolinium chelates. Radiology 289(2):517–534

    Article  Google Scholar 

  6. Robinson AA, Chow K, Salerno M (2019) Myocardial T1 and ECV measurement: underlying concepts and technical considerations. JACC Cardiovasc Imaging 12(11 Pt 2):2332–2344

    Article  Google Scholar 

  7. von Knobelsdorff-Brenkenhoff F, Prothmann M, Dieringer MA et al (2013) Myocardial T1 and T2 mapping at 3 T: reference values, influencing factors and implications. J Cardiovasc Magn Reson 15(1):53

    Article  Google Scholar 

  8. Gottbrecht M, Kramer CM, Salerno M (2019) Native T1 and extracellular volume measurements by cardiac MRI in healthy adults: a meta-analysis. Radiology 290(2):317–326

    Article  Google Scholar 

  9. Leiner T, Rueckert D, Suinesiaputra A et al (2019) Machine learning in cardiovascular magnetic resonance: basic concepts and applications. J Cardiovasc Magn Reson 21(1):61

    Article  Google Scholar 

  10. Neisius U, El-Rewaidy H, Nakamori S, Rodriguez J, Manning WJ, Nezafat R (2019) Radiomic analysis of myocardial native T1 imaging discriminates between hypertensive heart disease and hypertrophic cardiomyopathy. JACC Cardiovasc Imaging 12(10):1946–1954

    Article  Google Scholar 

  11. Neisius U, El-Rewaidy H, Kucukseymen S et al (2020) Texture signatures of native myocardial T1 as novel imaging markers for identification of hypertrophic cardiomyopathy patients without scar. J Magn Reson Imaging 52(3):906–919

    Article  Google Scholar 

  12. Wang J, Yang F, Liu W et al (2020) Radiomic analysis of native T1 mapping images discriminates between MYH7 and MYBPC3-related hypertrophic cardiomyopathy. J Magn Reson Imaging 52(6):1714–1721

    Article  Google Scholar 

  13. Dafflon J, Pinaya WHL, Turkheimer F et al (2020) An automated machine learning approach to predict brain age from cortical anatomical measures. Hum Brain Mapp 41(13):3555–3566

    Article  Google Scholar 

  14. Le TT, Fu W, Moore JH (2020) Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics 36(1):250–256

    Article  CAS  Google Scholar 

  15. Su X, Chen N, Sun H et al (2020) Automated machine learning based on radiomics features predicts H3 K27M mutation in midline gliomas of the brain. Neuro Oncol 22(3):393–401

    CAS  PubMed  Google Scholar 

  16. Zhou H, Hu R, Tang O et al (2020) Automatic machine learning to differentiate pediatric posterior fossa tumors on routine MR imaging. AJNR Am J Neuroradiol 41(7):1279–1285

    Article  CAS  Google Scholar 

  17. Authors/Task Force members, Elliott PM, Anastasakis A et al (2014) 2014 ESC guidelines on diagnosis and management of hypertrophic cardiomyopathy: the task force for the diagnosis and management of hypertrophic cardiomyopathy of the European Society of Cardiology (ESC). Eur Heart J 35(39):2733–2779

    Article  Google Scholar 

  18. Xu J, Zhuang B, Sirajuddin A et al (2020) MRI T1 mapping in hypertrophic cardiomyopathy: evaluation in patients without late gadolinium enhancement and hemodynamic obstruction. Radiology 294(2):275–286

    Article  Google Scholar 

  19. Raisi-Estabragh Z, Izquierdo C, Campello VM et al (2020) Cardiac magnetic resonance radiomics: basic principles and clinical perspectives. Eur Heart J Cardiovasc Imaging 21(4):349–356

    Article  Google Scholar 

  20. Baeßler B, Mannil M, Maintz D, Alkadhi H, Manka R (2018) Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-Preliminary results. Eur J Radiol 102:61–67

    Article  Google Scholar 

  21. Schofield R, Ganeshan B, Fontana M et al (2019) Texture analysis of cardiovascular magnetic resonance cine images differentiates aetiologies of left ventricular hypertrophy. Clin Radiol 74(2):140–149

    Article  CAS  Google Scholar 

  22. Olson RS, Bartley N, Urbanowicz RJ, Moore JH (2016) Evaluation of a tree-based pipeline optimization tool for automating data science. Proc GECCO 485–492. https://doi.org/10.1145/2908812.2908918

  23. Langdon WB, Poli R, McPhee NF, Koza JR (2008) Genetic programming: an introduction and tutorial, with a survey of techniques and applications. Stud Comput Intell 927–1028. https://doi.org/10.1007/978-3-540-78293-3_22

  24. Galati G, Leone O, Pasquale F et al (2016) Histological and histometric characterization of myocardial fibrosis in end-stage hypertrophic cardiomyopathy: a clinical-pathological study of 30 explanted hearts. Circ Heart Fail 9(9):e003090

    Article  Google Scholar 

  25. Ando K, Nagao M, Watanabe E et al (2020) Association between myocardial hypoxia and fibrosis in hypertrophic cardiomyopathy: analysis by T2* BOLD and T1 mapping MRI. Eur Radiol 30(8):4327–4336

    Article  CAS  Google Scholar 

Download references

Acknowledgements

We thank the Intellispace Discovery Platform (Philips Healthcare, Best, The Netherlands) to further facilitate our radiomics research.

Funding

This study was financially supported by the 1–3–5 project for disciplines of excellence of West China Hospital, Sichuan University (ZYGD18019).

Author information

Authors and Affiliations

  1. Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China

    Wan-Lin Peng, Ke Shi, Chun-Chao Xia & Zhen-Lin Li

  2. Philips Healthcare, Guangzhou, Guangdong, China

    Tian-Jing Zhang & Hai-Xia Li

  3. Department of Electronic , Communication Engineering, School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China

    Ying Li

  4. Department of Cardiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China

    Sen He & Chen Li

  5. Chengdu Library and Information Center, Chinese Academy of Sciences, Chengdu, Sichuan, China

    Dong Xia

Authors
  1. Wan-Lin Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tian-Jing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ke Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hai-Xia Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ying Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sen He
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Chen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Dong Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Chun-Chao Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Zhen-Lin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Chun-Chao Xia or Zhen-Lin Li.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Prof. Zhen-Lin Li.

Conflict of interest

Two authors of this manuscript (Tian-Jing Zhang and Hai-Xia Li) are employees of Philips Healthcare, and they are participants in the analysis of the data. The remaining authors declare no relationships with any companies whose products or services may be related to the subject matter of the manuscript. Zhen-Lin Li of West China Hospital controls the data.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from each participant.

Ethical approval

Institutional Review Board approval was obtained from the Biomedical Research Ethics Committee of West China Hospital.

Methodology

• Prospective

• Diagnostic study

• Performed at one institution

Additional information

Publisher’s note

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

Wan-Lin Peng and Tian-Jing Zhang contributed equally to this work and should be considered as co-first authors.

Chun-Chao Xia and Zhen-Lin Li contributed equally to this work and should be considered as co-corresponding authors.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 31 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Peng, WL., Zhang, TJ., Shi, K. et al. Automatic machine learning based on native T1 mapping can identify myocardial fibrosis in patients with hypertrophic cardiomyopathy. Eur Radiol 32, 1044–1053 (2022). https://doi.org/10.1007/s00330-021-08228-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-021-08228-7

Keywords

Search

Navigation