Original Research

Radiomic Analysis of Native T₁ Mapping Images Discriminates Between MYH7 and MYBPC3-Related Hypertrophic Cardiomyopathy

Jie Wang MD

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

College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK

Both authors contributed equally to this work.

Search for more papers by this author

Fuyao Yang BMSci,

Fuyao Yang BMSci

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

Both authors contributed equally to this work.

Search for more papers by this author

Wentao Liu BMSci,

Wentao Liu BMSci

Medical Big Data Center, West China Hospital, Sichuan University, Chengdu, P. R. China

Search for more papers by this author

Jiayu Sun MD,

Jiayu Sun MD

Department of Radiology, West China Hospital, Sichuan University, Chengdu, P. R. China

Search for more papers by this author

Yuchi Han MD, MMSc,

Yuchi Han MD, MMSc

Department of Medicine (Cardiovascular Division), University of Pennsylvania, Philadelphia, Pennsylvania, USA

Search for more papers by this author

Dong Li PhD,

Dong Li PhD

Division of Hospital Medicine, Emory University School of Medicine, Atlanta, Georgia, USA

Search for more papers by this author

Georgios V. Gkoutos PhD,

Georgios V. Gkoutos PhD

College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK

MRC Health Data Research UK (HDR UK), London, UK

Search for more papers by this author

Yanjie Zhu PhD,

Corresponding Author

Yanjie Zhu PhD

[email protected]

Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, P. R. China

Address reprint requests to: Y. C., Guoxue Xiang No. 37, Chengdu, Sichuan 610041, China. E-mail: [email protected] and Y. Z., 1068 Xueyuan Ave., Shenzhen university town, Nanshan, Shenzhen, Guangdong, China. E-mail: [email protected]Search for more papers by this author

Yucheng Chen MD,

Corresponding Author

Yucheng Chen MD

[email protected]

orcid.org/0000-0002-0601-8039

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

Department of Radiology, West China Hospital, Sichuan University, Chengdu, P. R. China

Center of Rare diseases, West China Hospital, Sichuan University, Chengdu, P. R. China

Jie Wang MD,

Jie Wang MD

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

College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK

Both authors contributed equally to this work.

Search for more papers by this author

Fuyao Yang BMSci,

Fuyao Yang BMSci

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

Both authors contributed equally to this work.

Search for more papers by this author

Wentao Liu BMSci,

Wentao Liu BMSci

Medical Big Data Center, West China Hospital, Sichuan University, Chengdu, P. R. China

Search for more papers by this author

Jiayu Sun MD,

Jiayu Sun MD

Department of Radiology, West China Hospital, Sichuan University, Chengdu, P. R. China

Search for more papers by this author

Yuchi Han MD, MMSc,

Yuchi Han MD, MMSc

Department of Medicine (Cardiovascular Division), University of Pennsylvania, Philadelphia, Pennsylvania, USA

Search for more papers by this author

Dong Li PhD,

Dong Li PhD

Division of Hospital Medicine, Emory University School of Medicine, Atlanta, Georgia, USA

Search for more papers by this author

Georgios V. Gkoutos PhD,

Georgios V. Gkoutos PhD

College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK

MRC Health Data Research UK (HDR UK), London, UK

Search for more papers by this author

Yanjie Zhu PhD,

Corresponding Author

Yanjie Zhu PhD

[email protected]

Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, P. R. China

Yucheng Chen MD,

Corresponding Author

Yucheng Chen MD

[email protected]

orcid.org/0000-0002-0601-8039

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

Department of Radiology, West China Hospital, Sichuan University, Chengdu, P. R. China

Center of Rare diseases, West China Hospital, Sichuan University, Chengdu, P. R. China

First published: 11 June 2020

https://doi.org/10.1002/jmri.27209

Citations: 18

Share a link

Email
Wechat
Bluesky

Abstract

Background

The phenotype via conventional cardiac MRI analysis of MYH7 (β-myosin heavy chain)- and MYBPC3 (β-myosin-binding protein C)-associated hypertrophic cardiomyopathy (HCM) groups is similar. Few studies exist on the genotypic–phenotypic association as assessed by machine learning in HCM patients.

Purpose

To explore the phenotypic differences based on radiomics analysis of T₁ mapping images between MYH7 and MYBPC3-associated HCM subgroups.

Study Type

Prospective observational study.

Subjects

In all, 102 HCM patients with pathogenic, or likely pathogenic mutation, in MYH7 (n = 68) or MYBPC3 (n = 34) genes.

Field Strength/Sequence

Cardiac MRI was performed at 3.0T with balanced steady-state free precession (bSSFP), phase-sensitive inversion recovery (PSIR) late gadolinium enhancement (LGE), and modified Look–Locker inversion recovery (MOLLI) T₁ mapping sequences.

Assessment

All patients underwent next-generation sequencing and Sanger genetic sequencing. Left ventricular native T₁ and LGE were analyzed. One hundred and fifty-seven radiomic features were extracted and modeled using a support vector machine (SVM) combined with principal component analysis (PCA). Each subgroup was randomly split 4:1 (feature selection / test validation).

Statistical Tests

Mann–Whitney U-tests and Student's t-tests were performed to assess differences between subgroups. A receiver operating characteristic (ROC) curve was used to assess the model's ability to stratify patients based on radiomic features.

Results

There were no significant differences between MYH7- and MYBPC3-associated HCM subgroups based on traditional native T₁ values (global, basal, and middle short-axis slice native T₁; P = 0.760, 0.914, and 0.178, respectively). However, the SVM model combined with PCA achieved an accuracy and area under the curve (AUC) of 92.0% and 0.968 (95% confidence interval [CI]: 0.968–0.971), respectively. For the test validation dataset, the accuracy and AUC were 85.5% and 0.886 (95% CI: 0.881–0.901), respectively.

Data Conclusion

Radiomic analysis of native T₁ mapping images may be able to discriminate between MYH7- and MYBPC3-associated HCM patients, exceeding the performance of conventional native T₁ values.

Level of Evidence

Technical Efficacy Stage

2 J. MAGN. RESON. IMAGING 2020;52:1714–1721.

Conflict of Interest

All authors declare that they have no competing interests regarding this study.

REFERENCES

1Maron BJ, Gardin JM, Flack JM, Gidding SS, Kurosaki TT, Bild DE. Prevalence of hypertrophic cardiomyopathy in a general population of young adults echocardiographic analysis of 4111 subjects in the CARDIA study. Circulation 1995; 92: 785-789.
10.1161/01.CIR.92.4.785
CAS PubMed Web of Science® Google Scholar
2Weissler-Snir A, Hindieh W, Gruner C, et al. Lack of phenotypic differences by cardiovascular magnetic resonance imaging in MYH7 (β-myosin heavy chain) — versus MYBPC3 (myosin-binding protein C)-related hypertrophic cardiomyopathy. Circ Cardiovasc Imaging 2017; 10:e005311.
10.1161/CIRCIMAGING.116.005311
PubMed Web of Science® Google Scholar
3Hinojar R, Varma N, Child N, et al. T1 mapping in discrimination of hypertrophic phenotypes: Hypertensive heart disease and hypertrophic cardiomyopathy: findings from the international T1 multicenter cardiovascular magnetic resonance study. Circ Cardiovasc Imaging 2015; 8:e3285.
10.1161/CIRCIMAGING.115.003285
PubMed Web of Science® Google Scholar
4Wang S, Zou Y, Fu C, et al. Worse prognosis with gene mutations of beta-myosin heavy chain than myosin-binding protein C in Chinese patients with hypertrophic cardiomyopathy. Clin Cardiol 2008; 31: 114-118.
10.1002/clc.20151
PubMed Web of Science® Google Scholar
5Song L, Zou Y, Wang J, et al. Mutations profile in Chinese patients with hypertrophic cardiomyopathy. Clin Chim Acta 2005; 351: 209-216.
10.1016/j.cccn.2004.09.016
CAS PubMed Web of Science® Google Scholar
6Van Driest SL, Vasile VC, Ommen SR, et al. Myosin binding protein C mutations and compound heterozygosity in hypertrophic cardiomyopathy. J Am Coll Cardiol 2004; 44: 1903-1910.
10.1016/j.jacc.2004.07.045
CAS PubMed Web of Science® Google Scholar
7Ellims AH, Iles LM, Ling L, et al. A comprehensive evaluation of myocardial fibrosis in hypertrophic cardiomyopathy with cardiac magnetic resonance imaging: Linking genotype with fibrotic phenotype. Eur Heart J Cardiovasc Imaging 2014; 15: 1108-1116.
10.1093/ehjci/jeu077
PubMed Web of Science® Google Scholar
8Viswanathan SK, Sanders HK, McNamara JW, et al. Hypertrophic cardiomyopathy clinical phenotype is independent of gene mutation and mutation dosage. PLos One 2017; 12:e187948.
10.1371/journal.pone.0187948
PubMed Web of Science® Google Scholar
9White SK, Sado DM, Fontana M, et al. T1 mapping for myocardial extracellular volume measurement by CMR: Bolus only versus primed infusion technique. JACC Cardiovasc Imaging 2013; 6: 955-962.
10.1016/j.jcmg.2013.01.011
PubMed Web of Science® Google Scholar
10Rudolph A, Abdelaty H, Bohl S, et al. Noninvasive detection of fibrosis applying contrast-enhanced cardiac magnetic resonance in different forms of left ventricular hypertrophy relation to remodeling. J Am Coll Cardiol 2009; 53: 284-291.
10.1016/j.jacc.2008.08.064
PubMed Web of Science® Google Scholar
11Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology 2016; 278: 563-577.
10.1148/radiol.2015151169
PubMed Web of Science® Google Scholar
12Neisius U, El-Rewaidy H, Nakamori S, Rodriguez J, Manning WJ, Nezafat R. Radiomic analysis of myocardial native T1 imaging discriminates between hypertensive heart disease and hypertrophic cardiomyopathy. JACC Cardiovasc Imaging 2019; 12: 1946-1954.
10.1016/j.jcmg.2018.11.024
PubMed Web of Science® Google Scholar
13Baeßler 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.
10.1016/j.ejrad.2018.03.013
PubMed Web of Science® Google Scholar
14Yang F, Wang J, Li Y, et al. The prognostic value of biventricular long axis strain using standard cardiovascular magnetic resonance imaging in patients with hypertrophic cardiomyopathy. Int J Cardiol 2019; 294: 43-49.
10.1016/j.ijcard.2019.08.010
PubMed Web of Science® Google Scholar
15Elliott PM, Anastasakis A, Borger MA, et al. 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 2014; 35: 2733-2779.
10.1093/eurheartj/ehu284
PubMed Web of Science® Google Scholar
16Arbustini E, Narula N, Tavazzi L, et al. The MOGE(S) classification of cardiomyopathy for clinicians. J Am Coll Cardiol 2014; 64: 304-318.
10.1016/j.jacc.2014.05.027
PubMed Web of Science® Google Scholar
17Wang J, Wan K, Sun J, et al. Phenotypic diversity identified by cardiac magnetic resonance in a large hypertrophic cardiomyopathy family with a single MYH7 mutation. Sci Rep 2018; 8: 973.
10.1038/s41598-018-19372-4
PubMed Web of Science® Google Scholar
18Martin M. Cutadapt removes adapter sequences from high-throughput sequencing reads. EMBnetjournal 2011; 17: 10–12.
10.14806/ej.17.1.200
PubMed Google Scholar
19Koboldt DC, Zhang Q, Larson DE, et al. VarScan 2: Somatic mutation and copy number alteration discovery in cancer by exome sequencing. Genome Res 2012; 22: 568-576.
10.1101/gr.129684.111
CAS PubMed Web of Science® Google Scholar
20McKenna A, Hanna M, Banks E, et al. The genome analysis toolkit: A MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res 2010; 20: 1297-1303.
10.1101/gr.107524.110
CAS PubMed Web of Science® Google Scholar
21Xu Z, Xie C, Xia L, et al. Targeted exome sequencing identifies five novel loci at genome-wide significance for modulating antidepressant response in patients with major depressive disorder. Transl Psychiatry 2020; 10: 30.
10.1038/s41398-020-0689-x
CAS PubMed Web of Science® Google Scholar
22Wang K, Li M, Hakonarson H. ANNOVAR: Functional annotation of genetic variants from high-throughput sequencing data. Nucleic Acids Res 2010; 38:e164.
10.1093/nar/gkq603
CAS PubMed Web of Science® Google Scholar
23Ng PC, Henikoff S. SIFT: Predicting amino acid changes that affect protein function. Nucleic Acids Res 2003; 31: 3812-3814.
10.1093/nar/gkg509
CAS PubMed Web of Science® Google Scholar
24Adzhubei IA, Schmidt S, Peshkin L, et al. A method and server for predicting damaging missense mutations. Nat Methods 2010; 7: 248-249.
10.1038/nmeth0410-248
CAS PubMed Web of Science® Google Scholar
25Schwarz JM, Rödelsperger C, Schuelke M, Seelow D. MutationTaster evaluates disease-causing potential of sequence alterations. Nat Methods 2010; 7: 575-576.
10.1038/nmeth0810-575
CAS PubMed Web of Science® Google Scholar
26Richards S, Aziz N, Bale S, et al. Standards and guidelines for the interpretation of sequence variants: A joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med 2015; 17: 405-424.
10.1038/gim.2015.30
PubMed Web of Science® Google Scholar
27Wang J, Li W, Sun J, et al. Improved segmental myocardial strain reproducibility using deformable registration algorithms compared with feature tracking cardiac MRI and speckle tracking echocardiography. J Magn Reson Imaging 2018; 48: 404-414.
10.1002/jmri.25937
CAS PubMed Web of Science® Google Scholar
28Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification, IEEE transactions on systems. Man Cybern 1973; 3: 610-621.
10.1109/TSMC.1973.4309314
Web of Science® Google Scholar
29Haralick RM, Shapiro LG. Computer and robot vision, Vol. 1. Boston: Addison-Wesley Longman Publishing Co., Inc.; 1992. p 460.
Google Scholar
30Ahonen T, Matas J, He C, et al. Rotation invariant image description with local binary pattern histogram Fourier features. Image analysis, 16th Scandinavian Conference, SCIA 2009, Oslo, Norway; June 15–18, 2009. Proceedings DBLP, 2009.
Google Scholar
31Bianconi F, Alvarez-Larrán A, Fernández A. Discrimination between tumour epithelium and stroma via perception-based features. Neurocomputing 2015; 154: 119-126.
10.1016/j.neucom.2014.12.012
Web of Science® Google Scholar
32Tang X. Texture information in run-length matrices. IEEE Trans Image Process 1998; 7: 1602-1609.
10.1109/83.725367
CAS PubMed Web of Science® Google Scholar
33Jin X, Zheng X, Chen D, et al. Prediction of response after chemoradiation for esophageal cancer using a combination of dosimetry and CT radiomics. Eur Radiol 2019; 29: 6080-6088.
10.1007/s00330-019-06193-w
PubMed Web of Science® Google Scholar
34Sedaghat-hamedani F, Kayvanpour E, Tugrul OF, et al. Clinical outcomes associated with sarcomere mutations in hypertrophic cardiomyopathy: A meta-analysis on 7675 individuals. Clin Res Cardiol 2017; 107: 30-41.
10.1007/s00392-017-1155-5
PubMed Web of Science® Google Scholar
35Miller RJH, Heidary S, Pavlovic A, et al. Defining genotype-phenotype relationships in patients with hypertrophic cardiomyopathy using cardiovascular magnetic resonance imaging. PLos One 2019; 14:e217612.
10.1371/journal.pone.0217612
Web of Science® Google Scholar
36Ho CY, Day SM, Ashley EA, et al. Genotype and lifetime burden of disease in hypertrophic cardiomyopathy: Insights from the sarcomeric human cardiomyopathy registry (SHaRe). Circulation 2018; 138: 1387-1398.
10.1161/CIRCULATIONAHA.117.033200
PubMed Web of Science® Google Scholar
37van Rosendael AR, Maliakal G, Kolli KK, et al. Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry. J Cardiovasc Comput 2018; 12: 204-209.
10.1016/j.jcct.2018.04.011
PubMed Web of Science® Google Scholar
38Gould J, Porter B, Claridge S, et al. Mean entropy predicts implantable cardioverter-defibrillator therapy using cardiac magnetic resonance texture analysis of scar heterogeneity. Heart Rhythm 2019; 16: 1242-1250.
10.1016/j.hrthm.2019.03.001
PubMed Web of Science® Google Scholar

Citing Literature

Volume52, Issue6

December 2020

Pages 1714-1721

Radiomic Analysis of Native T₁ Mapping Images Discriminates Between MYH7 and MYBPC3-Related Hypertrophic Cardiomyopathy

Abstract

Background

Purpose

Study Type

Subjects

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Level of Evidence

Technical Efficacy Stage

Conflict of Interest

REFERENCES

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Radiomic Analysis of Native T1 Mapping Images Discriminates Between MYH7 and MYBPC3-Related Hypertrophic Cardiomyopathy

Abstract

Background

Purpose

Study Type

Subjects

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Level of Evidence

Technical Efficacy Stage

Conflict of Interest

REFERENCES

Citing Literature

References

Related

Information

Radiomic Analysis of Native T₁ Mapping Images Discriminates Between MYH7 and MYBPC3-Related Hypertrophic Cardiomyopathy