Radiomic analysis of native T1 mapping images discriminates between MYH7 and MYBPC3-related hypertrophic cardiomyopathy

Research output: Contribution to journalArticlepeer-review

Standard

Radiomic analysis of native T1 mapping images discriminates between MYH7 and MYBPC3-related hypertrophic cardiomyopathy. / Wang, Jie; Yang, Fuyao; Liu, Wentao; Sun, Jiayu; Han, Yuchi; Li, Dong; Gkoutos, Georgios V; Zhu, Yanjie; Chen, Yucheng.

In: Journal of Magnetic Resonance Imaging, 11.06.2020.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{d0224511c3a043458b91cfa6a8a017b9,
title = "Radiomic analysis of native T1 mapping images discriminates between MYH7 and MYBPC3-related hypertrophic cardiomyopathy",
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: 3 TECHNICAL EFFICACY STAGE: 2",
keywords = "magnetic resonance imaging, cardiomyopathy, hypertrophic, machine learning, support vector machine, human genetics",
author = "Jie Wang and Fuyao Yang and Wentao Liu and Jiayu Sun and Yuchi Han and Dong Li and Gkoutos, {Georgios V} and Yanjie Zhu and Yucheng Chen",
note = "{\textcopyright} 2020 International Society for Magnetic Resonance in Medicine.",
year = "2020",
month = jun,
day = "11",
doi = "10.1002/jmri.27209",
language = "English",
journal = "Journal of Magnetic Resonance Imaging",
issn = "1053-1807",
publisher = "Wiley",

}

RIS

TY - JOUR

T1 - Radiomic analysis of native T1 mapping images discriminates between MYH7 and MYBPC3-related hypertrophic cardiomyopathy

AU - Wang, Jie

AU - Yang, Fuyao

AU - Liu, Wentao

AU - Sun, Jiayu

AU - Han, Yuchi

AU - Li, Dong

AU - Gkoutos, Georgios V

AU - Zhu, Yanjie

AU - Chen, Yucheng

N1 - © 2020 International Society for Magnetic Resonance in Medicine.

PY - 2020/6/11

Y1 - 2020/6/11

N2 - 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: 3 TECHNICAL EFFICACY STAGE: 2

AB - 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: 3 TECHNICAL EFFICACY STAGE: 2

KW - magnetic resonance imaging

KW - cardiomyopathy, hypertrophic

KW - machine learning

KW - support vector machine

KW - human genetics

U2 - 10.1002/jmri.27209

DO - 10.1002/jmri.27209

M3 - Article

C2 - 32525266

JO - Journal of Magnetic Resonance Imaging

JF - Journal of Magnetic Resonance Imaging

SN - 1053-1807

ER -