Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes
Abstract We explored whether radiomic features from T1 maps by cardiac magnetic resonance (CMR) could enhance the diagnostic value of T1 mapping in distinguishing health from disease and classifying cardiac disease phenotypes. A total of 149 patients (n = 30 with no heart disease, n = 30 with LVH, n...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-02971-z |
| _version_ | 1818402368592543744 |
|---|---|
| author | Alexios S. Antonopoulos Maria Boutsikou Spyridon Simantiris Andreas Angelopoulos George Lazaros Ioannis Panagiotopoulos Evangelos Oikonomou Mikela Kanoupaki Dimitris Tousoulis Raad H. Mohiaddin Konstantinos Tsioufis Charalambos Vlachopoulos |
| author_facet | Alexios S. Antonopoulos Maria Boutsikou Spyridon Simantiris Andreas Angelopoulos George Lazaros Ioannis Panagiotopoulos Evangelos Oikonomou Mikela Kanoupaki Dimitris Tousoulis Raad H. Mohiaddin Konstantinos Tsioufis Charalambos Vlachopoulos |
| author_sort | Alexios S. Antonopoulos |
| collection | DOAJ |
| description | Abstract We explored whether radiomic features from T1 maps by cardiac magnetic resonance (CMR) could enhance the diagnostic value of T1 mapping in distinguishing health from disease and classifying cardiac disease phenotypes. A total of 149 patients (n = 30 with no heart disease, n = 30 with LVH, n = 61 with hypertrophic cardiomyopathy (HCM) and n = 28 with cardiac amyloidosis) undergoing a CMR scan were included in this study. We extracted a total of 850 radiomic features and explored their value in disease classification. We applied principal component analysis and unsupervised clustering in exploratory analysis, and then machine learning for feature selection of the best radiomic features that maximized the diagnostic value for cardiac disease classification. The first three principal components of the T1 radiomics were distinctively correlated with cardiac disease type. Unsupervised hierarchical clustering of the population by myocardial T1 radiomics was significantly associated with myocardial disease type (chi2 = 55.98, p < 0.0001). After feature selection, internal validation and external testing, a model of T1 radiomics had good diagnostic performance (AUC 0.753) for multinomial classification of disease phenotype (normal vs. LVH vs. HCM vs. cardiac amyloid). A subset of six radiomic features outperformed mean native T1 values for classification between myocardial health vs. disease and HCM phenocopies (AUC of T1 vs. radiomics model, for normal: 0.549 vs. 0.888; for LVH: 0.645 vs. 0.790; for HCM 0.541 vs. 0.638; and for cardiac amyloid 0.769 vs. 0.840). We show that myocardial texture assessed by native T1 maps is linked to features of cardiac disease. Myocardial radiomic phenotyping could enhance the diagnostic yield of T1 mapping for myocardial disease detection and classification. |
| first_indexed | 2024-12-14T08:07:15Z |
| format | Article |
| id | doaj.art-c7a46f826a284b85927ae72f79116f31 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T08:07:15Z |
| publishDate | 2021-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c7a46f826a284b85927ae72f79116f312022-12-21T23:10:09ZengNature PortfolioScientific Reports2045-23222021-12-0111111110.1038/s41598-021-02971-zMachine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypesAlexios S. Antonopoulos0Maria Boutsikou1Spyridon Simantiris2Andreas Angelopoulos3George Lazaros4Ioannis Panagiotopoulos5Evangelos Oikonomou6Mikela Kanoupaki7Dimitris Tousoulis8Raad H. Mohiaddin9Konstantinos Tsioufis10Charalambos Vlachopoulos11Unit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensCMR Unit, Mediterraneo HospitalUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensCMR Unit, Mediterraneo HospitalUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensCMR Unit, Faculty of Medicine, National Heart and Lung Institute, Imperial College LondonUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensUnit of Inherited Cardiac Conditions and Sports Cardiology, 1st Department of Cardiology, National and Kapodistrian University of AthensAbstract We explored whether radiomic features from T1 maps by cardiac magnetic resonance (CMR) could enhance the diagnostic value of T1 mapping in distinguishing health from disease and classifying cardiac disease phenotypes. A total of 149 patients (n = 30 with no heart disease, n = 30 with LVH, n = 61 with hypertrophic cardiomyopathy (HCM) and n = 28 with cardiac amyloidosis) undergoing a CMR scan were included in this study. We extracted a total of 850 radiomic features and explored their value in disease classification. We applied principal component analysis and unsupervised clustering in exploratory analysis, and then machine learning for feature selection of the best radiomic features that maximized the diagnostic value for cardiac disease classification. The first three principal components of the T1 radiomics were distinctively correlated with cardiac disease type. Unsupervised hierarchical clustering of the population by myocardial T1 radiomics was significantly associated with myocardial disease type (chi2 = 55.98, p < 0.0001). After feature selection, internal validation and external testing, a model of T1 radiomics had good diagnostic performance (AUC 0.753) for multinomial classification of disease phenotype (normal vs. LVH vs. HCM vs. cardiac amyloid). A subset of six radiomic features outperformed mean native T1 values for classification between myocardial health vs. disease and HCM phenocopies (AUC of T1 vs. radiomics model, for normal: 0.549 vs. 0.888; for LVH: 0.645 vs. 0.790; for HCM 0.541 vs. 0.638; and for cardiac amyloid 0.769 vs. 0.840). We show that myocardial texture assessed by native T1 maps is linked to features of cardiac disease. Myocardial radiomic phenotyping could enhance the diagnostic yield of T1 mapping for myocardial disease detection and classification.https://doi.org/10.1038/s41598-021-02971-z |
| spellingShingle | Alexios S. Antonopoulos Maria Boutsikou Spyridon Simantiris Andreas Angelopoulos George Lazaros Ioannis Panagiotopoulos Evangelos Oikonomou Mikela Kanoupaki Dimitris Tousoulis Raad H. Mohiaddin Konstantinos Tsioufis Charalambos Vlachopoulos Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes Scientific Reports |
| title | Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| title_full | Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| title_fullStr | Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| title_full_unstemmed | Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| title_short | Machine learning of native T1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| title_sort | machine learning of native t1 mapping radiomics for classification of hypertrophic cardiomyopathy phenotypes |
| url | https://doi.org/10.1038/s41598-021-02971-z |
| work_keys_str_mv | AT alexiossantonopoulos machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT mariaboutsikou machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT spyridonsimantiris machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT andreasangelopoulos machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT georgelazaros machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT ioannispanagiotopoulos machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT evangelosoikonomou machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT mikelakanoupaki machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT dimitristousoulis machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT raadhmohiaddin machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT konstantinostsioufis machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes AT charalambosvlachopoulos machinelearningofnativet1mappingradiomicsforclassificationofhypertrophiccardiomyopathyphenotypes |