Ulf Neisius1, Hossam El-Rewaidy1, Shiro Nakamori1, Jennifer Rodriguez1, Warren J Manning2, Reza Nezafat3. 1. Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts. 2. Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts; Department of Radiology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts. 3. Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts. Electronic address: rnezafat@bidmc.harvard.edu.
Abstract
OBJECTIVES: This study sought to examine the diagnostic ability of radiomic texture analysis (TA) on quantitative cardiovascular magnetic resonance images to differentiate between hypertensive heart disease (HHD) and hypertrophic cardiomyopathy (HCM). BACKGROUND: HHD and HCM are associated with increased left ventricular wall thickness (LVWT). Contemporary guidelines define HCM as LVWT ≥15 mm that is unexplained by other disease, which complicates diagnosis in cases of co-occurrences. Conventional global native T1 mapping involves calculation of mean T1 values as a surrogate for fibrosis. However, there may be differences in its spatial localization, such as diffuse and more focal fibrosis in HHD and HCM, respectively. METHODS: This study identified 232 subjects (53 with HHD, 108 with HCM, and 71 control subjects) for TA who consecutively underwent free-breathing multislice native T1 mapping. Four sets of texture descriptors were applied to capture spatially dependent and independent pixel statistics. Six texture features were sequentially selected with the best discriminatory capacity between HHD and HCM and were tested using a support vector machine (SVM) classifier. Each disease group was randomly split 4:1 (feature selection/test validation), in which the reproducibility of the pattern was analyzed in the test validation dataset. RESULTS: The selected texture features provided the maximum diagnostic accuracy of 86.2% (c-statistic: 0.820; 95% confidence interval [CI]: 0.769 to 0.903) using the SVM. For the test validation dataset, the accuracy of the pattern remained high at 80.0% (c-statistic: 0.89; 95% CI: 0.77 to 1.00). Global native T1, with an accuracy of 64%, separated HHD and HCM patients modestly (c-statistic: 0.549; 95% CI: 0.452 to 0.640). CONCLUSIONS: Radiomics analysis of native T1 images discriminates between HHD and HCM patients and provides incremental value over global native T1 mapping.
OBJECTIVES: This study sought to examine the diagnostic ability of radiomic texture analysis (TA) on quantitative cardiovascular magnetic resonance images to differentiate between hypertensive heart disease (HHD) and hypertrophic cardiomyopathy (HCM). BACKGROUND:HHD and HCM are associated with increased left ventricular wall thickness (LVWT). Contemporary guidelines define HCM as LVWT ≥15 mm that is unexplained by other disease, which complicates diagnosis in cases of co-occurrences. Conventional global native T1 mapping involves calculation of mean T1 values as a surrogate for fibrosis. However, there may be differences in its spatial localization, such as diffuse and more focal fibrosis in HHD and HCM, respectively. METHODS: This study identified 232 subjects (53 with HHD, 108 with HCM, and 71 control subjects) for TA who consecutively underwent free-breathing multislice native T1 mapping. Four sets of texture descriptors were applied to capture spatially dependent and independent pixel statistics. Six texture features were sequentially selected with the best discriminatory capacity between HHD and HCM and were tested using a support vector machine (SVM) classifier. Each disease group was randomly split 4:1 (feature selection/test validation), in which the reproducibility of the pattern was analyzed in the test validation dataset. RESULTS: The selected texture features provided the maximum diagnostic accuracy of 86.2% (c-statistic: 0.820; 95% confidence interval [CI]: 0.769 to 0.903) using the SVM. For the test validation dataset, the accuracy of the pattern remained high at 80.0% (c-statistic: 0.89; 95% CI: 0.77 to 1.00). Global native T1, with an accuracy of 64%, separated HHD and HCM patients modestly (c-statistic: 0.549; 95% CI: 0.452 to 0.640). CONCLUSIONS: Radiomics analysis of native T1 images discriminates between HHD and HCM patients and provides incremental value over global native T1 mapping.
Authors: Bernard J Gersh; Barry J Maron; Robert O Bonow; Joseph A Dearani; Michael A Fifer; Mark S Link; Srihari S Naidu; Rick A Nishimura; Steve R Ommen; Harry Rakowski; Christine E Seidman; Jeffrey A Towbin; James E Udelson; Clyde W Yancy Journal: Circulation Date: 2011-11-08 Impact factor: 29.690
Authors: Peter Ganz; Bettina Heidecker; Kristian Hveem; Christian Jonasson; Shintaro Kato; Mark R Segal; David G Sterling; Stephen A Williams Journal: JAMA Date: 2016-06-21 Impact factor: 56.272
Authors: Marco Canepa; Iraklis Pozios; Pier Filippo Vianello; Pietro Ameri; Claudio Brunelli; Luigi Ferrucci; Theodore P Abraham Journal: Heart Date: 2016-04-27 Impact factor: 5.994
Authors: Jonathan C L Rodrigues; Antonio Matteo Amadu; Amardeep Ghosh Dastidar; Gergley V Szantho; Stephen M Lyen; Cattleya Godsave; Laura E K Ratcliffe; Amy E Burchell; Emma C Hart; Mark C K Hamilton; Angus K Nightingale; Julian F R Paton; Nathan E Manghat; Chiara Bucciarelli-Ducci Journal: Heart Date: 2016-06-03 Impact factor: 5.994
Authors: Alexander Rau; Martin Soschynski; Jana Taron; Philipp Ruile; Christopher L Schlett; Fabian Bamberg; Tobias Krauss Journal: Radiologie (Heidelb) Date: 2022-08-25
Authors: Fernando U Kay; Suhny Abbara; Parag H Joshi; Sonia Garg; Amit Khera; Ronald M Peshock Journal: Circ Cardiovasc Imaging Date: 2020-02-18 Impact factor: 7.792
Authors: Donna K Arnett; Ramachandran S Vasan; Matthew Nayor; Li Shen; Gary M Hunninghake; Peter Kochunov; R Graham Barr; David A Bluemke; Ulrich Broeckel; Peter Caravan; Susan Cheng; Paul S de Vries; Udo Hoffmann; Márton Kolossváry; Huiqing Li; James Luo; Elizabeth M McNally; George Thanassoulis Journal: Circ Cardiovasc Imaging Date: 2021-08-13 Impact factor: 8.589
Authors: Jihye Jang; Long H Ngo; Jennifer Mancio; Selcuk Kucukseymen; Jennifer Rodriguez; Patrick Pierce; Beth Goddu; Reza Nezafat Journal: Radiol Cardiothorac Imaging Date: 2020-06-25