Author + information
- Received July 31, 2018
- Revision received October 20, 2018
- Accepted November 7, 2018
- Published online January 16, 2019.
- Ulf Neisius, MD, PhDa,∗,
- Hossam El-Rewaidy, MSa,∗,
- Shiro Nakamori, MD, PhDa,
- Jennifer Rodriguez, BAa,
- Warren J. Manning, MDa,b and
- Reza Nezafat, PhDa,∗ ()
- aDepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
- bDepartment of Radiology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
- ↵∗Address for correspondence:
Dr. Reza Nezafat, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, Boston, Massachusetts 02215.
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.
- cardiovascular magnetic resonance
- hypertensive heart disease
- hypertrophic cardiomyopathy
- left ventricular hypertrophy
- T1 mapping
↵∗ Drs. Neisius and El-Rewaidy contributed equally to this work and are joint first authors.
This study was supported in part by National Institutes of Health (1R01HL129185-01, 1R01HL129157, and 1R01HL127015) and the American Heart Association (15EIA22710040). Dr. Nezafat has a patent pending for T1 and T2 mapping. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
- Received July 31, 2018.
- Revision received October 20, 2018.
- Accepted November 7, 2018.
- 2019 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.