Identification of fibrosis in hypertrophic cardiomyopathy: a radiomic study on cardiac magnetic resonance cine imaging

Abstract

Objectives Hypertrophic cardiomyopathy (HCM) often requires repeated enhanced cardiac magnetic resonance (CMR) imaging to detect fibrosis. We aimed to develop a practical model based on cine imaging to help identify patients with high risk of fibrosis and screen out patients without fibrosis to avoid unnecessary injection of contrast. Methods A total of 273 patients with HCM were divided into training and test sets at a ratio of 7:3. Logistic regression analysis was used to find predictive image features to construct CMR model. Radiomic features were derived from the maximal wall thickness (MWT) slice and entire left ventricular (LV) myocardium. Extreme gradient boosting was used to build radiomic models. Integrated models were established by fusing image features and radiomic models. The model performance was validated in the test set and assessed by ROC and calibration curve and decision curve analysis (DCA). Results We established five prediction models, including CMR, R1 (based on the MWT slice), R2 (based on the entire LV myocardium), and two integrated models (ICMR+R1 and ICMR+R2). In the test set, ICMR+R2 model had an excellent AUC value (0.898), diagnostic accuracy (89.02%), sensitivity (92.54%), and F1 score (93.23%) in identifying patients with positive late gadolinium enhancement. The calibration plots and DCA indicated that ICMR+R2 model was well-calibrated and presented a better net benefit than other models. Conclusions A predictive model that fused image and radiomic features from the entire LV myocardium had good diagnostic performance, robustness, and clinical utility. Key Points • Hypertrophic cardiomyopathy is prone to fibrosis, requiring patients to undergo repeated enhanced cardiac magnetic resonance imaging to detect fibrosis over their lifetime follow-up. • A predictive model based on the entire left ventricular myocardium outperformed a model based on a slice of the maximal wall thickness. • A predictive model that fused image and radiomic features from the entire left ventricular myocardium had excellent diagnostic performance, robustness, and clinical utility.

Perfect Match: Radiomics and Artificial Intelligence in Cardiac Imaging

“…55 Radiomics and AI have also been widely applied for the task of differentiating various cardiomyopathies, with the main focus lying on the different etiologies of the hypertrophic heart including (but not limited to) hypertrophic cardiomyopathy based on LGE or cine imaging, or, more recently, mapping. [56][57][58] Several studies also investigated the usefulness of radiomics to detect the presence or extent of myocardial fibrosis without relying on gadolinium contrast, either using native T1-weighted imaging, 59 cine imaging, 60 or T1/T2 mapping. 61 Radiomics and T1 mapping were also utilized to differentiate different hypertrophic cardiomyopathy genotypes and phenotypes 62,63 and to predict outcomes in patients with hypertrophic cardiomyopathy.…”

A study on the application of radiomics based on cardiac MR non-enhanced cine sequence in the early diagnosis of hypertensive heart disease

“…Recognizing the potential of radiomics in extracting comprehensive information for images, research focusing on radiomics based on CMR cine sequences is on the rise. Limited studies have indicated that radiomics based on CMR cine sequences can effectively identify myocardial fibrosis and scar [ 15 – 19 ]. Furthermore, it has demonstrated the capability to differentiate myocardial amyloidosis from hypertrophic cardiomyopathy [ 20 ].…”

Editorial for “Cine MRI‐Derived Radiomics Features of the Cardiac Blood Pool: Periodicity, Specificity, and Reproducibility”

“…As a last example, Pu et al reported that a radiomics-based predictive model was able to identify myocardial fibrosis in patients with hypertrophic cardiomyopathy with high diagnostic accuracy, using cine images only. 9 Such an approach exhibits clinical potential by providing fibrosis assessment without the need for contrast administration. While it would be difficult to discuss every cardiac MRI related radiomics study considering the limits of an editorial, it can be generally concluded that most, if not all, of the prior studies focused on features of the cardiac chambers (i.e.…”

“…They demonstrated high accuracy in the discrimination of patients with hypertrophic and dilated cardiomyopathies from each other and from healthy participants. As a last example, Pu et al reported that a radiomics‐based predictive model was able to identify myocardial fibrosis in patients with hypertrophic cardiomyopathy with high diagnostic accuracy, using cine images only 9 . Such an approach exhibits clinical potential by providing fibrosis assessment without the need for contrast administration.…”