Key result
A radiomics-based machine learning model achieved an excellent one-vs-rest ROC-AUC of 0.964 for the automated diagnosis of LVNC, HCM, and DCM, performing comparably to conventional CMR indices without requiring manual trabeculae delineation.
Why the study?
LVNC, HCM, and DCM share morphological and functional traits that complicate diagnosis, and existing CMR hypertrabeculation indices require tedious, time-consuming trabecular delineations.
Does a radiomics-based machine learning approach applied to CMR images accurately classify LVNC, HCM, and DCM?
Cross-Sectional (n=118)
No
Does a radiomics-based machine learning approach applied to CMR images accurately classify LVNC, HCM, and DCM?
Absolute Event Rate: 0.964% vs 0.978%
p-value: p=>0.05
A radiomics-based machine learning approach applied to CMR images can accurately differentiate between overlapping cardiomyopathies (LVNC, HCM, DCM) without the need for manual trabeculae delineation.
May aid cardiomyopathy differentiation via hypertrabeculation indices; leaves open prospective validation before clinical use.
Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is usually required to reach a definitive diagnosis, including electrocardiography (ECG), family history, and genetics. Alternatively, indices of hypertrabeculation have been introduced, but they require tedious and time-consuming delineations of the trabeculae on the CMR images. In this paper, we propose a radiomics approach to automatically encode differences in the underlying shape, gray-scale and textural information in the myocardium and its trabeculae, which may enhance the capacity to differentiate between these overlapping conditions. A total of 118 subjects, including 35 patients with LVNC, 25 with HCM, 37 with DCM, as well as 21 healthy volunteers (NOR), underwent CMR imaging. A comprehensive radiomics characterization was applied to LV short-axis images to quantify shape, first-order, co-occurrence matrix, run-length matrix, and local binary patterns. Conventional CMR indices (LV volumes, mass, wall thickness, LV ejection fraction-LVEF-), as well as hypertrabeculation indices by Petersen and Jacquier, were also analyzed. State-of-the-art Machine Learning (ML) models (one-vs.-rest Support Vector Machine-SVM-, Logistic Regression-LR-, and Random Forest Classifier-RF-) were used for one-vs.-rest classification tasks. The use of radiomics models for the automated diagnosis of LVNC, HCM, and DCM resulted in excellent one-vs.-rest ROC-AUC values of 0.95 while generating these results without the need for the delineation of the trabeculae. First-order and texture features resulted to be among the most discriminative features in the obtained radiomics signatures, indicating their added value for quantifying relevant tissue patterns in cardiomyopathy differential diagnosis.
No takes yet. Share an insight, caveat, or question.
Izquierdo et al. (2021) conducted a cross-sectional in Cardiomyopathies (Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, Dilated Cardiomyopathy) (n=118). Radiomics-based machine learning classification vs. Conventional CMR indices (including Petersen and Jacquier coefficients) was evaluated on One-vs-rest classification performance (ROC-AUC) (p=>0.05). A radiomics-based machine learning model achieved an excellent one-vs-rest ROC-AUC of 0.964 for the automated diagnosis of LVNC, HCM, and DCM, performing comparably to conventional CMR indices without requiring manual trabeculae delineation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: