A robust radiomic-based machine learning approach to detect cardiac amyloidosis using cardiac computed tomography

Francesca Lo Iacono; Riccardo Maragna; Gianluca Pontone; Valentina D A Corino

doi:10.3389/fradi.2023.1193046

A robust radiomic-based machine learning approach to detect cardiac amyloidosis using cardiac computed tomography

Front Radiol. 2023 Jun 16:3:1193046. doi: 10.3389/fradi.2023.1193046. eCollection 2023.

Authors

Francesca Lo Iacono¹, Riccardo Maragna², Gianluca Pontone^{2

3}, Valentina D A Corino^{1

2}

Affiliations

¹ Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
² Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
³ Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy.

Abstract

Introduction: Cardiac amyloidosis (CA) shares similar clinical and imaging characteristics (e.g., hypertrophic phenotype) with aortic stenosis (AS), but its prognosis is generally worse than severe AS alone. Recent studies suggest that the presence of CA is frequent (1 out of 8 patients) in patients with severe AS. The coexistence of the two diseases complicates the prognosis and therapeutic management of both conditions. Thus, there is an urgent need to standardize and optimize the diagnostic process of CA and AS. The aim of this study is to develop a robust and reliable radiomics-based pipeline to differentiate the two pathologies.

Methods: Thirty patients were included in the study, equally divided between CA and AS. For each patient, a cardiac computed tomography (CCT) was analyzed by extracting 107 radiomics features from the LV wall. Feature robustness was evaluated by means of geometrical transformations to the ROIs and intra-class correlation coefficient (ICC) computation. Various correlation thresholds (0.80, 0.85, 0.90, 0.95, 1), feature selection methods [p-value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA, sequential forwards selection] and machine learning classifiers (k-nearest neighbors, support vector machine, decision tree, logistic regression and gradient boosting) were assessed using a leave-one-out cross-validation. Data augmentation was performed using the synthetic minority oversampling technique. Finally, explainability analysis was performed by using the SHapley Additive exPlanations (SHAP) method.

Results: Ninety-two radiomic features were selected as robust and used in the further steps. Best performances of classification were obtained using a correlation threshold of 0.95, PCA (keeping 95% of the variance, corresponding to 9 PCs) and support vector machine classifier reaching an accuracy, sensitivity and specificity of 0.93. Four PCs were found to be mainly dependent on textural features, two on first-order statistics and three on shape and size features.

Conclusion: These preliminary results show that radiomics might be used as non-invasive tool able to differentiate CA from AS using clinical routine available images.

Keywords: aortic stenosis; cardiac amyloidosis; cardiac computed tomography; radiomic feature stability; radiomics.