Diagnosis of Cardiac Amyloidosis Using a Radiomics Approach Applied to Late Gadolinium-Enhanced Cardiac Magnetic Resonance Images: A Retrospective, Multicohort, Diagnostic Study

Examining the Difficulties in Identifying and Handling Cardiac Amyloidosis; Acquiring Important Knowledge and Robust Treatment Methods

Systemic amyloidosis is a rare protein misfolding and deposition condition that causes slow organ failure. Each of the more than 15 exclusive sorts of systemic amyloidosis, which encourage amyloid production and tissue deposition, is introduced by a unique precursor protein. Amyloidosis can affect various organs, including the heart, kidneys, liver, nerves, gastrointestinal tract, lungs, muscles, skin, and soft tissues. It can either be acquired or hereditary. Insidious and doubtful signs often cause a put-off in diagnosis. In the closing decade, noteworthy progressions have been made in the identity, prediction, and handling of amyloidosis. Shotgun proteomics based on mass spectrometry has revolutionized amyloid typing and enabled the identification of novel amyloid forms. It is critical to correctly identify the precursor protein implicated in amyloidosis because the kind of protein influences the proper treatment strategy. Cardiac amyloidosis is a disorder characterized by the systemic accumulation of amyloid protein in the myocardium's extracellular space, which causes a variety of symptoms. The buildup of amyloid aggregates precipitates myocardial thickening and stiffening, culminating in diastolic dysfunction and, in due course, heart failure. We examine every kind of systemic amyloidosis in this text to offer practitioners beneficial equipment for diagnosing and treating those unusual diseases. This review presents a comprehensive analysis of cardiac amyloidosis and consolidates current methods for screening, diagnosis, evaluation, and treatment alternatives.

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

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.

State of the Art: Quantitative Cardiac MRI in Cardiac Amyloidosis

Cardiac amyloidosis (CA) is characterized by amyloid infiltration in the myocardial extracellular space, causing heart failure. Patients with CA are currently underdiagnosed. Cardiac involvement is significantly associated with the prognosis and treatment decision-making for CA. Early identification and accurate stratification are the crucial first step in patient management. Comprehensive cardiac MRI-based evaluation of the cardiac structure, function, and myocardial tissue characterization assesses cardiac involvement by tracing disease processes. Emerging quantitative tissue characterization techniques have introduced new measures that can identify early staged CA and monitor disease progression or response after treatment. Quantitative cardiac MRI is becoming an instrumental tool in understanding CA, which leads to changes in individualized patient care. This review aimed to discuss the quantitative cardiac MRI-based assessment of CA using established and emerging techniques. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 3.