Echocardiographic Tissue Characterization Using Radiomics in Patients With Transthyretin-Related Cardiac Amyloidosis

Abstract

Background: Transthyretin-related cardiac amyloidosis (ATTR-CA) is often diagnosed at an advanced stage. Emerging evidence suggests that radiomics applied to echocardiographic images (ie, ultrasonomics) can detect early myocardial texture changes in ATTR-CA.

Objectives: This study aimed to develop a radiomic model for characterizing ATTR-infiltrated myocardium via echocardiography.

Methods: Echocardiographic images in parasternal long-axis and apical 4-chamber views from ATTR-CA and control patients were collected across 4 Italian centers. A region of interest (ROI) within the interventricular septum was delineated. Ninety-four radiomic features were extracted and classified into 2 categories for analysis, based on whether they were ROI-dependent or independent. Five logistic regression models analyzed data from 3 centers (229 ATTR-CA, 224 controls) to assess diagnostic accuracy and area under the curve (AUC) of different sets of radiomic features, with external validation conducted on patients from a fourth center (32 ATTR-CA, 32 controls).

Results: Models analyzing the entire ROI using both ROI-dependent and ROI-independent features demonstrated high cross-validated accuracies (93%-95%) and AUC values (0.97-0.99). Using a fixed-size 0.5 × 0.5 cm ROI, these values decreased to 85% and 0.91, respectively, highlighting previous models' dependence on ROI size. The fifth model used 73 ROI-independent features on the entire ROI and demonstrated significantly better accuracy and AUC (92% and 0.97, respectively, P < 0.001), confirmed in the external validation cohort (87% and 0.95, respectively). Removing the least informative features slightly improved the model, achieving 90% accuracy and 0.95 precision.

Conclusions: This study showcases ultrasonomics potential to differentiate ATTR-CA and control patients by capturing disease-specific textural features independent of ROI dimensions.

Keywords: echocardiography; radiomic; texture; transthyretin cardiac amyloidosis.

Graphical abstract

Central Illustration

Echocardiographic Tissue Characterization Using Radiomics in Patients With Transthyretin-Related Cardiac Amyloidosis (A) Frame extraction and annotation were manually performed by an expert clinical cardiologist, delineating the ROI within IVS with a perimeter that varied according to IVS size. A variable-sized mask was drawn within the left ventricular cavity to provide a brightness reference for grayscale normalization. (B) Radiomic features were divided into 2 classes: shape features (such as ROI area or perimeter) and texture features, which were further divided into ROI-dependent features, whose values vary based on ROI dimension, and ROI-independent features, whose values remain constant regardless of ROI size. (C) Logistic regression models were built to classify control vs ATTR-CA, using different subsets of radiomic features as independent variables. Model performance was assessed via leave-one-out cross-validation. Ranking of radiomic features was computed based on regression coefficients. (D) The best ROI-independent predictive model was selected for external validation after following the same frame extraction and annotation process shown in panel (A). 4CH = 4-chamber; ATTR-CA = transthyretin cardiac amyloidosis; GLCM = gray level co-occurrence matrix; GLRLM = gray level run length matrix; IVS = interventricular septum; PLAX = parasternal long axis; ROI = region of interest.

Figure 1

Top 10 Discriminative Features Logistic regression coefficients of the 10 most discriminative features from model #1 (including all 94 texture and shape features, upper section) and from model #5 (including 73 ROI-independent texture features, lower section) in both the 4CH and PLAX views are shown. Positive coefficients indicate higher values of the corresponding feature in the ATTR-CA group, while negative coefficients indicate higher values in the control group. Feature categories (listed and explained in detail in Supplemental Table 2) are color-coded, and ROI-dependent features are marked with a star. 4CH = 4-chamber; ATTR-CA = transthyretin cardiac amyloidosis; PLAX = parasternal long axis; ROI = region of interest.