Differentiation of Fat-poor and Atypical Adrenal Adenomas from Metastases: MRI-based Radiomic, Radiologic, and...

The accurate differentiation of fat-poor and atypical adrenal adenomas from metastases remains a diagnostic challenge. This study aimed to evaluate the predictive value of MRI-based radiomic, radiologic, and combined radiomic-radiologic machine learning (ML) models.

This single-center retrospective study included 37 patients with 44 adrenal masses (19 adenomas; 25 metastases). Data were split into training and testing sets (2:1). To expand the training set, data augmentation was performed by multiple sampling (56 labeled slices from 30 masses). Radiomic features were extracted from T2-weighted (T2W), in-phase, out-of-phase, and apparent diffusion coefficient (ADC) sequences, while mass size, T2W signal intensity, heterogeneity, and signal drop were assessed as radiologic features. Dimension reduction was performed by reliability analysis and wrapper-based feature selection with five algorithms. A support vector machine was used for classification, and performance was assessed using 10-fold cross-validation and unseen testing. Friedman test and post-hoc analyses compared bootstrapped unseen test AUCs.

Only 12% of radiomic features demonstrated excellent reproducibility. A significant difference was observed among the three models, χ2(2)=779.5, p<0.001. The combined radiomic-radiologic model achieved the best performance (AUC 0.939; accuracy 85.7%), outperforming radiomic-only (AUC 0.898; accuracy 85.7%) and radiologic-only (AUC 0.857; accuracy 78.5%) models (adjusted p<0.001).

Integrating radiomic and radiologic features improved classification performance compared to using either feature set alone. Although the reproducibility of radiomic features was limited, their complementary value enhanced model robustness.

A combined radiomic-radiologic ML model based on multi-sequence MRI may serve as a promising non-invasive tool for differentiating atypical adrenal adenomas from metastases.