Combination of color-Doppler ultrasound and MRI to improve lacrimal gland lesion characterization: A machine learning approach.

In multiclass analysis (benign non-epithelial, benign epithelial, malignant non-epithelial and malignant epithelial), the random forest yielded a macro-averaged AUC of 0.857 (95% CI: 0.722-0.972) for the all-features model.

A 5-top features signature comprising apparent diffusion coefficient and resistance index values, echogenicity, age and lesion type (infiltrative vs. well-delineated mass), yielded an AUC of 0.785 (95% CI: 0.641-0.941) to distinguish between the four classes.