Image Biomarker Analysis of Ultrasonography Images of the Parotid Gland for Baseline Characteristic Establishment with Reduced Shape Effects

Background: This study aimed to analyze image biomarkers of the parotid glands in ultrasonography images with reduced shape effects, providing a reference for the radiomic diagnosis of parotid gland lesions. Methods: Ultrasound (US) and sialography images of the parotid glands, acquired from September 2019 to March 2024, were reviewed along with their clinical information. Parotid glands diagnosed as within the normal range were included. Overall, 91 US images depicting the largest portion of the parotid glands were selected for radiomic feature extraction. Regions of interest were drawn twice on 50 images using different shapes to assess the intraclass correlation coefficient (ICC). Feature dimensions were statistically reduced by selecting features with an ICC > 0.8 and applying four statistical algorithms. The selected features were used to distinguish age and sex using the four classification models. Classification performance was evaluated using the area under the receiver operating characteristic curve (AUC), recall, and precision. Results: The combinations of the information gain ratio algorithm or stochastic gradient descent and the naïve Bayes model showed the highest AUC for both age and sex classification (AUC = 1.000). The features contributing to these classifications included the first-order and gray-level co-occurrence matrix (high-order) features, particularly discretized intensity skewness and kurtosis, intensity skewness, and GLCM angular second moment. These features also contributed to achieving one of the highest recall (0.889) and precision (0.926) values. Conclusions: The two features were the most significant factors in discriminating radiomic variations related to age and sex in US images with reduced shape effects. These radiomic findings should be assessed when diagnosing parotid gland pathology versus normal using US images and radiomics in a heterogeneous population.