Objective
This study aims to develop an algorithm for the automatic segmentation of the parotid gland on CT images of the head and neck using U-Net architecture and to evaluate the model’s performance.
Methods
In this retrospective study, a total of 30 anonymized CT volumes were used, which were sliced into 931 axial images of the parotid glands. Ground truth labeling was performed by two oral and maxillofacial radiologists using the CranioCatch Annotation Tool. The images were resized to 512 × 512 and split into training (80%), validation (10%), and testing (10%) subgroups. A deep convolutional neural network model was developed using U-net architecture. The automatic segmentation performance was evaluated in terms of the F1-score, precision, sensitivity, and the Area Under Curve (AUC) statistics. The threshold for a successful segmentation was determined by the intersection of over 50% of the pixels with the ground truth.
Results
The AI model's F1-score, precision, and sensitivity in segmenting the parotid glands in the axial CT slices were found to be 1. The AUC value was calculated as 0.96. This study has shown that AI models based on deep learning can be used to automatically segment the parotid gland on axial CT images.
