Neural network combining with clinical ultrasonography: A new approach for classification of salivary gland tumors.

OBJECTIVE

Little information is available about deep learning methods used in ultrasound images of salivary gland tumors. We aimed to compare the accuracy of the ultrasound-trained model to computed tomography or magnetic resonance imaging trained model.

MATERIALS AND

METHODS

Six hundred and thirty-eight patients were included in this retrospective study. There were 558 benign and 80 malignant salivary gland tumors. A total of 500 images (250 benign and 250 malignant) were acquired in the training and validation set, then 62 images (31 benign and 31 malignant) in the test set. Both machine learning and deep learning were used in our model.

RESULTS

The test accuracy, sensitivity, and specificity of our final model were 93.5%, 100%, and 87%, respectively. There were no over fitting in our model as the validation accuracy was similar with the test accuracy.

CONCLUSIONS

The sensitivity and specificity were comparable with current MRI and CT images using artificial intelligence.