27May 2023
Neural network combining with clinical ultrasonography: A new approach for classification of salivary gland tumors

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

In this study, researchers aimed to assess the accuracy of a deep learning model trained on ultrasound images of salivary gland tumors compared to models trained on computed tomography (CT) or magnetic resonance imaging (MRI). They analyzed data from 638 patients, including 558 benign and 80 malignant tumors. The training and validation set consisted of 500 images, while the test set had 62 images. The final model achieved a test accuracy of 93.5%, sensitivity of 100%, and specificity of 87%. The results suggest that the deep learning model performed comparably to AI models trained on current MRI and CT images in terms of sensitivity and specificity.

  • #ent

Like

Save

Share