Research on the Classification of Benign and Malignant Parotid Tumors Based on Transfer Learning and a Convolutional Neural Network

The classification of benign and malignant parotid tumors is very crucial for the selection surgical methods their prognoses. wide application deep learning technology in field medical imaging also provides new ideas computer-aided diagnosis gland tumors. In addition, because pathological types are complicated computed tomography (CT) images patients similar, some clinicians may misjudge due to a lack experience, which affects effect treatment prognosis. Therefore, this research proposes using solve problem. This study uses four classic pretraining models VGG16, InceptionV3, ResNet DenseNet classify CT transfer an improved convolutional neural network (CNN) model images. experimental results show that CNN achieves accuracy 97.78%, its performance better than those other methods. It can effectively diagnose improve diagnostic accuracy.