Oral Cancer Classification with CNN Based State-of-the-art Transfer Learning Methods

Abstract

The importance of oral and dental health closely affects other vital organs. In this study, CNN-based transfer learning models are built on histopathologic and intraoral images with benign and malignant lesions. Histopathologic and intraoral images from two different sources have benign or malignant classes of lesions in the mouth. EfficientNetB7, ResNet50, VGG16, and VGG19, Xception, ConvNextBase, and MobileNetV2 were used as transfer learning methods. Model training was performed with 80%-20% train test separation and 20% validation separation on the train set. Accuracy (Acc), Precision (Prec), Recall (Rec), and F1-score (F1) metrics were used to evaluate the model. In histopathologocial images, ResNet50 was ahead with 0.8125 Acc and 0.8525 F1. In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.

The importance of oral and dental health closely affects other vital organs. In this study, CNN-based transfer learning models are built on histopathologic and intraoral images with benign and malignant lesions. Histopathologic and intraoral images from two different sources have benign or malignant classes of lesions in the mouth. EfficientNetB7, ResNet50, VGG16, and VGG19, Xception, ConvNextBase, and MobileNetV2 were used as transfer learning methods. Model training was performed with 80%-20% train test separation and 20% validation separation on the train set. Accuracy (Acc), Precision (Prec), Recall (Rec), and F1-score (F1) metrics were used to evaluate the model. In histopathologocial images, ResNet50 was ahead with 0.8125 Acc and 0.8525 F1. In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.