Efficient deep learning models for oral squamous cell carcinoma classification in histopathological images

Abstract

Abstract Recent advances in deep learning have significantly improved the accuracy and efficiency of disease classification in digital pathology. Early diagnosis and precise classification of histopathological images are crucial for enabling timely treatment and improving therapeutic outcomes. Oral squamous cell carcinoma (OSCC) is one of the most common malignancies in the oral cavity, with manual histopathological examination serving as the gold standard for diagnosis—though it is time-consuming and subject to observer variability. This study investigates the performance of four deep learning convolutional neural network (CNN) models—ResNet50 (residual blocks), DenseNet201 (dense connectivity), EfficientNetB0 (compound scaling), and ConvNeXt_Tiny (transformer-based convolutions)—for binary classification (benign vs. carcinoma) of 10,000 histopathological images. Among the models, EfficientNetB0 achieved the highest accuracy of 97.6% and an ROC-AUC score of 0.9963, demonstrating superior generalization and discriminative power. ConvNeXt_Tiny followed with an accuracy of 95.92%, DenseNet201 with 86.08%, and ResNet50 with the lowest accuracy of 71.52%. The comparative analysis underscores the advantages of modern CNN architectures over traditional residual networks, supporting the integration of deep learning models into diagnostic frameworks for improved detection of oral squamous cell carcinoma.