Search

Simple Summary: Transformer models, originally successful in natural language processing, have found application in computer vision, demonstrating promising results in tasks related to cancer image analysis. Despite being one of the prevalent and swiftly spreading cancers globally, there is a pressing need for accurate automated analysis methods for oral cancer. This need is particularly critical for high-risk populations residing in low- and middle-income countries. In this study, we evaluated the performance of the Vision Transformer (ViT) and the Swin Transformer in the classification of mobile-based oral cancer images we collected from high-risk populations. The results showed that the Swin Transformer model achieved higher accuracy than the ViT model, and both transformer models work better than the conventional convolution model VGG19. Oral cancer, a pervasive and rapidly growing malignant disease, poses a significant global health concern. Early and accurate diagnosis is pivotal for improving patient outcomes. Automatic diagnosis methods based on artificial intelligence have shown promising results in the oral cancer field, but the accuracy still needs to be improved for realistic diagnostic scenarios. Vision Transformers (ViT) have outperformed learning CNN models recently in many computer vision benchmark tasks. This study explores the effectiveness of the Vision Transformer and the Swin Transformer, two cutting-edge variants of the transformer architecture, for the mobile-based oral cancer image classification application. The pre-trained Swin transformer model achieved 88.7% accuracy in the binary classification task, outperforming the ViT model by 2.3%, while the conventional convolutional network model VGG19 and ResNet50 achieved 85.2% and 84.5% accuracy. Our experiments demonstrate that these transformer-based architectures outperform traditional convolutional neural networks in terms of oral cancer image classification, and underscore the potential of the ViT and the Swin Transformer in advancing the state of the art in oral cancer image analysis. [ABSTRACT FROM AUTHOR]

Simple Summary: Convolutional neural networks (CNNs) have shown promising performance in recognizing oral cancer. However, the lack of interpretability and reliability remain major challenges in the development of trustworthy computer-aided diagnosis systems. To address this issue, we proposed a neural network architecture that integrates visual explanation and attention mechanisms. It improves the recognition performance via the attention mechanism while simultaneously providing interpretability for decision-making. Furthermore, our system incorporates Human-in-the-loop (HITL) deep learning to enhance the reliability and accuracy of the system through the integration of human and machine intelligence. We embedded expert knowledge into the network by manually editing the attention map for the attention mechanism. Convolutional neural networks have demonstrated excellent performance in oral cancer detection and classification. However, the end-to-end learning strategy makes CNNs hard to interpret, and it can be challenging to fully understand the decision-making procedure. Additionally, reliability is also a significant challenge for CNN based approaches. In this study, we proposed a neural network called the attention branch network (ABN), which combines the visual explanation and attention mechanisms to improve the recognition performance and interpret the decision-making simultaneously. We also embedded expert knowledge into the network by having human experts manually edit the attention maps for the attention mechanism. Our experiments have shown that ABN performs better than the original baseline network. By introducing the Squeeze-and-Excitation (SE) blocks to the network, the cross-validation accuracy increased further. Furthermore, we observed that some previously misclassified cases were correctly recognized after updating by manually editing the attention maps. The cross-validation accuracy increased from 0.846 to 0.875 with the ABN (Resnet18 as baseline), 0.877 with SE-ABN, and 0.903 after embedding expert knowledge. The proposed method provides an accurate, interpretable, and reliable oral cancer computer-aided diagnosis system through visual explanation, attention mechanisms, and expert knowledge embedding. [ABSTRACT FROM AUTHOR]