Interpretable and Reliable Oral Cancer Classifier with Attention Mechanism and Expert Knowledge Embedding via Attention Map.

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]