Leukocyte subtypes identification using bilinear self-attention convolutional neural network

Effective identification of leukocyte subtypes in microscopic images can help doctors diagnose diseases more accurately. Previous studies have achieved well performance by using segmentation techniques for multi-step processing. However, this increases the complexity of the whole identification process. In this paper, we proposed a novel model structure that can be trained end-to-end. The model combines attention mechanisms to emphasize the most discriminative features, and bilinear strategy to capture the interactions between features. We called this model Bilinear Self-Attention Network (BSA-Net). BSA-Net directly performs leukocyte subtypes identification in a one-step manner, which not only reduces complexity, but also achieves higher accuracy. To better understand the impact of the attention mechanism, we visualized the attention feature map in the BSA-Net model. Experiments demonstrated the effectiveness of our proposed method, which can meet the requirements of doctors for the accuracy and timeliness of cell identification results.

Automated summary

A novel model structure, BSA-Net, with attention mechanisms and bilinear strategy for leukocyte subtypes identification is proposed in this study. Experiments demonstrate that the model not only reduces complexity but also achieves higher accuracy, meeting doctors' requirements for accuracy and timeliness in cell identification results.