Cell Classification Based on Self-Supervision and Multi-Level Feature Fusion

In order to solve the current problem of missed detection caused by the difficulty in labeling urine exfoliated cell data, the low number of labeled samples, and the low sensitivity of the classification model, a cell classification method is proposed in this paper. First, the multi-level feature fusion module fuses semantic feature information and spatial feature information. Secondly, the adaptive comparison loss function can automatically adjust the loss weight according to the similarity between cell features, so that the model can learn more discriminative high-dimensional features and improve the classification accuracy. The experimental results show that the urine exfoliated cell classification method proposed in this paper has high sensitivity and specificity on the test set, which has a certain improvement in sensitivity compared with the existing methods.