Cell classification method and device based on multi-channel information fusion

The invention provides a cell classification method and device based on multi-channel information fusion, and the method comprises the steps: carrying out the instance segmentation of a cell nucleus image through a cell instance segmentation model, obtaining a cell region of each cell in the cell nucleus image, cutting a cell fluorescence image of the same cell in each channel from a fluorescence signal point image of each channel, and carrying out the segmentation of the cell region. Inputting the cell fluorescence image of any cell in each channel into a dichotomy model, performing image feature extraction on the cell fluorescence image of the cell in each channel by using the dichotomy model, extracting and fusing signal point features under each channel, and obtaining fused image features of the cell; according to the method and the device, the fusion image features of the cells are obtained, the cells are classified on the basis of the fusion image features of the cells, the cell classification result of