Meta-learning cell nucleus segmentation system and method based on label correction

The invention discloses a meta-learning cell nucleus segmentation system and method based on label correction. The system comprises a cell nucleus extraction module, a segmentation correction module and a post-processing module. The method comprises the following steps: for an original pathological picture and noise marks of corresponding parts thereof, extracting all connected domains, and performing pixel-level mask correction; for each extracted connected domain noise label and a corresponding original image, completing correction of noise labels through the label correction network, and supervising training of the segmentation network; after the correction mask of each connected domain noise label is obtained, using the watershed algorithm with identifiers for all the correction masks, labels of overlapped cell nucleuses are segmented, and finally obtaining the segmentation boundary for each cell nucleus. The network model trained by the invention can accurately identify the boundary contour of each cell