An image processing method and apparatus based on artificial intelligence, and a device and a storage medium, which belong to the technical field of computers. The method comprises: acquiring a slice image (201); segmenting the slice image to obtain a plurality of image blocks (202); and inputting the plurality of image blocks into a labeling model, and the labeling model extracting pixel features of the slice image according to the plurality of image blocks, determining a plurality of vertex positions of a polygonal area in the slice image according to the pixel features, connecting the plurality of vertex positions, and outputting labeling information of the slice image, wherein the polygonal area is an area in which target human tissue is located (203).
展开▼