Digital pathological image segmentation method based on cascaded convolutional network and model thereof

The invention discloses a digital pathological image segmentation method and model based on a cascaded convolutional network, and the method comprises the steps: inputting a to-be-segmented pathological image, obtaining a high-resolution feature map and a low-resolution feature map through sampling, and obtaining the segmentation capability probability of the low-resolution feature map according to the current low-resolution feature map; comparing the segmentation capability probability with a test threshold value, if the segmentation capability probability is greater than the test threshold value, performing image segmentation through a trained low-resolution segmentation model, and if the segmentation capability probability is less than or equal to the test threshold value, and performing image segmentation through a trained high-resolution segmentation model to obtain a segmentation result; wherein the model comprises a first attention module, a threshold comparison module, a low-resolution segmentation mo