Segmentation method for unconventional cells in pathological section

Abstract

The invention discloses a segmentation method for unconventional cells in a pathological section. The method comprises the steps that cells in the pathological section are processed into separate to-be-segmented cell images with a transparent background, and a pixel tag is allocated to each pixel point of each to-be-segmented image; a mapping method is used to randomly distribute the to-be-segmented cell images on a white background, the cells are superposed according to a certain probability to form pseudo-input images, and corresponding full-image pixel tags are acquired and marked as real-value tags; the pseudo-input images and the real-value tags are used as training data to train a Mask-RCNN, so that the Mask-CNN has the abilities of detecting an unconventional cell boundary box and predicting the pixel tags in the box; and a new pathological section not marked is input into the converged Mask-RCNN, the unconventional cells in the non-segmented pathological section are detected, and a final segmentation result is obtained through postprocessing. Through the segmentation method, marking time can be effectively shortened, marking cost can be effectively lowered, a large amount of training data can be generated in a short time, and fitting can be well performed on a large amount of data.

Description

technical field [0001] The invention belongs to the field of medical image data processing, in particular to a method for segmenting unconventional cells in pathological slices. Background technique [0002] Image instance semantic segmentation (Instance Semantic Segmentation) is an important research direction of computer vision. Its task is to use a computer algorithm to mark the number of objects in the image using a square frame, and predict the category label for each pixel in the frame. Complete semantic segmentation in the box. Instance semantic segmentation tasks have important applications in scenarios such as autonomous driving, industrial manufacturing, and criminal tracking. In medical imaging, semantic segmentation is often used to segment cells, tissues, or organs in images. [0003] In 1998, LECUN and others first proposed the convolutional neural network (NCC) LeNet model, which was used by many banks in the United States to recognize handwritten numbers on...

AI Technical Summary

Problems solved by technology

[0005] However, due to the large difference between the segmentation of medical images and natural images, and the large number of negatives, it is often not effective to directly apply the general semantic segmentation model to images. In addition, semantic segmentation on natural images is often based on The relatively fixed shape features of the target, in the segmentation of pathological slices, due to the easy aggregation of the shape of unconventional cells in pathological slices, the size and shape are irregular, which brings great difficulties to the instance segmentation task

Images