Deep learning-based pathology image automatic segmentation system

Abstract

The invention relates to the technical field of image processing, in particular to a Deep learning-based pathology image automatic segmentation system, and the system comprises: an image collection module which is used for collecting a plurality of pathological images; the image segmentation module that is used for uniformly dividing the plurality of pathological images into a plurality of segmented images; the image labeling module used for dividing the segmented image into a plurality of regions according to a preset clustering algorithm, and labeling each region with a label in each region to obtain a plurality of label images; the model training module used for taking the segmented image and the label image as input and taking the corresponding real segmented image as output, and training to obtain a deep learning segmentation network model; and the prediction module used for inputting the segmented image to be segmented and the label image into the deep learning segmentation network model to obtain a predicted segmented image, wherein the predicted segmented image is used as a reference basis for doctors. According to the invention, unsupervised pathological image segmentation is realized, the image segmentation precision is improved, and the segmentation error is reduced.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an automatic pathological image segmentation system based on deep learning. Background technique [0002] Deep learning (DL, Deep Learning) is a new research direction in the field of machine learning (ML, Machine Learning). It is introduced into machine learning to make it closer to the original goal-artificial intelligence (AI, Artificial Intelligence). [0003] Deep learning is to learn the internal laws and representation levels of sample data. The information obtained during the learning process is of great help to the interpretation of data such as text, images and sounds. Its ultimate goal is to enable machines to have the ability to analyze and learn like humans, and to be able to recognize data such as text, images, and sounds. Deep learning is a complex machine learning algorithm that has achieved results in speech and image recognition that far exceed...

AI Technical Summary

Problems solved by technology

[0007] At present, most of the existing technical solutions use manual labeling to label the images to be segmented, but manual labeling has high requirements for labelers, and requires labelers to have sufficient prior knowledge, so manual labeling is more difficult ,the cost is too high

At the same time, the existing technical solutions have low accuracy and large errors in image segmentation, which is not conducive to the development of clinical medicine.

Images