Image segmentation method and system, medium and electronic terminal

Abstract

The invention provides an image segmentation method and system, a medium and an electronic terminal. The method comprises the steps of obtaining to-be-segmented training images; inputting the paired to-be-segmented training images into a positioning network, and obtaining a positioning feature map, wherein the step of obtaining the positioning feature map comprises the substeps that the paired training images to be segmented are subjected to same point feature map extraction and overall attention feature map extraction, and the positioning feature map is obtained according to the overall attention feature map; inputting the positioning feature map into a segmentation network for training to obtain an image segmentation model; inputting the paired tumor images to be segmented into the image segmentation model, and performing tumor image segmentation. According to the image segmentation method, the paired training images to be segmented are input into the positioning network, the same semantic features are extracted, different-point semantic features can also be extracted, the obtained positioning feature map is input into the segmentation network for training, the image segmentation model is obtained, cross-image semantic extraction is achieved, and the segmentation accuracy is high.

Description

technical field [0001] The present invention relates to the technical field of image segmentation, in particular to an image segmentation method, system, medium and electronic terminal. Background technique [0002] With the development of image segmentation technology, weakly supervised image segmentation learning has received more and more attention. Weakly supervised image segmentation learning uses image-level annotations with few annotations instead of pixel-by-pixel annotations. For example, weakly supervised images for tumor images Segmentation, the existing weakly supervised image segmentation learning usually obtains the location feature map through the classification network to supervise the segmentation network learning. However, at present, in the process of weakly supervised image segmentation learning, only the same location feature map is retained Semantic features, and only pay attention to the information in the current image, can not obtain more complete ob...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides an image segmentation method, system, medium, and electronic terminal to solve the problem of generating strategies for positioning feature maps in the prior art, only retaining the same semantic features, and only paying attention to the information in the current image, and cannot obtain better results. Complete object information, resulting in poor image segmentation and low segmentation accuracy

Images