Transform-based medical image segmentation method and system, medium and electronic equipment

Abstract

The invention provides a transform-based medical image segmentation method and system, a medium and electronic equipment, and the method comprises the steps: extracting a training set and a test set corresponding to a medical image; and constructing a first encoder block based on transformer to obtain a preset segmentation model, inputting the training set into the segmentation model for training, stopping training when the number of training times reaches a preset threshold, and inputting the test set into the preset segmentation model for testing to obtain a segmented image. According to the transform-based medical image segmentation method and system, the medium and the electronic equipment, the transform and the convolutional neural network are combined, improvement is carried out on the basis of a U-shaped structure of a traditional segmentation model, the transform is used as a backbone network, different features are fused, and deep supervision is carried out on the results of decoder blocks, so that the segmentation accuracy of the medical image is improved. Therefore, the model has stronger feature extraction and feature fusion capabilities, so that more accurate image segmentation is realized, and the precision of medical image segmentation is improved.

Description

technical field [0001] The present invention relates to the technical field of image segmentation, in particular to a transformer-based medical image segmentation method, system, medium and electronic equipment. Background technique [0002] Medical assistance systems are gradually becoming a reality, and can provide assistance to doctors in diagnosis and treatment by processing and analyzing medical images. [0003] In the process of medical image processing, image segmentation is a particularly critical step, and it is the basis for subsequent auxiliary diagnosis and treatment. Automatic object segmentation from medical images is a difficult task and is becoming the subject of extensive research. Contents of the invention [0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a transformer-based medical image segmentation method, system, medium and electronic equipment for solving the problem of low medi...

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a transformer-based medical image segmentation method, system, medium and electronic equipment for solving the problem of low medical image segmentation accuracy in the prior art

Images