Efficient medical image segmentation method and system, terminal and medium

Abstract

The invention provides an efficient medical image segmentation method and system, a terminal and a medium, and the method comprises the steps: obtaining a medical image training set, training a first segmentation network for medical image pre-segmentation, and obtaining a segmentation feature map; optimizing network parameters of the first segmentation network and the segmentation feature map to obtain a second segmentation network; iteratively updating network parameters of the second segmentation network to convergence based on a medical image training set to obtain a final medical image segmentation network; and inputting the medical image into the final medical image segmentation network to obtain a segmentation result. As the network parameters and the segmentation feature map are low in precision and simple in calculation, the medical image segmentation result can be quickly given, and the method is suitable for being applied to auxiliary diagnosis on various medical devices.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a high-efficiency medical image segmentation method and system, a terminal, and a medium. Background technique [0002] Image segmentation technology based on deep learning has become an important component method of image segmentation in the continuous development of neural networks, and with the development of computer-aided medical care, medical image segmentation also plays an extremely important role in practical applications. It often It is used to identify and divide key lesion areas or tissues. Commonly used medical images, such as CT or MRI, use segmentation to identify pixels of organs or lesions in medical diagnosis to extract or display key information such as the shape and volume of these organs or tissues. This is the most challenging aspect of medical image analysis. one of the tasks. [0003] In recent years, after the U-net network stru...

AI Technical Summary

Problems solved by technology

This approach can be demanding, especially for high-resolution or 3D images

Images