Medical image segmentation system and method based on multi-level neural network
A medical image and neural network technology, which is applied in the field of medical image segmentation systems based on multi-level neural networks, can solve the problems of insufficient segmentation accuracy of images, and achieve the effects of rich features, efficient segmentation, and accurate image processing results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0041] Such as figure 1 As shown, the present invention provides a medical image segmentation system based on a multi-level neural network, including an image initialization module, a multi-level depth feature extraction module, a pyramid pooling long connection module and a multi-level segmentation module; an image initialization module for The original medical image collected is input to the image initialization model, and the initialization feature of the original medical image is extracted according to the image initialization model; the multi-level depth feature extraction module is used to train the multi-level depth feature extraction model using the initialization feature of the original medical image, and According to the multi-level depth feature extraction model after training, the multi-level depth features and shallow features of the medical image are respectively extracted; the pyramid pooling long connection module is used to use the pyramid pooling long connecti...
Embodiment 2
[0050] Such as Image 6 As shown, the present invention provides a medical image segmentation method based on a multi-level neural network medical image segmentation system, and its implementation method is as follows:
[0051] S1. Input the collected original medical image into the image initialization model, and use the image initialization model to extract the initialization features of the original medical image;
[0052] S2. Using the initialization features of the original medical image to train the multi-level deep feature extraction model, and using the trained multi-level deep feature extraction model to extract the multi-level deep features and shallow features of the medical image respectively;
[0053] S3. According to the shallow features of the medical image, the pyramid pooling long connection model is used to make up for the lost convolution information in the multi-level deep feature extraction model to obtain global aggregation features;
[0054] S4. Using t...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More