Medical image super-pixel gray texture sampling feature-oriented graph attention network segmentation method
The invention discloses a medical image super-pixel gray texture sampling feature-oriented graph attention network segmentation method. The method comprises the following steps of 1, performing super-pixel segmentation; 2, extracting super-pixel gray texture sampling features; 3, carrying out superp...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
01.10.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a medical image super-pixel gray texture sampling feature-oriented graph attention network segmentation method. The method comprises the following steps of 1, performing super-pixel segmentation; 2, extracting super-pixel gray texture sampling features; 3, carrying out superpixel composition; 4, setting a super-pixel truth value label; 5, training a multi-head attention network model; and 6, carrying out superpixel classification and image segmentation. The invention provides the medical image attention network segmentation method with high segmentation precision and high operation efficiency, the data processing scale of a medical image segmentation task is reduced, and the training speed of a segmentation model is improved.
一种面向医学图像超像素灰度纹理采样特征的图注意力网络分割方法,包括以下步骤:步骤一:超像素分割;步骤二:提取超像素灰度纹理采样特征;步骤三:超像素构图;步骤四:超像素真值标签设定;步骤五:训练多头注意力网络模型;步骤六:超像素分类与图像分割。本发明提出了一种分割精度高、运行效率高的医学图像图注意力网络分割方法,降低了医学图像分割任务的数据处理规模,提高了其分割模型的训练速度。 |
---|---|
Bibliography: | Application Number: CN202110667134 |