Automatic segmentation of brain structures in MRI images based on statistical multi-atlas registration optimization
A technology for automatic segmentation of magnetic resonance images, applied in the field of medical image processing, can solve problems affecting segmentation results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] Various details involved in the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be pointed out that the described embodiments are only intended to facilitate the understanding of the present invention, and do not have any limiting effect.
[0018] The invention is an automatic segmentation of a three-dimensional magnetic resonance brain image of a T1 weighted image. Such as figure 1 As shown, images 102 and 104 show the input images required for brain image segmentation, wherein 102 is an axial view of a layer of T1-weighted 3D MRI brain images, and 104 is a group of manually segmented atlases .
[0019] The present invention proposes a multi-atlas segmentation method based on iterative statistics under the framework of multi-atlas segmentation. Using a group of images with manual segmentation results as the atlas, first use the traditional statistical multi-atlas method to initial...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 