Medical image registration method based on combination of mutual information and gradient information
A gradient information, medical image technology, applied in the field of medical image processing, can solve the problem of low precision
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2014-06-25
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to a medical image registration method based on the combination of mutual information and gradient information, in particular to a medical image registration method based on the combination of weighted normalized mutual information and gradient information, belonging to the field of medical image processing. Background technique
[0002] With the development of medicine, computer technology and bioengineering technology, medical imaging provides medical images of various modalities (CT, MRI, PET) for clinical diagnosis. In actual clinical applications, images of different modalities usually need to be Fusion together, get richer information in order to understand the comprehensive information of diseased tissues or organs, so as to make an accurate diagnosis or formulate an appropriate treatment plan. Image registration is an important prerequisite for image fusion. Image registration began in the 1990s. It refers to spatially cha...
Examples
Embodiment Construction
[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0037] figure 1 is a framework diagram for medical image registration. First, image acquisition is carried out, and two devices are designed: imaging equipment and acquisition equipment. Medical imaging equipment includes CT, MRI, B-ultrasound, etc.; secondly, image preprocessing, including image denoising and image enhancement; and then the preprocessed image The image is registered, and the registration method based on the combination of weighted normalized mutual information and improved gradient information is adopted, and the registration can be output after successful registration. The present invention mainly makes corresponding improvements to the similarity measure of registration.
[0038] figure 2 It is a specific flowchart of medical image registration based on GWNMI. After preprocessing, space transform the floating ...