B-mode and Elastic Bimodal Ultrasound Achilles Tendon Image Stitching Method
An image stitching and dual-modal technology, which is applied in image analysis, image enhancement, and image-to-image conversion, can solve problems such as evaluation of the severity of Achilles tendon diseases that are difficult for doctors, and achieve the effect of helping diagnosis and treatment evaluation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] Such as figure 1 As shown, a B-type and elastic dual-mode ultrasonic Achilles tendon image stitching method includes the following steps:
[0055] Step 1: Coarse registration of B-mode ultrasound images: Calculate the similarity measure of rigid registration based on the boundary vector field, and maximize the similarity measure of the rigid registration through particle swarm optimization algorithm to realize two B-mode ultrasound Achilles tendons Coarse registration of images;
[0056] Step 2: Fine registration of B-mode ultrasound images: use the B-spline free-form deformation model or differential homeomorphism model to perform non-rigid registration on the two B-mode ultrasound Achilles tendon images that have undergone rough registration to achieve fine registration ;
[0057] Step 3: Elastic ultrasound image registration: use the same spatial transformation relationship as the B-mode ultrasonic Achilles tendon image registration to register two elastic ultrasou...
Embodiment 2
[0082] Embodiment 2 has 5 steps in total, of which steps 1, 3, 4, and 5 are the same as the corresponding steps of Embodiment 1. Step 2 is: perform non-rigid registration on the B-type image to achieve fine registration. The technology used is to Diffeomorphism model.
[0083] In the step 2, the method of using the logarithmic diffeomorphism model to realize fine registration consists of the following specific steps:
[0084] Step 2-1: The target energy function of the algorithm of log diffeomorphism is:
[0085]
[0086] In the formula, u is the update field, s is the deformation;
[0087] Step 2-2: Set the initialization displacement field v;
[0088] Step 2-3: Calculate the deformation s=exp(v), and obtain the corresponding update field u by minimizing the target energy function;
[0089] Step 2-4: update the displacement field v, v←u+v;
[0090]Step 2-5: Do a Gaussian convolution on the update field u: u←K diff *u;K diff is a Gaussian convolution kernel;
[0091]...
PUM

Abstract
Description
Claims
Application Information

- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com