A 3D/2D Medical Image Registration Method Based on Deep Reinforcement Learning
A technology of reinforcement learning and medical images, applied in medical images, image analysis, image enhancement, etc., can solve the problems of unfavorable registration accuracy, need for manual intervention, and low registration accuracy, so as to reduce the number of subsequent iteration steps and solve the problem of initialization problem, the effect of improving the registration accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0035] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:
[0036] GPU (Graphics Processing Unit): graphics processing unit;
[0037] DRR (Digitally reconstructed radiographs): Digitally reconstructed radiographs;
[0038] Dueling Networks: Competition Networks.
[0039] figure 1 It is a flow chart of the 3D / 2D medical image registration method based on deep reinforcement learning of the present invention.
[0040] In this example, if figure 1 Shown, a kind of 3D / 2D medical image registration method based on deep reinforcement learning of the present invention comprises the following steps:
[0041] S1. Acquire 2D and 3D medical images
[0042] Obtain X-ray images as intraoperative 2D reference images in the registration process, and obtain LIDC-IDRI chest CT as the training image set and preoperative 3D images to be registered in the registration process.
[0043] S2. Training image set preproce...
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