Registration of a 2D Image with a 3D Image

Simple SummaryContent extracted from patent full text and abstract with AI.

This invention describes a computer-based method for accurately aligning (registering) a two-dimensional (2D) image with a three-dimensional (3D) image. The process involves analyzing and identifying key contours (edges) in both images, applying a trained algorithm to improve alignment accuracy, and then generating a transformation instruction so the 2D image can be precisely overlaid onto the 3D image.

Use CasesContent extracted from patent full text and abstract with AI.

• Medical imaging, such as overlaying 2D X-rays onto 3D CT or MRI scans for diagnosis and surgical planning
• Industrial inspection, where 2D photos are aligned with 3D models to detect defects or deviations
• Augmented reality applications, integrating real-world 2D camera views onto 3D spatial data
• Robotics, where robotic vision systems must correlate 2D camera images with 3D environmental maps

BenefitsContent extracted from patent full text and abstract with AI.

• Enables more accurate and robust alignment of 2D and 3D images, improving diagnostics and analysis
• Facilitates advanced visualizations and overlays, enhancing user understanding in fields like medicine and engineering
• Reduces manual effort and operator error by automating the image registration process
• Supports improved precision in surgical navigation and planning by connecting different imaging modalities

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The disclosure relates to a computer-implemented method for the provision of a transformation instruction for registering a 2D image with a 3D image. The method includes: receiving the 2D image and the 3D image; generating input data based on the 2D image having contour pixels and the 3D image having contour voxels; applying a trained function to the input data for identification of contour pixels of the 2D image and contour voxels of the 3D image, wherein at least one parameter of the trained function is adjusted based on a comparison of training contour pixels with comparison contour pixels and a comparison of training contour voxels corresponding thereto with comparison contour voxels; determining the transformation instruction based on the identified contour pixels of the 2D image and the contour voxels corresponding thereto of the 3D image for registering the 2D image with the 3D image; and providing the transformation instruction.