Method of Reconstructing a Three-Dimensional Outcome Image Data Set

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

This patent describes a method for reconstructing high-quality three-dimensional image datasets (such as CT scans) using two-dimensional images that are taken from a limited range of angles. The invention significantly reduces image artifacts that typically occur due to this restricted angular coverage by employing an artifact-reduction algorithm—potentially machine learning-based—and then uses both the artifact-reduced 3D data and the original 2D images together in the final reconstruction. This approach preserves real anatomical structures in the images while minimizing distortions and artifacts.

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

• Medical imaging (CT scans) in situations where full rotation around the patient is not possible, such as in operating rooms with C-arm systems.
• Imaging for trauma patients or in surgical settings where patient repositioning or equipment movement is limited.
• Industrial nondestructive testing of objects where access is restricted to certain angles only.
• Veterinary imaging when animals cannot be repositioned easily for full-angle scans.
• Mobile and field CT services, where equipment motion is inherently restricted.

BenefitsContent extracted from patent full text and abstract with AI.

• Produces high-quality 3D reconstructions even when only partial angular data is available, enabling imaging in difficult or constrained environments.
• Greatly reduces artifacts that commonly occur in limited-angle CT, improving clinical and diagnostic confidence.
• Minimizes the risk of accidentally removing real anatomical or structural features, unlike some machine learning post-processing methods.
• Supports both real-time and delayed processing modes, adaptable to local (machine) or remote (cloud) computing resources.
• Can lower the required radiation dose by reducing the number of exposures needed to obtain a diagnostically useful 3D image.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

Systems and methods are provided for reconstructing a three-dimensional result image data set from computed tomography from a plurality of two-dimensional images that create an image of an object undergoing examination from a particular imaging angle, The imaging angles of all the images lie within a restricted angular range. A three-dimensional artifact-reduced image data set is provided based on the two-dimensional images using an algorithm for reducing artifacts that are the result of a restriction of the angular range. The result image data set is reconstructed using a reconstruction algorithm that processes both the artifact-reduced image data set and the two-dimensional images as input data.