Method of Determining Corrected Geometries of Projection Images

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

This patent describes a method for automatically correcting the geometric alignment (acquisition geometries) of projection images, like those used in medical imaging (e.g., CT scans), to improve the quality of reconstructed 3D images. The method involves a two-step optimization process: first, it estimates provisional geometries using consistency checks among image pairs, and second, it refines these geometries by maximizing the image quality through a machine learning algorithm. This approach reduces artifacts and increases accuracy without requiring elaborate pre-calibration, even when the scan trajectory and object positioning vary.

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

• Medical imaging, such as computed tomography (CT) or C-arm X-ray imaging, where accurate 3D reconstructions are needed.
• Correction of motion artifacts due to patient movements (e.g., heartbeats or breathing) during scanning.
• Industrial non-destructive testing with variable scan trajectories.
• Any multi-angle imaging setup where the exact camera or detector position might deviate from planned positions, including robotic inspection systems.
• Post-processing software for improving legacy datasets with uncertain acquisition geometries.

BenefitsContent extracted from patent full text and abstract with AI.

• Improves the quality and accuracy of 3D reconstructions from projection images by correcting geometric misalignments.
• Reduces the need for complex and frequent calibration procedures, allowing free positioning and customized scan trajectories.
• Efficient computational approach combining fast initial corrections and more accurate machine-learning-based refinement.
• Can compensate for both equipment-related and object-related (e.g., patient movement) deviations.
• Adaptable to different hardware setups and operational scenarios, increasing its versatility.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

A method is provided for determining corrected acquisition geometries of projection images. The method includes providing a projection image dataset that has a plurality of projection images of an object under examination acquired by an acquisition device in different acquisition geometries. The method further includes determining a provisional acquisition geometry for each of the projection images by a first optimization method by minimizing a first cost function by varying the provisional acquisition geometry, wherein the first cost function is contingent on a plurality of consistency measures determined based on the provisional acquisition geometry for a respective pair of projection images. The method further includes determining the respective corrected acquisition geometry for each of the projection images by a second optimization method by minimizing a second cost function by varying the corrected acquisition geometries, wherein the second cost function is contingent on a measure for an image quality of image data reconstructed based on the projection images and the corrected acquisition geometries, and wherein, in a first iteration act of the second optimization method, the provisional acquisition geometries determined by the first optimization method are used as corrected acquisition geometries.