Method for Reducing Artifacts Caused by Vessel Overlays in a Four-Dimensional Angiography Dataset, Computer-Implemented Method for Providing a Trained Function, Image Processing Device, Computer Program, Electronically Readable Data Carrier, and Training System

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

This invention relates to a method and system for reducing artifacts in four-dimensional (4D) angiography images that are caused by overlapping blood vessels. By using computational techniques, such as a trained function (likely involving machine learning), the system distributes the visible intensity from contrast agents more accurately across 3D vessel datasets. This enhances the quality and diagnostic value of 4D angiography images.

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

• Improving visualization quality in medical angiography scans for diagnosis of cardiovascular diseases
• Supporting radiologists in more accurate detection of vascular abnormalities and blockages
• Enabling cleaner and more reliable datasets for advanced surgical planning and navigation
• Providing training datasets and tools for developing and validating new medical imaging algorithms
• Integration into medical imaging devices and software for hospitals and clinics

BenefitsContent extracted from patent full text and abstract with AI.

• Significantly reduces imaging artifacts caused by vessel overlap, leading to clearer and more accurate images
• Enhances diagnostic capabilities for healthcare professionals
• Improves reliability and interpretability of 4D angiographic data
• Supports advanced image-guided interventions and pre-surgical planning
• Can be implemented as a computer program, making it scalable and easily distributable
• Facilitates the development and training of improved medical image processing tools

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

A method is provided for reducing artifacts occurring due to vessel overlaps in a four-dimensional angiography dataset acquired with administration of a contrast agent, wherein distribution data relating to a concentration of the contrast agent in the blood circulatory system is generated at the respective time points for a three-dimensional vessel dataset of a blood circulatory system or for a reduced dataset derived therefrom, e.g., by a trained function. A color intensity of a pixel showing a contrast agent filling state contained in a respective projection image of the blood circulatory system is distributed according to the distribution data at the respective time point of the acquired projection image across voxels of the vessel dataset that lie along a ray associated with the pixel in the backprojection.