Trained Function for Accurate Difference Image Data in Angiography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In digital subtraction angiography, errors occur due to structures with similar X-ray absorption to contrast medium, leading to inaccurate determination of difference image data records.
Innovation Solution
A method involving the use of a trained function that processes both first and multi-energetic real image data records, allowing for the determination of difference image data records by applying X-ray energies differently to distinguish between materials with similar absorption values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a trained function is applied to a real image data record to determine a difference image data record without an additional mask recording, then the examination time is reduced and productivity is improved, but structures with similar X-ray absorption (osseous structures, metal structures, calciferous structures) lead to errors in the determination of the difference image data record
Solution Approach 1:
The patent applies multiple X-ray energies (parameter change) to the real image data record instead of using a single energy level. By capturing images at different energy levels and processing them through the trained function, the system can differentiate between structures with similar absorption at one energy level but different absorption characteristics at other energy levels. This resolves the contradiction by maintaining high productivity (no mask recording needed) while improving measurement precision through multi-energetic differentiation.
2Measurement precision
If higher X-ray doses are used to improve the accuracy of difference image data record determination, then measurement precision is improved, but the X-ray burden on the examination volume increases
Solution Approach 1:
Instead of increasing the X-ray dose (intensity), the patent changes the parameter of X-ray energy by using multiple energy levels. This allows the system to achieve better material differentiation and accuracy in determining the difference image data record without proportionally increasing the harmful X-ray burden. The trained function processes multi-energetic data to extract accurate information while maintaining lower overall radiation exposure compared to single-high-dose approaches.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach results in a more accurate and less error-prone determination of difference image data records, reducing the need for higher X-ray doses and improving material differentiation in the examination region.
Implementation Method 1
In digital subtraction angiography (DSA for short), one or more vessels are represented in an examination volume by way of X-ray recordings... the contrast medium is introduced into the vessel during the examination in order to determine parameters... osseous structures, metal structures (e.g. implants) or calciferous structures (calcification in vessels) in the examination region have a similar X-ray absorption to contrast medium
Data Source
AI summary
A computer-implemented method is for providing a difference image data record. In an embodiment, the method includes a determination of a first real image data record of an examination volume in respect of a first X-ray energy, and a determination of a multi-energetic real image data record of the examination volume in respect of a first X-ray energy and a second X-ray energy, the second X-ray energy differing from the first X-ray energy. The method further includes the determination of the difference image data record of the examination volume by applying a trained function to input data, wherein the input data is based upon the first real image data record and the multi-energetic real image data record, as well as the provision of the difference image data record.