Computer-implemented method for providing a trained function set for determining scatter radiation information, computer-implemented method and evaluation device for determining scatter radiation information, computer program and electronically readable data carrier
DE102025105310B3Undetermined Publication Date: 2026-08-06SIEMENS HEALTHINEERS AG
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- SIEMENS HEALTHINEERS AG
- Filing Date
- 2025-02-13
- Publication Date
- 2026-08-06
Smart Images

Figure 00000000_0000_ABST
Abstract
The invention relates to a computer-implemented method for providing a trained set of functions for determining scatter radiation information (53) describing a scatter radiation contribution in a two-dimensional X-ray image (50) acquired with an X-ray device (75), comprising the following steps: - providing a first evaluation function (48) to be trained, which determines as output data an average distribution data set (52) from input data comprising the X-ray image (50), which describes an average scatter radiation distribution over a variation of at least one image acquisition parameter (51); - providing a second evaluation function (49) to be trained, which determines as output data transformation parameters (43) of a transformation (44) from input data comprising the at least one image acquisition parameter (51) during the acquisition of the X-ray image (50).so that the scatter radiation information (53) can be determined by applying the transformation (44) to the mean distribution data set (52),- providing a training data set for each of a first number of basic scenarios for which only the at least one image acquisition parameter (51) is variable, wherein each training data set comprises a second number of sub-data sets for different values of the at least one image acquisition parameter (51), each comprising a training X-ray image as input data for the first evaluation function (48), a training set of values for the at least one image acquisition parameter (51) as input data for the second evaluation function (48), and a training scatter radiation image (57) comprising the scatter radiation distribution as the respective basic truth,- separate training of the evaluation functions (48, 49) using the training data sets, and- providing the trained first and second evaluation functions (48,49).,
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Computer-implemented method and data processing device for scatter radiation correction and parameterization of a determination algorithm for determining a quality measure, computer program and data carrier
DE102023207125B3
Computer-implemented method, computer program, systems and x-ray facility for correction of x-ray image data with regard to noise effects
US20210330274A1
Devices, systems, and methods for deep-learning kernel-based scatter estimation and correction
US20230177745A1