# US 2026/0076637 A1 · Image correction method and medical x-ray device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0076637 A1
- Document ID: US20260076637A1
- Status: Published application
- Kind: A1
- Application number: 19/328,086
- Filed: 2025-09-12
- Published: 2026-03-19
- Earliest claimed: 2024-09-13
- Applicants: Siemens Healthineers AG
- Inventors: Philipp` Roser; Alois Regensburger
- Web page: https://patentgrep.com/patent/US20260076637A1

## CPC

- A61B 6/5258: {involving detection or reduction of artifacts or noise}
- A61B 6/4233: {using matrix detectors}
- A61B 6/482: {involving multiple energy imaging}
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G06T 5/73: Deblurring; Sharpening
- G06T 2207/10116: X-ray image
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20192: Edge enhancement; Edge preservation
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for correcting artifacts includes recording an X-ray image of an object by an X-ray detector. A primary X-ray spectrum of X-ray radiation is provided, and an off focal radiation spectrum in relation to the primary X-ray spectrum is provided. An image X-ray spectrum is determined from the X-ray image for each image pixel. One weighting factor each is determined by calculating a quotient between high-energy irradiation and overall energy irradiation for each image pixel, and a weighted image is determined from the weighting factors of the image pixels. A high-energy image is provided from high-energy components of the image X-ray spectrum, and low-energy components of the image X-ray spectrum are processed by taking into account image features and/or structures of the high-energy image. The high-energy component and the processed low-energy component are recombined for each image pixel, and a corrected X-ray image is created.

## Claims

### Claim 1

A method for correcting artifacts, generated by off focal radiation, in an X-ray image of an object, the method comprising:
recording the X-ray image I(u, v) of the object by an X-ray detector with a number of detector pixels, the object being radiographed by X-ray radiation emitted by an X-ray tube;
providing a primary X-ray spectrum I0(u, v, E) of the X-ray radiation and providing an estimated or ascertained off focal radiation spectrum in relation to the primary X-ray spectrum;
determining an image X-ray spectrum IS(u, v, E) from the X-ray image for each image pixel;
dividing the image X-ray spectrum IS(u, v, E) into a high-energy component Ih(u, v) and a low-energy component Il(u, v) for each image pixel;
determining a weighting factor wuv, the determining of the weighting factor wuv comprising calculating a quotient between high-energy irradiation and overall energy irradiation for each image pixel and determining a weighted image W(u, v) from the weighting factors wuv of the image pixels;
providing a high-energy image from the high-energy components Ih(u, v);
processing the low-energy components Il(u, v) for each image pixel with regard to the off focal radiation portion using at least one image-processing algorithm, the processing comprising taking into account image features, structures, or the image features and the structures of the high-energy image; and
recombining the high-energy component and the processed low-energy component for each image pixel and creating a corrected X-ray image therefrom.

### Claim 2 (depends on 1)

The method of claim 1, wherein dividing the image X-ray spectrum for each image pixel into a high-energy component and a low-energy component comprises selecting a first threshold value between high energy and low energy, such that the off focal radiation portion of the high-energy component is negligible.

### Claim 3 (depends on 1)

The method of claim 1, wherein the primary X-ray spectrum is calculated from an X-ray voltage, an X-ray current, a filtering of the X-ray radiation, and a position of the image pixels, and
wherein u, v represent positions of the image pixels.

### Claim 4 (depends on 1)

The method of claim 1, wherein the off focal radiation spectrum is determined by simulation or by a machine learning algorithm.

### Claim 5 (depends on 4)

The method of claim 4, wherein the simulation is a Monte Carlo simulation.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the image X-ray spectrum for each image pixel is carried out using a division of the X-ray image into at least one bone density image and one water density image and using the primary X-ray spectrum and the off focal radiation spectrum.

### Claim 7 (depends on 6)

The method of claim 6, wherein dividing the X-ray image into the at least one bone density image and the water density image is carried out using patient convexity conditions or using bone structure constructions based on detected image contents.

### Claim 8 (depends on 6)

The method of claim 6, wherein determining the image X-ray spectrum is carried out using the Beer-Lambert law.

### Claim 9 (depends on 2)

The method of claim 2, wherein the first threshold value between high energy and low energy is selected such that the off focal radiation of the high-energy component drops below a limit value.

### Claim 10 (depends on 1)

The method of claim 1, wherein the high-energy components Ih(u, v) are representable as: Ih(u, v)=I(u, v)·W(u, v).

### Claim 11 (depends on 1)

The method of claim 1, wherein the at least one image-processing algorithm comprises an edge reinforcement algorithm, a guided filter algorithm, or the edge reinforcement algorithm and the guided filter algorithm.

### Claim 12 (depends on 1)

The method of claim 1, wherein the recording, the providing of the primary X-ray spectrum of the X-ray spectrum of the X-ray radiation and the providing of the estimated or ascertained off focal radiation spectrum, the determining of the image X-ray spectrum, the dividing, the determining of the weighting factor, the providing of the high-energy image, the processing, the recombining, or any combination thereof is executed using machine learning.

### Claim 13

A medical X-ray device comprising:
an X-ray detector with a number of image pixels for recording an X-ray image of an object radiographed by X-ray radiation;
an X-ray tube comprising a cathode and an anode, the X-ray tube being configured to generate X-ray radiation that also generates off focal radiation,
a controller configured to:
record the X-ray image I(u, v) of the object by the X-ray detector with the number of detector pixels, the object being radiographed by the X-ray radiation emitted by the X-ray tube;
provide a primary X-ray spectrum I0(u, v, E) of the X-ray radiation and provide an estimated or ascertained off focal radiation spectrum in relation to the primary X-ray spectrum;
determine an image X-ray spectrum IS(u, v, E) from the X-ray image for each image pixel;
divide the image X-ray spectrum IS(u, v, E) into a high-energy component Ih(u, v) and a low-energy component Il(u, v) for each image pixel;
determine a weighting factor wuv, the determination of the weighting factor wuv comprising calculation of a quotient between high-energy irradiation and overall energy irradiation for each image pixel and determination of a weighted image W(u, v) from the weighting factors wuv of the image pixels;
provide a high-energy image from the high-energy components Ih(u, v);
process of the low-energy components Il(u, v) for each image pixel with regard to the off focal radiation portion using at least one image-processing algorithm, the process comprising taking into account image features, structures, or the image features and the structures of the high-energy image; and
recombine the high-energy component and the processed low-energy component for each image pixel and create a corrected X-ray image therefrom;
a calculation unit; and
an image processing unit with at least one algorithm for processing at least one X-ray image.

### Claim 14 (depends on 13)

The medical X-ray device of claim 13, further comprising at least one algorithm for machine learning.
