# US 2026/0097235 A1 · Pre-treatment processing of phase-contrast and/or dark-field image data for radiation therapy

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

- Number: US 2026/0097235 A1
- Document ID: US20260097235A1
- Status: Published application
- Kind: A1
- Application number: 18/906,177
- Filed: 2024-10-04
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Assignees: Siemens Healthineers International AG
- Applicants: Siemens Healthineers International AG
- Inventors: Vidhya KRISHNAMURTHI; Jörg FREUDENBERGER; Thomas WEBER; Michael FOLKERTS
- Web page: https://patentgrep.com/patent/US20260097235A1

## CPC

- A61N 5/1037: {taking into account the movement of the target, e.g. 4D-image based planning}
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- A61N 5/1045: {using a multi-leaf collimator, e.g. for intensity modulated radiation therapy or IMRT}
- G06V 10/145: Illumination specially adapted for pattern recognition, e.g. using gratings
- G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H 30/40: for processing medical images, e.g. editing
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Example methods and systems for image data processing for radiation therapy are provided. In one example, a computer system may obtain planning image data that is generated using an imaging source to emit an imaging beam towards a patient and a detector to image a target structure within the patient during a pre-treatment phase of radiation therapy. Based on the planning image data, the computer system may generate at least one of (a) phase-contrast image data associated with the target structure and (b) dark-field image data associated with the target structure. The computer system may generate template image data associated with the target structure by processing at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) derived image data that is generated based on the phase-contrast image data or the dark-field image data.

## Claims

### Claim 1

A method for a computer system to perform image data processing for radiation therapy, wherein the method comprises:
obtaining planning image data that is generated using an imaging source to emit an imaging beam towards a patient and a detector to image a target structure within the patient during a pre-treatment phase of radiation therapy;
based on the planning image data, generating at least one of (a) phase-contrast image data associated with the target structure and (b) dark-field image data associated with the target structure; and
generating template image data associated with the target structure by processing at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) derived image data that is generated based on the phase-contrast image data or the dark-field image data, wherein the template image data is generated for tracking the target structure during a treatment phase of the radiation therapy.

### Claim 2 (depends on 1)

The method of claim 1, wherein obtaining the planning image data comprises:
obtaining the planning image data that is generated using a grating-based imaging system that includes the imaging source, the detector and multiple gratings that are positioned between the imaging source and the detector.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating at least one of (a) the phase-contrast image data and (b) the dark-field image data comprises:
determining first parameter data associated with the planning image data that includes a set of multiple planning images associated with a set of respective multiple phase steps, wherein the first parameter data includes first intensity offset data, first amplitude data and first phase data;
determining second parameter data associated with reference image data that is generated using the grating-based imaging system without the patient, wherein the reference image data includes a set of multiple reference images associated with the set of respective multiple phase steps, wherein the second parameter data includes second intensity offset data, second amplitude data and second phase data; and
based on the first parameter data and the second parameter data, generating (a) the phase-contrast image data, (b) the dark-field image data and (c) absorption image data.

### Claim 4 (depends on 1)

The method of claim 1, wherein generating the template image data comprises at least one of the following:
in response to determination that first metric data associated with the phase-contrast image data satisfies a first threshold, selecting the phase-contrast image data for use in generating the template image data; and
in response to determination that second metric data associated with the dark-field image data satisfies the first threshold or a second threshold, selecting the dark-field image data for use in generating the template image data.

### Claim 5 (depends on 1)

The method of claim 1, wherein the method further comprises:
generating the derived image data by applying a function to combine or calculate a ratio between at least two of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) absorption image data.

### Claim 6 (depends on 1)

The method of claim 1, wherein generating the template image data comprises:
identifying one or more regions of interest in input data associated with a particular gantry angle, wherein the input data includes at least one of (a) the phase-contrast image data, (b) the dark-field image data, and (c) the derived image data; and
extracting the one or more regions of interest from the input data to generate a template image associated with the particular gantry angle.

### Claim 7 (depends on 1)

The method of claim 1, wherein generating the template image data comprises:
generating the template image data using an artificial intelligence (AI) engine to process at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) the derived image data, wherein the AI engine includes multiple processing layers that are trained to perform template generation.

### Claim 8

A radiation therapy system, comprising:
a grating-based imaging system that includes an imaging source, a detector and multiple gratings that are positioned between the imaging source and the detector; and
a computer system configured to:
obtain, from the grating-based imaging system, planning image data that is generated using the imaging source to emit an imaging beam towards the multiple gratings and the detector to image a target structure within a patient during a pre-treatment phase of radiation therapy;
based on the planning image data, generate at least one of (a) phase-contrast image data associated with the target structure and (b) dark-field image data associated with the target structure; and
generate template image data associated with the target structure by processing at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) derived image data that is generated based on the phase-contrast image data or the dark-field image data, wherein the template image data is generated for tracking the target structure during a treatment phase of the radiation therapy.

### Claim 9 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is configured to generate at least one of (a) the phase-contrast image data and (b) the dark-field image data by:
determining first parameter data associated with the planning image data that includes a set of multiple planning images associated with a set of respective multiple phase steps, wherein the first parameter data includes first intensity offset data, first amplitude data and first phase data;
determining second parameter data associated with reference image data that is generated using the grating-based imaging system without the patient, wherein the reference image data includes a set of multiple reference images associated with the set of respective multiple phase steps, wherein the second parameter data includes second intensity offset data, second amplitude data and second phase data; and
based on the first parameter data and the second parameter data, generating (a) the phase-contrast image data, the dark-field image data and (c) absorption image data.

### Claim 10 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is configured to generate the template image data by:
in response to determination that first metric data associated with the phase-contrast image data satisfies a threshold, selecting the phase-contrast image data for use in generating the template image data.

### Claim 11 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is configured to generate the template image data by:
in response to determination that second metric data associated with the dark-field image data satisfies a threshold, selecting the dark-field image data for use in generating the template image data.

### Claim 12 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is further configured to:
generate the derived image data by applying a function to combine or calculate a ratio between at least two of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) absorption image data.

### Claim 13 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is configured to generate the template image data by:
identifying one or more regions of interest in input data associated with a particular gantry angle, wherein the input data includes at least one of (a) the phase-contrast image data, (b) the dark-field image data and (c) the derived image data; and
extracting the one or more regions of interest from the input data to generate a template image associated with the particular gantry angle.

### Claim 14 (depends on 8)

The radiation therapy system of claim 8, wherein the computer system is configured to generate the template image data by:
generating the template image data using an artificial intelligence (AI) engine to process at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data and (c) the derived image data, wherein the AI engine includes multiple processing layers that are trained to perform template generation.

### Claim 15

A method for a computer system to perform target structure tracking for radiation therapy, wherein the method comprises:
obtaining treatment image data that is generated using an imaging source to emit an imaging beam towards a patient and a detector to image a target structure within the patient during a treatment phase of radiation therapy;
selecting template image data that is generated based on at least one of the following: (a) phase-contrast image data associated with the target structure, (b) dark-field image data associated with the target structure and (c) derived image data that is generated based on the phase-contrast image data or the dark-field image data; and
based on the selected template image data and the treatment image data, determining position data associated with the target structure, thereby tracking the target structure during the treatment phase.

### Claim 16 (depends on 15)

The method of claim 15, wherein selecting the template image data comprises:
selecting the template image data that is generated based on planning image data that is acquired during a pre-treatment phase of radiation therapy, wherein the planning image data is processed to generate at least one of the following: (a) the phase-contrast image data, (b) the dark-field image data or (c) the derived image data.

### Claim 17 (depends on 15)

The method of claim 15, wherein determining the position data comprises:
performing template matching to match (a) the treatment image data, being absorption treatment image data, to (b) the selected template image data that includes one or more template images associated with the target structure.

### Claim 18 (depends on 15)

The method of claim 15, wherein determining the position data comprises:
processing the treatment image data to generate at least one of the following: (a) phase-contrast treatment image data associated with the target structure, (b) dark-field treatment image data associated with the target structure, and (c) derived treatment image data that is generated based on the phase-contrast treatment image data or the dark-field treatment image data.

### Claim 19 (depends on 18)

The method of claim 18, wherein determining the position data comprises:
performing template matching based on the selected template image data and at least one of the following: (a) the phase-contrast treatment image data, (b) the dark-field treatment image data and (c) the derived treatment image data.

### Claim 20 (depends on 18)

The method of claim 18, wherein obtaining the treatment image data comprises:
obtaining the treatment image data that is generated using a grating-based imaging system that includes the imaging source, the detector and multiple gratings that are positioned between the imaging source and the detector.
