# US 10,311,585 B2 · Mechanism for advanced structure generation and editing

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

- Number: US 10,311,585 B2
- Document ID: US10311585B2
- Status: Granted
- Kind: B2
- Application number: 12/821,985
- Filed: 2010-06-23
- Published: 2011-12-29
- Granted: 2019-06-04
- Earliest claimed: 2010-06-23
- Assignees: Varian Medical Systems International AG
- Applicants: Michael Huber; Michael Waschbuesch; Lasse Toimela; Patrik Kunz
- Inventors: Michael Huber; Michael Waschbuesch; Lasse Toimela; Patrik Kunz
- Web page: https://patentgrep.com/patent/US10311585B2

## CPC

- G06T 7/33: using feature-based methods
- A61N 5/103: {Treatment planning systems}
- G06T 7/337: {involving reference images or patches}
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10116: X-ray image
- G06T 2207/20096: Interactive definition of curve of interest
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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)

## Abstract

Embodiments of the present invention are directed to methods and a mechanism for manipulating images generated by radiotherapy machines used in radiation diagnostic and treatment applications. In one embodiment, a method is provided for intelligent automatic propagation of manual or automatic contouring across linked (e.g., registered) images and image data sets by acquiring one or more images of one or more image data sets; determining the correlation between the images with respect to identified structures; and generating a deformation map that establishes a correspondence for each point in the source image with a point in the target image. Subsequently, the intelligent propagation mechanism applies this deformation map individually to each structure of the source image and propagates the deformed structure to the target image.

## Claims

### Claim 1

A method for automatically propagating defined structures across data sets comprising:
accessing a first image acquired using a medical imaging system, the first image comprising a first plurality of structures and a plurality of manually contoured effects corresponding to the first plurality of structures;
accessing a second image acquired using the medical imaging system, the second image comprising a second plurality of structures corresponding to the first plurality of structures;
generating a deformation map in a processor of the computing system by mapping a first set of pixels comprising at least part of the first image to a second set of pixels comprising at least part of the second image, the deformation map defining a relativity between the first and second plurality of pixels and corresponding to the first and second pluralities of structures, respectively; and
based on the deformation map, using the processor of the computing system to automatically propagate the plurality of manually contoured effects comprised in the first image to the second image,
wherein mapping the first set of pixels to the second set of pixels comprises determining, in the processor, a relativity of a first plurality of pixel intensities corresponding to a feature comprised in the first set of pixels with a second plurality of pixel intensities corresponding to the same feature comprised in the second set of pixels.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the first plurality of structures comprises a first plurality of anatomical structures.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the second plurality of structures comprises a second plurality of anatomical structures.

### Claim 4 (depends on 1)

The method according to claim 1 wherein the first image is comprised in an image data set comprising a plurality of images.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the second image is comprised in the same image data set comprising the first image.

### Claim 6 (depends on 4)

The method according to claim 4, wherein the second image is comprised in a different image data set comprising the first image.

### Claim 7 (depends on 1)

The method of claim 1, wherein the propagating the plurality of manually contoured effects comprises:
applying the deformation map to the plurality of manually contoured effects; and
copying an output of the applying the deformation to the plurality of manually contoured effects on to the second image.

### Claim 8 (depends on 1)

The method according to claim 1, wherein at least one of the first image and the second image comprises a scan image generated by a group of imaging modalities comprising:
a computer tomography (CT);
a magnetic resonance imaging (MRI);
an X-ray imaging; and
a cone-beam computer tomography (CBCT).

### Claim 9 (depends on 1)

The method according to claim 1, wherein the deformation map comprises a vector field.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the mapping comprises:
comparing the first plurality of pixels to the second plurality of pixels; and
determining a displacement of any pixels of the second image relative to a position of a corresponding pixel of the first image.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the determining an relativity comprises:
determining the first plurality of pixel intensities for the first plurality of pixels;
determining the second plurality of pixel intensities for the second plurality of pixels; and
comparing the first plurality of pixel intensities with the second plurality of pixel intensities.

### Claim 12

A method for propagating updated structural contouring data among a plurality of data sets, the method comprising:
acquiring initial image data of a plurality of anatomical structures, the initial image data being acquired using an a medical imaging system;
receiving, via a user interface of a computing system, user input corresponding to a contouring data of the plurality of anatomical structures in the initial image data;
editing the plurality of anatomical structures in the initial image data according to contouring data;
acquiring, using the medical imaging system, updated image data of the plurality of anatomical structures in an updated image data set;
establishing a relationship between the updated image data and the initial image data in the computing system;
generating a deformation map in a processor of the computing system, the deformation map defining structural deviation between the initial image data and the updated image data by comparing a first plurality of pixels comprising the initial image data to a second plurality of pixels comprising the updated image data to determine a presence of structural deviation between the initial image data and the updated image data based on a relativity between the first and second plurality of pixels; and
based on the deformation map, using the processor of the computing system to propagate the contour data comprised in the initial image data to the updated image data,
wherein the relativity between the first plurality of pixels to the second plurality of pixels comprises a relativity between a first plurality of pixel intensities corresponding to a feature comprised in the first plurality of pixels and a second plurality of pixel intensities corresponding to the same feature comprised in the second plurality of pixels.

### Claim 13 (depends on 12)

The method according to claim 12, wherein the editing the plurality of anatomical structures further comprises:
creating a treatment plan for at least a portion of an anatomical structure of the plurality of anatomical structures in the initial image data.

### Claim 14 (depends on 13)

The method according to claim 13, further comprising:
subsequent to the propagating the contour data comprised in the initial image data to the updated image data, adapting the treatment plan to comprise an updated treatment plan based on the updated image data.

### Claim 15 (depends on 14)

The method according to claim 14, further comprising:
treating the target volume according to the updated treatment plan.

### Claim 16

A radiation therapy device comprising:
one or more radiation sources;
one or more imagers configured to receive radiation from the one or more radiation sources, and to generate data representing a target image comprising one or more anatomical structures; and
a computing device configured to access data representing a source image comprising manual contouring and a deformation map mapping a relativity between a first plurality of pixels comprising the source image to a second plurality of pixels comprising the data image, wherein the manual contouring is automatically propagated while taking into account the deformation map,
wherein the relativity between the first plurality of pixels to the second plurality of pixels comprises a relativity between a first plurality of pixel intensities corresponding to a feature comprised in the first plurality of pixels and a second plurality of pixel intensities corresponding to the same feature comprised in the second plurality of pixels.

### Claim 17 (depends on 16)

The device according to claim 16, wherein the computing device is further configured to generate a deformation map which maps the correspondence between the source image and the target image.

### Claim 18 (depends on 17)

The device according to claim 17, wherein the manual contouring is automatically propagated to the target image by applying the deformation map to the source image and replicating the manual contouring on to the target image while adjusting for the deformation map.

### Claim 19 (depends on 1)

The method according to claim 1, wherein the relativity of the first plurality of pixel intensities and the second plurality of pixel intensities corresponding to the second set of pixels is stored as a three dimensional vector field.