# US 2008/0304744 A1 · Method for Facilitating Post-Processing of Images Using Deformable Meshes

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

- Number: US 2008/0304744 A1
- Document ID: US20080304744A1
- Status: Published application
- Kind: A1
- Application number: 12/097,855
- Filed: 2006-12-14
- Published: 2008-12-11
- Earliest claimed: 2005-12-19
- Assignees: Koninklijke Philips Electronics N.V.
- Inventors: Jochen Peters; Olivier Ecabert; Juergen Weese; Christian Lorenz; Jens Von Berg
- Web page: https://patentgrep.com/patent/US20080304744A1

## CPC

- G06T 9/001: {Model-based coding, e.g. wire frame}
- G06T 7/12: Edge-based segmentation
- G06T 7/149: involving deformable models, e.g. active contour models
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Method and system for facilitating post-processing of images using deformable meshes in which a deformable mesh model of an object such as an organ is extended by attaching information thereon in order to simplify and/or facilitate a desired post-processing task so that the post-processing task effected when the mesh is applied to the same object in an additional image can expeditiously use this information. The information may be attached to the mesh after its creation, for example, upon segmentation of the same object in some training image. The post-processing task can therefore be performed automatically without user interaction upon segmentation of the object in the additional image. Information is encoded on the mesh by enumerating a list of triangles or vertices of the mesh which have to be considered in the subsequent, post-processing task and by optionally providing additional parameters defining the precise post-processing algorithm(s) to be used.

## Claims

### Claim 1

A method for expediting post-processing of an object in an image being segmented using a mesh, comprising:
identifying a post-processing task to be performed upon the object after segmentation using the mesh (22);
determining information required for the post-processing task (24);
encoding the information on the mesh (30);
segmenting the object in a new image using the mesh with encoded information (36); and
performing the post-processing task by extracting the encoded information from the mesh (40).

### Claim 2 (depends on 1)

The method of claim 1, wherein the information required for the post-processing task is a list of triangles or vertices of the mesh for which the post-processing task will be performed.

### Claim 3 (depends on 1)

The method of claim 1, wherein the information required for the post-processing task is a distance value representing a distance between each triangle or vertex of the mesh and an object of interest for the post-processing task.

### Claim 4 (depends on 1)

The method of claim 1, wherein the information required for the post-processing task is a probability function representing the probability of usefulness of each triangle or vertex of the mesh for the post-processing task.

### Claim 5 (depends on 1)

The method of claim 1, wherein the step of determining the information required for the post-processing task comprises acquiring at least one training image including the object (20), segmenting the object in the at least one training image by means of the mesh (26) and deriving the information based on the segmentation of the at least one training image (28).

### Claim 6 (depends on 1)

The method of claim 1, further comprising defining a plurality of post-processing tasks, each having different required information to enable performance thereof.

### Claim 7 (depends on 1)

The method of claim 1, wherein the post-processing task is performed automatically without user interaction upon segmentation of the object in the new image.

### Claim 8 (depends on 1)

The method of claim 1, wherein the encoding of the information on the mesh comprises encoding different types of data required for the post-processing task in different regions of the mesh such that different post-processing tasks are applicable on different regions of the mesh.

### Claim 9 (depends on 1)

The method of claim 1, wherein the post-processing task involves execution of a post-processing algorithm and the encoding of the information on the mesh comprises encoding a regionally-varying parameter that controls the post-processing algorithm.

### Claim 10 (depends on 1)

The method of claim 1, wherein the object in the image is a heart, the information required for the post-processing task is the identification of triangles or vertices of the mesh within a predetermined distance to actual ostium positions, the mesh being encoded with the identified triangles or vertices and the distance between each triangle or vertices and the ostium position, the performance of the post-processing task comprising executing an algorithm to analyze the identified triangles or vertices to determine the likelihood of an ostium being present therein or thereat.

### Claim 11 (depends on 1)

The method of claim 1, wherein the object of the image is the heart, the information required for the post-processing task is the likelihood of each triangle or vertex of the mesh containing a surface in which a coronary vessel is near, the performance of the post-processing task comprising executing an algorithm to analyze only those triangles or vertices with a high likelihood of containing a surface in which a coronary vessel is near.

### Claim 12 (depends on 11)

The method of claim 11, wherein the information required for the post-processing task is a distance between each triangle or vertex of the mesh and coordinates of the coronary vessel, the performance of the post-processing task comprising executing an algorithm to analyze only those triangles or vertices within a predetermined distance from the coordinates of the coronary vessel.

### Claim 13 (depends on 1)

The method of claim 1, wherein the information required for the post-processing task is the identification of regions of the mesh to be subject to refined segmentation, the mesh being encoded with the triangles or vertices in each identified region, the performance of the post-processing task comprising executing a refined segmentation algorithm to additionally segment the portion of the image represented by the encoded triangles or vertices.

### Claim 14 (depends on 1)

The method of claim 1, wherein the object of the image is the heart, the information required for the post-processing task is the identification of triangles or vertices in an area of a valve region to be artificially flattened, the performance of the post-processing task comprising executing a flattening algorithm to shift the identified triangles or vertices.

### Claim 15

A method for processing an image and displaying the processed image, comprising:
in a preparatory step,
identifying a processing task to be performed upon an object after segmentation using a mesh (22),
determining information required for the processing task (24), and encoding the information on the mesh (30); and
in an operative step,
acquiring a new image containing the same object (34),
segmenting the object in the new image using the mesh with encoded information (36),
performing the processing task by extracting the encoded information from the mesh (38, 40), and
displaying a derivation of the new image modified by the performance of the processing task (42).

### Claim 16 (depends on 15)

The method of claim 15, wherein the step of determining the information required for the processing task comprises acquiring at least one training image including the object (20), segmenting the object in the at least one training image by means of the mesh (26) and deriving the information based on the segmentation of the at least one training image (28).

### Claim 17 (depends on 15)

The method of claim 15, wherein the information required for the processing task is a list of triangles or vertices of the mesh for which the processing task will be performed.

### Claim 18 (depends on 15)

The method of claim 15, wherein the information required for the processing task is a distance value representing a distance between each triangle or vertex of the mesh and an object of interest for the processing task.

### Claim 19 (depends on 15)

The method of claim 15, wherein the information required for the processing task is a probability function representing the probability of usefulness of each triangle or vertex of the mesh for the processing task.

### Claim 20

An image processing system (10), comprising:
an image acquisition device (12) for acquiring images of objects to be processed;
a display (16) for displaying images acquired by said image acquisition device (12) before and after processing;
a processing unit (14) coupled to said image acquisition device (12) and said display (16); and
a user interface (18) for controlling said image acquisition device (12) and said processing unit (14),
said processing unit (14) being arranged to enable via said user interface (18) initiation of image acquisition, initiation of mesh model-based segmentation of an object in the image, identification of a post-processing task to be performed upon the object after segmentation using the mesh and determination of information required for the post-processing task,
said processing unit (14) being further arranged to encode the information required for the post-processing task on the mesh, segment the object in a new image acquired by said image acquisition device (12) using the mesh with encoded information, automatically performing the post-processing task by extracting the encoded information from the mesh and display an image derived from the post-processing of the new image on said display (16).

### Claim 21

Computer readable media for effecting image processing in an image processing system (10) including an image acquisition device (12) for acquiring images of objects to be processed, a display (16) for displaying images acquired by the image acquisition device (12) before and after processing, and a user interface (18) for controlling the image acquisition device (12), the media being arranged to
initiate image acquisition via the user interface (18);
initiate mesh model-based segmentation of an object in the image via the user interface (18);
identify a post-processing task to be performed upon the object after segmentation using the mesh via the user interface (18);
determine information required for the post-processing task via the user interface (18);
encode the information on the mesh;
segment the object in a new image acquired by the image acquisition device (12) using the mesh with encoded information;
automatically perform the post-processing task by extracting the encoded information from the mesh; and
display an image derived from the post-processing of the new image on the display (16).
