Generating supplementary slice images based on atlas data

Patent metadata

Field	Value
Publication number	US-9865057-B2
Application number	US-201315024542-A
Country	US
Kind code	B2
Filing date	Sep 30, 2013
Priority date	Sep 30, 2013
Publication date	Jan 9, 2018
Grant date	Jan 9, 2018

Abstract

A medical data processing method of determining a virtual image ( 2 ) of a part of a patient's body ( 4 ), the method being constituted to be executed by a computer and comprising the following steps: a) acquiring (S 1 ) patient image data describing at least two two-dimensional patient images ( 1 ) of anatomical body parts ( 3 ) of the patient's body ( 4 ); b) acquiring (S 2 ) atlas data describing a general structure ( 5 ) of at least part of the patient's body comprising correspondence parts corresponding to the anatomical body parts ( 3 ); c) acquiring correspondence part position data describing the positions of the correspondence parts in the general structure ( 5 ); determining (S 4.1 , S 4.2 , S 4.3 ), based on the patient image data and the atlas data and the correspondence part position data, virtual image data describing a two-dimensional virtual image ( 2 ) of a part ( 21, 22 ) of the general structure ( 5 ) having a position in the general structure ( 5 ) which lies between the positions of the correspondence parts.

First claim

The invention claimed is:

1. A digital image data processing system, comprising:
at least one data storage device and at least one computer,
wherein the at least one data storage device comprises at least one database that is operably coupled to the at least one computer and stores patient image data describing at least two two-dimensional patient images of anatomical body parts of a patient's body, atlas data describing a general structure of at least part of the patient's body comprising correspondence parts corresponding to the anatomical body parts, and correspondence part position data describing the positions of the correspondence parts in the general structure;
wherein the at least one computer has at least one processor and at least one memory, wherein a program is running on the at least one processor or loaded into the at least one memory which, when executed by the at least one computer, causes the computer to execute steps of:
a) acquiring, at the at least one processor and from the at least one database, the patient image data;
b) acquiring, at the at least one processor and from the at least one database, the atlas data;
c) acquiring, at the at least one processor and from the at least one database, the correspondence part position data; and
d) determining, by the at least one processor and based on the patient image data and the atlas data and the correspondence part position data, virtual image data describing a two-dimensional virtual image of a part of the general structure having a position in the general structure which lies between the positions of the correspondence parts,
wherein the virtual image data describes at least two two-dimensional virtual images of the part of the general structure having the position in the general structure which lies between the positions of the correspondence parts, the method further comprising:

e) comparing, by the at least one processor, the virtual images with the patient images; and
f) determining, by the at least one processor and based on comparing the virtual images with the patient images, which one of the virtual images matches the patient images best, wherein, if it is determined that none of the virtual images matches the patient images within a predetermined degree of accuracy, an imaging transformation comprising at least one of a rotational and a translational positional transformation is applied, by the at least one processor, to the virtual images such that at least one of the virtual images matches the patient images within the predetermined degree of accuracy.

2. A computer-implemented method of determining a virtual image of a part of a patient's body, the method comprising executing at least one processor of at least one computer, steps of:
a) acquiring, at the at least one processor and from a database located in a data storage device, patient image data describing at least two two-dimensional patient images of anatomical body parts of the patient's body;
b) acquiring, at the at least one processor and from a database located in a data storage device, atlas data describing a general structure of at least part of the patient's body comprising correspondence parts corresponding to the anatomical body parts;
c) acquiring, at the at least one processor and from a database located in a data storage device, correspondence part position data describing the positions of the correspondence parts in the general structure;
d) determining, by the at least one processor and based on the patient image data and the atlas data and the correspondence part position data, virtual image data describing a two-dimensional virtual image of a part of the general structure having a position in the general structure which lies between the positions of the correspondence parts,
wherein the virtual image data describes at least two two-dimensional virtual images of the part of the general structure having the position in the general structure which lies between the positions of the correspondence parts, the method further comprising:

e) comparing, by the at least one processor, the virtual images with the patient images; and
f) determining, by the at least one processor and based on comparing the virtual images with the patient images, which one of the virtual images matches the patient images best, wherein, if it is determined that none of the virtual images matches the patient images within a predetermined degree of accuracy, an imaging transformation comprising at least one of a rotational and a translational positional transformation is applied, by the at least one processor, to the virtual images such that at least one of the virtual images matches the patient images within the predetermined degree of accuracy.

3. The method according to claim 2 , wherein the atlas data that includes the description of the general structure is adapted to reference data describing a reference patient.

4. The method according to claim 3 , wherein the reference data comprises at least one of:
a. reference patient image data describing a three-dimensional image of the structure of the anatomical body parts in the patient's body; or
b. patient metadata comprising meta-information about the patient, the meta-information relating to and indicating at least one of the patient's gender, ethnicity, age, size, weight, or pathologic state.

5. The method according to claim 2 , wherein the virtual image is a digitally rendered radiograph.

6. The method according to claim 2 , comprising updating, by the at least one processor, the description of the general structure by the atlas data based on the virtual image data.

7. The method according to claim 2 , comprising determining, by the at least one processor and based on the correspondence part position data, indication data for indicating the position of the correspondence parts in the general structure.

8. The method according to claim 2 , wherein the atlas data comprises representation class data describing a representation of the part of the general structure in the virtual image by describing representation classes of in body tissue or fluids.

9. The method according to claim 8 , further comprising determining, by the at least one processor, a distribution of representation classes of image elements neighbouring the positions of the correspondence parts determining the virtual image data based on the distribution of representation classes.

10. The method according to claim 9 , wherein the representation class data describes the representation of the general structure in dependence on at least one medical imaging modality in dependence on at least one of an absorption and a scattering of image radiation applied by the medical imaging modality used to generate the patient image data.

11. The method according to claim 2 , wherein the patient image data contains imaging information about the imaging process with which the patient image data was generated.

12. The method according to claim 11 , wherein the imaging information is acquired, at the at least one processor and from a database located in a data storage device, based on information about an envisaged medical treatment which is acquired by user input.

13. A non-transitory computer-readable program storage medium storing a program which, when on at least one processor of at least one computer or loaded into at least one memory of at least one computer, causes the at least one computer to execute a medical data processing method of determining a virtual image of a part of a patient's body, the method comprising executing at least one processor of at least one computer, steps of:
a. acquiring, at the at least one processo

Assignees

• Brainlab Ag

Inventors

• Lachner Rainer
• Varkuti Bálint
• Blumhofer Andreas

Classifications

• G06T2207/30012

  Spine; Backbone · CPC title

• G06T2207/10072

  Tomographic images · CPC title

• G06T2207/30016

  Brain · CPC title

• G06T7/344

  involving models · CPC title

• G06T7/337 Primary

  involving reference images or patches · CPC title