Automatic transfer of outlined objects from one data set into another data set

• US 8,265,361 B2
• Filed: 10/27/2008
• Issued: 09/11/2012
• Est. Priority Date: 10/26/2007
• Status: Active Grant

• Current Assignee: Brainlab AG
• Original Assignee: Brainlab AG
• Inventors: Achatz, Stefan, Raupach, Carsten, Frielinghaus, Nils, Lang, Andreas
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US12/258,807
• Publication Number:
  US 20090110294A1
• Time in Patent Office: 1,415 Days
• Field of Search: 382/128, 382/131, 382/173, 382/294
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 2201/031 of internal organs

Abstract

A method for automatically localizing at least one object or structure in a second data set is provided. A reference data set is provided, and at least one object or structure is outlined or marked in the reference data set, the outline or marking information being a first or reference label data set. A mapping function is determined, using which said reference data set is approximately mapped onto said second data set, and the reference label data set assigned to said reference data set is transformed into a second label data set using said mapping function.

Claims

1. A method for automatically localizing at least one object or structure in a second data set, wherein:

a) a reference data set is provided;

b) at least one object or structure is outlined or marked in the reference data set, the outline or marking information being a first or reference label data set;

c) a mapping function is determined, using which said reference data set is approximately mapped onto said second data set; and

d) the reference label data set assigned to said reference data set is transformed into a second label data set using said mapping function, wherein the method is repeated for further n data sets using the first or (n−

1)-th label data set as the reference label data set to calculate the n-th label data set.

2. The method as set forth in claim 1, wherein said reference data set is determined using the same measuring method as is used to obtain said second data set.

3. The method as set forth in claim 1, wherein the data sets represent two-dimensional images or three-dimensional volumes.

4. The method as set forth in claim 1, wherein the mapping function includes at least one of (i) a transforming operator, (ii) a rotating operator, (iii) a shearing operator, and (iv) a deforming operator.

5. The method as set forth in claim 1, wherein the mapping function is determined using a hierarchical method including performing a rigid transformation and an elastic transformation.

6. The method as set forth in claim 1, wherein the reference data set is selected from a number of predetermined reference data sets, depending on characteristics of an object characterized by the second data set.

7. The method as set forth in claim 1, wherein the reference data set and the second data set are fused by using the same frame of reference or scanner.

8. The method as set forth in claim 1, wherein the method is used to localize tumors or brain structures.

9. The method as set forth in claim 1, further comprising:

superimposing the second label data set onto the second data set.

10. The method as set forth in claim 1, wherein the position or area irradiated during radiotherapy is calculated based on the position of the object or structure in the second label data set.

11. A non-transitory computer readable medium comprising computer executable instructions adapted to perform the method in accordance with claim 1.

12. A method for automatically localizing at least one object or structure in a second data set, wherein:

a) a reference data set is provided;

b) at least one object or structure is outlined or marked in the reference data set, the outline or marking information being a first or reference label data set;

c) a mapping function is determined, using which said reference data set is approximately mapped onto said second data set; and

d) the reference label data set assigned to said reference data set is transformed into a second label data set using said mapping function, wherein the mapping function is determined using a hierarchical method including performing a rigid transformation and an elastic transformation, and wherein the elastic transformation is performed only on regions surrounding or being directly adjacent to the outlined or marked object.

13. A method for automatically localizing at least one object or structure in a second data set, wherein:

a) a reference data set is provided;

b) at least one object or structure is outlined or marked in the reference data set, the outline or marking information being a first or reference label data set;

c) a mapping function is determined, using which said reference data set is approximately mapped onto said second data set; and

d) the reference label data set assigned to said reference data set is transformed into a second label data set using said mapping function, wherein only a the rigid transformation of the mapping function is used for transforming the reference label data set, wherein the method is repeated for further n data sets using the first or (n−

1)-th label data set as the reference label data set to calculate the n-th label data set.

14. A device for localizing at least one object or structure in a second data set, said device comprising:

a data input device which receives the second data set;

a memory which stores a reference data set together with a corresponding reference label data set; and

a processor which determines a mapping function for mapping the reference data set onto a second data set or vice versa and for mapping said reference label data set onto a second label data set, using the determined mapping function, wherein the mapping is repeated for further n data sets using the first or (n−

1)-th label data set as the reference label data set to determine the n-th label data set.

15. The device as set forth in claim 14, further comprising a measuring device for capturing the second data set.

16. The device as set forth in claim 14, further comprising a data output device for displaying the second data set, the reference data set, the reference label data set and the second label data set.

17. The device as set forth in claim 14, further comprising a radiation source or linear accelerator controlled by the processor using the calculated second label data set.