Determination of result data on the basis of medical measurement data from various measurements

Patent metadata

Field	Value
Publication number	US-10699434-B2
Application number	US-201715672347-A
Country	US
Kind code	B2
Filing date	Aug 9, 2017
Priority date	Aug 23, 2016
Publication date	Jun 30, 2020
Grant date	Jun 30, 2020

Abstract

A method is disclosed for determining result data based upon medical measurement data of an examination object. Within the method, a high-dimensional first parameter space is formed, in which measurement values of the various measurements are represented with the aid of value tuples. The measurement values of the various measurements are assigned to a value tuple based on their spatial arrangement in the examination object and/or on their temporal arrangement relative to one another. In the first parameter space, the value tuples are analyzed, using at least one mapping function to at least one further parameter space including a lower dimension than the first parameter space, in order to obtain result data. Furthermore, the result data is output, preferably visualized. In addition, a corresponding device for determining result data is described.

First claim

What is claimed is:

1. A method for determining result data based upon medical imaging data of an examination object, the method comprising:
collecting the medical imaging data having been collected in various measurements from multiple medical images,
forming a high-dimensional first parameter space in which measurement values of the multiple medical images are represented with aid of value tuples, each of the measurement values of the multiple medical images being assigned to a value tuple of the value tuples at least one of based on a spatial arrangement of a respective measurement value in the examination object;
analyzing the value tuples in the high-dimensional first parameter space using a mapping function to at least one further parameter space including a relatively lower dimension having reduced value tuples than the high-dimensional first parameter space to determine result data, the mapping function including integrating the value tuples over defined areas of the high-dimensional first parameter space thereby reducing the value tuples to a relatively lower dimension than the high-dimensional first parameter space; and
outputting the determined result data.

2. The method of claim 1 , wherein the various measurements comprise identical measurements at various times.

3. The method of claim 1 , wherein, to determine the result data, interim result data is first determined by a first mapping function from the first parameter space to a second parameter space and an analysis is performed on the interim result data;
wherein the analysis is performed using at least a second mapping function to at least a third parameter space including a relatively lower dimension than the second parameter space; and
wherein the first mapping function and the second mapping function include different function types.

4. The method of claim 1 , wherein the analyzing is performed taking into account positions of the value tuples in a parameter space in relation to a boundary hyperplane of the parameter space.

5. The method of claim 1 , wherein the analyzing includes an assignment of the value tuples to value-tuple groups.

6. The method of claim 5 , further comprising analyzing an arrangement of a value-tuple group, of the value-tuple groups, in the parameter space.

7. The method of claim 6 , wherein the arrangement of the value-tuple group is determined taking into account a collective position of the respective value-tuple group in the parameter space.

8. The method of claim 1 , wherein the analyzing of the value tuples is performed taking into account a position in relation to at least one reference value tuple.

9. The method of claim 1 , wherein the analyzing of the value tuples includes a segmentation.

10. The method of claim 1 , wherein the analyzing includes at least one of morphological operations and filtering.

11. The method of claim 1 , further comprising a temporal analysis of a change of value tuples in the parameter space.

12. The method of claim 1 , wherein the analyzing includes a machine learning method.

13. The method of claim 1 , wherein the outputting includes visualizing of the result data and wherein the visualizing of the result data includes labeling of at least one of picture elements and regions in a spatial domain representation of the examination object, wherein the labeling is performed depending on a result of the analyzing of the value tuples in at least one of the high-dimensional first and a further parameter space.

14. The method of claim 13 , wherein the visualizing of the result data includes a visualization of a temporal analysis by at least one of colors and vectors.

15. A device for determining result data based upon medical imaging data of multiple medical images of an examination object, the medical imaging data having been collected in various measurements, the device comprising:
at least one processor, the at least one processor being configured to:
form a high-dimensional first parameter space in which measurement values of the multiple medical images are represented with aid of value tuples, each the measurement values of the multiple medical images being assigned to a value tuple of the value tuples at least one of based on a spatial arrangement of a respective measurement value in the examination object;
analyze the value tuples in the high-dimensional first parameter space using a mapping function to at least one further parameter space including a relatively lower dimension having reduced value tuples than the high-dimensional first parameter space to determine result data, the mapping function including integrating the value tuples over defined areas of the high-dimensional first parameter space thereby reducing the value tuples to a relatively lower dimension than the high-dimensional first parameter space; and
output the determined result data.

16. A non-transitory computer program product including a computer program, directly loadable into a storage device of computer unit, including program sections for executing the method of claim 1 when the computer program product is executed in the computing unit.

17. A non-transitory computer-readable medium including program sections, readable and executable by a computer unit, to execute the method of claim 1 when the program sections are executed by the computer unit.

18. The method of claim 1 , wherein the medical imaging data was collected in various measurements with different measurement devices.

19. The method of claim 1 , wherein the outputting includes visualization of the determined result data.

20. The method of claim 2 , wherein the mapping function further includes at least one of the following:
mapping to a color space,
mapping to discrete classes,
mapping to a space with clinically relevant semantic coordinate axes, and
mapping to a system of coordinates with mathematical characteristics.

21. The method of claim 1 , wherein, to determine the result data, interim result data is first determined by a first mapping function from the first parameter space to a second parameter space and an analysis is performed on the interim result data;
wherein the analysis is performed using at least a second mapping function to at least a third parameter space including a relatively lower dimension than the second parameter space; and
wherein the first mapping function and the second mapping function include different function types.

22. The method of claim 4 , wherein the analyzing includes an assignment of the value tuples to value-tuple groups.

23. The method of claim 22 , further comprising analyzing an arrangement of a value-tuple group, of the value-tuple groups, in the parameter space.

24. The method of claim 23 , wherein the arrangement of the value-tuple group is determined taking into account a collective position of the respective value-tuple group in the parameter space.

25. The method of claim 11 , wherein the temporal analysis includes a temporal shift of individual value tuples.

26. The method of claim 13 , wherein the visualizing of the result data includes a visualization of a temporal analysis by at least one of colors and vectors.

27. The device of claim 15 , wherein the medical imaging data was collected in various measurements with different measurement devices.

28. The device of claim 15 , wherein the output includes visualization of the determ

Assignees

• Siemens Healthcare Gmbh

Inventors

• GRIMM Robert
• Schweizer Bernd

Classifications

• G06F18/24 Primary

  Classification techniques · CPC title

• A61B5/0035 Primary

  adapted for acquisition of images from more than one imaging mode, e.g. combining MRI and optical tomography · CPC title

• G06T7/73 Primary

  using feature-based methods · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H10/40

  for data related to laboratory analysis, e.g. patient specimen analysis · CPC title