Granted Patent B2

US 12,322,091 · App. 17/671,950 · Granted Jun 3, 2025

Inventors: Sailesh Conjeti (Erlangen, DE); Alexis Laugerette (Erlangen, DE); Christian Huemmer (Lichtenfels, DE)

Assignee: SIEMENS HEALTHINEERS AG

G06T7/0012G06T2207/20081G06T2207/20084

Abstract

Claims (64)

1. A computer-implemented method for providing at least one first metadata attribute associated with a medical image, the computer-implemented method comprising:

receiving the medical image and the at least one first metadata attribute, the received at least one first metadata attribute including an attribute tag and a provisional attribute value;

applying a first trained function to the medical image to determine an image-based attribute value;

checking whether the provisional attribute value is empty;

determining a final attribute value based on the provisional attribute value, the image-based attribute value, and a result of the checking; and

providing the at least one first metadata attribute, the provided at least one first metadata attribute including the attribute tag and the final attribute value.

2. The computer-implemented method of claim 1 , wherein the determining of the final attribute value includes,

filling the final attribute value with the image-based attribute value upon the provisional attribute value being empty.

3. The computer-implemented method of claim 1 , wherein the determining of the final attribute value includes,

comparing the provisional attribute value and the image-based attribute value upon the provisional attribute value not being empty, and wherein

the final attribute value is determined based on the comparing.

4. The computer-implemented method of claim 3 , wherein the comparing of the provisional attribute value and the image-based attribute value comprises:

applying a second trained function to the provisional attribute value and the image-based attribute value to determine the final attribute value.

5. The computer-implemented method of claim 4 , wherein the first trained function includes the second trained function.

6. The computer-implemented method of claim 1 , further comprising:

selecting the first trained function from a plurality of first trained functions based on at least one of the result of the checking or the attribute tag.

7. The computer-implemented method of claim 1 ,

wherein a plurality of metadata attributes are associated with the medical image,

wherein each metadata attribute of the plurality of metadata attributes includes an attribute tag and an attribute value,

wherein the at least one first metadata attribute is a metadata attribute of from among the plurality of metadata attributes, and

wherein the method further includes determining the at least one first metadata attribute out of the plurality of metadata attributes, based on at least one of an application configured to process the medical image or the attribute tags.

8. The computer-implemented method of claim 1 ,

wherein a plurality of metadata attributes are associated with the medical image,

wherein the at least one first metadata attribute is a metadata attribute of from among the plurality of metadata attributes,

wherein the method further includes receiving at least one second metadata attribute from among the plurality of metadata attributes,

wherein the at least one second metadata attribute is related to the at least one first metadata attribute, and

wherein first trained function is also applied to the at least one second metadata attribute in the applying of the first trained function.

9. The computer-implemented method of claim 1 ,

wherein the provisional attribute value includes a free-text attribute value,

wherein the method further includes standardizing the free-text attribute value by applying a third trained function to the at least one first metadata attribute, and

wherein the free-text attribute value is replaced by the standardized attribute value in the provisional attribute value of the at least one first metadata attribute.

10. The computer-implemented method of claim 9 , further comprising:

categorizing the standardized attribute value by applying a fourth trained function to the at least one first metadata attribute, and

wherein the standardized attribute value is replaced by the categorized standardized attribute value in the provisional attribute value of the at least one first metadata attribute.

11. The computer-implemented method of claim 10 , further comprising:

performing a semantic matching of the categorized standardized attribute value with higher-level terms by applying a fifth trained function to the at least one metadata attribute, and wherein

the categorized standardized attribute value is replaced by the matched categorized standardized attribute value in the provisional attribute value of the at least one first metadata attribute.

12. The computer-implemented method of claim 2 , wherein the determining of the final attribute value includes,

comparing the provisional attribute value and the image-based attribute value upon the provisional attribute value not being empty, and wherein

the final attribute value is determined based on the comparing.

13. The computer-implemented method of claim 12 , wherein the comparing of the provisional attribute value and the image-based attribute value comprises:

applying a second trained function to the provisional attribute value and the image-based attribute value to determine the final attribute value.

14. The computer-implemented method of claim 13 , wherein the first trained function includes the second trained function.

15. The computer-implemented method of claim 2 , further comprising:

selecting the first trained function from a plurality of first trained functions based on at least one of the result of the checking or the attribute tag.

16. The computer-implemented method of claim 2 , further comprising:

selecting the first trained function from a plurality of first trained functions based on the at least one second metadata attribute.

17. A unifying system for providing at least one metadata attribute associated with a medical image, the unifying system comprising:

an interface configured to

receive the medical image and the at least one metadata attribute, the received at least one metadata attribute including an attribute tag and a provisional attribute value, and

provide the at least one metadata attribute, the provided at least one metadata attribute including the attribute tag and a final attribute value; and at least one processor configured to

apply a first trained function to the medical image to determine an image-based attribute value,

check whether the provisional attribute value is empty, and

determine the final attribute value based on the provisional attribute value, the image-based attribute value, and a result of the check.

18. A non-transitory computer program product storing program elements that are loaded into a memory of a unifying system including at least one processor, the program elements inducing the unifying system to execute the computer-implemented method of claim 1 , when the program elements are executed by the at least one processor-unifying system.

19. A non-transitory computer-readable storage medium storing program elements that, when executed by at least one processor at a unifying system, cause the unifying system to perform the computer-implemented method of claim 1 .

20. A computer-implemented method for providing at least one first metadata attribute associated with a medical image, the computer-implemented method comprising:

receiving the medical image and the at least one first metadata attribute, the received at least one first metadata attribute including an attribute tag and a provisional attribute value;

applying a first trained function to the medical image to determine an image-based attribute value;

determining a final attribute value based on the provisional attribute value and the image-based attribute value; and

providing the at least one first metadata attribute, the provided at least one first metadata attribute including the attribute tag and the final attribute value; wherein

the provisional attribute value includes a free-text attribute value,

the method further includes standardizing the free-text attribute value by applying a second trained function to the received at least one first metadata attribute, and

the free-text attribute value is replaced by the standardized attribute value in the provisional attribute value of the received at least one first metadata attribute.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (17)