Granted Patent B2

US 12,198,335 · App. 17/618,445 · Granted Jan 14, 2025

Inventors: Christian Haase (Hamburg, DE); Dirk Schaefer (Hamburg, DE); Michael Grass (Buchholz in der Nordheide, DE)

Assignee: KONINKLIJKE PHILIPS N.V.

G06T7/0012A61B6/481A61B6/504G06T2200/24G06T2207/10116G06T2207/20081G06T2207/30096G06T2207/30101

Abstract

Claims (73)

1. A computer-implemented method for analyzing diagnostic image data, the method comprising:

receiving diagnostic image data comprising a plurality of acquisition images of a vessel of interest at a trained classifying device, wherein the diagnostic image data is acquired using a pre-defined acquisition method,

classifying the diagnostic image data to extract at least one quantitative feature of the vessel of interest from at least one acquisition image of the plurality of acquisition images,

outputting the at least one quantitative feature of the vessel of interest associated with the at least one acquisition image while the acquisition of the diagnostic image data is still in progress, and

adjusting one or more adjustable image acquisition settings based on the at least one quantitative feature to optimize the acquisition of the diagnostic image data.

2. The method according to claim 1 , wherein the adjusting the one or more adjustable image acquisition settings comprises:

prematurely terminating the acquisition of the diagnostic image data if it is determined that an already acquired portion of the diagnostic image data fulfils at least one pre-defined reliability criteria.

3. The method according to claim 1 , wherein the adjusting the one or more adjustable acquisition settings comprises:

adjusting an image acquisition trajectory to improve visibility of the vessel of interest in the diagnostic image data.

4. The method according to claim 1 , wherein the adjusting the one or more adjustable acquisition settings comprises:

a contrast agent injection rate into the vessel of interest during image acquisition.

5. The method according to claim 1 , further comprising:

obtaining training image data of the vessel of interest according to the pre-defined acquisition method and extracting the at least one quantitative feature from the training image data,

generating at least one training dataset, the training dataset comprising the training image data associated with the at least one quantitative feature, and

training the classifying device using the at least one training dataset.

6. The method according to claim 5 , wherein the training image data comprises simulated training image data generated by simulating an image acquisition according to the pre-defined acquisition method, wherein the simulating comprises:

obtaining at least one three-dimensional geometric model of the vessel of interest;

obtaining at least one two-dimensional background image for the vessel of interest; and

simulating a contrast agent fluid dynamic through the patient's vasculature based on at least one contrast agent fluid parameter.

7. The method according to claim 6 , wherein the simulating further comprises:

obtaining deformation translation and rotation data, and

augmenting the simulated training image data based on the translation and rotation data.

8. The method according to claim 5 , wherein the generating the at least one training dataset further comprises:

receiving additional patient data, and

adjusting the at least one training dataset in accordance with the additional patient data.

9. The method according to claim 1 , wherein the at least one quantitative feature comprises one or more of: a vessel label of a vessel in the patient's vasculature, or a vessel length of a vessel in the patient's vasculature, a severity of a lesion in a vessel in the patient's vasculature, a vessel diameter of a vessel in the patient's vasculature, a visibility score for a lesion, a vessel in the patient's vasculature, a completeness score for the at least one of the plurality of acquisition images, and a myocardial blush value.

10. The method according to claim 1 wherein the outputting the at least one quantitative feature for further evaluation comprises at least one of:

displaying the at least one quantitative feature to a user, and

outputting the at least one quantitative feature in a pre-defined format for automatic reporting to a reporting entity.

11. An apparatus for analyzing diagnostic image data, the apparatus comprising:

a processor in communication with memory, the processor configured to:

receive diagnostic image data comprising a plurality of acquisition images of a vessel of interest, wherein the diagnostic image data is acquired using a pre-defined acquisition method,

classify the diagnostic image data to extract at least one quantitative feature of the vessel of interest from at least one acquisition image of the plurality of acquisition images, and

output the at least one quantitative feature of the vessel of interest associated with the at least one acquisition image while the acquisition of the diagnostic image data is still in progress, and

adjust one or more adjustable image acquisition settings based on the at least one quantitative feature to optimize the acquisition of the diagnostic image data.

12. The apparatus according to claim 11 , further comprising:

a second processor in communication with memory, the second processor configured to:

obtain training image data of the vessel of interest according to the pre-defined acquisition method,

extract the at least one quantitative feature of the vessel of interest from the training image data,

generate at least one training dataset comprising the training image data associated with the at least one quantitative feature, and

provide the at least one training dataset to the processor for training.

13. The apparatus according to claim 11 , wherein the processor is further configured to:

generate a graphical representation of one or more of: at least one acquisition image of the plurality of acquisition images and the at least one quantitative feature, and

receive user inputs in response to the graphical representation.

14. A non-transitory computer-readable medium having stored a computer program comprising instructions which, when executed by a processor, cause the processor to:

receive diagnostic image data comprising a plurality of acquisition images of a vessel of interest at a trained classifying device, wherein the diagnostic image data is acquired using a pre-defined acquisition method,

classify the diagnostic image data to extract at least one quantitative feature of the vessel of interest from at least one acquisition image of the plurality of acquisition images,

output the at least one quantitative feature of the vessel of interest associated with the at least one acquisition image while the acquisition of the diagnostic image data is still in progress, and

adjust one or more adjustable image acquisition settings based on the at least one quantitative feature to optimize the acquisition of the diagnostic image data.

15. The non-transitory computer-readable medium according to claim 14 , wherein the instructions, when executed by the processor, further cause the processor to:

obtain training image data of the vessel of interest according to the pre-defined acquisition method and extracting the at least one quantitative feature from the training image data,

generate at least one training dataset for the classifying device, the training dataset comprising the training image data associated with the at least one quantitative feature, and

train the classifying device using the at least one training dataset.

16. The non-transitory computer-readable medium according to claim 15 , wherein the training image data comprises simulated training image data generated by simulating an image acquisition according to the pre-defined acquisition method, and,

to simulate the image acquisition, the instructions, when executed by the processor, further cause the processor to:

obtain at least one three-dimensional geometric model of the vessel of interest;

obtain at least one two-dimensional background image for the vessel of interest; and

simulate a contrast agent fluid dynamic through the patient's vasculature based on at least one contrast agent fluid parameter.

17. The non-transitory computer-readable medium according to claim 16 , wherein, to simulate the image acquisition, the instructions, when executed by the processor, further cause the processor to:

obtain deformation translation and rotation data, and

augment the simulated training image data based on the translation and rotation data.

18. The apparatus according to claim 11 , wherein the processor is further configured to:

obtain training image data of the vessel of interest according to the pre-defined acquisition method and extracting the at least one quantitative feature from the training image data,

generate at least one training dataset for the classifying device, the training dataset comprising the training image data associated with the at least one quantitative feature, and

train the classifying device using the at least one training dataset.

19. The apparatus according to claim 18 , wherein the training image data comprises simulated training image data generated by simulating an image acquisition according to the pre-defined acquisition method, and,

to simulate the image acquisition, the processor is further configured to:

obtain at least one three-dimensional geometric model of the vessel of interest;

obtain at least one two-dimensional background image for the vessel of interest; and

simulate a contrast agent fluid dynamic through the patient's vasculature based on at least one contrast agent fluid parameter.

20. The apparatus according to claim 19 , wherein, to simulate the image acquisition, the processor is further configured to:

obtain deformation translation and rotation data, and

augment the simulated training image data based on the translation and rotation data.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (28)

Cited By (5)

US 12,446,965 US 12,499,646 US 12,512,196 US 12,531,159 US 12,567,489