Methods and systems for generating surrogate marker based on medical image data

Patent metadata

Field	Value
Publication number	US-11748878-B2
Application number	US-202016992379-A
Country	US
Kind code	B2
Filing date	Aug 13, 2020
Priority date	Aug 13, 2019
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

In a method for generating a surrogate marker based on medical image data mapping an image region, the medical image data is detected using a first interface, a first subregion of the image region is selected by segmenting a first structure included in the image region, a first property of the first subregion is extracted, the surrogate marker is determined based on the first property, and the surrogate marker is provided using a second interface.

First claim

The invention claimed is:

1. A method for generating a surrogate marker based on medical image data mapping an image region, the method comprising:
detecting the medical image data using a first interface;
segmenting a first structure included in the image region to select a first subregion of the image region, the first structure including a liver, a spleen, a kidney, pancreas, or a substructure of the liver, the spleen, the kidney or pancreas;
extracting a first property of the first subregion, the first property including a signal intensity within the first subregion, a volume of the first subregion, and a diffusion value within the first subregion;
detecting, using the first interface, further medical image data mapping a further image region comprising the first structure, the further medical image data having been generated with a time lag of at least one month from the medical image data, wherein segmenting the first structure further selects a second subregion of the further image region;
extracting a second property of the second subregion;
determining the surrogate marker based on the first property and the second property; and
providing the surrogate marker using a second interface.

2. The method as claimed in claim 1 , wherein the selection of the first subregion takes place by applying, on the medical image data: a trained function, a neural network, an active shape model, and/or a level set method.

3. The method as claimed in claim 1 , further comprising:
provisioning, based on the surrogate marker, a recommendation for a diagnosis and/or for a therapy, and/or
provisioning a probability for addressing a therapy based on the surrogate marker.

4. The method as claimed in claim 1 , wherein the first structure further comprises:
a prostate;
a substructure of the prostate;
a peripheral zone of the prostate; and/or
a transition zone of the prostate.

5. The method as claimed in claim 1 , wherein the surrogate marker comprises:
a volume;
a diameter;
a threshold value for a diffusion value;
threshold property;
a spatial distribution of a texture; and/or
a ratio of the first property to a threshold value.

6. The method as claimed in claim 1 , wherein the surrogate marker comprises:
a ratio of the second property to the first property; and/or
a ratio of the first property and/or the second property to at least one threshold value.

7. The method as claimed in claim 1 , further comprising:
segmenting a second structure included in the image region to select a third subregion of the image region; and
extracting a third property of the third subregion, wherein the determining the surrogate marker is further based on the third property.

8. The method as claimed in claim 7 , wherein the first subregion and the third subregion are disjointed.

9. The method as claimed in claim 7 , wherein the medical image data comprising the first structure and the medical image data comprising the second structure have been acquired using two recording methods, the two recording methods differing by at least one parameter.

10. The method as claimed in claim 7 , wherein the surrogate marker comprises:
a ratio of the third property to the first property; and/or
a ratio of the first property and/or the third property to at least one threshold value.

11. A computer program product, embodied on a non-transitory computer-readable storage medium, that includes a program and is directly loadable into a memory of a programmable provisioning system, when the program is executed by the provisioning system, causes the provisioning system to perform the method for generating a surrogate marker as claimed in claim 1 .

12. A non-transitory computer-readable storage medium with an executable program stored thereon, that when executed, instructs a processor to perform the method of claim 1 .

13. A provisioning system comprising:
a first interface configured to:
detect medical image data, the medical image data mapping an image region, and
detect further medical image data mapping a further image region, the further medical image data having been generated with a time lag of at least one month from the medical image data;

a second interface; and
a computer configured to:
segment a first structure included in the image region to select a first subregion of the image region and select a second subregion of the further image region, the first structure including a liver, a spleen, a kidney, pancreas, or a substructure of the liver, the spleen, the kidney or pancreas;
extract a first property of the first subregion, the first property including a signal intensity within the first subregion, a volume of the first subregion, and a diffusion value within the first subregion;
extract a second property of the second subregion;
determine a surrogate marker based on the first property and the second property; and
provide the surrogate marker using the second interface.

14. The provisioning system as claimed in claim 13 , wherein the computer is configured to use a trained function to perform the segmenting, extracting, determining, and providing.

15. The provisioning system as claimed in claim 13 , wherein the providing of the surrogate marker comprises generating an electronic data signal corresponding to the surrogate marker and outputting the electronic data signal via the second interface.

16. The method as claimed in claim 1 , wherein the surrogate marker comprises:
a threshold value for a diffusion value;
threshold property; and/or
a ratio of the first property to a threshold value.

17. The method as claimed in claim 1 , further comprising associating the surrogate marker with other medical image data of one or more other examination objects, the other medical image data including the first property, wherein the one or more other examination objects are different from an examination object in which the medical image data is detected.

Assignees

• Siemens Healthcare Gmbh

Inventors

• GRIMM Robert
• Kiefer Berthold
• Von Busch Heinrich

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/62

  of area, perimeter, diameter or volume · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H50/20

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