Method and device for automatic determination of the change of a hollow organ

Patent metadata

Field	Value
Publication number	US-11538154-B2
Application number	US-202017012281-A
Country	US
Kind code	B2
Filing date	Sep 4, 2020
Priority date	Sep 12, 2019
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

A method and device are for automatic determination of the change of a hollow organ. The method includes providing a first medical image of the organ recorded at a first time; computing a first representation of the organ in the first image; computing a first reference-line of the organ based on the first representation and providing a second medical image of the organ recorded at a second point. The method further includes computing a second representation of the organ in the second image; computing a second reference-line of the organ based on the second representation of the organ; registering of the first and second reference-line to obtain at least one of matched representations of the organ and features derived from the matched representations of the organs; and comparing at least one of the matched representations of the organs and the features derived from the matched representations of the organ.

First claim

What is claimed is:

1. A method for automatic determination of a change of an organ, the method comprising:
computing a first representation of the organ in a first medical image, the first medical image being recorded at a first time;
computing a first centerline of the organ based on the first representation of the organ, the computing the first centerline including performing a first iterative calculation of a next point d of the first centerline based on a first known or defined point d prev on the first centerline;
computing a second representation of the organ in a second medical image, the second medical image being recorded at a second time;
computing a second centerline of the organ based on the second representation of the organ, the computing the second centerline including performing a second iterative calculation of a next point d of the second centerline based on a second known or defined point d prev on the second centerline;
registering the first centerline and the second centerline to obtain at least one of
matched representations of the organ, or
features derived from the matched representations; and

comparing the at least one of the matched representations or the features.

2. The method of claim 1 , further comprising:
determining at least one of first distances or first cross sections from a set of coordinates of the first centerline to a surface of the organ in the first medical image;
determining at least one of second distances or second cross sections from a set of coordinates of the second centerline to the surface of the organ in the second medical image;
obtaining a matching of the at least one of first distances or first cross sections and the at least one of second distances or second cross sections based on the registering; and
pairwise comparing at least one of respective distances or respective cross sections among the at least one of first distances or first cross sections and the at least one of second distances or second cross sections based on the matching.

3. The method of claim 1 , wherein each of the first iterative calculation and the second iterative calculation is performed with a defined distance between points d and d prev rev and points p on a surface S of the organ by solving an optimization problem min d max peS ∥d−p∥.

4. The method of claim 1 , further comprising:
performing measurements to obtain respective size values of parts of the organ.

5. The method of claim 4 , wherein
the performing measurements performs measurements for a defined set of points of the first centerline or the second centerline; and
the measurements include at least one of
a maximum diameter of the organ at a defined coordinate on the first centerline or the second centerline,
an average diameter of the organ at the defined coordinate on the first centerline or the second centerline, or
a cross-sectional area of the organ at the defined coordinate on the first centerline or the second centerline.

6. The method of claim 1 , wherein the registering registers the first centerline and the second centerline using a numerical optimization techniques.

7. The method of claim 6 , wherein the registering registers the first centerline and the second centerline by applying a rigid or non-rigid spatial transformation to points on one of first centerline or the second centerline.

8. The method of claim 1 , further comprising:
determining changes between the at least one of the matched representations or the features including matching each respective point among a plurality of points on the second centerline to a corresponding point among a plurality of points on the first centerline.

9. The method of claim 8 , wherein the determining determines changes between the features based on the matching.

10. The method of claim 1 , further comprising:
visualizing changes between the at least one of the matched representations or the features based on the comparing.

11. The method of claim 10 , further comprising:
applying a graphical filter function to at least one of the features or an image visualizing the changes.

12. The method of claim 1 , further comprising:
labeling or marking changes between the at least one of the matched representations or the features based on the comparing, wherein
the labeling or the marking depends on a respective quantity of each change among the changes.

13. The method of claim 1 , wherein
the computing the first representation of the organ includes segmenting the first representation from the first medical image; and
the computing the first centerline computes the first centerline based on the first representation of the organ after the segmenting.

14. The method of claim 1 , wherein
the comparing includes
determining a first distance or a first cross section corresponding to the first medical image, and
determining a second distance or a second cross section corresponding to the second medical image; and

the method further comprises determining a ratio based on (i) the first distance and the second distance or (ii) the first cross section and the second cross section.

15. The method of claim 1 , wherein
the comparing includes determining a quantity of the change of the organ; and
the method further includes outputting a label, a marker, a warning message or an acoustic signal in response to determining the quantity of the change exceeds a threshold.

16. A device for automatic determination of a change of an organ, the device comprising:
a segmentation unit to compute a first representation of the organ in a first medical image and a second representation of the organ in a second medical image, the first medical image being recorded at a first time, and the second medical image being recorded at a second time;
a reference unit to compute a first centerline of the organ based on the first representation of the organ and to compute a second centerline of the organ based on the second representation of the organ, computation of the first centerline including performing a first iterative calculation of a next point d of the first centerline based on a first known or defined point d prev on the first centerline, and computation of the second centerline including performing a second iterative calculation of a next point d of the second centerline based on a second known or defined point d prev on the second centerline;
a registration unit to register the first centerline and the second centerline to obtain at least one of
matched representations of the organ, or
features derived from the matched representations; and

a comparison unit to compare the at least one of the matched representations or the features.

17. The device according to claim 16 , further comprising;
a measuring unit configured to determine
at least one of first distances or first cross sections from a set of defined coordinates of the first centerline to a surface of the organ in the first medical image, and
at least one of second distances or second cross sections from a set of defined coordinates of the second centerline to the surface of the organ in the second medical image, wherein
the registration unit is configured to obtain a matching of the at least one of first distances or first cross sections and the at least one of second distances or second cross sections based on the registration of the first centerline and the second centerline, and
the comparison unit is configured to pairwise compare at least one of respective distances or respective cross sections among the at least one of first distances or

Assignees

• Siemens Healthcare Gmbh

Inventors

• Sperl Jonathan
• Kaergel Rainer

Classifications

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• A61B6/032

  Transmission computed tomography [CT] · CPC title

• G06T7/33

  using feature-based methods · CPC title