# US 10,121,244 B2 · Transformation determination device and method for determining a transformation for image registration

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,121,244 B2
- Document ID: US10121244B2
- Status: Granted
- Kind: B2
- Application number: 15/246,673
- Filed: 2016-08-25
- Published: 2017-03-16
- Granted: 2018-11-06
- Earliest claimed: 2015-09-10
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: Oxana Gruenwald; Bernd Schreiber
- Web page: https://patentgrep.com/patent/US10121244B2

## CPC

- A61B 6/4441: {the rigid structure being a C-arm or U-arm}
- A61B 6/481: {involving the use of contrast agents}
- A61B 6/504: {for diagnosis of blood vessels, e.g. by angiography}
- A61B 6/5205: {involving processing of raw data to produce diagnostic data}
- A61B 6/5217: {extracting a diagnostic or physiological parameter from medical diagnostic data}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06T 3/14: Transformations for image registration, e.g. adjusting or mapping for alignment of images
- G06T 3/20: Linear translation of whole images or parts thereof, e.g. panning
- G06T 3/60: Rotation of whole images or parts thereof
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/30: Determination of transform parameters for the alignment of images, i.e. image registration
- G06T 7/33: using feature-based methods
- G06V 10/7515: {Shifting the patterns to accommodate for positional errors}
- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/0035: {adapted for acquisition of images from more than one imaging mode, e.g. combining MRI and optical tomography}
- A61B 2576/00: Medical imaging apparatus involving image processing or analysis (A61B1/00009, A61B6/52 and A61B8/52 take precedence)
- G06T 2207/10116: X-ray image
- G06T 2207/20224: Image subtraction
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method is for determining a transformation for image registration of a first image relative to a second image. The method includes ascertaining a test series of test elements including a test transformation and a test value, the ascertaining including ascertaining the test transformation based on a sequence of test transformations and/or based on previously ascertained test elements, transforming the first image via the ascertained test transformation, ascertaining a difference image, and ascertaining the test value of the test element based on the difference image such that the test value is a measure for an extension of a frequency distribution of values of pixels of the difference image in a direction of pixel value increase. It further includes determining a minimum test value based on test values encompassed by the test elements and determining the transformation which is the test transformation of a test element including the minimum test value.

## Claims

### Claim 1

A method for determining a registration transformation for image registration of a first image relative to a second image, comprising:
generating a plurality of test elements, each test element among the plurality of test elements including a test transformation and a test value, the generating including determining a test element among the plurality of test elements by at least
determining a test transformation of the test element based on at least one of
a sequence of test transformations, or
one or more previously determined test elements among the plurality of test elements,
transforming the first image via the determined test transformation,
generating a difference image based on the transformed first image and the second image,
calculating a frequency distribution of pixel values of the difference image, and
determining a test value of the test element based on the frequency distribution such that the test value increases as one or more frequencies of higher pixel values increase;
determining a minimum test value among the test values included in the plurality of test elements; and
determining the registration transformation as the test transformation included in the same test element as the minimum test value.

### Claim 2 (depends on 1)

The method of claim 1, wherein the test value is determined based on a pixel group of the difference image, each pixel of the pixel group meeting at least one of
a pixel position condition relating to a position of the pixel, or
a pixel value condition relating to a pixel value of the pixel.

### Claim 3 (depends on 2)

The method of claim 2, wherein the test value is at least one of
a parameter of at least one of the pixel group or the difference image, or
determined based on a parameter of at least one of the pixel group or the difference image, and wherein
the parameter includes at least one of a maximum of the pixel values, a sum of the pixel values or a location parameter of the frequency distribution.

### Claim 4 (depends on 3)

The method of claim 3, wherein the location parameter includes at least one of a mean value, a mode or a quantile.

### Claim 5 (depends on 3)

The method of claim 3, wherein the pixel position condition is met if the pixel is positioned in a region of interest.

### Claim 6 (depends on 3)

The method of claim 3, wherein the pixel value condition is met if the pixel value exceeds a pixel threshold value.

### Claim 7 (depends on 2)

The method of claim 2, wherein the pixel position condition is met if the pixel is positioned in a region of interest.

### Claim 8 (depends on 2)

The method of claim 2, wherein the pixel value condition if the pixel value exceeds a pixel threshold value.

### Claim 9 (depends on 2)

The method of claim 2, wherein the test transformation comprises at least one of a translation or a rotation.

### Claim 10 (depends on 2)

The method of claim 2, wherein the test transformation is determined by way of a search algorithm.

### Claim 11 (depends on 2)

The method of claim 2, further comprising:
comparing the test value with a test threshold value; and
discontinuing the determining a test element in response to determining that the test value is lower than the test threshold value based on the comparing.

### Claim 12 (depends on 2)

A method for determining a subtraction angiography image based on a first image pair set containing one or more first image pairs, each of the one or more first image pairs including a mask image and a contrast agent image, the method comprising:
providing the first image pair set;
generating a registered image pair set containing one or more registered image pairs by performing at least the following for each of the one or more first image pairs of the first image pair set
determining a registration transformation for image registration via the method of claim 2, the first image being the mask image of the first image pair and the second image being the contrast agent image of the first image pair, and
transforming the mask image via the determined registration transformation, the transformed mask image and the contrast agent image forming a registered image pair of the registered image pair set; and
determining the subtraction angiography image based on the registered image pair set.

### Claim 13 (depends on 1)

The method of claim 1, wherein the test transformation comprises at least one of a translation or a rotation.

### Claim 14 (depends on 1)

The method of claim 1, wherein the test transformation is determined by way of a search algorithm.

### Claim 15 (depends on 1)

The method of claim 1, further comprising:
comparing the test value with a test threshold value; and
discontinuing the determining a test element in response to determining that the test value is lower than the test threshold value based on the comparing.

### Claim 16 (depends on 1)

A method for determining a subtraction angiography image based on a first image pair set containing one or more first image pairs, each of the one or more first image pairs including a mask image and a contrast agent image, the method comprising:
providing the first image pair set;
generating a registered image pair set containing one or more registered image pairs by performing at least the following for each of the one or more first image pairs of the first image pair set
determining a registration transformation for image registration via the method of claim 1, the first image being the mask image of the first image pair and the second image being the contrast agent image of the first image pair, and
transforming the mask image via the determined registration transformation, the transformed mask image and the contrast agent image forming the registered image pair of the registered image pair set; and
determining the subtraction angiography image based on the registered image pair set.

### Claim 17 (depends on 16)

A non-transitory computer-readable medium storing computer-readable instructions that, when executed by at least one processor, cause the at least one processor to perform the method of claim 16.

### Claim 18 (depends on 1)

A non-transitory computer-readable medium storing computer-readable instructions that, when executed by at least one processor, cause the at least one processor to perform the method of claim 1.

### Claim 19 (depends on 1)

The method of claim 1, further comprising:
identifying pixels of the difference image having a corresponding pixel value that exceeds a pixel value threshold,
wherein the calculating calculates the frequency distribution of pixel values of the identified pixels.

### Claim 20 (depends on 1)

The method of claim 1, wherein
the frequency distribution includes a plurality of frequency bins, each frequency bin of the plurality of frequency bins being associated with a corresponding pixel value range of a plurality of different pixel value ranges, the plurality of frequency bins including a highest frequency bin associated with a highest pixel value range of the plurality of different pixel value ranges, the highest pixel value range including a highest pixel value of the pixel values of the difference image, and
the determining includes determining the test value based on the frequency distribution such that the test value increases as one or more frequencies of the highest frequency bin increase.

### Claim 21 (depends on 1)

The method of claim 1, wherein the determining includes:
determining the test value based on the frequency distribution such that the test value increases as a highest pixel value of the pixel values of the difference image increases.

### Claim 22

A transformation determination device for determining a registration transformation for image registration of a first image relative to a second image, comprising:
a first memory configured to store first computer-readable instructions thereon; and
at least one first processor coupled to the first memory and configured to execute the first computer-readable instructions to
generate a plurality of test elements, each test element among the plurality of test elements including a test transformation and a test value, the generation including determining a test element among the plurality of test elements by at least
determining a test transformation of the test element based on at least one of
a sequence of test transformations, or
one or more previously determined test elements among the test plurality of test elements,
transforming the first image via the determined test transformation,
generating a difference image based on the transformed first image and the second image,
calculating a frequency distribution of pixel values of the difference image, and
determining a test value of the test element based on the frequency distribution such that the test value increases as one or more frequencies of higher pixel values increase,
determine a minimum test value among the test values included in the plurality of test elements, and
determine the registration transformation as the test transformation included in the same test element as the minimum test value.

### Claim 23 (depends on 22)

An image determination device comprising:
the transformation determination device of claim 22.

### Claim 24 (depends on 22)

An image determination device for determining a subtraction angiography image based on a first image pair set containing one or more first image pairs, each of the one or more first image pairs including a mask image and a contrast agent image, the image determination device comprising the transformation determination device of claim 22, wherein the at least one first processor is further configured to execute the first computer-readable instructions to
provide the first image pair set;
generate a registered image pair set containing one or more registered image pairs by performing at least the following for each of the one or more first image pairs of the first image pair set
determining a registration transformation via the transformation determination device, the first image being the mask image of the first image pair and the second image being the contrast agent image of the first image pair, and
transforming the mask image via the determined registration transformation, the transformed mask image and the contrast agent image forming a registered image pair of the registered image pair set; and
determine the subtraction angiography image based on the registered image pair set.

### Claim 25 (depends on 24)

An imaging apparatus comprising:
the image determination device of claim 24.

### Claim 26 (depends on 22)

An image determination device for determining a subtraction angiography image based on a first image pair set containing one or more first image pairs, each of the one or more first image pairs including a mask image and a contrast agent image, the image determination device comprising:
a second memory configured to store second computer-readable instructions thereon; and
at least one second processor coupled to the second memory and configured to execute the second computer-readable instructions to
provide the first image pair set,
generate a registered image pair set containing one or more registered image pairs by performing at least the following for each of the one or more first image pairs of the first image pair set
determining a registration transformation via the transformation determination device of claim 22, the first image being the mask image of the first image pair and the second image being the contrast agent image of the first image pair, and
transforming the mask image via the determined registration transformation, the transformed mask image and the contrast agent image forming a registered image pair of the registered image pair set, and
determine the subtraction angiography image based on the registered image pair set.

### Claim 27 (depends on 22)

An imaging apparatus comprising:
the transformation determination device of claim 22.

### Claim 28 (depends on 1)

The method of claim 1, wherein
the test value is determined based on a pixel group of the difference image,
the test value is at least one of
a parameter of at least one of the pixel group or the difference image, or
determined based on the parameter of at least one of the pixel group or the difference image, and
the parameter includes at least one of a maximum of the pixel values, a sum of the pixel values or a location parameter of the frequency distribution.

### Claim 29 (depends on 28)

The method of claim 28, wherein the location parameter includes at least one of a mean value, a mode or a quantile.