# US 10,768,259 B2 · Cerebrovascular segmentation from MRA images

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

- Number: US 10,768,259 B2
- Document ID: US10768259B2
- Status: Granted
- Kind: B2
- Application number: 16/159,790
- Filed: 2018-10-15
- Published: 2020-04-16
- Granted: 2020-09-08
- Earliest claimed: 2018-10-15
- Assignees: Zayed University
- Applicants: Zayed University
- Inventors: Fatma Taher; Ayman S. El-Baz
- Web page: https://patentgrep.com/patent/US10768259B2

## CPC

- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/4064: {Evaluating the brain (for intracranial pressure A61B5/031; for cerebral blood gases A61B5/14553; using EEG A61B5/369)}
- A61B 5/489: {Blood vessels}
- G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)}
- G01R 33/56316: {involving phase contrast techniques}
- G01R 33/5635: {Angiography, e.g. contrast-enhanced angiography [CE-MRA] or time-of-flight angiography [TOF-MRA]}
- G06T 5/90: Dynamic range modification of images or parts thereof
- G06T 7/11: Region-based segmentation
- G06T 7/143: involving probabilistic approaches, e.g. Markov random field [MRF] modelling
- G06T 7/162: involving graph-based methods
- A61B 5/02014: {Determining aneurysm}
- A61B 5/0263: {using NMR}
- A61B 2576/026: for the brain
- G01R 33/5602: {by filtering or weighting based on different relaxation times within the sample, e.g. T1 weighting using an inversion pulse}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20121: Active appearance model [AAM]
- G06T 2207/20224: Image subtraction
- G06T 2207/30016: Brain
- G06T 2207/30104: Vascular flow; Blood flow; Perfusion
- G16H 30/40: for processing medical images, e.g. editing
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

There is provided a method of processing a cerebrovascular medical image, the method comprising receiving magnetic resonance angiography (MRA) image associated with a cerebrovascular tissue comprising blood vessels and brain tissues other than blood vessels; segmenting MRA image using a prior appearance model for generating first prior appearance features representing a first-order prior appearance model and second appearance features representing a second-order prior appearance model of the cerebrovascular tissue, wherein current appearance model comprises a 3D Markov-Gibbs Random Field (MGRF) having a 2D rotational and translational symmetry such that MGRF model is 2D rotation and translation invariant; segmenting MRA image using current appearance model for generating current appearance features distinguishing blood vessels from other brain tissues; adjusting MRA image using first and second prior appearance features and current appearance futures; and generating an enhanced MRA image based on said adjustment. There is also provided a system for doing the same.

## Claims

### Claim 1

A method of processing a cerebrovascular medical image, the method comprising:
receiving a magnetic resonance angiography (MRA) image associated with a cerebrovascular tissue comprising blood vessels and brain tissues other than blood vessels;
segmenting the MRA image using a prior appearance model for generating first prior appearance features representing a first-order prior appearance model and second appearance features representing a second-order prior appearance model of the cerebrovascular tissue, wherein the current appearance model comprises a 3D Markov-Gibbs Random Field (MGRF) having a 2D rotational and translational symmetry such that the MGRF model is 2D rotation and translation invariant;
segmenting the MRA image using a current appearance model for generating current appearance features distinguishing the blood vessels from the other brain tissues;
adjusting the MRA image using the first and second prior appearance features and the current appearance futures; and
generating an enhanced MRA image based on said adjustment.

### Claim 2 (depends on 1)

The method of processing a cerebrovascular medical image according to claim 1, wherein said prior appearance model uses interaction parameters analytically estimated from a set of MRA training data.

### Claim 3 (depends on 2)

The method of processing a cerebrovascular medical image according to claim 2, wherein the first prior appearance features representing a first-order prior appearance model and the second appearance features representing a second-order prior appearance model are respectively provided by energies of the training data according to the following equations:
E
0
⁡
(
z
)
=
∑
q
=
0
Q
-
1
⁢
F
0
,
vasc
⁡
(
q
,
z
)
⁡
[
F
0
,
vasc
⁡
(
q
;
z
)
-
1
_
]
E
v
⁡
(
z
)
=
∑
q
=
0
Q
-
1
⁢
∑
q
′
=
0
Q
-
1
⁢
F
v
,
vasc
⁡
(
q
,
q
′
;
z
)
⁡
[
F
v
,
vasc
⁡
(
q
,
q
′
;
z
)
-
1
_
]
wherein:
E0: variance of a co-occurrence distribution representing the first order prior appearance model;
Ev: variance of a co-occurrence distribution representing the second order prior appearance model;
F0,vasc: marginal empirical distributions of gray levels;
Fv,vasc: gray level co-occurrences.

### Claim 4 (depends on 3)

The method of processing a cerebrovascular medical image according to claim 3, wherein said prior appearance model excludes alignment of the training data.

### Claim 5 (depends on 4)

The method of processing a cerebrovascular medical image according to claim 4, wherein said current appearance model comprises a Linear combination of Discrete Gaussians (LCDG) model and an EM-based model for linear combination of Gaussian approximation.

### Claim 6 (depends on 5)

The method of processing a cerebrovascular medical image according to claim 5, wherein said generating current appearance features comprises estimating first Gibbs probability densities of voxels to be blood vessels (P (q Vessels)) and estimating second Gibbs probability densities of voxels to be brain tissues other than blood vessels (P (q Brain)) according to the following equations respectively and making probabilistic decisions based on said first and second calculated Gibbs probability densities:
P
⁡
(
q
|
Brain
)
=
1
α
⁢
∑
r
=
1
2
⁢
wp
,
r
⁢
⁢
ψ
⁡
(
q
|
θ
⁢
⁢
p
,
r
)
-
∑
l
=
1
C
n
⁢
w
n
,
l
⁢
ψ
⁡
(
q
|
θ
n
,
l
)
P
⁡
(
qVessels
)
=
1
1
-
α
⁢
∑
r
=
3
C
p
⁢
wp
,
r
⁢
⁢
ψ
⁡
(
q
|
θ
⁢
⁢
p
,
r
)
-
∑
l
=
1
C
n
⁢
w
n
,
l
⁢
ψ
⁡
(
q
|
θ
n
,
l
)
Where
⁢
⁢
α
=
wp
,
1
+
wp
,
2
∑
r
⁢
w
p
,
r
and wherein Cp, Cn, wp, wn, θp, θn denotes parameters of the LCDG.

### Claim 7 (depends on 6)

The method of processing a cerebrovascular medical image according to claim 6, further comprising applying bias correction and skull stripping to the MRA image prior to the segmentations.

### Claim 8 (depends on 7)

The method of processing a cerebrovascular medical image according to claim 7, wherein the adjusting of the MRA image comprises analysing the MRA image using a 3D connectivity analysis based on the first and second prior appearance features and the current appearance futures.

### Claim 9 (depends on 8)

The method of processing a cerebrovascular medical image according to claim 8, wherein the adjusting the MRA image is conducted using a Random Forest model.

### Claim 10 (depends on 1)

The method of processing a cerebrovascular medical image according to claim 1, wherein the blood vessels comprise small and large blood vessels.

### Claim 11 (depends on 1)

The method of processing a cerebrovascular medical image according to claim 1, wherein said MRA image of a cerebrovascular tissue is related to a mammalian.

### Claim 12 (depends on 11)

The method of processing a cerebrovascular medical image according to claim 11, wherein said mammalian is a human.

### Claim 13 (depends on 1)

The system for processing a cerebrovascular medical image according to claim 1, further comprising a display for displaying the enhanced MRA image to a user.

### Claim 14

A system for processing a cerebrovascular medical image, the system comprising:
a data input interface for receiving a magnetic resonance angiography (MRA) image associated with a cerebrovascular tissue comprising blood vessels and brain tissues other than blood vessels;
at least one processor for processing the received MRA image, the MRA image processing comprising:
segmenting the MRA image using a prior appearance model for generating first prior appearance features representing a first-order prior appearance model and second appearance features representing a second-order prior appearance model of the cerebrovascular tissue, wherein the current appearance model comprises a 3D Markov-Gibbs Random Field (MGRF) having a 2D rotational and translational symmetry such that the MGRF model is 2D rotation and translation invariant;
segmenting the MRA image using a current appearance model for generating current appearance features distinguishing the blood vessels from the other brain tissues;
adjusting the MRA image using the first and second prior appearance features and the current appearance futures; and
generating an enhanced MRA image based on said adjustment.

### Claim 15 (depends on 14)

The system for processing a cerebrovascular medical image according to claim 14, wherein said prior appearance model uses interaction parameters analytically estimated from a set of MRA training data.

### Claim 16 (depends on 15)

The system for processing a cerebrovascular medical image according to claim 15, wherein the first prior appearance features representing a first-order prior appearance model and the second appearance features representing a second-order prior appearance model are respectively provided by energies of the training data according to the following equations:
E
0
⁡
(
z
)
=
∑
q
=
0
Q
-
1
⁢
F
0
,
vasc
⁡
(
q
,
z
)
⁡
[
F
0
,
vasc
⁡
(
q
;
z
)
-
1
_
]
E
v
⁡
(
z
)
=
∑
q
=
0
Q
-
1
⁢
∑
q
′
=
0
Q
-
1
⁢
F
v
,
vasc
⁡
(
q
,
q
′
;
z
)
⁡
[
F
v
,
vasc
⁡
(
q
,
q
′
;
z
)
-
1
_
]
wherein:
E0: variance of a co-occurrence distribution representing the first order prior appearance model;
Ev: variance of a co-occurrence distribution representing the second order prior appearance model;
F0,vasc: marginal empirical distributions of gray levels;
Fv,vasc: gray level co-occurrences.

### Claim 17 (depends on 16)

The system for processing a cerebrovascular medical image according to claim 16, wherein said prior appearance model excludes alignment of the training data.

### Claim 18 (depends on 17)

The system for processing a cerebrovascular medical image according to claim 17, wherein said current appearance model comprises a Linear combination of Discrete Gaussians (LCDG) model and an EM-based model for linear combination of Gaussian approximation.

### Claim 19 (depends on 18)

The system for processing a cerebrovascular medical image according to claim 18, wherein said generating current appearance features comprises estimating first Gibbs probability densities of voxels to be blood vessels (P (q Vessels)) and estimating second Gibbs probability densities of voxels to be brain tissues other than blood vessels (P (q Brain)) according to the following equations respectively and making probabilistic decisions based on said first and second calculated Gibbs probability densities:
P
⁡
(
q
|
Brain
)
=
1
α
⁢
∑
r
=
1
2
⁢
wp
,
r
⁢
⁢
ψ
⁡
(
q
|
θ
⁢
⁢
p
,
r
)
-
∑
l
=
1
C
n
⁢
w
n
,
l
⁢
ψ
⁡
(
q
|
θ
n
,
l
)
P
⁡
(
qVessels
)
=
1
1
-
α
⁢
∑
r
=
3
C
p
⁢
wp
,
r
⁢
⁢
ψ
⁡
(
q
|
θ
⁢
⁢
p
,
r
)
⁢
∑
l
=
1
C
n
⁢
-
w
n
,
l
⁢
ψ
⁡
(
q
|
θ
n
,
l
)
Where
⁢
⁢
α
=
wp
,
1
+
wp
,
2
∑
r
⁢
w
p
,
r
and wherein Cp, Cn, wp, wn, θp, θn denotes the parameters of the LCDG.

### Claim 20 (depends on 19)

The system for processing a cerebrovascular medical image according to claim 19, wherein the MRA image processing further comprising applying bias correction and skull stripping to the MRA image prior to the segmentations.

### Claim 21 (depends on 20)

The system for processing a cerebrovascular medical image according to claim 20, wherein the adjusting of the MRA image comprises analysing the MRA image using a 3D connectivity analysis based on the first and second prior appearance features and the current appearance futures.

### Claim 22 (depends on 21)

The system for processing a cerebrovascular medical image according to claim 21, wherein the adjusting the MRA image is conducted using a Random Forest model.