US 10,853,941 B2Granted

Registration method and system for non-rigid multi-modal medical image

AssigneeHuazhong University of Science and Technology

InventorsXuming Zhang, Fei Zhu, Jingke Zhang, Jinxia Ren, Feng Zhao, Guanyu Li, Mingyue Ding

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present invention discloses a registration method and system for a non-rigid multi-modal medical image. The registration method comprises: obtaining local descriptors of a reference image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the reference image; obtaining local descriptors of a floating image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the floating image; and finally obtaining a registration image according to the local descriptors of the reference image and the floating image. In the present, by using self-similarity of the multi-modal medical image and adopting the Zernike moment based local descriptor, the non-rigid multi-modal medical image registration is thus converted into the non-rigid mono-modal medical image registration, thereby greatly improving its accuracy and robustness.

A registration method for a non-rigid multi-modal medical image, comprising:

according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of a reference image and a floating image, respectively obtaining a local descriptor of the reference image and a local descriptor of the floating image, and obtaining a registration image, wherein the method comprises the following steps:
step 1:
obtaining the local descriptor ZMLDA(i) of the reference image IA(i) according to a Zernike moment ZA00(i) of order 0 and repetition 0 and a Zernike moment ZA11(i) of order 1 and repetition 1 of a pixel point i in the reference image IA(i), wherein i is an integer from 1 to M, and M represents the size of the reference image and the floating image;
step 2:
obtaining the local descriptor ZMLDB(i) of the floating image IB(i) according to a Zernike moment Z800(i) of order 0 and repetition 0 and a Zernike moment ZB11(i) of order 1 and repetition 1 of a pixel point i at the same position in the floating image IB(i);
and
step 3:
establishing an objective function g(T) according to the local descriptor ZMLDA(i) of the reference image and the local descriptor ZMLDB(i) of the floating image;
obtaining a transformation parameter according to the objective function, transforming the floating image according to the transformation parameter, and performing an interpolation process on a transformed floating image, thereby obtaining the registration image,
wherein the step 2 further comprises the following sub-steps:
step 2-1:
obtaining a similarity distance DA00(i) corresponding to the Zernike moment of order 0 and repetition 0 and a similarity distance DA11(i) corresponding to the Zernike moment of order 1 and repetition 1 of the pixel point i to other pixel points in an image patch centered at the pixel point i in the reference image;
simultaneously, obtaining a similarity distance DB00(i) corresponding to the Zernike moment of order 0 and repetition 0 and a similarity distance DB11(i) corresponding to the Zernike moment of order 1 and repetition 1 of the pixel point i to other pixel points in an image patch centered at the pixel point i in the floating image;
step 2-2:
obtaining the local descriptor ZMLDA(i) of the reference image and the local descriptor ZMLDB (i) of the floating image,
ZMLD
A
⁡
(
i
)
=
exp
⁡
(
-
D
00
A
⁡
(
i
)
00
A
⁢
(
i
)
-
D
11
A
⁡
(
i
)
11
A
⁢
(
i
)
)
,
⁢
ZMLD
B
⁡
(
i
)
=
exp
⁡
(
-
D
00
B
⁡
(
i
)
00
B
⁢
(
i
)
-
D
11
B
⁡
(
i
)
11
B
⁢
(
i
)
)
,
wherein hA00(i), hA11(i), hB00(i) and hB11(i) are decay parameters.

94 more elements

Facts

Application

16/094,473Filed 9 Oct 2016

Priority

CN 2016 1 050661930 Jun 2016

Published

US 2019/0130572 A12 May 2019

Granted

1 Dec 2020

Term ends

Not estimatedThe source records don’t support an estimate.

Classification20 codes

G06T 7/0016
Using an image reference approach: involving temporal comparison
G06T 3/14
Geometric image transformations in the plane of the image: transformations for image registration, e.g. adjusting or mapping for alignment of images
G06T 3/60
Geometric image transformations in the plane of the image: rotation of whole images or parts thereof
G06T 7/00
Image analysis

Abstract

Claims11