CN111445492A - Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image - Google Patents

Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image Download PDF

Info

Publication number
CN111445492A
CN111445492A CN202010224539.0A CN202010224539A CN111445492A CN 111445492 A CN111445492 A CN 111445492A CN 202010224539 A CN202010224539 A CN 202010224539A CN 111445492 A CN111445492 A CN 111445492A
Authority
CN
China
Prior art keywords
image
fusion
decomposition
follows
images
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010224539.0A
Other languages
Chinese (zh)
Inventor
袁双虎
李玮
李莉
韩毅
刘宁
刘希斌
陈财
袁朔
吕慧颖
于金明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinan Bishan Network Technology Co ltd
Shandong Cancer Hospital & Institute (shandong Cancer Hospital)
Beijing Yikang Medical Technology Co ltd
Shandong University
Original Assignee
Jinan Bishan Network Technology Co ltd
Shandong Cancer Hospital & Institute (shandong Cancer Hospital)
Beijing Yikang Medical Technology Co ltd
Shandong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinan Bishan Network Technology Co ltd, Shandong Cancer Hospital & Institute (shandong Cancer Hospital), Beijing Yikang Medical Technology Co ltd, Shandong University filed Critical Jinan Bishan Network Technology Co ltd
Priority to CN202010224539.0A priority Critical patent/CN111445492A/en
Publication of CN111445492A publication Critical patent/CN111445492A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20064—Wavelet transform [DWT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Urology & Nephrology (AREA)
  • Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

A three-dimensional fusion method of a magnetic resonance image and a radiotherapy positioning image comprises the following steps of firstly, thinning and detecting the edge of an image, and rotating the image to obtain four parameters of the image; and performing wavelet decomposition on the image to obtain a high-frequency component in the vertical direction and a low-frequency component in the horizontal direction, establishing tower decomposition of the image, and performing wavelet image reconstruction after image fusion. The current radiotherapy calibration method needs manual cooperation, is relatively complicated in calibration and partially depends on the experience of a clinician, and the method determines the target area and the spatial relationship between the target area and surrounding normal tissues, accurately calibrates the position of the target area and reduces the radioactive damage of the surrounding normal tissues.

Description

Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image
Technical Field
The invention relates to the field of three-dimensional fusion of images, in particular to a three-dimensional fusion calibration method of a magnetic resonance image and a radiotherapy positioning image.
Background
With the development of science and technology in the medical field, magnetic resonance imaging technology has become very popular, which uses static magnetic field and radio frequency magnetic field to image human tissue, and in the imaging process, a clear image with high contrast can be obtained without using electron ion radiation or contrast agent. It can reflect the abnormality and early pathological changes of human organs from the interior of human molecules.
At present, before radiotherapy is carried out on a patient, an imaging technology is required to be applied to determine a target area and the spatial relation between the target area and surrounding normal tissues, the position of the target area is accurately calibrated, and radioactive damage to the surrounding normal tissues is reduced. However, the current calibration method has the disadvantages of manual cooperation, low accuracy, slow calibration speed, partial dependence on the experience of a clinician, low sensitivity to a local target region and the like.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a three-dimensional fusion calibration method for a magnetic resonance image and a radiotherapy positioning image
In order to achieve the purpose, the invention adopts the following technical scheme:
for two images, edge thinning detection is carried out to facilitate the following image fusion, and the principle of the sub-pixel edge detection of the Zemike moment is to calculate 4 edge parameters according to the rotation invariant characteristic of the Zemike moment and compare the parameters with a preset threshold value so as to accurately position. After the four edge parameters are determined, determining coordinate positioning;
based on the fine positioning of the edge detection, wavelet decomposition is respectively carried out, and the decomposition process is as follows:
the range of variation is in space L2(R) introducing a scale function
Figure BDA0002427206590000011
Let { VjIs L2(R) a multi-resolution analysis of (R) in tensor space
Figure BDA0002427206590000021
Form L2(R) a multi-resolution analysis of (R) a,
Figure BDA0002427206590000022
scale parameter of
Figure BDA0002427206590000023
Is composed of
Figure BDA0002427206590000024
The fusion steps of the acquired magnetic resonance and radiotherapy positioning images are as follows:
(1) respectively carrying out image decomposition on each source image, and establishing tower-shaped decomposition of the images;
(2) respectively carrying out fusion processing on the images decomposed in each layer, and carrying out fusion processing on different frequency components on each decomposition layer by adopting different fusion operators to finally obtain a fused pyramid;
(3) performing inverse wavelet transform on the pyramid obtained after fusion, namely reconstructing an image to obtain a reconstructed image which is a fused image
The wavelet transformation aims at decomposing an original image into a series of frequency channels respectively, and fusing different decomposition layers and different frequency bands respectively by utilizing a tower-shaped structure after decomposition, so that details from different images are effectively fused together; during fusion, different features and details carried by fused images are fused on a plurality of decomposition layers and a plurality of frequency bands by different operators respectively;
the fusion rule is as follows:
and (3) fusion rules:
(1) taking an average operator for the low-frequency part of the decomposed image;
(2) selecting and weighting average operators based on rectangular window characteristic measurement are adopted for the high-frequency part;
(3) operators with different characteristics are respectively selected for high-frequency parts in the vertical direction, the transverse direction and the diagonal direction;
the operator selection method is as follows:
(1) calculating corresponding local energies from the magnetic resonance image and the radiotherapy image
(2) Calculating the matching degree of the local areas of the two images
(3) And determining a fusion operator.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the application and not to limit the invention.
FIG. 1 is a flow chart disclosed in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
For both images, a refinement detection of the edges is performed to facilitate the following image fusion, the n-th order m-order Zernike matrix of f (x, y) of the images being defined as
Figure BDA0002427206590000031
Wherein,
Figure BDA0002427206590000032
is VnmThe complex conjugate of (a). The principle of sub-pixel edge detection of the Zemike moment is based on Zemike
The rotation invariant characteristic of the moment calculates 4 edge parameters, and compares the parameters with a preset threshold value, thereby accurately positioning. Z before and after rotationnmAnd the edge parameter φ is as follows:
Znm'＝Znme-imφ
Figure BDA0002427206590000033
from which other three-edge parameters can be determined
Figure BDA0002427206590000034
Figure BDA0002427206590000035
Figure BDA0002427206590000036
After the four edge parameters are determined, the coordinates are located as
Figure BDA0002427206590000041
Based on the fine positioning of the edge detection, wavelet decomposition is respectively carried out, and the decomposition process is as follows:
the range of variation is in space L2(R) introducing a scale function
Figure BDA0002427206590000042
Let { VjIs L2(R) a multi-resolution analysis of (R) in tensor space
Figure BDA0002427206590000043
Figure BDA0002427206590000044
Form L2(R) a multi-resolution analysis of (R) a,
Figure BDA0002427206590000045
scale parameter of
Figure BDA0002427206590000046
Is composed of
Figure BDA0002427206590000047
Assuming H and G as filter operators, r and c denote row and column, respectively, the decomposition at the scale j-1 is as follows:
Figure BDA0002427206590000048
wherein, Cj,
Figure BDA0002427206590000049
Is a low frequency component, a high frequency component in the vertical direction, a high frequency component in the horizontal direction, and a high frequency component of the image, and is opposed theretoThe corresponding reconstruction formula is
Figure BDA00024272065900000410
Wherein H*And G*The transposed conjugate matrices for H and G respectively,
the fusion steps of the acquired magnetic resonance and radiotherapy positioning images are as follows:
(4) respectively carrying out image decomposition on each source image, and establishing tower-shaped decomposition of the images;
(5) respectively carrying out fusion processing on the images decomposed in each layer, and carrying out fusion processing on different frequency components on each decomposition layer by adopting different fusion operators to finally obtain a fused pyramid;
(6) performing inverse wavelet transform on the pyramid obtained after fusion, namely reconstructing an image to obtain a reconstructed image which is a fused image
The wavelet transformation aims at decomposing an original image into a series of frequency channels respectively, and fusing different decomposition layers and different frequency bands respectively by utilizing a tower-shaped structure after decomposition, so that details from different images are effectively fused together; during fusion, different features and details carried by fused images are fused on a plurality of decomposition layers and a plurality of frequency bands by different operators respectively;
the fusion algorithm is as follows:
fusion rules and fusion algorithms based on regional characteristics:
(1) taking an average operator for the low-frequency part of the decomposed image;
(2) selecting and weighting average operators based on rectangular window characteristic measurement are adopted for the high-frequency part;
(3) operators with different characteristics are respectively selected for high-frequency parts in the vertical direction, the transverse direction and the diagonal direction;
the operator selection method is as follows:
(4) calculating the corresponding local energy from the magnetic resonance image and the radiotherapy image, and the related formula is as follows:
Figure BDA0002427206590000051
wherein E represents energy, D represents high frequency components,
Figure BDA0002427206590000055
representing the corresponding weight coefficients
(5) The matching degree of the local regions of the two images is as follows:
Figure BDA0002427206590000052
wherein M is the matching degree, and the calculation method of E is as shown above;
(6) determining fusion operators
Assume a match threshold of α, if MAB<α, then
Figure BDA0002427206590000053
When E isj,A≥Ej,B
Figure BDA0002427206590000054
When E isj,A＜Ej,B
MAB≥α, then
Figure BDA0002427206590000061
When E isj,A≥Ej,B
Figure BDA0002427206590000062
When E isj,A＜Ej,B
Wherein,
Figure BDA0002427206590000063
Figure BDA0002427206590000064
＝1,2,3
although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. A three-dimensional fusion method of a magnetic resonance image and a radiotherapy positioning image is characterized by comprising the following steps:
(1) for the two images, edge thinning detection and subpixel edge detection of Zemike moment are carried out, 4 edge parameters are calculated according to the rotation invariant characteristic of the Zemike moment, and the coordinate positioning of the images is determined;
(2) based on the fine positioning of the edge detection, wavelet decomposition is carried out respectively, and the decomposition process is as follows, the variation range of the decomposition process is in the space L2(R) introducing a scale function
Figure FDA0002427206580000011
Let { VjIs L2(R) a multi-resolution analysis of (R) in tensor space
Figure FDA0002427206580000012
Form L2(R) a multi-resolution analysis of (R) a,
Figure FDA0002427206580000013
scale parameter of
Figure FDA0002427206580000014
Is composed of
Figure FDA0002427206580000015
Calculating low-frequency and high-frequency components of the image in the horizontal and vertical directions, and establishing a reconstruction formula of the low-frequency and high-frequency components;
(3) respectively carrying out image decomposition on each source image, establishing tower-shaped decomposition of the images, respectively carrying out fusion processing on the decomposed images of each layer, and carrying out fusion processing on different frequency components on each decomposition layer by adopting different fusion operators to finally obtain a fused pyramid;
(3) and performing wavelet inverse transformation on the pyramid obtained after fusion, namely performing image reconstruction to obtain a reconstructed image which is the fused image.
2. The method of claim 1, wherein Z is before and after rotationnmAnd φ is as follows:
Znm'＝Znme-imφ
Figure FDA0002427206580000016
3. the method of claim 1, wherein the edge parameters k, h, l are as follows:
Figure FDA0002427206580000017
Figure FDA0002427206580000018
Figure FDA0002427206580000021
4. the method of claim 1, wherein the decomposition of the image at the scale j-1 is as follows:
Cj＝HcHrCj-1
Figure FDA0002427206580000022
Figure FDA0002427206580000023
Figure FDA0002427206580000024
5. the method of claim 1, wherein the reconstruction formula of the image at the scale j-1 is as follows:
Figure FDA0002427206580000025
6. the method of claim 1, wherein the rules for the image of step (3) are as follows: (1) taking an average operator for the low-frequency part of the decomposed image; (2) selecting and weighting average operators based on rectangular window characteristic measurement are adopted for the high-frequency part; (3) operators with different characteristics are respectively selected for high-frequency parts in the vertical direction, the transverse direction and the diagonal direction.
7. The method of claim 6, wherein the operator is selected as follows:
(1) calculating corresponding local energies from the magnetic resonance image and the radiotherapy image;
(2) the matching degree of the local regions of the two images is as follows:
Figure FDA0002427206580000026
(3) and determining a fusion operator.
8. The method according to claim 7, wherein the specific step of determining the fusion operator is:
assume a match threshold of α, if MAB<α, then
Figure FDA0002427206580000027
When E isj,A≥Ej,B
Figure FDA0002427206580000028
When E isj,A＜Ej,B
MABNot less than α, then
Figure FDA0002427206580000031
When E isj,A≥Ej,B
Figure FDA0002427206580000032
When E isj,A＜Ej,B
Wherein,
Figure FDA0002427206580000033
Figure FDA0002427206580000034
＝1,2,3。
CN202010224539.0A 2020-03-26 2020-03-26 Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image Pending CN111445492A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010224539.0A CN111445492A (en) 2020-03-26 2020-03-26 Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010224539.0A CN111445492A (en) 2020-03-26 2020-03-26 Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image

Publications (1)

Publication Number Publication Date
CN111445492A true CN111445492A (en) 2020-07-24

Family

ID=71648092

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010224539.0A Pending CN111445492A (en) 2020-03-26 2020-03-26 Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image

Country Status (1)

Country Link
CN (1) CN111445492A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114693579A (en) * 2022-05-23 2022-07-01 北京物资学院 Monitoring image processing system in logistics warehouse

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093449A (en) * 2013-02-28 2013-05-08 重庆大学 Multi-resolution fusion radial image enhancement method
CN105303535A (en) * 2015-11-15 2016-02-03 中国人民解放军空军航空大学 Global subdivision pyramid model based on wavelet transformation
CN106910179A (en) * 2017-01-22 2017-06-30 南京觅踪电子科技有限公司 Multimode medical image fusion method based on wavelet transformation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093449A (en) * 2013-02-28 2013-05-08 重庆大学 Multi-resolution fusion radial image enhancement method
CN105303535A (en) * 2015-11-15 2016-02-03 中国人民解放军空军航空大学 Global subdivision pyramid model based on wavelet transformation
CN106910179A (en) * 2017-01-22 2017-06-30 南京觅踪电子科技有限公司 Multimode medical image fusion method based on wavelet transformation

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘贵喜 等: "基于小波分解的图像融合方法及性能评价", 《自动化学报》 *
巴本东: "基于亚像素边缘特征的头部图像配准与融合研究", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114693579A (en) * 2022-05-23 2022-07-01 北京物资学院 Monitoring image processing system in logistics warehouse

Similar Documents

Publication Publication Date Title
Harms et al. Paired cycle‐GAN‐based image correction for quantitative cone‐beam computed tomography
JP6301081B2 (en) X-ray computed tomography apparatus, image reconstruction method, and structure of reconstruction filter
AU768756B2 (en) Imaging
US20120263360A1 (en) Scatter correction methods
Hristov et al. A grey‐level image alignment algorithm for registration of portal images and digitally reconstructed radiographs
JP4885138B2 (en) Method and system for motion correction in a sequence of images
WO2006008089A1 (en) Method for producing x-ray computer tomography images from limited data of an image object
Jin et al. Deep learning-enabled accurate normalization of reconstruction kernel effects on emphysema quantification in low-dose CT
CN104599268A (en) Local area accurate deformation registration algorithm combining point registration
Athavale et al. Multiscale properties of weighted total variation flow with applications to denoising and registration
Rabe et al. Porcine lung phantom-based validation of estimated 4D-MRI using orthogonal cine imaging for low-field MR-Linacs
Jiang et al. Enhancing digital tomosynthesis (DTS) for lung radiotherapy guidance using patient-specific deep learning model
CN111445492A (en) Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image
Che et al. AMNet: Adaptive multi-level network for deformable registration of 3D brain MR images
Oguz et al. Cortical correspondence using entropy-based particle systems and local features
CN112070856A (en) Limited angle C-arm CT image reconstruction method based on non-subsampled contourlet transform
CN103908252B (en) A kind of background phase extracting method and system
Dam et al. Prostate shape modeling based on principal geodesic analysis bootstrapping
CN114820432B (en) Radiotherapy effect evaluation method based on PET and CT elastic registration technology
CN116188615A (en) Sparse angle CT reconstruction method based on sine domain and image domain
CN115619693A (en) Space-time fusion model based on nested multi-scale transformation
CN113822796A (en) Multi-modal brain image registration method based on improved image pyramid
KR102329938B1 (en) Method for processing conebeam computed tomography image using artificial neural network and apparatus therefor
Thaler et al. Volumetric reconstruction from a limited number of digitally reconstructed radiographs using cnns
CN111583303A (en) System and method for generating pseudo CT image based on MRI image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200724

RJ01 Rejection of invention patent application after publication