CN111612778B - Preoperative CTA and intraoperative X-ray coronary artery registration method - Google Patents
Preoperative CTA and intraoperative X-ray coronary artery registration method Download PDFInfo
- Publication number
- CN111612778B CN111612778B CN202010456226.8A CN202010456226A CN111612778B CN 111612778 B CN111612778 B CN 111612778B CN 202010456226 A CN202010456226 A CN 202010456226A CN 111612778 B CN111612778 B CN 111612778B
- Authority
- CN
- China
- Prior art keywords
- ray
- cta
- center line
- point
- registration
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 210000004351 coronary vessel Anatomy 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 6
- 210000004204 blood vessel Anatomy 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000002591 computed tomography Methods 0.000 abstract 2
- 238000001356 surgical procedure Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013152 interventional procedure Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/504—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10116—X-ray image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30172—Centreline of tubular or elongated structure
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Optics & Photonics (AREA)
- Public Health (AREA)
- High Energy & Nuclear Physics (AREA)
- Veterinary Medicine (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Pulmonology (AREA)
- Vascular Medicine (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for registering a preoperative CTA (computed tomography) and an intraoperative X-ray coronary artery, which relates to the technical field of medical image processing and is characterized in that real-time registration is realized based on a point cloud registration network. According to the invention, the deformation field is directly predicted through the trained registration network without iterative optimization, so that the real-time requirement is met, the method has the advantages of rapidness, accuracy, suitability for practical application and the like, and the complexity of doctor operation can be reduced.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a registration method of preoperative CTA and intraoperative X-ray coronary artery.
Background
In recent years, with the improvement of the living standard of people, the incidence of cardiovascular diseases is also increasing. The current treatment is interventional surgery, which aims at dredging the stenosis with a guide wire. During interventional procedures, a physician often determines the position and direction of travel of the guidewire by taking X-ray contrast images. However, this presents a significant challenge to the surgeon's surgical procedure due to the varying degrees of artifacts present in X-ray coronary angiography. Meanwhile, the success rate of the surgery depends largely on the actual experience of the doctor. Before surgery, the physician would have a general knowledge of the patient's blood vessel by taking CTA, but often taken into account separately from the intraoperative X-rays.
The discovery of the prior art shows that the common coronary artery registration method is a characteristic-based registration method. For example, the most recent iterative point method, which treats the coronary registration problem as a rigid point set registration problem. Firstly, extracting a blood vessel center line as a point set to be registered, and then iteratively searching for an optimal rigid transformation matrix by optimizing Euclidean distance between the two point sets. The consistency point drift method extends the coronary registration to a non-rigid registration problem, which is regarded as a probability density estimation problem. It fits the center of one set of points to another set of points through likelihood maximization. However, since the above methods all require iterative optimization, it is often difficult to meet the real-time requirements. Along with the development of deep learning in the field of image processing, a point cloud registration method based on learning is also greatly developed. The method utilizes a point cloud network to extract features from a point set, inputs the features into a multi-layer perceptron and outputs required transformation parameters. Such methods can predict deformation fields end-to-end, which also provides a solution for coronary registration.
Accordingly, those skilled in the art have focused their efforts on developing methods of registering preoperative CTA with intraoperative X-rays in real time to reduce the complexity of the surgeon's procedure.
Disclosure of Invention
In view of the above problems, the technical problem to be solved by the invention is to realize real-time registration of preoperative CTA and intraoperative X-ray, and adopt an end-to-end preoperative CTA and intraoperative X-ray coronary artery registration method. The deformation field is directly predicted through the trained registration network without iterative optimization, so that the real-time requirement is met.
In order to achieve the above purpose, the invention provides a method for registering preoperative CTA and intraoperative X-ray coronary artery, which is characterized in that real-time registration is achieved based on a point cloud registration network.
Further, the method for registering the preoperative CTA with the intraoperative X-ray coronary artery comprises the following steps:
step 1, performing blood vessel segmentation on the CTA data before operation and the X-ray data in operation by using a convolutional neural network U-Net to obtain CTA blood vessels and X-ray blood vessels, extracting a maximum communication area, and performing central line extraction on the segmentation result by using a skeleton extraction algorithm to obtain a CTA central line and an X-ray central line;
step 2, calibrating an X-ray machine, reading DICOM header file information, constructing a projection matrix, and generating a projection center line by using the CTA center line;
and 3, performing point set sampling on the projection center line and the X-ray center line, inputting the point set sampling into the point cloud registration network to obtain a deformation field, deforming the projection center line by using the deformation field, calculating a loss function with the X-ray center line, and optimizing the point cloud registration network.
Further, the step 1 includes the following steps:
step 1.1, performing pixel-by-pixel vessel labeling on the preoperative CTA data, and training the convolutional neural network U-Net for CTA vessel segmentation by using an original image and a corresponding label;
step 1.2, carrying out pixel-by-pixel vessel labeling on the X-ray data in the operation, and training the convolutional neural network U-Net for X-ray vessel segmentation by utilizing the original image and the corresponding label;
step 1.3, analyzing the maximum connected domain of the CTA blood vessel and the X-ray blood vessel obtained by the segmentation, reserving the maximum connected domain, extracting a main blood vessel, and removing noise;
step 1.4, extracting the central line of the blood vessel by using the skeleton extraction algorithm.
Further, step 2 reads the DICOM header information, where the DICOM header information includes: (1) a probe-to-target distance SDD; (2) width W of the image; (3) height H of the image.
Further, the formula for constructing the projection matrix in the step 2 is as follows:
wherein s is H Is the pixel interval in the X-axis direction, s W Is the pixel spacing in the Y-axis direction.
Further, in step 2, the projection matrix and the CTA center line are utilized to generate the projection center line, and the formula is as follows:
wherein, (x) i ,y i ) Coordinates of each pixel point for the CTA centerline.
Further, the step 3 includes the following steps:
step 3.1, constructing the point cloud registration network based on a DGCNN point cloud network, wherein the point cloud registration network comprises 5 side convolution layers, the convolution kernel number of each side convolution layer is 64, 64, 128, 256 and 512 respectively, and then 1 three-layer perceptron is connected, and the unit number of each perceptron is 256 and 128,2 respectively;
and 3.2, forming a registration pair according to the projection center line generated in the step 2 and the X-ray center line obtained in the step 1. 600 points are randomly sampled from the projection center line and the X-ray center line and used as blood vessel characteristic points to be input into the point cloud registration network;
step 3.3, outputting the deformation field through processing the point cloud registration network, wherein the deformation field comprises the displacement of each blood vessel characteristic point and is represented by T;
and 3.4, deforming the projection center line according to the deformation field, wherein the formula is as follows:
P w (x i ,y i )＝P s (x i ,y i )+T(x i ,y i )
wherein P is s (x i ,y i ) Represents the coordinates of the ith point, T (x i ,y i ) Representing the deformation of the ith point, P w (x i ,y i ) Representing the coordinates of the ith point after deformation;
step 3.5, calculating the loss functions of the projection center line and the X-ray center line after deformation, wherein the loss functions comprise three parts, namely chamfer distances L chamfer Global topology constraint term L GMM Local topology constraint term L LPC The formula is as follows:
L＝L chamfer αL GMM +βL LPC
wherein, alpha and beta are used for measuring the intensity of constraint;
and 3.6, the loss function value obtained through calculation in the step is back-propagated to optimize the point cloud registration network, so that the point cloud registration network is fitted to an optimal solution.
Further, the chamfer distance L chamfer For measuring the distance between two point sets which do not correspond, for each point in the first point set, calculate the closest point to the other point set, and then accumulate the squares of the distances as follows:
wherein P is w Representing the deformed point set, P t Representing a set of target points.
Further, the global topological constraint term L GMM Defined as a gaussian mixture model error between two sets of points that measures similarity between two sets of points as a continuous density function, moving one set of points to the other coherently, as follows:
wherein P is w Representing the deformed point set, P t Representing a set of target points. Delta represents the standard deviation of the gaussian mixture model.
Further, the local topology constraint term L LPC Defined as the gradient between two points of the blood vessel, the length transformation range of the blood vessel is controlled, and the formula is as follows:
wherein P is s Representing the source point set, P w Representing the deformed point set.
Compared with the prior art, the method and the device have the advantages that the deformation field is predicted end to end by utilizing the point cloud registration network, and simultaneously, the topological constraint is applied, so that the deformation field is smoother and more reasonable, the real-time coronary artery registration is realized, the method and the device are rapid and accurate, and the method and the device are suitable for practical application.
The conception, specific structure, and technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, features, and effects of the present invention.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a block diagram of a point cloud registration network.
Detailed Description
The following description of the preferred embodiments of the present invention refers to the accompanying drawings, which make the technical contents thereof more clear and easy to understand. The present invention may be embodied in many different forms of embodiments and the scope of the present invention is not limited to only the embodiments described herein.
The embodiment is realized on a 64-bit Linux system, a 64GB RAM and an Intel (R) Xeon E5-2630 v3 CPU,Nvidia Titan X pascal GPU computer, and the whole method is realized by adopting a python programming language based on a PyTorch deep learning framework.
The implementation flow of this embodiment is shown in fig. 1, and specifically includes the following steps:
step 1, performing blood vessel segmentation on preoperative CTA and intraoperative X-ray data by utilizing a U-Net network, extracting a maximum connected region, and extracting a central line of a segmentation result by utilizing a skeleton extraction algorithm;
step 2, calibrating an X-ray machine, reading DICOM header file information, constructing a projection matrix, and generating a projection center line by using a CTA center line;
step 3, sampling a point set of the projection center line and the X-ray center line, inputting the point set into a point cloud registration network to obtain a deformation field, deforming the projection center line by using the deformation field, calculating a loss function with the X-ray center line, and optimizing the point cloud registration network;
further, the step 1 includes the following steps:
step 1.1, performing pixel-by-pixel vessel labeling on preoperative CTA data, and training a convolutional neural network U-Net for CTA vessel segmentation by using an original image and a corresponding label;
step 1.2, performing pixel-by-pixel vessel labeling on X-ray data in operation, and training a convolutional neural network U-Net for X-ray vessel segmentation by using an original image and a corresponding label;
step 1.3, carrying out maximum connected domain analysis on the CTA and X-ray blood vessels obtained by segmentation, reserving the maximum connected domain, extracting a main blood vessel, and removing noise;
and step 1.4, extracting the central line of the blood vessel by using a skeleton extraction algorithm.
Further, the step 2 includes the steps of:
step 2.1, calibrating an X-ray machine, and reading DICOM header file information, wherein the DICOM header file information comprises the following contents: (1) a probe-to-target distance SDD; (2) width W of the image; (3) height H of the image. The projection matrix is constructed using the following definition:
wherein s is H Is the pixel interval in the X-axis direction, s W Is the pixel spacing in the Y-axis direction.
Step 2.2, generating a projection center line by using the projection matrix and the CTA center line. The specific formula is as follows:
wherein, (x) i ,y i ) Sitting for each pixel point of CTA center lineAnd (5) marking.
Further, the step 3 includes the following steps:
step 3.1, constructing a registration network based on a DGCNN point cloud network, wherein the registration network totally comprises 5 side convolution layers, and the convolution kernel number of each side convolution layer is 64, 64, 128, 256 and 512 respectively. And then a three-layer perceptron is connected, and the number of units of each perceptron is 256 and 128,2 respectively.
And 3.2, forming a registration pair according to the projection center line generated in the step 2 and the X-ray center line obtained in the step 1. 600 points are randomly sampled for two centerlines and input into the network as vessel feature points.
And 3.3, outputting a deformation field through the processing of the registration network. The deformation field includes the displacement of each feature point, denoted by T.
And 3.4, deforming the projection center line according to a deformation field, wherein the specific formula is as follows:
P w (x i ,y i )＝P s (x i ,y i )+T(x i ,y i )
wherein P is s (x i ,y i ) Represents the coordinates of the ith point, T (x i ,y i ) Representing the deformation of the ith point, P w (x i ,y i ) Representing the coordinates of the i-th point after deformation.
And 3.5, calculating a loss function of the deformed central line and the X-ray central line. The loss function comprises three parts, namely a chamfer distance L chamfer Global topology constraint term L GMM Local topology constraint term L LPC . The specific formula is as follows:
L＝L chamfer αL GMM +βL LPC
where α and β are used to measure the strength of the constraint.
Chamfer distance L chamfer For measuring the distance between two sets of points that do not correspond. For each point in the first set of points, the closest point in the other set of points is calculated and then the squares of the distances are accumulated, defined in particular as follows:
wherein P is w Representing the deformed point set, P t Representing a set of target points.
Global topology constraints term L GMM Defined as a gaussian mixture model error between two sets of points that measures similarity between two sets of points as a continuous density function, moving one set of points coherently to the other set of points, specifically defined as follows:
wherein P is w Representing the deformed point set, P t Representing a set of target points. Delta represents the standard deviation of the gaussian mixture model.
Local topology constraint term L LPC Defined as the gradient between two points of the blood vessel, so that the length transformation range of the blood vessel is not too large, specifically defined as follows:
wherein P is s Representing the source point set, P w Representing the deformed point set.
And 3.6, calculating the loss function value, and back-propagating and optimizing the point cloud registration network to enable the point cloud registration network to be fitted to the optimal solution.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (8)
1. A registration method of preoperative CTA and intraoperative X-ray coronary artery is characterized in that real-time registration is realized based on a point cloud registration network;
the method comprises the following steps:
step 1, performing blood vessel segmentation on preoperative CTA data and intraoperative X-ray data by using a convolutional neural network U-Net to obtain CTA blood vessels and X-ray blood vessels, extracting a maximum communication region, and performing central line extraction on the segmentation result by using a skeleton extraction algorithm to obtain a CTA central line and an X-ray central line;
step 2, calibrating an X-ray machine, reading DICOM header file information, constructing a projection matrix, and generating a projection center line by using the CTA center line;
step 3, sampling the projection center line and the X-ray center line in a point set, inputting the point set into the point cloud registration network to obtain a deformation field, deforming the projection center line by using the deformation field, calculating a loss function with the X-ray center line, and optimizing the point cloud registration network;
the step 3 comprises the following steps:
step 3.1, constructing the point cloud registration network based on a DGCNN point cloud network, wherein the point cloud registration network totally comprises 5 side convolution layers, the convolution kernel number of each side convolution layer is respectively 64, 64, 128, 256 and 512, 1 three-layer perceptron is connected, and the unit number of each perceptron is respectively 256 and 128,2;
step 3.2, forming a registration pair according to the projection center line generated in the step 2 and the X-ray center line obtained in the step 1, and randomly sampling 600 points of the projection center line and the X-ray center line as blood vessel characteristic points to be input into the point cloud registration network;
step 3.3, outputting the deformation field through processing the point cloud registration network, wherein the deformation field comprises the displacement of each blood vessel characteristic point and is represented by T;
and 3.4, deforming the projection center line according to the deformation field, wherein the formula is as follows:
P w (x i ,y i )＝P s (x i ,y i )+T(x i ,y i )
wherein P is s (x i ,y i ) Represents the coordinates of the ith point, T (x i ,y i ) Representing the deformation of the ith point, P w (x i ,y i ) Representing the coordinates of the ith point after deformation;
step 3.5, calculating the loss functions of the projection center line and the X-ray center line after deformation, wherein the loss functions comprise three parts, namely chamfer distances L chamfer Global topology constraints item L GMM Local topology constraint term L LPC The formula is as follows:
L＝L chamfer +αL GMM +βL LPC
wherein, alpha and beta are used for measuring the intensity of constraint;
and 3.6, the loss function value obtained through calculation in the step is back-propagated to optimize the point cloud registration network, so that the point cloud registration network is fitted to an optimal solution.
2. The method of pre-operative CTA and intra-operative X-ray coronary registration according to claim 1, wherein step 1 comprises the steps of:
step 1.1, performing pixel-by-pixel vessel labeling on the preoperative CTA data, and training the convolutional neural network U-Net for CTA vessel segmentation by using an original image and a corresponding label;
step 1.2, carrying out pixel-by-pixel vessel labeling on the X-ray data in the operation, and training the convolutional neural network U-Net for X-ray vessel segmentation by utilizing the original image and the corresponding label;
step 1.3, analyzing the maximum connected domain of the CTA blood vessel and the X-ray blood vessel obtained by the segmentation, reserving the maximum connected domain, extracting a main blood vessel, and removing noise;
and 1.4, extracting the central lines of the CTA blood vessel and the X-ray blood vessel by using the skeleton extraction algorithm to obtain the CTA central line and the X-ray central line.
3. The method of pre-operative CTA and intra-operative X-ray coronary registration of claim 1 wherein step 2 reads the DICOM header file information comprising: (1) a probe-to-target distance SDD; (2) width W of the image; (3) height H of the image.
4. The method for registration of preoperative CTA with intraoperative X-ray coronary artery of claim 3 wherein the formula for constructing the projection matrix in step 2 is:
wherein s is H Is the pixel interval in the X-axis direction, s W Is the pixel spacing in the Y-axis direction.
5. The method for registration of preoperative CTA with intraoperative X-ray coronary artery as defined in claim 1, wherein the projection center line is generated in step 2 by using the projection matrix and the CTA center line, and the formula is as follows:
wherein, (x) i ,y i ) Coordinates of each pixel point for the CTA centerline.
6. A method of registration of preoperative CTA with an intraoperative X-ray coronary artery as defined in claim 1,
the chamfer distance L chamfer For measuring the distance between two point sets which do not correspond, for each point in the first point set, calculate the closest point to the other point set, and then accumulate the squares of the distances as follows:
wherein P is w Representing the deformed point set, P t Representing a set of target points.
7. The method of pre-operative CTA and intra-operative X-ray coronary registration of claim 1, wherein the global topological constraint term L GMM Defined as a gaussian mixture model error between two sets of points that measures similarity between two sets of points as a continuous density function, moving one set of points to the other coherently, as follows:
wherein P is w Representing the deformed point set, P t Represents the set of target points, and delta represents the standard deviation of the gaussian mixture model.
8. The method of pre-operative CTA and intra-operative X-ray coronary registration of claim 1 wherein the local topological constraint term L LPC Defined as the gradient between two points of the blood vessel, the length transformation range of the blood vessel is controlled, and the formula is as follows:
wherein P is s Representing the source point set, P w Representing the deformed point set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010456226.8A CN111612778B (en) | 2020-05-26 | 2020-05-26 | Preoperative CTA and intraoperative X-ray coronary artery registration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010456226.8A CN111612778B (en) | 2020-05-26 | 2020-05-26 | Preoperative CTA and intraoperative X-ray coronary artery registration method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111612778A CN111612778A (en) | 2020-09-01 |
| CN111612778B true CN111612778B (en) | 2023-07-11 |
Family
ID=72196340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010456226.8A Active CN111612778B (en) | 2020-05-26 | 2020-05-26 | Preoperative CTA and intraoperative X-ray coronary artery registration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612778B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884885A (en) * | 2021-03-17 | 2021-06-01 | 先临三维科技股份有限公司 | Method and device for training dental model deformation model |
| CN112991407B (en) * | 2021-04-02 | 2022-06-28 | 浙江大学计算机创新技术研究院 | Point cloud registration method based on non-local operation |
| TWI797767B (en) * | 2021-10-06 | 2023-04-01 | 中原大學 | Device and method of angiography for cerebrovascular obliteration |
| CN114972165B (en) * | 2022-03-24 | 2024-03-15 | 中山大学孙逸仙纪念医院 | Method and device for measuring time average shearing force |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999902A (en) * | 2012-11-13 | 2013-03-27 | 上海交通大学医学院附属瑞金医院 | Optical navigation positioning system based on CT (computed tomography) registration results and navigation method thereby |
| CN109741344A (en) * | 2018-12-28 | 2019-05-10 | 上海联影智能医疗科技有限公司 | Blood vessel segmentation method, apparatus, medical imaging equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097334B (en) * | 2016-06-08 | 2023-09-12 | 北京航空航天大学 | Point cloud registration method based on deep learning |
| CN109300147B (en) * | 2018-09-17 | 2020-10-16 | 北京理工大学 | Method and device for registering two-dimensional center line and three-dimensional center line of blood vessel |
| CN110009669B (en) * | 2019-03-22 | 2021-12-10 | 电子科技大学 | 3D/2D medical image registration method based on deep reinforcement learning |
-
2020
- 2020-05-26 CN CN202010456226.8A patent/CN111612778B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999902A (en) * | 2012-11-13 | 2013-03-27 | 上海交通大学医学院附属瑞金医院 | Optical navigation positioning system based on CT (computed tomography) registration results and navigation method thereby |
| CN109741344A (en) * | 2018-12-28 | 2019-05-10 | 上海联影智能医疗科技有限公司 | Blood vessel segmentation method, apparatus, medical imaging equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| Gaurav Kaila等.Fusion of CTA and XA data using 3D centerline registration for plaque visualization during coronary intervention.《Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling》.2016,全文. * |
| Haofu Liao等.Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation.《Conference on Computer Vision and Pattern Recognition (CVPR)》.2019,第2-4节. * |
| Haofu Liao等.Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation.《Conference on Computer Vision and Pattern Recognition (CVPR)》.2019,第3节. * |
| 李致勋.2D/3D冠状动脉血管分割与配准方法研究.《中国博士学位论文全文数据库 信息科技辑》.2019,(第01期),第二章2.4-2.6节、第五章5.2-5.6节. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111612778A (en) | 2020-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612778B (en) | Preoperative CTA and intraoperative X-ray coronary artery registration method | |
| JP7391846B2 (en) | Computer-aided diagnosis using deep neural networks | |
| US10762637B2 (en) | Vascular segmentation using fully convolutional and recurrent neural networks | |
| Ambrosini et al. | Fully automatic and real-time catheter segmentation in X-ray fluoroscopy | |
| KR102250164B1 (en) | Method and system for automatic segmentation of vessels in medical images using machine learning and image processing algorithm | |
| US9892361B2 (en) | Method and system for cross-domain synthesis of medical images using contextual deep network | |
| US10685438B2 (en) | Automated measurement based on deep learning | |
| US20080058611A1 (en) | Medical image processing apparatus | |
| JP2018139693A (en) | Image classification device, method and program | |
| CN110110808B (en) | Method and device for performing target labeling on image and computer recording medium | |
| CN116012555A (en) | Vascular guide wire tracking method based on Res-Unet and hidden Markov model | |
| Kara et al. | Identification and localization of endotracheal tube on chest radiographs using a cascaded convolutional neural network approach | |
| Tahoces et al. | Deep learning method for aortic root detection | |
| Li et al. | EchoEFNet: multi-task deep learning network for automatic calculation of left ventricular ejection fraction in 2D echocardiography | |
| US11494908B2 (en) | Medical image analysis using navigation processing | |
| Han et al. | Coronary artery stenosis detection via proposal-shifted spatial-temporal transformer in X-ray angiography | |
| CN114255235A (en) | Method and arrangement for automatic localization of organ segments in three-dimensional images | |
| Zhou et al. | Fully automatic dual-guidewire segmentation for coronary bifurcation lesion | |
| CN116109872A (en) | Blood vessel naming method and device, electronic equipment and storage medium | |
| CN113469962B (en) | Feature extraction and image-text fusion method and system for cancer lesion detection | |
| KR102250173B1 (en) | Method and system for automatic segmentation of vessels in medical images using machine learning and image processing algorithm | |
| CN113935889A (en) | Method, system and medium for automatic 2D/3D coronary artery registration | |
| Marie et al. | Segmentation of kidneys deformed by nephroblastoma using case-based reasoning | |
| US20240153094A1 (en) | Systems and methods for annotating tubular structures | |
| Zhang et al. | Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |