CN112991522A - Personalized automatic modeling method, system and equipment for mitral valve - Google Patents

Personalized automatic modeling method, system and equipment for mitral valve Download PDF

Info

Publication number
CN112991522A
CN112991522A CN202110343621.XA CN202110343621A CN112991522A CN 112991522 A CN112991522 A CN 112991522A CN 202110343621 A CN202110343621 A CN 202110343621A CN 112991522 A CN112991522 A CN 112991522A
Authority
CN
China
Prior art keywords
mitral valve
ultrasonic image
dimensional
target
automatic
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.)
Granted
Application number
CN202110343621.XA
Other languages
Chinese (zh)
Other versions
CN112991522B (en
Inventor
谢龙汉
陈锦辉
姚尖平
姚凤娟
赖立炫
何高伟
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.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
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 South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202110343621.XA priority Critical patent/CN112991522B/en
Publication of CN112991522A publication Critical patent/CN112991522A/en
Application granted granted Critical
Publication of CN112991522B publication Critical patent/CN112991522B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
    • 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
    • G06T2207/10132—Ultrasound 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • G06T2207/30048—Heart; Cardiac
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/41—Medical

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an automatic modeling method for an individualized mitral valve, which comprises the following steps: constructing a mitral valve three-dimensional ultrasonic image database; inputting data in the mitral valve three-dimensional ultrasonic image database into a convolutional neural network as a training data set to obtain a trained mitral valve automatic segmentation model; acquiring a three-dimensional ultrasonic image of a target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model, and outputting a target segmentation result; acquiring point cloud data according to the target segmentation result; and performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve, and obtaining a three-dimensional surface model of the mitral valve according to the surface equation of the mitral valve. Corresponding systems and devices are also disclosed. The invention realizes the automation of personalized mitral valve modeling and greatly shortens the modeling time. The curved surface model obtained by automatic modeling can be subjected to three-dimensional zooming and rotating viewing, and can also be used for measuring the spatial position relation between the mitral valve tissue structures.

Description

Personalized automatic modeling method, system and equipment for mitral valve
Technical Field
The invention relates to the technical field of three-dimensional modeling of medical images, in particular to a personalized mitral valve automatic modeling method, system and equipment.
Background
Heart disease has become one of the first diseases endangering human health and life safety, including the common valvular heart disease, and the incidence is rising year by year. The non-invasive requirement and the establishment of a better surgical plan in the process of diagnosing the disease are always difficult problems in the medical field.
In recent years, medical image diagnosis technology has been greatly improved, and research on diagnostic treatment schemes for mitral valve diseases based on medical image data is of great significance. With the continuous promotion of software technology and hardware technology, the application of computer-aided diagnosis technology in the medical field is more and more extensive. By visualizing the three-dimensional model of the human mitral valve, physicians can be helped to obtain more diagnostic information. Therefore, a process of three-dimensional modeling of the personalized mitral valve is indispensable.
The existing mitral valve three-dimensional modeling method mainly marks the characteristic contour of the mitral valve anatomical structure in a plurality of medical images through manual input and constructs a three-dimensional model based on the marked characteristic contour. However, the method needs to manually extract the feature outline, consumes a lot of manpower and time, is easily subjected to error marking caused by visual fatigue in the manual extraction process, and is not beneficial to popularization and application. A mitral valve three-dimensional modeling method proposed by Wangtian Tiantian et al (Wangtian Tiantian, functional simulation mathematical model and algorithm research of human heart mitral valve, D, Shaanxi, Sian Ringji university, 2018:19-23) is to assume the shape of the mitral valve as a semi-elliptical cylindrical shell, give a corresponding parameter equation, fit and solve the parameter equation by utilizing statistical data of local medical structure of the human mitral valve and visualize the fitting result to obtain a curved surface model of the mitral valve. However, the curved surface model of the method is obtained by fitting according to medical statistical data, and cannot reflect the personalized geometric characteristics of different mitral valves.
Disclosure of Invention
The invention aims to solve the problems that manual interaction operation in the existing mitral valve modeling process is time-consuming and labor-consuming and a geometric model cannot embody personalized characteristics, and provides a personalized automatic mitral valve modeling method, a system and equipment.
In order to achieve the object of the present invention, the present invention provides an automatic modeling method for a personalized mitral valve, which is applied to an embedded device integrated with a personalized mitral valve modeling system, and comprises:
constructing a mitral valve three-dimensional ultrasonic image database;
inputting data in the mitral valve three-dimensional ultrasonic image database into a convolutional neural network as a training data set to obtain a trained mitral valve automatic segmentation model;
acquiring a three-dimensional ultrasonic image of a target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model, and outputting a target segmentation result;
acquiring point cloud data according to the target segmentation result;
and performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve, and obtaining a three-dimensional surface model of the mitral valve through the surface equation of the mitral valve.
Preferably, the ultrasound image database contains segmented tag data, which is obtained by dividing the corresponding region of the ultrasound image according to the medical anatomy structure of the mitral valve.
Preferably, the training data set is subjected to data augmentation before being input into the convolutional neural network, and the augmentation comprises random scaling and rotation.
Preferably, the normalization processing is performed before the training data set is input into the convolutional neural network, so as to ensure the consistency of the training data.
Preferably, the convolutional neural network adopts a 3D-UNet convolutional neural network, the 3D-UNet convolutional neural network adopts binary cross entropy as a loss function, Adam is selected as an optimizer, and IoU (iteration over unit) is selected as an evaluation index.
Preferably, the curved surface equation of the mitral valve is as follows:
Figure BDA0003000054450000031
wherein alpha is1，α2，α3Is a shape control parameter, which respectively controls the dimension of the curved surface along the x, y and z axes, epsilon1And ε2Is a square factor and respectively adjusts the curvatures of the curved surface in different directions. x is the number of0，y0，z0Is a global origin coordinate parameter introduced for centering the coordinate system, and the parameter theta is an included angle between the adjustment curved surface and the Z axis;
preferably, the obtaining a three-dimensional curved surface model of the mitral valve through the curved surface equation of the mitral valve specifically includes:
preferably, the curved surface equation of the mitral valve is solved by an optimization method, and an objective function equation in the optimization solution is set as:
Figure BDA0003000054450000032
where i denotes the ith point in the point cloud used to participate in the surface fitting, Fi(xi,yi,zi) Representing the result of each point cloud coordinate substituting into the mitral valve surface equation, alpha1，α2，α3And ε1The parameter values are the same as those of the mitral valve surface equation;
preferably, the convergence criterion in the optimization solution is set as:
Figure BDA0003000054450000041
where N denotes the number of total iterationsNumber, RnAn objective function representing the nth iteration;
preferably, the minimum value of the objective function R is solved to obtain the optimal mitral valve surface fitting parameter (alpha)1，α2，α3，ε1，ε2，θ，x0，y0，z0) And substituting the fitting parameters into the mitral valve curved surface equation and visualizing the fitting result to obtain the mitral valve three-dimensional curved surface model.
In order to achieve the object of the present invention, the present invention further provides a personalized mitral valve automatic modeling system, comprising:
the storage module is used for constructing a mitral valve three-dimensional ultrasonic image database;
the training module is used for inputting the data in the database into a convolutional neural network as a training data set to obtain a trained automatic mitral valve segmentation model;
and the acquisition and segmentation module is used for acquiring a three-dimensional ultrasonic image of the target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model and outputting a target segmentation result.
The conversion module is used for acquiring point cloud data through the target segmentation result;
and the fitting module is used for performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve, and obtaining a three-dimensional surface model of the mitral valve through the surface equation of the mitral valve.
Preferably, the system further comprises a data preprocessing module for training data amplification and normalization processing on the data in the data set.
In order to achieve the object of the present invention, the present invention also provides an embedded device, comprising:
a memory for storing a computer program;
a processor for implementing the automatic modeling method for a mitral valve as described in any one of the above when the computer program is executed.
The invention provides an individualized automatic modeling method for a mitral valve, which comprises the steps of inputting a three-dimensional ultrasonic image of a target mitral valve into a trained automatic mitral valve segmentation model to obtain a target segmentation result, fitting point cloud data obtained through the target segmentation result to obtain a curved surface equation of the mitral valve, and obtaining the three-dimensional curved surface model of the mitral valve through the curved surface equation of the mitral valve. The automation of the personalized mitral valve modeling is realized, the modeling efficiency is improved, a frequent human-computer interaction process is not needed like manual modeling, and the modeling time is greatly shortened. And the problem of wrong marking caused by visual fatigue in manual marking in the prior art can be effectively avoided through automatic modeling, and the accuracy rate is higher.
The curved surface model obtained by automatic modeling can also be subjected to three-dimensional zooming and rotating viewing, and can also be used for measuring the spatial position relation between the mitral valve tissue structures, so that the practicability is higher.
The invention also provides a personalized automatic modeling system and equipment for the mitral valve, and the system and the equipment have the same beneficial effects as the method.
Drawings
Fig. 1 is a schematic flow chart of a method for automatically modeling a personalized mitral valve according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an automatic personalized mitral valve modeling system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, the method for automatically modeling a personalized mitral valve provided by the present invention is applied to an embedded device integrated with a personalized mitral valve modeling system, and includes the following steps:
step 1: and constructing a mitral valve three-dimensional ultrasonic image database.
In one embodiment of the present invention, the ultrasound image database contains segmented tag data, which is obtained by dividing the corresponding region of the ultrasound image according to the medical anatomy of the mitral valve.
And 2, inputting data in the mitral valve three-dimensional ultrasonic image database into a convolutional neural network as a training data set to obtain a trained mitral valve automatic segmentation model.
In one embodiment of the present invention, the training data set is further subjected to a data augmentation process before being input into the network, wherein the augmentation process includes random scaling and rotation.
In one embodiment of the present invention, the training data set needs to be normalized before being input into the network, so as to ensure the consistency of the training data.
In one embodiment of the invention, the convolutional neural network adopts a 3D-UNet convolutional neural network, the 3D-UNet convolutional neural network adopts binary cross entry as a loss function, Adam is selected as an optimizer, and IoU (interference over unit) is selected as an evaluation index.
And 3, acquiring a three-dimensional ultrasonic image of the target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model, and outputting a target segmentation result, wherein the target segmentation result is the division of a target ultrasonic image region corresponding to the medical anatomical structure of the mitral valve.
And 4, acquiring point cloud data according to the target segmentation result.
In one embodiment of the invention, data conversion is carried out on the target segmentation result to obtain STL format data, and point cloud data is obtained according to the STL data.
And 5, performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve.
In one embodiment of the present invention, the surface fitting is to solve the surface equation of the mitral valve by optimally solving a nonlinear minimization problem. The curved surface equation of the mitral valve is as follows:
Figure BDA0003000054450000071
wherein alpha is1，α2，α3Is a shape control parameter, which respectively controls the dimension of the curved surface along the x, y and z axes, epsilon1And ε2Is a square factor and respectively adjusts the curvatures of the curved surface in different directions. x is the number of0，y0，z0Is a global origin coordinate parameter introduced for centering the coordinate system, and the parameter theta is an included angle between the curved surface and the Z axis;
the objective function equation in the optimization solution is set as:
Figure BDA0003000054450000072
where i denotes the ith point in the point cloud used to participate in the surface fitting, Fi(xi,yi,zi) Representing the result of each point cloud coordinate substituting into the mitral valve surface equation, alpha1，α2，α3And ε1The parameter values are the same as those of the mitral valve surface equation;
the convergence discrimination condition in the optimization solution is set as follows:
Figure BDA0003000054450000073
where N denotes the number of total iterations, RnAn objective function representing the nth iteration;
solving the minimum value of the objective function R to obtain the optimal mitral valve surface fitting parameter (alpha)1，α2，α3，ε1，ε2，θ，x0，y0，z0) And substituting the fitting parameters into the mitral valve curved surface equation and visualizing the fitting result to obtain the mitral valve three-dimensional curved surface model.
Referring to fig. 2, the present invention further provides a personalized mitral valve automatic modeling system, including:
the ultrasonic image database comprises segmented label data, and the label data are obtained by dividing the medical anatomical structure of the mitral valve in the corresponding area of the ultrasonic image.
And the training module is used for inputting the data in the database into a convolutional neural network as a training data set to obtain a trained automatic mitral valve segmentation model.
And the acquisition and segmentation module is used for acquiring a three-dimensional ultrasonic image of the target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model and outputting a target segmentation result.
And the conversion module is used for carrying out data conversion on the target segmentation result, acquiring STL format data and acquiring point cloud data according to the STL data.
And the fitting module is used for performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve and obtaining a three-dimensional surface model of the mitral valve according to the surface equation of the mitral valve.
In one embodiment of the present invention, the system further comprises a data preprocessing module, wherein the data preprocessing module is used for performing data amplification and normalization on the data set.
The data preprocessing module comprises:
and the data amplification sub-processing module is used for performing data amplification processing on the data in the training data set. The training data set can be increased through the module, so that the trained model has stronger generalization capability. And
and the normalization processing module is used for performing normalization processing on the data in the data set so as to ensure the consistency of the training data.
In the fitting module, the curved surface model is obtained in the following manner:
the surface fitting is to solve the surface equation of the mitral valve by solving the nonlinear minimization problem through optimization, and the surface equation of the mitral valve is as follows:
Figure BDA0003000054450000091
wherein alpha is1，α2，α3Is a shape control parameter, which respectively controls the dimension of the curved surface along the x, y and z axes, epsilon1And ε2Is a square factor and respectively adjusts the curvatures of the curved surface in different directions. x is the number of0，y0，z0Is a global origin coordinate parameter introduced for centering the coordinate system, and the parameter theta is an included angle between the adjustment curved surface and the Z axis;
the objective function equation in the optimization solution is set as:
Figure BDA0003000054450000092
where i denotes the ith point in the point cloud used to participate in the surface fitting, Fi(xi,yi,zi) Representing the result of each point cloud coordinate substituting into the mitral valve surface equation, alpha1，α2，α3And ε1The parameter values are the same as those of the mitral valve surface equation;
the convergence discrimination condition in the optimization solution is set as follows:
Figure BDA0003000054450000093
where N denotes the number of total iterations, RnAn objective function representing the nth iteration;
solving the minimum value of the objective function R to obtain the optimal mitral valve surface fitting parameter (alpha)1，α2，α3，ε1，ε2，θ，x0，y0，z0) And substituting the fitting parameters into the mitral valve curved surface equation and visualizing the fitting result to obtain the mitral valve three-dimensional curved surface model.
In an embodiment of the present invention, there is also provided an embedded device, including:
a memory for storing a computer program;
a processor for implementing the steps of any one of the above-described methods for personalized automatic modeling of a mitral valve when executing a computer program.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the mitral valve automatic modeling system and the embedded device disclosed by the embodiment, the description is relatively simple because the mitral valve automatic modeling system and the embedded device correspond to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution of the present invention and the inventive concept within the technical scope of the present invention.

Claims (10)

1. A personalized mitral valve automatic modeling method is applied to an embedded device integrated with a personalized mitral valve modeling system, and is characterized by comprising the following steps:
constructing a mitral valve three-dimensional ultrasonic image database;
inputting data in the mitral valve three-dimensional ultrasonic image database into a convolutional neural network as a training data set to obtain a trained mitral valve automatic segmentation model;
acquiring a three-dimensional ultrasonic image of a target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model, and outputting a target segmentation result;
acquiring point cloud data according to the target segmentation result;
and performing surface fitting according to the point cloud data to obtain a surface equation of the mitral valve, and obtaining a three-dimensional surface model of the mitral valve according to the surface equation of the mitral valve.
2. The method of claim 1, wherein the database of ultrasound images comprises segmented label data, the label data being segmented in regions corresponding to ultrasound images according to the medical anatomy of the mitral valve.
3. The method of claim 1, wherein the training data set is subjected to data augmentation before being input into the convolutional neural network.
4. The method of claim 1, wherein the training data set is normalized before being input into the convolutional neural network.
5. The method of claim 1, wherein the convolutional neural network is a 3D-UNet convolutional neural network, the 3D-UNet convolutional neural network uses binary cross entry as a loss function, Adam is selected as an optimizer, and IoU is selected as an evaluation index.
6. The method according to any of claims 1-5, wherein the equations for the curved surface of the mitral valve are:
Figure FDA0003000054440000021
wherein alpha is1，α2，α3Is a shape control parameter, which respectively controls the dimension of the curved surface along the x, y and z axes, epsilon1And ε2Is a square factor, and respectively adjusts the curvatures, x, of the curved surface in different directions0，y0，z0Is a global origin coordinate parameter introduced to center the coordinate system, and the parameter θ is an angle between the adjustment surface and the Z-axis.
7. The method according to claim 6, wherein the obtaining a three-dimensional curved model of the mitral valve by using a curved equation of the mitral valve specifically comprises:
solving the curved surface equation of the mitral valve through an optimization method, and setting an objective function equation as follows:
Figure FDA0003000054440000022
where i denotes the ith point in the point cloud used to participate in the surface fitting, Fi(xi,yi,zi) Representing the result of each point cloud coordinate substituting into the mitral valve surface equation, alpha1，α2，α3And ε1The parameter values are the same as those of the mitral valve surface equation;
the convergence discrimination condition is set to:
Figure FDA0003000054440000023
where N denotes the number of total iterations, RnAn objective function representing the nth iteration;
solving the minimum value of the objective function R to obtain the optimal mitral valve surface fitting parameter (alpha)1，α2，α3，ε1，ε2，θ，x0，y0，z0) And substituting the fitting parameters into the mitral valve curved surface equation and visualizing the fitting result to obtain the mitral valve three-dimensional curved surface model.
8. An automated personalized mitral valve modeling system, configured to implement the method of any of claims 1-comprising:
the storage module is used for constructing a mitral valve three-dimensional ultrasonic image database;
the training module is used for inputting the data in the database into a convolutional neural network as a training data set to obtain a trained automatic mitral valve segmentation model;
the acquisition and segmentation module is used for acquiring a three-dimensional ultrasonic image of a target mitral valve, inputting the target ultrasonic image into the automatic mitral valve segmentation model and outputting a target segmentation result;
the conversion module is used for acquiring point cloud data through the target segmentation result;
and the fitting module is used for carrying out surface fitting according to the point cloud data to obtain a surface equation of the mitral valve, and obtaining a three-dimensional surface model of the mitral valve through the surface equation of the mitral valve.
9. The system of claim 8, further comprising a data preprocessing module for performing data augmentation and normalization on the training data set.
10. An embedded device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for automatic modeling of a mitral valve according to any of claims 1 to 7 when executing said computer program.
CN202110343621.XA 2021-03-30 2021-03-30 Personalized automatic modeling method, system and equipment for mitral valve Active CN112991522B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110343621.XA CN112991522B (en) 2021-03-30 2021-03-30 Personalized automatic modeling method, system and equipment for mitral valve

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110343621.XA CN112991522B (en) 2021-03-30 2021-03-30 Personalized automatic modeling method, system and equipment for mitral valve

Publications (2)

Publication Number Publication Date
CN112991522A true CN112991522A (en) 2021-06-18
CN112991522B CN112991522B (en) 2023-03-24

Family

ID=76338553

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110343621.XA Active CN112991522B (en) 2021-03-30 2021-03-30 Personalized automatic modeling method, system and equipment for mitral valve

Country Status (1)

Country Link
CN (1) CN112991522B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115249236A (en) * 2022-06-10 2022-10-28 拓微摹心数据科技(南京)有限公司 Automatic calculation method for aortic valve leaflet length

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6542249B1 (en) * 1999-07-20 2003-04-01 The University Of Western Ontario Three-dimensional measurement method and apparatus
CN101034480A (en) * 2007-04-05 2007-09-12 上海交通大学 Method for computer-assisted rebuilding heart mitral annulus
CN101127123A (en) * 2007-09-11 2008-02-20 东南大学 Sign point hole filling method based on neural network in tri-D scanning point cloud
US20150265248A1 (en) * 2012-12-03 2015-09-24 Shenzhen Mindray Bio-Medical Electronics Co., Ltd. Ultrasound systems, methods and apparatus for associating detection information of the same
US20190378278A1 (en) * 2018-06-09 2019-12-12 Uih-Rt Us Llc Systems and methods for generating augmented segmented image set
US20200082531A1 (en) * 2018-09-07 2020-03-12 3Mensio Medical Imaging B.V. Method, Device and System for Dynamic Analysis from Sequences of Volumetric Images
WO2020190821A1 (en) * 2019-03-15 2020-09-24 Genentech, Inc. Deep convolutional neural networks for tumor segmentation with positron emission tomography

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6542249B1 (en) * 1999-07-20 2003-04-01 The University Of Western Ontario Three-dimensional measurement method and apparatus
CN101034480A (en) * 2007-04-05 2007-09-12 上海交通大学 Method for computer-assisted rebuilding heart mitral annulus
CN101127123A (en) * 2007-09-11 2008-02-20 东南大学 Sign point hole filling method based on neural network in tri-D scanning point cloud
US20150265248A1 (en) * 2012-12-03 2015-09-24 Shenzhen Mindray Bio-Medical Electronics Co., Ltd. Ultrasound systems, methods and apparatus for associating detection information of the same
US20190378278A1 (en) * 2018-06-09 2019-12-12 Uih-Rt Us Llc Systems and methods for generating augmented segmented image set
US20200082531A1 (en) * 2018-09-07 2020-03-12 3Mensio Medical Imaging B.V. Method, Device and System for Dynamic Analysis from Sequences of Volumetric Images
WO2020190821A1 (en) * 2019-03-15 2020-09-24 Genentech, Inc. Deep convolutional neural networks for tumor segmentation with positron emission tomography

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吴博 等: "人体左心室三维有限元模型构建及流-固耦合动力学分析", 《生物医学工程学杂志》 *
朱锴 等: "利用关键点检测算法的超声图像定点测量", 《哈尔滨工业大学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115249236A (en) * 2022-06-10 2022-10-28 拓微摹心数据科技(南京)有限公司 Automatic calculation method for aortic valve leaflet length
CN115249236B (en) * 2022-06-10 2023-09-15 拓微摹心数据科技(南京)有限公司 Automatic calculation method for aortic valve leaflet length

Also Published As

Publication number Publication date
CN112991522B (en) 2023-03-24

Similar Documents

Publication Publication Date Title
CN112155729B (en) Intelligent automatic planning method and system for surgical puncture path and medical system
CN110234394B (en) Treatment of patients using TTField with electrode positions optimized with deformable templates
CN110738681A (en) automatic pedicle screw operation path planning method based on deep learning network
CN107622492A (en) Lung splits dividing method and system
CN111739000B (en) System and device for improving left ventricle segmentation accuracy of multiple cardiac views
JP2017532092A (en) System and method for segmenting medical images based on anatomical landmark-based features
CN107451609A (en) Lung neoplasm image identification system based on depth convolutional neural networks
CN110910377B (en) Cerebral infarction MRI image identification method based on neural network
CN113096137B (en) Adaptive segmentation method and system for OCT (optical coherence tomography) retinal image field
CN113781640A (en) Three-dimensional face reconstruction model establishing method based on weak supervised learning and application thereof
CN110097557B (en) Medical image automatic segmentation method and system based on 3D-UNet
CN113344864A (en) Ultrasonic thyroid nodule benign and malignant prediction method based on deep learning
CN106780453A (en) A kind of method realized based on depth trust network to brain tumor segmentation
US10373701B2 (en) Methods and apparatuses for creating a statistical average model of an enamel-dentine junction
CN112991522B (en) Personalized automatic modeling method, system and equipment for mitral valve
CN114792326A (en) Surgical navigation point cloud segmentation and registration method based on structured light
Matsopoulos et al. Thoracic non-rigid registration combining self-organizing maps and radial basis functions
CN109919216B (en) Counterlearning method for computer-aided diagnosis of prostate cancer
CN116128942A (en) Registration method and system of three-dimensional multi-module medical image based on deep learning
CN114820730B (en) CT and CBCT registration method based on pseudo CT
JP7378694B2 (en) Lung lobe segmentation method based on digital human technology
CN111951950A (en) Three-dimensional data medical classification system, method and device based on deep learning
CN114419309A (en) High-dimensional feature automatic extraction method based on brain T1-w magnetic resonance image
CN114529553A (en) Automatic dental digital model segmentation algorithm
CN114549396A (en) Spine interactive and automatic segmentation and refinement method based on graph neural network

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