CN115205293B - Bone cement flow prediction method, device, equipment and storage medium - Google Patents

Bone cement flow prediction method, device, equipment and storage medium Download PDF

Info

Publication number
CN115205293B
CN115205293B CN202211120783.8A CN202211120783A CN115205293B CN 115205293 B CN115205293 B CN 115205293B CN 202211120783 A CN202211120783 A CN 202211120783A CN 115205293 B CN115205293 B CN 115205293B
Authority
CN
China
Prior art keywords
bone cement
vertebral body
bone
dimensional structure
flow distribution
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
Application number
CN202211120783.8A
Other languages
Chinese (zh)
Other versions
CN115205293A (en
Inventor
黄冕
齐欢
杨柯笛
吴天驰
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.)
Bone's Biological Technology Shenzhen Co ltd
Original Assignee
Bone's Biological Technology Shenzhen Co ltd
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 Bone's Biological Technology Shenzhen Co ltd filed Critical Bone's Biological Technology Shenzhen Co ltd
Priority to CN202211120783.8A priority Critical patent/CN115205293B/en
Publication of CN115205293A publication Critical patent/CN115205293A/en
Application granted granted Critical
Publication of CN115205293B publication Critical patent/CN115205293B/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
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • 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
    • 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
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G16H20/17—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
    • 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
    • G06T2207/10081—Computed x-ray tomography [CT]
    • 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
    • G06T2207/30008—Bone
    • G06T2207/30012—Spine; Backbone

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Geometry (AREA)
  • Mathematical Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Fluid Mechanics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention relates to the field of artificial intelligence, and discloses a bone cement flow prediction method, a bone cement flow prediction device, bone cement flow prediction equipment and a bone cement flow prediction storage medium, which are used for improving the accuracy and efficiency of bone cement flow prediction. The method comprises the following steps: performing automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebra initial three-dimensional structure, and performing cancellous bone cavity reconstruction on the vertebra initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result; respectively calculating a plurality of bone cement flow distribution forms based on numerical simulation rules of computational fluid mechanics to obtain flow distribution corresponding to each numerical simulation rule; and carrying out variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule to obtain target design variables.

Description

Bone cement flow prediction method, device, equipment and storage medium
Technical Field
The invention relates to the field of artificial intelligence, in particular to a bone cement flow prediction method, a bone cement flow prediction device, bone cement flow prediction equipment and a storage medium.
Background
For predicting the bone cement flow in the bone cement injection process, the currently common method mainly comprises the following steps: the clinician judges according to clinical experience, but only depends on the clinical experience of the clinician, lacks physical theory basis, lacks accurate identification of submicron structures of cavities in the spongy bone of the vertebral body, and lacks understanding of fluid mechanics theory and bone cement material properties.
The existing centrum three-dimensional reconstruction method based on the image editing function of medical image control software is low in efficiency because the centrum three-dimensional structure is segmented and reconstructed through manual operation; at present, a bone cement flow numerical simulation method based on computational fluid mechanics is mainly used for simulating a dispersion process when bone cement seeps out of a bone filling mesh bag in mesh bag forming operation, lacks of modeling for cancellous bone cavities of an osteoporosis vertebral body, and does not consider the influence of vertebral body bone mass distribution on bone cement flow. Namely, the existing scheme has low accuracy and efficiency.
Disclosure of Invention
The invention provides a bone cement flow prediction method, a bone cement flow prediction device, bone cement flow prediction equipment and a bone cement flow prediction storage medium, which are used for improving the accuracy and efficiency of bone cement flow prediction.
The invention provides a bone cement flow prediction method in a first aspect, which comprises the following steps: acquiring vertebral body image data of a target user, and acquiring vertebral body bone mass distribution parameters of the target user; performing automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebral body initial three-dimensional structure, and performing cancellous bone cavity reconstruction on the vertebral body initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; obtaining bone cement parameters corresponding to bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into a vertebral body; respectively calculating a plurality of bone cement flow distribution forms based on numerical simulation rules of computational fluid mechanics to obtain flow distribution corresponding to each numerical simulation rule; performing variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
Optionally, in a first implementation manner of the first aspect of the present invention, the performing automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain an initial three-dimensional structure of a vertebral body, and performing cancellous bone cavity reconstruction on the initial three-dimensional structure of the vertebral body according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure includes: carrying out automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images; inputting the plurality of vertebral body images into a preset three-dimensional reconstruction model for carrying out vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of the vertebra; and carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure.
Optionally, in a second implementation manner of the first aspect of the present invention, the obtaining a bone cement parameter corresponding to a bone cement, and performing a flow distribution calculation on the bone cement according to the bone cement parameter and the target three-dimensional structure to obtain a flow distribution calculation result, where the flow distribution calculation result is used to indicate a flow distribution of the bone cement injected into a vertebral body, includes: acquiring bone cement parameters corresponding to bone cement, wherein the bone cement parameters comprise: bone cement material properties and bone cement injection parameters; and calculating the flow distribution of the bone cement according to the bone cement parameters and the target three-dimensional structure through computational fluid mechanics to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body.
Optionally, in a third implementation manner of the first aspect of the present invention, the calculating a plurality of bone cement flow distribution morphologies respectively based on the numerical simulation rule of computational fluid dynamics to obtain a flow distribution corresponding to each numerical simulation rule includes: generating a plurality of numerical simulation rules based on a plurality of preset injection modes; and respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the variable optimization is performed on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule, so as to obtain target design variables, where the target design variables include: injection amount, injection rate and injection location of bone cement, including: comparing the flow distribution calculation result with the flow distribution corresponding to each numerical simulation rule to obtain a comparison result; performing variable optimization on the design variables of the bone cement according to the comparison result to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the acquiring vertebral body image data of a target user and acquiring vertebral body bone mass distribution parameters of the target user includes: carrying out CT image acquisition on a target user to obtain vertebral body image data of the target user; and calling a preset bone quality detection model to carry out vertebral body bone quality detection on the target user to obtain vertebral body bone quality distribution parameters of the target user.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the bone cement flow prediction method further includes: searching a osteopenia area according to the vertebral body bone mass distribution parameters; and calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region.
A second aspect of the present invention provides a bone cement flow prediction apparatus comprising: the acquisition module is used for acquiring vertebral body image data of a target user and acquiring vertebral body bone mass distribution parameters of the target user; the three-dimensional reconstruction module is used for carrying out automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebral body initial three-dimensional structure, and carrying out cancellous bone cavity reconstruction on the vertebral body initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; the processing module is used for acquiring bone cement parameters corresponding to bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into a vertebral body; the calculation module is used for calculating the flow distribution forms of the bone cement respectively based on numerical simulation rules of computational fluid mechanics to obtain the flow distribution corresponding to each numerical simulation rule; an optimization module, configured to perform variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule, so as to obtain target design variables, where the target design variables include: injection amount of bone cement, injection rate, and injection location.
Optionally, in a first implementation manner of the second aspect of the present invention, the three-dimensional reconstruction module is specifically configured to: carrying out automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images; inputting the plurality of vertebral body images into a preset three-dimensional reconstruction model for carrying out vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of the vertebra; and carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure.
Optionally, in a second implementation manner of the second aspect of the present invention, the processing module is specifically configured to: acquiring bone cement parameters corresponding to bone cement, wherein the bone cement parameters comprise: bone cement material properties and bone cement injection parameters; and calculating the flow distribution of the bone cement according to the bone cement parameters and the target three-dimensional structure through computational fluid mechanics to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body.
Optionally, in a third implementation manner of the second aspect of the present invention, the calculation module is specifically configured to: generating a plurality of numerical simulation rules based on a plurality of preset injection modes; and respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the optimization module is specifically configured to: comparing the flow distribution calculation result with the flow distribution corresponding to each numerical simulation rule to obtain a comparison result; and performing variable optimization on the design variables of the bone cement according to the comparison result to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: carrying out CT image acquisition on a target user to obtain vertebral body image data of the target user; and calling a preset bone quality detection model to carry out vertebral body bone quality detection on the target user to obtain vertebral body bone quality distribution parameters of the target user.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the bone cement flow prediction apparatus further includes: the construction module is used for searching the osteopenia area according to the vertebral body bone mass distribution parameters; and calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region.
A third aspect of the present invention provides a bone cement flow prediction apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the bone cement flow prediction device to perform the bone cement flow prediction method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which when executed on a computer, cause the computer to execute the bone cement flow prediction method described above.
According to the technical scheme provided by the invention, the three-dimensional structure of the vertebral body of the target user is automatically segmented and reconstructed from the vertebral body image data of the target user; reconstructing a three-dimensional structure of the vertebral body and the cancellous bone cavity thereof based on the vertebral body bone quality detection result; and finally, simulating the flow distribution in the vertebral body after bone cement injection by using a numerical value. The method solves the problem that the efficiency of manually segmenting and reconstructing the vertebral body in the existing scheme is low, and solves the problems that when the flow of bone cement in the vertebral body is predicted, only the experience of a clinician is relied on, the theoretical basis of hydromechanics and the cognition of the properties of bone cement materials are lacked, the modeling of cancellous bone cavities in the osteoporosis vertebral body is lacked, and the influence of the mass distribution of the vertebral body on the flow of the bone cement is not considered. The flow characteristics of the bone cement in the vertebral body are analyzed numerically by establishing a simulation model of the bone cement flowing in the vertebral body after injection, flow field data are processed according to a fluid volume model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flow distribution of the bone cement is obtained. The bone mass and structural influence factors of the bone mass distribution are disclosed, influence rules of parameters related to vertebral body bone mass distribution, bone cement material attributes and injection modes are considered comprehensively, a unified bone cement flow prediction relation model is established, and therefore the accuracy of bone cement flow prediction is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for predicting bone cement flow in an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of the bone cement flow prediction method in the embodiment of the present invention;
FIG. 3 is a schematic view of an embodiment of a bone cement flow prediction device in an embodiment of the present invention;
FIG. 4 is a schematic view of another embodiment of a bone cement flow prediction device in an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a bone cement flow prediction apparatus in an embodiment of the present invention;
FIG. 6 is a schematic view of a bone cement distribution tube according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating a vertebral body segmentation result according to an embodiment of the present invention;
FIG. 8 is a first schematic view of a three-dimensional structure of a vertebral body according to an embodiment of the present invention;
FIG. 9 is a second schematic view of a three-dimensional structure of a vertebral body according to an embodiment of the present invention;
FIG. 10 is a schematic view of vertebral bone mass distribution in an embodiment of the present invention;
FIG. 11 is a schematic illustration of the flow distribution in a vertebral body from a first set of experimental data according to an embodiment of the present invention;
FIG. 12 is a schematic illustration of the flow distribution in a vertebral body according to a second set of experimental data in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a bone cement flow prediction method, a bone cement flow prediction device, bone cement flow prediction equipment and a storage medium, which are used for improving the accuracy and efficiency of bone cement flow prediction. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a detailed flow chart of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for predicting bone cement flow in an embodiment of the present invention includes:
101. acquiring vertebral body image data of a target user, and acquiring vertebral body bone mass distribution parameters of the target user;
it is to be understood that the implementation subject of the present invention may be a bone cement flow prediction device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
Specifically, the server obtains vertebral body image data of a target user, detects relevant parameters of vertebral body bone mass distribution of the target user according to a preset bone mass detection model, and further obtains vertebral body bone mass parameters corresponding to the target user, and it should be noted that in the embodiment of the present invention, the server subsequently performs automatic segmentation and reconstruction according to the vertebral body bone mass distribution parameters, and determines a corresponding three-dimensional structure, so as to improve accuracy of bone cement flow prediction.
102. Performing automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebra initial three-dimensional structure, and performing cancellous bone cavity reconstruction on the vertebra initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure;
specifically, the server segments the image data of the vertebral body based on the bone mass distribution parameters of the vertebral body and reconstructs a three-dimensional structure of the vertebral body and cancellous bone cavities thereof by adopting a deep learning and three-dimensional reconstruction algorithm to form a drainage basin in the vertebral body after bone cement injection, fig. 7 is a schematic diagram of a segmentation result of the vertebral body in the embodiment of the present invention, and it should be noted that the segmentation and reconstruction of the vertebral body and cancellous bone cavities thereof are performed by using a deep learning and three-dimensional reconstruction technique, wherein the three-dimensional structure of the cancellous bone cavities is formed according to a three-dimensional communication domain formed by a bone reduction region of the vertebral body.
103. Acquiring bone cement parameters corresponding to bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and a target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into a vertebral body;
the method comprises the steps that a server obtains related parameters of bone cement material attributes and injection modes, a numerical simulation model based on computational fluid mechanics is built, transient flow distribution of the bone cement in a vertebral body after injection is numerically simulated based on the parameters by adopting a computational fluid mechanics method, the flow distribution forms of the bone cement in the vertebral body under different numerical simulation conditions are calculated and obtained, and comparison is carried out to optimize design variables, the optimized design variables serve as guidance of an injection mode implemented in an actual clinical operation, wherein the design variables comprise injection amount, injection rate and injection position of the bone cement, and an objective function of optimization design is flow distribution of the bone cement.
104. Respectively calculating a plurality of bone cement flow distribution forms based on numerical simulation rules of computational fluid mechanics to obtain flow distribution corresponding to each numerical simulation rule;
it should be noted that the simulation of the flow distribution in the vertebral body after the bone cement injection is performed by numerical simulation software, the material property of the bone cement is non-newtonian fluid, the dynamic viscosity exponentially changes with the shear rate, the invention does not consider the relationship of the dynamic viscosity of the bone cement with the change of the temperature of the bone cement and the mixing time of the bone cement powder and the liquid for the moment, wherein the injection mode of the bone cement is as follows: unilateral pedicle injection with the injection rate of 0.01m/s and uniform injection. The internal diameter of the bone cement dispenser is 2.8mm.
105. Performing variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
It is noted that the viscosity of the bone cement is increased along with the time of the treatment process, and the bone cement belongs to a rarefied stage within 0-1 min after being prepared; the cement paste belongs to a viscous stage within 1-5 min, and bone cement can be injected in the viscous stage; 5-7 min is in the hardening stage, and 7-12 min is in the polymerization heat generation stage. In this embodiment, the change of the dynamic viscosity of the bone cement with time is not considered for the moment, when the dynamic viscosity of the bone cement is calculated according to a dynamic viscosity formula of the bone cement, the moment is fixed to be powder and liquid are mixed and then the mixture is kept still for 2min, the flow distribution of the bone cement after injection predicted in different injection modes is obtained and compared to optimize the design variables, the optimized design variables are used as references of the injection mode of the actual clinical operation implementation, wherein the design variables include the injection amount, the injection rate and the injection position of the bone cement, and the target function of the optimized design is the flow distribution of the bone cement.
In the embodiment of the invention, the three-dimensional structure of the vertebral body of the target user is automatically segmented and reconstructed from the image data of the vertebral body of the target user; reconstructing a three-dimensional structure of the vertebral body and the cancellous bone cavity thereof based on the vertebral body bone quality detection result; and finally, simulating the flow distribution in the vertebral body after bone cement injection by using a numerical value. The method solves the problem that the efficiency of manually segmenting and reconstructing the vertebral body in the existing scheme is low, and solves the problems that when the flow of bone cement in the vertebral body is predicted, only the experience of a clinician is relied on, the theoretical basis of hydromechanics and the cognition of the properties of bone cement materials are lacked, the modeling of cancellous bone cavities in the osteoporosis vertebral body is lacked, and the influence of the mass distribution of the vertebral body on the flow of the bone cement is not considered. The flow characteristics of the bone cement in the vertebral body are analyzed numerically by establishing a simulation model of the bone cement flowing in the vertebral body after injection, flow field data are processed according to a fluid volume model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flow distribution of the bone cement is obtained. Structural influence factors of bone mass and bone cement material distribution are disclosed, influence rules of vertebral body bone mass distribution, bone cement material attributes and relevant injection mode parameters are considered comprehensively, a unified bone cement flow prediction relation model is established, and therefore accuracy of bone cement flow prediction is improved.
Referring to fig. 2, another embodiment of the method for predicting bone cement flow according to the present invention includes:
201. acquiring vertebral body image data of a target user, and acquiring vertebral body bone mass distribution parameters of the target user;
specifically, CT image acquisition is carried out on a target user to obtain vertebral body image data of the target user; and calling a preset bone quality detection model to carry out vertebral body bone quality detection on the target user to obtain vertebral body bone quality distribution parameters of the target user.
It should be noted that the target user raw CT data is volume data with a size of 512 × 512 × 483, in which the actual physical size of each voxel is 0.782 × 0.782 × 0.799mm 3 The value of each voxel representing the voxel spaceAnd HU value, the detection result of the bone mass of the vertebral body of the target user is volume data with the same size as the segmentation result of the vertebral body, wherein the value of each voxel represents the bone density (BMD) value of the voxel space, and finally, the bone mass distribution parameter of the vertebral body of the target user is obtained.
202. Carrying out automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images;
203. inputting a plurality of vertebral body images into a preset three-dimensional reconstruction model to carry out vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of a vertebra;
204. carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure;
specifically, the server obtains cone image data, and inputs the cone image data into a preset image segmentation network for automatic image segmentation processing to obtain a target segmentation result of the cone image data, wherein the image segmentation network is obtained based on training of a body loss and an edge loss of a training sample image, the body loss is a loss between a segmentation labeling result and a segmentation prediction result of the training sample image for a body region of a target object, the edge loss is a loss between a segmentation labeling result and a segmentation prediction result of the training sample image for an edge region of the target object, a cone image for the target object is segmented from the cone image data according to the target segmentation result, and then the server inputs a plurality of cone images into a preset three-dimensional reconstruction model for cone three-dimensional reconstruction to obtain an initial three-dimensional structure of a vertebra, fig. 8 is a first schematic diagram of the cone three-dimensional structure in the embodiment of the present invention, and fig. 9 is a second schematic diagram of the cone three-dimensional structure in the embodiment of the present invention; and carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure.
Optionally, searching a osteopenia region according to the vertebral body bone mass distribution parameters; and calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region.
The method comprises the steps of automatically segmenting a vertebral body from CT of a target user, reconstructing a three-dimensional structure of the vertebral body, constructing a three-dimensional structure of a cancellous bone cavity in the vertebral body according to a bone reduction region of the vertebral body based on a bone mass three-dimensional distribution detection result of the vertebral body, predicting flow distribution of bone cement in the vertebral body after injection by using a numerical simulation method based on a computational fluid mechanics technology, and providing guidance for selecting injection dosage, injection sites and the like of the bone cement in an actual clinical operation.
205. Obtaining bone cement parameters corresponding to the bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and a target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body;
specifically, bone cement parameters corresponding to bone cement are obtained, wherein the bone cement parameters include: bone cement material properties and bone cement injection parameters; and calculating the flow distribution of the bone cement by calculating the hydrodynamics according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body.
Wherein, the simulation of the flow distribution in the vertebral body after the bone cement injection is carried out by numerical simulation software. The material attribute of the bone cement is non-Newtonian fluid, the dynamic viscosity of the bone cement exponentially changes along with the shear rate, and the invention does not consider the change relation of the dynamic viscosity of the bone cement along with the temperature of the bone cement and the mixing time of the bone cement powder and the liquid. The injection mode of the bone cement is as follows: unilateral pedicle injection with the injection rate of 0.01m/s and uniform injection. The inner diameter of the bone cement distributor is 2.8mm, according to machine vision, computational fluid mechanics and biomedical materials science, a simulation model of the bone cement flowing in a vertebral body after injection is established, the flowing characteristics of the bone cement in the vertebral body are analyzed numerically, flow field data are processed according to a fluid Volume (VOF) model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flowing distribution of the bone cement is obtained. And (3) analyzing the influence of the individualized vertebral body bone mass distribution of different target users on the flow distribution in the vertebral body after bone cement injection.
Optionally, the server may also scan the vertebral body of the target user through CT to obtain CT data. The target user vertebral body is automatically segmented using a deep learning model. And measuring the bone mass distribution of the divided vertebral body of the target user by using the bone mass detection model. And constructing a target user vertebral body and a cancellous bone cavity structure thereof by utilizing a three-dimensional reconstruction algorithm according to the osteopenia region in the bone quality measurement result. And selecting the type of the bone cement to obtain the dynamic viscosity of the bone cement corresponding to the type of the bone cement and the related material properties of the bone cement. Two groups of calculation examples are set, dynamic viscosity parameters of a Simplex P type bone cement material are selected, a bone cement injection mode is set to be unilateral pedicle injection, the speed is 0.01m/s, and the inner diameter of a bone cement injector is 2.8mm. The two groups of cases were as follows: case 1: women, age 66, mean BMD 63.6 mg/cc, diagnosis of vertebral osteoporosis (no fracture), bone cement injection 2.5 mL, case 2: female, age 68, mean BMD 69.6 mg/cc, diagnosis of vertebral compression fracture, bone cement injection 1.3 mL. And (3) introducing the three-dimensional structure of the vertebral body and the cancellous bone cavity thereof into the numerical simulation software through numerical simulation software based on computational fluid mechanics, and calculating the transient volume fraction of the bone cement by using the numerical simulation of the VOF model according to the selected properties of the bone cement material and the set injection mode to obtain the flow distribution of the bone cement in the vertebral body after injection. FIG. 11 is a schematic illustration of the flow distribution within a first set of experimental data vertebrae according to an embodiment of the present invention, as shown in FIGS. 11 and 12; FIG. 12 is a graphical representation of the flow distribution within the vertebral body of the second set of experimental data in an example of the invention.
206. Respectively calculating a plurality of bone cement flow distribution forms based on numerical simulation rules of computational fluid mechanics to obtain flow distribution corresponding to each numerical simulation rule;
specifically, a plurality of numerical simulation rules are generated based on a plurality of preset injection modes; and respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule.
The method comprises the steps of calculating the flow and the distribution of bone cement in a vertebral body after injection by computational fluid mechanics based on a numerical simulation model and bone cement parameters, simulating the flow process of the bone cement in the vertebral body and cancellous bone by numerical values, and predicting the flow distribution of the bone cement. Wherein, the interface of two phases of bone cement and air in the vertebral body is defined as the surface formed by grid points with the volume fraction of the bone cement of 0.5. In step 2, the flow process in the vertebral body after the bone cement injection is described by adopting computational fluid mechanics, and the flow distribution of the bone cement is simulated and calculated. The process specifically comprises the following steps: simulating the effect of a spongy bone region of a vertebral body on the flow of bone cement by using a VOF model, setting a three-dimensional structure of a reconstructed spongy bone cavity communication domain as a fluid domain, giving a continuity equation, a momentum conservation equation, an energy equation and the like of the fluid domain, further solving the equations in a three-dimensional space by using a numerical solution method, calculating numerical results of physical quantities such as speed, pressure, volume fraction and the like of the bone cement at each grid point, and finally obtaining flow distribution corresponding to each numerical simulation rule.
207. Performing variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
Specifically, the flow distribution calculation result is compared with the flow distribution corresponding to each numerical simulation rule to obtain a comparison result; and carrying out variable optimization on the design variables of the bone cement according to the comparison result to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
The server obtains flow distribution after bone cement injection predicted under different injection modes and compares the flow distribution to optimize design variables, and the optimized design variables are used as references of actual clinical operation implementation injection modes; wherein the design variables comprise the injection amount, the injection rate and the injection position of the bone cement, and the objective function of the optimal design is the flow distribution of the bone cement. Specifically, medical CT equipment is used for scanning a vertebral body of a target user, and a deep learning model is used for automatically segmenting the vertebral body of the target user according to a CT image obtained after scanning; and finally, simulating the flow distribution in the vertebral body after bone cement injection according to the selected bone cement material property and the set injection mode and based on computational fluid mechanics by numerical values.
In the embodiment of the invention, the three-dimensional structure of the vertebral body of the target user is automatically segmented and reconstructed from the vertebral body image data of the target user; reconstructing a three-dimensional structure of the vertebral body and the cancellous bone cavity thereof based on the vertebral body bone quality detection result; and finally, simulating the flow distribution in the vertebral body after bone cement injection by using a numerical value. The method solves the problem that the efficiency of manually segmenting and reconstructing the vertebral body in the existing scheme is low, and solves the problems that when the flow of bone cement in the vertebral body is predicted, only the experience of a clinician is relied on, the theoretical basis of hydromechanics and the cognition of the properties of bone cement materials are lacked, the modeling of cancellous bone cavities in the osteoporosis vertebral body is lacked, and the influence of the mass distribution of the vertebral body on the flow of the bone cement is not considered. The flow characteristics of the bone cement in the vertebral body are analyzed numerically by establishing a simulation model of the bone cement flowing in the vertebral body after injection, flow field data are processed according to a fluid volume model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flow distribution of the bone cement is obtained. Structural influence factors of bone mass and bone cement material distribution are disclosed, influence rules of vertebral body bone mass distribution, bone cement material attributes and relevant injection mode parameters are considered comprehensively, a unified bone cement flow prediction relation model is established, and therefore accuracy of bone cement flow prediction is improved.
With reference to fig. 3, the method for predicting bone cement flow in an embodiment of the present invention is described above, and a bone cement flow prediction apparatus in an embodiment of the present invention is described below, where an embodiment of the bone cement flow prediction apparatus in an embodiment of the present invention includes:
an obtaining module 301, configured to obtain vertebral body image data of a target user, and obtain a vertebral body bone mass distribution parameter of the target user;
the three-dimensional reconstruction module 302 is configured to perform automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain an initial three-dimensional structure of a vertebral bone, and perform cancellous bone cavity reconstruction on the initial three-dimensional structure of the vertebral bone according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure;
the processing module 303 is configured to obtain bone cement parameters corresponding to bone cement, and perform flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, where the flow distribution calculation result is used to indicate a flow distribution of the bone cement injected into a vertebral body;
the calculation module 304 is configured to calculate a plurality of bone cement flow distribution forms based on a numerical simulation rule of computational fluid dynamics, so as to obtain a flow distribution corresponding to each numerical simulation rule;
an optimizing module 305, configured to perform variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule, so as to obtain target design variables, where the target design variables include: injection amount of bone cement, injection rate, and injection location.
In the embodiment of the invention, the three-dimensional structure of the vertebral body of the target user is automatically segmented and reconstructed from the image data of the vertebral body of the target user; reconstructing a three-dimensional structure of the vertebral body and a cancellous bone cavity thereof based on a vertebral body bone quality detection result; and finally, simulating the flow distribution in the vertebral body after bone cement injection by using a numerical value. The method solves the problem that the efficiency of manually segmenting and reconstructing the vertebral body in the existing scheme is low, and solves the problems that when the flow of bone cement in the vertebral body is predicted, only the experience of a clinician is relied on, the theoretical basis of hydromechanics and the cognition of the properties of bone cement materials are lacked, the modeling of cancellous bone cavities in the osteoporosis vertebral body is lacked, and the influence of the mass distribution of the vertebral body on the flow of the bone cement is not considered. The flow characteristics of the bone cement in the vertebral body are analyzed numerically by establishing a simulation model of the bone cement flowing in the vertebral body after injection, flow field data are processed according to a fluid volume model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flow distribution of the bone cement is obtained. Structural influence factors of bone mass and bone cement material distribution are disclosed, influence rules of vertebral body bone mass distribution, bone cement material attributes and relevant injection mode parameters are considered comprehensively, a unified bone cement flow prediction relation model is established, and therefore accuracy of bone cement flow prediction is improved.
Referring to fig. 4, another embodiment of the bone cement flow prediction apparatus according to the present invention includes:
an obtaining module 301, configured to obtain vertebral body image data of a target user, and obtain a vertebral body bone mass distribution parameter of the target user;
the three-dimensional reconstruction module 302 is configured to perform automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain an initial three-dimensional structure of a vertebral bone, and perform cancellous bone cavity reconstruction on the initial three-dimensional structure of the vertebral bone according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure;
the processing module 303 is configured to obtain bone cement parameters corresponding to bone cement, and perform flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, where the flow distribution calculation result is used to indicate a flow distribution of the bone cement injected into a vertebral body;
the calculation module 304 is configured to calculate a plurality of bone cement flow distribution forms based on a numerical simulation rule of computational fluid dynamics, so as to obtain a flow distribution corresponding to each numerical simulation rule;
an optimizing module 305, configured to perform variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule, so as to obtain target design variables, where the target design variables include: injection amount of bone cement, injection rate, and injection location.
Optionally, the three-dimensional reconstruction module 302 is specifically configured to: performing automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images; inputting the plurality of vertebral body images into a preset three-dimensional reconstruction model for carrying out vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of the vertebra; and carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure.
Optionally, the processing module 303 is specifically configured to: obtaining bone cement parameters corresponding to bone cement, wherein the bone cement parameters comprise: bone cement material properties and bone cement injection parameters; and calculating the flow distribution of the bone cement according to the bone cement parameters and the target three-dimensional structure through computational fluid dynamics to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body.
Optionally, the calculating module 304 is specifically configured to: generating a plurality of numerical simulation rules based on a plurality of preset injection modes; and respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule.
Optionally, the optimization module 305 is specifically configured to: comparing the flow distribution calculation result with the flow distribution corresponding to each numerical simulation rule to obtain a comparison result; performing variable optimization on the design variables of the bone cement according to the comparison result to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
Optionally, the obtaining module 301 is specifically configured to: carrying out CT image acquisition on a target user to obtain vertebral body image data of the target user; and calling a preset bone quality detection model to carry out vertebral body bone quality detection on the target user to obtain vertebral body bone quality distribution parameters of the target user.
Optionally, the bone cement flow prediction apparatus further comprises:
a construction module 306 for searching for osteopenic regions according to the vertebral body bone mass distribution parameters; and calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region.
In the embodiment of the invention, the three-dimensional structure of the vertebral body of the target user is automatically segmented and reconstructed from the vertebral body image data of the target user; reconstructing a three-dimensional structure of the vertebral body and the cancellous bone cavity thereof based on the vertebral body bone quality detection result; and finally, simulating the flow distribution in the vertebral body after bone cement injection by using the numerical value. The problem that the efficiency of manually segmenting and reconstructing the vertebral body in the existing scheme is low is solved, and the problems that when the flowing of bone cement in the vertebral body is predicted, only the experience of a clinician is relied on, the theoretical basis of hydromechanics and the cognition of the properties of bone cement materials are lacked, the modeling of cancellous bone cavities in the osteoporosis vertebral body is lacked, and the influence of the bone mass distribution of the vertebral body on the flowing of the bone cement is not considered are solved. The flow characteristics of the bone cement in the vertebral body are analyzed numerically by establishing a simulation model of the bone cement flowing in the vertebral body after injection, flow field data are processed according to a fluid volume model, the numerical value of the volume fraction of the bone cement in the vertebral body is calculated, and then the flow distribution of the bone cement is obtained. Structural influence factors of bone mass and bone cement material distribution are disclosed, influence rules of vertebral body bone mass distribution, bone cement material attributes and relevant injection mode parameters are considered comprehensively, a unified bone cement flow prediction relation model is established, and therefore accuracy of bone cement flow prediction is improved.
Fig. 3 and 4 above describe the bone cement flow prediction apparatus in the embodiment of the present invention in detail from the perspective of a modular functional entity, and the bone cement flow prediction apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a bone cement flow prediction apparatus 500 according to an embodiment of the present invention, which may have relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the bone cement flow prediction apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the bone cement flow prediction apparatus 500.
The bone cement flow prediction device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows service, mac OS X, unix, linux, freeBSD, and the like. It will be understood by those skilled in the art that the bone cement flow prediction device configuration shown in fig. 5 does not constitute a limitation of the bone cement flow prediction device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The present invention also provides a bone cement flow prediction apparatus, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the bone cement flow prediction method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-transitory computer readable storage medium, which may also be a volatile computer readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the bone cement flow prediction method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (7)

1. A bone cement flow prediction method, characterized in that the bone cement flow prediction method comprises:
acquiring vertebral body image data of a target user, and acquiring vertebral body bone mass distribution parameters of the target user;
performing automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebra initial three-dimensional structure, and performing cancellous bone cavity reconstruction on the vertebra initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; wherein, the automatic image segmentation and three-dimensional reconstruction are carried out on the vertebral body image data to obtain a vertebra initial three-dimensional structure, and the spongy bone cavity reconstruction is carried out on the vertebra initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure, and the method comprises the following steps: performing automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images; inputting the plurality of vertebral body images into a preset three-dimensional reconstruction model for vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of the vertebra; carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; specifically, the server acquires cone image data, inputs the cone image data into a preset image segmentation network for automatic image segmentation processing, and obtains a target segmentation result of the cone image data, wherein the image segmentation network is obtained based on body loss and edge loss training of a training sample image, the body loss is loss between a segmentation labeling result and a segmentation prediction result of the training sample image for a body region of a target object, the edge loss is loss between a segmentation labeling result and a segmentation prediction result of the training sample image for an edge region of the target object, a cone image for the target object is segmented from the cone image data according to the target segmentation result, and the server inputs a plurality of cone images into a preset three-dimensional reconstruction model for cone three-dimensional reconstruction, so as to obtain an initial three-dimensional structure of a vertebra; carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; searching a osteopenia area according to the vertebral body bone mass distribution parameters; calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region; automatically segmenting a vertebral body from CT of a target user and reconstructing a three-dimensional structure of the vertebral body, constructing a three-dimensional structure of a cancellous bone cavity in the vertebral body according to a bone reduction region of the vertebral body based on a bone mass three-dimensional distribution detection result of the vertebral body, and finally predicting the flow distribution of bone cement in the vertebral body after injection by using a numerical simulation method based on a computational fluid mechanics technology;
acquiring bone cement parameters corresponding to bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into a vertebral body;
respectively calculating a plurality of bone cement flow distribution forms based on numerical simulation rules of computational fluid mechanics to obtain flow distribution corresponding to each numerical simulation rule; wherein, the numerical simulation rule based on computational fluid dynamics respectively calculates a plurality of bone cement flow distribution forms to obtain the flow distribution corresponding to each numerical simulation rule, including: generating a plurality of numerical simulation rules based on a plurality of preset injection modes; respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule; specifically, based on numerical simulation model and bone cement parameters, computational fluid dynamics is adopted to calculate the flow and distribution of bone cement in the vertebral body after injection, numerical simulation shows the flow process of bone cement in the vertebral body and cancellous bone thereof, and the flow distribution of bone cement is predicted, wherein, the two-phase interface of bone cement in the vertebral body and air in the vertebral body is defined as the surface formed by grid points with the volume fraction of the bone cement of 0.5, the flow process in the vertebral body after injection of the bone cement is described by the computational fluid dynamics, and the flow distribution of the bone cement is simulated and calculated, which comprises: simulating the effect of a centrum cancellous bone area on bone cement flow by using a VOF model, setting a reconstructed three-dimensional structure of a cancellous bone cavity communication domain as a fluid domain, solving the above equation in a three-dimensional space by using a numerical solving method through a continuity equation, a momentum conservation equation and an energy equation of the fluid domain, calculating numerical results of the speed, the pressure and the volume fraction of the bone cement at each grid point, and finally obtaining flow distribution corresponding to each numerical simulation rule;
performing variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
2. The bone cement flow prediction method according to claim 1, wherein the obtaining of bone cement parameters corresponding to bone cement and performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating a flow distribution of the bone cement injected into a vertebral body, and comprises:
obtaining bone cement parameters corresponding to bone cement, wherein the bone cement parameters comprise: bone cement material properties and bone cement injection parameters;
and calculating the flow distribution of the bone cement according to the bone cement parameters and the target three-dimensional structure through computational fluid mechanics to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into the vertebral body.
3. The method for predicting bone cement flow according to claim 1, wherein the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule are used to perform variable optimization on the design variables of the bone cement to obtain target design variables, wherein the target design variables include: the injection amount, injection rate and injection position of the bone cement include:
comparing the flow distribution calculation result with the flow distribution corresponding to each numerical simulation rule to obtain a comparison result;
and performing variable optimization on the design variables of the bone cement according to the comparison result to obtain target design variables, wherein the target design variables comprise: injection amount of bone cement, injection rate, and injection location.
4. The method for predicting bone cement flow according to claim 1, wherein the acquiring vertebral body image data of the target user and acquiring vertebral body bone mass distribution parameters of the target user comprises:
carrying out CT image acquisition on a target user to obtain vertebral body image data of the target user;
and calling a preset bone quality detection model to carry out vertebral body bone quality detection on the target user to obtain vertebral body bone quality distribution parameters of the target user.
5. A bone cement flow prediction apparatus, comprising:
the acquisition module is used for acquiring vertebral body image data of a target user and acquiring vertebral body bone mass distribution parameters of the target user;
the three-dimensional reconstruction module is used for carrying out automatic image segmentation and three-dimensional reconstruction on the vertebral body image data to obtain a vertebral body initial three-dimensional structure, and carrying out cancellous bone cavity reconstruction on the vertebral body initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; wherein, the automatic image segmentation and three-dimensional reconstruction are carried out on the vertebral body image data to obtain a vertebra initial three-dimensional structure, and the spongy bone cavity reconstruction is carried out on the vertebra initial three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure, and the method comprises the following steps: carrying out automatic image segmentation on the vertebral body image data to obtain a plurality of vertebral body images; inputting the plurality of vertebral body images into a preset three-dimensional reconstruction model for carrying out vertebral body three-dimensional reconstruction to obtain an initial three-dimensional structure of the vertebra; carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; specifically, the server acquires cone image data, inputs the cone image data into a preset image segmentation network for automatic image segmentation processing, and obtains a target segmentation result of the cone image data, wherein the image segmentation network is obtained based on body loss and edge loss training of a training sample image, the body loss is loss between a segmentation labeling result and a segmentation prediction result of the training sample image for a body region of a target object, the edge loss is loss between a segmentation labeling result and a segmentation prediction result of the training sample image for an edge region of the target object, a cone image for the target object is segmented from the cone image data according to the target segmentation result, and the server inputs a plurality of cone images into a preset three-dimensional reconstruction model for cone three-dimensional reconstruction, so as to obtain an initial three-dimensional structure of a vertebra; carrying out vertebral body three-dimensional structure reconstruction and cancellous bone cavity three-dimensional structure reconstruction on the initial vertebral body three-dimensional structure according to the vertebral body bone mass distribution parameters to obtain a target three-dimensional structure; searching a osteopenia area according to the vertebral body bone mass distribution parameters; calling the three-dimensional reconstruction model to construct a vertebral body and a cancellous bone cavity structure corresponding to the target user according to the osteopenia region; automatically segmenting a vertebral body from CT of a target user and reconstructing a three-dimensional structure of the vertebral body, constructing a cancellous bone cavity three-dimensional structure in the vertebral body according to a bone reduction region of the vertebral body based on a bone mass three-dimensional distribution detection result of the vertebral body, and finally predicting the flow distribution in the vertebral body after bone cement injection by using a numerical simulation method based on a computational fluid mechanics technology;
the processing module is used for acquiring bone cement parameters corresponding to bone cement, and performing flow distribution calculation on the bone cement according to the bone cement parameters and the target three-dimensional structure to obtain a flow distribution calculation result, wherein the flow distribution calculation result is used for indicating the flow distribution of the bone cement injected into a vertebral body;
the calculation module is used for calculating the flow distribution forms of the bone cement based on the numerical simulation rules of computational fluid mechanics to obtain the flow distribution corresponding to each numerical simulation rule; wherein, the numerical simulation rule based on computational fluid dynamics respectively calculates a plurality of bone cement flow distribution forms to obtain the flow distribution corresponding to each numerical simulation rule, including: generating a plurality of numerical simulation rules based on a plurality of preset injection modes; respectively calculating the flow distribution form of each numerical simulation rule of the bone cement through a preset fluid volume model to obtain the flow distribution corresponding to each numerical simulation rule; specifically, based on numerical simulation model and bone cement parameters, computational fluid dynamics is adopted to calculate the flow and distribution of bone cement in the vertebral body after injection, numerical simulation shows the flow process of bone cement in the vertebral body and cancellous bone thereof, and the flow distribution of bone cement is predicted, wherein, the two-phase interface of bone cement in the vertebral body and air in the vertebral body is defined as the surface formed by grid points with the volume fraction of the bone cement of 0.5, the flow process in the vertebral body after injection of the bone cement is described by the computational fluid dynamics, and the flow distribution of the bone cement is simulated and calculated, which comprises: simulating the effect of a centrum cancellous bone area on bone cement flow by using a VOF model, setting a reconstructed three-dimensional structure of a cancellous bone cavity communication domain as a fluid domain, solving the above equation in a three-dimensional space by using a numerical solving method through a continuity equation, a momentum conservation equation and an energy equation of the fluid domain, calculating numerical results of the speed, the pressure and the volume fraction of the bone cement at each grid point, and finally obtaining flow distribution corresponding to each numerical simulation rule;
an optimization module, configured to perform variable optimization on the design variables of the bone cement according to the flow distribution calculation result and the flow distribution corresponding to each numerical simulation rule, so as to obtain target design variables, where the target design variables include: injection amount of bone cement, injection rate, and injection location.
6. A bone cement flow prediction device, characterized in that the bone cement flow prediction device comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the bone cement flow prediction device to perform the bone cement flow prediction method of any one of claims 1-4.
7. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the bone cement flow prediction method of any one of claims 1-4.
CN202211120783.8A 2022-09-15 2022-09-15 Bone cement flow prediction method, device, equipment and storage medium Active CN115205293B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211120783.8A CN115205293B (en) 2022-09-15 2022-09-15 Bone cement flow prediction method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211120783.8A CN115205293B (en) 2022-09-15 2022-09-15 Bone cement flow prediction method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN115205293A CN115205293A (en) 2022-10-18
CN115205293B true CN115205293B (en) 2022-12-09

Family

ID=83572903

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211120783.8A Active CN115205293B (en) 2022-09-15 2022-09-15 Bone cement flow prediction method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115205293B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116128957B (en) * 2023-04-20 2023-06-30 博志生物科技(深圳)有限公司 Vertebral bone cavity analysis method, device, equipment and storage medium

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006039358A2 (en) * 2004-09-30 2006-04-13 The Regents Of The University Of California Method for assessment of the structure-function characteristics of structures in a human or animal body
US7717918B2 (en) * 2004-12-06 2010-05-18 Dfine, Inc. Bone treatment systems and methods
US20150173818A1 (en) * 2010-01-20 2015-06-25 Gamal Baroud Minimally invasive method and applications for injectible materials
DE102014221942A1 (en) * 2014-10-28 2016-04-28 Siemens Aktiengesellschaft Method for the fully automatic detection and evaluation of vertebral damage
US11517375B2 (en) * 2016-11-08 2022-12-06 Mazor Robotics Ltd. Bone cement augmentation procedure
CN109758116B (en) * 2018-11-30 2021-07-13 广东工业大学 System for judging bone density distribution in bone reaming operation
CN109543350B (en) * 2018-12-20 2023-03-24 哈尔滨工业大学（深圳） Permeable concrete performance prediction method and system based on mesoscopic model reconstruction
ES2828728A1 (en) * 2019-11-27 2021-05-27 Fundacion Para La Investigacion Del Hospital Univ La Fe De La Comunidad Valenciana METHOD TO OBTAIN AN IMAGE BIOMARKER THAT QUANTIFIES THE QUALITY OF THE TRABECULAR STRUCTURE OF THE BONES (Machine-translation by Google Translate, not legally binding)
CN114240848A (en) * 2021-11-24 2022-03-25 慧影医疗科技(北京)股份有限公司 Bone mineral density measuring method, system, storage medium and electronic equipment
CN114155967A (en) * 2021-11-26 2022-03-08 山东省千佛山医院 Numerical simulation method and system for bone cement pressure exudation and dispersion
CN114068025A (en) * 2021-11-26 2022-02-18 山东省千佛山医院 Numerical simulation optimization method and system for bone repair forming of mesh bag type bone cement
CN114723763B (en) * 2022-05-24 2022-09-02 博志生物科技(深圳)有限公司 Medical image segmentation method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN115205293A (en) 2022-10-18

Similar Documents

Publication Publication Date Title
Giambini et al. The effect of quantitative computed tomography acquisition protocols on bone mineral density estimation
Cattaneo et al. A three-dimensional finite element model from computed tomography data: a semi-automated method
Soodmand et al. Interlaboratory comparison of femur surface reconstruction from CT data compared to reference optical 3D scan
Sakellariou et al. Developing a virtual materials laboratory
Stoyanova et al. An enhanced computational method for age‐at‐death estimation based on the pubic symphysis using 3 D laser scans and thin plate splines
Kalra Developing fe human models from medical images
CN115205293B (en) Bone cement flow prediction method, device, equipment and storage medium
Vanderesse et al. Image analysis characterization of periodic porous materials produced by additive manufacturing
CN113408172B (en) Manufacturing method and manufacturing system of interbody fusion cage
Podshivalov et al. Multiscale FE method for analysis of bone micro-structures
Giambini et al. Quantitative computed tomography protocols affect material mapping and quantitative computed tomography-based finite-element analysis predicted stiffness
Kallemeyn et al. An interactive multiblock approach to meshing the spine
CN112200914A (en) Method for predicting intracranial aneurysm occurrence by numerical simulation three-dimensional reconstruction reduced parent artery
EP3766080A1 (en) Method of estimating physiological parameters using medical image data
Huang et al. Patient-specific geometrical modeling of orthopedic structures with high efficiency and accuracy for finite element modeling and 3D printing
Zhou et al. An improved trabecular bone model based on Voronoi tessellation
Suputra et al. 3D Laplacian surface deformation for template fitting on craniofacial reconstruction
CN104778322A (en) Average femoral model construction method based on statistical information
Famouri et al. Refining anticipation of degraded bone microstructures during osteoporosis based on statistical homogenized reconstruction method via quality of connection function
CN108565027B (en) simulation system for simulating fracture healing process
Khoda Process plan for multimaterial heterogeneous object in additive manufacturing
CN115690063A (en) Bone density parameter detection method, computer device and storage medium
EP4011311A1 (en) Method for planning the nail path of a pedicle bone screw
Garcia-Andrés et al. Methodology for the assessment of the risk of failure of metastatic vertebrae through ROM-based patient-specific simulations
Mengoni et al. In-silico models of trabecular bone: a sensitivity analysis perspective

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