CN117152256B - Pelvis model channel positioning method and device based on templates - Google Patents
Pelvis model channel positioning method and device based on templates Download PDFInfo
- Publication number
- CN117152256B CN117152256B CN202311420362.1A CN202311420362A CN117152256B CN 117152256 B CN117152256 B CN 117152256B CN 202311420362 A CN202311420362 A CN 202311420362A CN 117152256 B CN117152256 B CN 117152256B
- Authority
- CN
- China
- Prior art keywords
- model
- pelvis
- channel
- image
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004197 pelvis Anatomy 0.000 title claims abstract description 159
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 230000000877 morphologic effect Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013179 statistical model Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims 1
- 238000004088 simulation Methods 0.000 abstract description 2
- 206010017076 Fracture Diseases 0.000 description 9
- 239000007943 implant Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 210000000988 bone and bone Anatomy 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010034246 Pelvic fractures Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/101—Computer-aided simulation of surgical operations
- A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
-
- 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
Abstract
The invention relates to the field of three-dimensional model simulation, and particularly discloses a pelvis model channel positioning method based on a template, which comprises the steps of establishing a pelvis average statistical form model according to a pelvis model library; obtaining a channel template based on a pelvic average statistical morphology model, the channel template comprising positional information of the channel in the pelvic average statistical morphology model and the pelvic average statistical morphology model; preprocessing the CT image, and generating a target model of pelvis by utilizing the preprocessed CT image; a channel is located in the target model based on the channel template. The automatic establishment of the channel can be realized, the time of doctors is saved, and the operation of the doctors is simplified.
Description
Technical Field
The invention relates to the field of three-dimensional model simulation, in particular to a pelvis model channel positioning method and device based on templates.
Background
Pelvic fractures are usually caused by severe trauma, with disability rates as high as 50% -60%, and improper treatment usually has a high mortality rate. In order to recover the fracture in the early stage, the fracture site is prevented from being damaged again, the patient needs to perform implantation operation, the fracture site is fixed by using implants such as steel nails, screws, k-nails and the like, the operation effect is extremely dependent on the fixing effect of the implants, the fixing effect is also dependent on the accuracy of the implant position, and therefore the pelvis implant position is positioned as a hot spot for research.
The implant location, i.e. the minimally invasive approach, is usually determined by the physician during the preoperative planning phase in the prior art, and whether it is accurate or not affects the patient's recovery effect, so it plays a vital role throughout the entire surgical cycle. The traditional minimally invasive channel determination method relies on image data of a fracture part of a patient, takes subjective experience of doctors as objective basis, firstly evaluates the fracture degree, then determines the approximate position of the minimally invasive channel on the image of the fracture part, and finally refines the operation flow scheme. The judgment process in the prior art depends on the manual experience of doctors to a great extent, the establishment of the channel depends on the manual operation and clinical experience of the doctors, the time and the labor are wasted, and the accurate positioning of the channel position cannot be realized; in some personalized scenes, multiple manual experiments are performed by using the 3D printed bone model of the patient to determine the specific position of the channel, but the method has higher cost and longer period and cannot meet the requirement of quickly determining the position of the channel.
Disclosure of Invention
The invention aims to provide a pelvis model channel positioning method and device based on templates, which are used for solving the problems in the background technology.
The invention provides a pelvis model channel positioning method based on a template, which comprises the following steps:
establishing a pelvis average statistical morphology model according to a pelvis model library;
obtaining a channel template based on a pelvic average statistical morphology model, the channel template comprising positional information of the channel in the pelvic average statistical morphology model and the pelvic average statistical morphology model;
preprocessing the CT image, and generating a target model of pelvis by utilizing the preprocessed CT image;
a channel is located in the target model based on the channel template.
Preferably, the template-based pelvis model channel positioning method comprises an off-line link and an on-line link, wherein in the off-line link, a channel template is acquired, a pelvis target model is generated in the on-line link, and a channel is positioned in the target model.
Preferably, the building the pelvis average statistical morphology model according to the pelvis model library specifically includes:
building a pelvis model library: collecting pelvis models of different ages and sexes to obtain a pelvis model library;
generating an average statistical morphology model: acquiring the point and surface information of all models in the pelvis model library, and carrying out statistical morphological analysis on the point and surface information of all models by using a statistical morphological model filter to obtain fitting morphological errors; and fitting a statistical model by using all models in the pelvis model library, and establishing an average statistical morphology model based on the fitting morphology error and the statistical model.
Preferably, the pelvis minimally invasive channels are positioned on the pelvis average statistical morphology model, and the position information of the channels in the pelvis average statistical morphology model and the pelvis average statistical morphology model are derived to serve as channel templates.
Preferably, the preprocessing the CT image, generating a target model of the pelvis by using the preprocessed CT image specifically includes:
the CT images are multiple, the preprocessing comprises the steps of respectively extracting a section of a pelvis area from a plurality of CT body data containing the whole lower body to obtain a plurality of pelvis images only containing fracture areas, compressing each pelvis image to a preset size, and registering the compressed pelvis images to be registered based on a registration network to obtain a spatial registration deformation field from the pelvis images to be registered to a target image.
Preferably, the target image in the registration process is a pelvis image corresponding to any patient selected randomly, and the image to be registered is a pelvis image corresponding to the rest patients.
Preferably, the registration network specifically includes:
jumping the concatenated encoder-decoder and the first predetermined number of consecutive layers; in the encoder, an encoding operation of an image pyramid type structure is adopted; in the decoder, up-sampling, convolution and connection hopping are used alternately.
Preferably, the generating a target model of pelvis by using the preprocessed CT image specifically includes:
extraction of affine matrix in CT volume dataObtaining a spatial transformation of the image coordinate system into the anatomical coordinate system according to the spatial registration deformation>，/>Registering the deformation field for space; and converting voxel information of the pelvis image to be registered and the target pelvis image into corresponding three-dimensional anatomical models of the pelvis to be registered and the target pelvis.
Preferably, the positioning a channel in the target model based on the channel template specifically includes:
registering the average statistical morphological model and the target pelvis anatomical three-dimensional model to obtain a first transformation matrix between the model and the target pelvis anatomical three-dimensional model; obtaining a channel of a target pelvis three-dimensional model according to the position information of the channel in the pelvis average statistical form model in the channel template and a space conversion matrix between the two; and calculating a three-dimensional model of the pelvis after registration according to the spatial transformation from the image coordinate system to the anatomical coordinate system and the three-dimensional model of the pelvis to be registered, and calculating a channel of the pelvis after registration according to the corresponding relation between the pelvis model after registration and the target pelvis model and the channel of the target pelvis model to be used as the channel of the pelvis model to be registered.
The invention also provides a pelvis model channel positioning device based on the template, which comprises:
the modeling module is used for establishing a pelvis average statistical morphology model according to the pelvis model library;
the template building module is used for obtaining a channel template based on a pelvis average statistical morphology model, wherein the channel template comprises position information of the channel in the pelvis average statistical morphology model and the pelvis average statistical morphology model;
the pelvis modeling module is used for preprocessing the CT image and generating a pelvis target model by utilizing the preprocessed CT image;
and the channel positioning module is used for positioning a channel in the target model based on the channel template.
The invention provides a method and a device for positioning a pelvic model channel based on a template, which can obtain the channel template based on a model in statistical sense and automatically position the channel in a target model for generating pelvis based on CT images by using the template. On the one hand, the positioning can be automatically completed based on the image in the process of positioning the channel without human intervention, so that the dependence of the channel positioning process on human experience is reduced, and the automatic process of positioning the channel is improved; on the other hand, a target model is directly generated based on the CT image, the target model is identical to the real pelvis form and parameters, and channel positioning is performed in the target model, so that a doctor is prevented from directly checking the CT image to perform channel positioning, and the accuracy of channel positioning is improved. In the traditional method, the establishment of the channel depends on the manual operation and clinical experience of doctors, and is time-consuming and labor-consuming, compared with the traditional preoperative matching method, the method for three-dimensional reconstruction of the medical CT image by taking the internal bone information into consideration can obtain a precise target model of pelvis, can realize the automatic establishment of the channel, saves the time of doctors and simplifies the operation of the doctors.
Drawings
FIG. 1 is a flowchart of a method for positioning a pelvic model channel based on a template according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a registration network structure according to an embodiment of the present invention.
Description of the embodiments
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown.
The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is further described below with reference to the accompanying drawings.
The embodiment of the invention provides a pelvic model channel positioning method based on a template, which is shown in fig. 1 and comprises the following steps:
establishing a pelvis average statistical morphology model according to a pelvis model library;
obtaining a channel template based on a pelvic average statistical morphology model, the channel template comprising positional information of the channel in the pelvic average statistical morphology model and the pelvic average statistical morphology model;
preprocessing the CT image, and generating a target model of pelvis by utilizing the preprocessed CT image;
a channel is located in the target model based on the channel template.
The pelvis model channel positioning method based on the template provided by the invention can obtain the channel template based on a model in statistical sense, and automatically position the channel in a target model for generating pelvis based on CT images by using the template. On the one hand, the positioning can be automatically completed based on the image in the process of positioning the channel without human intervention, so that the dependence of the channel positioning process on human experience is reduced, and the automatic process of positioning the channel is improved; on the other hand, a target model is directly generated based on the CT image, the target model is identical to the real pelvis form and parameters, and channel positioning is performed in the target model, so that a doctor is prevented from directly checking the CT image to perform channel positioning, and the accuracy of channel positioning is improved. In the traditional method, the establishment of the channel depends on the manual operation and clinical experience of doctors, and is time-consuming and labor-consuming, compared with the traditional preoperative matching method, the method for three-dimensional reconstruction of the medical CT image by taking the internal bone information into consideration can obtain a precise target model of pelvis, can realize the automatic establishment of the channel, saves the time of doctors and simplifies the operation of the doctors.
Further, the pelvis model channel positioning method based on the template comprises an off-line link and an on-line link, wherein in the off-line link, a channel template is acquired, a target model of pelvis is generated in the on-line link, and a channel is positioned in the target model. The invention completes the channel positioning in a mode of combining offline and online modes, the offline processing stage takes the clinical experience of doctors as support, and the online processing stage can be automatically obtained without manual operation of the doctors. The model and the template in statistical sense need to be obtained by analyzing a larger data volume, and the object to be analyzed is the existing model in the pelvis model library, so that the whole process can be calculated in an off-line link, the calculated amount and the calculated time in the on-line link are reduced, and the pelvis model channel positioning efficiency is further improved.
As an optional embodiment, the building a pelvis average statistical morphology model according to the pelvis model library specifically includes:
building a pelvis model library: collecting pelvis models of different ages and sexes to obtain a pelvis model library, wherein the pelvis model is preferably a pelvis model of a person in a preset country, and the preset country is specifically China.
Generating an average statistical morphology model: acquiring the point and surface information of all models in the pelvis model library, and carrying out statistical morphological analysis on the point and surface information of all models by using a statistical morphological model filter to obtain fitting morphological errors; and fitting a statistical model by using all models in the pelvis model library, and establishing an average statistical morphology model based on the fitting morphology error and the statistical model.
The pelvis model channel positioning method based on the template provided by the invention takes the models in the model library as input, firstly reads in the point and face information of all the models, then uses a statistical morphological model filter to carry out statistical morphological analysis on the point and face information of all the models to obtain fitting morphological errors, uses all the models to fit the predicted statistical models, and finally establishes an average statistical morphological model. For the researched objects with different characteristics, the pelvis outline shapes are basically consistent, but the structural parameters are different, in order to establish templates in advance, the method provided by the invention utilizes the point and surface information of all the models in the model library to perform fitting, so that an average statistical form model is obtained, namely, the average statistical form model is obtained through fitting of a large number of models, so that a channel template is obtained based on the average statistical form model, the average statistical form model synthesizes the point and surface information of all the models in the model library, each model is prevented from being marked manually, and the workload of template generation is simplified.
Preferably, a channel template is obtained based on a pelvis average statistical morphology model, and a pelvis minimally invasive channel can be positioned on the pelvis average statistical morphology model according to clinical experience provided by a doctor, and the position information of the channel in the pelvis average statistical morphology model and the pelvis average statistical morphology model are derived to be used as the channel template, wherein the channel template comprises the position information of the channel in the pelvis average statistical morphology model and the pelvis average statistical morphology model.
As an optional embodiment, the preprocessing the CT image, generating the target model of the pelvis by using the preprocessed CT image specifically includes: the CT images are multiple, the preprocessing comprises the steps of respectively extracting a section of a pelvis area from a plurality of CT body data containing the whole lower body to obtain a plurality of pelvis images only containing fracture parts, compressing each pelvis image to a preset size, and registering the compressed pelvis images based on a registration network to obtain a spatial registration deformation field from an image to be registered to a target image.
Preferably, each of the pelvic images may be compressed to 440x256x256. Registering the compressed pelvis images containing the fracture parts, wherein the pelvis images are used for realizing the registration between non-homologous CT images, the target image in the registration process is a pelvis image corresponding to any randomly selected patient, and the image to be registered is a pelvis image corresponding to other patients. Registration network as shown in fig. 2, the registration network specifically includes: the method comprises the steps of jumping a coder-decoder and a first preset number of continuous layers, wherein in the coder, adopting coding operation of an image pyramid structure, and preferably, the image pyramid structure uses three-dimensional convolution with a convolution kernel size of 3x3x3 and a step length of 2, and the space dimension is reduced to 1/2 of the original dimension each time under the action of the convolution step length until the space dimension is reduced to 1/16 of the original dimension; in the decoder, up-sampling, convolution and connection hopping are used alternately. The registration network provided by the invention adopts the structure of the encoder-decoder and the continuous layer, so that the receptive field of the image is finer, and the alignment of the anatomical structure is realized more accurately.
Because the spatial registration deformation field from the image to be registered to the target image is the change of each voxel of CT volume data under an image coordinate system in three directions, and the channel template is positioned in the three-dimensional model under an anatomical coordinate system, as an optional embodiment, the method for generating the target model of the pelvis by using the preprocessed CT image specifically comprises the following steps: extraction of affine matrix in CT volume dataObtaining a spatial transformation of the image coordinate system into the anatomical coordinate system according to the spatial registration deformation>，/>Registering the deformation field for space; and converting the voxel information of the image to be registered and the target image into a corresponding three-dimensional model of the pelvis to be registered and a corresponding three-dimensional model of the pelvis to be registered.
Positioning a channel in the target model based on the channel template, specifically comprising: registering the average statistical morphological model and the target pelvis three-dimensional model to obtain a space conversion matrix between the average statistical morphological model and the target pelvis three-dimensional model; obtaining a channel of a target pelvis model according to the position information of the channel in the pelvis average statistical morphology model in the channel template and the space conversion matrix; and calculating a registered pelvis model according to the spatial transformation from the image coordinate system to the anatomical coordinate system and the pelvis model to be registered, and calculating a channel of the registered pelvis according to the corresponding relation between the registered pelvis model and the target pelvis model and the channel of the target pelvis model to be used as the channel of the pelvis model to be registered.
The embodiment of the invention also provides a pelvis model channel positioning device based on the template, which comprises:
the modeling module is used for establishing a pelvis average statistical morphology model according to the pelvis model library;
the template building module is used for obtaining a channel template based on a pelvis average statistical morphology model, wherein the channel template comprises position information of the channel in the pelvis average statistical morphology model and the pelvis average statistical morphology model;
the pelvis modeling module is used for preprocessing the CT image and generating a pelvis target model by utilizing the preprocessed CT image;
and the channel positioning module is used for positioning a channel in the target model based on the channel template.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents. Such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Finally, it should be noted that the invention is not limited to the alternative embodiments described above, but can be used by anyone in various other forms of products in the light of the present invention. The above detailed description should not be construed as limiting the scope of the invention, which is defined in the claims and the description may be used to interpret the claims.
Claims (6)
1. A method for positioning a pelvic model channel based on a template, the method comprising:
establishing a pelvis average statistical morphology model according to a pelvis model library, which specifically comprises the following steps:
building a pelvis model library: collecting pelvis models of different ages and sexes to obtain a pelvis model library;
generating a pelvic average statistical morphology model: acquiring the point and surface information of all models in the pelvis model library, and carrying out statistical morphological analysis on the point and surface information of all models by using a statistical morphological model filter to obtain fitting morphological errors; fitting a statistical model by using all models in the pelvis model library, and establishing a pelvis average statistical form model based on the fitting form error and the statistical model;
obtaining a channel template based on a pelvic average statistical morphology model, the channel template comprising positional information of the channel in the pelvic average statistical morphology model and the pelvic average statistical morphology model;
preprocessing the CT image, and generating a target model of pelvis by utilizing the preprocessed CT image;
the preprocessing of the CT image, generating a target model of pelvis by utilizing the preprocessed CT image, specifically comprises the following steps:
the CT images are multiple, the preprocessing comprises the steps of respectively extracting a section of a pelvis area from a plurality of CT body data containing the whole lower body to obtain a plurality of pelvis images only containing fracture areas, compressing each pelvis image to a preset size, and registering the compressed pelvis images based on a registration network to obtain a spatial registration deformation field from an image to be registered to a target image;
generating a target model of pelvis by using the preprocessed CT image specifically comprises the following steps:
extracting affine matrix T in CT volume data, and obtaining spatial transformation from an image coordinate system to an anatomical coordinate system according to spatial registration deformation，/>Registering the deformation field for space; converting voxel information of the image to be registered and the target image into a corresponding three-dimensional model of pelvis to be registered and a corresponding three-dimensional model of pelvis to be registered;
locating a channel in the target model based on the channel template;
the positioning the channel in the target model based on the channel template specifically comprises:
registering the pelvis average statistical morphology model and the target pelvis model to obtain a space conversion matrix between the pelvis average statistical morphology model and the target pelvis model; obtaining a channel of a target pelvis model according to the position information of the channel in the pelvis average statistical morphology model in the channel template and the space conversion matrix; and calculating a registered pelvis model according to the spatial transformation from the image coordinate system to the anatomical coordinate system and the pelvis model to be registered, and calculating a channel of the pelvis model to be registered according to the corresponding relation between the registered pelvis model and the target pelvis model and the channel of the second three-dimensional model to be used as the channel of the pelvis model to be registered.
2. The method for template-based pelvic model passage positioning of claim 1,
the pelvis model channel positioning method based on the template comprises an off-line link and an on-line link, wherein in the off-line link, a channel template is acquired, a target model of pelvis is generated in the on-line link, and a channel is positioned in the target model.
3. The template-based pelvic model tunnel positioning method of claim 1, wherein a pelvic minimally invasive tunnel is positioned over a pelvic average statistical morphology model, and positional information of the tunnel in the pelvic average statistical morphology model and the pelvic average statistical morphology model are derived as a tunnel template.
4. The template-based pelvic model channel localization method of claim 1, wherein the target image in the registration process is a randomly selected pelvic image corresponding to any patient, and the image to be registered is a pelvic image corresponding to the remaining patients.
5. The template-based pelvic model passage positioning method of claim 1, wherein the registration network specifically comprises:
jumping the concatenated encoder-decoder and the first predetermined number of consecutive layers; in the encoder, an encoding operation of an image pyramid type structure is adopted; in the decoder, up-sampling, convolution and connection hopping are used alternately.
6. A positioning device for applying the template-based pelvic model passage positioning method according to any one of claims 1-5, characterized in that the positioning device comprises:
the modeling module is used for establishing a pelvis average statistical morphology model according to the pelvis model library;
the template building module is used for obtaining a channel template based on a pelvis average statistical morphology model, wherein the channel template comprises position information of the channel in the pelvis average statistical morphology model and the pelvis average statistical morphology model;
the pelvis modeling module is used for preprocessing the CT image and generating a pelvis target model by utilizing the preprocessed CT image;
and the channel positioning module is used for positioning a channel in the target model based on the channel template.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311420362.1A CN117152256B (en) | 2023-10-30 | 2023-10-30 | Pelvis model channel positioning method and device based on templates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311420362.1A CN117152256B (en) | 2023-10-30 | 2023-10-30 | Pelvis model channel positioning method and device based on templates |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117152256A CN117152256A (en) | 2023-12-01 |
| CN117152256B true CN117152256B (en) | 2024-02-13 |
Family
ID=88897209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311420362.1A Active CN117152256B (en) | 2023-10-30 | 2023-10-30 | Pelvis model channel positioning method and device based on templates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152256B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447764A (en) * | 2016-09-08 | 2017-02-22 | 福州大学 | Three-dimensional visualization automatic measuring method for human body pelvis parameters |
| CN110688929A (en) * | 2019-09-20 | 2020-01-14 | 北京华捷艾米科技有限公司 | Human skeleton joint point positioning method and device |
| CN111008974A (en) * | 2019-11-22 | 2020-04-14 | 浙江飞图影像科技有限公司 | Multi-model fusion femoral neck fracture region positioning and segmentation method and system |
| CN114155286A (en) * | 2021-11-09 | 2022-03-08 | 大连理工大学 | Individualized registration method for anatomical morphology and material mechanics characteristic template library of skeleton CT image |
| WO2022217660A1 (en) * | 2021-04-15 | 2022-10-20 | 卡本(深圳)医疗器械有限公司 | Posterior superior iliac spine automatic detection and location method based on ct images |
| CN115331059A (en) * | 2022-08-17 | 2022-11-11 | 上海交通大学 | Spine three-column fracture classification and positioning system based on residual attention constraint mechanism |
| KR20230078905A (en) * | 2021-11-26 | 2023-06-05 | 경희대학교 산학협력단 | Real-time measuring method and apparatus for 3D direction of anterior pelvic plane |
| CN116433477A (en) * | 2023-06-13 | 2023-07-14 | 北京壹点灵动科技有限公司 | Pelvis registration method, device, storage medium and electronic equipment |
| CN116616893A (en) * | 2023-04-17 | 2023-08-22 | 南京航空航天大学 | Automatic positioning method for pelvis implant channel |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1894538B1 (en) * | 2006-09-01 | 2009-11-04 | BrainLAB AG | Method and device for determining the position of pelvic planes |
-
2023
- 2023-10-30 CN CN202311420362.1A patent/CN117152256B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447764A (en) * | 2016-09-08 | 2017-02-22 | 福州大学 | Three-dimensional visualization automatic measuring method for human body pelvis parameters |
| CN110688929A (en) * | 2019-09-20 | 2020-01-14 | 北京华捷艾米科技有限公司 | Human skeleton joint point positioning method and device |
| CN111008974A (en) * | 2019-11-22 | 2020-04-14 | 浙江飞图影像科技有限公司 | Multi-model fusion femoral neck fracture region positioning and segmentation method and system |
| WO2022217660A1 (en) * | 2021-04-15 | 2022-10-20 | 卡本(深圳)医疗器械有限公司 | Posterior superior iliac spine automatic detection and location method based on ct images |
| CN114155286A (en) * | 2021-11-09 | 2022-03-08 | 大连理工大学 | Individualized registration method for anatomical morphology and material mechanics characteristic template library of skeleton CT image |
| KR20230078905A (en) * | 2021-11-26 | 2023-06-05 | 경희대학교 산학협력단 | Real-time measuring method and apparatus for 3D direction of anterior pelvic plane |
| CN115331059A (en) * | 2022-08-17 | 2022-11-11 | 上海交通大学 | Spine three-column fracture classification and positioning system based on residual attention constraint mechanism |
| CN116616893A (en) * | 2023-04-17 | 2023-08-22 | 南京航空航天大学 | Automatic positioning method for pelvis implant channel |
| CN116433477A (en) * | 2023-06-13 | 2023-07-14 | 北京壹点灵动科技有限公司 | Pelvis registration method, device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117152256A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970426B2 (en) | Methods, systems, and devices for designing and manufacturing a spinal rod | |
| JP2023014084A5 (en) | ||
| CN101390773B (en) | Production method of navigation template for positioning the pediculus arcus vertebrae | |
| CN101953713B (en) | Navigation template capable of being used for positioning vertebral pedicle | |
| CN110214341A (en) | The method for rebuilding skull | |
| CN103099680B (en) | Production method for guide template | |
| CN101816590A (en) | Method for manufacturing navigation template of human bone surgery and female die thereof | |
| CN102147919A (en) | Intraoperative registration method for correcting preoperative three-dimensional image and device | |
| AU2020101836A4 (en) | A method for generating femoral x-ray films based on deep learning and digital reconstruction of radiological image | |
| CN107358608A (en) | Bone tissue geometric state parameter auto-testing device and method based on image processing techniques | |
| ES2856941T3 (en) | Automated generation of bone treatment agents | |
| KR20160091322A (en) | Bone reconstruction and orthopedic implants | |
| CN106264731A (en) | A kind of method based on point-to-point registration technique virtual knee joint single condyle replacement model construction | |
| CN105608741A (en) | Computer simulation method for predicting soft tissue appearance change after maxillofacial bone plastic surgery | |
| CN104706425A (en) | Bone cutting navigation device capable of positioning accurately and manufacturing and using method thereof | |
| CN108320288A (en) | A kind of data processing method of idiopathic scoliosis image | |
| CN103099669B (en) | Single-side pedicle screw-driving auxiliary device and manufacturing method thereof | |
| CN103099679B (en) | Personalized lumbar internal fixation auxiliary device and manufacturing method thereof | |
| CN107016666A (en) | The post processing of image method of pelvis CT three-dimensional reconstructions based on coordinate-system | |
| CN106991720B (en) | Personalized acetabulum reconstruction steel plate pre-bending method based on finite element analysis and operation | |
| CN104905869A (en) | Navigation template for vertebral pedicle locating and real-time screw path monitoring and manufacturing method thereof | |
| CN105982722A (en) | Digital skeleton operation repair method and system | |
| CN107714078B (en) | Method and system for positioning three-dimensional positions of plants in bones and joints by using structural features | |
| CN115844531A (en) | Hip replacement surgery navigation system | |
| CN106308919A (en) | Method for producing navigation template for assisting imbedding of thoracic vertebra pedicle screw and navigation template |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tang Peifu Inventor after: Du Qingjie Inventor after: Zhao Jingxin Inventor after: Chen Fang Inventor after: Zhang Licheng Inventor after: Chen Lingyu Inventor after: Chen Hua Inventor before: Tang Peifu |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |