CN116758210A - Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model - Google Patents
Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model Download PDFInfo
- Publication number
- CN116758210A CN116758210A CN202310139537.5A CN202310139537A CN116758210A CN 116758210 A CN116758210 A CN 116758210A CN 202310139537 A CN202310139537 A CN 202310139537A CN 116758210 A CN116758210 A CN 116758210A
- Authority
- CN
- China
- Prior art keywords
- bone surface
- surface model
- model
- joint
- medical image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Prostheses (AREA)
Abstract
The present disclosure relates to a three-dimensional reconstruction method, apparatus, device and storage medium for bone surface model, wherein the method comprises: acquiring a first medical image comprising a first joint of a user, wherein a metal prosthesis is present in the first joint, and a second medical image comprising a second joint of the user, the second joint corresponding to the first joint and being free of the metal prosthesis; performing bone surface reconstruction based on the first medical image, generating a first bone surface model, and performing bone surface reconstruction and overturning based on the second medical image, generating a second bone surface model; registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model; and performing transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint. According to the technical scheme, the problem of difficult segmentation and reconstruction caused by metal artifact images can be solved.
Description
Technical Field
The disclosure relates to the technical field of image processing, and in particular relates to a three-dimensional reconstruction method, device and equipment of a bone surface model and a storage medium.
Background
The surgical robot is used as intelligent medical equipment, can finish fine surgical operation in the human body cavity, blood vessels and nerve dense areas, and can be divided into a neurosurgery robot, an orthopedic surgery robot, a laparoscopic surgery robot and the like in the clinical medical application field. The knee joint replacement operation robot can segment and reconstruct the knee joint bone structure of a patient according to a knee joint CT (Computer Tomography, computed tomography) image scanned before operation of the patient, so that a personalized operation planning scheme is formulated for the patient, and the placement accuracy of prosthesis replacement and the life quality of the patient after healing are improved. Therefore, accurate image segmentation and three-dimensional reconstruction of a patient CT image are important preconditions for successful preoperative planning.
At present, in the practical application scene of hospitals, there are cases that patients with metal prostheses implanted need to perform secondary operations, and serious metal artifacts usually exist in CT images of the patients, so that image segmentation and reconstruction are difficult, and follow-up operation planning is affected. Therefore, a solution for accurate segmentation and three-dimensional reconstruction of the bone structure of a patient for such situations is needed.
Disclosure of Invention
In order to solve the technical problems, the present disclosure provides a three-dimensional reconstruction method, device, equipment and storage medium for bone surface model.
In a first aspect, an embodiment of the present disclosure provides a three-dimensional reconstruction method of a bone surface model, including:
acquiring a first medical image comprising a first joint of a user, and a second medical image comprising a second joint of the user, wherein a metal prosthesis is present in the first joint, the second joint corresponds to the first joint, and no metal prosthesis is present in the second joint;
performing bone surface reconstruction based on the first medical image, generating a first bone surface model, and performing bone surface reconstruction and overturning based on the second medical image, generating a second bone surface model;
registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model;
and performing transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint.
In a second aspect, embodiments of the present disclosure provide a three-dimensional reconstruction apparatus of a bone surface model, including:
an acquisition module for acquiring a first medical image comprising a first joint of a user, and a second medical image comprising a second joint of the user, wherein a metal prosthesis is present in the first joint, the second joint corresponds to the first joint, and no metal prosthesis is present in the second joint;
the reconstruction module is used for performing bone surface reconstruction based on the first medical image, generating a first bone surface model, performing bone surface reconstruction and overturning based on the second medical image, and generating a second bone surface model;
the registration module is used for registering the first bone surface model and the second bone surface model and generating a transformation matrix between the first bone surface model and the second bone surface model;
and the generation module is used for carrying out transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the three-dimensional reconstruction method of the bone surface model according to the first aspect.
In a fourth aspect, an embodiment of the present disclosure provides a computer readable storage medium storing a computer program, where the computer program is executed by a processor to implement the three-dimensional reconstruction method of a bone surface model according to the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages: the method comprises the steps of performing bone surface reconstruction through a medical image of a joint with a metal prosthesis, generating a first bone surface model, performing bone surface reconstruction through a medical image of a joint with no metal prosthesis on the opposite side, generating a second bone surface model, registering the first bone surface model and the second bone surface model, generating a transformation matrix, performing transformation processing on the second bone surface model through the transformation matrix, and generating a repaired bone surface model, so that the application scene that secondary operation is required for a patient implanted with the metal prosthesis is effectively utilized, the problem of difficult segmentation and reconstruction caused by the metal artifact image can be effectively solved while the accuracy is ensured, and the accurate segmentation and three-dimensional reconstruction of the bone structure of the patient are performed according to the situation.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a schematic flow chart of a three-dimensional reconstruction method of a bone surface model according to an embodiment of the disclosure;
fig. 2 is a schematic diagram of a lower limb full-length tablet according to an embodiment of the disclosure;
FIG. 3 is a schematic diagram of another three-dimensional reconstruction method of a bone surface model according to an embodiment of the present disclosure;
FIG. 4 is a schematic illustration of a knee joint metal artifact provided by an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a three-dimensional reconstruction device for a bone surface model according to an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.
Fig. 1 is a schematic flow chart of a three-dimensional reconstruction method of a bone surface model according to an embodiment of the present disclosure, where the method provided by the embodiment of the present disclosure may be performed by a three-dimensional reconstruction device of a bone surface model, and the device may be implemented by software and/or hardware and may be integrated on any electronic device with computing capability.
As shown in fig. 1, a three-dimensional reconstruction method of a bone surface model according to an embodiment of the present disclosure may include:
step 101, a first medical image is acquired comprising a first joint of a user and a second medical image comprising a second joint of the user.
Wherein, there is metal prosthesis in the first joint, the second joint corresponds with the first joint, and there is no metal prosthesis in the second joint. Medical images include, but are not limited to, CT images, PET (Positron Emission Computed Tomography, positron emission tomography) images, MRI (Magnetic Resonance Imaging ) images.
In this embodiment, before performing an operation on a first joint of a user, a medical image of the user is acquired by a medical imaging device, and the acquired medical image is cropped to determine a first medical image including the first joint of the user and a second medical image including a second joint of the user.
Wherein the first joint and the second joint include, but are not limited to, knee joint, hip joint, shoulder joint, elbow joint, ankle joint, and the like.
In one embodiment of the present disclosure, the first joint and the second joint are knee joints, the first medical image and the second medical image are full-length lower limb slices, for example, as shown in fig. 2, as an example, a metal prosthesis is present in the left knee joint of a patient, and a metal prosthesis is not present in the right knee joint, then the full-length lower limb slices on both sides of the patient are acquired in a pre-operation stage, and then the full-length lower limb slices on both sides of the patient are cut left and right, so as to obtain a CT image on one side of a leg (including the leg of the metal prosthesis) of the left prosthesis of the patient as the first medical image including the first joint, and a CT image on the right healthy leg (leg excluding the metal prosthesis) of the patient is obtained as the second medical image including the second joint.
Step 102, performing bone surface reconstruction based on the first medical image, generating a first bone surface model, and performing bone surface reconstruction and overturning based on the second medical image, generating a second bone surface model.
In this embodiment, image segmentation and three-dimensional reconstruction are performed based on the first medical image and the second medical image, respectively, to generate a corresponding first bone surface model and second bone surface model.
As an example, for a first medical image containing a first joint, a metal artifact region in the first medical image is first identified and cropped, then the cropped first medical image is subjected to image segmentation, and further three-dimensional reconstruction is performed based on the segmented image to generate a first reconstructed bone surface corresponding to one side of the first joint, and to generate a second reconstructed bone surface corresponding to the other side of the first joint, taking a knee joint as an example, a femur on one side and a tibia on the other side, and in this example, to generate a reconstructed bone surface corresponding to a prosthetic leg femur, and to generate a reconstructed bone surface corresponding to the prosthetic leg tibia as a first bone surface model. And, for a second medical image including a second joint, first performing image segmentation on the second medical image, and then performing three-dimensional reconstruction based on the segmented image to generate a reconstructed bone surface corresponding to one side of the second joint and a reconstructed bone surface corresponding to the other side of the second joint, and further performing left-right turning on the generated reconstructed bone surface to obtain a third reconstructed bone surface and a fourth reconstructed bone surface, wherein in the example, the knee joint is taken as an example, by generating a reconstructed bone surface corresponding to a healthy leg femur and a reconstructed bone surface corresponding to a healthy leg tibia as a second bone surface model.
Step 103, registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model.
In this embodiment, a related registration algorithm is used to register the first bone surface model and the second bone surface model, and a transformation matrix is generated, where the transformation matrix is used to transform the second bone surface model to register the second bone surface model to the image space of the first bone surface model.
As an example, the first reconstructed bone surface and the third reconstructed bone surface in the previous example are registered to generate a transformation matrix one, and the second reconstructed bone surface and the fourth reconstructed bone surface in the previous example are registered to generate a transformation matrix two.
The registration process is described below.
In one embodiment of the present disclosure, registering a first bone surface model and a second bone surface model generates a transformation matrix between the first bone surface model and the second bone surface model, comprising the steps of: registering the first bone surface model and the second bone surface model according to the preset key points on the first bone surface model and the preset key points on the second bone surface model to obtain initial position information of the second bone surface model; and according to the initial position information, registering the first bone surface model and the second bone surface model by adopting an ICP (Iterative Closest Point) algorithm and iterating nearest neighbor points to generate a transformation matrix between the first bone surface model and the second bone surface model.
In this embodiment, N key points are selected in advance on the first bone surface model, and N key points are selected correspondingly on the second bone surface model, where the key points are used for registration, and the positions of the key points on the respective bone surface models during selection are about the same, i.e. the errors between the positions are within a preset range, and are not required to be completely the same.
The method comprises the steps of carrying out registration on the basis of key points by adopting a least square method to obtain a rigid transformation matrix, determining an initial position of a second bone surface model through the rigid transformation matrix, and carrying out registration on the basis of the initial position by adopting an ICP algorithm to generate the transformation matrix. It should be noted that, the above registration algorithm is not limited to the least square method and the ICP algorithm, and other registration algorithms, such as NDT (Normal Distributions Transform, normal distribution transform) algorithm, may be used as required, which is not limited herein.
Step 104, performing transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint.
In this embodiment, the second bone surface model is registered to the image space containing the joint on one side of the metal prosthesis by the transformation matrix as a reconstructed bone surface model corresponding to the first joint after repair. For example, a repaired reconstructed bone surface model is obtained by registering the third reconstructed bone surface into the image space of the first joint by means of the transformation matrix one and registering the fourth reconstructed bone surface into the image space of the first joint by means of the transformation matrix two.
According to the technical scheme of the embodiment of the disclosure, the bone surface reconstruction is performed through the medical image of the joint with the metal prosthesis, the first bone surface model is generated, the bone surface reconstruction is performed through the medical image of the joint without the metal prosthesis on the opposite side, the second bone surface model is generated, the first bone surface model and the second bone surface model are registered, the transformation matrix is generated, the second bone surface model is transformed through the transformation matrix, and the repaired bone surface model is generated, so that the application scene of secondary operation is required for the patient implanted with the metal prosthesis, the bone anatomical structure information with good signal to noise ratio on the opposite side of the joint is effectively utilized, the problems of segmentation and reconstruction difficulty caused by the metal artifact image can be effectively solved while the accuracy is ensured, the accurate segmentation and three-dimensional reconstruction are performed on the bone structure of the patient according to the conditions, and the influence on the follow-up operation planning is reduced.
Based on the above embodiments, the method of the embodiments of the present disclosure is described below with respect to a knee joint.
Fig. 3 is a schematic diagram of another three-dimensional reconstruction method of a bone surface model according to an embodiment of the disclosure, as shown in fig. 3, the method includes:
step 301, a first medical image is acquired comprising a knee joint on one side of a user and a second medical image comprising a knee joint on the other side of the user.
Wherein, there is a metal prosthesis in one knee joint and no metal prosthesis in the other knee joint.
In this embodiment, a full-length sheet of the lower limb on both sides of the patient is acquired at the preoperative stage, and the full-length sheet is cut left and right into a first medical image on one side of the prosthetic leg and a second medical image on one side of the healthy leg.
Step 302, performing bone-surface reconstruction based on the first medical image, generating a first femur model and a first tibia model, and performing bone-surface reconstruction and flipping based on the second medical image, generating a second femur model and a second tibia model.
In this embodiment, the first medical image is cropped to delete the metal artifact region in the first medical image, the cropped first medical image is subjected to image segmentation to determine a first femur image and a first tibia image, and further, the first femur image is subjected to bone surface reconstruction to generate a first femur model, and the first tibia image is subjected to bone surface reconstruction to generate a first tibia model.
The method comprises the steps of cutting a scanned image of a prosthetic leg, removing a knee joint part image seriously affected by metal artifacts, reserving a normal image of the upper half part of a femur (namely a femoral neck and a femoral head side part), reserving a normal image of the lower half part of a tibia (namely a lower joint part), performing image segmentation on the two-part prosthetic leg lower limb image reserved after cutting, determining a first femur image and a first tibia image, and further performing bone surface three-dimensional reconstruction. Knee metal artifacts are shown, for example, in fig. 4.
In this embodiment, the second medical image is segmented, the second femur image and the second tibia image are determined, the bone surface of the second femur image is reconstructed, the candidate femur model is generated, the bone surface of the second tibia image is reconstructed, the candidate tibia model is generated, the candidate femur model is further turned left and right, the second femur model is generated, and the candidate tibia model is turned left and right, so that the second tibia model is generated.
And performing image segmentation on the second medical image by adopting a U-net deep learning segmentation model to determine a second femur image and a second tibia image.
Step 303, registering the first femur model and the second femur model to generate a first transformation matrix between the first femur model and the second femur model.
In this embodiment, a plurality of key points are selected on the first femur model, and a plurality of key points are correspondingly selected on the second femur model, and then, according to the key points on the first femur model and the key points on the second femur model, a rigid transformation matrix is solved by adopting a least square method, and according to the rigid transformation matrix, initial position information of the second femur model can be determined. Further, according to the initial position information, registering the first femur model and the second femur model by adopting an ICP algorithm to generate a first transformation matrix.
As an example, 16 keypoints are selected on the femoral neck and femoral head portion bone surface of the first femoral model, and 16 keypoints are selected on the femoral neck and femoral head portion bone surface of the second femoral model, the above keypoints being approximately the same in the respective femoral models.
Step 304, registering the first tibial model and the second tibial model to generate a second transformation matrix between the first tibial model and the second tibial model.
The implementation manner of registering the first tibia model and the second tibia model may refer to the first femur model and the second femur model, which will not be described herein.
As an example, 16 keypoints are selected in the tibial lower articular portion of the first tibial model and 16 keypoints are selected in the tibial lower articular portion of the second tibial model, the above keypoints being approximately the same in the location of the respective tibial models.
In step 305, the second femur model is transformed by the first transformation matrix, and the second tibia model is transformed by the second transformation matrix, so as to obtain a bone-plane model corresponding to the knee joint on one side.
In this embodiment, the second femoral model is registered into the prosthetic leg image space based on the first transformation matrix, and the second tibial model is registered into the prosthetic leg image space based on the second transformation matrix, and the resulting bone-plane model is taken as the reconstructed bone-plane model after repair corresponding to the above-described one-sided knee joint.
Therefore, the image processing scheme for image segmentation and three-dimensional reconstruction is provided for the condition that the metal prosthesis exists in the knee joint, specifically, the image information of healthy legs on opposite sides of the prosthesis legs is utilized by collecting the lower limb full length pieces on two sides of a patient, and the bone segmentation mask and the three-dimensional reconstruction model of the knee joint of the prosthesis legs are restored through image processing, so that the bone anatomical structure information with good signal to noise ratio on one side of the healthy legs is effectively utilized, and the problems of difficulty in segmentation and reconstruction caused by metal artifact images can be effectively solved while the accuracy is ensured.
Fig. 5 is a schematic structural diagram of a three-dimensional reconstruction device of a bone surface model according to an embodiment of the present disclosure, and as shown in fig. 5, the three-dimensional reconstruction device of a bone surface model includes: an acquisition module 51, a reconstruction module 52, a registration module 53, a generation module 54.
The acquiring module 51 is configured to acquire a first medical image including a first joint of a user, and a second medical image including a second joint of the user, where the first joint has a metal prosthesis, the second joint corresponds to the first joint, and the second joint has no metal prosthesis.
The reconstruction module 52 is configured to perform bone surface reconstruction based on the first medical image, generate a first bone surface model, and perform bone surface reconstruction and flipping based on the second medical image, generate a second bone surface model.
The registration module 53 is configured to register the first bone surface model and the second bone surface model, and generate a transformation matrix between the first bone surface model and the second bone surface model.
The generating module 54 is configured to perform a transformation process on the second bone surface model through a transformation matrix, and generate a bone surface model corresponding to the first joint.
In one embodiment of the present disclosure, the first joint and the second joint are knee joints, the first medical image and the second medical image are full-length slices of the lower limb, and the reconstruction module 52 is specifically configured to: clipping the first medical image to delete the metal artifact region in the first medical image; image segmentation is carried out on the cut first medical image, and a first femur image and a first tibia image are determined; performing bone surface reconstruction on the first femur image to generate a first femur model, and performing bone surface reconstruction on the first tibia image to generate a first tibia model.
In one embodiment of the present disclosure, the reconstruction module 52 is specifically configured to: performing image segmentation on the second medical image to determine a second femur image and a second tibia image; performing bone surface reconstruction on the second femur image to generate a candidate femur model, and performing bone surface reconstruction on the second tibia image to generate a candidate tibia model; and turning left and right the candidate femur model to generate a second femur model, and turning left and right the candidate tibia model to generate a second tibia model.
In one embodiment of the present disclosure, the registration module 53 is specifically configured to: registering the first femur model and the second femur model to generate a first transformation matrix between the first femur model and the second femur model; registering the first and second tibial models to generate a second transformation matrix between the first and second tibial models.
In one embodiment of the present disclosure, the registration module 53 is specifically configured to: registering the first bone surface model and the second bone surface model according to the preset key points on the first bone surface model and the preset key points on the second bone surface model to obtain initial position information of the second bone surface model; and registering the first bone surface model and the second bone surface model according to the initial position information to generate a transformation matrix between the first bone surface model and the second bone surface model.
The three-dimensional reconstruction device of the bone surface model provided by the embodiment of the disclosure can execute the three-dimensional reconstruction method of any bone surface model provided by the embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method. Details of the embodiments of the apparatus of the present disclosure that are not described in detail may refer to descriptions of any of the embodiments of the method of the present disclosure.
The embodiment of the disclosure also provides an electronic device, which comprises one or more processors and a memory. The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device to perform the desired functions. The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory can include, for example, random Access Memory (RAM) and/or cache memory (cache) and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer readable storage medium and a processor may execute the program instructions to implement the methods of embodiments of the present disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device may further include: input devices and output devices, which are interconnected by a bus system and/or other forms of connection mechanisms. In addition, the input device may include, for example, a keyboard, a mouse, and the like. The output device may output various information including the determined distance information, direction information, etc., to the outside. The output means may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc. In addition, the electronic device may include any other suitable components, such as a bus, input/output interface, etc., depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform any of the methods provided by the embodiments of the present disclosure.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform any of the methods provided by the embodiments of the present disclosure.
A computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for three-dimensional reconstruction of a bone-surface model, comprising:
acquiring a first medical image comprising a first joint of a user, and a second medical image comprising a second joint of the user, wherein a metal prosthesis is present in the first joint, the second joint corresponds to the first joint, and no metal prosthesis is present in the second joint;
performing bone surface reconstruction based on the first medical image, generating a first bone surface model, and performing bone surface reconstruction and overturning based on the second medical image, generating a second bone surface model;
registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model;
and performing transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint.
2. The method of claim 1, wherein the first joint and the second joint are knee joints, the first medical image and the second medical image are full-length slices of a lower limb, the performing a bone-surface reconstruction based on the first medical image, generating a first bone-surface model comprising:
clipping the first medical image to delete a metal artifact region in the first medical image;
image segmentation is carried out on the cut first medical image, and a first femur image and a first tibia image are determined;
and performing bone surface reconstruction on the first femur image to generate a first femur model, and performing bone surface reconstruction on the first tibia image to generate a first tibia model.
3. The method of claim 2, wherein the generating a second bone surface model based on the bone surface reconstruction and flipping of the second medical image comprises:
performing image segmentation on the second medical image to determine a second femur image and a second tibia image;
performing bone surface reconstruction on the second femur image to generate a candidate femur model, and performing bone surface reconstruction on the second tibia image to generate a candidate tibia model;
and turning the candidate femur model left and right to generate a second femur model, and turning the candidate tibia model left and right to generate a second tibia model.
4. The method of claim 3, wherein the registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model comprises:
registering the first femur model and the second femur model to generate a first transformation matrix between the first femur model and the second femur model;
registering the first and second tibial models to generate a second transformation matrix between the first and second tibial models.
5. The method of claim 1, wherein the registering the first bone surface model and the second bone surface model to generate a transformation matrix between the first bone surface model and the second bone surface model comprises:
registering the first bone surface model and the second bone surface model according to the preset key points on the first bone surface model and the preset key points on the second bone surface model to obtain initial position information of the second bone surface model;
and registering the first bone surface model and the second bone surface model according to the initial position information to generate a transformation matrix between the first bone surface model and the second bone surface model.
6. A three-dimensional reconstruction device for a bone surface model, comprising:
an acquisition module for acquiring a first medical image comprising a first joint of a user, and a second medical image comprising a second joint of the user, wherein a metal prosthesis is present in the first joint, the second joint corresponds to the first joint, and no metal prosthesis is present in the second joint;
the reconstruction module is used for performing bone surface reconstruction based on the first medical image, generating a first bone surface model, performing bone surface reconstruction and overturning based on the second medical image, and generating a second bone surface model;
the registration module is used for registering the first bone surface model and the second bone surface model and generating a transformation matrix between the first bone surface model and the second bone surface model;
and the generation module is used for carrying out transformation processing on the second bone surface model through the transformation matrix to generate a bone surface model corresponding to the first joint.
7. The apparatus of claim 6, wherein the first joint and the second joint are knee joints, the first medical image and the second medical image are full-length slices of the lower limb, the reconstruction module is specifically configured to:
clipping the first medical image to delete a metal artifact region in the first medical image;
image segmentation is carried out on the cut first medical image, and a first femur image and a first tibia image are determined;
and performing bone surface reconstruction on the first femur image to generate a first femur model, and performing bone surface reconstruction on the first tibia image to generate a first tibia model.
8. The apparatus of claim 6, wherein the registration module is specifically configured to:
registering the first bone surface model and the second bone surface model according to the preset key points on the first bone surface model and the preset key points on the second bone surface model to obtain initial position information of the second bone surface model;
and registering the first bone surface model and the second bone surface model according to the initial position information to generate a transformation matrix between the first bone surface model and the second bone surface model.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the three-dimensional reconstruction method of a bone-plane model according to any one of the preceding claims 1-5.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements a three-dimensional reconstruction method of a bone surface model according to any one of the preceding claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139537.5A CN116758210B (en) | 2023-02-15 | 2023-02-15 | Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139537.5A CN116758210B (en) | 2023-02-15 | 2023-02-15 | Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116758210A true CN116758210A (en) | 2023-09-15 |
| CN116758210B CN116758210B (en) | 2024-03-19 |
Family
ID=87955894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310139537.5A Active CN116758210B (en) | 2023-02-15 | 2023-02-15 | Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758210B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118892358A (en) * | 2024-07-12 | 2024-11-05 | 北京纳通医用机器人科技有限公司 | ACL stop point analysis method, device, equipment and storage medium |
| CN118941579A (en) * | 2024-07-22 | 2024-11-12 | 北京纳通医用机器人科技有限公司 | Bone image processing method, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104622572A (en) * | 2014-12-15 | 2015-05-20 | 上海昕健医疗技术有限公司 | Individual orthopedics department positioning sheet based on medical images |
| CN106264731A (en) * | 2016-10-11 | 2017-01-04 | 昆明医科大学第附属医院 | A kind of method based on point-to-point registration technique virtual knee joint single condyle replacement model construction |
| US20180318014A1 (en) * | 2017-05-03 | 2018-11-08 | Stryker European Holdings I, Llc | Methods of pose estimation of three-dimensional bone models in surgical planning a total ankle replacement |
| US20200175774A1 (en) * | 2018-12-03 | 2020-06-04 | Metal Industries Research & Development Centre | Medical image modeling system and medical image modeling method |
| CN112957126A (en) * | 2021-02-10 | 2021-06-15 | 北京长木谷医疗科技有限公司 | Deep learning-based unicondylar replacement preoperative planning method and related equipment |
| CN115358995A (en) * | 2022-08-22 | 2022-11-18 | 复旦大学 | Fully automatic spatial registration system based on multimodal information fusion |
-
2023
- 2023-02-15 CN CN202310139537.5A patent/CN116758210B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104622572A (en) * | 2014-12-15 | 2015-05-20 | 上海昕健医疗技术有限公司 | Individual orthopedics department positioning sheet based on medical images |
| CN106264731A (en) * | 2016-10-11 | 2017-01-04 | 昆明医科大学第附属医院 | A kind of method based on point-to-point registration technique virtual knee joint single condyle replacement model construction |
| US20180318014A1 (en) * | 2017-05-03 | 2018-11-08 | Stryker European Holdings I, Llc | Methods of pose estimation of three-dimensional bone models in surgical planning a total ankle replacement |
| US20200175774A1 (en) * | 2018-12-03 | 2020-06-04 | Metal Industries Research & Development Centre | Medical image modeling system and medical image modeling method |
| CN112957126A (en) * | 2021-02-10 | 2021-06-15 | 北京长木谷医疗科技有限公司 | Deep learning-based unicondylar replacement preoperative planning method and related equipment |
| CN115358995A (en) * | 2022-08-22 | 2022-11-18 | 复旦大学 | Fully automatic spatial registration system based on multimodal information fusion |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118892358A (en) * | 2024-07-12 | 2024-11-05 | 北京纳通医用机器人科技有限公司 | ACL stop point analysis method, device, equipment and storage medium |
| CN118941579A (en) * | 2024-07-22 | 2024-11-12 | 北京纳通医用机器人科技有限公司 | Bone image processing method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116758210B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5634880B2 (en) | Method for producing a customized surgical instrument or prosthesis and method for generating a patient-specific model of a body part and medium having program code therefor | |
| US9681956B2 (en) | Acquiring and utilizing kinematic information for patient-adapted implants, tools and surgical procedures | |
| White et al. | Accuracy of MRI vs CT imaging with particular reference to patient specific templates for total knee replacement surgery | |
| Grassi et al. | Evaluation of the generality and accuracy of a new mesh morphing procedure for the human femur | |
| CN116758210B (en) | Three-dimensional reconstruction method, device, equipment and storage medium for bone surface model | |
| Neubert et al. | Comparison of 3D bone models of the knee joint derived from CT and 3T MR imaging | |
| Lebailly et al. | Semi-automated stereoradiographic upper limb 3D reconstructions using a combined parametric and statistical model: a preliminary study | |
| CN110809451A (en) | Transform determination for anatomically aligning fragments of fractured bones | |
| Balwan et al. | Development of patient specific knee joint implant | |
| Asvadi et al. | Bone surface reconstruction and clinical features estimation from sparse landmarks and statistical shape models: A feasibility study on the femur | |
| KR102832501B1 (en) | Image processing methods | |
| Gomes et al. | Patient-specific modelling in orthopedics: from image to surgery | |
| Gajny et al. | Fast quasi-automated 3D reconstruction of lower limbs from low dose biplanar radiographs using statistical shape models and contour matching | |
| Viceconti et al. | An automated method to position prosthetic components within multiple anatomical spaces | |
| CN114862780B (en) | Method and device for determining femoral trochlear groove curve | |
| CN120154416A (en) | Preoperative planning methods and medical equipment | |
| CN120114173A (en) | Osteotomy planning method, device, computer equipment, storage medium and program product | |
| Eldeeb et al. | Design of thoracolumbosacral orthosis (TLSO) braces using CT/MR | |
| Pan et al. | 3d reconstruction of tibia and fibula using one general model and two x-ray images | |
| Ohnishi et al. | Robust 2D/3D registration for fast-flexion motion of the knee joint using hybrid optimization | |
| Valenti | Statistical shape models based 2D/3D registration methods for knee orthopaedic surgery | |
| Moneta | Development of an applicative model to filter outliers from intra-operative acquired data in Total Knee Replacement using Computer Assisted Surgery | |
| Hudzari et al. | Mesh convergence analysis of three-dimensional tibial bone model: A finite element method | |
| CN116681719A (en) | A Digital Knee Articular Cartilage Segmentation Method | |
| Adeeb et al. | Reza Kakavand, Mehrdad Palizi 2, Peyman Tahghighi, Reza Ahmadi, Neha Gianchandani |
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 |