CN116721062B - Method and device for determining spine registration matrix based on global optimality - Google Patents

Method and device for determining spine registration matrix based on global optimality Download PDF

Info

Publication number
CN116721062B
CN116721062B CN202310582723.6A CN202310582723A CN116721062B CN 116721062 B CN116721062 B CN 116721062B CN 202310582723 A CN202310582723 A CN 202310582723A CN 116721062 B CN116721062 B CN 116721062B
Authority
CN
China
Prior art keywords
registration
preoperative
points
intraoperative
point set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310582723.6A
Other languages
Chinese (zh)
Other versions
CN116721062A (en
Inventor
张逸凌
刘星宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Longwood Valley Medtech Co Ltd
Original Assignee
Beijing Changmugu Medical Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Changmugu Medical Technology Co Ltd filed Critical Beijing Changmugu Medical Technology Co Ltd
Priority to CN202310582723.6A priority Critical patent/CN116721062B/en
Publication of CN116721062A publication Critical patent/CN116721062A/en
Application granted granted Critical
Publication of CN116721062B publication Critical patent/CN116721062B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • 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
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G06T2207/30012—Spine; Backbone
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明提供了一种基于全局最优的脊柱配准矩阵的确定方法及装置，方法包括：提取数量相同的多个术前配准点与多个术中配准点；基于术前配准点集P和术中配准点集Q，确定优化函数中的目标特征参数；基于确定目标特征参数之后的优化函数，确定目标配准矩阵。上述方法，在提取到数量相同的术前配准点与术中配准点之后，可以确定出优化函数的目标特征参数，从而有效的过滤掉噪声点的影响，进而基于确定目标特征参数之后的优化函数，能够准确的确定出多个术前配准点与多个术中配准点对应的目标配准矩阵。基于该目标配准矩阵，在对脊柱进行配准时，能够提高配准的准确性，减小了配准过程中产生的误差，提高了配准精度，有效的保证了配准精度。

The present invention provides a method and device for determining a spine registration matrix based on global optimality. The method includes: extracting multiple preoperative registration points and multiple intraoperative registration points of the same number; based on the preoperative registration point sets P and The intraoperative registration point set Q determines the target feature parameters in the optimization function; based on the optimization function after determining the target feature parameters, the target registration matrix is determined. The above method, after extracting the same number of preoperative registration points and intraoperative registration points, can determine the target feature parameters of the optimization function, thereby effectively filtering out the influence of noise points, and then based on the optimization function after determining the target feature parameters , can accurately determine the target registration matrix corresponding to multiple preoperative registration points and multiple intraoperative registration points. Based on this target registration matrix, when registering the spine, the accuracy of registration can be improved, errors generated during the registration process can be reduced, the accuracy of registration can be improved, and the accuracy of registration can be effectively guaranteed.

Description

Global-optimization-based spine registration matrix determination method and device
Technical Field
The invention relates to the medical field, in particular to a method and a device for determining a vertebral column registration matrix based on global optimization.
Background
As the popularization of spinal surgery by using robots, the requirements on the registration accuracy before and during spinal surgery are increasing. However, there is a large uncertainty in the error in registration of the spine due to the diversity of spinal lesions. Meanwhile, because the number of the registration points in the spinal column registration process is smaller, the registration difficulty is higher than that of the common point cloud registration. Therefore, how to solve the above-mentioned problems is considered.
Disclosure of Invention
The invention provides a method and a device for determining a global optimal spine registration matrix, which are used for solving the problems.
In a first aspect, the present invention provides a method for determining a global optimal-based spinal registration matrix, comprising:
extracting a plurality of preoperative registration points and a plurality of intraoperative registration points with the same quantity, wherein the plurality of preoperative registration points form a preoperative registration point set P, the plurality of intraoperative registration points form an intraoperative registration point set Q, and the preoperative registration point set and the intraoperative registration point set form a registration point cloud set K;
determining target feature parameters in an optimization function based on a preoperative registration point set P and an intraoperative registration point set Q, wherein the optimization function is used for optimizing registration points in the registration point cloud set K;
and determining a target registration matrix based on an optimization function after determining the target characteristic parameters, wherein the target registration matrix is used for determining the correspondence between the plurality of preoperative registration points and the plurality of intraoperative registration points.
Optionally, the extracting a plurality of preoperative registration points and a plurality of intraoperative registration points, which are the same in number, includes:
and extracting a plurality of preoperative registration points and a plurality of operative points based on a point characteristic histogram algorithm PFH and a random sampling consensus algorithm RANSAC or a rapid point characteristic histogram algorithm FPFH and a random sampling consensus algorithm RANSAC to obtain a plurality of preoperative registration points and a plurality of intraoperative registration points with the same quantity.
Optionally, the optimization function is expressed in the following form:
E(T)＝∑ (p,q)∈ kρ (|p-Tq|) formula (1)
Wherein p represents a preoperative registration point, q represents an intraoperative registration point, T represents a registration matrix, and ρ (|p-tq|) represents an estimation function, which is expressed in the following form:
mu is a constant.
Alternatively, based on the dual nature, another expression of the optimization function expressed by equation (1) is as follows:
E(T,L)＝∑ (p,q)∈K l p,q ‖p-Tq‖ 2 +∑ (p,q)∈K Ψ(l p,q ) Formula (2)
Wherein,l p,q and representing the target characteristic parameters, wherein L is a set of the target characteristic parameters.
Optionally, the determining the target feature parameter in the optimization function based on the preoperative registration point set P and the intra-operative registration point set Q includes:
initializing characteristic parameters;
based on the feature parameters obtained by initialization, the preoperative registration point set P, the intraoperative registration point set Q and the formula (2), an initial registration matrix T is obtained 0 ；
Based on an initial registration matrix T 0 Initializing the obtained characteristic parameters, a preoperative registration point set P, an intraoperative registration point set Q and a formula (2) to obtain the target characteristic parameters.
Optionally, the initial registration matrix T is based on 0 Initializing the obtained characteristic parameters, a preoperative registration point set P, an intraoperative registration point set Q and a formula (2), and obtaining the target characteristic parameters, wherein the method comprises the following steps:
conducting derivation processing on the characteristic parameters, and based on results obtained by the derivation processing and the initial registration matrix T 0 Iterating the characteristic parameters and the registration matrix by the preoperative registration point set P and the intraoperative registration point set Q;
and when the characteristic parameters obtained based on the formula (2) are not converged, determining the characteristic parameters as target characteristic parameters.
Optionally, the feature parameter is subjected to derivative processing, and a result obtained by the derivative processing is expressed by the following formula:
in a second aspect, the present invention provides a device for determining a global optimal spinal registration matrix, comprising:
the extraction module is used for extracting a plurality of preoperative registration points and a plurality of intra-operative registration points with the same quantity, wherein the plurality of preoperative registration points form a preoperative registration point set P, the plurality of intra-operative registration points form an intra-operative registration point set Q, and the preoperative registration point set and the intra-operative registration point set form a registration point cloud set K;
the determining module is used for determining target characteristic parameters in an optimizing function based on a preoperative registration point set P and an intraoperative registration point set Q, wherein the optimizing function is used for optimizing registration points in the registration point cloud set K;
the determining module is further configured to determine a target registration matrix based on an optimization function after determining the target feature parameter, where the target registration matrix is used to determine correspondence between the plurality of preoperative registration points and the plurality of intra-operative registration points.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of determining a global optimal spinal registration matrix based on the above, when executing the program.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of determining a global optimal based spinal registration matrix as described above.
The technical scheme of the invention has at least the following beneficial effects:
according to the method for determining the vertebral column registration matrix based on global optimization, after the preoperative registration points and the intraoperative registration points with the same number are extracted, the target characteristic parameters of the optimization function can be determined, the influence of noise points can be effectively filtered out in the process of determining the target characteristic parameters by the optimization function, and further the target registration matrix corresponding to the preoperative registration points and the intraoperative registration points can be accurately determined based on the optimization function after the target characteristic parameters are determined. Based on the target registration matrix, when the spine is aligned, the accuracy of registration can be improved, errors generated in the registration process are reduced, the registration accuracy is improved, and the registration accuracy is effectively ensured.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a global optimum-based spinal registration matrix provided by the invention;
FIG. 2 is a block diagram of a global optimum-based determination apparatus for a spinal registration matrix according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. 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 terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.
It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, and means that three relationships may exist, for example, and/or B may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.
It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Referring to fig. 1, a flow chart of a method for determining a global optimal spine registration matrix according to the present invention includes the following steps:
s11: extracting a plurality of preoperative registration points and a plurality of intraoperative registration points with the same quantity, wherein the plurality of preoperative registration points form a preoperative registration point set P, the plurality of intraoperative registration points form an intraoperative registration point set Q, and the preoperative registration point set and the intraoperative registration point set form a registration point cloud set K.
Optionally, the number of the plurality of preoperative registration points and the plurality of intraoperative registration points is, for example, 32 or 35, respectively, that is, the number of preoperative registration points and the number of intraoperative registration points are both 32, or the number of preoperative registration points and the number of intraoperative registration points are both 35.
Specifically, the method for extracting the preoperative registration points and the intraoperative registration points with the same quantity comprises the following steps:
and extracting a plurality of preoperative registration points and a plurality of operative points based on a point characteristic histogram algorithm PFH and a random sampling consensus algorithm RANSAC or a rapid point characteristic histogram algorithm FPFH and a random sampling consensus algorithm RANSAC to obtain a plurality of preoperative registration points and a plurality of intraoperative registration points with the same quantity.
S12: and determining target feature parameters in an optimization function based on the preoperative registration point set P and the intraoperative registration point set Q, wherein the optimization function is used for optimizing registration points in the registration point cloud set K.
It should be noted that, after the registration points in the registration point cloud set K are processed by the optimization function, the number of obtained pre-operative registration points is smaller than or equal to the number of pre-operative registration points in the pre-operative registration point set P, and the number of obtained intra-operative registration points is smaller than or equal to the number of intra-operative registration points in the intra-operative registration point set Q.
S13: and determining a target registration matrix based on an optimization function after determining the target characteristic parameters, wherein the target registration matrix is used for determining the correspondence between the plurality of preoperative registration points and the plurality of intraoperative registration points.
According to the method for determining the vertebral column registration matrix based on global optimization, after the preoperative registration points and the intraoperative registration points with the same number are extracted, the target characteristic parameters of the optimization function can be determined, the influence of noise points can be effectively filtered out in the process of determining the target characteristic parameters by the optimization function, and further the target registration matrix corresponding to the preoperative registration points and the intraoperative registration points can be accurately determined based on the optimization function after the target characteristic parameters are determined. Based on the target registration matrix, when the spine is aligned, the accuracy of registration can be improved, errors generated in the registration process are reduced, the registration accuracy is improved, and the registration accuracy is effectively ensured.
Illustratively, the optimization function is expressed in the form:
E(T)＝∑ (q,p)∈K ρ(‖p-T q II) formula (1)
Wherein p represents a pre-operative registration point, q represents an intra-operative registration point, T represents a registration matrix, ρ (|p-T) q II) represents an estimation function, which is represented as follows:
mu is a constant.
Alternatively, the registration point cloud set K may be represented as k= { (P, Q) }, where P is the registration point in the preoperative registration point set P and Q is the registration point in the intraoperative registration point set Q. By introducing the estimation function ρ (|p-tq|), the influence of noise points can be effectively filtered out, resulting in better robustness. It should be noted that, μ is a curve fitting coefficient, the smaller μ is, the better the fitting effect is, the larger the influence of the iterative difference on the optimization function is, that is, the smaller μ is, the better the effect of the optimization function on filtering noise points is, preferably, μ is 0.1, and therefore the non-convex problem can be converted into the convex problem, and the accuracy of the optimization function is improved.
It should be noted that, the pre-operative registration point p and the intra-operative registration point q may be represented in the form of coordinates, for example, p= (1, 2, 3), q= (2, 3, 4), and Tq represents the product of the registration matrix T and the intra-operative registration point q.
By way of example, based on the dual nature, another representation of the optimization function represented by equation (1) is as follows:
E(T,L)＝∑ (p,q)∈K l p,q ‖p-Tq‖ 2 +∑ (p,q)∈K Ψ(l p,p ) Formula (2)
Wherein,l p,q and representing the target characteristic parameters, wherein L is a set of the target characteristic parameters.
Alternatively, L is expressed in the form of l= { p, q }, i.e. L is L p,q { p, q } is a set of corresponding pre-operative registration points and intra-operative registration points.
Illustratively, the determining the target feature parameter in the optimization function based on the preoperative registration point set P and the intraoperative registration point set Q includes:
initializing characteristic parameters;
the feature parameter may be initialized, for example, by setting an initial value of the feature parameter to 1.
Based on the feature parameters obtained by initialization, the preoperative registration point set P, the intraoperative registration point set Q and the formula (2), an initial registration matrix T is obtained 0 ；
It should be noted that, since the value of the initialized feature parameter, the coordinates of each preoperative registration point in the preoperative registration point set P, and the coordinates of each intraoperative registration point in the intraoperative registration point set Q are all known, and μ=0.1, let the value of formula (2) be 0, the initial registration matrix T can be calculated 0 。
Based on an initial registration matrix T 0 Initializing the obtained characteristic parameters, the preoperative registration point set P, the intraoperative registration point set Q and the formula (2) to obtainThe target characteristic parameter.
Specifically, the initial registration matrix T is based on 0 Initializing the obtained characteristic parameters, a preoperative registration point set P, an intraoperative registration point set Q and a formula (2), and obtaining the target characteristic parameters, wherein the method comprises the following steps:
conducting derivation processing on the characteristic parameters, and based on results obtained by the derivation processing and the initial registration matrix T 0 Iterating the characteristic parameters and the registration matrix by the preoperative registration point set P and the intraoperative registration point set Q;
and when the characteristic parameters obtained based on the formula (2) are not converged, determining the characteristic parameters as target characteristic parameters.
Optionally, the feature parameters are subjected to derivative processing, and the calculation mode is as follows:the result obtained by the derivation process is expressed by the following formula:
due to the registration matrix T 0 The coordinates of each preoperative registration point in the set of preoperative registration points P, the coordinates of each intraoperative registration point in the set of intraoperative registration points Q, and μ are all known, and therefore, based on equation (2), an iterative feature parameter l can be derived p,q . After obtaining iterative characteristic parameter l p,q Then, let the value of equation (2) be 0, based on the iterative characteristic parameter l p,q An iterative registration matrix is obtained. In the characteristic parameter l p,q After a plurality of iterations, the characteristic parameter l p,q And tending to a fixed value, i.e. the characteristic parameter no longer converges, at which point the characteristic parameter is determined to be the target characteristic parameter.
Referring next to fig. 2, based on the same technical concept as the above method, another embodiment of the present invention provides a determination device based on a globally optimal spinal registration matrix, which has the same function as the above method, and will not be described herein. The global optimum-based spine registration matrix determining device comprises:
an extracting module 21, configured to extract a plurality of preoperative registration points and a plurality of intra-operative registration points that are the same in number, where the plurality of preoperative registration points form a preoperative registration point set P, the plurality of intra-operative registration points form an intra-operative registration point set Q, and the preoperative registration point set and the intra-operative registration point set form a registration point cloud set K;
a determining module 22, configured to determine a target feature parameter in an optimization function based on a preoperative registration point set P and an intra-operative registration point set Q, where the optimization function is configured to perform optimization processing on registration points in the registration point cloud set K;
the determining module 22 is further configured to determine a target registration matrix, based on the optimization function after determining the target feature parameter, where the target registration matrix is used to determine correspondence between the plurality of preoperative registration points and the plurality of intra-operative registration points.
Optionally, the extracting module 21 is specifically configured to, when extracting a plurality of preoperative registration points and a plurality of intraoperative registration points with the same number:
and extracting a plurality of preoperative registration points and a plurality of operative points based on a point characteristic histogram algorithm PFH and a random sampling consensus algorithm RANSAC or a rapid point characteristic histogram algorithm FPFH and a random sampling consensus algorithm RANSAC to obtain a plurality of preoperative registration points and a plurality of intraoperative registration points with the same quantity.
Optionally, the optimization function is expressed in the following form:
E(T)＝∑ (p,q)∈K ρ (|p-Tq|) formula (1)
Wherein p represents a preoperative registration point, q represents an intraoperative registration point, T represents a registration matrix, and ρ (|p-tq|) represents an estimation function, which is expressed in the following form:
mu is a constant.
Alternatively, based on the dual nature, another expression of the optimization function expressed by equation (1) is as follows:
E(T,L)＝∑ (p,q)∈K l p,q ‖p-Tq‖ 2 +∑ (p,q)∈K Ψ(l p,q ) Formula (2)
Wherein,l p,q and representing the target characteristic parameters, wherein L is a set of the target characteristic parameters.
Optionally, the determining module 22 is specifically configured to, when determining the target feature parameter in the optimization function based on the preoperative registration point set P and the intra-operative registration point set Q:
initializing characteristic parameters;
based on the feature parameters obtained by initialization, the preoperative registration point set P, the intraoperative registration point set Q and the formula (2), an initial registration matrix T is obtained 0 ；
Based on an initial registration matrix T 0 Initializing the obtained characteristic parameters, a preoperative registration point set P, an intraoperative registration point set Q and a formula (2) to obtain the target characteristic parameters.
Optionally, the determining module 22 is based on an initial registration matrix T 0 Initializing the obtained characteristic parameters, a preoperative registration point set P, an intraoperative registration point set Q and a formula (2), wherein the method is specifically used for:
conducting derivation processing on the characteristic parameters, and based on results obtained by the derivation processing and the initial registration matrix T 0 Iterating the characteristic parameters and the registration matrix by the preoperative registration point set P and the intraoperative registration point set Q;
and when the characteristic parameters obtained based on the formula (2) are not converged, determining the characteristic parameters as target characteristic parameters.
Optionally, the feature parameter is subjected to derivative processing, and a result obtained by the derivative processing is expressed by the following formula:
referring next to fig. 3, a schematic entity structure of an electronic device according to the present invention may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. Processor 310 may invoke logic instructions in memory 330 to perform the determination method based on the globally optimal spinal registration matrix provided by the methods described above.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Another embodiment of the invention provides a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method of determining a global optimum-based spinal registration matrix as described above.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Note that all features disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Thus, unless expressly stated otherwise, each feature disclosed is one example only of a generic set of equivalent or similar features. Where used, further, preferably, still further and preferably, the brief description of the other embodiment is provided on the basis of the foregoing embodiment, and further, preferably, further or more preferably, the combination of the contents of the rear band with the foregoing embodiment is provided as a complete construct of the other embodiment. A further embodiment is composed of several further, preferably, still further or preferably arrangements of the strips after the same embodiment, which may be combined arbitrarily.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are by way of example only and are not limiting. The objects of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been shown and described in the examples and embodiments of the invention may be modified or practiced without departing from the principles described.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present disclosure, and not for limiting the same; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present disclosure.

Claims (9)

1.一种基于全局最优的脊柱配准矩阵的确定方法，其特征在于，包括：1. A method for determining the spine registration matrix based on global optimality, which is characterized by including: 提取数量相同的多个术前配准点与多个术中配准点，其中，所述多个术前配准点组成术前配准点集P，所述多个术中配准点组成术中配准点集Q，所述术前配准点集与所述术中配准点集组成配准点云集合K；Extract multiple preoperative registration points and multiple intraoperative registration points with the same number, wherein the multiple preoperative registration points form a preoperative registration point set P, and the multiple intraoperative registration points form an intraoperative registration point set Q, the preoperative registration point set and the intraoperative registration point set form a registration point cloud set K; 基于术前配准点集P和术中配准点集Q，确定优化函数中的目标特征参数，其中，所述优化函数用于对所述配准点云集合K中的配准点进行优化处理；Based on the preoperative registration point set P and the intraoperative registration point set Q, determine the target characteristic parameters in the optimization function, wherein the optimization function is used to optimize the registration points in the registration point cloud set K; 基于确定所述目标特征参数之后的优化函数，确定目标配准矩阵，其中，所述目标配准矩阵，用于确定所述多个术前配准点与所述多个术中配准点之间的对应关系；Based on the optimization function after determining the target characteristic parameters, a target registration matrix is determined, wherein the target registration matrix is used to determine the distance between the plurality of preoperative registration points and the plurality of intraoperative registration points. Correspondence; 所述优化函数用如下形式表示：The optimization function is expressed in the following form: E(T)＝∑(p，q)∈Kρ(||p-Tq||) 公式(1)E(T)＝∑ (p, q)∈K ρ(||p-Tq||) Formula (1) 其中，p表示术前配准点，q表示术中配准点，T表示配准矩阵，ρ(‖p-Tq‖)表示估计函数，其表示形式如下：Among them, p represents the preoperative registration point, q represents the intraoperative registration point, T represents the registration matrix, ρ(‖p-Tq‖) represents the estimation function, and its expression is as follows: μ为常数。 μ is a constant. 2.根据权利要求1所述的基于全局最优的脊柱配准矩阵的确定方法，其特征在于，所述提取数量相同的多个术前配准点与多个术中配准点，包括：2. The method for determining a spine registration matrix based on global optimality according to claim 1, characterized in that the extraction of multiple preoperative registration points and multiple intraoperative registration points with the same number includes: 基于点特征直方图算法PFH与随机采样一致算法RANSAC或者快速点特征直方图算法FPFH与随机采样一致算法RANSAC，对多个术前配准点与多个术中点进行提取，得到数量相同的多个术前配准点与多个术中配准点。Based on the point feature histogram algorithm PFH and the random sampling consensus algorithm RANSAC or the fast point feature histogram algorithm FPFH and the random sampling consensus algorithm RANSAC, multiple preoperative registration points and multiple intraoperative points are extracted to obtain multiple identical numbers. Preoperative registration points versus multiple intraoperative registration points. 3.根据权利要求1所述的基于全局最优的脊柱配准矩阵的确定方法，其特征在于，基于对偶性质，公式(1)所表示的优化函数的另一种表示形式如下：3. The method for determining the spine registration matrix based on global optimality according to claim 1, characterized in that, based on the duality property, another expression form of the optimization function represented by formula (1) is as follows: E(T，L)＝Σ(p，q)∈Klp，q||p-Tq||2+Σ(p，q)∈KΨ(lp，q)， 公式(2)E(T, L)＝Σ (p, q)∈K l p, q ||p-Tq|| 2 +Σ (p, q)∈K Ψ(l p, q ), formula (2) 其中，lp,q表示所述目标特征参数，L为目标特征参数的集合。in, l p, q represent the target feature parameters, and L is a set of target feature parameters. 4.根据权利要求3所述的基于全局最优的脊柱配准矩阵的确定方法，其特征在于，所述基于术前配准点集P和术中配准点集Q，确定优化函数中的目标特征参数，包括：4. The method for determining the spine registration matrix based on global optimality according to claim 3, characterized in that the target characteristics in the optimization function are determined based on the preoperative registration point set P and the intraoperative registration point set Q. Parameters, including: 初始化特征参数；Initialize feature parameters; 基于初始化得到的特征参数、术前配准点集P、术中配准点集Q与公式(2)，得到初始配准矩阵T0；Based on the initialized characteristic parameters, the preoperative registration point set P, the intraoperative registration point set Q and formula (2), the initial registration matrix T 0 is obtained; 基于初始配准矩阵T0、初始化得到的特征参数、术前配准点集P、术中配准点集Q与公式(2)，得到所述目标特征参数。Based on the initial registration matrix T 0 , the initialized characteristic parameters, the preoperative registration point set P, the intraoperative registration point set Q and formula (2), the target characteristic parameters are obtained. 5.根据权利要求4所述的基于全局最优的脊柱配准矩阵的确定方法，其特征在于，所述基于初始配准矩阵T0、初始化得到的特征参数、术前配准点集P、术中配准点集Q与公式(2)，得到所述目标特征参数，包括：5. The method for determining the spine registration matrix based on global optimality according to claim 4, characterized in that the method is based on the initial registration matrix T0 , the characteristic parameters obtained by initialization, the preoperative registration point set P, the surgical By registering the point set Q and formula (2), the target characteristic parameters are obtained, including: 对特征参数进行求导处理，并基于求导处理得到的结果与所述初始配准矩阵T0、术前配准点集P以及术中配准点集Q对所述特征参数以及配准矩阵进行迭代；Perform derivation processing on the characteristic parameters, and iterate the characteristic parameters and the registration matrix based on the results obtained by the derivation processing and the initial registration matrix T 0 , the preoperative registration point set P and the intraoperative registration point set Q ; 在基于公式(2)得到的特征参数不再收敛时，则确定该特征参数为目标特征参数。When the characteristic parameter obtained based on formula (2) no longer converges, the characteristic parameter is determined to be the target characteristic parameter. 6.根据权利要求5所述的基于全局最优的脊柱配准矩阵的确定方法，其特征在于，对所述特征参数进行求导处理，求导处理得到的结果用如下公式表示：6. The method for determining the spine registration matrix based on global optimality according to claim 5, characterized in that the characteristic parameters are derivation processed, and the result obtained by the derivation process is expressed by the following formula: 7.一种基于全局最优的脊柱配准矩阵的确定装置，其特征在于，包括：7. A device for determining a spine registration matrix based on global optimality, characterized by including: 提取模块，用于提取数量相同的多个术前配准点与多个术中配准点，其中，所述多个术前配准点组成术前配准点集P，所述多个术中配准点组成术中配准点集Q，所述术前配准点集与所述术中配准点集组成配准点云集合K；The extraction module is used to extract multiple preoperative registration points and multiple intraoperative registration points of the same number, wherein the multiple preoperative registration points constitute a preoperative registration point set P, and the multiple intraoperative registration points constitute Intraoperative registration point set Q, the preoperative registration point set and the intraoperative registration point set form a registration point cloud set K; 确定模块，用于基于术前配准点集P和术中配准点集Q，确定优化函数中的目标特征参数，其中，所述优化函数用于对所述配准点云集合K中的配准点进行优化处理；Determining module, used to determine the target characteristic parameters in the optimization function based on the preoperative registration point set P and the intraoperative registration point set Q, wherein the optimization function is used to perform registration points in the registration point cloud set K Optimization processing; 确定模块，还用于基于确定所述目标特征参数之后的优化函数，确定目标配准矩阵，其中，所述目标配准矩阵，用于确定所述多个术前配准点与所述多个术中配准点之间的对应关系；The determination module is further configured to determine a target registration matrix based on the optimization function after determining the target characteristic parameters, wherein the target registration matrix is used to determine the relationship between the multiple preoperative registration points and the multiple surgical registration points. Correspondence between registration points; 所述优化函数用如下形式表示：The optimization function is expressed in the following form: E(T)＝∑(p,q)∈Kρ(||p-Tq||) 公式(1)E(T)＝∑ (p,q)∈K ρ(||p-Tq||) Formula (1) 其中，p表示术前配准点，q表示术中配准点，T表示配准矩阵，ρ(‖p-Tq‖)表示估计函数，其表示形式如下：Among them, p represents the preoperative registration point, q represents the intraoperative registration point, T represents the registration matrix, ρ(‖p-Tq‖) represents the estimation function, and its expression is as follows: μ为常数。 μ is a constant. 8.一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现如权利要求1至6任一项所述的基于全局最优的脊柱配准矩阵的确定方法。8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the program, it implements claim 1 The method for determining the spine registration matrix based on the global optimal as described in any one of to 6. 9.一种非暂态计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述的基于全局最优的脊柱配准矩阵的确定方法。9. A non-transitory computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the global optimal method as described in any one of claims 1 to 6 is realized. Determination method of spine registration matrix.
CN202310582723.6A 2023-05-22 2023-05-22 Method and device for determining spine registration matrix based on global optimality Active CN116721062B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310582723.6A CN116721062B (en) 2023-05-22 2023-05-22 Method and device for determining spine registration matrix based on global optimality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310582723.6A CN116721062B (en) 2023-05-22 2023-05-22 Method and device for determining spine registration matrix based on global optimality

Publications (2)

Publication Number Publication Date
CN116721062A CN116721062A (en) 2023-09-08
CN116721062B true CN116721062B (en) 2024-02-20

Family

ID=87865162

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310582723.6A Active CN116721062B (en) 2023-05-22 2023-05-22 Method and device for determining spine registration matrix based on global optimality

Country Status (1)

Country Link
CN (1) CN116721062B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111415379A (en) * 2020-03-23 2020-07-14 南京大学 Three-dimensional point cloud data registration method based on cuckoo optimization
CN114387319A (en) * 2022-01-13 2022-04-22 北京百度网讯科技有限公司 Point cloud registration method, device, equipment and storage medium
CN114419118A (en) * 2022-01-24 2022-04-29 安徽酷哇机器人有限公司 Three-dimensional point cloud registration method, mobile device and storage medium
CN115471531A (en) * 2022-08-31 2022-12-13 广东工业大学 A method and system for evaluating robot self-positioning accuracy based on vision sensors
CN115797419A (en) * 2022-10-28 2023-03-14 五邑大学 Point cloud registration method, device and medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111415379A (en) * 2020-03-23 2020-07-14 南京大学 Three-dimensional point cloud data registration method based on cuckoo optimization
CN114387319A (en) * 2022-01-13 2022-04-22 北京百度网讯科技有限公司 Point cloud registration method, device, equipment and storage medium
CN114419118A (en) * 2022-01-24 2022-04-29 安徽酷哇机器人有限公司 Three-dimensional point cloud registration method, mobile device and storage medium
CN115471531A (en) * 2022-08-31 2022-12-13 广东工业大学 A method and system for evaluating robot self-positioning accuracy based on vision sensors
CN115797419A (en) * 2022-10-28 2023-03-14 五邑大学 Point cloud registration method, device and medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
基于FPFH特征的三维场景重建;艾达;王苗;倪国斌;;计算机测量与控制(07);全文 *
基于ICP算法的手术导航三维配准技术;王君臣;王田苗;徐源;方礼明;;北京航空航天大学学报(04);全文 *
采用轮廓特征匹配的红外-可见光视频自动配准;孙兴龙;韩广良;郭立红;刘培勋;许廷发;;光学精密工程(05);全文 *

Also Published As

Publication number Publication date
CN116721062A (en) 2023-09-08

Similar Documents

Publication Publication Date Title
JP6099793B2 (en) Method and system for automatic selection of one or more image processing algorithms
US10430518B2 (en) Word vector processing for foreign languages
CN113505848B (en) Model training method and device
CN110378966A (en) Camera extrinsic scaling method, device, computer equipment and storage medium
CN108064385A (en) Compare extracted user name and the user data stored
JP6158882B2 (en) Generating device, generating method, and generating program
CN112580324A (en) Text error correction method and device, electronic equipment and storage medium
US20170323149A1 (en) Rotation invariant object detection
EP3673386A1 (en) Edit script verification with match operations and difference operations
US12153710B2 (en) Synthetic data generation
WO2018225291A1 (en) Computer system, secret information verification method, and computer
CN116503595B (en) Instance segmentation method, device and storage medium based on point supervision
CN108985190A (en) Target identification method and device, electronic equipment, storage medium, program product
CN111368860B (en) Repositioning method and terminal equipment
CN116721062B (en) Method and device for determining spine registration matrix based on global optimality
CN110598771A (en) Visual target identification method and device based on deep semantic segmentation network
CN113963166A (en) Training method and device of feature extraction model and electronic equipment
CN115294396B (en) Backbone network training method and image classification method
CN110275991B (en) Hash value determination method and device, storage medium and electronic device
US20220415481A1 (en) Mesh topology adaptation
WO2022134338A1 (en) Domain adaptation method and apparatus, electronic device, and storage medium
CN112991451A (en) Image recognition method, related device and computer program product
CN111353039B (en) File category detection method and device
CN115311351B (en) Visual map update methods, devices, electronic devices and storage media
CN115034255A (en) Signal modulation identification algorithm with attention mechanism time convolution network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20251118

Address after: 101100 Building 19, Courtyard 3, Jinghai Fifth Road, Tongzhou District, Beijing

Patentee after: Beijing Changmugu Medical Technology Co.,Ltd.

Country or region after: China

Address before: 100176 2201, 22 / F, building 1, yard 2, Ronghua South Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing

Patentee before: Beijing Changmugu Medical Technology Co.,Ltd.

Country or region before: China

Patentee before: Zhang Yiling

TR01 Transfer of patent right