WO2022141368A1 - 医学轮廓数据的全局法向量一致性调整方法和装置 - Google Patents

医学轮廓数据的全局法向量一致性调整方法和装置 Download PDF

Info

Publication number
WO2022141368A1
WO2022141368A1 PCT/CN2020/142019 CN2020142019W WO2022141368A1 WO 2022141368 A1 WO2022141368 A1 WO 2022141368A1 CN 2020142019 W CN2020142019 W CN 2020142019W WO 2022141368 A1 WO2022141368 A1 WO 2022141368A1
Authority
WO
WIPO (PCT)
Prior art keywords
normal vector
medical
contour
spline curve
vector
Prior art date
Application number
PCT/CN2020/142019
Other languages
English (en)
French (fr)
Inventor
胡尊亭
闫浩
Original Assignee
西安大医集团股份有限公司
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 西安大医集团股份有限公司 filed Critical 西安大医集团股份有限公司
Priority to PCT/CN2020/142019 priority Critical patent/WO2022141368A1/zh
Priority to CN202080108424.3A priority patent/CN116917948A/zh
Publication of WO2022141368A1 publication Critical patent/WO2022141368A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects

Definitions

  • the present application mainly relates to the technical field of surface reconstruction, and in particular relates to a method and device for adjusting the consistency of global normal vectors of medical contour data.
  • Surface reconstruction means that discrete measurement data can be reconstructed into a continuously changing surface through modeling.
  • 3D surface reconstruction in terms of processing data, it can be divided into the reconstruction of scattered point clouds and the reconstruction of parallel contour data such as topographic maps and medical slice images; in terms of reconstruction methods, it can be divided into explicit and Implicit.
  • Delaunay triangulation is a common explicit method for scattered point clouds, which is used to generate accurate interpolated surfaces, but because this technique is not robust to noise, and for sparse datasets, the generated surfaces will have holes.
  • Scattered point cloud implicit methods are divided into global methods and local methods.
  • the global method usually defines the implicit function as the sum of the radial basis functions centered on the point, and the local method estimates the tangent plane and defines the implicit function to the nearest point.
  • the directed point set refers to the normal vectors that are uniformly toward the outside of the surface or toward the inside of the surface, and the consistent normal vector estimation is the basis for surface reconstruction.
  • the existing algorithm is prone to the normal vector adjustment error, which makes the normal vector inconsistent, and is prone to inferior and redundant pseudo meshes, and the 3D surface reconstruction effect is not good.
  • the present application provides a method and device for adjusting the consistency of the global normal vector of medical contour data, which adjusts the consistency of the global normal vector of the medical contour data and improves the accuracy of three-dimensional surface reconstruction.
  • the present application provides a method for adjusting the consistency of global normal vectors of medical contour data, the method comprising:
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the obtaining medical contour data of the target object includes:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the acquiring the normal vector of the spline curve of the medical contour data includes:
  • the spline curve tangent vector of the medical contour data is acquired, and the spline curve normal vector of the medical contour data is determined according to the relationship between the preset spline curve tangent vector and the spline curve normal vector.
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the obtaining of the spline tangent vector of the target contour point includes:
  • determining the spline normal vector of the target contour point according to the preset relationship between the spline tangent vector and the spline normal vector including:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the acquisition of the spline tangent vector of the target contour point includes:
  • determining the spline normal vector of the target contour point according to the preset relationship between the spline tangent vector and the spline normal vector including:
  • the mid-perpendicular line between the target contour point and the adjacent contour points is used as the normal vector of the spline curve of the target contour point.
  • the acquiring the normal vector of the spline curve of the medical contour data includes:
  • the spline curve normal vector of the medical contour data is obtained.
  • the normal vector of each spline curve in the normal vector of the first spline curve is adjusted to face the outer side of the contour of the medical contour data, so as to obtain the second normal vector of the spline curve, include:
  • the second spline curve normal vector is obtained.
  • the judging whether the direction of the normal vector of the target spline curve is toward the outer side of the contour of the medical contour data includes:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the obtaining the plane normal vector of the plane where the medical contour data is located includes:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the obtaining, according to the second spline curve normal vector, the spline curve normal vector of the medical contour data includes:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the spline curve normal vector of the medical contour data is obtained:
  • the verification of the validity of the spline curve normal vector in the second spline curve normal vector to obtain the spline curve normal vector of the medical contour data includes:
  • angle adjustment is performed on the target normal vector to be adjusted so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline normal vector of the medical contour data is obtained.
  • the adjusting the global normal vector according to the spline curve normal vector to obtain a consistent global normal vector including:
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the present application provides a method for reconstructing medical contour data, the method comprising:
  • the obtaining medical contour data of the target object includes:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the acquiring the normal vector of the spline curve of the medical contour data includes:
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the obtaining of the spline tangent vector of the target contour point includes:
  • determining the spline normal vector of the target contour point according to the preset relationship between the spline tangent vector and the spline normal vector including:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the obtaining of the spline tangent vector of the target contour point includes:
  • determining the spline normal vector of the target contour point according to the preset relationship between the spline tangent vector and the spline normal vector including:
  • the mid-perpendicular line of the target contour point and the adjacent contour points is used as the spline normal vector of the target contour point.
  • the acquiring the normal vector of the spline curve of the medical contour data includes:
  • the spline curve normal vector of the medical contour data is obtained.
  • the normal vector of each spline curve in the normal vector of the first spline curve is adjusted to face the outer side of the contour of the medical contour data, so as to obtain the second normal vector of the spline curve, include:
  • the second spline curve normal vector is obtained.
  • the judging whether the direction of the normal vector of the target spline curve is toward the outer side of the contour of the medical contour data includes:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the obtaining the plane normal vector of the plane where the medical contour data is located includes:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the obtaining, according to the second spline curve normal vector, the spline curve normal vector of the medical contour data includes:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the spline curve normal vector of the medical contour data is obtained:
  • the verification of the validity of the spline curve normal vector in the second spline curve normal vector to obtain the spline curve normal vector of the medical contour data includes:
  • angle adjustment is performed on the target normal vector to be adjusted so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline normal vector of the medical contour data is obtained.
  • the global normal vector is adjusted according to the spline curve normal vector to obtain an adjusted global normal vector
  • surface reconstruction is performed according to the adjusted global normal vector to obtain the Surface reconstruction model of the target object, including:
  • Surface reconstruction is performed according to the adjusted global normal vector to obtain a surface reconstruction model of the target object.
  • the present application provides a global normal vector consistency adjustment device for medical contour data, the device comprising:
  • a first acquiring unit used for acquiring medical contour data of the target object
  • the second acquisition unit is used to acquire the global normal vector of the medical contour data
  • a third acquiring unit used for acquiring the spline curve normal vector of the medical contour data
  • An adjustment unit configured to adjust the global normal vector according to the spline curve normal vector to obtain a consistent global normal vector.
  • the first obtaining unit is specifically configured to:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the third obtaining unit is specifically configured to:
  • the spline curve tangent vector of the medical contour data is acquired, and the spline curve normal vector of the medical contour data is determined according to the relationship between the preset spline curve tangent vector and the spline curve normal vector.
  • the third obtaining unit is specifically configured to:
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the third obtaining unit is specifically configured to:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the third obtaining unit is specifically configured to:
  • the mid-perpendicular line between the target contour point and the adjacent contour points is used as the normal vector of the spline curve of the target contour point.
  • the third obtaining unit is specifically configured to:
  • the spline curve normal vector of the medical contour data is obtained.
  • the third obtaining unit is specifically configured to:
  • the second spline curve normal vector is obtained.
  • the third obtaining unit is specifically configured to:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the third obtaining unit is specifically configured to:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the third obtaining unit is specifically configured to:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the third obtaining unit is specifically configured to:
  • the third obtaining unit is specifically configured to:
  • angle adjustment is carried out to the target normal vector to be adjusted, so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline normal vector of the medical contour data is obtained.
  • the adjustment unit is specifically used for:
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the present application provides an apparatus for reconstructing medical contour data, the apparatus comprising:
  • a first acquiring unit used for acquiring medical contour data of the target object
  • the second acquisition unit is used to acquire the global normal vector of the medical contour data
  • a third acquiring unit used for acquiring the spline curve normal vector of the medical contour data
  • a reconstruction unit configured to adjust the global normal vector according to the spline curve normal vector to obtain the adjusted global normal vector, and perform surface reconstruction according to the adjusted global normal vector to obtain the surface of the target object Refactor the model.
  • the first obtaining unit is specifically configured to:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the third obtaining unit is specifically configured to:
  • the spline curve tangent vector of the medical contour data is acquired, and the spline curve normal vector of the medical contour data is determined according to the relationship between the preset spline curve tangent vector and the spline curve normal vector.
  • the third obtaining unit is specifically configured to:
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the third obtaining unit is specifically configured to:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the third obtaining unit is specifically configured to:
  • the mid-perpendicular line between the target contour point and the adjacent contour points is used as the normal vector of the spline curve of the target contour point.
  • the third obtaining unit is specifically configured to:
  • the spline curve normal vector of the medical contour data is obtained.
  • the third obtaining unit is specifically configured to:
  • the second spline curve normal vector is obtained.
  • the third obtaining unit is specifically configured to:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the third obtaining unit is specifically configured to:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the third obtaining unit is specifically configured to:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the third obtaining unit is specifically configured to:
  • the third obtaining unit is specifically configured to:
  • angle adjustment is performed on the target normal vector to be adjusted so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline normal vector of the medical contour data is obtained.
  • the reconstruction unit is specifically used for:
  • Surface reconstruction is performed according to the adjusted global normal vector to obtain a surface reconstruction model of the target object.
  • the present application provides a computer device, the computer device comprising:
  • processors one or more processors
  • One or more application programs wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the globalization of the medical contour data of any one of the first aspects
  • the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute any one of the first aspects. Steps in a method for adjusting the consistency of global normal vectors of medical contour data, or steps in a method for reconstructing medical contour data according to any one of the second aspects.
  • the method and device for adjusting the consistency of the global normal vector of medical contour data provided by the present application, by acquiring the normal vector of the spline curve of the medical contour data, and using the normal vector of the spline curve as the reference direction for adjusting the global normal vector, the global normal vector is adjusted. Consistency adjustment, the adjusted global normal vector can be used for medical contour data reconstruction, and a 3D surface reconstruction model with clearer details and smoother surface can be obtained.
  • the global normal vectors of the medical contour data are adjusted consistently, the accuracy of the three-dimensional surface reconstruction is improved, and the three-dimensional surface reconstruction effect with smooth surface and intact details is obtained.
  • FIG. 1 is a schematic diagram of a scenario of a system for adjusting the consistency of global normal vectors of medical contour data provided by an embodiment of the present application;
  • FIG. 2 is a schematic flowchart of an embodiment of a method for adjusting the consistency of global normal vectors of medical contour data provided in an embodiment of the present application;
  • FIG. 3 is a schematic flowchart of an embodiment of acquiring medical contour data of a target object in the embodiment of the present application
  • FIG. 4 is a schematic flowchart of an embodiment of obtaining the normal vector of the spline curve of the medical contour data in the embodiment of the present application;
  • FIG. 5 is a schematic flowchart of an embodiment of a method for reconstructing medical contour data provided in an embodiment of the present application
  • FIG. 6 is a schematic structural diagram of an embodiment of an apparatus for adjusting the consistency of global normal vectors of medical contour data provided in an embodiment of the present application;
  • FIG. 7 is a schematic structural diagram of an embodiment of an apparatus for reconstructing medical contour data provided in an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an embodiment of a computer device provided in an embodiment of the present application.
  • first and second are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, features defined as “first”, “second” may expressly or implicitly include one or more of said features. In the description of the present application, “plurality” means two or more, unless otherwise expressly and specifically defined.
  • Point cloud data refers to a set of vectors in a three-dimensional coordinate system. These vectors are usually expressed in the form of (X, Y, Z) three-dimensional coordinates, and are generally mainly used to represent the outer surface shape of an object. In addition to representing geometric location information, point cloud data can also represent the RGB color, gray value, depth, and segmentation results of a point.
  • Embodiments of the present application provide a method and device for adjusting the consistency of global normal vectors of medical contour data, which will be described in detail below.
  • FIG. 1 is a schematic diagram of a scene of a system for adjusting the global normal vector consistency of medical contour data provided by an embodiment of the application.
  • the global normal vector consistency adjusting system for medical contour data may include an imaging apparatus 100 and computer equipment. 200 , the imaging apparatus 100 is connected in communication with the computer equipment 200 , and the imaging apparatus 100 can transmit data to the computer equipment 200 , such as the imaging apparatus 100 in FIG. 1 .
  • the imaging device 100 may be a computed tomography (Computed Tomography, CT), a magnetic resonance (Magnetic Resonance, MR), a B-scan ultrasonography (B-scanultrasonography), or other imaging equipment, etc., which is not specifically limited here.
  • computed tomography Computed Tomography, CT
  • magnetic resonance Magnetic Resonance
  • B-scanultrasonography B-scanultrasonography
  • the computer device 200 may be an independent server, or may be a server network or server cluster composed of servers.
  • the computer device 200 described in the embodiments of the present application includes but is not limited to computers, network A host, a single web server, a set of multiple web servers, or a cloud server consisting of multiple servers.
  • the cloud server is composed of a large number of computers or network servers based on cloud computing (Cloud Computing).
  • the above-mentioned computer device 200 may be a general-purpose computer device or a special-purpose computer device.
  • the computer device 200 may be a desktop computer, a portable computer, a network server, a PDA (Personal Digital Assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc.
  • PDA Personal Digital Assistant
  • This embodiment does not limit the computer Type of device 200
  • communication between the imaging apparatus 100 and the computer device 200 may be implemented in any communication manner, including but not limited to, based on the 3rd Generation Partnership Project (3rd Generation Partnership Project, 3GPP), Long Term Evolution (Long Term Evolution, LTE), Mobile communication of Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on TCP/IP protocol suite (TCP/IP Protocol Suite, TCP/IP), User Datagram Protocol (User Datagram Protocol, UDP), etc.
  • 3rd Generation Partnership Project 3rd Generation Partnership Project, 3GPP
  • Long Term Evolution Long Term Evolution
  • LTE Long Term Evolution
  • WiMAX Worldwide Interoperability for Microwave Access
  • TCP/IP protocol suite TCP/IP Protocol Suite, TCP/IP
  • User Datagram Protocol User Datagram Protocol
  • UDP User Datagram Protocol
  • FIG. 1 is only one application scenario of the solution of the present application, and does not constitute a limitation to the application scenario of the solution of the present application.
  • Other application environments may also include more than those shown in FIG. More or less computer devices are shown, for example, only one computer device is shown in FIG. 1.
  • the global normal vector consistency adjustment system for medical contour data may also include one or more other data processing devices.
  • Computer equipment which is not specifically limited here.
  • the global normal vector consistency adjustment system for medical contour data may further include a memory 300 for storing data, such as medical image data, such as medical image data collected by the imaging device 100 .
  • FIG. 1 the schematic diagram of the scene of the system for adjusting the global normal vector consistency of medical contour data shown in FIG. 1 is only an example. Explaining the technical solutions of the embodiments of the present application more clearly does not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that, with the evolution of the global normal vector consistency adjustment system for medical contour data and the When a new business scenario emerges, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
  • an embodiment of the present application provides a method for adjusting the consistency of global normal vectors of medical contour data, including: obtaining medical contour data of a target object; obtaining a global normal vector of the medical contour data; spline curve normal vector; adjust the global normal vector according to the spline curve normal vector to obtain a consistent global normal vector.
  • FIG. 2 it is a schematic flowchart of an embodiment of the method for adjusting the consistency of the global normal vector of medical contour data in the embodiment of the present application.
  • the method for adjusting the consistency of the global normal vector of the medical contour data includes the following steps 201-204:
  • the target object can be the patient's target point, target area or other reference markers.
  • a target object is photographed by an imaging device to obtain a medical image of the target object.
  • the medical image may be a CT image, a magnetic resonance image or a B-ultrasound image, etc.
  • the medical image of the target object is delineated to obtain
  • the original medical contour data of the target object has many overlapping points in the original medical contour data, and the effective medical contour data of the target object is obtained by filtering the original medical contour data.
  • principal component analysis may be performed on the medical contour data to obtain the global normal vector of the medical contour data.
  • the way to obtain the global normal vector of the medical contour data may be to perform principal component analysis on the medical contour data to obtain the global normal vector of the medical contour data
  • the medical contour data may also be processed by the least squares method to obtain a global normal vector of the medical contour data, which is not specifically limited here.
  • the normal vector of the spline curve of the medical contour data may be directly obtained from the medical contour data to obtain the normal vector of the spline curve of the medical contour data.
  • the spline curve normal vector can also be obtained from the medical contour data to obtain a spline curve (Spline Curves), and the spline curve normal vector of the medical contour data can be obtained according to the spline curve, which is not specifically limited here.
  • spline curve refers to a curve obtained by a set of control points, and the approximate shape of the curve is controlled by these points.
  • interpolation spline is usually used for digital drawing.
  • approximation splines are generally used to construct the surface of an object.
  • the spline curve can be a B-spline curve (B-spline curve), and the B-spline curve refers to a special representation in the numerical analysis of the sub-discipline of mathematics. It is a linear combination of B-spline base curves, a generalization of Bezier curves.
  • the consistent global normal vector is directed to the outside of the contour of the medical contour data of the target object.
  • the spline curve normal vector is used as a reference normal vector, a preset value is set, and the relationship between the angle between the spline curve normal vector and the global normal vector and the preset value is determined, Thereby adjusting the global normal vector.
  • the surface reconstruction method may be an implicit method of scattered point cloud, which is roughly divided into a global method or a local method.
  • Global methods typically define the implicit function as the sum of point-centered radial basis functions, and local methods estimate the tangent plane and define the implicit function as the signed distance to the tangent plane to the closest point.
  • a classical implicit method of scattered point cloud that is, a Poisson reconstruction (PoissonSurfaceReconstruction) method
  • PoissonSurfaceReconstruction The input of Poisson reconstruction is point cloud data with normal vector attributes, and the output is a triangular network model.
  • the point cloud represents the position of the surface of the object, and its normal vector represents the direction of the inside and outside.
  • the method and device for adjusting the consistency of the global normal vector of medical contour data provided by the present application, by acquiring the normal vector of the spline curve of the medical contour data, and using the normal vector of the spline curve as the reference direction for adjusting the global normal vector, the global normal vector is adjusted. Consistency adjustment, the adjusted global normal vector can be used for medical contour data reconstruction, and a 3D surface reconstruction model with clearer details and smoother surface can be obtained.
  • the global normal vectors of the medical contour data are adjusted consistently, the accuracy of the three-dimensional surface reconstruction is improved, and the three-dimensional surface reconstruction effect with smooth surface and intact details is obtained.
  • the acquiring medical contour data of the target object includes the following steps 301 to 304:
  • a target object is photographed by an imaging device to obtain a medical image of the target object.
  • the medical image may be a CT image, a magnetic resonance image or a B-ultrasound image, etc., and the medical image of the target object is delineated to obtain The original medical contour data of the target object, which is often stored in the RT structure set in the patient's DICOMRT file.
  • the DICOMRT file (Radiothearapyin DICOM) is used to support the transmission of radiotherapy-related data in the radiotherapy department equipment or with other department equipment, and specially handles the data transmission between radiotherapy equipment.
  • the RT structure set (RT Structureset) is a specification of the patient's anatomical structure and related data transmission requirements obtained from equipment such as CT, virtual simulation workstation or treatment planning system. Its scope includes information related to the patient's anatomy, such as Region of Interest (ROI) markers, isocenter positions, and dose reference points, etc. These entities are usually determined by equipment such as CT, virtual simulation workstations or treatment planning systems, and can also be used. Includes audio commentary.
  • ROI Region of Interest
  • the original medical contour data is converted into point cloud data with coordinates.
  • raw medical contour data of the target object is obtained from the patient's RT structure set, and the raw medical contour data is converted into point cloud data having, for example, (X, Y, Z) coordinates.
  • the valid point cloud data is used as the medical contour data of the target object.
  • the method for adjusting the global normal vector consistency of medical contour data obtained by the embodiment of the present application obtains valid point cloud data by converting and filtering the original medical contour data, which reduces the data errors brought to subsequent spline curve fitting or calculation methods. Negative effects of vector.
  • the acquiring the normal vector of the spline curve of the medical contour data includes the following steps: acquiring the tangent vector of the spline curve of the medical contour data, and according to the preset tangent vector of the spline curve The relationship with the normal vector of the spline curve determines the normal vector of the spline curve of the medical contour data.
  • the relationship between the preset tangent vector of the spline curve and the normal vector of the spline curve is a mutually perpendicular relationship, that is, the tangent vector of the spline curve and the normal vector of the spline curve are perpendicular to each other, and the tangent vector of the spline curve and the normal vector of the spline curve are mutually perpendicular.
  • the vector product is zero.
  • the curve normal vector includes the following steps: respectively taking a contour point corresponding to the medical contour data as a target contour point, obtaining a spline curve tangent vector of the target contour point; according to the preset spline curve tangent vector and spline The relationship between the curve normal vectors, the spline curve normal vector of the target contour point is determined; when the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vector of the medical contour data is obtained. .
  • a contour point corresponding to the medical contour data as the target contour point for example, take a contour point i corresponding to the medical contour data as the target contour point, obtain the spline tangent vector of the i point, according to The relationship between them is perpendicular to each other, and the normal vector of the spline curve of point i is obtained.
  • the spline curve normal vectors of all the contour points in the medical contour data can be obtained at the same time, and the spline curve normal vectors of all the contour points in the medical contour data can also be obtained in sequence. limited.
  • spline curve fitting is performed on the medical contour data, and the spline curve C(u) of the medical contour data can be obtained through the following The formula gets:
  • the spline tangent vector of the spline curve at point i can be obtained by the following formula:
  • the acquiring the spline tangent vector of the target contour point includes the following steps: acquiring adjacent contour points of the target contour point; combining the target contour point and the adjacent contour point The formed vector is used as the spline tangent vector of the target contour point; correspondingly, according to the preset relationship between the spline curve tangent vector and the spline curve normal vector, the spline curve method of the target contour point is determined vector, including: taking the target contour point and the mid-perpendicular line of the adjacent contour point as the spline curve normal vector of the target contour point.
  • the adjacent contour point is the contour point with the coordinates adjacent to the target contour point obtained in the clockwise direction. If the counterclockwise direction is used as an example, the adjacent contour point is the The contour point with the coordinates adjacent to the target contour point obtained in the counterclockwise direction.
  • point i is the target contour point
  • the calculation direction of the contour point is clockwise
  • the coordinates of the target contour point are p i
  • the coordinates of the adjacent contour points are p i+1
  • the tangent vector of the i-th point is The tangent vector of the i-th point can be obtained by the following formula:
  • the method for adjusting the consistency of the global normal vector of the medical contour data provides a reference for the subsequent adjustment of the global normal vector of the medical contour data by acquiring the normal vector of the spline curve of the medical contour data, which is beneficial to the adjustment of the global normal vector. Consistency adjustment.
  • the acquiring the normal vector of the spline curve of the medical contour data includes the following steps 401 to 403:
  • the normal vector of each spline curve in the normal vector of the first spline curve is adjusted to face the outer side of the contour of the medical contour data, so as to obtain the second normal vector of the spline curve, Including the following steps: respectively taking a spline curve normal vector in the first spline curve normal vector as the target spline curve normal vector; judging whether the direction of the target spline curve normal vector is towards the direction of the medical contour data.
  • each spline curve normal vector in the first spline curve normal vector may be adjusted respectively, or each spline curve normal vector in the first spline curve normal vector may be adjusted sequentially. Adjustments are not specifically limited here.
  • the judging whether the direction of the normal vector of the target spline curve is toward the outer side of the contour of the medical contour data includes the following steps: acquiring the plane normal vector of the plane where the medical contour data is located; The path vector of the target spline curve normal vector, the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector, and the target connection vector is the first contour point and the second The vector formed after connecting the contour points, the first contour point is the contour point corresponding to the normal vector of the target spline curve, and the second contour point is the contour point adjacent to the first contour point; Determine whether the plane normal vector and the path vector are in the same direction; if the plane normal vector and the path vector are not in the same direction, it is determined that the direction of the target spline curve normal vector does not face the contour of the medical contour data outside.
  • acquiring the plane normal vector of the plane where the medical contour data is located includes the following steps: acquiring a plane contour point corresponding to the normal vector of the target spline curve; taking the plane contour point as a starting point , determine the third contour point and the fourth contour point of the plane where the medical contour data is located; for the vector of the plane contour point and the third contour point, and the third contour point and the fourth contour point Cross-multiply the vectors of , to obtain the plane normal vector of the plane where the medical contour data is located.
  • the plane contour point where the normal vector of the target spline curve is located is point j
  • the third contour point is point j+1 with the coordinates adjacent to point j
  • the fourth contour point is the j+2 point that is separated from the j point by a coordinate
  • the plane normal vector of the medical contour data can use the j point, the j+1 point adjacent to the j point coordinate and the j point that is separated by a coordinate.
  • the j+2 points of are connected and obtained by cross product.
  • a first preset number of contour points are spaced between the third contour point and the plane contour point, and the fourth contour point and A second preset number of contour points are spaced between the third contour points.
  • the first preset number and the second preset number may be the same or different, and the values of the first preset number and the second preset number may be 1, 3, 5 or other numbers of points, which can be determined according to the actual situation. Application scenario limitations are not limited here.
  • the cross product is a binary operation of vectors in the vector space, which generally refers to the quantity product.
  • the operation result of the cross product is a vector rather than a scalar.
  • the plane normal vector of the medical contour data is The coordinate of the contour point where the normal vector of the target spline curve is located is p j , and the plane normal vector of the medical contour data can be obtained by the following formula:
  • the target spline curve normal vector is path vector of target spline normal vector It can be obtained by the following formula:
  • the second spline curve normal vector can be directly used as the spline curve normal vector of the medical contour data.
  • the spline curve normal vector in the medical contour data can also be The validity of the curve normal vector is verified.
  • obtaining the spline curve normal vector of the medical contour data according to the second spline curve normal vector includes the following steps: The validity of the spline curve normal vector in the two-spline curve normal vector is verified, and the spline curve normal vector of the medical contour data is obtained.
  • the validation of the spline normal vector in the second spline normal vector to obtain the spline normal vector of the medical contour data includes the following steps: : respectively take a spline curve normal vector in the second spline curve normal vector as the target normal vector to be adjusted; obtain the adjacent normal vector to be adjusted of the target normal vector to be adjusted; verify the target normal vector to be adjusted Whether it is perpendicular to the adjacent to-be-adjusted normal vector; if it is vertical, the angle adjustment is performed on the target to-be-adjusted normal vector, so that the target to-be-adjusted normal vector is not perpendicular to the adjacent adjacent to-be-adjusted normal vector; After the validity verification of all spline curve normal vectors in the two-spline curve normal vector is completed, the spline curve normal vector of the medical contour data is obtained.
  • the method for adjusting the consistency of the global normal vector of the medical contour data provides a reference for the subsequent adjustment of the global normal vector of the medical contour data by acquiring the normal vector of the spline curve of the medical contour data, which is beneficial to the adjustment of the global normal vector. Consistency adjustment.
  • adjusting the global normal vector according to the spline curve normal vector to obtain a consistent global normal vector includes the following steps: judging the global normal vector and the spline curve normal vector Whether the included angle is greater than the preset value; if the included angle is greater than the preset value, the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the preset value can be 90 degrees. Taking the spline curve as the spline curve as an example, it is determined whether the angle between the global normal vector and the normal vector of the spline curve is greater than 90 degrees. If the angle is greater than 90 degrees, the spline curve The normal vector is the reference normal vector, and the global normal vector is adjusted according to the direction of the spline curve normal vector, so that the angle between the global normal vector and the spline curve normal vector is less than or equal to 90 degrees.
  • the global normal vector is adjusted with the spline curve normal vector as the reference normal vector, a consistent global normal vector is obtained, so that new medical contour data is determined according to the consistent global normal vector, and the new medical contour data is processed.
  • the surface reconstruction can be Poisson reconstruction, and the Poisson reconstruction model of the target object is obtained.
  • the consistency of the global normal vector is adjusted. After adjustment, a 3D surface reconstruction model with clear details and smooth surface was obtained.
  • An embodiment of the present application also provides a method for reconstructing medical contour data, including: obtaining medical contour data of a target object; obtaining a global normal vector of the medical contour data; obtaining a spline curve normal vector of the medical contour data ; Adjust the global normal vector according to the spline curve normal vector to obtain the adjusted global normal vector, and perform surface reconstruction according to the adjusted global normal vector to obtain the surface reconstruction model of the target object.
  • FIG. 5 it is a schematic flowchart of an embodiment of a method for reconstructing medical contour data in an embodiment of the present application.
  • the method for reconstructing medical contour data includes the following steps 501 to 504:
  • the target object can be the patient's target point, target area or other reference markers.
  • a target object is photographed by an imaging device to obtain a medical image of the target object.
  • the medical image may be a CT image, a magnetic resonance image or a B-ultrasound image, etc.
  • the medical image of the target object is delineated to obtain
  • the original medical contour data of the target object has many overlapping points in the original medical contour data, and the effective medical contour data of the target object is obtained by filtering the original medical contour data.
  • principal component analysis may be performed on the medical contour data to obtain the global normal vector of the medical contour data.
  • the way to obtain the global normal vector of the medical contour data may be to perform principal component analysis on the medical contour data to obtain the global normal vector of the medical contour data
  • the medical contour data may also be processed by the least squares method to obtain a global normal vector of the medical contour data, which is not specifically limited here.
  • the normal vector of the spline curve of the medical contour data may be directly obtained from the medical contour data to obtain the normal vector of the spline curve of the medical contour data.
  • the spline curve normal vector can also be obtained from the medical contour data to obtain a spline curve (Spline Curves), and the spline curve normal vector of the medical contour data can be obtained according to the spline curve, which is not specifically limited here.
  • spline curve refers to a curve obtained by a set of control points, and the approximate shape of the curve is controlled by these points.
  • interpolation spline is usually used for digital drawing.
  • approximation splines are generally used to construct the surface of an object.
  • the spline curve can be a B-spline curve (B-spline curve), and the B-spline curve refers to a special representation in the numerical analysis of the sub-discipline of mathematics. It is a linear combination of B-spline base curves, a generalization of Bezier curves.
  • the adjusted global normal vector is directed to the outside of the contour of the medical contour data of the target object.
  • the spline curve normal vector is used as a reference normal vector, a preset value is set, and the relationship between the angle between the spline curve normal vector and the global normal vector and the preset value is determined, Thus, the global normal vector is adjusted to obtain the adjusted global normal vector.
  • the surface reconstruction method may be an implicit method of scattered point cloud, which is roughly divided into a global method or a local method.
  • Global methods typically define the implicit function as the sum of point-centered radial basis functions, and local methods estimate the tangent plane and define the implicit function as the signed distance to the tangent plane to the closest point.
  • a classical implicit method for scattered point clouds that is, a Poisson Surface Reconstruction (Poisson Surface Reconstruction) method may be used.
  • the input of Poisson reconstruction is point cloud data with normal vector attributes, and the output is a triangular network model.
  • the point cloud represents the position of the surface of the object, and its normal vector represents the direction of the inside and outside.
  • the reconstruction method of medical contour data provided by the present application, by obtaining the normal vector of the spline curve of the medical contour data, and using the normal vector of the spline curve as the reference direction of the adjustment of the global normal vector, the global normal vector is adjusted consistently, and the obtained 3D surface reconstruction model with clear details and smooth surface.
  • the global normal vectors of the medical contour data are adjusted consistently, the accuracy of the three-dimensional surface reconstruction is improved, and the three-dimensional surface reconstruction effect with smooth surface and intact details is obtained.
  • steps 501 to 503 and step 504 adjust the global normal vector according to the spline curve normal vector, and to obtain the adjusted global normal vector, refer to the above-mentioned method for adjusting global normal vector consistency of medical contour data The specific implementation manner is not repeated here.
  • the embodiment of the present application further provides a method for adjusting the consistency of the global normal vector of medical contour data.
  • the global normal vector consistency adjustment device as shown in FIG. 6 , the global normal vector consistency adjustment device 600 of the medical contour data includes:
  • the first obtaining unit 601 is used to obtain medical contour data of the target object
  • a second obtaining unit 602 configured to obtain the global normal vector of the medical contour data
  • a third obtaining unit 603, configured to obtain the normal vector of the spline curve of the medical contour data
  • An adjustment unit 604 configured to adjust the global normal vector according to the spline curve normal vector to obtain a consistent global normal vector.
  • the device for adjusting the consistency of the global normal vector of medical contour data provided by the present application, by acquiring the normal vector of the spline curve of the medical contour data, and using the normal vector of the spline curve as the reference direction for adjusting the global normal vector, the consistency of the global normal vector is adjusted. After adjustment, a 3D surface reconstruction model with clear details and smooth surface was obtained.
  • the adjustment device provided by the present application makes the global normal vector adjustment of the medical contour data consistent, improves the accuracy of three-dimensional surface reconstruction, and achieves a three-dimensional surface reconstruction effect with smooth surface and intact details.
  • the first obtaining unit 601 is specifically configured to:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the third obtaining unit 603 is specifically configured to:
  • the spline curve tangent vector of the medical contour data is acquired, and the spline curve normal vector of the medical contour data is determined according to the preset relationship between the spline curve tangent vector and the spline curve normal vector.
  • the third obtaining unit 603 is specifically configured to:
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the third obtaining unit 603 is specifically configured to:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the third obtaining unit 603 is specifically configured to:
  • the mid-perpendicular line between the target contour point and the adjacent contour points is used as the normal vector of the spline curve of the target contour point.
  • the third obtaining unit 603 is specifically configured to:
  • the spline curve normal vector of the medical contour data is obtained.
  • the third obtaining unit 603 is specifically configured to:
  • the second spline curve normal vector is obtained.
  • the third obtaining unit 603 is specifically configured to:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the third obtaining unit 603 is specifically configured to:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the third obtaining unit 603 is specifically configured to:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the third obtaining unit 603 is specifically configured to:
  • the third obtaining unit 603 is specifically configured to:
  • angle adjustment is performed on the target normal vector to be adjusted so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline curve normal vector of the medical profile data is obtained.
  • the adjustment unit 604 is specifically configured to:
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the embodiment of the present application further provides an apparatus for reconstructing medical contour data, as shown in FIG. 7 .
  • the apparatus 700 for reconstructing medical contour data includes:
  • a first obtaining unit 701 used for obtaining medical contour data of the target object
  • a second obtaining unit 702 configured to obtain the global normal vector of the medical contour data
  • a third obtaining unit 703, configured to obtain the normal vector of the spline curve of the medical contour data
  • the reconstruction unit 704 is configured to adjust the global normal vector according to the spline curve normal vector, obtain the adjusted global normal vector, perform surface reconstruction according to the adjusted global normal vector, and obtain the target object's normal vector.
  • Surface reconstruction model is configured to adjust the global normal vector according to the spline curve normal vector, obtain the adjusted global normal vector, perform surface reconstruction according to the adjusted global normal vector, and obtain the target object's normal vector.
  • the device for reconstructing medical contour data provided by the present application, by acquiring the normal vector of the spline curve of the medical contour data, and using the normal vector of the spline curve as the reference direction for adjusting the global normal vector, the global normal vector is adjusted consistently, and the obtained 3D surface reconstruction model with clear details and smooth surface.
  • the global normal vector of the medical contour data can be adjusted consistently, the accuracy of three-dimensional curved surface reconstruction is improved, and a three-dimensional curved surface reconstruction effect with smooth surface and intact details is achieved.
  • the first obtaining unit 701 is specifically configured to:
  • the valid point cloud data is used as the medical contour data of the target object.
  • the third obtaining unit 703 is specifically configured to:
  • the spline curve tangent vector of the medical contour data is acquired, and the spline curve normal vector of the medical contour data is determined according to the relationship between the preset spline curve tangent vector and the spline curve normal vector.
  • the third obtaining unit 703 is specifically configured to:
  • the spline curve normal vectors of all contour points in the medical contour data are determined, the spline curve normal vectors of the medical contour data are obtained.
  • the third obtaining unit 703 is specifically configured to:
  • the vertical line of the spline curve tangent vector of the spline curve at the target contour point is determined as the spline curve normal vector of the target contour point.
  • the third obtaining unit 703 is specifically configured to:
  • the mid-perpendicular line between the target contour point and the adjacent contour points is used as the normal vector of the spline curve of the target contour point.
  • the third obtaining unit 703 is specifically configured to:
  • the spline curve normal vector of the medical contour data is obtained.
  • the third obtaining unit 703 is specifically configured to:
  • the second spline curve normal vector is obtained.
  • the third obtaining unit 703 is specifically configured to:
  • the path vector is the vector after the cross product of the target spline curve normal vector and the target connection vector
  • the target connection vector is the first contour point and A vector formed by connecting lines between the second contour points
  • the first contour point is the contour point corresponding to the normal vector of the target spline curve
  • the second contour point is the contour adjacent to the first contour point point
  • the plane normal vector is not in the direction of the path vector, it is determined that the direction of the target spline curve normal vector is not toward the outer side of the contour of the medical contour data.
  • the third obtaining unit 703 is specifically configured to:
  • Cross-multiplying the vector of the plane contour point and the third contour point, as well as the vector of the third contour point and the fourth contour point obtains the plane normal vector of the plane where the medical contour data is located.
  • the third obtaining unit 703 is specifically configured to:
  • the second spline curve normal vector is used as the spline curve normal vector of the medical contour data.
  • the third obtaining unit 703 is specifically configured to:
  • the third obtaining unit 703 is specifically configured to:
  • angle adjustment is performed on the target normal vector to be adjusted so that the target normal vector to be adjusted is not perpendicular to the adjacent normal vector to be adjusted;
  • the spline normal vector of the medical contour data is obtained.
  • the reconstruction unit 704 is specifically configured to:
  • Surface reconstruction is performed according to the adjusted global normal vector to obtain a surface reconstruction model of the target object.
  • the embodiments of the present application further provide a computer device that integrates any of the apparatuses for adjusting the global normal vector consistency of medical contour data provided by the embodiments of the present application, and the computer device includes:
  • processors one or more processors
  • One or more application programs wherein the one or more application programs are stored in the memory and configured to be executed by the processor any of the above-mentioned method embodiments of the global normal vector consistency adjustment for medical contour data The steps in the method for adjusting the consistency of the global normal vector of medical contour data described in the embodiment.
  • FIG. 8 shows a schematic structural diagram of a computer device involved in an embodiment of the present application, specifically:
  • the computer device may include a processor 801 of one or more processing cores, a memory 802 of one or more computer-readable storage media, a power supply 803 and an input unit 804 and other components.
  • a processor 801 of one or more processing cores may include a processor 801 of one or more processing cores, a memory 802 of one or more computer-readable storage media, a power supply 803 and an input unit 804 and other components.
  • FIG. 8 does not constitute a limitation to the computer device, and may include more or less components than the one shown, or combine some components, or arrange different components. in:
  • the processor 801 is the control center of the computer equipment, uses various interfaces and lines to connect various parts of the entire computer equipment, runs or executes the software programs and/or modules stored in the memory 802, and calls the software programs stored in the memory 802. Data, perform various functions of computer equipment and process data, so as to conduct overall monitoring of computer equipment.
  • the processor 801 may include one or more processing cores; the processor 801 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP) ), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the processor 801 can integrate an application processor and a modulation and demodulation processor, wherein the application processor mainly processes the operating system, User interface and applications, etc., the modem processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 801.
  • the memory 802 can be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 802 .
  • the memory 802 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program (such as a sound playback function, an image playback function, etc.) required for at least one function, and the like; Data created by the use of computer equipment, etc.
  • memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 802 may also include a memory controller to provide processor 801 access to memory 802 .
  • the computer equipment also includes a power supply 803 for supplying power to various components.
  • the power supply 803 can be logically connected to the processor 801 through a power management system, so as to manage charging, discharging, and power consumption management functions through the power management system.
  • the power source 803 may also include one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the computer device may also include an input unit 804 that may be operable to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and functional control.
  • an input unit 804 may be operable to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and functional control.
  • the computer device may also include a display unit and the like, which will not be described herein again.
  • the processor 801 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 802 according to the following instructions, and the processor 801 will run them and store them in the memory 802 .
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • an embodiment of the present application provides a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, etc. .
  • a computer program is stored thereon, and the computer program is loaded by the processor to execute the steps in any of the methods for adjusting the global normal vector consistency of medical contour data provided by the embodiments of the present application.
  • the computer program being loaded by the processor may perform the following steps:
  • the global normal vector is adjusted according to the spline curve normal vector to obtain a consistent global normal vector.
  • the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities.

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

本申请提出了一种医学轮廓数据的全局法向量一致性调整方法和装置，所述调整方法包括：获取目标对象的医学轮廓数据；获取所述医学轮廓数据的全局法向量；获取所述医学轮廓数据的样条曲线法向量；根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。本申请通过对医学轮廓数据的全局法向量进行一致性调整，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。

Description

医学轮廓数据的全局法向量一致性调整方法和装置 技术领域
本申请主要涉及曲面重构技术领域，具体涉及一种医学轮廓数据的全局法向量一致性调整方法和装置。
背景技术
曲面重构是指通过建模可以将离散的测量数据重构出连续变化的曲面。在三维曲面重构方面，就处理数据而言，可分为散乱点云的重构以及平行轮廓数据如地形图、医学切片图像等的重构；就重构方法而言，分为显式和隐式。
散乱点云显式方法常见的有Delaunay三角剖分技术，用于生成精确的插值曲面，但由于该技术对噪声不强健，并且对于稀疏的数据集，生成的曲面会有孔洞。散乱点云隐式方法分为全局方法和局部方法，全局方法通常将隐式函数定义为以点为中心的径向基函数的总和，局部方法是估计切平面并将隐式函数定义为到最近点的切平面的有符号距离。在隐式方法中，有向点集都是指一致朝曲面外或者朝曲面内的法向量，一致的法向量估计是曲面重构的基础。
现有的算法容易出现法向量调整错误的情况，使得法向量不一致，容易出现劣质的以及多余的伪网格，三维曲面重构效果不佳。
发明内容
本申请提供一种医学轮廓数据的全局法向量一致性调整方法和装置，对医学轮廓数据的全局法向量进行一致性调整，提高了三维曲面重构的准确性。
第一方面，本申请提供一种医学轮廓数据的全局法向量一致性调整方法，所述方法包括：
获取目标对象的医学轮廓数据；
获取所述医学轮廓数据的全局法向量；
获取所述医学轮廓数据的样条曲线法向量；
根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
在本申请一些实施例中，所述获取目标对象的医学轮廓数据，包括：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量，包括：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包括：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包 括：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量，包括：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
在本申请一些实施例中，所述判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧，包括：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请一些实施例中，所述获取所述医学轮廓数据所在平面的平面法向量，包括：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请一些实施例中，所述第三轮廓点和所述平面轮廓点之间间隔第一预设数目的轮廓点，所述第四轮廓点和所述第三轮廓点之间间隔第二预设数目的轮廓点。
在本申请一些实施例中，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，包括：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量，包括：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法 向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量，包括：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到一致的全局法向量。
第二方面，本申请提供一种医学轮廓数据的重构方法，所述方法包括：
获取目标对象的医学轮廓数据；
获取所述医学轮廓数据的全局法向量；
获取所述医学轮廓数据的样条曲线法向量；
根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
在本申请一些实施例中，所述获取目标对象的医学轮廓数据，包括：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量 和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量，包括：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包括：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包括：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样 条曲线法向量。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量，包括：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
在本申请一些实施例中，所述判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧，包括：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向 量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请一些实施例中，所述获取所述医学轮廓数据所在平面的平面法向量，包括：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请一些实施例中，所述第三轮廓点和所述平面轮廓点之间间隔第一预设数目的轮廓点，所述第四轮廓点和所述第三轮廓点之间间隔第二预设数目的轮廓点。
在本申请一些实施例中，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，包括：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量，包括：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型，包括：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到调整后的全局法向量；
根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
第三方面，本申请提供一种医学轮廓数据的全局法向量一致性调整装置，所述装置包括：
第一获取单元，用于获取目标对象的医学轮廓数据；
第二获取单元，用于获取所述医学轮廓数据的全局法向量；
第三获取单元，用于获取所述医学轮廓数据的样条曲线法向量；
调整单元，用于根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
在本申请一些实施例中，所述第一获取单元具体用于：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量 与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述调整单元具体用于：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到一致的全局法向量。
第四方面，本申请提供一种医学轮廓数据的重构装置，所述装置包括：
第一获取单元，用于获取目标对象的医学轮廓数据；
第二获取单元，用于获取所述医学轮廓数据的全局法向量；
第三获取单元，用于获取所述医学轮廓数据的样条曲线法向量；
重构单元，用于根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
在本申请一些实施例中，所述第一获取单元具体用于：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医 学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元具体用于：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述 第二样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请另一些实施例中，所述第三获取单元具体用于：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元具体用于：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述重构单元具体用于：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到调整后的全局法向量；
根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
第五方面，本申请提供一种计算机设备，所述计算机设备包括：
一个或多个处理器；
存储器；以及
一个或多个应用程序，其中所述一个或多个应用程序被存储于所述存储器中，并配置为由所述处理器执行以实现第一方面中任一项所述的医学轮廓数据的全局法向量一致性调整方法，或者第二方面中任一项所述的医学轮廓数据的重构方法。
第六方面，本申请提供一种计算机可读存储介质，所述计算机可读存储介质存储有多条指令，所述指令适于处理器进行加载，以执行第一方面中任一项所述的医学轮廓数据的全局法向量一致性调整方法中的步骤，或者第二方面中任一项所述的医学轮廓数据的重构方法中的步骤。
本申请提供的医学轮廓数据的全局法向量一致性调整方法和装置，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的参考方向，对全局法向量进行一致性调整，调整后的全局法向量可以用于医学轮廓数据重构，可以取得更细节清晰、表面光滑的三维曲面重构模型。采用本申请提供的方法，使得医学轮廓数据的全局法向量调整一致，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请 的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的医学轮廓数据的全局法向量一致性调整系统的场景示意图；
图2是本申请实施例中提供的医学轮廓数据的全局法向量一致性调整方法的一个实施例流程示意图；
图3是本申请实施例中获取目标对象的医学轮廓数据的一个实施例流程示意图；
图4是本申请实施例中获取所述医学轮廓数据的样条曲线法向量的一个实施例流程示意图；
图5是本申请实施例中提供的医学轮廓数据的重构方法的一个实施例流程示意图；
图6是本申请实施例中提供的医学轮廓数据的全局法向量一致性调整装置的一个实施例结构示意图；
图7是本申请实施例中提供的医学轮廓数据的重构装置的一个实施例结构示意图；
图8是本申请实施例中提供的计算机设备的一个实施例结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在本申请的描述中，需要理解的是，术语“中心”、“纵向”、“横向”、“长度”、“宽度”、“厚度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定 的方位构造和操作，因此不能理解为对本申请的限制。此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个所述特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
在本申请中，“示例性”一词用来表示“用作例子、例证或说明”。本申请中被描述为“示例性”的任何实施例不一定被解释为比其它实施例更优选或更具优势。为了使本领域任何技术人员能够实现和使用本申请，给出了以下描述。在以下描述中，为了解释的目的而列出了细节。应当明白的是，本领域普通技术人员可以认识到，在不使用这些特定细节的情况下也可以实现本申请。在其它实例中，不会对公知的结构和过程进行详细阐述，以避免不必要的细节使本申请的描述变得晦涩。因此，本申请并非旨在限于所示的实施例，而是与符合本申请所公开的原理和特征的最广范围相一致。
下面首先对本申请实施例中涉及到的一些基本概念进行介绍：
点云数据：点云数据(pointclouddata)是指在一个三维坐标系统中的一组向量的集合。这些向量通常以(X,Y,Z)三维坐标的形式表示，一般主要用来代表一个物体的外表面形状。除了表示几何位置信息之外，点云数据还可以表示一个点的RGB颜色、灰度值、深度和分割结果等。
本申请实施例提供一种医学轮廓数据的全局法向量一致性调整方法和装置，以下分别进行详细说明。
请参阅图1，图1为本申请实施例所提供的医学轮廓数据的全局法向量一致性调整系统的场景示意图，该医学轮廓数据的全局法向量一致性调整系统可以包括成像装置100和计算机设备200，成像装置100和计算机设备200通信连接，成像装置100可以向计算机设备200传输数据，如图1中的成像装置100，成像装置100可以采集人体的医学图像，并输出至计算机设备200。
本申请实施例中，成像装置100可以是电子计算机断层扫描(ComputedTomography，CT)、磁共振(MagneticResonance，MR)、B型超声(B-scanultrasonography)或者其他成像设备等等，具体此处不作限定。
本申请实施例中，该计算机设备200可以是独立的服务器，也可以是服务器组成的服务器网络或服务器集群，例如，本申请实施例中所描述的计算机设备200，其包括但不限于计算机、网络主机、单个网络服务器、多个网络服务器集或多个服务器构成的云服务器。其中，云服务器由基于云计算(CloudComputing)的大量计算机或网络服务器构成。
本申请实施例中，上述的计算机设备200可以是一个通用计算机设备或者是一个专用计算机设备。在具体实现中计算机设备200可以是台式机、便携式电脑、网络服务器、掌上电脑(PersonalDigitalAssistant，PDA)、移动手机、平板电脑、无线终端设备、通信设备、嵌入式设备等，本实施例不限定计算机设备200的类型
本申请的实施例中，成像装置100与计算机设备200之间可通过任何通信方式实现通信，包括但不限于，基于第三代合作伙伴计划(3rdGenerationPartnershipProject，3GPP)、长期演进(LongTermEvolution，LTE)、全球互通微波访问(WorldwideInteroperabilityforMicrowaveAccess，WiMAX)的移动通信，或基于TCP/IP协议族(TCP/IPProtocolSuite，TCP/IP)、用户数据报协议(UserDatagramProtocol，UDP)的计算机网络通信等。
本领域技术人员可以理解，图1中示出的应用环境，仅仅是与本申请方案一种应用场景，并不构成对本申请方案应用场景的限定，其他的应用环境还可以包括比图1中所示更多或更少的计算机设备，例如图1中仅示出1个计算机设备，可以理解的，该医学轮廓数据的全局法向量一致性调整系统还可以包括一个或多个可处理数据的其他计算机设备，具体此处不作限定。
另外，如图1所示，该医学轮廓数据的全局法向量一致性调整系统还可以包括存储器300，用于存储数据，如存储医学图像数据，例如成像装置100采集的医学图像数据。
需要说明的是，图1所示的医学轮廓数据的全局法向量一致性调整系统的场景示意图仅仅是一个示例，本申请实施例描述的医学轮廓数据的全局法向量一致性调整系统以及场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知， 随着医学轮廓数据的全局法向量一致性调整系统的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
首先，本申请实施例中提供一种医学轮廓数据的全局法向量一致性调整方法，包括：获取目标对象的医学轮廓数据；获取所述医学轮廓数据的全局法向量；获取所述医学轮廓数据的样条曲线法向量；根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
如图2所示，为本申请实施例中医学轮廓数据的全局法向量一致性调整方法的一个实施例流程示意图，该医学轮廓数据的全局法向量一致性调整方法包括如下步骤201～204：
201、获取目标对象的医学轮廓数据。
其中，目标对象可以是患者的靶点、靶区或者而其他参考标记。
在本申请一些实施例中，通过成像装置拍摄目标对象，得到目标对象的医学图像，医学图像可以是CT图像、磁共振图像或者B超图像等等，在目标对象的医学图像上进行勾画，得到目标对象的原始医学轮廓数据，在原始医学轮廓数据中存在很多重合的点，对原始医学轮廓数据进行过滤得到目标对象的有效医学轮廓数据。
202、获取所述医学轮廓数据的全局法向量。
本申请实施例中，获取所述医学轮廓数据的全局法向量的方式可以多种方式，例如可以对所述医学轮廓数据进行主成分分析，得到所述医学轮廓数据的全局法向量，具体的，对所述医学轮廓数据进行主成分分析，从医学轮廓数据中导出少数几个主成分，使它们尽可能多地保留医学轮廓数据的信息，且主成分之间互不相关，对这些主成分进行分析，得到医学轮廓数据的全局法向量。
可以理解的是，在本申请另一些实施例中，获取所述医学轮廓数据的全局法向量的方式可以是对所述医学轮廓数据进行主成分分析，得到所述医学轮廓数据的全局法向量，也可以通过最小二乘法对所述医学轮廓数据进行处理，得到所述医学轮廓数据的全局法向量，具体此处不作限定。
203、获取所述医学轮廓数据的样条曲线法向量。
本申请实施例中，获取所述医学轮廓数据的样条曲线法向量的方式可以多 种方式，例如可以是对所述医学轮廓数据直接求取样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，也可以对所述医学轮廓数据求取样条曲线(Spline Curves)，根据样条曲线得到所述医学轮廓数据的样条曲线法向量，具体此处不作限定。
其中，样条曲线是指给定一组控制点而得到一条曲线，曲线的大致形状由这些点予以控制，一般可分为插值样条和逼近样条两种，插值样条通常用于数字化绘图或动画的设计，逼近样条一般用来构造物体的表面。
进一步的，样条曲线可以是B样条曲线(B-spline curve)，B样条曲线是指在数学的子学科数值分析里的一种特殊的表示形式。它是B样条基曲线的线性组合，是贝塞尔曲线的一般化。
204、根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
其中，所述一致的全局法向量朝向所述目标对象的医学轮廓数据的轮廓外侧。
在本申请一些实施例中，以所述样条曲线法向量为参考法向量，设置预设值，判断所述样条曲线法向量和所述全局法向量的夹角与预设值的关系，从而调整所述全局法向量。
可以理解的是，在所述全局法向量调整一致后，对所述目标对象进行曲面重构，曲面重构的方法可以是散乱点云隐式方法，大致分为全局方法或者局部方法。全局方法通常将隐式函数定义为以点为中心的径向基函数的总和，局部方法是估计切平面并将隐式函数定义为到最近点的切平面的有符号距离。
优选的，在本申请一些实施例中，可以采用散乱点云的经典隐式方法，即泊松重构(PoissonSurfaceReconstruction)方法。泊松重构的输入是带有法向量属性的点云数据，输出的是三角网络模型。点云代表了物体表面的位置，其法向量代表了内外的方向。通过隐式地拟合一个由物体派生的指示函数，可以给出一个平滑的物体表面的估计。
本申请提供的医学轮廓数据的全局法向量一致性调整方法和装置，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的 参考方向，对全局法向量进行一致性调整，调整后的全局法向量可以用于医学轮廓数据重构，可以取得更细节清晰、表面光滑的三维曲面重构模型。采用本申请提供的方法，使得医学轮廓数据的全局法向量调整一致，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。
如图3所示，在本申请一些实施例中，所述获取目标对象的医学轮廓数据，包括如下步骤301～304：
301、获取所述目标对象的原始医学轮廓数据。
在本申请一些实施例中，通过成像装置拍摄目标对象，得到目标对象的医学图像，医学图像可以是CT图像、磁共振图像或者B超图像等等，在目标对象的医学图像上进行勾画，得到目标对象的原始医学轮廓数据，原始医学轮廓数据往往存储在患者的DICOMRT文件中的RT结构集中。
其中，DICOMRT文件(RadiothearapyinDICOM)是用于支持放射治疗相关的数据在放疗科内设备或者与其他科室设备的传输，专门处理放射治疗设备间的数据传输。
其中，RT结构集(RTStructureset)是从CT、虚拟模拟工作站或治疗计划系统等设备得到的病人解剖结构及相关数据传输要求的规范。其范围包括与病人解剖相关的信息，如感兴趣区域(RegionofInterest，ROI)标志物、等中心位置和剂量参考点等，这些实体通常由CT、虚拟模拟工作站或治疗计划系统等设备确定，还可以包括声音解说。
可以理解的是，如果要对目标对象的医学轮廓进行曲面重构或者其他图像处理，需要从患者的RT结构集中获取原始医学轮廓数据。
302、将所述原始医学轮廓数据转换为具有坐标的点云数据。
在步骤301获取所述目标对象的原始医学轮廓数据之后，将所述原始医学轮廓数据转换为具有坐标的点云数据。
在一个具体实施例中，从患者的RT结构集中获取所述目标对象的原始医学轮廓数据，将所述原始医学轮廓数据转换为具有例如(X,Y,Z)坐标的点云数据。
303、过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据。
可以理解的是，人为或者AI勾画的轮廓数据可能存在重合的轮廓点或者轮廓线，对后续的样条曲线拟合或者计算法向量会带来误差，所以在本申请一些实施例中，可能存在坐标相同的点云数据，所以对具有相同坐标的点云数据进行过滤，得到有效点云数据，
304、将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，在对具有相同坐标的点云数据进行过滤得到有效点云数据之后，将所述有效点云数据作为所述目标对象的医学轮廓数据。
本申请实施例提供的医学轮廓数据的全局法向量一致性调整方法，通过对原始医学轮廓数据进行转换并过滤，得到有效点云数据，减少了数据误差带给后续样条曲线拟合或者计算法向量的负面影响。
在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括如下步骤：获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
其中，预设的样条曲线切向量和样条曲线法向量的关系为相互垂直关系，即样条曲线切向量和样条曲线法向量相互垂直，样条曲线切向量和样条曲线法向量的向量积为零。
本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量，包括如下步骤：分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
进一步的，分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，例如以所述医学轮廓数据对应的一个轮廓点i点为目标轮廓点，获取i点的样条曲线切向量，根据相互垂直关系，求出i点的样条曲线法向量。
可以理解的是，可以同时获取所述医学轮廓数据中的所有轮廓点的样条曲线法向量，也可以依次获取所述医学轮廓数据中的所有轮廓点的样条曲线法向量，具体此处不作限定。
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包括如下步骤：对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
具体的，例如以i点为目标轮廓点，目标轮廓点的坐标为P i，对所述医学轮廓数据进行样条曲线拟合，所述医学轮廓数据的样条曲线C(u)可以通过如下公式获得：
Figure PCTCN2020142019-appb-000001
进一步的，对i点进行求导，可以通过如下公式获得所述样条曲线在i点的样条曲线切向量：
Figure PCTCN2020142019-appb-000002
相应的，根据预设的样条曲线切向量和样条曲线法向量的关系，即
Figure PCTCN2020142019-appb-000003
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为i点的样条曲线法向量
Figure PCTCN2020142019-appb-000004
在本申请一些实施例中，所述获取所述目标轮廓点的样条曲线切向量，包括如下步骤：获取所述目标轮廓点的邻接轮廓点；将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
其中，以轮廓点计算方向为顺时针方向为例，邻接轮廓点为以顺时针方向获取的与目标轮廓点相邻坐标的轮廓点，如果是以逆时针方向为例，则邻接轮 廓点为以逆时针方向获取的与目标轮廓点相邻坐标的轮廓点。
进一步的，例如以i点为目标轮廓点，以轮廓点计算方向为顺时针方向，目标轮廓点的坐标为p i，邻接轮廓点的坐标为p i+1，第i点的切向量为
Figure PCTCN2020142019-appb-000005
第i点的切向量可以由如下公式获得：
Figure PCTCN2020142019-appb-000006
相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，即
Figure PCTCN2020142019-appb-000007
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量
Figure PCTCN2020142019-appb-000008
本申请实施例提供的医学轮廓数据的全局法向量一致性调整方法，通过获取医学轮廓数据的样条曲线法向量，为后续医学轮廓数据的全局法向量调整提供了参考，有利于全局法向量的一致性调整。
如图4所示，在本申请一些实施例中，所述获取所述医学轮廓数据的样条曲线法向量，包括如下步骤401～403：
401、获取所述医学轮廓数据的第一样条曲线法向量。
402、将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量。
403、根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量，包括如下步骤：分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
可以理解的是，可以是分别对所述第一样条曲线法向量中各样条曲线法向 量进行调整，也可以是依次对所述第一样条曲线法向量中各样条曲线法向量进行调整，具体此处不作限定。
在一个具体实施例中，所述判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧，包括如下步骤：获取所述医学轮廓数据所在平面的平面法向量；获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；判断所述平面法向量与所述路径向量是否同向；若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请一些实施例中，所述获取所述医学轮廓数据所在平面的平面法向量，包括如下步骤：获取所述目标样条曲线法向量对应的平面轮廓点；以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
具体的，以轮廓点计算方向为顺时针方向为例，目标样条曲线法向量所在的平面轮廓点为j点，所述第三轮廓点为与j点相邻坐标的j+1点，所述第四轮廓点为与j点相隔一个坐标的j+2点，所述医学轮廓数据的平面法向量可以利用j点、与j点相邻坐标的j+1点以及与j点相隔一个坐标的j+2点连线并进行叉乘获得。
可以理解的是，在本申请一些实施例中，在实际运算过程中，所述第三轮廓点和所述平面轮廓点之间间隔第一预设数目的轮廓点，所述第四轮廓点和所述第三轮廓点之间间隔第二预设数目的轮廓点。其中，第一预设数目和第二预设数目可以相同也可以不同，第一预设数目和第二预设数目的取值可以是1、3、5或其他数目的点，具体可以根据实际应用场景限定此处不作限定。
其中，叉乘是一种在向量空间中向量的二元运算，一般指向量积，与点积不同，叉乘的运算结果是一个向量而不是一个标量。
进一步的，医学轮廓数据的平面法向量为
Figure PCTCN2020142019-appb-000009
目标样条曲线法向量所在轮廓点的坐标为p j，医学轮廓数据的平面法向量可以通过如下公式获得：
Figure PCTCN2020142019-appb-000010
在获得医学轮廓数据的平面法向量之后，在本申请一些实施例中，目标样条曲线法向量为
Figure PCTCN2020142019-appb-000011
目标样条曲线法向量的路径向量
Figure PCTCN2020142019-appb-000012
可以通过如下公式获得：
Figure PCTCN2020142019-appb-000013
进一步的，判断所述平面法向量与所述路径向量是否同向，θ为路径向量
Figure PCTCN2020142019-appb-000014
与平面法向量
Figure PCTCN2020142019-appb-000015
的夹角，可以通过如下公式判断：
Figure PCTCN2020142019-appb-000016
可以理解的是，如果根据上述公式得出θ实质为180度，即平面法向量与路径向量不同向，对目标样条曲线法向量进行调整；相反地，如果根据上述公式得出θ实质为0度，即平面法向量与路径向量同向，不对目标样条曲线法向量进行调整。
本申请一些实施例中，根据所述第二样条曲线法向量，可以直接将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
但是由于所述医学轮廓数据的样条曲线法向量中可能存在样条曲线法向量与医学轮廓数据中的微小路径平行，因此也可以对所述医学轮廓数据的样条曲线法向量中的样条曲线法向量进行有效性验证，在本申请一些实施例中，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，包括如下步骤：对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
进一步的，在本申请一些实施例中，所述对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量，包括如下步骤：分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；获取所述目标待调法向量的邻接待调法向量；验证所述目标待调法向量与所述邻接待调法向量是否垂直；若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；当所述第二 样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
本申请实施例提供的医学轮廓数据的全局法向量一致性调整方法，通过获取医学轮廓数据的样条曲线法向量，为后续医学轮廓数据的全局法向量调整提供了参考，有利于全局法向量的一致性调整。
在本申请一些实施例中，所述根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量，包括如下步骤：判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到一致的全局法向量。
其中，预设值可以为90度，以样条曲线为样条曲线为例，判断全局法向量与样条曲线法向量的夹角是否大于90度，如果夹角大于90度，以样条曲线法向量为参考法向量，根据样条曲线法向量的方向对全局法向量进行调整，使得全局法向量与样条曲线法向量的夹角小于等于90度。
进一步的，当全局法向量以样条曲线法向量为参考法向量进行调整完毕后，得到一致的全局法向量，从而根据一致的全局法向量确定新的医学轮廓数据，对新的医学轮廓数据进行曲面重构，曲面重构可以是泊松重构，得到目标对象的泊松重构模型。
本申请提供的医学轮廓数据的全局法向量一致性调整方法，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的参考方向，对全局法向量进行一致性调整，取得了细节清晰、表面光滑的三维曲面重构模型。
本申请实施例中还提供一种医学轮廓数据的重构方法，包括：获取目标对象的医学轮廓数据；获取所述医学轮廓数据的全局法向量；获取所述医学轮廓数据的样条曲线法向量；根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
如图5所示，为本申请实施例中医学轮廓数据的重构方法的一个实施例流程示意图，该医学轮廓数据的重构方法包括如下步骤501～504：
501、获取目标对象的医学轮廓数据。
其中，目标对象可以是患者的靶点、靶区或者而其他参考标记。
在本申请一些实施例中，通过成像装置拍摄目标对象，得到目标对象的医学图像，医学图像可以是CT图像、磁共振图像或者B超图像等等，在目标对象的医学图像上进行勾画，得到目标对象的原始医学轮廓数据，在原始医学轮廓数据中存在很多重合的点，对原始医学轮廓数据进行过滤得到目标对象的有效医学轮廓数据。
502、获取所述医学轮廓数据的全局法向量。
本申请实施例中，获取所述医学轮廓数据的全局法向量的方式可以多种方式，例如可以对所述医学轮廓数据进行主成分分析，得到所述医学轮廓数据的全局法向量，具体的，对所述医学轮廓数据进行主成分分析，从医学轮廓数据中导出少数几个主成分，使它们尽可能多地保留医学轮廓数据的信息，且主成分之间互不相关，对这些主成分进行分析，得到医学轮廓数据的全局法向量。
可以理解的是，在本申请另一些实施例中，获取所述医学轮廓数据的全局法向量的方式可以是对所述医学轮廓数据进行主成分分析，得到所述医学轮廓数据的全局法向量，也可以通过最小二乘法对所述医学轮廓数据进行处理，得到所述医学轮廓数据的全局法向量，具体此处不作限定。
503、获取所述医学轮廓数据的样条曲线法向量。
本申请实施例中，获取所述医学轮廓数据的样条曲线法向量的方式可以多种方式，例如可以是对所述医学轮廓数据直接求取样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，也可以对所述医学轮廓数据求取样条曲线(Spline Curves)，根据样条曲线得到所述医学轮廓数据的样条曲线法向量，具体此处不作限定。
其中，样条曲线是指给定一组控制点而得到一条曲线，曲线的大致形状由这些点予以控制，一般可分为插值样条和逼近样条两种，插值样条通常用于数字化绘图或动画的设计，逼近样条一般用来构造物体的表面。
进一步的，样条曲线可以是B样条曲线(B-spline curve)，B样条曲线是指在数学的子学科数值分析里的一种特殊的表示形式。它是B样条基曲线的线 性组合，是贝塞尔曲线的一般化。
504、根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
其中，所述调整后的全局法向量朝向所述目标对象的医学轮廓数据的轮廓外侧。
在本申请一些实施例中，以所述样条曲线法向量为参考法向量，设置预设值，判断所述样条曲线法向量和所述全局法向量的夹角与预设值的关系，从而调整所述全局法向量，得到所述调整后的全局法向量。
可以理解的是，在所述全局法向量调整一致后，对所述目标对象进行曲面重构，曲面重构的方法可以是散乱点云隐式方法，大致分为全局方法或者局部方法。全局方法通常将隐式函数定义为以点为中心的径向基函数的总和，局部方法是估计切平面并将隐式函数定义为到最近点的切平面的有符号距离。
优选的，在本申请一些实施例中，可以采用散乱点云的经典隐式方法，即泊松重构(Poisson Surface Reconstruction)方法。泊松重构的输入是带有法向量属性的点云数据，输出的是三角网络模型。点云代表了物体表面的位置，其法向量代表了内外的方向。通过隐式地拟合一个由物体派生的指示函数，可以给出一个平滑的物体表面的估计。
本申请提供的医学轮廓数据的重构方法，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的参考方向，对全局法向量进行一致性调整，取得了细节清晰、表面光滑的三维曲面重构模型。采用本申请提供的方法，使得医学轮廓数据的全局法向量调整一致，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。
本申请实施例中，步骤501～503，以及步骤504根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量可以参照上述医学轮廓数据的全局法向量一致性调整方法的具体实施方式，此处不再赘述。
为了更好实施本申请实施例中医学轮廓数据的全局法向量一致性调整方法，在医学轮廓数据的全局法向量一致性调整方法基础之上，本申请实施例中 还提供一种医学轮廓数据的全局法向量一致性调整装置，如图6所示，所述医学轮廓数据的全局法向量一致性调整装置600包括：
第一获取单元601，用于获取目标对象的医学轮廓数据；
第二获取单元602，用于获取所述医学轮廓数据的全局法向量；
第三获取单元603，用于获取所述医学轮廓数据的样条曲线法向量；
调整单元604，用于根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
本申请提供的医学轮廓数据的全局法向量一致性调整装置，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的参考方向，对全局法向量进行一致性调整，取得了细节清晰、表面光滑的三维曲面重构模型。采用本申请提供的调整装置，使得医学轮廓数据的全局法向量调整一致，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。
在本申请一些实施例中，所述第一获取单元601具体用于：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述第三获取单元603具体用于：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元603具体用于：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元603具体用于：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元603具体用于：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请另一些实施例中，所述第三获取单元603具体用于：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元603具体用于：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得 到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述调整单元604具体用于：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到一致的全局法向量。
为了更好实施本申请实施例中医学轮廓数据的重构方法，在医学轮廓数据的重构方法基础之上，本申请实施例中还提供一种医学轮廓数据的重构装置，如图7所示，所述医学轮廓数据的重构装置700包括：
第一获取单元701，用于获取目标对象的医学轮廓数据；
第二获取单元702，用于获取所述医学轮廓数据的全局法向量；
第三获取单元703，用于获取所述医学轮廓数据的样条曲线法向量；
重构单元704，用于根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
本申请提供的医学轮廓数据的重构装置，通过获取医学轮廓数据的样条曲线法向量，以样条曲线法向量作为全局法向量调整的参考方向，对全局法向量进行一致性调整，取得了细节清晰、表面光滑的三维曲面重构模型。采用本申请提供的重构装置，使得医学轮廓数据的全局法向量调整一致，提高了三维曲面重构的准确性，取得了表面光滑且细节完好的三维曲面重构效果。
在本申请一些实施例中，所述第一获取单元701具体用于：
获取所述目标对象的原始医学轮廓数据；
将所述原始医学轮廓数据转换为具有坐标的点云数据；
过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
将所述有效点云数据作为所述目标对象的医学轮廓数据。
在本申请一些实施例中，所述第三获取单元703具体用于：
获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元703具体用于：
分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元703具体用于：
对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
对所述目标轮廓点进行求导，得到所述目标轮廓点的样条曲线切向量；
将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
在本申请一些实施例中，所述第三获取单元703具体用于：
获取所述目标轮廓点的邻接轮廓点；
将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
获取所述医学轮廓数据的第一样条曲线法向量；
将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲线法向量；
判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓 外侧；
若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
获取所述医学轮廓数据所在平面的平面法向量；
获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
判断所述平面法向量与所述路径向量是否同向；
若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
在本申请另一些实施例中，所述第三获取单元703具体用于：
获取所述目标样条曲线法向量对应的平面轮廓点；
以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
在本申请另一些实施例中，所述第三获取单元703具体用于：
分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
获取所述目标待调法向量的邻接待调法向量；
验证所述目标待调法向量与所述邻接待调法向量是否垂直；
若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
在本申请一些实施例中，所述重构单元704具体用于：
判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到调整后的全局法向量；
根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
本申请实施例还提供一种计算机设备，其集成了本申请实施例所提供的任一种医学轮廓数据的全局法向量一致性调整装置，所述计算机设备包括：
一个或多个处理器；
存储器；以及
一个或多个应用程序，其中所述一个或多个应用程序被存储于所述存储器中，并配置为由所述处理器执行上述医学轮廓数据的全局法向量一致性调整方法实施例中任一实施例中所述的医学轮廓数据的全局法向量一致性调整方法中的步骤。
如图8所示，其示出了本申请实施例所涉及的计算机设备的结构示意图，具体来讲：
该计算机设备可以包括一个或者一个以上处理核心的处理器801、一个或一个以上计算机可读存储介质的存储器802、电源803和输入单元804等部件。本领域技术人员可以理解，图8中示出的计算机设备结构并不构成对计算机设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器801是该计算机设备的控制中心，利用各种接口和线路连接整个计 算机设备的各个部分，通过运行或执行存储在存储器802内的软件程序和/或模块，以及调用存储在存储器802内的数据，执行计算机设备的各种功能和处理数据，从而对计算机设备进行整体监控。可选的，处理器801可包括一个或多个处理核心；处理器801可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，优选的，处理器801可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器801中。
存储器802可用于存储软件程序以及模块，处理器801通过运行存储在存储器802的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器802可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据计算机设备的使用所创建的数据等。此外，存储器802可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器802还可以包括存储器控制器，以提供处理器801对存储器802的访问。
计算机设备还包括给各个部件供电的电源803，优选的，电源803可以通过电源管理系统与处理器801逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源803还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该计算机设备还可包括输入单元804，该输入单元804可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。
尽管未示出，计算机设备还可以包括显示单元等，在此不再赘述。具体在本实施例中，计算机设备中的处理器801会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器802中，并由处理器801来运行存储在存储器802中的应用程序，从而实现各种功能，如下：
获取目标对象的医学轮廓数据；
获取所述医学轮廓数据的全局法向量；
获取所述医学轮廓数据的样条曲线法向量；
根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
本领域普通技术人员可以理解，上述实施例的各种方法中的全部或部分步骤可以通过指令来完成，或通过指令控制相关的硬件来完成，该指令可以存储于一计算机可读存储介质中，并由处理器进行加载和执行。
为此，本申请实施例提供一种计算机可读存储介质，该存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。其上存储有计算机程序，所述计算机程序被处理器进行加载，以执行本申请实施例所提供的任一种医学轮廓数据的全局法向量一致性调整方法中的步骤。例如，所述计算机程序被处理器进行加载可以执行如下步骤：
获取目标对象的医学轮廓数据；
获取所述医学轮廓数据的全局法向量；
获取所述医学轮廓数据的样条曲线法向量；
根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见上文针对其他实施例的详细描述，此处不再赘述。
具体实施时，以上各个单元或结构可以作为独立的实体来实现，也可以进行任意组合，作为同一或若干个实体来实现，以上各个单元或结构的具体实施可参见前面的方法实施例，在此不再赘述。
以上各个操作的具体实施可参见前面的实施例，在此不再赘述。
以上对本申请实施例所提供的一种医学轮廓数据的全局法向量一致性调 整方法和装置进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种医学轮廓数据的全局法向量一致性调整方法，其特征在于，所述方法包括：
    获取目标对象的医学轮廓数据；
    获取所述医学轮廓数据的全局法向量；
    获取所述医学轮廓数据的样条曲线法向量；
    根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
  2. 根据权利要求1所述的方法，其特征在于，所述获取目标对象的医学轮廓数据，包括：
    获取所述目标对象的原始医学轮廓数据；
    将所述原始医学轮廓数据转换为具有坐标的点云数据；
    过滤所述点云数据中具有相同坐标的点云数据，得到有效点云数据；
    将所述有效点云数据作为所述目标对象的医学轮廓数据。
  3. 根据权利要求1所述的方法，其特征在于，所述获取所述医学轮廓数据的样条曲线法向量，包括：
    获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量。
  4. 根据权利要求3所述的方法，其特征在于，所述获取所述医学轮廓数据的样条曲线切向量，并根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述医学轮廓数据的样条曲线法向量，包括：
    分别以所述医学轮廓数据对应的一个轮廓点为目标轮廓点，获取所述目标轮廓点的样条曲线切向量；
    根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量；
    当所述医学轮廓数据中所有轮廓点的样条曲线法向量确定后，得到所述医学轮廓数据的样条曲线法向量。
  5. 根据权利要求4所述的方法，其特征在于，所述获取所述目标轮廓点的样条曲线切向量，包括：
    对所述医学轮廓数据进行样条曲线拟合，得到所述医学轮廓数据的样条曲线；
    对所述目标轮廓点进行求导，得到所述样条曲线在所述目标轮廓点的样条曲线切向量；
    相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
    将所述样条曲线在所述目标轮廓点的样条曲线切向量的垂线，确定为所述目标轮廓点的样条曲线法向量。
  6. 根据权利要求4所述的方法，其特征在于，所述获取所述目标轮廓点的样条曲线切向量，包括：
    获取所述目标轮廓点的邻接轮廓点；
    将所述目标轮廓点和所述邻接轮廓点组成的向量作为所述目标轮廓点的样条曲线切向量；
    相应的，所述根据预设的样条曲线切向量和样条曲线法向量的关系，确定所述目标轮廓点的样条曲线法向量，包括：
    将所述目标轮廓点和所述邻接轮廓点的中垂线作为所述目标轮廓点的样条曲线法向量。
  7. 根据权利要求1所述的方法，其特征在于，所述获取所述医学轮廓数据的样条曲线法向量，包括：
    获取所述医学轮廓数据的第一样条曲线法向量；
    将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量；
    根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量。
  8. 根据权利要求7所述的方法，其特征在于，所述将所述第一样条曲线法向量中各样条曲线法向量，调整为朝向所述医学轮廓数据的轮廓外侧，以得到第二样条曲线法向量，包括：
    分别以所述第一样条曲线法向量中的一个样条曲线法向量为目标样条曲 线法向量；
    判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧；
    若否，则对所述目标样条曲线法向量进行调整，使所述目标样条曲线法向量的方向朝向所述医学轮廓数据的轮廓外侧；
    当所述第一样条曲线法向量中所有样条曲线法向量调整完成后，得到所述第二样条曲线法向量。
  9. 根据权利要求8所述的方法，其特征在于，所述判断所述目标样条曲线法向量的方向是否朝向所述医学轮廓数据的轮廓外侧，包括：
    获取所述医学轮廓数据所在平面的平面法向量；
    获取所述目标样条曲线法向量的路径向量，所述路径向量为所述目标样条曲线法向量和目标连线向量叉乘运算后的向量，所述目标连线向量为第一轮廓点和第二轮廓点之间连线后形成的向量，所述第一轮廓点为所述目标样条曲线法向量对应的轮廓点，所述第二轮廓点为所述第一轮廓点相邻的轮廓点；
    判断所述平面法向量与所述路径向量是否同向；
    若所述平面法向量与所述路径向量不同向，则确定所述目标样条曲线法向量的方向未朝向所述医学轮廓数据的轮廓外侧。
  10. 根据权利要求9所述的方法，其特征在于，所述获取所述医学轮廓数据所在平面的平面法向量，包括：
    获取所述目标样条曲线法向量对应的平面轮廓点；
    以所述平面轮廓点为起点，确定所述医学轮廓数据所在平面的第三轮廓点和第四轮廓点；
    对所述平面轮廓点与所述第三轮廓点的向量，以及所述第三轮廓点和所述第四轮廓点的向量进行叉乘，得到所述医学轮廓数据所在平面的平面法向量。
  11. 根据权利要求10所述的方法，其特征在于，所述第三轮廓点和所述平面轮廓点之间间隔第一预设数目的轮廓点，所述第四轮廓点和所述第三轮廓点之间间隔第二预设数目的轮廓点。
  12. 根据权利要7所述的的方法，其特征在于，所述根据所述第二样条曲 线法向量，得到所述医学轮廓数据的样条曲线法向量，包括：
    将所述第二样条曲线法向量作为所述医学轮廓数据的样条曲线法向量。
  13. 根据权利要求7所述的的方法，其特征在于，所述根据所述第二样条曲线法向量，得到所述医学轮廓数据的样条曲线法向量，包括：
    对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量。
  14. 根据权利要求13所述的方法，其特征在于，所述对所述第二样条曲线法向量中的样条曲线法向量有效性验证，得到所述医学轮廓数据的样条曲线法向量，包括：
    分别以所述第二样条曲线法向量中的一个样条曲线法向量为目标待调法向量；
    获取所述目标待调法向量的邻接待调法向量；
    验证所述目标待调法向量与所述邻接待调法向量是否垂直；
    若垂直，则对所述目标待调法向量进行角度调整，使所述目标待调法向量与所述邻接待调法向量不垂直；
    当所述第二样条曲线法向量中所有样条曲线法向量有效性验证完成后，得到所述医学轮廓数据的样条曲线法向量。
  15. 根据权利要求1所述的方法，其特征在于，所述根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量，包括：
    判断所述全局法向量与所述样条曲线法向量的夹角是否大于预设值；
    若所述夹角大于所述预设值，则根据所述样条曲线法向量对所述全局法向量进行调整，得到一致的全局法向量。
  16. 一种医学轮廓数据的重构方法，其特征在于，所述方法包括：
    获取目标对象的医学轮廓数据；
    获取所述医学轮廓数据的全局法向量；
    获取所述医学轮廓数据的样条曲线法向量；
    根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重 构模型。
  17. 一种医学轮廓数据的全局法向量一致性调整装置，其特征在于，所述装置包括：
    第一获取单元，用于获取目标对象的医学轮廓数据；
    第二获取单元，用于获取所述医学轮廓数据的全局法向量；
    第三获取单元，用于获取所述医学轮廓数据的样条曲线法向量；
    调整单元，用于根据所述样条曲线法向量调整所述全局法向量，得到一致的全局法向量。
  18. 一种医学轮廓数据的重构装置，其特征在于，所述装置包括：
    第一获取单元，用于获取目标对象的医学轮廓数据；
    第二获取单元，用于获取所述医学轮廓数据的全局法向量；
    第三获取单元，用于获取所述医学轮廓数据的样条曲线法向量；
    重构单元，用于根据所述样条曲线法向量调整所述全局法向量，得到调整后的全局法向量，根据所述调整后的全局法向量进行曲面重构，得到所述目标对象的曲面重构模型。
  19. 一种计算机设备，其特征在于，所述计算机设备包括：
    一个或多个处理器；
    存储器；以及
    一个或多个应用程序，其中所述一个或多个应用程序被存储于所述存储器中，并配置为由所述处理器执行以实现权利要求1至15中任一项所述的医学轮廓数据的全局法向量一致性调整方法，或权利要求16中所述的医学轮廓数据的重构方法。
  20. 一种计算机可读存储介质，其特征在于，其上存储有计算机程序，所述计算机程序被处理器进行加载，以执行权利要求1至15任一项所述的医学轮廓数据的全局法向量一致性调整方法中的步骤，或权利要求16所述的医学轮廓数据的重构方法中的步骤。
PCT/CN2020/142019 2020-12-31 2020-12-31 医学轮廓数据的全局法向量一致性调整方法和装置 WO2022141368A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/142019 WO2022141368A1 (zh) 2020-12-31 2020-12-31 医学轮廓数据的全局法向量一致性调整方法和装置
CN202080108424.3A CN116917948A (zh) 2020-12-31 2020-12-31 医学轮廓数据的全局法向量一致性调整方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/142019 WO2022141368A1 (zh) 2020-12-31 2020-12-31 医学轮廓数据的全局法向量一致性调整方法和装置

Publications (1)

Publication Number Publication Date
WO2022141368A1 true WO2022141368A1 (zh) 2022-07-07

Family

ID=82258870

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/142019 WO2022141368A1 (zh) 2020-12-31 2020-12-31 医学轮廓数据的全局法向量一致性调整方法和装置

Country Status (2)

Country Link
CN (1) CN116917948A (zh)
WO (1) WO2022141368A1 (zh)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104424655A (zh) * 2013-09-10 2015-03-18 鸿富锦精密工业（深圳）有限公司 点云曲面重构系统及方法
CN106683176A (zh) * 2016-12-30 2017-05-17 飞依诺科技(苏州)有限公司 一种脏器三维模型构建方法及装置

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104424655A (zh) * 2013-09-10 2015-03-18 鸿富锦精密工业（深圳）有限公司 点云曲面重构系统及方法
CN106683176A (zh) * 2016-12-30 2017-05-17 飞依诺科技(苏州)有限公司 一种脏器三维模型构建方法及装置

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LIU DAFENG,DAI NING,SUN QUANPING,LIAO WENHE: "Algorithm for Adjusting Directions of Normal Vectors of Tangent Planes Based on Surface Reconstruction", MECHANICAL SCIENCE AND TECHNOLOGY FOR AEROSPACE ENGINEERING, vol. 27, no. 2, 15 February 2008 (2008-02-15), pages 192 - 197, XP055948170, ISSN: 1003-8728, DOI: 10.13433/j.cnki.1003-8728.2008.02.027 *
YI CHUANYUN , WANG TAO: "Solution of the Normal Vector on Digitalized Surface", JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY, vol. 30, no. 8, 30 August 2002 (2002-08-30), pages 49 - 51, XP055948175, ISSN: 1671-4512, DOI: 10.13245/j.hust.2002.08.017 *

Also Published As

Publication number Publication date
CN116917948A (zh) 2023-10-20

Similar Documents

Publication Publication Date Title
US20110262015A1 (en) Image processing apparatus, image processing method, and storage medium
US9595121B2 (en) Systems and methods for PET penalized-likelihood image reconstruction with spatially varying smoothing parameters
CN106887000B (zh) 医学图像的网格化处理方法及其系统
US9256967B2 (en) Systems and methods for partial volume correction in PET penalized-likelihood image reconstruction
US8068650B2 (en) Lesion quantification and tracking using multiple modalities
US10346504B2 (en) 3D modelling of bodies
US20070165948A1 (en) Mesh models with internal discrete elements
CN106683176A (zh) 一种脏器三维模型构建方法及装置
WO2017148332A1 (zh) 一种灌注分析方法与设备
CN111340756B (zh) 一种医学图像病变检出合并方法、系统、终端及存储介质
Chen et al. Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds
JP5194138B2 (ja) 画像診断支援装置およびその動作方法、並びに画像診断支援プログラム
Filko et al. Wound measurement by RGB-D camera
JP2021506434A (ja) 肺画像を評価するためのシステム及び方法
Hill et al. Constrained distance transforms for spatial atlas registration
CN113888566B (zh) 目标轮廓曲线确定方法、装置、电子设备以及存储介质
WO2022141368A1 (zh) 医学轮廓数据的全局法向量一致性调整方法和装置
CN114219919A (zh) 医学图像的处理方法、装置、计算机设备及存储介质
CN115311334A (zh) 图像配准评估方法、计算机设备及可读存储介质
Cheng et al. Ground truth delineation for medical image segmentation based on Local Consistency and Distribution Map analysis
CN114758073A (zh) 一种基于rgbd输入和柔性配准口腔数字化系统
CN108230377B (zh) 点云数据的拟合方法和系统
Wang et al. Graph-based segmentation of lymph nodes in CT data
Wan et al. Variational reconstruction of left cardiac structure from CMR images
Zhang et al. An effective approach of teeth segmentation within the 3D cone beam computed tomography image based on deformable surface model

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20967707

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 202080108424.3

Country of ref document: CN

122 Ep: pct application non-entry in european phase

Ref document number: 20967707

Country of ref document: EP

Kind code of ref document: A1