Vascular respiratory motion atlas construction method, device, equipment and medium

Abstract

This invention discloses a method, apparatus, device, and medium for constructing a vascular respiratory motion map, relating to the field of medical technology. The method establishes a directed vascular graph based on the topological connectivity within the vascular structure. By extracting structural control points and calculating branch bending energy, it quantifies the overall displacement of the blood vessel and the posture of each branch. The propagation direction of motion between branch points is defined, providing consistency constraints for vascular motion modeling. Adaptive deformation compensation is used to quantify vascular deformation in motion modeling, employing rotation and stretching metrics to characterize the motion deformation of each branch segment in a spherical coordinate system within manifold space. Simultaneously, based on the vascular map and SRVF constraints, bending energy weights are adaptively assigned to each branch, improving the model's learning efficiency for local posture deformation.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a method, apparatus, device, and medium for constructing vascular respiratory motion maps based on topological constraints and deformation compensation. Background Technology

[0002] In hepatic vascular interventional surgery, the displacement and deformation of hepatic vessels caused by the patient's free breathing pose a significant challenge to the accuracy and safety of the surgery. Usually, interventional physicians use preoperative computed tomography (CTA) to obtain the patient's three-dimensional (3D) vascular structure and combine it with the enhanced vascular branches in the intraoperative X-ray angiography (XRA) sequence to complete the operation through spatial imagination and clinical experience [1]. This method of estimating vascular motion based on experience is prone to deviation in complex situations, thus affecting the surgical outcome. In order to quantify the movement of vascular branches during the operation, it is usually necessary to continuously inject contrast agent until the blood vessels are filled, and then establish a two-dimensional (2D) vascular motion model based on the periodic movement of visible branches during the respiratory cycle. Then, dynamic vascular pathway maps are generated through these models and superimposed on real-time X-ray fluoroscopic image sequences to provide intraoperative navigation support for interventional operations. On this basis, Ma et al. compensated for the vascular motion caused by heartbeat and breathing by aligning 2D image frames with ECG signals and tracking the catheter tip in motion modeling. Wang et al. input high-resolution features into the detection network to extract more refined vascular motion features from X-ray images; Yang et al. used an optical flow-based method to extract the displacement and deformation of angiographic vascular branches during respiratory motion.

[0003] Meanwhile, in order to complete the 2D motion modeling of blood vessels and reduce the use of contrast agents during the operation, many studies have used the 3D / 2D registration method to project the preoperative vascular structure onto the intraoperative X-ray image sequence, and then combined it with 2D motion modeling to obtain the 2D dynamic pose of the blood vessels. Baka et al. proposed a method based on directional Gaussian mixture model to reduce the interference of 3D / 2D initial pose difference and image noise, thereby improving the accuracy of vascular motion estimation. Ambrosini et al. registered 3D blood vessels with 2D guide wires based on the hidden Markov model, and guided the 3D blood vessel branches to the corresponding positions through the trajectory of the guide wire between frames.

[11] A population-based method was proposed to establish a coronary artery motion model to provide constraints for 2D+t / 3D registration, including the average range of coronary artery motion and the change of heart shape during coronary artery deformation. In order to further improve the estimation accuracy of deformation motion, a neural network based on deep learning was proposed. The segment-by-segment registration method was adopted, and the center line that retains the topological information of blood vessels was represented by the origin tensor and the shape tensor, and input into the network to predict the deformation field of each segment. Although the methods described above can generate dynamic poses of blood vessels on 2D images, their output is still limited to planar information.

[0004] To achieve 3D respiratory motion modeling of blood vessels, it is necessary to quantify the three-dimensional pose changes of blood vessels under different respiratory states. However, current research mainly focuses on 3D motion modeling of organs. Typically, such studies acquire organ structures at different time phases using 4D-CT scans and extract features to characterize organ position and morphological changes. Common methods include using principal component analysis (PCA) to achieve statistical shape modeling (SSM), which generates organ shape templates by extracting edge feature points of organs and performing sparse representation on dense shape meshes. Further developed statistical deformation models (SDM) establish deformation libraries for the pose changes of multiple organs during respiratory motion, not only performing local statistics and quantification on different regions of organs but also incorporating the inter-organ motion correlations into the model. To make the motion template more closely resemble the patient's actual 3D organ motion during surgery, the patient's intraoperative X-ray image sequence is correlated with the 3D motion template through 2D / 3D deformation registration. Guided by the contours of the diaphragm or lungs, these methods can achieve personalized dynamic deformation prediction for the liver and lungs. In addition to organ structure-based analysis, some studies have also directly performed motion modeling on 4D-CT images. Fu et al. proposed a group registration method based on global-local map contraction to construct a 3D motion atlas of the liver.

[0005] Similarly, to obtain hepatic vascular structures under different respiratory states, clinical practice typically involves acquiring CT images at multiple respiratory phases using 4D-CTA scanning, followed by vascular segmentation techniques to extract the vascular branch distribution at each phase. Several 3D point cloud registration algorithms have been used to calculate the transformation relationship between the initial and target vascular poses. These include the Iterative Nearest Point (ICP) algorithm using a nearest neighbor matching strategy, the Coherent Point Drift (CPD) algorithm which completes registration through probability density estimation, and the centerline-guided Gaussian mixture model-based registration algorithm (CG-GMM). Considering the rich branching of blood vessels, Zhu et al. quantified matching scores using a heuristic tree search strategy and optimized node matching to obtain a registration matrix with a higher score. Furthermore, non-rigid registration iteratively reduces rigidity weights, allowing the initial structure to deform locally to adapt to the target structure. Khallaghi et al., based on prior knowledge from biomechanical models, used a finite element model (FEM) to generate a deformation field for non-rigid registration. While this method can accurately characterize complex deformation features, its computational complexity is high and it is highly dependent on the alignment accuracy of the initial pose.

[0006] To address this, manifold regularization constraints based on Hilbert space transform are introduced into the registration process. This method, by balancing the weight constraints of structural deformation and shape preservation, can extract intrinsic information about the structure from unmatched feature point pairs. However, how to quickly and accurately estimate the motion patterns of hepatic vessels and extract effective features from vascular structures in multiple patients and multiple phases to establish a general motion model remains a challenge that urgently needs to be solved. Summary of the Invention

[0007] In view of the above problems, the present invention provides a method, apparatus, device and medium for constructing a vascular respiratory motion map to overcome the above problems or at least partially solve the above problems.

[0008] This invention provides the following solution:

[0009] A method for constructing a vascular respiratory motion atlas includes:

[0010] Acquire 4D-CTA image data of the patient, the 4D-CTA image data including vascular images;

[0011] The 4D-CTA image data is input into the constructed respiratory motion model so that the respiratory motion model can output a 4D vascular motion atlas.

[0012] The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints.

[0013] The data preprocessing includes extracting vascular structures and vascular centerlines from the 4D-CTA images using the TotalSegmentator algorithm and morphological algorithms, respectively, and calculating the lumen diameter at each centerline point;

[0014] The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy.

[0015] The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints.

[0016] The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

[0017] Preferably, the structural control points include vascular branch endpoints, bifurcation points, and branch points. A distance vector between the structural control points is established to characterize the direction and amplitude of the displacement vector of each branch in order to approximate the movement of a dense set of vascular points.

[0018] The bending energy of the corresponding segment is quantified by calculating the curvature of dense points on the center line of the segmented branch.

[0019] Preferably, the topological constraint is represented by the following formula:

[0020]

[0021] In the formula: C represents the curvature matrix, Let represent the displacement matrix of the centerline point set, and La represent the Laplacian matrix.

[0022] Preferably: the quantification of branch deformation by characterizing the motion and deformation of each segment using rotation and stretching metrics in the spherical coordinate system of the manifold space includes:

[0023] The branch structure β is transformed from a spatial rectangular coordinate system (x, y, z) to a spherical coordinate system (r, θ, φ). Rotation is quantified by measuring the change in the direction of the tangent vector of curve f on branch β along the deformation path, and stretching is quantified by measuring the change in the length of the curve along the deformation path.

[0024] Preferably, the adaptive deformation compensation constraint is expressed by the following formula:

[0025]

[0026] In the formula: W represents the branch bending energy weight matrix, O represents the branch rotation metric matrix, and L represents the branch length metric matrix.

[0027] Preferably, the branch rotation metric matrix includes all branch rotation metrics, and each branch rotation metric is represented by the following formula:

[0028]

[0029] In the formula: a and b represent constant weights, Let e ​​be the unit vector tangent to curve f at point s. φ(s) This represents the magnitude of the tangent vector at point s;

[0030] The branch length metric matrix includes all branch length metrics, which are represented by the following formula:

[0031]

[0032] In the formula: It is a velocity vector, and The inner product <·> is used as a definite metric operator.

[0033] Preferably, the overall structural constraint is represented by the following formula:

[0034]

[0035] In the formula: Ls(Δv) and Ls(Δr) represent the absolute values ​​of the differences in vessel diameter and volume under different respiratory phases, respectively, w m The bending energy weights are the points on the branch centerline, and num represents the number of branches in the current vascular structure.

[0036] A vascular respiratory motion atlas construction device is used to perform the above-described vascular respiratory motion atlas construction method, the device comprising:

[0037] An image acquisition unit is used to acquire 4D-CTA image data of a patient, the 4D-CTA image data including vascular images;

[0038] The motion atlas output unit is used to input the 4D-CTA image data into the constructed respiratory motion model so that the respiratory motion model outputs a 4D vascular motion atlas.

[0039] The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints.

[0040] The data preprocessing includes extracting vascular structures and vascular centerlines from the 4D-CTA images using the TotalSegmentator algorithm and morphological algorithms, respectively, and calculating the lumen diameter at each centerline point;

[0041] The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy.

[0042] The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints.

[0043] The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

[0044] A device for constructing a vascular respiratory motion map, the device comprising a processor and a memory:

[0045] The memory is used to store program code and transmit the program code to the processor;

[0046] The processor is used to execute the above-described method for constructing a vascular respiratory motion map according to the instructions in the program code.

[0047] A computer-readable storage medium is characterized in that the computer-readable storage medium is used to store program code, the program code being used to execute the above-described method for constructing a vascular respiratory motion map.

[0048] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0049] This application provides a method, apparatus, device, and medium for constructing a vascular respiratory motion map. Based on the topological connections within the vascular structure, a directed vascular graph is established. By extracting structural control points and calculating branch bending energy, the overall displacement of the vessel and the posture of each branch are quantified. The propagation direction of motion between branch points is defined, providing consistency constraints for vascular motion modeling. Adaptive deformation compensation is used to quantify vascular deformation in motion modeling. Rotation and stretching metrics are used to characterize the motion deformation of each branch segment in a spherical coordinate system within manifold space. Simultaneously, bending energy weights are adaptively assigned to each branch based on the vascular map and SRVF constraints, improving the model's learning efficiency for local posture deformation. Furthermore, a vascular structure preservation constraint is introduced. By designing a loss minimization metric, the integrity of the skeleton and the luminal retention during deformation are jointly optimized to avoid topological breakage and changes in vascular volume. This method can effectively capture the dynamic deformation characteristics of hepatic vessels, providing reliable motion modeling support for interventional surgical navigation under complex respiratory conditions.

[0050] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0052] Figure 1 This is a flowchart of the method for constructing a vascular respiratory motion map provided in an embodiment of the present invention;

[0053] Figure 2 This is a framework diagram of the vascular respiratory motion atlas construction method provided in the embodiments of the present invention;

[0054] Figure 3This is a schematic diagram of the vascular respiratory motion atlas construction device provided in an embodiment of the present invention;

[0055] Figure 4 This is a schematic diagram of the vascular respiratory motion atlas construction device provided in an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0057] See Figure 1 This invention provides a method for constructing a vascular respiratory motion atlas, such as... Figure 1 As shown, the method may include:

[0058] S101: Acquire the patient's 4D-CTA image data, wherein the 4D-CTA image data includes vascular images;

[0059] S102: Input the 4D-CTA image data into the constructed respiratory motion model so that the respiratory motion model outputs a 4D vascular motion atlas;

[0060] The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints.

[0061] The data preprocessing includes extracting vascular structures and vascular centerlines from the 4D-CTA images using TotalSegmentator and morphological algorithms, respectively, and calculating the lumen diameter at each centerline point;

[0062] The topological constraints include establishing a directed graph of blood vessels based on the topological connections within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the posture of each branch by extracting structural control points and calculating branch bending energy. In specific implementation, the embodiments of this application may provide that the structural control points include the endpoints, bifurcation points and branch points of blood vessels, and establish distance vectors between the structural control points to characterize the direction and motion amplitude of each branch displacement vector in order to approximate the motion of a dense set of blood vessel points.

[0063] The bending energy of the corresponding segment is quantified by calculating the curvature of dense points on the center line of the segmented branch.

[0064] Furthermore, the topological constraints are represented by the following formula:

[0065]

[0066] In the formula: C represents the curvature matrix, Let represent the displacement matrix of the centerline point set, and La represent the Laplacian matrix.

[0067] The adaptive deformation compensation constraint includes quantifying the deformation of each branch by characterizing the motion deformation of each segment in the spherical coordinate system of the manifold space using rotation and stretching metrics, and adaptively assigning bending energy weights to each branch based on the vascular map and SRVF constraints. Specifically, embodiments of this application may provide that quantifying the deformation of each branch by characterizing the motion deformation of each segment in the spherical coordinate system of the manifold space using rotation and stretching metrics includes:

[0068] The branch structure β is transformed from a spatial rectangular coordinate system (x, y, z) to a spherical coordinate system (r, θ, φ). Rotation is quantified by measuring the change in the direction of the tangent vector of curve f on branch β along the deformation path, and stretching is quantified by measuring the change in the length of the curve along the deformation path.

[0069] The adaptive deformation compensation constraint is expressed by the following equation:

[0070]

[0071] In the formula: W represents the branch bending energy weight matrix, O represents the branch rotation metric matrix, and L represents the branch length metric matrix.

[0072] Furthermore, the branch rotation metric matrix includes all branch rotation metrics, each of which is represented by the following formula:

[0073]

[0074] In the formula: a and b represent constant weights, Let φ(s) represent the unit vector tangent to curve f at point s, and let eφ(s) represent the magnitude of the tangent vector at point s.

[0075] The branch length metric matrix includes all branch length metrics, which are represented by the following formula:

[0076]

[0077] In the formula: It is a velocity vector, and The inner product <·> is used as a definite metric operator.

[0078] The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

[0079] In a specific implementation, the overall structure retention constraint of this application embodiment can be expressed by the following formula:

[0080]

[0081] In the formula: Ls(Δv) and Ls(Δr) represent the absolute values ​​of the differences in vessel diameter and volume under different respiratory phases, respectively, w m The bending energy weights are the points on the branch centerline, and num represents the number of branches in the current vascular structure.

[0082] The vascular respiratory motion atlas construction method provided in this application establishes a directed vascular graph based on the topological connectivity within the vascular structure. By extracting structural control points and calculating branch bending energy, the overall displacement of the vascular system and the posture of each branch are quantified. This defines the propagation direction of motion between branch points, providing consistency constraints for vascular motion modeling.

[0083] An adaptive deformation compensation method is proposed to quantify vascular deformation in motion modeling. Rotation and stretching metrics are used to characterize the motion deformation of each branch segment in a spherical coordinate system within manifold space. Simultaneously, bending energy weights are adaptively assigned to each branch based on the vascular map and SRVF constraints, improving the model's learning efficiency for local posture deformation. A vascular structure preservation constraint is introduced, and a loss minimization metric is designed to jointly optimize the skeletal integrity and lumen retention during deformation, avoiding topological breakage and changes in vascular volume.

[0084] The method for constructing vascular respiratory motion atlases provided in this application will be described in detail below.

[0085] like Figure 2 As shown in the embodiments of this application, the method for constructing a vascular respiratory motion atlas comprises four parts: data preprocessing, topological connectivity constraints, adaptive deformation compensation, and overall structure preservation. The input data consists of 4D-CTA image data from multiple patients. After processing by the respiratory motion model, a 4D motion atlas of blood vessels is output. This atlas contains vascular deformation fields between multiple respiratory phases, used to predict continuous vascular pose changes within the respiratory cycle.

[0086] 1. Data preprocessing.

[0087] In the preprocessing, this application uses TotalSegmentator and morphological algorithms to extract vascular structures and vascular centerlines from 4D-CTA images, and calculates the lumen diameter at each centerline point. After sampling normalization and coordinate alignment of the vascular point sets for each phase (0%-90%), two different respiratory phases of vascular data are randomly selected from multiple phases in the 4D-CTA image for motion analysis. This process iterates through all combinations of phase data to finally complete respiratory motion modeling and obtain a 4D respiratory motion atlas of the blood vessels.

[0088] 2. Topology connection constraints.

[0089] The vascular topology exhibits geometric invariance during respiratory motion, ensuring that the connections between branches remain constant throughout the process. To guarantee the accuracy of vascular deformation compensation and improve the computational efficiency of respiratory modeling, this application introduces topological connectivity constraints to maintain the structural consistency of blood vessels under different respiratory states.

[0090] First, this application constructs a topological structure based on the input set of vessel centerline points. This structure can be defined as a curve obtained by connecting the vessel bifurcation points and branch endpoints, which are considered vertices. It describes the connection relationships between the vessel centerline points and the vessel's orientation. Graph models are the most common way to represent vessel topology. After obtaining the coordinates of the vessel centerline point set, the root nodes, endpoints, bifurcation points, branch points, and segmented curves of the vessel can be identified. This application defines these points as the structural control points of the vessel.

[0091] Through the centerline point set To determine the topological connectivity between nodes, this application establishes an adjacency matrix A∈[0,1]. K×K Sum and metric matrix D K×K Here, K represents the number of structural control points, and defines the vascular structure consistency constraint based on topological connections in motion modeling. A(i,j) = 1 indicates that the i-th point is connected to the j-th point; in other states, A(i,j) = 0. The value of D(i,j) represents the number of branches connected at the i-th centerline point. The motion of each branch node propagates unidirectionally along the topological direction, and other affected nodes and branch points can be uniquely determined by A and D.

[0092] Meanwhile, with the establishment of topological connectivity between nodes, the displacements of topologically adjacent points exhibit consistency. This application uses topological regularization terms. To constrain these topological adjacency points:

[0093]

[0094] in, The displacement matrix represents the set of points along the centerline. Constrain the variation in the length of the branch centerline. This is based on the definition of a Laplace graph. It can be represented by a manifold, and the topological relation can be extended to a Laplacian matrix La = DA, where Therefore, formula (1) can be expressed in the following matrix form:

[0095]

[0096] Here, tr(·) represents the trace of the matrix.

[0097] Based on the identified vascular branch endpoints, bifurcation points, and branching points, this application can construct a displacement matrix. The construction of the displacement matrix involves the vascular centerline at two different respiratory phases, including the initial phase and the target phase. Each element τ in the displacement matrix... ij This represents the spatial distance between the i-th point on the initial phase vessel centerline and the j-th point on the target phase vessel centerline. Based on this, this application establishes a distance vector between structural control points to characterize the direction and amplitude of the displacement vector of each branch, thereby fully approximating the motion of the dense vessel point set.

[0098] In respiratory motion, the curvature of the segmented vascular curve is also an important feature in motion modeling. As the curvature of the branches increases, the accumulated bending elastic potential energy within the branch structure causes the local region to reach maximum entropy (LME), making that part more prone to deformation during respiratory motion. Therefore, this application quantifies the bending energy of a segment by calculating the curvature of dense points on the centerline of the segmented branch based on the constructed topological connectivity. Here, this application uses three-dimensional Bezier curve fitting to perform energy calculation. Let P0, P1, and P2 be any three points on the centerline of the same branch, P0, P1, P2 ∈ X. The Bezier curve equation is defined as follows:

[0099] B(μ)=(1-μ) 2 P0+2(1-μ)μP1+μ 2 P2 (3)

[0100] Where μ∈[0,1], P0, P1, and P2 represent three-dimensional coordinates. To obtain the curvature... The first and second derivatives of the Bezier curve are calculated as follows:

[0101] B′(μ)=2(1-μ)(P1-P0)+2μ(P2-P1), B″(μ)=2(P2-2P1+P0). (4)

[0102] The curvature κ(μ) can then be calculated using the following formula:

[0103]

[0104] Where × denotes the cross product of vectors, and |·| denotes the modulus operation of vectors. The resulting κ(μ) of each branch of the multi-phase system is statistically recorded as a curvature matrix C, where each element c ij ∈C represents the curvature value of the segment formed by connecting the i-th point and the j-th point along the centerline on the branch. In summary, this application constructs topological connectivity constraints based on the centerline point set. It encompasses branch structure consistency metrics, branch displacement metrics, and branch bending metrics, and can be expressed by the following formula:

[0105]

[0106] 3. Adaptive deformation compensation.

[0107] During respiration, inconsistent deformation occurs in different regions of the liver parenchyma, resulting in diverse deformation distributions of the hepatic vessels enclosed by the parenchyma across their branches. This application proposes an adaptive deformation compensation model to enhance the posture learning of local branches, reducing the interference of deformation errors. The essence of branch deformation diversity lies in the inconsistent rotation and stretching of different branches during respiration. To address this issue, this application utilizes a non-rigid measure to quantify bending characteristics.

[0108] First, this application transforms the branch structure β from a spatial rectangular coordinate system (x, y, z) to a spherical coordinate system (r, θ, φ). Rotation is quantified by measuring the change in the direction of the tangent vector of curve f on branch β along the deformation path, and stretching is quantified by measuring the change in the length of the curve along the deformation path. Where f ∈ β, the deformation path α can be represented as... It indicates that during the respiratory phase t1 to t2, the branching... Deformed to And obtained It is defined in the Hilbert manifold space. The sphere in the diagram. The branch β can be parameterized as... Where D is a parameterized specific field. This application restricts branches β that are absolutely continuous on D, and D is usually set to [0, 1].

[0109] Furthermore, the stretching of the branch should be related to the elongation of the branch curve f, which can be quantified by observing the magnitude of the change in the tangent vector along curve f at each point s along the deformation path. The branch length metric L[β] can be defined as:

[0110]

[0111] in, It is a velocity vector, and The inner product <·> is used as a definite metric operator.

[0112] In fact, branch β can be obtained by the following formula:

[0113]

[0114] Then for a continuous curve f at every point s, we have:

[0115]

[0116] Where θ(s) is the unit vector tangent to curve f at point s, and e φ(s) Then, the magnitude of the tangent vector is represented, defined as:

[0117]

[0118] The branch rotation metric is defined as the weighted sum of φ and θ along the deformation path α:

[0119]

[0120] Where a and b represent constant weights. The first term in the above formula quantifies the change in elevation angle θ, and the second term quantifies the change in azimuth angle φ. The sum of these two terms is equivalent to The rotation metric between curves in space, combined with the branch length metric L[β], can effectively quantify the deformation process of the branch structure. To improve the computational efficiency of learning the pose of branch β, this application establishes a mapping relationship for branch β using the Square Root Velocity Function (SRVF). The specific form is as follows:

[0121]

[0122] Here, ||·|| represents the Euclidean 2-norm norm in the real space, and F is a continuous mapping. This application uses the SRVF form of the elasticity metric to replace the representation of the pose of each vascular branch, and preferentially performs SRVF mapping in the region near the structural control point (structural control region). Then, the deformation constraint of branch β... It can be represented as:

[0123]

[0124] Here, c, like a and b, is a constant weight.

[0125] After quantifying the deformation of each branch, this application requires adaptive compensation for the deformation on each branch. Based on Bezier curves, this application calculates the bending energy of segmented branches. For the entire vascular structure, branch segments with higher bending energy are more likely to deform preferentially during respiratory motion, thus influencing the deformation of other segments in the branch topology. Therefore, this application assigns weights based on the bending energy distribution of all branches in the current vascular structure. If the current vascular structure has a total of num branches, the sum of the energies of all branches is... The weight of the deformation constraint for each branch is w m =κ(μ) m / κ sum Therefore, the adaptive deformation compensation constraint for the branch can be updated as follows:

[0126]

[0127] Rewritten in matrix form:

[0128]

[0129] 4. Preservation of vascular structure.

[0130] After completing adaptive deformation compensation for vascular branches, maintaining the structural integrity of the vascular branches can further encompass the diverse vascular postures of multiple patients in motion modeling. This application decomposes this into maintaining the integrity of the vascular skeleton structure and maintaining the invariance of branch lumen volume, ensuring that topological control points are not lost, topological connections are not broken, and lumen diameters do not degrade during motion. This application performs branch decomposition on the deformed vascular structure through the extracted vascular centerline, making the deformation of each branch relatively independent during respiratory motion.

[0131] Meanwhile, to maintain the lumen volume unchanged during the deformation of the blood vessel from the initial structure to the target structure, this application uses morphological methods in the preprocessing stage to calculate the diameter *r* and the total lumen volume *v* at the corresponding centerline points before and after deformation, i.e., the number of voxels occupied by the blood vessel, and designs a loss minimization metric to jointly optimize the diameter and volume losses during the blood vessel posture deformation process. When the respiratory phase changes from t1 to t2, the branches... Deformed to The diameter of the pipe at a certain point on the center line is from Become The total volume of blood vessels is Become Furthermore, since the more severe the branch deformation, the easier it is for the pipe diameter to change, this application introduces a branch bending energy weighting matrix W. Therefore, the overall structural maintenance constraint can be defined as:

[0132]

[0133] Where Ls(Δv) and Ls(Δr) represent the absolute values ​​of the differences in vessel diameter and volume at different respiratory phases, respectively, w m Let be the bending energy weight corresponding to each point on the branch centerline. Therefore, the breathing motion model constructed in this application based on topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints can be defined by the following formula:

[0134]

[0135] Experimental results show that the method proposed in this application is superior to the latest motion modeling methods, and in clinical free breathing mode, the vasomotor estimation error is: Hausdorff distance is 1.04±0.27 mm, and root mean square error is 1.26±0.26 mm.

[0136] In summary, the vascular respiratory motion atlas construction method provided in this application aims to explore the motion patterns of hepatic vessels and construct their 4D motion atlas. First, a vascular map structure is constructed based on the topological connections between vascular branches, and the overall uniform displacement and branch posture of the vessels are quantified by extracting structural control points and calculating bending energy. Then, the Euclidean coordinates of the vascular branches are converted to manifold coordinates using the spherical coordinate system of Hilbert manifold space, and the deformation information of the vessels is characterized by quantifying the rotation and stretching of the branches. Based on this, local deformation of each branch is adaptively compensated by combining the vascular topology map and square root velocity function (SRVF) constraints. Finally, a vascular structure preservation constraint is introduced, and the consistency and integrity of the vascular morphology are ensured by designing a loss function that minimizes topological structure breakage and luminal volume changes. Experimental results show that this method can effectively capture the dynamic deformation characteristics of hepatic vessels, providing reliable motion modeling support for interventional surgical navigation under complex respiratory conditions.

[0137] See Figure 3 This application embodiment can also provide a vascular respiratory motion atlas construction device, such as... Figure 3 As shown, the device may include:

[0138] Image acquisition unit 301 is used to acquire 4D-CTA image data of a patient, the 4D-CTA image data including vascular images;

[0139] The motion atlas output unit 302 is used to input the 4D-CTA image data into the constructed respiratory motion model so that the respiratory motion model outputs a 4D vascular motion atlas.

[0140] The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints.

[0141] The data preprocessing includes extracting vascular structures and vascular centerlines from the 4D-CTA images using the TotalSegmentator algorithm and morphological algorithms, respectively, and calculating the lumen diameter at each centerline point;

[0142] The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy.

[0143] The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints.

[0144] The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

[0145] This application embodiment can also provide a vascular respiratory motion atlas construction device, the device including a processor and a memory:

[0146] The memory is used to store program code and transmit the program code to the processor;

[0147] The processor is used to execute the steps of the above-described method for constructing a vascular respiratory motion map according to the instructions in the program code.

[0148] like Figure 4 As shown in the figure, a vascular respiratory motion atlas construction device provided in this application embodiment may include: a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, memory 11, and communication interface 12 all communicate with each other through the communication bus 13.

[0149] In this embodiment, the processor 10 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic devices.

[0150] The processor 10 can call the program stored in the memory 11. Specifically, the processor 10 can execute the operations in the embodiments of the vascular respiratory motion map construction method.

[0151] The memory 11 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 11 stores at least a program for implementing the following functions:

[0152] Acquire 4D-CTA image data of the patient, the 4D-CTA image data including vascular images;

[0153] The 4D-CTA image data is input into the constructed respiratory motion model so that the respiratory motion model can output a 4D vascular motion atlas.

[0154] The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints.

[0155] The data preprocessing includes extracting vascular structures and vascular centerlines from the 4D-CTA images using the TotalSegmentator algorithm and morphological algorithms, respectively, and calculating the lumen diameter at each centerline point;

[0156] The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy.

[0157] The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints.

[0158] The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

[0159] In one possible implementation, the memory 11 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function (such as file creation or data read / write). The data storage area may store data created during use, such as initialization data.

[0160] In addition, memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0161] Communication interface 12 can be an interface for the communication module, used to connect with other devices or systems.

[0162] Of course, it should be noted that, Figure 4The structure shown does not constitute a limitation on the vascular respiratory motion mapping device in the embodiments of this application. In practical applications, the vascular respiratory motion mapping device may include devices that are more advanced than those described above. Figure 4 More or fewer components as shown, or combinations of certain components.

[0163] This application embodiment may also provide a computer-readable storage medium for storing program code for executing the steps of the above-described method for constructing a vascular respiratory motion map.

[0164] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0165] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0166] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0167] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method for constructing a vascular respiratory motion atlas, characterized in that, include: Acquire 4D-CTA image data of the patient, the 4D-CTA image data including vascular images; The 4D-CTA image data is input into the constructed respiratory motion model so that the respiratory motion model can output a 4D vascular motion atlas. The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints. The data preprocessing includes using respectively... Algorithms and morphological algorithms extract vascular structures and vascular centerlines from the 4D-CTA images and calculate the lumen diameter at each centerline point. The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy. The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints. The overall structural preservation constraint includes joint optimization of skeleton integrity and cavity retention during deformation using a loss minimization metric; The adaptive deformation compensation constraint is expressed by the following equation: In the formula: This represents the branch bending energy weight matrix. Represents the branch rotation metric matrix. Represents the branch length metric matrix; The branch rotation metric matrix includes all branch rotation metrics, each of which is represented by the following formula: In the formula: and Indicates constant weight. Indicates at point Tangent to the curve unit vector, Then it represents a point The magnitude of the tangent vector; The branch length metric matrix includes all branch length metrics, which are represented by the following formula: In the formula: It is a velocity vector, and inner product As a defined metric operator.

2. The method for constructing a vascular respiratory motion atlas according to claim 1, characterized in that, The structural control points include the endpoints of blood vessel branches, bifurcation points, and branch points. A distance vector between the structural control points is established to characterize the direction and amplitude of the displacement vector of each branch in order to approximate the motion of a dense set of blood vessel points. The bending energy of the corresponding segment is quantified by calculating the curvature of dense points on the center line of the segmented branch.

3. The method for constructing a vascular respiratory motion atlas according to claim 1, characterized in that, The topological constraints are expressed by the following formula: In the formula: Represents the curvature matrix. The displacement matrix represents the set of points along the centerline. express matrix.

4. The method for constructing a vascular respiratory motion atlas according to claim 1, characterized in that, The method of characterizing the motion and deformation of each branch segment using rotation and stretching metrics in the spherical coordinate system of the manifold space to quantify the deformation of each branch includes: Branch structure From the spatial rectangular coordinate system ( Transform to spherical coordinate system ), by measuring branches upper curve Rotation is quantified by the change of the tangent vector along the deformation path, and stretching is quantified by the change of the length of the curve along the deformation path.

5. The method for constructing a vascular respiratory motion atlas according to claim 1, characterized in that, The overall structural constraint is represented by the following formula: In the formula: and These represent the absolute values ​​of the differences in vessel diameter and volume at different respiratory phases. The bending energy weights are the values ​​corresponding to each point on the branch centerline. This indicates the number of branches in the current vascular structure.

6. A device for constructing a vascular respiratory motion map, characterized in that, The apparatus for performing the vascular respiratory motion mapping method according to any one of claims 1-5, the apparatus comprising: An image acquisition unit is used to acquire 4D-CTA image data of a patient, the 4D-CTA image data including vascular images; The motion atlas output unit is used to input the 4D-CTA image data into the constructed respiratory motion model so that the respiratory motion model outputs a 4D vascular motion atlas. The processing of the respiratory motion model includes data preprocessing, topological constraints, adaptive deformation compensation constraints, and overall structure preservation constraints. The data preprocessing includes using respectively... Algorithms and morphological algorithms extract vascular structures and vascular centerlines from the 4D-CTA images and calculate the lumen diameter at each centerline point. The topological constraints include establishing a directed graph of blood vessels based on the topological connectivity within the blood vessel structure, and quantifying the overall displacement of the blood vessel and the orientation of each branch by extracting structural control points and calculating branch bending energy. The adaptive deformation compensation constraint includes using rotation and stretching metrics to characterize the motion deformation of each branch segment in the spherical coordinate system of the manifold space to quantify the deformation of each branch, and adaptively assigning bending energy weights to each branch based on the angiogram and SRVF constraints. The overall structure preservation constraint includes joint optimization of skeleton integrity and lumen retention during deformation using a loss minimization metric.

7. A device for constructing a vascular respiratory motion atlas, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the vascular respiratory motion atlas construction method according to any one of claims 1-5 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the vascular respiratory motion map construction method according to any one of claims 1-5.

Images