Pulmonary vessel motion compensation method based on spatiotemporal sequences

Abstract

The present application relates to medical image processing technical field, more specifically, it relates to a lung blood vessel motion compensation method based on space-time sequence, based on three-dimensional CT image sequence and monitoring data, four-dimensional space-time data set is constructed;Based on the four-dimensional space-time data set, the motion field between adjacent data frames is calculated, and the continuous motion field based on pixels is obtained;According to the continuous motion field based on pixels, the blood vessel motion is decomposed, and the separated heart and lung motion is obtained;Based on the separated heart and lung motion, the prediction field and the local prediction field of the blood vessel motion are calculated;According to the local prediction field, the imaging parameter of the angiography system is adjusted;Based on the separated heart and lung motion and the adjusted imaging parameter, the non-rigid motion field between images is estimated through frame registration method;According to the non-rigid motion field, the motion compensated image is generated through multi-frame image fusion method, through the construction of four-dimensional space-time data set, combined with the innovative blood vessel motion decomposition model, the high-precision compensation of complex lung blood vessel motion is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing technology, and more particularly to a pulmonary vascular motion compensation method based on spatiotemporal sequences. Background Art

[0002] With the continuous advancement of medical imaging technology, pulmonary vascular imaging plays an increasingly important role in the diagnosis and treatment of diseases such as pulmonary embolism and pulmonary hypertension. However, due to the influence of respiratory motion and cardiac pulsation, obtaining high-quality pulmonary vascular images has always been a challenge. Existing pulmonary vascular motion compensation methods mainly focus on two aspects: respiratory gating technology and image registration technology.

[0003] Respiratory gating technology monitors the patient's respiratory signals and captures images at specific respiratory phases, thereby reducing the impact of respiratory motion. Although simple and straightforward, this method has several significant drawbacks. First, it significantly prolongs the scan time, increasing patient discomfort and radiation dose. Second, it cannot completely eliminate the influence of cardiac pulsation, especially for pulmonary vessels close to the heart, where image quality remains unsatisfactory. Furthermore, this method is significantly less effective in patients with irregular breathing.

[0004] Image registration techniques attempt to compensate for the image by calculating the motion field within the image sequence. This approach can theoretically address the effects of both respiratory motion and cardiac pulsation. However, existing registration algorithms mostly employ global deformation models, which struggle to accurately capture the local deformation of pulmonary vessels. Small vessels, in particular, are prone to being overlooked or mishandled during the registration process due to their weak signal strength. Furthermore, while some local registration algorithms can address local deformation, their high computational complexity hinders their widespread clinical application.

[0005] In addition to the technical challenges of motion compensation, existing methods also have shortcomings in image acquisition strategies. Traditional fixed sampling rate strategies cannot adapt to complex lung motion, often resulting in image quality degradation during periods of intense motion and unnecessary radiation dose during periods of less intense motion. Furthermore, existing contrast agent administration methods face the trade-off between image quality and patient safety. Summary of the Invention

[0006] To address these issues with existing technologies, the present invention proposes a pulmonary vascular motion compensation method based on spatiotemporal sequences. This method aims to accurately model and compensate for pulmonary vascular motion while optimizing image acquisition strategies and contrast agent usage, thereby improving image quality while maximizing patient safety.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] Pulmonary vascular motion compensation method based on spatiotemporal sequence, including:

[0009] The acquisition steps include:

[0010] Acquire three-dimensional CT image sequences acquired by angiography systems and monitoring data acquired by respiratory / ECG monitoring equipment;

[0011] Processing steps include:

[0012] constructing a four-dimensional spatiotemporal data set based on the three-dimensional CT image sequence and the monitoring data;

[0013] Based on the four-dimensional spatiotemporal data set, calculating the motion field between adjacent data frames to obtain a pixel-based continuous motion field;

[0014] Decomposing the vascular motion according to the pixel-based continuous motion field to obtain separated cardiopulmonary motion;

[0015] calculating a predicted field and a local predicted field of vascular motion based on the separated cardiopulmonary motion;

[0016] performing adaptive control to adjust imaging parameters of an angiography system according to the local prediction field;

[0017] Output steps include:

[0018] estimating a non-rigid motion field between images by a frame registration method based on the separated cardiopulmonary motion and the adjusted imaging parameters;

[0019] According to the non-rigid motion field, a motion-compensated image is generated by a multi-frame image fusion method.

[0020] Preferably, the obtaining step specifically includes:

[0021] Acquire three-dimensional angiographic data through an angiography system, and record the three-dimensional angiographic data as I(t,r), where t represents different time points and r represents different spatial positions;

[0022] Initializing the three-dimensional CT image sequence;

[0023] The three-dimensional CT image sequence is initialized using a 3DFCM clustering method so that each pixel obtains three initialization labels;

[0024] aligning the three-dimensional angiography data with the three-dimensional CT image sequence by a rigid alignment method;

[0025] The aligned three-dimensional CT image sequences are merged into the four-dimensional spatiotemporal dataset.

[0026] Preferably, the step of calculating the motion field between adjacent data frames specifically includes:

[0027] The motion field between two adjacent time interval angiographic data I(t,r) and I(t+1,r) is calculated using a variational model based on non-rigid registration;

[0028] The motion field parameterization is decomposed into two parts: global and local, denoted as u = u g +u l ;

[0029] The pixel-based continuous motion field is obtained by minimizing the energy function E(u)=D(I, J, u)+αS(u), where D represents the data term, S represents the regularization term, and α is the weight coefficient.

[0030] Preferably, the step of decomposing the vascular motion specifically includes:

[0031] Constructing a vascular motion decomposition model:

[0032] E(u1,u2)=∑[w(r)(I(t+1,r)-I(t,r+u1+u2)) 2 ]+λR(u1,u2);

[0033] Where u1 represents lung motion, u2 represents heart motion, w(r) is the weight function, R(u1,u2) is the regularization term, and λ is the regularization parameter;

[0034] By optimizing the vascular motion decomposition model, separated cardiopulmonary motion is obtained.

[0035] Preferably, the step of calculating the prediction field and the local prediction field of vascular motion specifically includes:

[0036] Calculate the global prediction field: u g =argminE g (u);

[0037] Calculate the local prediction field: u l =argminE l (u);

[0038] Among them, E g and E l are the energy functions of the global and local prediction fields, respectively.

[0039] Preferably, the step of performing adaptive control specifically includes:

[0040] Calculate the adaptive sampling rate: s = f(u l );

[0041] Among them, f is the local prediction field u l Determined function;

[0042] The imaging rate of the angiography system is dynamically adjusted according to the adaptive sampling rate s.

[0043] Preferably, the step of estimating the non-rigid motion field between images by using a frame registration method specifically includes:

[0044] Frame registration based on cardiac motion estimation: u = argminE r (u);

[0045] Among them, E r is the energy function of the non-rigid motion field;

[0046] Combined with the initial estimation of the non-rigid motion field for frame registration: u = argminE′ r (u);

[0047] Among them, E′ r The energy function for the initialization estimate is considered.

[0048] Preferably, the method further comprises:

[0049] Image segmentation methods are used to transform the vascular motion decomposition problem into a voxel-level segmentation problem;

[0050] The segmentation problem is solved using an expectation-maximization algorithm to obtain estimates of lung and heart motion.

[0051] Preferably, the method further comprises:

[0052] Convolutional neural networks are used to solve the vascular motion decomposition problem;

[0053] extracting image features of angiography data through the convolutional neural network;

[0054] Based on the image features, estimates of lung and heart motion are calculated.

[0055] Preferably, the method further comprises:

[0056] On the injection side, a non-ionic X-ray non-contrast agent and an ionic contrast agent are mixed and then injected into the body of the patient to be imaged for vascular imaging;

[0057] The non-ionic X-ray non-developing agent is used to reduce the radiation dose caused by X-ray fluoroscopy of pulmonary blood vessels during scanning;

[0058] The ionic contrast agent is used to increase X-ray absorption in the heart, blood vessels, and lungs, helping to identify tiny hemorrhages.

[0059] The method of the present invention has the following significant technical effects:

[0060] 1. High-Precision Motion Compensation: This method constructs a four-dimensional spatiotemporal dataset and combines it with an innovative vascular motion decomposition model to accurately separate cardiopulmonary motion and achieve high-precision compensation for complex pulmonary vascular motion. This method not only accounts for the overall motion of large vessels but also captures the localized deformation of smaller vessels, significantly improving image clarity and diagnostic value.

[0061] 2. Adaptive Sampling Strategy: The adaptive control method proposed in this paper dynamically adjusts the sampling rate based on real-time motion prediction. This strategy effectively reduces radiation dose to patients while maintaining image quality, making it particularly suitable for patients with chronic lung diseases who require long-term follow-up.

[0062] 3. Optimized contrast agent usage: By combining non-ionic and ionic contrast agents, the present invention significantly reduces the risk of contrast agent-related adverse reactions while providing excellent image contrast. This innovative contrast agent strategy reflects the present invention's deep concern for patient safety.

[0063] 4. Improved Computational Efficiency: The motion estimation and decomposition algorithms employed in this paper, including an improved non-rigid registration method and deep learning-based feature extraction technology, significantly improve computational efficiency. This enables near-real-time processing in clinical practice, enabling immediate diagnosis by physicians.

[0064] 5. Broad Applicability: The method of the present invention is not only applicable to CT angiography but can also be extended to other modalities such as MR angiography. This broad applicability provides a unified solution for pulmonary vascular imaging in different clinical scenarios.

[0065] 6. Enhanced Diagnostic Value: By providing high-quality, high-resolution images of lung vessels, this invention significantly improves the ability to detect subtle lesions. This is crucial for the early diagnosis of diseases such as pulmonary embolism and pulmonary hypertension, and is expected to improve the early diagnosis rate and treatment effectiveness of these diseases.

[0066] 7. Improved patient experience: Due to the use of adaptive sampling and optimized contrast agent strategies, this invention can significantly shorten scan time and reduce patient discomfort. This not only improves patient compliance but also enables rapid examinations in emergency situations.

[0067] In summary, the pulmonary vascular motion compensation method based on spatiotemporal sequence proposed in the present invention comprehensively solves the problems existing in the prior art through innovative technical means and humanized design. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1The figure is an overall flow chart of the method of the present invention.

[0069] Figure 2 Detailed flow chart of the acquisition steps of the present invention.

[0070] Figure 3 Flowchart constructed for the four-dimensional spatiotemporal dataset of the present invention.

[0071] Figure 4 Flowchart of the motion field calculation of the present invention.

[0072] Figure 5 Flowchart of the vascular motion decomposition of the present invention.

[0073] Figure 6 Flowchart of the adaptive control of the present invention.

[0074] Figure 7 Flowchart of the output steps of the present invention. DETAILED DESCRIPTION

[0075] like Figure 1-7 As shown, the present invention first provides a method for compensating pulmonary vascular motion based on spatiotemporal sequences. This method combines data acquired from an angiography system and respiratory / ECG monitoring equipment to accurately compensate for pulmonary vascular motion, thereby improving the quality and accuracy of pulmonary vascular imaging. Specific embodiments of the present invention are described in detail below.

[0076] First, the method of the present invention includes an acquisition step, a processing step, and an output step. In the acquisition step, the method acquires a 3D CT image sequence acquired by an angiography system and monitoring data collected by a respiratory / ECG monitoring device. This data provides the basis for subsequent processing.

[0077] During the processing step, the present method first constructs a 4D spatiotemporal dataset based on the acquired 3D CT image sequence and monitoring data. This step is crucial because it organically combines spatial and temporal information, laying the foundation for subsequent motion analysis. Preferably, the present invention employs an interpolation algorithm to construct the 4D spatiotemporal dataset to ensure data continuity and integrity.

[0078] Next, based on the constructed four-dimensional spatiotemporal dataset, this method calculates the motion field between adjacent data frames to obtain a pixel-based continuous motion field. This step uses a variational model based on non-rigid registration, and its mathematical expression is as follows:

[0079] E(u)=D(I,J,u)+αS(u)

[0080] Where E(u) is the energy function, D represents the data term, S represents the regularization term, and α is the weight coefficient. In one embodiment of the present invention, the value of α ranges from 0.1 to 1.0, with a preferred value of 0.5. This range was selected based on extensive experimental data and achieves a good balance between maintaining motion field smoothness and accuracy.

[0081] Then, the method decomposes the vascular motion according to the obtained pixel-based continuous motion field to obtain the separated cardiopulmonary motion. This step adopts an innovative vascular motion decomposition model, whose mathematical expression is as follows:

[0082]

[0083] Where u1 represents lung motion, u2 represents heart motion, w(r) is the weight function, R(u1,u2) is the regularization term, and λ is the regularization parameter. In a preferred embodiment of the present invention, λ ranges from 0.01 to 0.1, which effectively balances the accuracy and stability of motion decomposition.

[0084] Based on the separated cardiopulmonary motion, this method calculates the predicted field and local predicted field of vascular motion. This step is crucial for subsequent adaptive control. The present invention combines the global and local predicted fields to more comprehensively capture the characteristics of vascular motion.

[0085] Based on the calculated local prediction field, this method adaptively adjusts the imaging parameters of the angiography system. The innovation of this step lies in its ability to dynamically adjust imaging parameters based on real-time motion prediction, thereby improving imaging quality and efficiency. For example, when intense motion is predicted, the system might increase the sampling rate; when motion is minimal, it might decrease the sampling rate to reduce radiation dose.

[0086] In the output step, the method estimates the non-rigid motion field between images through frame registration based on the separated cardiopulmonary motion and the adjusted imaging parameters. This step uses an improved non-rigid registration algorithm, and its objective function can be expressed as:

[0087] u=argminE r (u)

[0088] Among them, E r is the energy function of the non-rigid motion field. In one embodiment of the present invention, E r Image similarity terms, smoothness constraint terms, and volume preservation terms may be included to ensure the accuracy and physical rationality of the registration results.

[0089] Finally, based on the estimated non-rigid motion field, this method generates a motion-compensated image through multi-frame image fusion. This step not only compensates for image distortion caused by motion but also improves the signal-to-noise ratio and resolution of the image through multi-frame fusion.

[0090] A key feature of the present method is the specific implementation of its acquisition step. Specifically, this step involves obtaining 3D angiographic data using an angiography system and denoting the data as I(t,r), where t represents different points in time and r represents different spatial locations. This representation allows for precise capture of vascular changes in both time and space.

[0091] Next, the method initializes the three-dimensional CT image sequence. Preferably, the present invention employs the 3DFCM (Fuzzy C-Means) clustering method for initialization, so that each pixel receives three initialization labels. This method is advantageous in that it can handle fuzzy boundaries, which is particularly important in medical image processing. In one embodiment, the fuzziness parameter m of the FCM algorithm can be set to 2, a value widely used in practice that achieves a good balance between clustering effectiveness and computational efficiency.

[0092] Subsequently, the method aligns the 3D angiography data with the 3D CT image sequence using a rigid alignment method. This step ensures spatial consistency between the images of different modalities, laying the foundation for subsequent motion analysis. In practical applications, a rigid registration algorithm based on mutual information can be used, and its objective function can be expressed as:

[0093] T*=argmaxMI(I fixed ,T(I moving ))

[0094] Among them, MI represents mutual information, I fixed and I moving denote fixed image and moving image respectively, and T denotes rigid transformation.

[0095] Finally, the method combines the aligned 3D CT image sequences into the 4D spatiotemporal dataset. This step organically combines spatial and temporal information, providing a comprehensive data foundation for subsequent motion analysis.

[0096] Another key step in the method is calculating the motion field between adjacent data frames. Specifically, this method uses a variational model based on non-rigid registration to calculate the motion field between two adjacent time intervals of angiographic data (t, r) and I(t+1, r). This method can effectively capture complex non-rigid motion and is particularly suitable for motion analysis of soft tissues such as pulmonary vessels.

[0097] In this step, the method decomposes the motion field parameter into two parts: global and local, denoted as u = u g +u l The advantage of this decomposition method is that it can simultaneously capture large-scale global motion and small-scale local deformation, thus describing the vascular motion more comprehensively.

[0098] This method obtains the pixel-based continuous motion field by minimizing the energy function E(u) = D(I, J, u) + αS(u). Here, D represents the data term, which measures the similarity between images; S represents the regularization term, which ensures the smoothness of the motion field; and α is a weight coefficient, which balances the contributions of the data term and the regularization term. In practical applications, α is typically set between 0.1 and 1, and the optimal value can be determined through methods such as cross-validation.

[0099] In summary, the spatiotemporal sequence-based pulmonary vascular motion compensation method provided by this invention has the following advantages: First, it fully utilizes spatiotemporal information to more accurately capture and compensate for complex vascular motion; second, through an adaptive control strategy, it dynamically adjusts imaging parameters based on real-time motion prediction results, improving imaging quality and efficiency; finally, the application of multi-frame image fusion technology further enhances the quality of the final image. These advantages make this method promising for broad application in the field of pulmonary vascular imaging, particularly in the diagnosis and treatment of diseases such as pulmonary embolism and pulmonary hypertension.

[0100] Next, the method of the present invention decomposes vascular motion to separate cardiopulmonary motion. This step is one of the core innovations of the present invention and is achieved by constructing a vascular motion decomposition model. Specifically, the method uses the following mathematical model:

[0101]

[0102] In this model, u1 represents lung motion, u2 represents heart motion, w(r) is the weight function, and R(u1,u2) is the regularization term. Preferably, the present invention uses a spatially adaptive weight function w(r) to better account for the motion characteristics of different regions. For example, at the edge of the lung, the weight may be smaller to reduce the impact of boundary effects.

[0103] The design of the regularization term R(u1,u2) is crucial to obtain a smooth and physically reasonable motion field. In a preferred embodiment of the present invention, R(u1,u2) can be expressed as:

[0104]

[0105] in, represents the gradient operator. This form of regularization term can effectively suppress noise and discontinuities in the motion field. The parameter λ controls the balance between the data term and the regularization term. Practice of the present invention has shown that the value of λ typically ranges from 0.01 to 0.1. The specific value can be adjusted based on the image quality and the complexity of the motion. For example, when the image is noisy, the value of λ can be appropriately increased to enhance smoothness.

[0106] Based on the above vascular motion decomposition model, the present method obtains separated cardiopulmonary motion through an optimization algorithm. Preferably, the present invention uses the alternating direction method of multipliers (ADMM) for optimization, which has good convergence and computational efficiency when dealing with large-scale optimization problems.

[0107] After obtaining the separated cardiopulmonary motion, the method of the present invention further calculates the prediction field and local prediction field of vascular motion. This step is crucial for achieving subsequent adaptive control. Specifically, the method first calculates the global prediction field:

[0108] u g =argminE g (u)

[0109] Among them, E g is the energy function of the global prediction field. In one embodiment of the present invention, E g Can be designed as:

[0110]

[0111] This form of energy function not only considers the similarity between images, but also includes the smoothness constraint of the motion field.

[0112] Next, the method computes the local prediction field:

[0113] u l =argminE l (u)

[0114] Among them, E l is the energy function of the local prediction field. Preferably, E l Can be designed as:

[0115]

[0116] Here, w(r) is a local weight function used to emphasize the importance of local regions. The parameter β controls the smoothness of the local prediction field and is usually smaller than α in the global prediction field to allow more local deformation.

[0117] Based on the calculated local prediction field, the method of the present invention performs adaptive control to adjust the imaging parameters of the angiography system. The core idea of ​​this step is to dynamically adjust the sampling strategy according to the predicted motion to achieve a balance between image quality and radiation dose.

[0118] Specifically, this method calculates the adaptive sampling rate:

[0119] s=f(u l )

[0120] Among them, f is based on the local prediction field u l In a preferred embodiment of the present invention, f can be designed as:

[0121] f(u l )=s0(1+γ||u l ||)

[0122] Here, s0 is the basic sampling rate, γ is a tuning parameter, ||u l || represents the norm of the local prediction field. This design increases the sampling rate when violent motion is predicted, and reduces the sampling rate when the motion is small. Preferably, the value range of γ can be set to 0.1 to 1, and the specific value can be adjusted according to clinical needs and equipment performance. For example, for applications that require high temporal resolution, a larger γ value can be selected; while for patients who are particularly sensitive to radiation dose, a smaller γ value can be selected. Based on the calculated adaptive sampling rate s, the present method dynamically adjusts the imaging rate of the angiography system. This adaptive control strategy can not only improve image quality, but also effectively reduce unnecessary radiation dose, which is more patient-friendly.

[0123] Finally, the method of the present invention estimates the non-rigid motion field between images through the frame registration method and performs multi-frame image fusion. In the frame registration step, the method performs frame registration based on cardiac motion estimation:

[0124] u=argminE r (u)

[0125] Among them, E r is the energy function of the non-rigid motion field. In one embodiment of the present invention, E r Can be designed as:

[0126]

[0127] This form of energy function not only considers the similarity between images and the smoothness of the motion field, but also includes the volume preservation constraint (through the divergence term Parameters λ1 and λ2 control the strength of the smoothness constraint and volume preservation constraint respectively, and their values ​​can be determined by methods such as cross-validation.

[0128] In order to further improve the accuracy of registration, this method also combines the initialization estimation of non-rigid motion field for frame registration:

[0129] u=argminE r ′(u)

[0130] Among them, E′ r is the energy function considered for initialization estimation. Preferably, E′ r Can be designed as:

[0131] E r ′(u)=E r (u)+μ∫||uu init || 2 dr

[0132] Here, y init is the initialization motion field estimate, and μ is a weight parameter used to control the influence of the initialization estimate.

[0133] Through the above frame registration method, the present invention can effectively estimate the non-rigid motion field between images, laying the foundation for subsequent image fusion. Finally, the present method uses multi-frame image fusion techniques such as weighted averaging to generate high-quality images after motion compensation.

[0134] In general, the pulmonary vascular motion compensation method based on spatiotemporal sequences provided by the present invention achieves accurate compensation for pulmonary vascular motion through an innovative motion decomposition model, an adaptive control strategy, and a high-precision frame registration technology. This method not only improves the quality and accuracy of pulmonary vascular imaging, but also reduces the radiation dose received by the patient through an adaptive sampling strategy. Therefore, the present invention has important application value in clinical diagnosis and treatment, especially for lung diseases that require precise vascular imaging, such as pulmonary embolism, pulmonary hypertension, etc., this method can provide more reliable diagnostic basis and treatment guidance. In a preferred embodiment of the present invention, the method also includes using an image segmentation method to convert the vascular motion decomposition problem into a voxel-level segmentation problem. The advantage of this method is that it can process complex vascular structures more finely, thereby improving the accuracy of motion decomposition. Specifically, the method first uses a threshold-based method to perform image segmentation:

[0135]

[0136] Where S(r) represents the segmentation result of the r-th spatial position, I(r) represents the pixel intensity at that position, and T is the threshold. Preferably, the threshold T can be adaptively determined using the Otsu method, which can automatically adjust between different images to improve the robustness of the segmentation.

[0137] After obtaining the preliminary segmentation results, this method uses the maximum expectation algorithm to solve and obtain the estimation of lung and heart motion. The objective function of the maximum expectation algorithm can be expressed as:

[0138] Q(θθ (t) )=E Z [logp(X,Z|θ)|X,θ (t) ]

[0139] Where θ represents the model parameters, X represents the observed data, and Z represents the latent variables. In the application of the present invention, X can be understood as image data, and Z corresponds to the labels of different tissue types.

[0140] Specifically, this method updates the model parameters in an iterative manner:

[0141]

[0142] In each iteration, the expectation step (E-step) calculates the posterior probability:

[0143]

[0144] The maximization step (M-step) updates the model parameters:

[0145]

[0146] By using this method, the present invention can estimate the motion of the lungs and heart more accurately, thereby improving the accuracy of vascular motion compensation.

[0147] In another embodiment of the present invention, the method further comprises using a convolutional neural network to solve the vascular motion decomposition problem. This deep learning-based method can automatically learn complex feature representations and performs well in processing large-scale medical image data.

[0148] Specifically, this method first extracts the image features of angiography data through a convolutional neural network. A typical convolutional layer can be expressed as:

[0149] F l =σ(W l *F l-1 +b l )

[0150] Among them, F lrepresents the feature map of the ι-th layer, W l and b l are the convolution kernel and bias of the layer respectively, * represents the convolution operation, and σ is the activation function. Preferably, the present invention adopts ReLU as the activation function:

[0151] σ(x)=max(0,x)

[0152] This activation function can effectively alleviate the gradient vanishing problem and accelerate the network training process.

[0153] After extracting image features, this method obtains the final classification result through the fully connected layer and the softmax layer:

[0154] p(y|x)=softmax(Wx+b)

[0155] Where x is the input feature vector, W and b are the weight matrix and bias vector respectively, and y is the predicted category label.

[0156] Based on the above network structure, this method trains the model by minimizing the cross entropy loss function:

[0157]

[0158] Among them, y is the true label, p(y i |x i ) is the probability predicted by the model.

[0159] Through this convolutional neural network-based method, the present invention can automatically learn the complex characteristics of vascular motion, thereby achieving more accurate motion decomposition and compensation.

[0160] Finally, the method of the present invention includes an important pretreatment step, in which a non-ionic X-ray invisibility agent and an ionic contrast agent are mixed on the injection side and then injected into the patient's body for vascular imaging. This step reflects the consideration of patient safety in the practical application of the present invention.

[0161] Specifically, nonionic X-ray contrast agents are used to reduce the radiation exposure to pulmonary vascular X-rays during scanning. These contrast agents typically have low osmotic pressure and viscosity, minimizing adverse effects on the human body. Preferably, the present invention uses iohexol as a nonionic contrast agent, which has a molecular weight of approximately 821 and a concentration between 300 and 370 mgI / mL. The specific concentration can be adjusted based on the patient's weight and the examination site.

[0162] The effect of ionic contrast agent is to improve the X-ray absorption of heart, blood vessel and lung, and helps to identify tiny hemorrhage.This contrast agent has higher osmotic pressure usually, can provide better image contrast.Preferably, the present invention adopts iodixanol as ionic contrast agent, and its molecular weight is about 1550, and concentration can be selected between 320-400mgI / mL.

[0163] The mixing ratio of the two contrast agents needs to be adjusted based on specific clinical needs and patient conditions. Generally, a slightly higher ratio of the non-ionic contrast agent can be used to reduce the overall risk of adverse reactions. For example, a mixing ratio of 7:3 or 8:2 can be used. This mixing strategy provides excellent image quality while maximizing patient safety.

[0164] By employing this innovative contrast agent mixing strategy, combined with the aforementioned motion compensation method, the present invention not only achieves high-quality pulmonary vascular images but also significantly reduces the patient's radiation dose and the risk of contrast agent-related adverse reactions. This makes this method promising in clinical practice, especially for patients with chronic lung diseases who require frequent follow-up examinations.

[0165] In general, the spatiotemporal sequence-based pulmonary vascular motion compensation method provided by the present invention comprehensively improves the quality and safety of pulmonary vascular imaging through innovative image segmentation technology, deep learning methods and contrast agent strategies.

[0166] The above description is only a preferred specific embodiment of the present invention; however, the protection scope of the present invention is not limited thereto; any person familiar with the art who makes equivalent replacements or changes based on the scheme and improved concepts of the present invention within the scope disclosed by the present invention shall be covered by the protection scope of the present invention.

Claims

1. A pulmonary vascular motion compensation method based on spatiotemporal sequences, characterized in that: include: The acquisition steps include: Acquire three-dimensional CT image sequences acquired by angiography systems and monitoring data acquired by respiratory / ECG monitoring equipment; Processing steps include: constructing a four-dimensional spatiotemporal data set based on the three-dimensional CT image sequence and the monitoring data; Based on the four-dimensional spatiotemporal data set, calculating the motion field between adjacent data frames to obtain a pixel-based continuous motion field; Decomposing the vascular motion according to the pixel-based continuous motion field to obtain separated cardiopulmonary motion; calculating a global prediction field and a local prediction field of vascular motion based on the separated cardiopulmonary motion; performing adaptive control to adjust imaging parameters of an angiography system according to the local prediction field; Output steps include: estimating a non-rigid motion field between images by a frame registration method based on the separated cardiopulmonary motion and the adjusted imaging parameters; generating a motion-compensated image by a multi-frame image fusion method according to the non-rigid motion field; The obtaining step specifically includes: The three-dimensional angiography data is obtained by the angiography system and recorded as , where t represents different time points, Indicates different spatial locations; Initializing the three-dimensional CT image sequence; The three-dimensional CT image sequence is initialized using a 3DFCM clustering method so that each pixel obtains three initialization labels; aligning the three-dimensional angiography data with the three-dimensional CT image sequence by a rigid alignment method; merging the aligned three-dimensional CT image sequences into the four-dimensional spatiotemporal dataset; The step of calculating the motion field between adjacent data frames specifically includes: Computing 3D angiographic data at two adjacent time intervals using a variational model based on non-rigid registration and the sports fields between; The motion field parameterization is decomposed into two parts: global and local, denoted as ,in, is the global prediction field, represents the local prediction field; By minimizing the energy function The pixel-based continuous motion field is obtained, where D represents the data term, S represents the regularization term, is the weight coefficient; The step of decomposing the vascular motion specifically includes: Constructing a vascular motion decomposition model: ； in, Indicates lung movement, Indicates heart movement, is the weight function, is the regularization term, is the regularization parameter; By optimizing the vascular motion decomposition model, separated cardiopulmonary motion is obtained.

2. The method according to claim 1, characterized in that The step of calculating the global prediction field and the local prediction field of the vascular motion specifically includes: Compute the global prediction field: ; Compute the local prediction field: ; in, and are the energy functions of the global and local prediction fields, respectively.

3. The method according to claim 1, characterized in that The steps of performing adaptive control specifically include: Calculate the adaptive sampling rate: ; Where f is the local prediction field Determined function; The imaging rate of the angiography system is dynamically adjusted according to the adaptive sampling rate s.

4. The method according to claim 1, wherein The step of estimating the non-rigid motion field between images by the frame registration method specifically includes: Frame registration based on cardiac motion estimation: ; in, is the energy function of the non-rigid motion field; Combined with the initial estimation of the non-rigid motion field for frame registration: ; in, The energy function for the initialization estimate is considered.

5. The method according to claim 1, wherein The method further comprises: Image segmentation methods are used to transform the vascular motion decomposition problem into a voxel-level segmentation problem; The segmentation problem is solved using an expectation-maximization algorithm to obtain estimates of lung and heart motion.

6. The method according to claim 1, characterized in that The method further comprises: Convolutional neural networks are used to solve the vascular motion decomposition problem; extracting image features of angiography data through the convolutional neural network; Based on the image features, estimates of lung and heart motion are calculated.

7. The method according to claim 1, characterized in that The method further comprises: On the injection side, a non-ionic X-ray non-contrast agent and an ionic contrast agent are mixed and then injected into the body of the patient to be imaged for vascular imaging; The non-ionic X-ray non-developing agent is used to reduce the radiation dose caused by X-ray fluoroscopy of pulmonary blood vessels during scanning; The ionic contrast agent is used to increase X-ray absorption in the heart, blood vessels, and lungs, helping to identify tiny hemorrhages.

Images