Medical image processing system and method

Abstract

The present application discloses a medical image processing system and method, which is configured to: acquire dual-energy projection data, perform material decomposition on a high-energy projection sequence and a low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence; segment the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence; perform three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; segment the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image; align the two-dimensional vascular iodine density segmented projection sequence and the three-dimensional vascular iodine density segmented image to obtain a registered projection correction matrix sequence; obtain a corrected projection matrix sequence based on the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; and reconstruct a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and in particular to a system and method for processing dual-energy X-ray images. Background Art

[0002] With the continuous advancement of medical imaging technology, digital subtraction angiography (DSA) has become an important tool for vascular imaging and interventional therapy. By subtracting X-ray images before and after contrast agent injection, DSA can clearly visualize vascular structures, providing important evidence for clinical diagnosis and interventional therapy. However, in practical applications, medical image processing technology still faces many challenges.

[0003] For example, image blurring and motion artifacts caused by the patient's involuntary movement reduce the quality of clinical images, hinder doctors from accurately diagnosing and treating vascular diseases, selecting appropriate interventional treatment plans, and evaluating lesions, thereby reducing the safety and effectiveness of interventional operations.

[0004] Therefore, there is an urgent need for an effective medical image processing system and method to improve image quality and clinical application value. Summary of the Invention

[0005] In order to solve the problem in the field of medical image processing, especially the problem of blurred vascular images and many motion artifacts caused by involuntary movement of patients, the present invention provides a medical image processing system and method that can effectively improve the clarity of vascular images.

[0006] A medical image processing system is configured to: acquire dual-energy projection data, the dual-energy projection data including a high-energy projection sequence and a low-energy projection sequence; perform material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence; segment the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence; perform three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; segment the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image; align the two-dimensional vascular iodine density segmented projection sequence and the three-dimensional vascular iodine density segmented image to obtain a registered projection correction matrix sequence; obtain a corrected projection matrix sequence based on the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; and reconstruct a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0007] Optionally, performing material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain the two-dimensional vascular iodine density projection sequence includes inputting the high-energy projection sequence and the low-energy projection sequence into a dichotomy model to obtain the two-dimensional vascular iodine density projection sequence.

[0008] Optionally, the material decomposition of the high-energy projection sequence and the low-energy projection sequence to obtain the two-dimensional vascular iodine density projection sequence includes obtaining the two-dimensional vascular iodine density projection sequence based on the high-energy projection sequence and the low-energy projection sequence using a pre-constructed two-dimensional vascular iodine density projection sequence relationship table.

[0009] Optionally, segmenting the two-dimensional vascular iodine density projection sequence to obtain the two-dimensional vascular iodine density segmented projection sequence includes processing the two-dimensional vascular iodine density projection sequence using a threshold segmentation method to obtain the two-dimensional vascular iodine density segmented projection sequence.

[0010] Optionally, the three-dimensional reconstruction of the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image includes using a gradient descent method and a projection matrix to reconstruct the two-dimensional vascular iodine density projection sequence to obtain the three-dimensional vascular iodine density image.

[0011] Optionally, the system includes processing the three-dimensional vascular iodine density image using a threshold segmentation method to obtain the three-dimensional vascular iodine density segmentation image.

[0012] Optionally, the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image are aligned to obtain a registered projection correction matrix sequence, including using a forward projection method to align the two-dimensional vascular segmentation projection sequence and the three-dimensional segmentation image to obtain a registered projection correction matrix sequence.

[0013] Optionally, the method reconstructs a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence, including reconstructing a motion-corrected three-dimensional vascular iodine density image using a gradient descent method based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0014] Optionally, the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence, including simultaneously obtaining the high-energy projection sequence and the low-energy projection sequence after scanning the target site injected with iodine-containing contrast agent using a dual-flat panel detector DSA imaging system.

[0015] A medical image processing method is executed by a medical image processing system and includes the following steps: acquiring dual-energy projection data, the dual-energy projection data including a high-energy projection sequence and a low-energy projection sequence; performing material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence; segmenting the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence; performing three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; segmenting the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image; registering the two-dimensional vascular iodine density segmented projection sequence and the three-dimensional vascular iodine density segmented image to obtain a registered projection correction matrix sequence; obtaining a corrected projection matrix sequence based on the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; and reconstructing a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0016] The beneficial effect of the present invention lies in the fact that, through the aforementioned series of methodological steps, including data acquisition, material decomposition of projection sequences, segmentation, and three-dimensional reconstruction, multiple technical means are employed to achieve more precise observation and quantitative analysis of blood vessels in dynamic imaging. This approach not only improves overall image quality but also enhances understanding of vascular motion, contributing to improved clinical diagnosis and treatment outcomes. Utilizing dual-layer detector digital subtraction angiography (DSA) vascular imaging technology, material decomposition is performed using X-rays of varying energies to reconstruct clear vascular images. Image registration within the vascular motion cycle effectively reduces motion artifacts and improves imaging accuracy and clarity. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a medical image processing system provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the relationship between a double-layer detector and a radiation source of a medical image processing system provided in an embodiment of the present application;

[0019] Figure 3 A schematic diagram of the principle of the process of processing projection data by the medical image processing system provided in an embodiment of the present application;

[0020] Figure 4 A flowchart of a medical image processing method provided in an embodiment of the present application;

[0021] Figure 5 A schematic diagram of the structure of a processing device of a medical image processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] To make the above-mentioned objects, features, and advantages of the present application more clearly understood, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings. The following description sets forth many specific details to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar improvements without violating the scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0023] In the description of this application, it should be understood that if the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. appear, the orientation or position relationship indicated by these terms is based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0024] In addition, if the terms "first" or "second" appear, these terms are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of this application, if the term "plurality" appears, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0025] In this application, unless otherwise specified or limited, the terms "mounted," "connected," "connected," "fixed," etc., should be interpreted broadly. For example, these terms may refer to fixed connections, removable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediary; and internal communication between two components or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0026] In this application, unless otherwise expressly specified or limited, if a first feature is described as being "above" or "below" a second feature, or similar descriptions, this may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Furthermore, when a first feature is described as being "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is described as being "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0027] It should be noted that if an element is referred to as being "fixed to" or "disposed on" another element, it may be directly on the other element or there may be an intermediate element. If an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. If any, the terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used in this application are for illustrative purposes only and do not represent the only embodiment.

[0028] Figure 1 FIG. 1 is a schematic diagram of a medical image processing system according to some embodiments of this specification. Figure 1 As shown, the medical image processing system 100 may include an imaging device 110 , a network 120 , a terminal 130 , a processing device 140 , a storage device 150 , and a scanning bed 160 .

[0029] The imaging device 110 may be configured to scan the target subject to obtain image data (e.g., projection data, images, etc.). In some embodiments, the imaging device 110 may include a medical imaging device, such as a DSA (Digital Subtraction Angiography) imaging device, or other imaging devices, such as a CT (Computed Tomography) imaging device or an MR (Magnetic Resonance) imaging device.

[0030] In some embodiments, the imaging device 110 is a dual-layer detector digital subtraction angiography (DSA) device, which may include a gantry 1101, a detector 1102, a radiation source 1103, and a support structure 1104. The gantry 1101 is a C-arm structure, and the detector 1102 and the radiation source 1103 are mounted on opposite ends of the gantry 1101, respectively. The support structure 1104 is connected to the middle position of the gantry 1101. The C-arm structure may provide a scanning area to accommodate the subject to be scanned. The subject may be placed on the scanning bed 160 and moved to the scanning area to be scanned. In some embodiments, the detector 1102 may be a flat-plate structure, including one or more detection modules, each of which may be a dual-layer detector (see Figure 2 ), including a first detection layer (low-energy detection layer) and a second detection layer (high-energy detection layer), the low-energy detection layer being closer to the radiation source (focus) than the high-energy detection layer. The detection module may include one or more detection units arranged perpendicular to the scanning bed plate. In some embodiments, each of the multiple detection units may be configured to generate an electrical signal in response to detecting radiation. In some embodiments, each of the multiple detection units or detection modules may be detachable. It should be noted that Figure 1 The number of detection modules in the figure is for illustration only and does not limit the scope of this specification. The number of detection modules may be multiple. Detection units may include scintillators (e.g., cesium iodide detectors), semiconductors, etc. In some embodiments, the imaging device 110 may further include a collimator (not shown). The collimator may include multiple collimation modules arranged parallel to the detector modules. Each of the multiple collimation modules may include multiple collimation units in different configurations. Further descriptions of the collimator and / or detector can be found elsewhere in this specification. Optionally, the detector may be a dual-layer (dual-energy) detector, the main feature of which is the use of two different detection modules (a dual-layer structure): one low-energy detection layer and the other high-energy detection layer. This dual-layer detector design enables the system to simultaneously capture X-ray signals of different energies, thereby achieving efficient spectral imaging. The low-energy projection data captured in the low-energy detection layer is highly sensitive to low-atomic-number substances such as water, while the high-energy detection layer is more sensitive to high-atomic-number substances (e.g., iodine-containing contrast agents).

[0031] The network 120 may comprise any suitable network capable of facilitating information and / or data exchange between the imaging device 110. In some embodiments, at least one component of the medical image processing system 100 (e.g., the imaging device 110, the terminal 130, the processing device 140, the storage device 150) may exchange information and / or data with at least one other component of the medical image processing system 100 via the network 120. For example, the processing device 140 may obtain scan data from the imaging device 110 via the network 120. In some embodiments, the network 120 may comprise at least one network access point. For example, the network 120 may comprise a wired and / or wireless network access point (e.g., a base station and / or an internet exchange point), and at least one component of the medical image processing system 100 may connect to the network 120 via the access point to exchange data and / or information.

[0032] The terminal 130 can communicate and / or connect with the imaging device 110, the processing device 140, and / or the storage device 150. In some embodiments, the terminal 130 may include a mobile device 131, a tablet computer 132, a laptop computer 133, or any combination thereof. For example, the mobile device 131 may include a mobile controller, a personal digital assistant (PDA), a smartphone, or any combination thereof. In some embodiments, the terminal 130 may include a display device, such as a monitor. The display device may be configured to display images or other information obtained through imaging, such as a medical image of a patient, a three-dimensional model, or an operation panel related to medical imaging. In some embodiments, the terminal 130 may be part of the processing device 140.

[0033] The processing device 140 can be configured to process data and / or information obtained by the imaging device 110, the terminal 130, the storage device 150, or other components of the medical image processing system 100. For example, the processing device (processor) can be configured to perform one or more operations of the imaging data processing methods disclosed in some embodiments of this specification. In some embodiments, the processing device 140 can include a single server or a server group. The server group can include a centralized server group or a distributed server group. In some embodiments, the processing device 140 can include a local device or a remote device. For example, the processing device 140 can access information and / or data from the imaging device 110, the storage device 150, and / or the terminal 130 via the network 120. As another example, the processing device 140 can be directly connected to the imaging device 110, the terminal 130, and / or the storage device 150 to access information and / or data. As another example, the processing device 140 can be installed on the imaging device 110. In some embodiments, the processing device 140 can be implemented on a cloud platform. For example, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud cloud, a multi-cloud, etc., or any combination thereof.

[0034] Storage device 150 can be configured to store data, instructions, and / or any other information. For example, storage device 150 can store data obtained by imaging device 110, terminal 130, and / or processing device 140. In some embodiments, storage device 150 can store data and / or instructions used by processing device 140 to execute or implement the exemplary methods described herein. In some embodiments, storage device 150 can include mass storage, removable storage, volatile read / write memory, read-only memory (ROM), or the like, or any combination thereof. In some embodiments, storage device 150 can be implemented on a cloud platform.

[0035] In some embodiments, the storage device 150 can be connected to the network 120 to communicate with at least one other component of the medical image processing system 100 (e.g., the processing device 140, the terminal 130). At least one component of the medical image processing system 100 can access data stored in the storage device 150 via the network 120. In some embodiments, the storage device 150 can be part of the processing device 140. In some embodiments, the processing device 140 and the storage device 150 can be integrated into the imaging device 110.

[0036] It should be noted that the above description is for illustrative purposes only and is not intended to limit the scope of this specification. For those skilled in the art, various modifications and variations can be made under the guidance of the description of this specification. The features, structures, methods and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the storage device 150 can be a data storage device, which can include a cloud computing platform, such as a public cloud, a private cloud, a community cloud and a hybrid cloud. However, these modifications and variations do not depart from the scope of this specification.

[0037] See also Figure 3An embodiment of the present application discloses a schematic diagram of the principle of a medical image processing system for processing projection data, wherein the medical image processing system includes a processing device for processing medical images, and the medical image processing system is configured to: acquire dual-energy projection data, wherein the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence; perform material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence; segment the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence; perform three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; segment the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image; align the two-dimensional vascular iodine density segmented projection sequence and the three-dimensional vascular iodine density segmented image to obtain a registered projection correction matrix sequence; obtain a corrected projection matrix sequence based on the projection correction matrix sequence and the projection matrix for three-dimensional image reconstruction; and reconstruct a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0038] The medical image processing system primarily processes dual-energy projection data, producing motion-corrected three-dimensional vascular iodine density images through a series of processing steps. The system first acquires dual-energy projection data consisting of high-energy and low-energy projection sequences, representing different X-ray energy levels. Using material decomposition techniques, intravascular iodine density information is extracted from the dual-energy projection data, generating a two-dimensional vascular iodine density projection sequence. The distribution of iodine within the blood vessels directly affects X-ray transmittance, resulting in a specific density distribution in the projections. Segmentation is performed on this two-dimensional vascular iodine density projection sequence, effectively removing background noise and other irrelevant information and enhancing the vascular iodine density features. A three-dimensional reconstruction algorithm is then used to convert the processed two-dimensional vascular iodine density projection sequence into a three-dimensional image. This reconstruction process preserves and restores the spatial characteristics of the vascular structure. After the 3D reconstruction is complete, image segmentation is performed again to ensure accurate localization and visualization of vascular lesions in the three-dimensional image. Registration of the two-dimensional segmentation sequence with the three-dimensional segmentation results effectively adjusts for image deviations, thereby establishing an accurate projection correction matrix sequence. Finally, a corrected projection matrix sequence is obtained based on the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; a motion-corrected three-dimensional vascular iodine density image is reconstructed based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0039] This corrected projection matrix sequence is used to process the original 2D vascular iodine density projection sequence, further optimizing data entry for 3D reconstruction. The resulting motion-corrected 3D images eliminate artifacts caused by factors such as patient movement during scanning, significantly improving diagnostic accuracy. This entire process focuses on enhancing the clarity and accuracy of vascular imaging, making it more practical and reliable in clinical diagnosis.

[0040] Optionally, the dual-energy projection data may be acquired by an imaging device 110; the imaging device may be a CBCT (ConeBeam Computed Tomography) system (see Figure 1-2 ), whose main feature is the use of two different detection layers: an upper low-energy detection layer and a lower high-energy detection layer. This dual-layer detector design enables the CBCT system to simultaneously capture X-ray signals of different energies, thereby achieving efficient spectral imaging. Alternatively, the imaging device can also be a dual-source device, which mainly features the use of two X-ray sources with different energy levels, emitting X-rays of different energy levels. The X-ray signals of different energy levels are captured separately by two different detection layers.

[0041] Alternatively, a dual-detector digital subtraction angiography (DSA) device can be used to simultaneously acquire high-energy and low-energy two-dimensional projection sequences. The high-energy two-dimensional (2D) projection sequence is obtained using the parameter P Hi The low-energy two-dimensional (2D) projection sequence is represented by the parameter P Li Indicates; i represents the frame number recorded in digital form, ranging from 1,⋯n, where n is the total number of collected projections, which is an integer such as 10, 30, 1000, etc.

[0042] Optionally, the step of performing material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence comprises inputting the high-energy projection sequence and the low-energy projection sequence into a dichotomy model to obtain the two-dimensional vascular iodine density projection sequence. This step outputs the two-dimensional vascular iodine density projection sequence P Ioi .

[0043] As described above, a bisection model can be used to decompose material components to obtain a two-dimensional vascular iodine density projection sequence. This model distinguishes iodine from other material components based on the differences between X-ray projections at two different energy levels. After acquiring two sets of high-energy and low-energy projections, they are sequentially input into the model for a series of calculations and comparisons. Due to differences in penetrating power, high-energy and low-energy X-rays experience different attenuation levels when encountering tissue of the same thickness and homogeneity. This difference is directly reflected in the two sequences. The bisection model exploits this subtle difference between the high-energy and low-energy sequences, repeatedly calculating and approximating the solution to gradually decompose the image sequences into independent sequences of iodine density and residual tissue components. The result is a two-dimensional vascular iodine density projection sequence that accurately displays the iodine distribution within the area, providing an essential data foundation for subsequent segmentation and three-dimensional reconstruction. This approach greatly ensures the accuracy of the decomposition effect, making the final vascular image have great advantages in background noise suppression and contrast enhancement, and fully demonstrates the effectiveness of material decomposition technology in eliminating non-vascular background materials and restoring the true value of vascular iodine density.

[0044] These density maps can help doctors accurately distinguish different types of tissue and potential lesions, leading to more effective diagnosis and treatment plans.

[0045] For example, to describe the basic relationship between the data collected by the two layers of detectors, the following two formulas can be used to express the relationship between the high and low energy projection data and the density projections of water and iodine;

[0046] Formula (1)

[0047] Formula (2)

[0048] In these formulas (1) and (2), the relevant parameters are defined as follows:

[0049] and are the two coordinates of the 2D detector, corresponding to the X-direction and Y-direction coordinates in the plane coordinate system.

[0050] is the mass attenuation coefficient of water, and is the mass attenuation coefficient of iodine; the mass attenuation coefficient is an inherent property of the substance and is a known value.

[0051] represents the density projection of water, represents the density projection of iodine; where the integration range is from the focus to the detector, L is the integration ray path, and r is the material position. and is the value to be solved.

[0052] , are the known low-energy and high-energy X-ray spectra, respectively;

[0053] is the ray energy, is the minimum ray energy of the system, is the maximum ray energy of the system;

[0054] is the low-energy projection data (low-energy projection sequence) collected by the upper detector, which is equivalent to the above parameter P Li ; is the high-energy projection data (high-energy projection sequence) collected by the lower detector, which is equivalent to the above parameter P Hi , are all known values.

[0055] The above two relationships (Formula 1, Formula 2) constitute a feasible dichotomy model. According to the above formulas (1) and (2), the density projections of water and iodine are calculated by dichotomy.

[0056] Optionally, the material decomposition of the high-energy projection sequence and the low-energy projection sequence to obtain the two-dimensional vascular iodine density projection sequence includes obtaining the two-dimensional vascular iodine density projection sequence by a table lookup method based on the high-energy projection sequence and the low-energy projection sequence and utilizing a pre-constructed two-dimensional vascular iodine density projection sequence relationship table (pre-constructed based on a dichotomy model using actually collected high-energy projection data and low-energy projection data, or simulated high-energy projection data and low-energy projection data).

[0057] As mentioned above, the medical image processing system performs material decomposition on high-energy and low-energy projection sequences to generate a two-dimensional vascular iodine density projection sequence. An effective approach is to use a pre-constructed two-dimensional vascular iodine density projection sequence relationship table. This two-dimensional vascular iodine density projection sequence relationship table is constructed using combinations of high-energy and low-energy projection sequences, each containing different types and densities of iodine solutions, as well as various other material combinations. Simply put, it is a database that stores the matching relationships between various high-energy and low-energy projection sequence combinations and actual iodine densities under different conditions. After initially collecting the high-energy and low-energy projection sequences, the corresponding iodine density values ​​are matched with the relationship table, ultimately constructing the desired two-dimensional vascular iodine density projection sequence. Because human tissue in real life contains multiple elements and media, and there are significant individual differences, the pre-constructed relationship table needs to cover as many scenarios and conditions as possible to approximate real-world conditions. A significant advantage of this approach is its high processing efficiency. Complex real-time computation and simulation are not required; sequence decomposition can be completed through simple table lookups and matching. However, this also means that the accuracy and inclusiveness of the table have a very important impact on the overall performance of the system. When building the table, it is necessary to fully and specifically analyze the characteristics of different human tissues and the different factors that may affect the results.

[0058] Optionally, the two-dimensional vascular iodine density projection sequence Segmentation is performed to obtain a two-dimensional vascular iodine density segmentation projection sequence , including processing the two-dimensional vascular iodine density projection sequence using a threshold segmentation method to obtain the two-dimensional vascular iodine density segmented projection sequence. The two-dimensional vascular iodine density projection sequence refers to a two-dimensional iodine density projection sequence within a blood vessel. The two-dimensional vascular iodine density segmented projection sequence refers to a two-dimensional iodine density segmented projection sequence within a blood vessel.

[0059] The above describes a feasible method for segmenting two-dimensional vascular iodine density projection sequences, namely, threshold segmentation. Threshold segmentation is an important method for extracting regions of interest from original images or classifying images into different categories. It relies on the threshold segmentation method. For example, in current two-dimensional iodine density projection sequences, a reasonable iodine density value can be selected as a benchmark. Regions above this benchmark are suitable for identifying intravascular iodine products, while those below this benchmark are likely non-vascular areas. By classifying each point in the image according to this distinction, segmentation is achieved. More specifically, grayscale conversion is first performed to convert the original image into black and white, which provides a more contrasting color. Then, a threshold value is selected that lies between vascular and non-vascular regions, serving as the demarcation point. Furthermore, selecting an appropriate threshold is crucial for determining the effectiveness of segmentation. This requires comprehensive consideration of factors such as sharpness, accuracy, and error tolerance, and requires thorough testing and adjustment throughout the process to achieve the optimal threshold. Choosing an appropriate threshold can result in clearer and more coherent images of the segmented two-dimensional vascular iodine density projection sequence, which in turn accelerates subsequent three-dimensional reconstruction and registration.

[0060] Optionally, the three-dimensional reconstruction of the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image includes using a gradient descent method and a projection matrix to reconstruct the two-dimensional vascular iodine density projection sequence to obtain the three-dimensional vascular iodine density image.

[0061] For example, there are two-dimensional vascular iodine density projection sequences , use the projection matrix for the following formula and gradient descent method to reconstruct the optimal three-dimensional vascular iodine density image ,in, is the object to be optimized, n is the number of two-dimensional vascular iodine density projection sequences, n is an integer, which can be 10, 100, etc., i is the projection sequence number, which is an integer less than or equal to n, is the optimal solution to the problem being optimized.

[0062] Formula (3)

[0063] Projection Matrix It plays a vital role in imaging technology. Its main function is to convert the desired three-dimensional vascular iodine density image into Compared with the actual acquired two-dimensional vascular iodine density projection sequence Specifically, in X-ray imaging, the system matrix performs the reprojection operation. The projection matrix provides the mathematical foundation for the imaging process and is the core of the image reconstruction algorithm, enabling efficient conversion from a two-dimensional vascular iodine density projection sequence to a three-dimensional vascular iodine density image.

[0064] The above formula (3) is a specific method for extracting and segmenting the two-dimensional vascular iodine density projection sequence and instructing it to reconstruct the three-dimensional image. Here, we propose to use the gradient descent method and the projection matrix. The gradient descent method is one of the commonly used optimization algorithms. It helps the image processing system find the spatial structure that meets the expected effect in the three-dimensional reconstruction by searching for the best solution in the parameter space. In this process, the two-dimensional projection data is first imported into the mathematical space and systematized using the finite element line array, and then the projection matrix is ​​created. Then, multiple iterations are used to reach a minimum value, that is, the three-dimensional image shape with the minimum error. The projection matrix is ​​actually a mathematical structure tool that describes the input method of the two-dimensional projection data in three dimensions. Through this platform, the specific positions of all two-dimensional projection images in three dimensions and the spatial relationship between the entire layout system are clear at a glance. The gradient descent method can guide the corresponding adjustments required for each cycle update construction process during the entire reconstruction, and improve the spatial layout and density curvature characteristics. In this way, the detailed and in-depth content in the three-dimensional space is vividly displayed. The reconstructed three-dimensional vascular iodine density image has the diagnostic value of accurately expressing the iodine density level of each part and can intuitively reflect the pathological lesions in the blood vessels, providing better experimental data for its further segmentation.

[0065] Optionally, the image processing system further comprises using a threshold segmentation method to process the three-dimensional vascular iodine density image. Processing is performed to obtain the three-dimensional vascular iodine density segmentation image .

[0066] The three-dimensional vascular iodine density image is generated by three-dimensional reconstruction using the gradient descent method and its projection matrix, and is segmented again based on the idea of ​​threshold segmentation technology.

[0067] Optionally, the image processing system also includes aligning the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image to obtain a projection correction coefficient, including aligning the two-dimensional vascular segmentation projection sequence and the three-dimensional segmentation image using a forward projection method to obtain a registered projection correction matrix sequence.

[0068] Application of forward projection method to segmentation of two-dimensional vascular iodine density projection sequence and three-dimensional vascular iodine density segmentation images Perform registration to obtain the projection correction matrix sequence after registration The registration process is achieved by minimizing the following objective function:

[0069] Formula (4)

[0070] is the projection matrix used for 3D image reconstruction, is the human body rotation matrix, which is also the solution target. The optimal value of , an optimization method such as gradient descent can be used.

[0071] Obtaining a corrected projection matrix sequence according to the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction;

[0072] Formula (5)

[0073] The image processing system is designed to register 2D vascular segmentation projection sequences with 3D vascular iodine density segmentation images, generating a registered projection correction matrix sequence. Specifically, the system employs the orthographic projection method for registration. The concept of the orthographic projection method is to project 3D spatial information onto a 2D plane according to a fixed perspective and rules. Conversely, this method also supports the reconstruction and estimation of 3D geometric models based on the 2D projection information. When registering 2D and 3D segmented images, the orthographic projection method compares pixel information from the two images at the same field of view, while also considering vascular edge characteristics, continuity, and image structural markers. It then analyzes whether the final segmentation information matches the 2D image and generates a corresponding set of projection correction coefficients or matrices. This process ensures consistency and traceability between the 2D and 3D distribution maps in perspective and projection, resolves mismatches such as positional offset, rotation, and scaling between the two sequences, and generates a well-registered projection correction matrix sequence. Finally, based on the projection correction matrix sequence and the projection matrix used for 3D image reconstruction, a corrected projection matrix sequence is obtained. Compared to manual registration, this more closely matches modern medical image processing standards and provides a reliable foundation for motion compensation in the next step.

[0074] Optionally, the image processing system reconstructs a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence, including reconstructing a motion-corrected three-dimensional vascular iodine density image using a gradient descent method based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0075] For example, the corrected projection matrix can be used and two-dimensional vascular iodine density projection sequence , using the gradient descent method to reconstruct the motion-corrected three-dimensional vascular iodine density image .in, is the object to be optimized, is the optimal solution to the problem being optimized.

[0076] Formula (6)

[0077] The motion-corrected 3D vascular iodine density image is regenerated using the advanced gradient descent method. As a common optimization tool, gradient descent aims to minimize a loss function by repeatedly adjusting various parameters, ensuring that the generated 3D image is as consistent as possible with the actual image. This method also achieves better reproduction of lesion or structural details within the sequence. When laser positioning or motion cues are used, the improved 2D image-state data stream is recursively used to correct and fit the corresponding 3D rendering data. Furthermore, projection correction coefficients are intelligently weighted during the gradient descent reconstruction process, resulting in a highly optimized image that maximizes the restoration of the vascular tree, ensuring unobstructed and complete image quality, while also displaying dynamic images. A significant advantage of the resulting 3D vascular iodine density image is that it effectively mitigates image blurring and ghosting caused by accidental patient movement during the examination, while reliably enhancing the contrast between vessels and surrounding tissues. This allows physicians and researchers to observe and analyze the image with greater precision, authenticity, and ease of interference.

[0078] Through the aforementioned methodological steps, including data acquisition, material decomposition of projection sequences, segmentation, and 3D reconstruction, multiple technical approaches have enabled more precise observation and quantitative analysis of blood vessels in dynamic imaging. This approach not only improves overall image quality but also enhances understanding of vascular motion, contributing to improved clinical diagnosis and treatment outcomes.

[0079] Optionally, the dual-energy projection data is acquired, and the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence, including using a dual-flat-panel detector DSA imaging system to scan the target site where iodine-containing contrast agent is injected, and then simultaneously acquiring the high-energy projection sequence and the low-energy projection sequence.

[0080] Dual-energy projection data refers to a set of permutations and combinations of X-ray projection information at two different energy levels. The primary method for acquiring this projection data is direct target scanning using a dual-flat-panel detector DSA imaging system. Combined with the injection of iodinated contrast agent, simultaneous acquisition of image data of the target area yields independent projection sequences with two different energy standards: high and low. Dual-panel technology utilizes two layers (blocks) of flat-panel detectors to simultaneously record the X-ray dose distribution of two different radiation sources after they pass through the target area. This method significantly reduces exposure time and improves the signal-to-noise ratio, ensuring higher resolution and contrast between the resulting high- and low-energy projection sequences.

[0081] See also Figure 4 Another embodiment of the present application discloses a medical image processing method, which is executed by a medical image processing system and includes the following steps:

[0082] Step 301: Acquire dual-energy projection data, where the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence;

[0083] Step 302: performing material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence;

[0084] Step 303, segmenting the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence;

[0085] Step 304 , performing three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image;

[0086] Step 305 , segmenting the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image;

[0087] Step 306 , registering the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image to obtain a registered projection correction matrix sequence;

[0088] Step 307: Obtain a corrected projection matrix sequence based on the projection correction matrix sequence and the projection matrix for 3D image reconstruction;

[0089] Step 308 : reconstructing a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0090] The specific implementation methods or manners of each step in the medical image processing method in this embodiment can be found in the above description and will not be repeated here.

[0091] See also Figure 5 , a structural diagram of a processing device of a medical image processing system provided in another embodiment of the present application, the processing device includes a data acquisition module 501, a material decomposition module 502, a two-dimensional segmentation module 503, a three-dimensional reconstruction module 504, a three-dimensional segmentation module 505, an image registration module 506, a projection correction module 507 and a motion correction module 508, and the above modules are interconnected.

[0092] A data acquisition module 501 is configured to acquire dual-energy projection data, wherein the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence;

[0093] A material decomposition module 502 is used to perform material decomposition on the high-energy projection sequence and the low-energy projection sequence to obtain a two-dimensional vascular iodine density projection sequence;

[0094] A two-dimensional segmentation module 503 is used to segment the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmented projection sequence;

[0095] A three-dimensional reconstruction module 504 is used to perform three-dimensional reconstruction on a two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image;

[0096] A three-dimensional segmentation module 505 is used to segment the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmented image;

[0097] An image registration module 506 registers the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image to obtain a registered projection correction matrix sequence;

[0098] The projection correction module 507 obtains a corrected projection matrix sequence according to the projection correction matrix sequence and the projection matrix for 3D image reconstruction;

[0099] The motion correction module 508 is configured to reconstruct a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

[0100] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A medical image processing system, characterized in that: The medical image processing system is configured to: Acquiring dual-energy projection data, wherein the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence; Perform material decomposition on high-energy projection sequences and low-energy projection sequences to obtain a two-dimensional vascular iodine density projection sequence; Segmenting the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmentation projection sequence; Perform three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; Segmenting the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmentation image; Registering the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image to obtain a registered projection correction matrix sequence; Obtaining a corrected projection matrix sequence according to the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; A motion-corrected three-dimensional vascular iodine density image is reconstructed based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

2. The system according to claim 1, wherein: The material decomposition of the high-energy projection sequence and the low-energy projection sequence to obtain the two-dimensional vascular iodine density projection sequence includes inputting the high-energy projection sequence and the low-energy projection sequence into a dichotomy model to obtain the two-dimensional vascular iodine density projection sequence.

3. The system according to claim 1, wherein: The material decomposition of the high-energy projection sequence and the low-energy projection sequence to obtain the two-dimensional vascular iodine density projection sequence includes obtaining the two-dimensional vascular iodine density projection sequence based on the high-energy projection sequence and the low-energy projection sequence using a pre-constructed two-dimensional vascular iodine density projection sequence relationship table.

4. The system according to claim 1, wherein: The segmenting of the two-dimensional vascular iodine density projection sequence to obtain the two-dimensional vascular iodine density segmented projection sequence includes processing the two-dimensional vascular iodine density projection sequence using a threshold segmentation method to obtain the two-dimensional vascular iodine density segmented projection sequence.

5. The system according to claim 1, wherein: The three-dimensional reconstruction of the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image includes using a gradient descent method and a projection matrix to reconstruct the two-dimensional vascular iodine density projection sequence to obtain the three-dimensional vascular iodine density image.

6. The system according to claim 5, characterized in that The method comprises processing the three-dimensional vascular iodine density image by using a threshold segmentation method to obtain the three-dimensional vascular iodine density segmentation image.

7. The system according to claim 6, characterized in that The two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image are registered to obtain the registered projection correction matrix sequence, which includes using a forward projection method to register the two-dimensional vascular segmentation projection sequence and the three-dimensional segmentation image to obtain the registered projection correction matrix sequence.

8. The system according to claim 1, wherein: The method reconstructs a motion-corrected three-dimensional vascular iodine density image based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence, including reconstructing the motion-corrected three-dimensional vascular iodine density image using a gradient descent method based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

9. The system according to claim 1, wherein: The dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence, and is obtained simultaneously after scanning the target site injected with iodine-containing contrast agent using a dual-flat panel detector DSA imaging system.

10. A medical image processing method, characterized in that: The medical image processing method is performed by a medical image processing system and includes the following steps: Acquiring dual-energy projection data, wherein the dual-energy projection data includes a high-energy projection sequence and a low-energy projection sequence; Perform material decomposition on high-energy projection sequences and low-energy projection sequences to obtain a two-dimensional vascular iodine density projection sequence; Segmenting the two-dimensional vascular iodine density projection sequence to obtain a two-dimensional vascular iodine density segmentation projection sequence; Perform three-dimensional reconstruction on the two-dimensional vascular iodine density projection sequence to generate a three-dimensional vascular iodine density image; Segmenting the three-dimensional vascular iodine density image to obtain a three-dimensional vascular iodine density segmentation image; Registering the two-dimensional vascular iodine density segmentation projection sequence and the three-dimensional vascular iodine density segmentation image to obtain a registered projection correction matrix sequence; Obtaining a corrected projection matrix sequence according to the projection correction matrix sequence and the projection matrix used for three-dimensional image reconstruction; A motion-corrected three-dimensional vascular iodine density image is reconstructed based on the corrected projection matrix sequence and the two-dimensional vascular iodine density projection sequence.

Images