An aneurysm stability evaluation method and device, electronic equipment and storage medium

Abstract

The application discloses an aneurysm stability evaluation method and device, electronic equipment and a storage medium. The aneurysm stability evaluation method comprises the following steps: obtaining a 3D blood vessel image and a T1 weighted enhancement image of a target patient; mapping the signal intensity value of a pixel point on the T1 weighted enhancement image to the 3D blood vessel image; for the signal intensity value of each pixel point of the aneurysm on the 3D blood vessel image, determining an aneurysm stability evaluation value based on the signal intensity value and a target signal intensity value, and obtaining an aneurysm stability evaluation result based on the aneurysm stability evaluation value, wherein the target signal intensity value is the maximum signal intensity value of a target region selected on the T1 weighted enhancement image. The application does not need to rely on high-resolution equipment, and realizes automatic aneurysm stability evaluation, reduces manual operation errors, and improves aneurysm stability evaluation accuracy and reliability.

Description

Technical Field

[0001] This application generally relates to the field of medical image processing technology. More specifically, this application relates to a method, apparatus, electronic device, and storage medium for assessing aneurysm stability. Background Technology

[0002] Intracranial aneurysms (UIA, hereinafter referred to as aneurysms) are a common cerebrovascular disease, and their rupture can lead to subarachnoid hemorrhage (SAH). For aneurysms with a low risk of rupture, long-term stability assessment is crucial in clinical management. Here, aneurysm stability assessment refers to the probability of aneurysm rupture.

[0003] Currently, aneurysm stability assessment generally relies on two-dimensional multiplanar views, where physicians manually mark the aneurysm region. However, this method requires high-resolution MRI equipment, making it difficult to apply on conventional equipment such as 1.5T or 3T MRI scanners. Furthermore, manually marking the aneurysm region is highly subjective and can easily lead to discrepancies between the reconstructed morphology and the actual situation.

[0004] In view of this, there is an urgent need to provide a method, device, electronic device and storage medium for aneurysm stability assessment that does not rely on high-resolution equipment or manually mark the aneurysm area in a two-dimensional multi-planar view, thereby achieving automated aneurysm stability assessment, reducing manual operation errors and improving the accuracy and reliability of aneurysm stability assessment. Summary of the Invention

[0005] In order to at least address one or more of the technical problems mentioned above, this application proposes a method, apparatus, electronic device, and storage medium for assessing aneurysm stability in several aspects.

[0006] In a first aspect, this application provides a method for assessing aneurysm stability, comprising: acquiring 3D vascular images and T1-weighted enhanced images of a target patient; mapping the signal intensity values ​​of pixels on the T1-weighted enhanced images onto the 3D vascular images; determining an aneurysm stability assessment value based on the signal intensity value of each pixel of the aneurysm on the 3D vascular images and a target signal intensity value, and obtaining an aneurysm stability assessment result based on the aneurysm stability assessment value, wherein the target signal intensity value is the maximum signal intensity value of a selected target region on the T1-weighted enhanced images.

[0007] In some embodiments, mapping the signal intensity values ​​of pixels on the T1-weighted enhanced image to the 3D vascular image includes: acquiring first spatial data of the 3D vascular image and second spatial data of the T1-weighted enhanced image; registering pixels on the 3D vascular image and pixels on the T1-weighted enhanced image based on the first spatial data and the second spatial data to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image, and performing spatial transformation on the 3D vascular image based on the transformation matrix; performing three-dimensional reconstruction processing on the transformed 3D vascular image to obtain a vascular model; and for each pixel on the vascular model, mapping the signal intensity value of the registration point matching that pixel on the T1-weighted enhanced image to the vascular model.

[0008] In some embodiments, acquiring the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image includes: acquiring the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image based on the Digital Imaging and Communication Medicine (DICOM) data structure; wherein the first spatial data includes at least: the spatial coordinates of the first pixel on the 3D vascular image, the distance between adjacent pixels, and the pixel intensity value; the second spatial data includes at least: the spatial coordinates of the first pixel on the T1-weighted enhanced image, the distance between adjacent pixels, and the signal intensity value.

[0009] In some embodiments, registering pixels on the 3D vascular image and pixels on the T1-weighted enhanced image based on the first spatial data and the second spatial data to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image includes: acquiring a first set of points from the 3D vascular image and a second set of points from the T1-weighted enhanced image; wherein the spatial coordinates of the points in the first set of points are obtained based on the first spatial data, and the spatial coordinates of the points in the second set of points are obtained based on the second spatial data; registering the first set of points and the second set of points based on a set registration method to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image.

[0010] In some embodiments, the transformation matrix includes a rotation matrix and a translation matrix; the registration of the first point set and the second point set based on a set registration method to obtain the transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image includes: for each target point in the first point set, finding the nearest matching point in the second point set, and forming a third point set from the matching points of all target points; calculating the first centroid of the first point set and the second centroid of the third point set; constructing a covariance equation based on the first centroid, the second centroid, the first point set, and the third point set; and performing singular value decomposition. The SVD method and the covariance equation are used to calculate the candidate rotation matrix, and the candidate translation matrix is ​​obtained based on the first centroid, the second centroid, and the rotation matrix. The target points in the first point set are subjected to coordinate transformation based on the candidate rotation matrix and the candidate translation matrix to obtain a candidate point set, and the mean square error is calculated based on the candidate point set and the third point set. When the mean square error meets the set conditions, the candidate rotation matrix and the candidate translation matrix are determined as the transformation matrix. When the mean square error does not meet the set conditions, the first point set is re-acquired from the 3D vascular image and the second point set is re-acquired from the T1-weighted enhanced image.

[0011] In some embodiments, the first point set and the second point set are obtained from the aneurysm region, the carotid artery region, and the M1 segment region of the middle cerebral artery.

[0012] In some embodiments, obtaining an aneurysm stability assessment result based on the aneurysm stability assessment value includes: if there is an aneurysm stability assessment value greater than a set assessment value, a first aneurysm stability assessment result is obtained, which is used to characterize aneurysm instability; if all aneurysm stability assessment values ​​are less than or equal to the set assessment value, a second aneurysm stability assessment result is obtained, which is used to characterize aneurysm stability.

[0013] In a second aspect, this application provides an aneurysm stability assessment device, comprising: an image acquisition module for acquiring 3D vascular images and T1-weighted enhanced images of a target patient; a mapping module for mapping the signal intensity values ​​of pixels on the T1-weighted enhanced images to the 3D vascular images; and a stability assessment module for determining an aneurysm stability assessment value based on the signal intensity value of each pixel of the aneurysm on the 3D vascular images and a target signal intensity value, and obtaining an aneurysm stability assessment result based on the aneurysm stability assessment value, wherein the target signal intensity value is the maximum signal intensity value of a selected target region on the T1-weighted enhanced images.

[0014] In a third aspect, this application provides an electronic device comprising: a processor configured to execute program instructions; and a memory configured to store the program instructions, which, when loaded and executed by the processor, cause the processor to perform a method for assessing aneurysm stability according to the first aspect or any optional embodiment of the first aspect.

[0015] In a fourth aspect, this application provides a computer-readable storage medium storing program instructions that, when loaded and executed by a processor, cause the processor to perform the method for assessing aneurysm stability according to the first aspect or any optional embodiment of the first aspect.

[0016] By using the aneurysm stability assessment method, device, electronic device and storage medium provided above, the embodiments of this application acquire 3D vascular images and T1-weighted enhanced images of the target patient, map the signal intensity values ​​of the pixels on the T1-weighted enhanced images onto the 3D vascular images, and calculate the aneurysm stability assessment value by combining the maximum signal intensity value of the target area. This achieves automated aneurysm stability assessment without relying on high-resolution equipment or manually marking the aneurysm area in a two-dimensional multi-planar view, reducing manual operation errors and improving the accuracy and reliability of aneurysm stability assessment. Attached Figure Description

[0017] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts, wherein:

[0018] Figure 1 An exemplary flowchart of an aneurysm stability assessment method according to some embodiments of this application is shown;

[0019] Figure 2 Three-dimensional thermograms of aneurysm wall enhancement are shown in some embodiments of this application;

[0020] Figure 3 An exemplary structural block diagram of an aneurysm stability assessment device according to some embodiments of this application is shown;

[0021] Figure 4 An exemplary structural block diagram of an electronic device according to some embodiments of this application is shown. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be understood that the terms "comprising" and "including" used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0024] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0025] As used in this specification and claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0026] The specific embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0027] Exemplary application scenarios

[0028] Intracranial aneurysms (UIA, hereinafter referred to as aneurysms) are a common cerebrovascular disease, and their rupture can lead to subarachnoid hemorrhage (SAH). However, apart from high-risk aneurysms larger than 7 mm in diameter, most aneurysms have a low probability of rupture. Therefore, long-term stability assessment of aneurysms is crucial in clinical management. Here, aneurysm stability assessment refers to the probability of aneurysm rupture.

[0029] Histological analysis of the aneurysm wall indicates that chronic inflammation of the aneurysm wall is an important marker of aneurysm instability, which may lead to aneurysm formation and rupture, as well as postoperative aneurysm recurrence.

[0030] In recent years, ultra-small superparamagnetic iron oxide (USPIO) enhancement technology has been frequently used to target the detection of inflammation in aneurysm walls, and has been confirmed in 3T gadolinium-enhanced vascular wall MRI (VW-MRI): after the contrast agent is circumferentially taken up in the aneurysm wall (24-72 hours after infusion), it will show a significant increase in image signal in T1-weighted enhanced images. This signal enhancement phenomenon near the aneurysm is called aneurysm wall enhancement (AWE).

[0031] Furthermore, by studying patients' T1-weighted imaging combined with clinical information, it was demonstrated that the incidence of AWE in stable aneurysms was significantly lower than that in aneurysms with morphological changes, and the incidence of AWE in aneurysms with daughter sac formation was significantly higher than that in aneurysms with complete sac dilation, proving that AWE is related to aneurysm growth.

[0032] Meanwhile, some studies have quantified AWE values ​​and conducted statistical analysis on the AWE values ​​of ruptured aneurysms and unruptured aneurysms. The results showed that the AWE value of ruptured aneurysms was much higher than that of unruptured aneurysms.

[0033] Currently, aneurysm stability assessment usually relies on two-dimensional multiplanar views or manually marked three-dimensional reconstructions. However, this method requires high-resolution MRI equipment, which is difficult to apply on conventional equipment such as 1.5T or 3T. Furthermore, manually marking the aneurysm region is highly subjective and can easily lead to deviations between the reconstructed morphology and the actual situation.

[0034] In view of this, the embodiments of this application provide a method for assessing aneurysm stability, which does not rely on high-resolution equipment or require manual marking of the aneurysm region in a two-dimensional multi-planar view, thereby achieving automated aneurysm stability assessment, reducing manual operation errors, and improving the accuracy and reliability of aneurysm stability assessment.

[0035] Figure 1 An exemplary flowchart of an aneurysm stability assessment method 100 according to some embodiments of this application is shown. It is understood that the aneurysm stability assessment method 100 described above can be executed by any suitable device with data processing capabilities, such as, but not limited to, terminal devices, processors, and servers.

[0036] like Figure 1As shown, the aneurysm stability assessment method 100 includes: step S110: acquiring 3D vascular images and T1-weighted enhanced images of the target patient; step S120: mapping the signal intensity values ​​of pixels on the T1-weighted enhanced images to the 3D vascular images; step S130: for each pixel of the aneurysm on the 3D vascular images, determining an aneurysm stability assessment value based on the signal intensity value and a target signal intensity value, and obtaining an aneurysm stability assessment result based on the aneurysm stability assessment value, wherein the target signal intensity value is the maximum signal intensity value of the selected target region on the T1-weighted enhanced images.

[0037] For example, in the embodiments of this application, the target patient in step S110 above refers to an individual who needs to undergo aneurysm stability assessment, such as a patient suspected of or diagnosed with an aneurysm.

[0038] 3D vascular imaging refers to three-dimensional vascular images obtained through three-dimensional vascular imaging technologies, such as CT angiography (CTA), magnetic resonance angiography (MRA), time-of-flight magnetic resonance angiography (MRA-TOF), phase-contrast magnetic resonance angiography (MRA-PC), and digital subtraction angiography (DSA). It can clearly display the morphology, location, and structure of blood vessels and aneurysms. These images are acquired using relevant medical imaging equipment.

[0039] T1-weighted contrast-enhanced imaging is a sequence in magnetic resonance imaging. It is an image acquired after the injection of a contrast agent. The contrast agent can enter the tissue through blood vessels, enhancing the signal in areas with rich blood supply or vascular abnormalities (such as aneurysms). Therefore, this image can reflect the blood supply characteristics or the degree of enhancement of the tissue.

[0040] Specifically, gadolinium (Gd) contrast agent can be injected into the target patient before image acquisition. During injection, 0.1 mmol / kg of Gd contrast agent is injected at an injection pressure of 100 psi and an injection rate of 2.0 mL / s, followed by flushing with 20 mL of normal saline. As a specific embodiment of this application, the MRI scanner used for acquiring T1-weighted enhanced images is a Siemens 3.0T Risma.

[0041] It should be noted that the 3D vascular images and T1-weighted enhanced images of the target patients were obtained with the consent of the target patients. Furthermore, the 3D vascular images and T1-weighted enhanced images can be obtained simultaneously or separately; this application does not specifically limit this.

[0042] For example, as described above, the signal intensity value of a pixel in a T1-weighted enhanced image can reflect the signal strength of the pixel in the T1-weighted enhanced image. Specifically, the signal intensity value of the aneurysm region is greater than that of the vascular region. Based on this, the signal intensity value of a pixel in the T1-weighted enhanced image can be mapped to the corresponding pixel in the 3D vascular image, enabling information fusion between the 3D vascular image and the T1-weighted enhanced image in a single coordinate system.

[0043] In this embodiment of the application, due to the different acquisition devices of the two types of images and the differences in the position of the target patient, there is a spatial positional deviation between the 3D vascular image and the T1-weighted enhanced image. Therefore, it is necessary to align the spatial coordinates of the two images (i.e., register) before mapping, so that the signal intensity values ​​of the pixels on the T1-weighted enhanced image can be mapped to the 3D vascular image. As for the specific registration method, it is described in detail in the following embodiments, and will not be repeated here.

[0044] For example, the target signal intensity value (denoted as Stalksignal) in step S130 above is the maximum signal intensity value of the selected target region on the T1-weighted enhanced image. Here, the target region can be the pituitary region of the brain (i.e., a gland in the brain), which can be manually selected on the T1-weighted enhanced image using the QTVTK.exe tool. For example, a 5mm spherical range can be selected on the T1-weighted enhanced image. In response to this selection operation, the electronic device obtains the maximum signal intensity value of the target region as the target signal intensity value, that is, the maximum signal intensity value of the pituitary gland is used as the comparison parameter.

[0045] It should be noted that the 5mm mentioned above is merely an example and is not intended to limit this application. Other suitable ranges are also within the protection scope of this application.

[0046] In this embodiment, the aneurysm stability assessment value is used to determine whether the aneurysm is stable. Its calculation method is as follows:

[0047] The signal intensity value of each pixel of an aneurysm in a 3D vascular image (denoted as ). The aneurysm stability assessment value is determined based on the signal intensity value and the target signal intensity value. Specifically, it can be calculated using the following formula (1).

[0048] Formula (1)

[0049] in, This is a value used to assess aneurysm stability. The signal intensity value of the pixel on the aneurysm; The target signal strength value.

[0050] In this embodiment, after obtaining the aneurysm stability assessment value for each pixel on the aneurysm, an aneurysm stability assessment result is obtained based on the aneurysm stability assessment value. There can be many types of aneurysm stability assessment results; as a specific implementation of this application, the aneurysm stability assessment result includes both aneurysm instability and aneurysm stability.

[0051] Based on the above description of the aneurysm stability assessment results, the aneurysm stability assessment results obtained based on the aneurysm stability assessment values ​​can be specifically as follows: if there is an aneurysm stability assessment value greater than the set assessment value, then the first aneurysm stability assessment result is obtained, which is used to characterize aneurysm instability; if all aneurysm stability assessment values ​​are less than or equal to the set assessment value, then the second aneurysm stability assessment result is obtained, which is used to characterize aneurysm stability.

[0052] For example, the evaluation value is a pre-set value (e.g., 0.64, etc.), which can be set based on experience or other determination methods. This application embodiment does not specifically limit the evaluation value.

[0053] If aneurysm stability assessment value is present If the value is greater than the set assessment value (0.64), the aneurysm is considered unstable; if all aneurysm stability assessment values ​​are greater than the set value (0.64), the aneurysm is considered unstable. If all values ​​are less than or equal to the set assessment value (0.64), the aneurysm is considered stable.

[0054] for The region with a value greater than 0.64 is the AWE region, which can be directly rendered using conventional software or algorithms to obtain a three-dimensional heat map of the aneurysm wall enhancement, making it easier for doctors to view.

[0055] Figure 2 Three-dimensional thermograms of aneurysm wall enhancement according to some embodiments of this application are shown. Figure 2 As shown, Figure 2 The left side includes a color bar, where each color corresponds to a specific color. The values ​​range from blue to red, from 0 to 0.64. If the value is greater than 0.64, it will be displayed as red on the blood vessel model. If it is within the range of 0-0.64, the corresponding color will be displayed on the model according to the value on the color bar.

[0056] This application embodiment acquires 3D vascular images and T1-weighted enhanced images of the target patient, maps the signal intensity values ​​of pixels on the T1-weighted enhanced images to the 3D vascular images, and calculates the aneurysm stability assessment value by combining the maximum signal intensity value of the target area. This achieves automated aneurysm stability assessment without relying on high-resolution equipment or manually marking the aneurysm area in a two-dimensional multi-planar view, reducing manual operation errors and improving the accuracy and reliability of aneurysm stability assessment.

[0057] The registration process of 3D vascular images and T1-weighted enhanced images is described below with an example:

[0058] As an optional embodiment of this application, the above-described mapping of the signal intensity values ​​of pixels on the T1-weighted enhanced image to the 3D vascular image includes: acquiring first spatial data of the 3D vascular image and second spatial data of the T1-weighted enhanced image; registering the pixels on the 3D vascular image and the pixels on the T1-weighted enhanced image according to the first spatial data and the second spatial data to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image, and performing spatial transformation on the 3D vascular image based on the transformation matrix; performing three-dimensional reconstruction processing on the transformed 3D vascular image to obtain a vascular model; and for each pixel on the vascular model, mapping the signal intensity value of the registration point matching that pixel on the T1-weighted enhanced image to the vascular model.

[0059] For example, the first spatial data mentioned above includes at least: the spatial coordinates of the first pixel on the 3D vascular image, the distance between adjacent pixels, and the pixel intensity value; here, the spatial coordinates of the first pixel refer to the physical coordinates of the first pixel at the top left corner of the first slice of the 3D vascular image, and the pixel intensity value refers to the brightness of the pixel, which is used to form a three-dimensional vascular model; the second spatial data includes at least: the spatial coordinates of the first pixel on the T1-weighted enhanced image, the distance between adjacent pixels, and the signal intensity value; here, the spatial coordinates of the first pixel refer to the physical coordinates of the first pixel at the top left corner of the first slice of the T1-weighted enhanced image, and the signal intensity value is used to assess the stability of the aneurysm.

[0060] In this embodiment of the application, obtaining the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image can specifically be: obtaining the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image based on the Digital Imaging and Communication Medicine (DICOM) data structure.

[0061] The DICOM data structure here is a standardized format for medical images, obtainable using the DicomVTK open-source library. In this embodiment, the spatial data contained in the DICOM data structure has a unified specification, ensuring that the spatial parameters of different devices and different images can be uniformly parsed.

[0062] For example, in a 3D vascular image, the spatial coordinates of the first pixel are labeled (0x0020, 0x0030), and the specific spatial coordinates are (101.44, -71.04, -364.72); the distance between adjacent pixels is labeled (0x0018, 0x0016), and its value is (0.4, 0.4); the pixel layer distance is labeled (0x0018, 0x0050), and its value is 0.226; the pixel intensity value is labeled (0x7FE0, 0x0010).

[0063] For example, for a T1 weighted enhanced image, the label for the spatial coordinates of the first pixel is (0x0020, 0x0030), and the specific spatial coordinates are (-58.64, -34.10, -80.75); the label for the distance between adjacent pixels is (0x0018, 0x0016), and its value is (0.6, 0.6); the label for the pixel layer distance is (0x0018, 0x0050), and its value is 0.7; the label for the signal strength value is (0x7FE0, 0x0010).

[0064] For example, in the embodiments of this application, the transformation matrix may include a rotation matrix (denoted as R) and a translation matrix (denoted as t). Registering pixels on the 3D vascular image with pixels on the T1-weighted enhanced image refers to spatially matching selected points in the 3D vascular image with selected points in the T1-weighted enhanced image to minimize the spatial distance error after matching. ,here, This represents the selected points in the 3D vascular image; n represents the number of selected points. Indicates the relationship between T1 weighted image and Matching points.

[0065] In this embodiment, pixels on the 3D vascular image and pixels on the T1-weighted enhanced image are registered based on first spatial data and second spatial data to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image. Specifically, this can be done by: acquiring a first point set from the 3D vascular image and a second point set from the T1-weighted enhanced image; and registering the first point set and the second point set based on a set registration method to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image.

[0066] In the embodiments of this application, the first point set and the second point set may be collected from the aneurysm region, or they may be collected from at least two regions among the aneurysm region, the carotid artery region, and the M1 segment region of the middle cerebral artery. The embodiments of this application do not specifically limit this.

[0067] Preferably, both the first and second point sets are collected from the aneurysm region, the carotid artery region, and the M1 segment region of the middle cerebral artery.

[0068] Based on the above preferred scheme, when collecting the first point set, the interactive selection tool QTAWE.exe developed based on QT and VTK can be used to select a 3mm sphere range from the aneurysm region, the C4 segment region of the carotid artery, and the initial segment region of the M1 segment of the middle cerebral artery on the 3D vascular image, respectively, to obtain 3 sub-point sets. These 3 sub-point sets constitute the first point set mentioned above. The spatial coordinates of the points in the first point set are obtained based on the first spatial data.

[0069] When acquiring the second point set, QTAWE.exe can be used to select a 3mm sphere from the aneurysm region, the C4 segment region of the carotid artery, and the initial segment region of the M1 segment of the middle cerebral artery on T1-weighted enhanced images to obtain three sub-point sets. These three sub-point sets constitute the aforementioned second point set, and the spatial coordinates of the points in the second point set are obtained based on the second spatial data.

[0070] It should be noted that the above 3mm is only an example and is not intended to limit this application. Other reasonable values ​​are also within the scope of protection of this application.

[0071] For example, after obtaining the first point set and the second point set, the first point set and the second point set can be registered based on a specified registration method to obtain a transformation matrix. There are many possible registration methods, such as the ICP algorithm with minimum spatial transformation. This application embodiment does not specifically limit the registration method used. This application embodiment only describes the ICP algorithm as an example of the registration method used.

[0072] Specifically, firstly, for each target point in the first point set, find the nearest matching point in the second point set;

[0073] For example, in this embodiment of the application, each target point in the first point set is denoted as For each target point in the first point set Find the target point from the second point. The nearest matching point (denoted as) The distance here can be represented in many ways, such as Euclidean distance, Hamming distance, etc. This application embodiment does not specifically limit this, and this application embodiment only describes it using Euclidean distance as an example.

[0074] The above matching points It can be calculated using the following formula (2):

[0075] (2)

[0076] in, Represents matching points; Let represent the i-th target point in the first set of points; n represents the number of target points in the first set of points. This represents the j-th point in the second point set.

[0077] After calculating each target point matching points After that, all target points matching points This constitutes the third point set.

[0078] Next, calculate the first centroid of the first point set and the second centroid of the third point set; specifically, these can be calculated using the following formulas (3) and (4):

[0079] Formula (3)

[0080] Formula (4)

[0081] in, Indicates the first mass center; It represents the second mass center.

[0082] Next, construct the covariance equation based on the first centroid, the second centroid, the first point set, and the third point set; specifically, it can be constructed using the following formula (5):

[0083] Formula (5)

[0084] Where H represents the covariance equation; This represents the transpose of A.

[0085] Next, candidate rotation matrices are calculated using the singular value decomposition (SVD) method and the covariance equation, and candidate translation matrices are obtained based on the first centroid, the second centroid, and the rotation matrices.

[0086] For example, the SVD described above is a common matrix factorization algorithm in linear algebra, applicable to matrices of various shapes. It can be characterized as follows: Where U is the left singular vector matrix and is an orthogonal matrix; V is a diagonal matrix of singular values, and V is a diagonal matrix; V is a right singular vector matrix, and V is an orthogonal matrix.

[0087] The candidate rotation matrix can be calculated using the Singular Value Decomposition (SVD) method and the covariance equation, specifically by the following formula (6):

[0088] Formula (6)

[0089] Here, R is the candidate rotation matrix.

[0090] The candidate translation matrix, based on the first centroid, the second centroid, and the rotation matrix, can be calculated using the following formula (7):

[0091] Formula (7)

[0092] in, This represents the candidate translation matrix.

[0093] Next, the target points in the first point set are transformed by the candidate rotation matrix and the candidate translation matrix to obtain the candidate point set, and the mean square error is calculated based on the candidate point set and the third point set.

[0094] In this embodiment of the application, after obtaining the candidate rotation matrix R and the candidate translation matrix t, the target points in the first point set are subjected to coordinate transformation based on the candidate rotation matrix and the candidate translation matrix. Specifically, the coordinate transformation can be performed using the following formula (8):

[0095] Formula (8)

[0096] in, This represents the target point after coordinate transformation.

[0097] In this embodiment, after performing coordinate transformation on all target points in the first point set based on the candidate rotation matrix and the candidate translation matrix, the transformed points form a candidate point set. The mean square error is calculated based on the candidate point set and the third point set, specifically by the following formula (9):

[0098] Formula (9)

[0099] in, This represents the mean square error.

[0100] Finally, when the mean square error meets the set conditions, the candidate rotation matrix and candidate translation matrix are determined as transformation matrices; when the mean square error does not meet the set conditions, the first point set is re-acquired from the 3D vascular image and the second point set is re-acquired from the T1-weighted enhanced image.

[0101] For example, there can be many different setting conditions, such as the mean square error being less than a set value, etc., and this application embodiment does not specifically limit them. This application embodiment only uses the setting condition of the mean square error being less than a set value as an example for illustration.

[0102] When the mean square error is less than the set value (e.g., 1e-3), the candidate rotation matrix and candidate translation matrix are determined as the transformation matrix; when the mean square error is greater than or equal to the set value, the first point set is re-acquired from the 3D vascular image and the second point set is re-acquired from the T1-weighted enhanced image, and the registration is repeated until the mean square error meets the set condition to obtain the transformation matrix.

[0103] For example, in the embodiments of this application, after registration to obtain the transformation matrix, the 3D vascular image is spatially transformed based on the transformation matrix. Specifically, for each pixel of the 3D vascular image, the coordinate transformation is performed according to the above formula (8), and then the 3D vascular image is spatially transformed. The spatial coordinates of the transformed 3D vascular image change, but the pixel intensity value remains unchanged.

[0104] Of course, after spatial transformation of the 3D vascular image, spatial interpolation can be performed on the spatial coordinates and pixel values ​​of the 3D vascular image using conventional 3D linear interpolation formulas, based on the pixels in the T1-weighted enhanced image. This integrates the pixels of the T1-weighted enhanced image into the spatial coordinates of the 3D vascular image. At this point, the spatial coordinate array structure of the 3D vascular image is (x, y, z, S), where (x, y, z) are the spatial coordinate values, containing all spatial coordinate points of both the 3D vascular image and the T1-weighted enhanced image, and S is the pixel intensity value of the corresponding spatial coordinate, used for 3D reconstruction.

[0105] The transformed 3D vascular image is then subjected to 3D reconstruction processing to obtain a vascular model. There are many methods for 3D reconstruction, such as level set reconstruction, to reconstruct the vascular model from the 3D image. This model is then converted into a triangular mesh model using the Marching Cubes algorithm. After obtaining the vascular model through 3D reconstruction, further processing (e.g., Laplacian smoothing) can be applied to eliminate surface noise, thereby obtaining a continuous and complete 3D vascular model.

[0106] Based on the above description, for each pixel in the blood vessel model, the signal intensity value of the registration point that matches that pixel in the T1-weighted enhanced image is mapped to the blood vessel model. Here, the registration point refers to the pixel in the T1-weighted enhanced image that has the shortest distance to the pixel.

[0107] The embodiments of this application use the above method to map the signal intensity values ​​on T1-weighted enhanced images onto a blood vessel model, thereby facilitating subsequent analysis.

[0108] Figure 3 An exemplary structural block diagram of an aneurysm stability assessment device 300 according to some embodiments of this application is shown.

[0109] like Figure 3 As shown, the aneurysm stability assessment device 300 includes: an image acquisition module 310 for acquiring 3D vascular images and T1-weighted enhanced images of the target patient; a mapping module 320 for mapping the signal intensity values ​​of pixels on the T1-weighted enhanced images to the 3D vascular images; and a stability assessment module 330 for determining an aneurysm stability assessment value based on the signal intensity value of each pixel of the aneurysm on the 3D vascular images and a target signal intensity value, and obtaining an aneurysm stability assessment result based on the aneurysm stability assessment value, wherein the target signal intensity value is the maximum signal intensity value of the selected target region on the T1-weighted enhanced images.

[0110] As an optional embodiment of this application, the mapping module 320 includes: a spatial data acquisition unit, used to acquire first spatial data of the 3D vascular image and second spatial data of the T1-weighted enhanced image; a registration unit, used to register pixels on the 3D vascular image and pixels on the T1-weighted enhanced image according to the first spatial data and the second spatial data, to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image, and to perform spatial transformation on the 3D vascular image based on the transformation matrix; a three-dimensional reconstruction module, used to perform three-dimensional reconstruction processing on the transformed 3D vascular image to obtain a vascular model; and a mapping unit, used to map the signal intensity value of the registration point matching the pixel on the T1-weighted enhanced image to the vascular model for each pixel on the vascular model.

[0111] As an optional embodiment of this application, the aforementioned spatial data acquisition unit is specifically used to: acquire first spatial data of 3D vascular images based on the Digital Imaging and Communication Medicine (DICOM) data structure and acquire second spatial data of T1-weighted enhanced images based on the Digital Imaging and Communication Medicine (DICOM) data structure; wherein, the first spatial data includes at least: the spatial coordinates of the first pixel on the 3D vascular image, the distance between adjacent pixels, and the pixel intensity value; the second spatial data includes at least: the spatial coordinates of the first pixel on the T1-weighted enhanced image, the distance between adjacent pixels, and the signal intensity value.

[0112] As an optional embodiment of this application, the above-mentioned registration unit is specifically used for: acquiring a first set of points from a 3D vascular image and acquiring a second set of points from a T1-weighted enhanced image; wherein, the spatial coordinates of the points in the first set of points are obtained based on the first spatial data, and the spatial coordinates of the points in the second set of points are obtained based on the second spatial data; registering the first set of points and the second set of points based on a set registration method to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image.

[0113] As an optional embodiment of this application, the transformation matrix includes a rotation matrix and a translation matrix; the registration unit above registers the first point set and the second point set based on a set registration method to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image, including: for each target point in the first point set, finding the nearest matching point in the second point set, and forming a third point set from the matching points of all target points; calculating the first centroid of the first point set and the second centroid of the third point set; constructing a covariance square based on the first centroid, the second centroid, the first point set, and the third point set. The process involves calculating candidate rotation matrices using Singular Value Decomposition (SVD) and covariance equations, and obtaining candidate translation matrices based on the first centroid, second centroid, and rotation matrices. Based on the candidate rotation and translation matrices, coordinate transformations are performed on the target points in the first point set to obtain a candidate point set. The mean square error is then calculated based on the candidate point set and the third point set. When the mean square error meets the set conditions, the candidate rotation and translation matrices are determined as transformation matrices. If the mean square error does not meet the set conditions, the first point set is re-acquired from 3D vascular images, and the second point set is re-acquired from T1-weighted enhanced images.

[0114] As an optional embodiment of this application, the first point set and the second point set are collected from the aneurysm region, the carotid artery region and the M1 segment region of the middle cerebral artery.

[0115] As an optional embodiment of this application, the stability assessment module 330 is specifically used to: if there is an aneurysm stability assessment value greater than a set assessment value, a first aneurysm stability assessment result is obtained, which is used to characterize aneurysm instability; if all aneurysm stability assessment values ​​are less than or equal to the set assessment value, a second aneurysm stability assessment result is obtained, which is used to characterize aneurysm stability.

[0116] Correspondingly, this disclosure also provides Figure 3 The hardware structure diagram of the device shown is as follows: Figure 4 As shown, the electronic device 400 can be a device for implementing the method 100 described above. For example... Figure 4As shown, the electronic device 400 includes a processor 410 and a memory 420. The memory 420 is configured to store program instructions; the processor 410 is configured to load and execute the program instructions stored in the memory 420 to implement the method embodiment of the corresponding aneurysm stability assessment method shown above.

[0117] As one embodiment, memory 420 can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as program instructions, data, etc. For example, memory 420 can be volatile memory, non-volatile memory, or similar storage media. Specifically, memory 420 can be RAM (Random Access Memory), flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0118] This concludes the process. Figure 4 Description of the electronic device shown.

[0119] While numerous embodiments of this application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will arise for those skilled in the art without departing from the spirit and intent of this application. It should be understood that various alternatives to the embodiments of this application described herein may be employed in the practice of this application. The appended claims are intended to define the scope of protection of this application and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A method for assessing aneurysm stability, characterized in that, include: Acquire 3D vascular images and T1-weighted enhanced images of the target patient; The signal intensity values ​​of pixels on the T1-weighted enhanced image are mapped to the 3D vascular image; For each pixel of the aneurysm in the 3D vascular image, an aneurysm stability assessment value is determined based on the signal intensity value and a target signal intensity value, and an aneurysm stability assessment result is obtained based on the aneurysm stability assessment value. The target signal intensity value is the maximum signal intensity value of the selected target region on the T1-weighted enhanced image; the selected target region is the pituitary region. The step of mapping the signal intensity values ​​of pixels on the T1-weighted enhanced image to the 3D vascular image includes: Acquire the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image; Based on the first spatial data and the second spatial data, the pixels on the 3D vascular image and the pixels on the T1 weighted enhanced image are registered to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1 weighted enhanced image, and the 3D vascular image is spatially transformed based on the transformation matrix. The transformed 3D vascular image is subjected to three-dimensional reconstruction processing to obtain a vascular model; For each pixel on the blood vessel model, the signal intensity value of the registration point that matches the pixel on the T1-weighted enhanced image is mapped onto the blood vessel model.

2. The method according to claim 1, characterized in that, The acquisition of the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image includes: The first spatial data of the 3D vascular image is obtained based on the Digital Imaging and Communication Medical DICOM data structure, and the second spatial data of the T1-weighted enhanced image is obtained based on the Digital Imaging and Communication Medical DICOM data structure; wherein, the first spatial data includes at least: the spatial coordinates of the first pixel on the 3D vascular image, the distance between adjacent pixels, and the pixel intensity value; the second spatial data includes at least: the spatial coordinates of the first pixel on the T1-weighted enhanced image, the distance between adjacent pixels, and the signal intensity value.

3. The method according to claim 1, characterized in that, The step of registering pixels on the 3D vascular image and pixels on the T1-weighted enhanced image based on the first spatial data and the second spatial data to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image includes: A first set of points is acquired from the 3D vascular image and a second set of points is acquired from the T1-weighted enhanced image; wherein the spatial coordinates of the points in the first set of points are obtained based on the first spatial data, and the spatial coordinates of the points in the second set of points are obtained based on the second spatial data; Based on the established registration method, the first point set and the second point set are registered to obtain the transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image.

4. The method according to claim 3, characterized in that, The transformation matrix includes a rotation matrix and a translation matrix; the transformation matrix for spatial transformation between the 3D vascular image and the T1-weighted enhanced image is obtained by registering the first point set and the second point set based on a set registration method, including: For each target point in the first point set, find the nearest matching point in the second point set, and the matching points of all target points form a third point set; Calculate the first centroid of the first point set and calculate the second centroid of the third point set; Construct a covariance equation based on the first centroid, the second centroid, the first point set, and the third point set; Candidate rotation matrices are calculated using the singular value decomposition (SVD) method and the covariance equation, and candidate translation matrices are obtained based on the first centroid, the second centroid, and the rotation matrices. Based on the candidate rotation matrix and the candidate translation matrix, the target points in the first point set are transformed to obtain a candidate point set, and the mean square error is calculated based on the candidate point set and the third point set. When the mean square error meets the set conditions, the candidate rotation matrix and the candidate translation matrix are determined as the transformation matrix; If the mean square error does not meet the set conditions, the first point set is re-acquired from the 3D vascular image and the second point set is re-acquired from the T1-weighted enhanced image.

5. The method according to claim 3, characterized in that, The first and second point sets were collected from the aneurysm region, the carotid artery region, and the M1 segment region of the middle cerebral artery.

6. The method according to claim 1, characterized in that, The aneurysm stability assessment result obtained based on the aneurysm stability assessment value includes: If an aneurysm stability assessment value is greater than the set assessment value, a first aneurysm stability assessment result is obtained, which is used to characterize aneurysm instability. If all aneurysm stability assessment values ​​are less than or equal to the set assessment value, a second aneurysm stability assessment result is obtained, which is used to characterize aneurysm stability.

7. An aneurysm stability assessment device, characterized in that, include: The image acquisition module is used to acquire 3D vascular images and T1-weighted enhanced images of the target patient. A mapping module is used to map the signal intensity values ​​of pixels on the T1-weighted enhanced image to the 3D vascular image; The stability assessment module is used to determine an aneurysm stability assessment value based on the signal intensity value of each pixel of the aneurysm in the 3D vascular image and a target signal intensity value, and to obtain an aneurysm stability assessment result based on the aneurysm stability assessment value, wherein the target signal intensity value is the maximum signal intensity value of the selected target region on the T1-weighted enhanced image; the selected target region is the pituitary region. The mapping module is specifically used to: acquire the first spatial data of the 3D vascular image and the second spatial data of the T1-weighted enhanced image; Based on the first spatial data and the second spatial data, the pixels on the 3D vascular image and the pixels on the T1 weighted enhanced image are registered to obtain a transformation matrix for spatial transformation between the 3D vascular image and the T1 weighted enhanced image, and the 3D vascular image is spatially transformed based on the transformation matrix. The transformed 3D vascular image is subjected to three-dimensional reconstruction processing to obtain a vascular model; For each pixel on the blood vessel model, the signal intensity value of the registration point that matches the pixel on the T1-weighted enhanced image is mapped onto the blood vessel model.

8. An electronic device, characterized in that, include: A processor, configured to execute program instructions; as well as A memory configured to store the program instructions, which, when loaded and executed by the processor, cause the processor to perform the method for assessing aneurysm stability according to any one of claims 1-6.

9. A computer-readable storage medium storing program instructions, characterized in that, When the program instructions are loaded and executed by the processor, the processor performs the method for assessing aneurysm stability according to any one of claims 1-6.

Images