Coronary artery lesion detection method, device and medium based on multi-dimensional dynamic imaging

Abstract

The present application relates to a method, device, and medium for detecting coronary artery lesions based on multidimensional dynamic imaging. The method comprises: obtaining dynamic motion information of the coronary arteries of multiple subjects based on multidimensional dynamic images of the coronary arteries; performing principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate; constructing a coronary artery lesion detection model based on each principal component contribution rate and the lesion label of the coronary artery of the corresponding subject; and inputting the principal component contribution rate corresponding to the dynamic motion information of the coronary artery of the subject to be tested into the coronary artery lesion detection model to obtain a result indicating whether the coronary artery is lesioned and the degree of the lesion. The method solves the problems of invasiveness, low precision, and low efficiency in the diagnosis of coronary artery lesions in related technologies, and realizes non-invasive, efficient, and accurate early diagnosis of coronary artery lesions.

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a method, device and medium for detecting coronary artery lesions based on multi-dimensional dynamic images. Background Art

[0002] Coronary artery disease refers to a series of pathological processes caused by abnormalities in the morphology, function or structure of the coronary arteries due to various reasons, which lead to myocardial ischemia, damage or necrosis.

[0003] Currently, the diagnosis of coronary artery disease is mainly based on the following methods:

[0004] (1) Use invasive and non-invasive static image morphological information to diagnose whether there are coronary artery lesions. Taking coronary angiography, which is considered the "gold standard", as an example, coronary angiography combined with intravascular ultrasound or optical coherence tomography is an invasive diagnosis that may cause kidney damage due to contrast agents and may cause vascular damage during the operation. Other proposed non-invasive diagnoses are challenged by insufficient image quality caused by excessively high image heart rate and / or immature image noise reduction technology, making it difficult to identify early coronary artery lesions from morphology.

[0005] (2) Diagnosis of coronary artery lesions through vascular biomechanical parameters. This is mainly because biomechanics is closely related to the progression of coronary artery disease. This method focuses on exploring the mechanical and hemodynamic parameters of the coronary artery, such as wall shear stress, wall stress, strain, and pressure, to enrich the detection index system for coronary artery stenosis. However, it is difficult and complex to obtain mechanical parameters and / or hemodynamic parameters in the in vivo environment. Generally, in vitro simulations are performed using modeling and finite element simulation, which is time-consuming and lacks a large amount of clinical data to establish the relationship between changes in mechanical parameters and coronary artery lesions.

[0006] Regarding the related technologies, the diagnosis of coronary artery lesions is invasive, inaccurate and inefficient, and no effective solution has been proposed yet. Summary of the Invention

[0007] Based on this, it is necessary to provide a method, device and medium for detecting coronary artery lesions based on multi-dimensional dynamic imaging to address the above technical problems.

[0008] In a first aspect, an embodiment of the present application provides a method for detecting coronary artery lesions based on multi-dimensional dynamic imaging, the method comprising:

[0009] Based on the multi-dimensional dynamic images of the coronary arteries of the multiple subjects, dynamic motion information of the coronary arteries of the subjects is obtained;

[0010] Performing principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate;

[0011] Constructing a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject;

[0012] The principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

[0013] In one embodiment, obtaining the dynamic motion information of the coronary arteries of the multiple subjects based on the multi-dimensional dynamic images of the coronary arteries of the multiple subjects includes:

[0014] Acquiring coronary artery images of the subject at multiple uniform phases, and selecting a reference phase image therefrom;

[0015] Annotating the reference phase image and selecting one or more target nodes;

[0016] registering the coronary artery images acquired at the remaining phases with the reference phase image, and obtaining the spatial coordinates of each target node in the coronary artery images acquired at each phase;

[0017] Based on the spatial coordinates of each target node in the coronary artery image acquired at each phase, the dynamic motion information of the coronary artery of the subject is obtained.

[0018] In one embodiment, the marking of the reference phase image and selecting one or more target nodes includes:

[0019] The reference phase image is annotated, and the intersection of the centerline of the coronary artery and the centerline of the small branch is used as the target node.

[0020] In one embodiment, the lesion label includes a coronary artery stenosis value and a stenosis degree, and constructing a coronary artery lesion detection model based on the principal component contribution rate and the label of the corresponding coronary artery of the subject includes:

[0021] Based on the contribution rate of each principal component and the coronary artery stenosis value of the corresponding subject, a first coronary artery lesion detection model is constructed to detect whether there is a lesion;

[0022] Based on the principal component contribution rate of the subject with lesions and the corresponding degree of coronary artery stenosis, a second coronary artery lesion detection model is constructed to detect the degree of lesions.

[0023] In one embodiment, the inputting of the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject into the coronary artery lesion detection model to obtain the result of whether there is a lesion and the degree of the lesion includes:

[0024] Inputting the principal component contribution rate corresponding to the dynamic motion information of the coronary artery of the subject into the first coronary artery lesion detection model to determine whether there is a lesion;

[0025] In the event of a lesion, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the second coronary artery lesion detection model to obtain the lesion extent.

[0026] In one embodiment, logistic regression is used to construct the first coronary artery lesion detection model:

[0027]

[0028] in, is the contribution rate of the first principal component of dynamic motion information, , is the fitting parameter; It is the coronary artery stenosis value, which is used to determine whether there is a lesion;

[0029] The second coronary artery lesion detection model was constructed using linear regression:

[0030]

[0031] in, is the degree of coronary artery stenosis, a and b are fitting parameters.

[0032] In one embodiment, the coronary artery dynamic motion information includes at least one of cumulative displacement, incremental displacement, velocity, and acceleration of the coronary artery during a cardiac cycle.

[0033] In one embodiment, the method further comprises:

[0034] The dynamic motion information of the coronary arteries of each of the subjects and the corresponding coronary artery lesion labels of the subjects are input into the model for training to obtain a coronary artery lesion detection model, which includes but is not limited to a machine learning model, a deep learning model, and a virtual vector machine.

[0035] In a second aspect, an embodiment of the present application further provides a coronary artery lesion detection device based on multi-dimensional dynamic imaging, the device comprising:

[0036] A dynamic information acquisition module, configured to obtain dynamic motion information of the coronary arteries of multiple subjects based on multi-dimensional dynamic images of the coronary arteries of the subjects;

[0037] A principal component analysis module is used to perform principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate;

[0038] A model building module, configured to build a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject;

[0039] The lesion detection module is used to input the principal component contribution rate corresponding to the dynamic motion information of the coronary artery of the subject to be tested into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

[0040] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0041] The above-mentioned coronary artery lesion detection method, device, and medium based on multidimensional dynamic imaging obtain dynamic coronary artery motion information for each subject based on multidimensional dynamic images of the coronary arteries of multiple subjects; perform principal component analysis on each piece of dynamic motion information to obtain the corresponding principal component contribution rate; construct a coronary artery lesion detection model based on each principal component contribution rate and the corresponding coronary artery lesion label of the subject; and input the principal component contribution rate corresponding to the coronary artery dynamic motion information of the subject into the coronary artery lesion detection model to obtain the presence of a lesion and the degree of the lesion. This method solves the problems of invasive, inaccurate, and inefficient coronary artery lesion diagnosis in related technologies, achieving non-invasive, efficient, and accurate early diagnosis of coronary artery lesions.

[0042] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 is a hardware structure block diagram of a terminal device of a method for detecting coronary artery lesions based on multi-dimensional dynamic images in an embodiment;

[0045] Figure 2 is a flow chart of a method for detecting coronary artery lesions based on multi-dimensional dynamic imaging in an embodiment;

[0046] Figure 3is a schematic diagram of a process for detecting coronary artery lesions based on multi-dimensional dynamic imaging in a specific embodiment;

[0047] Figure 4 The present invention is a structural block diagram of a coronary artery lesion detection device based on multi-dimensional dynamic imaging in an embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0049] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0050] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a block diagram of the hardware structure of the terminal of the coronary artery lesion detection method based on multi-dimensional dynamic imaging of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0051] Memory 104 can be used to store computer programs, such as software programs and modules for application software, such as the computer program corresponding to the method for detecting coronary artery lesions based on multi-dimensional dynamic imaging in this embodiment. Processor 102 executes the computer program stored in memory 104 to perform various functional applications and data processing, thereby implementing the aforementioned method. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located relative to processor 102, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0052] The transmission device 106 is used to receive or send data via a network. The network may include a wireless network provided by the terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0053] The present invention provides a method for detecting coronary artery lesions based on multi-dimensional dynamic images. Figure 1 The terminal in the example is as follows: Figure 2 As shown, the method includes the following steps:

[0054] Step 201 : obtaining dynamic motion information of the coronary arteries of the multiple subjects based on multi-dimensional dynamic images of the coronary arteries of the multiple subjects.

[0055] Specifically, a multidimensional dynamic image set of the coronary arteries of a large number of subjects is obtained through clinical data. The image set should have spatial dimension information of the coronary arteries and dynamic information of the changes in spatial information in the time dimension. These methods include but are not limited to ultrasound imaging, magnetic resonance imaging and multidimensional dynamic CTA imaging.

[0056] Preferably, this application utilizes multi-dimensional dynamic CTA imaging technology to obtain a set of multi-dimensional dynamic images of the coronary arteries. Multi-dimensional dynamic CTA imaging is an upgraded version of CTA technology. Through multi-phase CTA scanning, it can provide three-dimensional (3D) vascular spatial coordinates and the temporal changes of this information within the cardiac cycle. In practice, patients (subjects) undergo electrocardiogram-guided multi-dimensional dynamic CTA imaging scans, which reconstruct multiple evenly spaced phases to obtain dynamic motion information of the coronary arteries during the heartbeat.

[0057] In this step, the dynamic motion information of the coronary artery during the heartbeat is quantified. The dynamic motion information in this application includes obtaining quantified results such as the cumulative displacement, incremental displacement, velocity, acceleration, etc. of the coronary artery during the heartbeat cycle.

[0058] Step 202 : performing principal component analysis on each piece of dynamic motion information to obtain a corresponding principal component contribution rate.

[0059] Principal component analysis (PCA) is a method for reducing data dimensionality while retaining as much of the original information as possible. It projects the original data onto a new coordinate system through linear transformation, concentrating the variance of the data on as few dimensions as possible.

[0060] This application uses principal component analysis to perform dimensionality reduction processing on the quantified coronary artery dynamic motion information and extract characteristic indicators, such as principal component results, principal component contribution rate and other indicators as diagnostic indicators for coronary artery lesions.

[0061] For an input OK Taking the incremental displacement data set of the column as an example, M is each phase, N is the incremental displacement of each target node in each dimension, and the calculation process of the first principal component contribution rate is:

[0062] Centralized matrix calculation: ; is the incremental displacement vector corresponding to the i-th phase; is the mean vector of the incremental displacement of all phases of each target node in each dimension;

[0063] Formula for covariance matrix calculation: ;

[0064] The covariance matrix is ​​passed through Perform singular value decomposition to obtain the eigenvalue matrix and the eigenvector matrix ;

[0065] Extract eigenvalue matrix The eigenvalues ​​in ,in is the maximum eigenvalue, through Calculate the contribution rate of the first principal direction. The contribution rates of other principal components can be obtained by the above method.

[0066] The principal component contribution rates of the dynamic motion information of the remaining coronary arteries (such as cumulative displacement, velocity, acceleration, etc.) are calculated using the same method.

[0067] Step 203: construct a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject.

[0068] Step 204: input the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject into the coronary artery lesion detection model to obtain the result of whether there is lesion and the degree of lesion.

[0069] Specifically, a multi-dimensional dynamic image of the coronary arteries of the subject is obtained, the dynamic motion information of the coronary arteries of the subject is calculated, and principal component analysis is performed on the dynamic motion information of the coronary arteries of the subject to obtain the principal component contribution rate of the dynamic motion information of the coronary arteries of the subject to be measured. The principal component contribution rate is input into the established coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

[0070] The above-mentioned coronary artery lesion detection method, device and medium based on multi-dimensional dynamic imaging extracts coronary artery dynamic motion information through multi-dimensional dynamic imaging and quantifies the coronary artery dynamic motion information. Through principal component analysis and statistical models, the quantified coronary artery dynamic motion is reduced in dimension, analyzed, and features are extracted, and correlation with coronary artery lesions is established, thereby achieving non-invasive, efficient and accurate early diagnosis of coronary artery lesions and the degree of lesions, solving the problems of invasiveness, low accuracy and low efficiency in the diagnosis of coronary artery lesions in related technologies. Specifically, (1) Unlike traditional invasive diagnostic methods, this application uses a non-invasive method to extract cardiac dynamic motion information to diagnose coronary artery lesions. This information contains dynamic motion abnormalities caused by coronary artery lesions. (2) Unlike traditional methods that use various methods such as finite element simulation to simulate in vivo vascular parameters, this method uses principal component analysis to extract new diagnostic indicators from coronary artery dynamic motion information, which can efficiently realize the diagnosis of coronary artery lesions. (3) By establishing the correlation between the principal component analysis results and the clinical diagnosis of coronary artery lesions and the degree of lesions, it assists in the early diagnosis of coronary artery lesions.

[0071] In one embodiment, the step of obtaining the dynamic motion information of the coronary arteries of the multiple subjects based on the multi-dimensional dynamic images of the coronary arteries of the multiple subjects comprises the following steps:

[0072] Step 301 : Acquire coronary artery images of the subject at multiple uniform phases, and select a reference phase image from them.

[0073] Exemplarily, the phase with the best image quality and the clearest coronary arteries is selected as the reference phase image.

[0074] Step 302: annotate the reference phase image and select multiple target nodes.

[0075] It can be understood that the selected target nodes are key landmarks used to indicate the dynamic motion process of the coronary arteries.

[0076] In one embodiment, the intersection of the centerline of the coronary artery and the centerline of the small branch is used as the target node.

[0077] Step 303 : Register the coronary artery images acquired in the remaining phases with the reference phase image, and obtain the spatial coordinates of each target node in the coronary artery image acquired in each phase.

[0078] Among them, registration refers to aligning coronary artery images acquired at different phases so that they can be compared and analyzed in the same reference coordinate system.

[0079] Step 304 : obtaining the dynamic motion information of the coronary arteries of the subject based on the spatial coordinates of each target node in the coronary artery images acquired at each phase.

[0080] In one embodiment, the lesion label includes a coronary artery stenosis value and a stenosis degree. The steps of constructing a coronary artery lesion detection model based on the principal component contribution rate and the label of the corresponding coronary artery of the subject include the following:

[0081] Based on the principal component contribution rates and the coronary artery stenosis values ​​of the corresponding subjects, a first coronary artery lesion detection model is constructed to detect whether a lesion has occurred; based on the principal component contribution rates and the corresponding coronary artery stenosis levels of the subjects with lesions, a second coronary artery lesion detection model is constructed to detect the level of the lesion.

[0082] In one embodiment, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion, including the following:

[0083] The principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the first coronary artery lesion detection model to determine whether there is a lesion; if a lesion occurs, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the second coronary artery lesion detection model to obtain the degree of the lesion.

[0084] In one embodiment, logistic regression is used to construct the first coronary artery lesion detection model:

[0085]

[0086] in, is the contribution rate of the first principal component of dynamic motion information, , is the fitting parameter; The coronary artery stenosis value is used to determine whether a lesion exists; the first principal component contribution rate of the dynamic motion information is brought into the logistic regression model to predict the probability of coronary artery stenosis. The coronary artery stenosis value is compared with the empirical threshold. If it is greater than or equal to the empirical threshold, it is determined that a lesion exists; otherwise, no lesion exists. The empirical threshold is based on the subject's The optimal threshold is obtained by performing ROC curve analysis on the clinically obtained binary label of whether the subject has a lesion.

[0087] It should be noted that the above formula only uses the first principal component contribution rate corresponding to the dynamic motion information This is described as an example, and this application does not impose any specific limitations. In practical applications, a logistic regression fitting can also be performed based on the contribution rates of the first K principal components and the coronary artery stenosis value to obtain a first coronary artery lesion detection model.

[0088] The second coronary artery lesion detection model was constructed using linear regression:

[0089]

[0090] in, is the degree of coronary artery stenosis, a and b are fitting parameters.

[0091] It should be noted that the above formula only uses the first principal component contribution rate corresponding to the dynamic motion information This is described as an example, and this application does not impose any specific limitations. In practical applications, a linear regression fit can also be performed based on the contribution rates of the first K principal components and the degree of coronary artery stenosis to obtain a second coronary artery lesion detection model.

[0092] In one embodiment, the coronary artery dynamic motion information in step 201 includes, but is not limited to, at least one of cumulative displacement, incremental displacement, velocity, and acceleration of the coronary artery during a cardiac cycle. Principal component analysis is performed on each piece of dynamic motion information to obtain a corresponding principal component contribution rate.

[0093] The diagnosis of coronary artery lesions in this application can conduct targeted analysis of different coronary artery branches such as the left circumflex artery, left main trunk, right coronary artery, and left anterior descending artery. Among them, the left anterior descending artery is one of the main branches of the coronary artery, responsible for supplying blood to important areas such as the left anterior wall of the heart and the anterior part of the left ventricle.

[0094] The following example illustrates the acquisition of incremental displacement dynamic data of the left anterior descending artery of a subject:

[0095] Coronary artery images of the subject during heartbeat are acquired at multiple uniform phases, and the phase with the best image quality and the clearest coronary artery is selected as the reference phase image; the reference phase image is annotated using medical image processing software, and the intersection of the centerline of the left anterior descending branch and the centerline of the small branch is used as the target node, and there are multiple target nodes (other positions that are convenient for unified operation can also be selected as target nodes); the coronary artery images acquired at the remaining phases are respectively registered with the reference phase image using a registration algorithm to obtain the spatial coordinates of each target node in the coronary artery images acquired at each phase; the coordinate data of all phases are sorted by time, and based on the spatial coordinates of each target node in the coronary artery images acquired at each phase, the incremental displacement between adjacent phase images is calculated to obtain incremental displacement dynamic data.

[0096] Other dynamic motion information of the coronary artery can also be calculated using the spatial coordinates of each target node in the coronary artery images of each phase obtained above, such as dynamic motion information such as the cumulative displacement, velocity, and acceleration of the coronary artery during the cardiac cycle.

[0097] In a specific embodiment, Figure 3 As shown, the diagnosis of coronary artery lesions and the extent of lesions in the subject includes the following steps:

[0098] Step 401: acquiring a multi-dimensional dynamic image of the coronary arteries of the subject.

[0099] Taking the multi-dimensional dynamic CTA image of the coronary artery as an example, the CTA imaging scan reconstructs 34 phases, each of which has a uniform 3% RR interval.

[0100] Step 402: quantify the dynamic motion information of the coronary arteries of the subject.

[0101] Taking the acquisition of incremental displacement data of the left anterior descending artery as an example: the reference phase is selected for manual annotation to construct a reference left anterior descending artery model, and the remaining phase image sets are registered with the reference model using the registration algorithm. The intersection of the centerline of the left anterior descending artery and the centerline of the small branch is used as the target node, the spatial coordinate data is obtained, and the incremental displacement between adjacent phases is calculated.

[0102] Step 403: Perform principal component analysis on the coronary artery dynamic motion information.

[0103] Step 404: determine whether there is a pathological condition based on the principal component analysis results.

[0104] Taking the first principal direction contribution rate as an example, the relationship between the contribution rate and the coronary artery lesions is established by using statistical methods such as logistic regression models to determine whether the coronary artery is lesioned.

[0105] Step 405: If the coronary artery is diseased, the degree of the disease is quantified.

[0106] The relationship between the disease severity and the degree of coronary artery disease is established by using statistical methods such as linear regression models to determine the degree of disease severity.

[0107] In one embodiment, the method further includes: obtaining dynamic motion information of the coronary arteries of multiple subjects based on multi-dimensional dynamic images of the coronary arteries of the subjects; inputting the dynamic motion information of the coronary arteries of the subjects and the lesion labels of the corresponding coronary arteries into a machine learning model, a deep learning model, a virtual vector machine, or other models for training to obtain a coronary artery lesion detection model, extracting features of the dynamic motion information of the coronary arteries through the model, and establishing correlation with coronary artery lesions, thereby achieving non-invasive, efficient, and accurate early diagnosis of coronary artery lesions and the degree of lesions.

[0108] In one embodiment, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of each subject and the lesion label of the coronary artery of the corresponding subject can also be input into the model for training to obtain a coronary artery lesion detection model, which includes but is not limited to a machine learning model, a deep learning model, and a virtual vector machine.

[0109] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0110] In one embodiment, Figure 4 As shown, the embodiment of the present application further provides a coronary artery lesion detection device based on multi-dimensional dynamic imaging, the device comprising:

[0111] A dynamic information acquisition module 10 is configured to obtain dynamic motion information of the coronary arteries of multiple subjects based on multi-dimensional dynamic images of the coronary arteries of the subjects;

[0112] A principal component analysis module 20 is used to perform principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate;

[0113] A model building module 30 is used to build a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject;

[0114] The lesion detection module 40 is used to input the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

[0115] In one embodiment, the dynamic information acquisition module 10 is further configured to: acquire coronary artery images of the subject at multiple uniform phases and select a reference phase image therefrom; annotate the reference phase image and select multiple target nodes; register the coronary artery images acquired at the remaining phases with the reference phase image, and acquire the spatial coordinates of each target node in the coronary artery images acquired at each phase; and obtain dynamic coronary artery motion information of the subject based on the spatial coordinates of each target node in the coronary artery images acquired at each phase.

[0116] In one embodiment, the dynamic information acquisition module 10 is further configured to: mark the reference phase image, and use the intersection of the centerline of the coronary artery and the centerline of the small branch as the target node.

[0117] In one embodiment, the model building module 30 is further used to: construct a first coronary artery lesion detection model based on the principal component contribution rate and the coronary artery stenosis value of the corresponding subject, for detecting whether there is a lesion; and construct a second coronary artery lesion detection model based on the principal component contribution rate and the corresponding coronary artery stenosis degree of the subject with the lesion, for detecting the degree of the lesion.

[0118] In one embodiment, the lesion detection module 40 is further configured to input the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject into the first coronary artery lesion detection model to determine whether a lesion exists; if a lesion exists, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the second coronary artery lesion detection model to obtain the degree of the lesion.

[0119] In one embodiment, logistic regression is used to construct the first coronary artery lesion detection model:

[0120]

[0121] in, is the contribution rate of the first principal component of dynamic motion information, , is the fitting parameter; It is the coronary artery stenosis value, which is used to determine whether there is a lesion;

[0122] The second coronary artery lesion detection model was constructed using linear regression:

[0123]

[0124] in, is the degree of coronary artery stenosis, a and b are fitting parameters.

[0125] In one embodiment, the coronary artery dynamic motion information includes at least one of cumulative displacement, incremental displacement, velocity, and acceleration of the coronary artery during a cardiac cycle.

[0126] In one embodiment, the model building module 30 is further used to: input the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject into the model for training to obtain a coronary artery lesion detection model, wherein the model includes but is not limited to a machine learning model, a deep learning model, and a virtual vector machine.

[0127] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned embodiments of the method for detecting coronary artery lesions based on multi-dimensional dynamic imaging are implemented.

[0129] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0130] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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.

[0131] The above-described embodiments merely represent 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 present invention. It should be noted that a person skilled in the art could 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 method for detecting coronary artery lesions based on multi-dimensional dynamic imaging, characterized in that: The method comprises: Based on multi-dimensional dynamic images of the coronary arteries of multiple subjects, dynamic motion information of the coronary arteries of each subject is obtained; the method includes: acquiring coronary artery images of the subject at multiple uniform phases, and selecting a reference phase image therefrom; annotating the reference phase image, and selecting one or more target nodes; registering the coronary artery images acquired at other phases with the reference phase image, and obtaining the spatial coordinates of each target node in the coronary artery images acquired at each phase; and obtaining the dynamic motion information of the coronary arteries of the subject based on the spatial coordinates of each target node in the coronary artery images acquired at each phase. Performing principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate; Constructing a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject; The principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

2. The method according to claim 1, characterized in that The marking of the reference phase image and selecting one or more target nodes includes: The reference phase image is annotated, and the intersection of the centerline of the coronary artery and the centerline of the small branch is used as the target node.

3. The method according to claim 1, characterized in that The lesion label includes a binary label indicating whether there is stenosis and the degree of stenosis. The coronary artery lesion detection model is constructed based on the principal component contribution rate and the label of the corresponding coronary artery of the subject, including: Based on the contribution rate of each principal component and the coronary artery stenosis value of the corresponding subject, a first coronary artery lesion detection model is constructed to detect whether a lesion occurs; Based on the principal component contribution rate of the subjects with lesions and the corresponding degree of coronary artery stenosis, a second coronary artery lesion detection model is constructed to detect the degree of lesions.

4. The method according to claim 3, characterized in that The inputting of the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject into the coronary artery lesion detection model to obtain the result of whether there is lesion and the degree of lesion includes: Inputting the principal component contribution rate corresponding to the dynamic motion information of the coronary artery of the subject into the first coronary artery lesion detection model to determine whether there is a lesion; In the event of a lesion, the principal component contribution rate corresponding to the dynamic motion information of the coronary arteries of the subject is input into the second coronary artery lesion detection model to obtain the lesion extent.

5. The method according to claim 3, characterized in that Logistic regression was used to construct the first coronary artery lesion detection model: ； in, is the contribution rate of the first principal component of dynamic motion information, ， is the fitting parameter; It is the coronary artery stenosis value, which is used to determine whether there is a lesion; The second coronary artery lesion detection model was constructed using linear regression: ； in, is the degree of coronary artery stenosis, a, b is the fitting parameter.

6. The method according to claim 1, characterized in that The coronary artery dynamic motion information includes but is not limited to at least one of the cumulative displacement, incremental displacement, velocity, and acceleration of the coronary artery during a cardiac cycle.

7. The method according to claim 1, characterized in that The method further comprises: The dynamic motion information of the coronary arteries of each of the subjects and the corresponding coronary artery lesion labels of the subjects are input into the model for training to obtain a coronary artery lesion detection model, which includes but is not limited to a machine learning model, a deep learning model, and a virtual vector machine.

8. A coronary artery lesion detection device based on multi-dimensional dynamic imaging, characterized in that: The device comprises: A dynamic information acquisition module is configured to obtain dynamic coronary artery motion information of each subject based on multi-dimensional dynamic images of the coronary arteries of the subjects. The module comprises: acquiring coronary artery images of the subject at multiple uniform phases and selecting a reference phase image from the image; annotating the reference phase image and selecting one or more target nodes; registering coronary artery images acquired at other phases with the reference phase image and acquiring the spatial coordinates of each target node in the coronary artery images acquired at each phase; and acquiring the dynamic coronary artery motion information of the subject based on the spatial coordinates of each target node in the coronary artery images acquired at each phase. A principal component analysis module is used to perform principal component analysis on each of the dynamic motion information to obtain a corresponding principal component contribution rate; A model building module, configured to build a coronary artery lesion detection model based on the contribution rate of each principal component and the corresponding coronary artery lesion label of the subject; The lesion detection module is used to input the principal component contribution rate corresponding to the dynamic motion information of the coronary artery of the subject to be tested into the coronary artery lesion detection model to obtain the results of whether there is a lesion and the degree of the lesion.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images