Method and apparatus for determining blood flow field information, method and apparatus for obtaining model, and computing device

Abstract

Provided are a method and apparatus for determining blood flow field information, a method and apparatus for obtaining a blood flow field information determination model, a computing device, and a storage medium. The method for determining blood flow field information may comprise: obtaining an image for a target blood vessel segment (210); on the basis of the image, obtaining dimensionally reduced image data (220); on the basis of the dimensionally reduced image data, obtaining at least one feature vector by means of a pre-trained neural network (230); and, on the basis of the at least one feature vector, obtaining at least one piece of blood flow field information for the target blood vessel segment (240).

Description

Blood flow field information determination method, model acquisition method, device, and computing device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311799617X filed on December 25, 2023, the entire contents of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present disclosure relates to the field of data processing, and in particular to a method for determining blood flow field information, a method for obtaining a blood flow field information determination model, an apparatus, a computing device, and a storage medium. Background Art

[0004] In the medical field, various blood flow field information can reflect a lot of effective information. A method for analyzing or determining blood flow field information is desired.

[0005] The approaches described in this section are not necessarily approaches that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any approach described in this section is prior art simply by virtue of its inclusion in this section. Similarly, unless otherwise indicated, the issues raised in this section should not be considered as having been recognized in any prior art. Summary of the Invention

[0006] According to one aspect of the present disclosure, a method for determining blood flow field information is provided, comprising: obtaining an image of a target blood vessel segment; obtaining reduced-dimensionality image data based on the image; obtaining at least one feature vector based on the reduced-dimensionality image data through a pre-trained neural network; and obtaining at least one piece of blood flow field information for the target blood vessel segment based on the at least one feature vector.

[0007] According to another aspect of the present disclosure, a method for obtaining a blood flow field information determination model is provided, comprising: obtaining an image of a target blood vessel segment; obtaining reduced-dimensional image data based on the image; obtaining at least one eigenvector through a neural network based on the reduced-dimensional image data; obtaining predicted blood flow field information based on the at least one eigenvector; adjusting parameters of the neural network based on the predicted blood flow field information and reference blood flow field information; and obtaining the adjusted neural network as the blood flow field information determination model after an adjustment end condition is met.

[0008] According to yet another aspect of the present disclosure, a blood flow field information determination device is provided, comprising: an image acquisition unit for acquiring an image for a target blood vessel segment; a dimensionality reduction unit for acquiring reduced-dimensionality image data based on the image; a feature vector acquisition unit for acquiring at least one feature vector based on the reduced-dimensionality image data through a pre-trained neural network; and a blood flow field information acquisition unit for acquiring at least one piece of blood flow field information for the target blood vessel segment based on the at least one feature vector.

[0009] According to yet another aspect of the present disclosure, there is provided an apparatus for obtaining a blood flow field information determination model, comprising an image acquisition unit for obtaining an image of a target blood vessel segment; a dimension reduction unit for obtaining reduced-dimensionality image data based on the image; a feature vector acquisition unit for obtaining at least one feature vector through a neural network based on the reduced-dimensionality image data; a prediction unit for obtaining predicted blood flow field information based on the at least one feature vector; an adjustment unit for adjusting parameters of the neural network based on the predicted blood flow field information and reference blood flow field information; and a model acquisition unit for obtaining the adjusted neural network as the blood flow field information determination model after an adjustment end condition is met.

[0010] According to another aspect of the present disclosure, a computing device is provided, comprising: a memory, a processor, and a computer program stored on the memory, wherein the processor is configured to execute the computer program to implement a method for determining blood flow field information or a method for obtaining a blood flow field information determination model according to one or more embodiments of the present disclosure.

[0011] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements a method for determining blood flow field information or a method for obtaining a blood flow field information determination model according to one or more embodiments of the present disclosure.

[0012] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements a method for determining blood flow field information or a method for obtaining a blood flow field information determination model according to one or more embodiments of the present disclosure.

[0013] According to one or more embodiments of the present disclosure, a feature vector that can be used to calculate flow field information can be generated through a neural network based on the reduced-dimensional data, thereby achieving the determination of blood flow field information.

[0014] According to one or more embodiments of the present disclosure, calculations of parts that have no effect on flow field information results can be discarded, thereby achieving higher computational efficiency.

[0015] These and other aspects of the disclosure will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0017] FIG1 is a schematic diagram illustrating an example system in which various methods described herein may be implemented, according to an exemplary embodiment;

[0018] FIG2 is a flow chart illustrating a method for determining blood flow field information according to an exemplary embodiment;

[0019] 3 is a flow chart illustrating a method for obtaining blood flow field information determination model according to an exemplary embodiment;

[0020] FIG4 is a schematic diagram illustrating a data flow according to an exemplary embodiment;

[0021] FIG5 is a schematic diagram illustrating a blood vessel segment to which a method according to an exemplary embodiment may be applied;

[0022] FIG6 is a schematic block diagram illustrating a blood flow field information determining apparatus according to an exemplary embodiment;

[0023] FIG7 is a schematic block diagram illustrating an apparatus for obtaining blood flow field information and determining a model according to an exemplary embodiment;

[0024] FIG. 8 is a block diagram illustrating an exemplary computer device that can be used with the exemplary embodiments. DETAILED DESCRIPTION

[0025] In this disclosure, unless otherwise specified, the use of terms such as "first" and "second" to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases, based on the context of the description, they may also refer to different instances.

[0026] The terms used in the description of the various examples described in this disclosure are for the purpose of describing specific examples only and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. As used herein, the term "plurality" means two or more, and the term "based on" should be interpreted as "based at least in part on". In addition, the terms "and / or" and "at least one of..." cover any one of the listed items and all possible combinations.

[0027] Exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0028] FIG. 1 is a schematic diagram illustrating an example system 100 in which the various methods described herein may be implemented, according to an example embodiment.

[0029] 1 , the system 100 includes a client device 110 , a server 120 , and a network 130 communicatively coupling the client device 110 and the server 120 .

[0030] The client device 110 includes a display 114 and a client application (APP) 112 that can be displayed via the display 114. The client application 112 can be an application that needs to be downloaded and installed before running or a small program (liteapp) that is a lightweight application. In the case where the client application 112 is an application that needs to be downloaded and installed before running, the client application 112 can be pre-installed on the client device 110 and activated. In the case where the client application 112 is a small program, the user 102 can directly run the client application 112 on the client device 110 by searching for the client application 112 in the host application (for example, by the name of the client application 112, etc.) or scanning a graphic code (for example, a barcode, a QR code, etc.) of the client application 112, without installing the client application 112. In some embodiments, the client device 110 can be any type of mobile computer device, including a mobile computer, a mobile phone, a wearable computer device (for example, a smart watch, a head-mounted device, including smart glasses, etc.) or other types of mobile devices. In some embodiments, the client device 110 may alternatively be a stationary computer device, such as a desktop computer, a server computer, or other types of stationary computer devices. In some optional embodiments, the client device 110 may also be or include a medical image printing device.

[0031] The server 120 is typically a server deployed by an Internet Service Provider (ISP) or an Internet Content Provider (ICP). The server 120 may represent a single server, a cluster of multiple servers, a distributed system, or a cloud server that provides basic cloud services (such as cloud databases, cloud computing, cloud storage, and cloud communications). It will be understood that although FIG1 shows that the server 120 is communicating with only one client device 110, the server 120 can provide backend services to multiple client devices simultaneously.

[0032] Examples of network 130 include a local area network (LAN), a wide area network (WAN), a personal area network (PAN), and / or a combination of communication networks such as the Internet. Network 130 can be a wired or wireless network. In some embodiments, data exchanged through network 130 is processed using technologies and / or formats including Hypertext Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, encryption technologies such as Secure Sockets Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In some embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0033] The system 100 may further include an image acquisition device 140. In some embodiments, the image acquisition device 140 shown in FIG1 may be a medical scanning device, including but not limited to scanning or imaging devices used in positron emission tomography (PET), positron emission tomography with computerized tomography (PET / CT), single photon emission computed tomography with computerized tomography (SPECT / CT), computerized tomography (CT), medical ultrasonography, nuclear magnetic resonance imaging (NMRI), magnetic resonance imaging (MRI), cardiovascular angiography (CA), digital radiography (DR), and the like. For example, the image acquisition device 140 may include a digital subtraction angiography scanner, a magnetic resonance angiography scanner, a tomographic angiography scanner, a positron emission tomography scanner, a positron emission computed tomography scanner, a single photon emission computed tomography scanner, a computed tomography scanner, a medical ultrasound examination device, a nuclear magnetic resonance imaging scanner, an MRI scanner, a digital radiography scanner, etc. The image acquisition device 140 may be connected to a server (e.g., the server 120 in FIG. 1 or a separate server of the imaging system (not shown)) to implement image data processing, including but not limited to converting the scanned data (e.g., converting it into a medical image sequence), compressing it, performing pixel correction, and performing three-dimensional reconstruction.

[0034] The image acquisition device 140 may be connected to the client device 110 via the network 130 , for example, or directly connected to the client device in other ways to communicate with the client device.

[0035] Optionally, the system may further include an intelligent computing device or computing card 150. The image acquisition device 140 may include or be connected (e.g., removably connected) to such a computing card 150, etc. As an example, the computing card 150 may implement image data processing, including but not limited to conversion, compression, pixel correction, reconstruction, etc. As another example, the computing card 150 may implement a method for determining blood flow field information or a method for obtaining a blood flow field information determination model according to an embodiment of the present disclosure.

[0036] The system may also include other parts not shown, such as a data storage unit. The data storage unit may be a database, a data repository, or one or more other devices for data storage. It may be a conventional database, or it may include a cloud database, a distributed database, etc. For example, direct image data generated by the image acquisition device 140 or a medical image sequence or three-dimensional image data obtained through image processing may be stored in the data storage unit for subsequent retrieval from the data storage unit by the server 120 and the client device 110. In addition, the image acquisition device 140 may also directly provide the image data or the medical image sequence or three-dimensional image data obtained through image processing to the server 120 or the client device 110.

[0037] The user can use the client device 110 to control the acquisition of images or videos, view the acquired images or videos (including preliminary image data or images that have been analyzed and processed), view analysis results, interact with the acquired images or analysis results, input acquisition instructions, configure data, etc. The client device 110 can send configuration data, instructions, or other information to the image acquisition device 140 to control the acquisition of the image acquisition device, process data, etc.

[0038] For the purposes of the embodiments of the present disclosure, in the example of FIG. 1 , the client application 112 may be an image sequence management application that can provide various functions, such as storage management, indexing, sorting, and classification of acquired image sequences. Accordingly, the server 120 may be a server used in conjunction with the image sequence management application. The server 120 may provide image sequence management services to the client application 112 running on the client device 110 based on user requests or instructions generated according to embodiments of the present disclosure. These services include managing cloud-based image sequence storage, storing and categorizing image sequences according to specified indices (including, but not limited to, sequence type, patient identifier, body part, acquisition target, acquisition phase, acquisition machine, lesion detection, severity, etc.), and retrieving and providing image sequences to the client device based on specified indices. Alternatively, the server 120 may provide or allocate such service capabilities or storage space to the client device 110, with the client application 112 running on the client device 110 providing corresponding image sequence management services based on user requests or instructions generated according to embodiments of the present disclosure. It can be understood that the above is only one example, and the present disclosure is not limited thereto.

[0039] FIG2 is a flowchart illustrating a method 200 for determining blood flow field information according to an exemplary embodiment. Method 200 may be executed at a client device (e.g., client device 110 shown in FIG1 ), that is, the execution entity of each step of method 200 may be client device 110 shown in FIG1 . In some embodiments, method 200 may be executed at a server (e.g., server 120 shown in FIG1 ). In some embodiments, method 200 may be executed by a combination of a client device (e.g., client device 110) and a server (e.g., server 120).

[0040] Hereinafter, each step of the method 200 is described in detail by taking the client device 110 as an example.

[0041] 2 , at step 210 , an image of a target blood vessel segment is obtained.

[0042] At step 220 , dimensionally reduced image data is obtained based on the image.

[0043] At step 230 , at least one feature vector is obtained based on the dimensionally reduced image data through a pre-trained neural network.

[0044] At step 240 , at least one piece of blood flow field information for the target blood vessel segment is obtained based on the at least one feature vector.

[0045] Through the above method, blood flow field information can be obtained based on the image data after dimensionality reduction.

[0046] The images collected for a blood vessel segment may bring about a large amount of computation. On the one hand, because the blood vessels themselves are dynamic, the blood in them is constantly flowing, the shape of the blood vessels is not fixed, and there will be a certain degree of filling phenomenon as the heart beats. On the other hand, the blood vessels in certain locations may have complex topological structures, and the collected images may be blocked (for example, by other blood vessels or other tissues or organs), etc. In particular, in some cases, it is necessary to collect image sequences for the blood vessel segment over time, such as when a contrast agent is applied. Such image sequences or video streams will contain a large amount of data. Even if artificial intelligence and neural networks are introduced, analyzing the raw data will still consume a lot of resources and bring an unexpectedly long analysis time.

[0047] According to an embodiment of the present disclosure, the image can be firstly reduced in dimension, and then a feature vector that can be used to calculate flow field information is generated through a neural network based on the reduced-dimensional data, thereby realizing the determination of the blood flow field information.

[0048] During the diagnosis of certain diseases, it is necessary to analyze the health of blood vessels and blood flow, and in such analysis, blood flow field information can provide a wealth of useful information. It is understood that the term "blood flow field information" can encompass various flow field information related to blood vessel segments that can be understood or conceived by those skilled in the art, including but not limited to blood flow velocity, blood pressure, blood density, and other statistical quantities, including local values, sampled values, extreme values, and average values, and the present disclosure is not limited thereto.

[0049] It is understandable that the image of the target blood vessel segment may be an original image collected for the target blood vessel segment to be analyzed, image data obtained after image processing (eg, repair, enhancement, rotation), etc., and the present disclosure is not limited thereto.

[0050] It is understood that various dimensionality reduction methods can be used. As an example, when reducing the dimensionality of data, a strategy can be adopted to ensure that the dimensionality reduction features play a major role in the flow field. Exemplarily, a variational autoencoder (VAE) can be used for dimensionality reduction, but the present disclosure is not limited thereto.

[0051] According to some embodiments, the at least one feature vector may be a vector representation obtained by orthogonal decomposition. In such a case, the vector representation of the reduced-dimensional image data may be obtained by performing orthogonal decomposition on the reduced-dimensional image data.

[0052] Exemplarily, the at least one eigenvector may be a vector representation obtained through eigenorthogonal decomposition.

[0053] Proper orthogonal decomposition (POD), also known as principal component analysis (PCA), can be solved using a method consistent with those skilled in the art, and its specific principles are not repeated in this disclosure. According to some other exemplary embodiments, the at least one eigenvector can be obtained by at least one of the following: dynamic mode decomposition, extended eigenorthogonal decomposition, principal component analysis, singular value decomposition, and conjugate analysis.

[0054] According to some embodiments, obtaining at least one feature vector may include projecting the dimensionally reduced image data to a predetermined dimension associated with the pre-trained neural network.

[0055] For example, the predetermined dimension can be referred to as a mode, such as a POD mode in the case of principal component analysis. The predetermined dimension can be trained with the neural network. For example, the POD mode can correspond to a dominant spatial flow pattern or structure.

[0056] As a specific non-limiting example, when diagnosing coronary heart disease, it is often necessary to look at the health of the coronary arteries. Exemplarily, it can be judged functionally based on the fractional flow reserve (FFR). FFR refers to the ratio of the maximum blood flow that can be obtained in the myocardial area supplied by the blood vessel when there is a stenotic lesion in the coronary artery to the maximum blood flow that can be obtained in the same area under normal conditions in theory, that is, the ratio of the mean pressure in the stenotic distal coronary artery (Pd) to the mean pressure in the aorta at the coronary artery ostium (Pa) under the state of maximum myocardial congestion. For such usage scenarios, the embodiments of the present disclosure provide a method that can measure FFR non-invasively, and by reducing the dimensionality of the data, the amount of calculation can be greatly reduced. Exemplarily, the method may also include determining the fractional flow reserve FFR information for the target blood vessel segment based on the blood flow field information.

[0057] Exemplarily, the image of the target blood vessel segment may be an image acquired by a digital subtraction angiography (DSA) method, and the present disclosure is not limited thereto.

[0058] The following describes in detail the various steps of a method 300 for obtaining blood flow field information and determining a model according to an exemplary embodiment of the present disclosure with reference to FIG. 3 .

[0059] At step 310 , an image of a target blood vessel segment is acquired.

[0060] At step 320 , dimensionally reduced image data is obtained based on the image.

[0061] At step 330 , at least one feature vector is obtained through a neural network based on the dimensionally reduced image data.

[0062] At step 340 , predicted blood flow field information is obtained based on the at least one feature vector.

[0063] At step 350 , the parameters of the neural network are adjusted based on the predicted blood flow field information and the reference blood flow field information.

[0064] At step 360, after the adjustment end condition is met, the adjusted neural network is obtained as the blood flow field information determination model.

[0065] According to one or more embodiments of the present disclosure, a training method is provided to obtain a blood flow field information determination model, whereby such a model can obtain blood flow field information based on dimensionality-reduced data.

[0066] For example, the reference blood flow field information can be obtained based on the image data before dimensionality reduction. Since the blood flow field information is obtained based on the data before dimensionality reduction during the offline training phase, it does not affect the efficiency of real-time processing and calculation in the application. In such an example, according to the training method disclosed in the present invention, on the one hand, the data is reduced in dimensionality, reducing the amount of calculation required to train the neural network model. On the other hand, by adjusting the neural network by comparing it with the reference data generated by the non-dimensionality reduction data, the error caused by the dimensionality reduction can be directly compensated, and the accuracy comparable to the calculation of the non-dimensionality reduction data can still be obtained.

[0067] As a specific, non-limiting example, the predicted blood flow field information and the reference blood flow field information can be used to characterize the FFR result of the target vessel segment, for example, respectively representing the predicted FFR result and the reference FFR result. The reference FFR result can be obtained based on non-dimensionality-reduced data, for example, obtained through methods such as fluid dynamics, or can be a measurement value obtained by other means, and can be used as a ground truth value for training a neural network. It should be understood that the present disclosure is not limited to this.

[0068] In particular, according to one or more embodiments of the present disclosure, calculations that do not contribute to the flow field information results can be discarded, thereby achieving higher computational efficiency. This can be achieved through the following technical features: According to one or more embodiments of the present disclosure, comparison is performed directly based on non-dimensionality-reduced reference data, thereby ensuring that the information obtained based on the dimensionality-reduced features is accurate for generating the final flow field information (e.g., FFR results), while parts that do not affect the results can be simplified, thereby ensuring both accuracy and computational efficiency on both the training side and the application side.

[0069] It is understood that the adjustment termination condition may be any of various adjustment termination conditions that can be understood by those skilled in the art or can be conceived in the future, such as the difference between the predicted value and the reference value meeting a threshold, meeting a predetermined number of iterations, etc., and the present disclosure is not limited thereto. For example, the method further includes, after adjusting the parameters of the neural network, obtaining at least one updated vector representation based on the reduced-dimensional image data through the adjusted neural network, obtaining updated predicted blood flow field information based on the at least one updated vector representation, and further adjusting the parameters of the neural network based on the updated predicted blood flow field information and the reference blood flow field information, etc., and the present disclosure is not limited thereto.

[0070] According to some embodiments, the at least one feature vector may be an orthogonally decomposed vector representation.

[0071] According to some embodiments, the at least one eigenvector may be a vector representation obtained through proper orthogonal decomposition (POD).

[0072] According to some embodiments, method 300 may further include, after an adjustment termination condition is satisfied, obtaining a dimension associated with the at least one feature vector corresponding to the adjusted neural network as a vector modality associated with the blood flow field information determination model. A specific example algorithm for vector modality will be further elaborated below.

[0073] According to some embodiments, the method may further include determining fractional flow reserve (FFR) information for the target blood vessel segment based on the blood flow field information.

[0074] According to some embodiments, the reference blood flow field information may be obtained by performing fluid mechanics simulation on the image data of the target blood vessel segment.

[0075] A schematic diagram of data flow according to a specific non-limiting embodiment of the present disclosure is described below in conjunction with Figure 4. In Figure 4, the upper half shows the offline side data flow, and the lower half shows the online side data flow.

[0076] During the offline operation, for example, a vascular segment dataset 401 is obtained, which can be, for example, a vascular segment segmentation dataset, such as a vascular segment 3D segmentation dataset. By performing dimensionality reduction on the vascular segment dataset 401, for example, by performing dimensionality reduction using a variational autoencoder (VAE), a dimensionality reduction feature 402 is obtained. The dimensionality reduction feature 402 can be input into a fully connected neural network 403 to obtain a POD coefficient 404, such as a predicted POD coefficient. On the other hand, a flow field dataset 407 can be obtained based on the vascular segment dataset 401 through a fluid dynamics (CFD) computational simulation 408. The POD coefficient and POD mode 406 can be obtained by performing proper orthogonal decomposition (POD) on the flow field dataset. During the training process, the parameters of the neural network can be adjusted by comparing the output of the fully connected neural network with the results based on the flow field dataset 407.

[0077] During online operation, illustratively, dimensionality reduction features 412 can be obtained based on image data 411. The dimensionality reduction process can be illustratively based on a variational autoencoder (VAE), or other methods understood by those skilled in the art. Dimensionality reduction features 412 can be input into a fully connected neural network 413 to obtain predicted POD coefficients 414. Based on POD coefficients 414, vascular segment flow field information 417 can be obtained. Illustratively, further information, such as the vascular segment pressure drop Δp, can be obtained based on the obtained vascular segment flow field information 417, but the present disclosure is not limited thereto.

[0078] An exemplary model of a blood vessel segment can be shown in FIG5 . Assume there are M blood vessel segments of different shapes, and N data points are selected on each blood vessel segment. P hemodynamic parameters (e.g., pressure, flow rate) can be calculated at each point in space, for example, using simulation, such as 3D CFD simulation, or other methods known to those skilled in the art. For each parameter, a data set (D) can be constructed, which can be expressed in the following matrix form D∈R N×M

[0079] Through singular value decomposition, D can be written as follows:

[0080] Among them, Φ N×M is the orthogonal modal matrix, Σ M×M It is a diagonal matrix, the values ​​on its diagonal are arranged in descending order, and each value represents an eigenvalue. is the coefficient matrix.

[0081] In general, the first k-order modes (k is much smaller than the rank of D) can be used to approximate the data set D, that is,

[0082] Among them, Φ N×kMay correspond to a vector mode as described in one or more embodiments of the present disclosure, which may also be referred to as a mode, basis, or dimension. It may correspond to the eigenvector as described in one or more embodiments of the present disclosure, and in the case of POD decomposition, it may also be referred to as a POD coefficient.

[0083] It should be understood that although the various operations are depicted in the drawings as being performed in a particular order, this should not be construed as requiring that the operations must be performed in the particular order shown or in sequential order, nor should it be construed as requiring that all illustrated operations must be performed to obtain the desired result. For example, two steps described herein in sequential order may be performed in the reverse order, or may be performed concurrently. For another example, one or more steps in the various embodiments of the present disclosure may be omitted.

[0084] It is understood that throughout this disclosure, an image or image sequence may be or include two-dimensional image data, or may be or include three-dimensional image data. It is understood that this disclosure is not limited thereto.

[0085] FIG6 is a schematic block diagram illustrating a blood flow field information determination device 600 according to an exemplary embodiment. The blood flow field information determination device 600 may include an image acquisition unit 610, a dimension reduction unit 620, a feature vector acquisition unit 630, and a blood flow field information acquisition unit 640. The image acquisition unit 610 may be configured to acquire an image of a target blood vessel segment. The dimension reduction unit 620 may be configured to acquire reduced-dimensional image data based on the image. The feature vector acquisition unit 630 may be configured to acquire at least one feature vector based on the reduced-dimensional image data using a pre-trained neural network. The blood flow field information acquisition unit 640 may be configured to acquire at least one piece of blood flow field information for the target blood vessel segment based on the at least one feature vector.

[0086] It should be understood that the various modules of the apparatus 600 shown in FIG6 may correspond to the various steps in the method 200 described with reference to FIG2 . Thus, the operations, features, and advantages described above for the method 200 are also applicable to the apparatus 600 and the modules included therein. For the sake of brevity, certain operations, features, and advantages are not described in detail herein.

[0087] FIG7 is a schematic block diagram illustrating an apparatus 700 for obtaining blood flow field information and determining a model according to an exemplary embodiment. The apparatus 700 may include an image obtaining unit 710, a dimensionality reduction unit 702, a feature vector obtaining unit 730, a prediction unit 740, an adjustment unit 750, and a model obtaining unit 760.

[0088] The image data acquisition unit 710 can be used to obtain an image of a target blood vessel segment. The dimension reduction unit 702 can be used to obtain reduced-dimensional image data based on the image. The feature vector acquisition unit 730 can be used to obtain at least one feature vector through a neural network based on the reduced-dimensional image data. The prediction unit 740 can be used to obtain predicted blood flow field information based on the at least one feature vector. The adjustment unit 750 is used to adjust the parameters of the neural network based on the predicted blood flow field information and the reference blood flow field information. The model acquisition unit 760 can be used to obtain the adjusted neural network as the blood flow field information determination model after the adjustment end condition is met.

[0089] It should be understood that the various modules of the apparatus 700 shown in FIG7 may correspond to the various steps in the method 200 described with reference to FIG2 . Thus, the operations, features, and advantages described above for the method 300 are also applicable to the apparatus 700 and the modules included therein. For the sake of brevity, certain operations, features, and advantages are not described in detail herein.

[0090] According to an embodiment of the present disclosure, a computing device is also disclosed, including a memory, a processor, and a computer program stored on the memory, wherein the processor is configured to execute the computer program to implement the steps of the blood flow field information determination method or the method for obtaining a blood flow field information determination model and its variant examples according to an embodiment of the present disclosure.

[0091] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium is also disclosed, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method for determining blood flow field information or the method for obtaining a blood flow field information determination model and its variant examples according to an embodiment of the present disclosure are implemented.

[0092] According to an embodiment of the present disclosure, a computer program product is also disclosed, including a computer program, wherein when the computer program is executed by a processor, it implements the steps of the blood flow field information determination method or the method for obtaining a blood flow field information determination model according to an embodiment of the present disclosure and its variant examples.

[0093] Although specific functions are discussed above with reference to specific modules, it should be noted that the functions of the various modules discussed herein can be divided into multiple modules, and / or at least some functions of multiple modules can be combined into a single module. The specific module discussed herein performing an action includes the specific module itself performing the action, or alternatively, the specific module calling or otherwise accessing another component or module that performs the action (or performs the action in conjunction with the specific module). Therefore, the specific module that performs an action can include the specific module itself that performs the action and / or another module that the specific module calls or otherwise accesses to perform the action. For example, the various modules or units described in accordance with one or more embodiments of the present disclosure can be combined into a single module or unit in some embodiments. For another example, in one or more embodiments of the present disclosure, two or more modules or units may be described in parallel, while in other embodiments, these modules and units may have one or more inclusion relationships. As used herein, the phrases "entity A initiates action B" or "entity A causes action B to be performed" may mean that entity A issues an instruction to perform action B, but entity A itself does not necessarily perform action B. For example, the phrase “the display module causes display . . . ” may mean that the display module instructs a display (not shown) or other possible display device to display, while the display module itself does not need to perform the action of “displaying”.

[0094] It should also be understood that various technologies can be described herein in the general context of software hardware elements or program modules. The various modules described above with respect to Figure 6 can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer program code / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of the modules or units described according to one or more embodiments of the present disclosure can be implemented together in a system on chip (SoC). SoC can include an integrated circuit chip (which includes a processor (e.g., a central processing unit (CPU), a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and can optionally execute the received program code and / or include embedded firmware to perform functions.

[0095] According to one aspect of the present disclosure, a computing device is provided, comprising a memory, a processor, and a computer program stored in the memory. The processor is configured to execute the computer program to implement the steps of any one of the method embodiments described above.

[0096] According to one aspect of the present disclosure, a non-transitory 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 method embodiment described above are implemented.

[0097] According to one aspect of the present disclosure, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the steps of any one of the method embodiments described above are implemented.

[0098] Illustrative examples of such a computer device, non-transitory computer-readable storage medium, and computer program product are described below in conjunction with FIG. 8 .

[0099] FIG8 illustrates an example configuration of a computer device 800 that can be used to implement the methods described herein. For example, the server 120 and / or client device 110 shown in FIG1 may include an architecture similar to that of the computer device 800. The aforementioned device / apparatus for determining the fractional flow reserve (FFR) or obtaining blood flow field information and determining a model may also be implemented in whole or in part by the computer device 800 or a similar device or system.

[0100] The computer device 800 can be a variety of different types of devices, such as a server of a service provider, a device associated with a client (e.g., a client device), a system on a chip, and / or any other suitable computer device or computing system. Examples of the computer device 800 include, but are not limited to, a desktop computer, a server computer, a laptop or netbook computer, a mobile device (e.g., a tablet computer, a cellular or other wireless phone (e.g., a smartphone), a notepad computer, a mobile station), a wearable device (e.g., glasses, a watch), an entertainment device (e.g., an entertainment appliance, a set-top box communicatively coupled to a display device, a game console), a television or other display device, a car computer, and the like. Thus, the computer device 800 can range from a full-resource device with a large amount of memory and processor resources (e.g., a personal computer, a game console) to a low-resource device with limited memory and / or processing resources (e.g., a traditional set-top box, a handheld game console).

[0101] The computer device 800 may include at least one processor 802, memory 804, communication interface(s) 806, a display device 808, other input / output (I / O) devices 810, and one or more mass storage devices 812, all capable of communicating with one another, such as via a system bus 814 or other appropriate connections.

[0102] The processor 802 may be a single processing unit or multiple processing units, all of which may include a single or multiple computing units or multiple cores. The processor 802 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operational instructions. Among other capabilities, the processor 802 may be configured to retrieve and execute computer-readable instructions stored in the memory 804, mass storage device 812, or other computer-readable media, such as program code for an operating system 816, program code for application programs 818, program code for other programs 820, and the like.

[0103] The memory 804 and the mass storage device 812 are examples of computer-readable storage media for storing instructions that are executed by the processor 802 to implement the various functions described above. For example, the memory 804 may generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). In addition, the mass storage device 812 may generally include a hard drive, a solid-state drive, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CDs, DVDs), storage arrays, network attached storage, storage area networks, etc. The memory 804 and the mass storage device 812 may all be collectively referred to herein as memory or computer-readable storage media, and may be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code, which may be executed by the processor 802 as a specific machine configured to implement the operations and functions described in the examples herein.

[0104] A number of program modules may be stored on the mass storage device 812. These programs include an operating system 816, one or more application programs 818, other programs 820, and program data 822, and they may be loaded into the memory 804 for execution. Examples of such applications or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing components / functionality including method 200 and / or method 300 (including any suitable steps of methods 200, 300) and / or other embodiments described herein.

[0105] 8 as being stored in memory 804 of computer device 800, modules 816, 818, 820, and 822, or portions thereof, may be implemented using any form of computer-readable media accessible by computer device 800. As used herein, "computer-readable media" includes at least two types of computer-readable media, namely, computer storage media and communication media.

[0106] Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVDs), or other optical storage devices, magnetic cassettes, magnetic tape, magnetic disk storage devices or other magnetic storage devices, or any other non-transmission media that can be used to store information for access by a computer device.

[0107] In contrast, communication media may embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism. Computer storage media as defined herein does not include communication media.

[0108] The computer device 800 may also include one or more communication interfaces 806 for exchanging data with other devices, such as through a network, a direct connection, etc., as previously discussed. Such communication interfaces may be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), a wired or wireless (such as an IEEE 802.11 wireless LAN (WLAN)) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth TM The communication interface 806 may include a wireless network interface, a near field communication (NFC) interface, and the like. The communication interface 806 may facilitate communication within a variety of network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, and the like. The communication interface 806 may also provide for communication with external storage devices (not shown) such as storage arrays, network attached storage, storage area networks, and the like.

[0109] In some examples, a display device 808 such as a monitor may be included for displaying information and images to the user. Other I / O devices 810 may be devices that receive various inputs from the user and provide various outputs to the user, and may include a touch input device, a gesture input device, a camera, a keyboard, a remote control, a mouse, a printer, an audio input / output device, and the like.

[0110] Although the present disclosure has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative and exemplary and not restrictive; the disclosure is not limited to the disclosed embodiments. Variations to the disclosed embodiments will be understood and effected by those skilled in the art in practicing the claimed subject matter by studying the drawings, the disclosure and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps that are not listed, and the word "a" or "an" does not exclude a plurality. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Claims

1. A method for determining blood flow field information, comprising: Obtaining an image of a target blood vessel segment; Obtaining dimension-reduced image data based on the image; Obtaining at least one feature vector based on the dimension-reduced image data through a pre-trained neural network; And Obtaining at least one blood flow field information for the target blood vessel segment based on the at least one feature vector.

2. The method according to claim 1, wherein The at least one feature vector is a vector representation obtained by orthogonal decomposition.

3. The method according to claim 2, wherein, The at least one feature vector is a vector representation obtained by proper orthogonal decomposition (POD).

4. The method according to any one of claims 1-3, wherein Obtaining at least one feature vector includes projecting the dimension-reduced image data onto a predetermined dimension associated with the pre-trained neural network.

5. The method according to any one of claims 1-4, further comprising determining fractional flow reserve (FFR) information for the target blood vessel segment based on the blood flow field information.

6. A method for obtaining a blood flow field information determination model, comprising: Obtaining an image of a target blood vessel segment; Obtaining a dimension-reduced image based on the image; Obtaining at least one feature vector based on the dimension-reduced image through a neural network; Obtaining predicted blood flow field information based on the at least one feature vector; Adjusting parameters of the neural network based on the predicted blood flow field information and reference blood flow field information; And After meeting the adjustment end condition, obtaining the adjusted neural network as the blood flow field information determination model.

7. The method according to claim 6, wherein, The at least one feature vector is a vector representation obtained by orthogonal decomposition.

8. The method according to claim 7, wherein The at least one feature vector is a vector representation obtained by proper orthogonal decomposition (POD).

9. The method according to any one of claims 6-8, further comprising, after meeting the adjustment end condition, obtaining the dimension associated with the at least one feature vector corresponding to the adjusted neural network as the vector mode associated with the blood flow field information determination model.

10. The method according to any one of claims 6-9, further comprising determining fractional flow reserve (FFR) information for the target blood vessel segment based on the blood flow field information.

11. The method according to any one of claims 6 - 10, wherein, The reference blood flow field information is obtained by performing hydrodynamic simulation on the image of the target blood vessel segment.

12. A blood flow field information determination device, comprising: An image acquisition unit for obtaining an image of a target blood vessel segment; A dimension reduction unit for obtaining dimension-reduced image data based on the image; A feature vector acquisition unit for obtaining at least one feature vector based on the dimension-reduced image data through a pre-trained neural network; And A blood flow field information acquisition unit for obtaining at least one blood flow field information for the target blood vessel segment based on the at least one feature vector.

13. A device for obtaining a blood flow field information determination model, comprising: An image acquisition unit for obtaining an image of a target blood vessel segment; A dimension reduction unit for obtaining dimension-reduced image data based on the image; A feature vector acquisition unit for obtaining at least one feature vector based on the dimension-reduced image data through a neural network; A prediction unit for obtaining predicted blood flow field information based on the at least one feature vector; An adjustment unit, configured to adjust parameters of the neural network based on the predicted blood flow field information and the reference blood flow field information; and a model obtaining unit, configured to obtain the adjusted neural network as the blood flow field information determination model after an adjustment end condition is satisfied.

14. A computing device, comprising: a memory, a processor, and a computer program stored on the memory, wherein the processor is configured to execute the computer program to implement the steps of the method according to any one of claims 1-5 or 6-11.

15. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, the steps of the method according to any one of claims 1-5 or 6-11 are implemented.

16. A computer program product, comprising a computer program, wherein, When the computer program is executed by the processor, the steps of the method according to any one of claims 1-5 or 6-11 are implemented.

Images