Blood flow field information determination method, device, computing device and storage medium

Abstract

A method, apparatus, computing device, and storage medium for determining blood flow field information are provided. The method may include: obtaining vessel segment image data for a target vessel segment, the target vessel segment including at least one vessel branch; obtaining a straightened vessel segment model based on the vessel segment image data, the straightened vessel segment model being used to characterize the at least one vessel branch in a non-curved form; and determining at least one piece of blood flow field information associated with the target vessel segment based on the straightened vessel segment model.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, apparatus, computing device, and storage medium for determining blood flow field information. Background Art

[0002] In the medical field, various blood flow field information can reflect a lot of useful information. A method for analyzing or determining blood flow field information is desired.

[0003] 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

[0004] According to one aspect of the present disclosure, a method for determining blood flow field information is provided, comprising: obtaining vascular segment image data for a target vascular segment, the target vascular segment including at least one vascular branch; obtaining a straightened vascular segment model based on the vascular segment image data, the straightened vascular segment model being used to characterize the at least one vascular branch in a non-bent form; and determining at least one blood flow field information associated with the target vascular segment based on the straightened vascular segment model.

[0005] According to another aspect of the present disclosure, a blood flow field information determination device is provided, comprising: an image acquisition unit for obtaining vascular segment image data for a target vascular segment, the target vascular segment including at least one vascular branch; a model acquisition unit for obtaining a straightened vascular segment model based on the vascular segment image data, the straightened vascular segment model being used to characterize the at least one vascular branch in a non-bent form; and an information determination unit for determining at least one blood flow field information associated with the target vascular segment based on the straightened vascular segment model.

[0006] 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 blood flow field information determination method according to one or more embodiments of the present disclosure.

[0007] 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, the blood flow field information determination method according to one or more embodiments of the present disclosure is implemented.

[0008] 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 the blood flow field information determination method according to one or more embodiments of the present disclosure.

[0009] 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

[0010] 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:

[0011] Figure 1 is a schematic diagram illustrating an example system in which the various methods described herein may be implemented, according to an exemplary embodiment;

[0012] Figure 2 is a flow chart illustrating a method for determining blood flow field information according to an exemplary embodiment;

[0013] Figures 3A-3D is a schematic diagram illustrating an exemplary blood vessel segment;

[0014] Figure 4 is a flow chart illustrating a method for training a blood flow field prediction model according to an exemplary embodiment;

[0015] Figure 5 is a schematic block diagram illustrating a blood flow field information determining apparatus according to an exemplary embodiment;

[0016] Figure 6 is a block diagram illustrating an exemplary computer device that can be used with the exemplary embodiments. DETAILED DESCRIPTION

[0017] 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.

[0018] 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.

[0019] Exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0020] Figure 1 is a schematic diagram illustrating an example system 100 in which the various methods described herein may be implemented, according to an exemplary embodiment.

[0021] refer to Figure 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 .

[0022] 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.

[0023] 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 Figure 1 1. The server 120 is shown communicating with only one client device 110, but the server 120 may provide background services to multiple client devices simultaneously.

[0024] 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.

[0025] The system 100 may also include an image acquisition device 140. In some embodiments, Figure 1The image acquisition device 140 shown can 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), etc. 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, a magnetic resonance imaging scanner, a digital radiography scanner, etc. The image acquisition device 140 may communicate with a server (e.g., Figure 1 The server 120 in the figure or a separate server of the imaging system (not shown in the figure) is connected to realize image data processing, including but not limited to converting the scan data (for example, converting it into a medical image sequence), compression, pixel correction, three-dimensional reconstruction, etc.

[0026] 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.

[0027] 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. 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 according to an embodiment of the present disclosure.

[0028] 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.

[0029] 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.

[0030] For the purpose of the embodiments of this disclosure, Figure 1In the example, 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, server 120 may be a server used in conjunction with the image sequence management application. Server 120 may provide image sequence management services to client application 112 running on client device 110 based on user requests or instructions generated according to embodiments of the present disclosure. For example, server 120 may manage cloud-based image sequence storage, store and classify 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.), retrieve and provide image sequences to client devices based on specified indices, etc. Alternatively, server 120 may provide or allocate such service capabilities or storage space to client device 110, with client application 112 running on client device 110 providing corresponding image sequence management services based on user requests or instructions generated according to embodiments of the present disclosure. It will be appreciated that the above is merely an example and the present disclosure is not limited thereto.

[0031] Figure 2 2 is a flow chart illustrating a method 200 for determining blood flow field information according to an exemplary embodiment. The method 200 may be performed on a client device (eg, Figure 1 , that is, the execution subject of each step of the method 200 may be a client device 110 shown in FIG. Figure 1 In some embodiments, the method 200 may be performed on a server (e.g., Figure 1 In some embodiments, the method 200 may be performed by a client device (eg, the client device 110) and a server (eg, the server 120) in combination.

[0032] In the following, each step of the method 200 is described in detail.

[0033] refer to Figure 2 At step 210 , blood vessel segment image data for a target blood vessel segment is obtained, where the target blood vessel segment includes at least one blood vessel branch.

[0034] At step 220 , a straightened blood vessel segment model is obtained based on the blood vessel segment image data, where the straightened blood vessel segment model is used to represent the at least one blood vessel branch in a non-bending form.

[0035] At step 230 , at least one piece of blood flow field information associated with the target blood vessel segment is determined based on the straightened blood vessel segment model.

[0036] Through the above method, the calculation of blood flow field information can be simplified by straightening the blood vessel segment model.

[0037] Due to the morphology of human blood vessels, at least one of the vessel branches in the vessel segment image data may contain one or more bends. Modeling and calculations based on such vessel segment images are often very complex. However, in medical image modeling, the flow field information of interest is often known at specific points. Therefore, in this case, straightening a curved vessel does not introduce a measurable error in the calculation results, but can greatly simplify the modeling and calculation process.

[0038] For example, the process of obtaining a straightened vessel segment model based on the vessel segment image data may be referred to as straightening processing. For example, the straightening processing may be used to straighten one or more curved vessel branches of the target vessel segment into a non-curved vessel branch model. For example, the straightening processing may obtain a straightened vessel segment image, image sequence, or video. For example, the image data subjected to the straightening processing may be a straightened image in which one or more curved vessel branches of the target vessel segment are straightened.

[0039] Figure 3A An exemplary blood vessel segment is shown, which has a curved morphology and has an exemplary lesion (e.g., plaque) therein. The exemplary straightened image obtained after the straightening process can be shown as follows: Figure 3B shown. Figure 3A The flow rates Q1, Q2 and Q3 of each blood vessel segment in the curved blood vessel model or blood flow model shown in FIG. Figure 3B The flow rates Q1', Q2' and Q3' of each blood vessel segment in the non-bending blood vessel model or blood flow model shown in the figure correspond to each other. Before and after the straightening process, other physical quantities not shown, such as viscosity, pressure, flow rate, etc., can also correspond to each other, for example, be equal or satisfy a specific transformation relationship. Figure 3B In the specific example in FIG. 1 , the straightened blood vessel segment model is shown as a three-dimensional model, but it can be understood that the present disclosure is not limited thereto.

[0040] According to some embodiments, obtaining a straightened vessel segment model based on the vessel segment image data may include: obtaining a vessel centerline of the at least one vessel branch based on the vessel segment image data; and performing modeling based on the vessel centerline to obtain the straightened vessel segment model. For example, the vessel centerline of a curved vessel may be first obtained, then unfolded and deformed in a linear shape (e.g., a cylinder, a substantially cylindrical shape, a truncated cone, or a cone) along the length dimension to obtain the straightened vessel segment model. According to some embodiments, performing modeling based on the vessel centerline to obtain the straightened vessel segment model may include: obtaining vessel cross-sectional data corresponding to a plurality of points on the vessel centerline; and obtaining the straightened vessel segment model based on the vessel cross-sectional data and the vessel centerline. For example, a plurality of points may be acquired using a point selection strategy such as fixed interval sampling, a predetermined plurality of sampling points, key points, or bifurcation points to obtain cross-sectional data corresponding to the points, and the corresponding cross-sectional data may be mapped to the unfolded centerline to achieve straightened vessel modeling. According to other embodiments, the transformation (straightening) from curved vessel segment data to straightened vessel segment data may be achieved using a pre-trained model.

[0041] According to one or more embodiments of the present disclosure, at least one straightened image can be generated based on an original image. For example, a portion of the image region can be selected from the original image to generate the straightened image. For example, a portion of the image containing blood vessels can be selected, while regions not containing blood vessels can be disregarded (e.g., cropped or discarded).

[0042] Exemplarily, the method may further include obtaining at least one straightened blood vessel segment model based on the blood vessel segment image, wherein each straightened blood vessel segment model in the at least one straightened blood vessel segment model corresponds to a branch point in the blood vessel segment image.

[0043] Exemplarily, the method may further include, before obtaining at least one straightened vascular segment model based on the vascular segment image: obtaining at least one sub-region of the vascular segment image, the at least one sub-region corresponding to the at least one straightened vascular segment model. Exemplarily, the at least one sub-region of the vascular segment image is obtained based on a first selection strategy, and the first selection strategy is used to increase the proportion of the region corresponding to the side branch vessels in the target vascular segment in the corresponding sub-region. For example, a selection strategy may be based on preferentially selecting regions containing branches so that the branch regions occupy a larger image space. For example, regions containing branches may be selected as much as possible, regions containing more branches may be selected, regions in which the area of ​​the side branch vessels accounts for a larger proportion of the total area may be selected, or a combination or trade-off of the above items may be selected. Such an exemplary strategy is based on the following considerations: branches often have a greater impact on flow field prediction. Therefore, by preferentially selecting regions containing branches, the FFR value can be calculated more accurately. For example, referring to Figure 3C , compared to box 331, the area corresponding to box 332 is straightened and modeled. The resulting model may be more suitable for flow field analysis and more accurate. It is understood that other factors such as lesions, key points, and analysis objectives may also be considered when selecting sub-areas, and the present disclosure is not limited thereto.

[0044] Exemplarily, the target vascular segment may include a first vascular segment, a second vascular segment, and a third vascular segment connected via a first branch point. For example, the blood flow of the first vascular segment may be the sum of the blood flow of the second vascular segment and the third vascular segment. For example, the first vascular segment is shunted to the second vascular segment and the third vascular segment, or the second vascular segment and the third vascular segment merge into the first vascular segment. Alternatively, the first vascular segment and the second vascular segment are two segments of the same vascular segment on both sides of the branch point, and the third vascular segment is a branch vessel that merges in or out. For example, referring to Figure 3D As shown, an exemplary first vessel segment 341 , a second vessel segment 342 , and a third vessel segment 343 are connected at a branch point 340 .

[0045] Exemplarily, obtaining a straightened vascular segment model based on the vascular segment image data may include obtaining a first straightened vascular segment model about the first branch point by treating the first vascular segment and the second vascular segment as main vessels and the third vascular segment as a side branch vessel.

[0046] Exemplarily, determining at least one blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model may include: obtaining at least one blood flow field information at at least one position point in the third blood vessel segment based on the first straightened blood vessel segment model.

[0047] Additionally or alternatively, blood flow field information at at least one position point in the first blood vessel segment and the second blood vessel segment may be obtained based on the first straightened blood vessel segment model.

[0048] In other words, in the case of including branch points, the flow field information in the branch vessels can be calculated based on the straightened vessel model, and the flow field information in the main vessel can also be calculated.

[0049] As a further embodiment, obtaining a straightened vessel segment model based on the vessel segment image data may further include obtaining a second straightened vessel segment model related to the first branch point by treating the first and third vessel segments as main vessels and the second vessel segment as a side branch. For example, blood flow field information at least one location in the third vessel segment is also based on the second straightened vessel segment model.

[0050] Return Reference Figure 3DA specific non-limiting embodiment is described, wherein, for a branch point associated with at least three blood vessel segments, at least two straightened blood vessel models can be established, corresponding at least two sets of flow field prediction results are generated, and the flow field prediction results of the at least three blood vessel segments are determined based on the two sets of flow field prediction results. For example, referring to Figure 3D , vascular segments 341 and 342 can be treated as main vessels, and straightened maps can be generated for them, and corresponding flow field information for one or more locations, including locations in branch vessel 343, can be calculated. For convenience of description, this is referred to as the first set of flow field information. Alternatively, for example, vascular segments 341 and 343 can be treated as main vessels, and straightened maps can be generated for them, and corresponding flow field information for one or more locations, including locations in branch vessel 342, can be calculated. For convenience of description, this is referred to as the second set of flow field information. The locations targeted by the first set of flow field information and the second set of flow field information can partially or completely overlap. At those overlapping locations, a final flow field information result can be calculated based on the first set of flow field information and the second set of flow field information, for example, by taking a weighted average of the first set of flow field information and the second set of flow field information.

[0051] According to some embodiments, the method may further include obtaining lesion image data of at least one lesion region associated with the target vessel segment, wherein the straightened vessel segment model may also be based on the lesion image data. According to some embodiments, the lesion information may be segmentation data of the at least one lesion region, such as segmentation mask data.

[0052] As a specific non-limiting example, lesion information (e.g., lesion location) can be input as a prompt into a model used to determine blood flow field information. As another non-limiting example, the model can be trained to additionally have the ability to predict lesion information, thereby deepening its understanding of the current image.

[0053] For example, using lesion information as a reference can include leveraging lesion segmentation to personalize various thresholds related to the current subject, acquisition environment, contrast agent, and imaging level. For example, the overall image quality level can be corrected using the CT values ​​(e.g., pixel color depth) of lesion and non-lesion areas. For another example, the location of vascular branches, the width of vascular sections, etc. can be defined or corrected based on the location of the lesion. As another example, using lesion information as a reference can include performing flow field prediction at the lesion site with higher accuracy, higher precision requirements, more computing power, and lower error threshold requirements. As another additional or alternative example, using lesion information as a reference can include determining sampling points, prediction points, key points, etc. based on the lesion site. For example, the density of each point in the flow field information to be generated (e.g., the resolution of the result) can be determined based on the lesion size, so that the scale of the generated result matches the lesion size. For another example, key points can be determined based on the type and location of the lesion, where the specific flow field information at these key points is of greater importance for subsequent diagnosis, treatment, etc. Continuing with the above example of FFR prediction, for example, when the lesion location is obtained, the model can make higher-precision targeted predictions of the pressure field information in the upstream and downstream areas where the lesion (e.g., arterial stenosis) is located, thereby obtaining more accurate estimation results without wasting computing resources.

[0054] According to some embodiments, the blood flow field may be a pressure field. For example, the at least one piece of blood flow field information determined may include at least one of pressure, flow velocity, and flow rate. Thus, important physical quantities in the blood flow field can be obtained, and other physiological or pathological information of the human body related to the target blood vessel segment can be determined.

[0055] According to some embodiments, the method may further include obtaining at least one piece of human medical information about the target blood vessel segment based on the at least one piece of blood flow field information.

[0056] When diagnosing coronary heart disease, it's often necessary to assess the health of the coronary arteries. For example, functional assessment can be based on the fractional flow reserve (FFR). FFR refers to the ratio of the maximum blood flow available to the myocardial region supplied by a coronary artery in the presence of a stenotic lesion to the theoretically maximum blood flow that the same region could achieve under normal conditions. This refers to the ratio of the mean pressure (Pd) in the coronary artery distal to the stenosis at maximum myocardial hyperemia to the mean pressure (Pa) in the aorta at the coronary artery ostium. According to some embodiments, the at least one piece of human medical information may include fractional flow reserve (FFR) information. For example, if the blood flow field is a pressure field or the determined blood flow field information includes pressure values ​​at corresponding locations, a predicted FFR value can be obtained based on the blood flow field information. In other examples, at least one other piece of human medical information about the target vessel segment, as understood by those skilled in the art, such as plaque risk assessment, surgical guidance, etc., can also be determined based on the blood flow field information. The corresponding blood flow field information may include blood pressure, flow velocity, shear stress, etc., but the present disclosure is not limited thereto.

[0057] As a specific, non-limiting example, when the required human medical information includes FFR values, in addition to pressure P information, predictions can also be made for flow velocity v, flow rate Q, and / or viscosity η, and these predicted physical quantities can also be made to satisfy physical constraints, such as one or more fluid mechanics or dynamics equations. Such a prediction model can predict a more comprehensive range of physical quantities, thereby providing a deeper understanding of physical relationships and, therefore, greater accuracy. In other words, the method may include obtaining a vessel segment image of a target vessel segment and, based on the vessel segment image data, obtaining a predicted value of a first physical quantity and a predicted value of at least one second physical quantity in the blood flow field corresponding to the target vessel segment, wherein the predicted value of the first physical quantity and the predicted value of the at least one second physical quantity satisfy at least one constraint. At least one piece of human medical information regarding the target vessel segment can be determined based on the predicted value of the first physical quantity. For example, the predicted value of the second physical quantity may not be used to determine the human medical information, but rather simply to monitor the first physical quantity and / or the model itself within the physical constraints. According to such an embodiment, the model output can be made to conform to the effects of physical formulas, thereby ensuring the accuracy and rationality of the model output at the physical level.

[0058] Various types of vascular segment images can be used. Exemplarily, the vascular segment image can be a CT image. Exemplarily, the vascular segment image data for the target vascular segment can be an image acquired by a digital subtraction angiography (DSA) method, and the present disclosure is not limited thereto. Exemplarily, the vascular segment image data for the target vascular segment can be a coronary CTA image acquired by computed tomography angiography. As another non-limiting example, the vascular segment image data can also be segmentation data for the target vascular segment, such as segmentation mask data. In such an example, image segmentation can be achieved using any method that can be understood by those skilled in the art, and the present disclosure is not limited thereto.

[0059] According to some embodiments, the method may further include obtaining a prediction interval of the at least one blood flow field information. In such an embodiment, the at least one human medical information about the target blood vessel segment may also be based on the prediction interval.

[0060] Exemplarily, the method may further include obtaining an updated predicted value of the blood flow field information based on the prediction interval, and at least one human medical information may be determined based on the updated predicted value. In such an embodiment, the predicted value of the blood flow field information (e.g., a portion of the blood flow field information) may be updated based on the prediction interval, and the human medical information may be determined based on the updated predicted value, thereby increasing the accuracy of the prediction.

[0061] Due to the complex structure of the human body and the limitations of image acquisition conditions, images of vascular segments often experience occlusion, distortion, and overlap, resulting in differences in image clarity, accuracy, and contrast imaging quality for some vascular segments compared to others. Alternatively, the model's prediction capabilities may be subject to errors for vessels with distorted shapes, significant fluctuations in shape with breathing and heartbeat, small size, or blurred boundaries. For example, the predicted values ​​and prediction intervals for superior vascular segments with clearer images and more stable morphology can be used, and the connection between the two can be leveraged to update the predicted values ​​for inferior vascular segments with less clear images, occlusions, and significant fluctuations over time. For example, the target vascular segment may include a first vascular segment and a second vascular segment, where the first vascular segment may connect to the second vascular segment via a branch point. For example, one of the first and second vascular segments may be a side branch, while the other may be a main vessel. In another example, both the first and second vascular segments may be side branches. In other words, For example, determining the updated predicted value of the blood flow field information based on the prediction interval may include determining the updated predicted value of the blood flow field information at at least one position in the second blood vessel segment based on the prediction interval of the blood flow field information at at least one position in the first blood vessel segment.

[0062] Furthermore, it is understood that obtaining a prediction interval associated with the predicted value may include determining the predicted value and / or prediction interval of the blood flow field information for one or more locations (e.g., one or more prediction points) in the first blood vessel segment. Such at least one location or prediction point may be sampled or selected based on a predetermined or machine-selected resolution, or may be additionally selected based on the location of a lesion, a focus, a key point, etc., and the present disclosure is not limited thereto.

[0063] As another example of updating the predicted value of the associated blood vessel based on the vascular topology, in the target blood vessel segment, there may be a situation where the first blood vessel segment and the second blood vessel segment are connected to the third blood vessel segment via the branch point. For example, one of the first blood vessel segment, the second blood vessel segment, and the third blood vessel segment may be a main blood vessel, and the others may be side branches. The main blood vessel in the first blood vessel segment, the second blood vessel segment, and the third blood vessel segment may branch into two side branches, or may be formed by the confluence of two side branches. Alternatively, both of the first blood vessel segment, the second blood vessel segment, and the third blood vessel segment may belong to the main blood vessel, and the remaining one may be a side branch. In such an example, the updated predicted value of the blood flow field information at at least one position in the second blood vessel segment may be based on the predicted interval of the blood flow field information at at least one position in the third blood vessel segment.

[0064] Exemplarily, determining the updated predicted value of the blood flow field information at at least one position in the second vascular segment based on the predicted interval of the blood flow field information at at least one position in the first vascular segment may include: determining the updated predicted value of the blood flow field information at at least one position in the second vascular segment based on the blood flow convergence relationship at the branch point, and based on the predicted interval of the blood flow field information at at least one position in the first vascular segment and the predicted interval of the blood flow field information at at least one position in the third vascular segment. The blood flow convergence relationship may include a conservation relationship or an equation relationship consisting of the inflow and outflow of blood, for example, the blood flow rate flowing into the branch point and the blood flow rate flowing out of the branch point should be conserved. Return to reference Figure 3B For example, Q1'=Q2'+Q3' may be obtained. For another example, at various locations near or approximately located at a branch point in different vascular segments connected to the branch point, the predicted pressure values ​​should be approximately equal, continuous, or otherwise satisfy physical constraints. Exemplarily, each prediction interval may include a prediction upper limit and a prediction lower limit, and updating the predicted value may include adjusting the predicted value or prediction interval so that the upper and lower limits between the interconnected vascular segments satisfy corresponding conservation or equation relationships.

[0065] For example, the at least one blood flow field information associated with the target blood vessel segment determined based on the straightened blood vessel segment model can be obtained by a pre-trained neural network. The model or network required in one or more embodiments of the present disclosure, such as a model or network for predicting blood flow field information, can be trained using any method that can be understood by those skilled in the art. Figure 4 A non-limiting exemplary training method 400 is described.

[0066] At step 410 , straightened vessel model data regarding a sample vessel segment is obtained.

[0067] At step 420 , based on the straightened blood vessel model data, a predicted value of at least one blood flow field information corresponding to the sample blood vessel segment is obtained through a blood flow field prediction model.

[0068] At step 430 , the parameters of the blood flow field prediction model are adjusted based on at least a first strategy, wherein the first strategy is used to reduce the difference between the predicted value and the corresponding true value of the at least one blood flow field information.

[0069] Exemplarily, the at least one piece of blood flow field information can be used to determine at least one piece of human medical information about the sample blood vessel segment.

[0070] Exemplarily, the parameters of the blood flow field prediction model can also be adjusted based on additional strategies, and the additional strategies can be used to ensure that at least one constraint condition is satisfied between the various physical quantities of the at least one blood flow field information. Exemplarily, the at least one constraint condition can be a physical constraint condition. For example, the physical quantity that satisfies the constraint condition can satisfy one or more physical formulas or physical constraints expressed in other forms. As a specific non-limiting example, the true value of the flow rate Q can be estimated through the physical equation using the true values ​​of the pressure P and the flow rate v, and the corresponding predicted values ​​of the pressure, flow rate and flow rate are compared with the corresponding true values ​​respectively. If satisfied, it can be considered that the physical constraint condition is satisfied. According to such an embodiment, the model output can be made to fit the effect of the physical formula, thereby ensuring the accuracy and rationality of the model output at the physical level.

[0071] It will be understood that throughout this disclosure, the models described with respect to the training methods may be applicable to the prediction methods or determination methods of other embodiments of this disclosure, and the prediction methods or determination methods in the embodiments of this disclosure may use the models trained by the training methods according to the embodiments of this disclosure, or may use other models or algorithms that can be understood by those skilled in the art, and for the sake of brevity, these repeated or similar features will not be described in detail.

[0072] Furthermore, it should be understood that although the various operations are depicted in the various figures 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 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.

[0073] Furthermore, it is understood that the methods for predicting or determining data involved in one or more embodiments of the present disclosure are not methods for a doctor to directly determine a diagnosis result, but rather involve data processing or information processing during the medical process, and the data processing results can be used as a reference for the doctor, thereby assisting the doctor's medical operations. It is understood that the information processing methods, data prediction methods, determination methods, decision-making methods, etc. involved in one or more embodiments of the present disclosure are executed by a computer or a device containing a computer.

[0074] It is understood that throughout this disclosure, images, image data or image sequences may be or may include two-dimensional image data, or may be or include three-dimensional image data. Images, image data or image sequences may be image data that is directly collected and stored or otherwise sent to a terminal device for use by a user. Images, image data or image sequences may also be processed image data after various image processing. Images, image data or image sequences may undergo other analysis processes (for example, an analysis process for the presence or absence of pathological features or lesions) and include analysis results (for example, the circling of an area of ​​interest, the segmentation results of a tissue, etc.). It is understood that this disclosure is not limited thereto.

[0075] Figure 5 is a schematic block diagram illustrating a blood flow field information determination apparatus 500 according to an exemplary embodiment. The blood flow field information determination apparatus 500 may include an image acquisition unit 510, a model acquisition unit 520, and an information determination unit 530. The image acquisition unit 510 may be configured to acquire vascular segment image data for a target vascular segment, the target vascular segment including at least one vascular branch. The model acquisition unit 520 may be configured to acquire a straightened vascular segment model based on the vascular segment image data, the straightened vascular segment model being configured to characterize the at least one vascular branch in a non-bending form. The information determination unit 530 may be configured to determine at least one piece of blood flow field information associated with the target vascular segment based on the straightened vascular segment model.

[0076] It should be understood that Figure 5 The modules of the apparatus 500 shown in FIG. 5 can be used in conjunction with the reference Figure 2The steps in the method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 and its variants are also applicable to the apparatus 500 and the modules included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0077] 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 at least one of the blood flow field information determination method and the corresponding model training method according to the embodiment of the present disclosure and its variant examples.

[0078] 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 at least one of the blood flow field information determination method and the corresponding model training method according to the embodiment of the present disclosure and its variant examples are implemented.

[0079] 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 at least one of the blood flow field information determination method and the corresponding model training method according to the embodiment of the present disclosure and its variant examples.

[0080] 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.

[0081] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program modules. Figure 5The various modules described 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] In the following, combined Figure 6 Illustrative examples of such a computer device, non-transitory computer-readable storage medium, and computer program product are described.

[0086] Figure 6 6 shows an example configuration of a computer device 600 that can be used to implement the methods described herein. Figure 1 The server 120 and / or the client device 110 shown in FIG may include an architecture similar to the computer device 600. The blood flow field information determination device / apparatus may also be fully or at least partially implemented by the computer device 600 or similar devices or systems.

[0087] The computer device 600 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 600 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 600 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).

[0088] The computer device 600 may include at least one processor 602, memory 604, communication interface(s) 606, a display device 608, other input / output (I / O) devices 610, and one or more mass storage devices 612, all capable of communicating with one another, such as via a system bus 614 or other appropriate connections.

[0089] The processor 602 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 602 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 602 may be configured to retrieve and execute computer-readable instructions stored in the memory 604, mass storage device 612, or other computer-readable media, such as program code for an operating system 616, program code for application programs 618, program code for other programs 620, and the like.

[0090] The memory 604 and the mass storage device 612 are examples of computer-readable storage media for storing instructions that are executed by the processor 602 to implement the various functions described above. For example, the memory 604 may generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). In addition, the mass storage device 612 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 604 and the mass storage device 612 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 that can be executed by the processor 602 as a specific machine configured to implement the operations and functions described in the examples herein.

[0091] A number of program modules may be stored on the mass storage device 612. These programs include an operating system 616, one or more application programs 618, other programs 620, and program data 622, and they may be loaded into the memory 604 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 400 (including any suitable steps of methods 200, 400) and / or other embodiments described herein.

[0092] Although Figure 6 6 as being stored in the memory 604 of the computer device 600, but the modules 616, 618, 620, and 622, or portions thereof, may be implemented using any form of computer-readable media that can be accessed by the computer device 600. As used herein, "computer-readable media" includes at least two types of computer-readable media, namely, computer storage media and communication media.

[0093] 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.

[0094] 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.

[0095] The computer device 600 may also include one or more communication interfaces 606 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 606 may include a wireless network interface, a near field communication (NFC) interface, and the like. The communication interface 606 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 606 may also provide for communication with external storage devices (not shown) such as storage arrays, network attached storage, storage area networks, and the like.

[0096] In some examples, a display device 608 such as a monitor may be included for displaying information and images to the user. Other I / O devices 610 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.

[0097] 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 blood vessel segment image data for a target blood vessel segment, wherein the target blood vessel segment includes at least one blood vessel branch; obtaining a straightened blood vessel segment model based on the blood vessel segment image data, wherein the straightened blood vessel segment model is used to characterize the at least one blood vessel branch in a non-bending form; and determining at least one piece of blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model; The target blood vessel segment includes a first blood vessel segment, a second blood vessel segment, and a third blood vessel segment connected via a first branch point; Wherein, obtaining the straightened blood vessel segment model based on the blood vessel segment image data includes: obtaining a first straightened blood vessel segment model about the first branch point by taking the first blood vessel segment and the second blood vessel segment as main blood vessels and the third blood vessel segment as a side branch vessel, and obtaining a second straightened blood vessel segment model about the first branch point by taking the first blood vessel segment and the third blood vessel segment as main blood vessels and the second blood vessel segment as a side branch vessel; and Wherein, determining at least one piece of blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model includes: Determining a first set of flow field information based on the first straightened blood vessel segment model and determining a second set of flow field information based on the second straightened blood vessel segment model, the first set of flow field information including prediction results at a first set of location points, the second set of flow field information including prediction results at a second set of location points, the first set of location points and the second set of location points including overlapping location points; and The at least one blood flow field information is obtained by weighted averaging the first set of flow field information and the second set of flow field information. The at least one blood flow field information includes the weighted average flow field information prediction results at the overlapping position points.

2. The method according to claim 1, wherein Obtaining a straightened blood vessel segment model based on the blood vessel segment image data includes: obtaining a blood vessel centerline of the at least one blood vessel branch based on the blood vessel segment image data; and Modeling is performed based on the blood vessel centerline to obtain the straightened blood vessel segment model.

3. The method according to claim 2, wherein: Modeling based on the blood vessel centerline to obtain the straightened blood vessel segment model includes: Obtaining blood vessel section data corresponding to a plurality of points on the blood vessel centerline; and The straightened blood vessel segment model is obtained based on the blood vessel section data and the blood vessel centerline.

4. The method according to any one of claims 1 to 3, further comprising obtaining at least one straightened vascular segment model based on the vascular segment image, each straightened vascular segment model in the at least one straightened vascular segment model corresponding to a branch point in the vascular segment image.

5. The method according to claim 4 further comprises, before obtaining at least one straightened blood vessel segment model based on the blood vessel segment image: obtaining at least one sub-region of the blood vessel segment image, wherein the at least one sub-region corresponds to the at least one straightened blood vessel segment model respectively.

6. The method according to claim 5, wherein: The at least one sub-region of the blood vessel segment image is obtained based on a first selection strategy, where the first selection strategy is used to increase the proportion of the region corresponding to the side branch vessel in the target blood vessel segment in the corresponding sub-region.

7. The method according to claim 1, wherein Determining at least one piece of blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model includes: Based on the first straightened blood vessel segment model, at least one piece of blood flow field information at at least one position point in the third blood vessel segment is obtained.

8. The method according to any one of claims 1 to 7, further comprising obtaining lesion image data of at least one lesion region associated with the target blood vessel segment, wherein: The straightened blood vessel segment model is also based on the lesion image data.

9. The method according to any one of claims 1 to 8, wherein The straightened blood vessel segment model is a three-dimensional model.

10. The method according to any one of claims 1 to 9, wherein The method further includes obtaining at least one piece of human medical information about the target blood vessel segment based on the at least one piece of blood flow field information.

11. The method according to claim 10, wherein: The at least one human medical information includes fractional flow reserve (FFR) information.

12. The method according to claim 10 or 11, further comprising obtaining a prediction interval of the at least one blood flow field information, and wherein, The at least one piece of human medical information about the target blood vessel segment is further based on the prediction interval.

13. A device for determining blood flow field information, comprising: an image acquisition unit, configured to acquire blood vessel segment image data for a target blood vessel segment, wherein the target blood vessel segment includes at least one blood vessel branch; a model obtaining unit, configured to obtain a straightened blood vessel segment model based on the blood vessel segment image data, wherein the straightened blood vessel segment model is used to characterize the at least one blood vessel branch in a non-bending form; and an information determining unit, configured to determine at least one piece of blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model, The target blood vessel segment includes a first blood vessel segment, a second blood vessel segment, and a third blood vessel segment connected via a first branch point; Wherein, obtaining the straightened blood vessel segment model based on the blood vessel segment image data includes: obtaining a first straightened blood vessel segment model about the first branch point by taking the first blood vessel segment and the second blood vessel segment as main blood vessels and the third blood vessel segment as a side branch vessel, and obtaining a second straightened blood vessel segment model about the first branch point by taking the first blood vessel segment and the third blood vessel segment as main blood vessels and the second blood vessel segment as a side branch vessel; and Wherein, determining at least one piece of blood flow field information associated with the target blood vessel segment based on the straightened blood vessel segment model includes: Determining a first set of flow field information based on the first straightened blood vessel segment model and determining a second set of flow field information based on the second straightened blood vessel segment model, the first set of flow field information including prediction results at a first set of location points, the second set of flow field information including prediction results at a second set of location points, the first set of location points and the second set of location points including overlapping location points; and The at least one blood flow field information is obtained by weighted averaging the first set of flow field information and the second set of flow field information. The at least one blood flow field information includes the weighted average flow field information prediction results at the overlapping position points.

14. A computing device comprising: a memory, a processor, and a computer program stored on said memory, The processor is configured to execute the computer program to implement the steps of the method according to any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product comprising a computer program, wherein When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images