CN116245853A

CN116245853A - Fractional flow reserve determination method, fractional flow reserve determination device, electronic equipment and storage medium

Info

Publication number: CN116245853A
Application number: CN202310244822.3A
Authority: CN
Inventors: 左强; 尹思源; 王少康; 陈宽
Original assignee: Infervision Medical Technology Co Ltd
Current assignee: Infervision Medical Technology Co Ltd
Priority date: 2023-03-09
Filing date: 2023-03-09
Publication date: 2023-06-09

Abstract

The invention discloses a fractional flow reserve determining method, a fractional flow reserve determining device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a plurality of initial blood vessel images; determining a blood vessel centerline point based on the plurality of initial blood vessel images, and a blood vessel cross-sectional area and a flow coefficient corresponding to the blood vessel centerline point; and inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient into a score prediction model which is trained in advance to obtain the fractional flow reserve. According to the technical scheme, the fractional prediction model can realize fractional flow reserve prediction according to the blood vessel central line point and the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel central line point, and can effectively improve the accuracy of fractional flow reserve.

Description

Fractional flow reserve determination method, fractional flow reserve determination device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a fractional flow reserve determining method, a fractional flow reserve determining device, an electronic device, and a storage medium.

Background

Fractional flow reserve (fractional flow reserve, FFR) refers to the ratio of the maximum blood flow available from a current vessel to the maximum blood flow available from a normal vessel in the presence of a stenotic lesion in the coronary artery, and can be used to determine the severity of the lesion function.

Deep learning accomplishes classification or regression tasks by constructing a neural network and combining low-level features to form more abstract high-level features or attribute features to detect distributed representation features of the data. Current research on predicting hemodynamics through deep learning is still very limited. Limitations of these studies include: 1) Most research has focused on two-dimensional flow fields with limited application areas; 2) The sample resolution in the dataset is too low to represent a complex flow field distribution and geometry.

In the process of implementing the present invention, the inventor finds that at least the following technical problems exist in the prior art: the above prior art solutions have the problem of low fractional flow reserve accuracy.

Disclosure of Invention

The invention provides a fractional flow reserve determining method, a fractional flow reserve determining device, electronic equipment and a storage medium, so as to improve the accuracy of fractional flow reserve.

According to an aspect of the present invention, there is provided a fractional flow reserve determination method comprising:

acquiring a plurality of initial blood vessel images;

determining a blood vessel centerline point based on the plurality of initial blood vessel images, and a blood vessel cross-sectional area and a flow coefficient corresponding to the blood vessel centerline point;

and inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient into a score prediction model which is trained in advance to obtain the fractional flow reserve.

According to another aspect of the present invention, there is provided a fractional flow reserve determining apparatus comprising:

the image acquisition module is used for acquiring a plurality of initial blood vessel images;

the blood vessel center line point determining module is used for determining a blood vessel center line point based on the initial blood vessel images, and a blood vessel cross-section area and a flow coefficient corresponding to the blood vessel center line point;

and the blood flow reserve score determining module is used for inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient into a score prediction model which is trained in advance to obtain a blood flow reserve score.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor;

and a memory communicatively coupled to the at least one processor;

wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the fractional flow reserve determination method of any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement a fractional flow reserve determination method according to any one of the embodiments of the present invention when executed.

According to the technical scheme, the blood flow reserve score is obtained by acquiring a plurality of initial blood vessel images, and then determining the blood vessel central line point, the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel central line point based on the plurality of initial blood vessel images, and then inputting the determined blood vessel central line point, the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel central line point into the score prediction model trained in advance, and compared with the prior art, the score prediction model of the embodiment can effectively learn the flow field distribution and the geometric structure of the blood vessel, so that the accuracy of the predicted blood flow reserve score is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a fractional flow reserve determination method provided in accordance with a first embodiment of the present invention;

FIG. 2 is a flow chart of a fractional flow reserve determination method according to a second embodiment of the present invention;

FIG. 3 is a flow chart of a flow coefficient determination method according to a second embodiment of the present invention;

FIG. 4 is a flow chart of a fractional flow reserve determination method provided in accordance with a third embodiment of the present invention;

FIG. 5 is a flow chart of a score prediction model prediction process provided in accordance with a third embodiment of the present invention;

FIG. 6 is a flow chart of a fractional flow reserve determination method according to a fourth embodiment of the present invention;

fig. 7 is a schematic structural diagram of a fractional flow reserve determining device according to a fifth embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device implementing a fractional flow reserve determination method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a fractional flow reserve determination method according to a first embodiment of the present invention, where the method may be performed by fractional flow reserve determination device, which may be implemented in hardware and/or software, and the fractional flow reserve determination device may be configured in a computer terminal. As shown in fig. 1, the method includes:

s110, acquiring a plurality of initial blood vessel images.

In this embodiment, the initial blood vessel image refers to an image to be subjected to segmentation and midline extraction. By way of example, the initial vessel image may be medical image data, e.g., the initial vessel image may be digital imaging and communications in medicine (Digital Imaging and Communications in Medicine, DICOM) format, electronic computed tomography (computed tomography, CT), magnetic resonance imaging (Magnetic Resonance Imaging, MRI) or the like. Alternatively, the initial vessel image may be an image containing coronary arteries.

Specifically, a plurality of continuous initial blood vessel images may be obtained from a preset storage location of the electronic device, or a plurality of continuous initial blood vessel images may also be obtained from other devices or cloud connected to the electronic device, which is not limited herein.

S120, determining a blood vessel central line point based on the initial blood vessel images, and determining the blood vessel cross-sectional area and the flow coefficient corresponding to the blood vessel central line point.

In this embodiment, the centerline points of the blood vessel are points on a centerline of the blood vessel, and the centerline of the blood vessel may include a plurality of centerline points of the blood vessel. The cross-sectional area of a blood vessel refers to the area of the cross-section of the blood vessel corresponding to the centerline point of the blood vessel, and the cross-section of the blood vessel is perpendicular to the centerline of the blood vessel. The flow coefficient refers to an evaluation index of the flow at the blood vessel corresponding to the center line point of the blood vessel.

Specifically, a plurality of initial blood vessel images may be used as input data of a model, and input into a blood vessel segmentation model which is trained in advance, and the blood vessel segmentation model may predict and obtain a blood vessel segmentation result according to the initial blood vessel images and output the blood vessel segmentation result. Further, a blood vessel centerline is extracted from the blood vessel segmentation result, and then the blood vessel cross-sectional area and the flow coefficient corresponding to the blood vessel centerline point are obtained. The blood vessel segmentation result can be a three-dimensional blood vessel segmentation image, in other words, the three-dimensional distribution condition of the blood vessel can be checked through the blood vessel segmentation result. By way of example, the vessel segmentation result may be a three-dimensional model of a coronary tree or the like.

S130, inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient into a score prediction model which is trained in advance, and obtaining the fractional flow reserve.

In this embodiment, the score prediction model is a pre-trained network prediction model, and may be used to predict fractional flow reserve.

Specifically, the plurality of vessel centerline points, the vessel cross-sectional area corresponding to each vessel centerline point and the flow coefficient corresponding to each vessel centerline point may be used as input data of a model, and input into a score prediction model which is trained in advance, where the score prediction model may predict and obtain a fractional flow reserve according to the plurality of vessel centerline points, the vessel cross-sectional area corresponding to each vessel centerline point and the flow coefficient corresponding to each vessel centerline point, and output the fractional flow reserve.

Example two

Fig. 2 is a flowchart of a fractional flow reserve determination method according to a second embodiment of the present invention, where the method according to the present embodiment may be combined with each of the alternatives in the fractional flow reserve determination method according to the above embodiment. The fractional flow reserve determination method provided by the present embodiment is further optimized. Optionally, the determining a vessel centerline point based on the plurality of initial vessel images, and the vessel centerline point corresponds to a vessel cross-sectional area and a flow coefficient includes: inputting the initial blood vessel images into a blood vessel segmentation model which is trained in advance to obtain a blood vessel segmentation result; performing midline extraction on the blood vessel segmentation result to obtain a blood vessel midline, wherein the blood vessel midline comprises a plurality of blood vessel midline points; and determining the blood vessel cross-sectional area and the flow coefficient corresponding to each blood vessel centerline point.

As shown in fig. 2, the method includes:

s210, acquiring a plurality of initial blood vessel images.

S220, inputting the initial blood vessel images into a blood vessel segmentation model which is trained in advance, and obtaining a blood vessel segmentation result.

Specifically, a plurality of initial blood vessel images may be used as input data of a model, and input into a blood vessel segmentation model which is trained in advance, and the blood vessel segmentation model may predict and obtain a blood vessel segmentation result according to the initial blood vessel images and output the blood vessel segmentation result.

The training step of the blood vessel segmentation model comprises the following steps: acquiring an initial blood vessel sample image and a blood vessel segmentation labeling image corresponding to the initial blood vessel sample image; training the initial neural network model based on the initial blood vessel sample image and the blood vessel segmentation labeling image corresponding to the initial blood vessel sample image to obtain a blood vessel segmentation model.

For example, the vessel segmentation model may be trained beforehand from a large number of initial vessel sample images. In the trained neural network model, feature extraction is carried out on an initial blood vessel sample image in advance, model parameters in the neural network model are trained based on the extracted feature information, and the distance deviation between an output result of the model and a blood vessel segmentation labeling image is gradually reduced and tends to be stable by continuously adjusting the model parameters.

And S230, carrying out midline extraction on the blood vessel segmentation result to obtain a blood vessel midline, wherein the blood vessel midline comprises a plurality of blood vessel midline points.

Wherein the vessel centerline refers to a vessel centerline image, may include a plurality of vessel centerline points. Specifically, a series of morphological operations can be performed on the vessel segmentation result, and a smoothing algorithm is adopted to perform image smoothing, so as to obtain a vessel centerline image.

S240, determining the blood vessel cross-sectional area and the flow coefficient corresponding to each blood vessel centerline point.

In this embodiment, the cross-sectional area of the blood vessel corresponding to the centerline point of the blood vessel may be determined, the coronary inlet flow may be obtained, the coronary outlet flow may be determined based on the coronary inlet flow, and the flow coefficient corresponding to the centerline point of the blood vessel may be determined based on the coronary outlet flow.

The coronary inlet flow can be left coronary inlet flow and right coronary inlet flow, and can comprise left coronary blood flow distribution flow and right coronary blood flow distribution flow, and the coronary inlet flow can be obtained according to a statistical population average value.

Fig. 3 is a flowchart of a flow coefficient determining method according to the present embodiment. Specifically, the vessel cross-sectional area corresponding to the centerline point of the vessel can be obtained from the vessel segmentation result. In addition, the flow coefficient calculation process corresponding to the line point in the blood vessel comprises the following steps: distributing left crown and right crown inlet flow, and further determining crown outlet flow according to Murray law and the left crown and right crown inlet flow; further, the flow of the unknown blood vessel is calculated by the known coronary outlet flow from the tail end of the coronary to the blood vessel at the coronary inlet, so that the total flow at the inlet is obtained, and the flow coefficient corresponding to the central line point of the blood vessel in the coronary tree is obtained by normalizing the total flow at the inlet.

S250, inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient into a score prediction model which is trained in advance, and obtaining the fractional flow reserve.

According to the technical scheme, the multiple initial blood vessel images are input into the pre-trained blood vessel segmentation model to obtain the blood vessel segmentation result, the blood vessel segmentation result is further subjected to midline extraction to obtain the blood vessel midline, the blood vessel cross-section area and the flow coefficient corresponding to each blood vessel midline point are further determined, the acquisition of blood vessel midline data is realized, accurate input data is provided for model prediction, and the accuracy of blood flow reserve fraction is further improved.

Example III

Fig. 4 is a flowchart of a fractional flow reserve determination method according to a third embodiment of the present invention, where the method according to the present embodiment may be combined with each of the alternatives in the fractional flow reserve determination method according to the above embodiment. The fractional flow reserve determination method provided by the present embodiment is further optimized. Optionally, the inputting the blood vessel center line point, the blood vessel cross-section area corresponding to the blood vessel center line point, and the flow coefficient to a score prediction model trained in advance to obtain a fractional flow reserve, includes: carrying out sparse mapping on the blood vessel centerline points and the blood vessel cross-sectional areas and flow coefficients corresponding to the blood vessel centerline points to obtain blood vessel sparse mapping characteristics; inputting the vessel sparse mapping characteristic into the sparse segmentation network to obtain a vessel sparse segmentation characteristic; performing inverse sparse mapping on the vessel sparse segmentation features to obtain vessel original image space features; and inputting the spatial characteristics of the angiogram to a circulatory neural network to obtain fractional flow reserve.

As shown in fig. 4, the method includes:

s310, acquiring a plurality of initial blood vessel images.

S320, determining a blood vessel central line point based on the initial blood vessel images, and determining the blood vessel cross-sectional area and the flow coefficient corresponding to the blood vessel central line point.

S330, carrying out sparse mapping on the blood vessel centerline points, and the blood vessel cross-sectional areas and flow coefficients corresponding to the blood vessel centerline points to obtain blood vessel sparse mapping characteristics.

In this embodiment, the sparse mapping may be implemented through a hash mapping table, so as to obtain a vessel sparse mapping feature.

By way of example, the coordinates of the centerline points of the blood vessel, the cross-sectional areas of the blood vessel corresponding to the centerline points of the blood vessel, and the flow coefficients corresponding to the centerline points of the blood vessel are sparsely mapped by a pre-established hash map.

S340, inputting the vessel sparsification mapping characteristic into the sparse segmentation network to obtain a vessel sparse segmentation characteristic.

The sparse segmentation network is a neural network model for processing the sparse mapping characteristics of the blood vessels, and can be used for learning the flow field distribution and the geometric shape of the blood vessels.

The sparse segmentation network may be, for example, a sparse convolution network, and specifically, the vessel sparse mapping feature is input into the sparse convolution network to obtain a vessel sparse segmentation feature. It should be noted that the sparse convolution network can enable the coronary image to maintain higher resolution, so that flow field distribution and geometric shape of the coronary vessel model under high resolution are represented, and calculation amount of the model can be reduced due to sparsity of the sparse convolution network.

S350, performing inverse sparse mapping on the vessel sparse segmentation feature to obtain the vessel original image space feature.

Specifically, inverse sparsification mapping can be realized through a hash mapping table, so that the vessel sparse segmentation feature is mapped back to the original image space, and the vessel original image space feature is obtained.

S360, inputting the spatial characteristics of the angiograms to a circulatory neural network to obtain fractional flow reserve.

In this embodiment, a recurrent neural network may be used to capture the dependency between the centerline points in each vessel.

By way of example, the recurrent neural network may be a Long Short-Term Memory network (LSTM). Specifically, the spatial features of the angiograms can be input to a long-short term memory network to obtain fractional flow reserve.

It should be noted that the long-short-term memory network can control the transmission state through the gating state, so as to memorize the information which needs to be memorized for a long time and forget unimportant, and can be used for processing the data with long sequence change. For the fractional flow reserve prediction scenario of the present embodiment, fractional flow reserve between centerline points is associated. In addition, the loss weight of the blood vessel of the stenosis is increased when the circulatory neural network is trained, so that the circulatory neural network is more concerned about the change of the fractional flow reserve of the stenosis.

Fig. 5 is a flowchart of a score prediction model prediction process according to the present embodiment. Specifically, after the coronary artery midline is extracted, the coordinates of the vascular midline point, the vascular cross-section area corresponding to the vascular midline point and the flow coefficient are subjected to sparse mapping to obtain a vascular sparse mapping characteristic, and the vascular sparse mapping characteristic is input into a sparse segmentation network to obtain a vascular sparse segmentation characteristic; inverse sparse mapping is carried out on the vessel sparse segmentation characteristics to obtain vessel original image space characteristics; the spatial features of the angiogram are input to the LSTM network to obtain fractional flow reserve.

Based on the above embodiments, optionally, the training process of the score prediction model includes: obtaining blood vessel midline sample data and a blood flow reserve target fraction corresponding to the blood vessel midline sample data, wherein the blood vessel midline sample data comprises blood vessel midline sample points, and blood vessel cross-section areas and flow coefficients corresponding to the blood vessel midline sample points; training an initial neural network model based on blood vessel midline sample data and a blood flow reserve target score corresponding to the blood vessel midline sample data to obtain a score prediction model.

In the process of training the score prediction model, the characteristic extraction is carried out on the blood vessel centerline sample data in advance, model parameters in the neural network model are trained based on the extracted characteristic information, and the distance deviation between the output result of the model and the blood flow reserve target score is gradually reduced and tends to be stable by continuously adjusting the model parameters; the model loss function may be a mean square error (Mean Square Error, MSE) loss function, which may be used to calculate the loss between the fractional flow reserve predicted by each centerline point and the target fractional flow reserve, and thus back-propagate updated network parameters.

In some embodiments, after the fractional flow reserve is obtained, the coronary artery may be rendered from the fractional flow reserve and the distance of each midline point to the coronary artery surface to obtain a coronary hemodynamic result.

According to the technical scheme, the blood vessel center line point and the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel center line point are determined based on the initial blood vessel images, the blood vessel center line point and the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel center line point are subjected to sparse mapping, so that the blood vessel sparse mapping characteristic is obtained, the blood vessel sparse mapping characteristic is input into a sparse segmentation network, the blood vessel sparse segmentation characteristic is obtained, the blood vessel sparse segmentation characteristic is subjected to inverse sparse mapping, the space characteristic of a blood vessel original image is obtained, the space characteristic of the blood vessel original image is input into a circulating neural network, and the blood flow reserve score is obtained.

Example IV

Fig. 6 is a flowchart of a fractional flow reserve determination method according to a fourth embodiment of the present invention, and the method according to the present embodiment may be combined with each of the alternatives in the fractional flow reserve determination method according to the above embodiment. The fractional flow reserve determination method provided by the present embodiment is further optimized. Optionally, the score prediction model comprises a sparse point cloud segmentation model and a cyclic neural network; correspondingly, the step of inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient to a score prediction model which is trained in advance to obtain a blood flow reserve score comprises the following steps: carrying out sparse mapping on the blood vessel centerline points and the blood vessel cross-sectional areas and flow coefficients corresponding to the blood vessel centerline points to obtain blood vessel sparse mapping characteristics; inputting the vessel sparse mapping feature into the sparse point cloud segmentation model to obtain a vessel sparse segmentation feature; performing inverse sparse mapping on the vessel sparse segmentation features to obtain vessel original image space features; and inputting the spatial characteristics of the angiogram to a circulatory neural network to obtain fractional flow reserve.

As shown in fig. 6, the method includes:

s410, acquiring a plurality of initial blood vessel images.

S420, determining a blood vessel central line point based on the initial blood vessel images, and determining the blood vessel cross-sectional area and the flow coefficient corresponding to the blood vessel central line point.

S430, performing sparse mapping on the blood vessel centerline points, and the blood vessel cross-sectional areas and flow coefficients corresponding to the blood vessel centerline points to obtain blood vessel sparse mapping characteristics.

S440, inputting the vessel sparsification mapping characteristic into the sparse point cloud segmentation model to obtain a vessel sparse segmentation characteristic.

S450, performing inverse sparse mapping on the vessel sparse segmentation feature to obtain the vessel original image space feature.

S460, inputting the spatial characteristics of the angiogram to a circulatory neural network to obtain fractional flow reserve.

In this embodiment, the sparse point cloud segmentation model may be used to segment the vessel sparse mapping feature, and may be obtained after training based on the vessel sparse mapping sample feature and the vessel sparse segmentation sample feature corresponding to the vessel sparse mapping sample feature.

According to the technical scheme, the blood vessel center line point and the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel center line point are determined based on the initial blood vessel images, the blood vessel center line point and the blood vessel cross-section area and the flow coefficient corresponding to the blood vessel center line point are subjected to sparse mapping, the blood vessel sparse mapping characteristic is obtained, the blood vessel sparse mapping characteristic is input into a sparse point cloud segmentation model, the blood vessel sparse segmentation characteristic is obtained, the blood vessel sparse segmentation characteristic is subjected to inverse sparse mapping, the space characteristic of a blood vessel artwork is obtained, the space characteristic of the blood vessel artwork is input into a circulating neural network, and the blood flow reserve score is obtained.

Example five

Fig. 7 is a schematic structural diagram of a fractional flow reserve determining device according to a fifth embodiment of the present invention. As shown in fig. 7, the apparatus includes:

an image acquisition module 510 for acquiring a plurality of initial blood vessel images;

a vessel centerline point determining module 520, configured to determine a vessel centerline point based on the plurality of initial vessel images, and a vessel cross-sectional area and a flow coefficient corresponding to the vessel centerline point;

the fractional flow reserve determining module 530 is configured to input the vascular centerline point, and a vascular cross-sectional area and a flow coefficient corresponding to the vascular centerline point, to a score prediction model trained in advance, to obtain fractional flow reserve.

In some alternative embodiments, the vessel centerline point determination module 520 includes:

the blood vessel segmentation result determining unit is used for inputting the initial blood vessel images into a blood vessel segmentation model which is trained in advance to obtain a blood vessel segmentation result;

a blood vessel midline extraction unit, configured to perform midline extraction on the blood vessel segmentation result to obtain a blood vessel midline, where the blood vessel midline includes a plurality of blood vessel midline points;

and the midline information determining unit is used for determining the blood vessel cross-sectional area and the flow coefficient corresponding to each blood vessel midline point.

In some alternative embodiments, the centerline information determination unit is specifically configured to:

determining the cross-sectional area of the blood vessel corresponding to the centerline point of the blood vessel;

acquiring a coronary inlet flow, and determining a coronary outlet flow based on the coronary inlet flow;

and determining a flow coefficient corresponding to the central line point of the blood vessel based on the coronary outlet flow.

In some alternative embodiments, the score prediction model includes a sparse segmentation network for learning flow field distribution and geometry of blood vessels, and a recurrent neural network for capturing dependencies between centerline points of each of the blood vessels.

In some alternative embodiments, fractional flow reserve determination module 530 is specifically configured to:

carrying out sparse mapping on the blood vessel centerline points and the blood vessel cross-sectional areas and flow coefficients corresponding to the blood vessel centerline points to obtain blood vessel sparse mapping characteristics;

inputting the vessel sparse mapping characteristic into the sparse segmentation network to obtain a vessel sparse segmentation characteristic;

performing inverse sparse mapping on the vessel sparse segmentation features to obtain vessel original image space features;

and inputting the spatial characteristics of the angiogram to a circulatory neural network to obtain fractional flow reserve.

In some alternative embodiments, the training process of the score prediction model includes:

obtaining blood vessel midline sample data and a blood flow reserve target fraction corresponding to the blood vessel midline sample data, wherein the blood vessel midline sample data comprises blood vessel midline sample points, and blood vessel cross-section areas and flow coefficients corresponding to the blood vessel midline sample points;

training an initial neural network model based on blood vessel midline sample data and a blood flow reserve target score corresponding to the blood vessel midline sample data to obtain a score prediction model.

In some optional embodiments, the score prediction model comprises a sparse point cloud segmentation model and a recurrent neural network; the fractional flow reserve determination module 530 is further configured to:

inputting the vessel sparse mapping feature into the sparse point cloud segmentation model to obtain a vessel sparse segmentation feature;

The fractional flow reserve determining device provided by the embodiment of the invention can execute the fractional flow reserve determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

Example six

Fig. 8 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., helmets, eyeglasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An I/O interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as fractional flow reserve determination methods, which include:

acquiring a plurality of initial blood vessel images;

In some embodiments, the fractional flow reserve determination method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the fractional flow reserve determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fractional flow reserve determination method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A fractional flow reserve determination method, comprising:

acquiring a plurality of initial blood vessel images;

2. The method of claim 1, wherein the determining a vessel centerline point based on the plurality of initial vessel images and the vessel centerline point corresponds to a vessel cross-sectional area and a flow coefficient comprises:

inputting the initial blood vessel images into a blood vessel segmentation model which is trained in advance to obtain a blood vessel segmentation result;

performing midline extraction on the blood vessel segmentation result to obtain a blood vessel midline, wherein the blood vessel midline comprises a plurality of blood vessel midline points;

and determining the blood vessel cross-sectional area and the flow coefficient corresponding to each blood vessel centerline point.

3. The method of claim 2, wherein determining the vessel cross-sectional area and flow coefficient corresponding to the vessel centerline point comprises:

4. The method of claim 1, wherein the fractional prediction model comprises a sparse segmentation network for learning flow field distribution and geometry of blood vessels and a recurrent neural network for capturing dependencies between centerline points of each of the blood vessels.

5. The method of claim 4, wherein inputting the vessel centerline point, and the vessel cross-sectional area and flow coefficient corresponding to the vessel centerline point, to a pre-trained score prediction model to obtain a fractional flow reserve comprises:

6. The method of claim 1, wherein the training process of the score prediction model comprises:

7. The method of claim 1, wherein the score prediction model comprises a sparse point cloud segmentation model and a recurrent neural network;

correspondingly, the step of inputting the blood vessel central line point, the blood vessel cross-section area corresponding to the blood vessel central line point and the flow coefficient to a score prediction model which is trained in advance to obtain a blood flow reserve score comprises the following steps:

8. A fractional flow reserve determination device, comprising:

9. An electronic device, the electronic device comprising:

at least one processor;

and a memory communicatively coupled to the at least one processor;

wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the fractional flow reserve determination method of any one of claims 1-7.

10. A computer readable storage medium storing computer instructions for causing a processor to perform the fractional flow reserve determination method of any one of claims 1-7.