A vascular occlusion site determination system

Abstract

Some embodiments of the present specification provide a blood vessel occlusion position determination system. The system includes a processor that can be used to perform the following method: acquiring an image of a target object; determining an ischemic region in the image; and determining an occlusion position of a blood vessel of the target object based on the ischemic region.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of medical technology, and particularly relates to a blood vessel occlusion position determination system. BACKGROUND

[0002] In recent years, medical imaging is widely used for diagnosis and treatment of various medical conditions. However, for some brain diseases (for example, acute cerebral infarction), it is necessary to view the current blood vessel state of the patient through blood vessel imaging in order to determine the brain blood vessels that cause insufficient blood supply. Since blood vessel imaging has certain requirements for medical equipment, hospital level, and patient physical condition, in some cases, it is necessary to use computed tomography (CT), diffusion weighted imaging (DWI), and other scanning methods to determine the brain blood vessels that cause insufficient blood supply. Therefore, it is necessary to provide a system capable of determining the blood vessel occlusion position according to CT, DWI, and other brain images. SUMMARY

[0003] One of the embodiments of the present specification provides a blood vessel occlusion position determination system. The system can include a processor, which can be used to execute the following method: obtaining an image of a target object; determining an ischemic area in the image; determining an occlusion position of a blood vessel of the target object based on the ischemic area.

[0004] In some embodiments, the determining the occlusion position of the blood vessel of the target object based on the ischemic area can include: determining a blood supply area of the blood vessel based on the image; and determining the occlusion position of the blood vessel based on the ischemic area and the blood supply area.

[0005] In some embodiments, the determining the occlusion position of the blood vessel based on the ischemic area and the blood supply area can include: inputting the ischemic area and the blood supply area into a trained first identification model; and determining the occlusion position of the blood vessel based on an output of the first identification model.

[0006] In some embodiments, the determining the occlusion position of the blood vessel based on the ischemic area and the blood supply area can include: determining whether the blood supply area is in an ischemic state based on the ischemic area; and determining the occlusion position of the blood vessel based on the blood supply area in the ischemic state.

[0007] In some embodiments, the determining the occlusion position of the blood vessel based on the blood supply area in the ischemic state can include: determining the occlusion position of the blood vessel based on the blood supply area in the ischemic state and a mapping relationship.

[0008] In some embodiments, the determining the occlusion position of the blood vessel based on the ischemic region can include: inputting the ischemic region into a third trained identification model; and determining the occlusion position of the blood vessel based on an output of the third trained identification model.

[0009] In some embodiments, the determining the occlusion position of the blood vessel based on the ischemic region can include: inputting the ischemic region into a third trained identification model; and determining the occlusion position of the blood vessel based on an output of the third trained identification model.

[0010] In some embodiments, the target object can include a brain, the image can include a brain image, and the blood vessel can include a brain blood vessel.

[0011] One of the embodiments of the present specification provides a blood vessel occlusion position determination system. The system can include an image acquisition module, an ischemic region determination module, and an occlusion position determination module. The image acquisition module can be configured to acquire an image of a target object. The ischemic region determination module can be configured to determine an ischemic region in the image. The occlusion position determination module can be configured to determine an occlusion position of a blood vessel of the target object based on the ischemic region.

[0012] One of the embodiments of the present specification provides a computer readable storage medium storing computer instructions, when a computer reads the computer instructions in the storage medium, the computer executes a method in a blood vessel occlusion position determination system. BRIEF DESCRIPTION OF DRAWINGS

[0013] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, in which:

[0014] Figure 1 FIG. 1 is a schematic diagram of an application scenario of a blood vessel occlusion position determination system according to some embodiments of the present specification;

[0015] Figure 2 FIG. 2 is a module diagram of a blood vessel occlusion position determination system according to some embodiments of the present specification;

[0016] Figure 3 FIG. 3 is an exemplary flowchart of determining an occlusion position of a blood vessel according to some embodiments of the present specification;

[0017] Figure 4 FIG. 4 is a schematic diagram of an exemplary image according to some embodiments of the present specification;

[0018] Figure 5is a schematic diagram of an exemplary procedure for determining an occlusion location of a blood vessel according to some embodiments of the present specification;

[0019] Figure 6A is an exemplary flow chart for determining an occlusion location of a blood vessel according to some embodiments of the present specification;

[0020] Figure 6B is a schematic diagram of an exemplary procedure for determining an occlusion location of a blood vessel according to some embodiments of the present specification;

[0021] Figure 7 is a schematic diagram of an exemplary procedure for determining an occlusion location of a blood vessel according to some embodiments of the present specification;

[0022] Figure 8 is an exemplary schematic diagram of an occlusion location of a blood vessel according to some embodiments of the present specification. DETAILED DESCRIPTION

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, without paying creative labor, the present specification can also be applied to other similar scenarios according to these drawings. Unless it is clear from the language context or otherwise indicated, the same reference numbers in the drawings represent the same structure or operation.

[0024] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, sections or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0025] As shown in the specification and claims, unless the context clearly indicates otherwise, the words "one", "a", "an", and / or "the" do not refer to the singular, but can also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements.

[0026] Flowcharts are used in the present specification to illustrate the operations performed by the system according to the embodiments of the present specification. It should be understood that the preceding or subsequent operations are not necessarily performed in sequence. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can be added to these processes, or one or more steps of the operation can be removed from these processes.

[0027] Figure 1 is a schematic diagram of an application scenario of a blood vessel occlusion position determination system according to some embodiments of the present specification.

[0028] As shown in Figure 1 some embodiments, the blood vessel occlusion position determination system 100 can include an imaging device 110, a network 120, a terminal device 130, a processing device 140, and a storage device 150. The plurality of components in the blood vessel occlusion position determination system 100 can be connected to each other through the network 120. For example, the imaging device 110 and the terminal device 130 can be connected or communicate through the network 120. For another example, the imaging device 110 and the processing device 140 can be connected or communicate through the network 120. In some embodiments, the connection between the components in the blood vessel occlusion position determination system 100 can be varied. For example, the terminal device 130 can be directly connected to the processing device 140.

[0029] The imaging device 110 can be used to scan a target object in a detection area or a scanning area to obtain scanning data of the target object. In some embodiments, the target object can include a biological object and / or a non-biological object. For example, the target object can be a living or non-living organic and / or inorganic substance. For another example, the target object can include a brain.

[0030] In some embodiments, the imaging device 110 can be a non-invasive imaging device for disease diagnosis or research purposes. For example, the imaging device 110 can include a single modality scanner and / or a multi-modality scanner. The single modality scanner can include, for example, an ultrasound scanner, an X-ray scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, an ultrasound examination instrument, a positron emission computed tomography (PET) scanner, an optical coherence tomography (OCT) scanner, an ultrasound (US) scanner, an intravascular ultrasound (IVUS) scanner, a near-infrared spectroscopy (NIRS) scanner, a far-infrared (FIR) scanner, or the like, or any combination thereof. The multi-modality scanner can include, for example, an X-ray imaging-magnetic resonance imaging (X-ray-MRI) scanner, a positron emission tomography-X-ray imaging (PET-X-ray) scanner, a single photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PET-CT) scanner, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanner, or the like. The scanners provided above are for illustrative purposes only and are not intended to limit the scope of the present specification.

[0031] The network 120 can include any suitable network capable of facilitating the exchange of information and / or data of the vascular occlusion location determination system 100. In some embodiments, at least one component of the vascular occlusion location determination system 100 (e.g., the imaging device 110, the terminal device 130, the processing device 140, the storage device 150) can exchange information and / or data with at least one other component of the vascular occlusion location determination system 100 through the network 120. For example, the processing device 140 can obtain scan data or scan images of a target subject from the imaging device 110 through the network 120. The network 120 can include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN)), a wired network, a wireless network (e.g., an 802.11 network, a Wi-Fi network), a frame relay network, a virtual private network (VPN), a satellite network, a telephone network, routers, hubs, switches, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, ZigBee networks, near-field communication (NFC) networks, and / or the like, or any combination thereof. In some embodiments, the network 120 can include at least one network access point. For example, the network 120 can include wired and / or wireless network access points, such as base stations and / or Internet exchange points, through which at least one component of the vascular occlusion location determination system 100 can connect to the network 120 to exchange data and / or information.

[0032] The terminal device 130 can be in communication and / or connection with the imaging device 110, the processing device 140, and / or the storage device 150. For example, a user can interact with the imaging device 110 through the terminal device 130 to control one or more components of the imaging device 110. In some embodiments, the terminal device 130 can include a mobile device 131, a tablet computer 132, a laptop computer 133, and / or the like, or any combination thereof. For example, the mobile device 131 can include a mobile control handle, a personal digital assistant (PDA), a smartphone, and / or the like, or any combination thereof.

[0033] The processing device 140 can process data and / or information obtained from the imaging device 110, the at least one terminal device 130, the storage device 150, or other components of the vessel occlusion location determination system 100. For example, the processing device 140 can acquire an image of a target subject from the imaging device 110. For another example, the processing device 140 can determine an ischemic region in the image. For yet another example, the processing device 140 can determine an occlusion location of a blood vessel of the target subject based on the ischemic region. In some embodiments, the processing device 140 can be a single server or a group of servers. The group of servers can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. For example, the processing device 140 can access information and / or data from the imaging device 110, the at least one terminal device 130, and / or the storage device 150 through the network 120. For another example, the processing device 140 can be directly connected to the imaging device 110, the at least one terminal device 130, and / or the storage device 150 to access information and / or data. In some embodiments, the processing device 140 can be implemented on a cloud platform. For example, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof.

[0034] In some embodiments, the processing device 140 can include one or more processors (e.g., a single-chip processor or a multi-chip processor). For example only, the processing device 140 can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction-set processor (ASIP), a graphics processing unit (GPU), a physics processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof. In some embodiments, the processing device 140 can be part of the imaging device 110 or the terminal device 130. For example, the processing device 140 can be integrated within the imaging device 110 for acquiring an image of a target subject, determining an ischemic region in the image, and determining an occlusion location of a blood vessel of the target subject based on the ischemic region, etc.

[0035] The storage device 150 can store data, instructions, and / or any other information. For example, the storage device 150 can store scan images (e.g., images of target objects) obtained by the imaging device 110 and information related thereto, etc. In some embodiments, the storage device 150 can store data obtained from the imaging device 110, the at least one terminal device 130, and / or the processing device 140. In some embodiments, the storage device 150 can store data and / or instructions used by the processing device 140 to perform or use to complete the exemplary methods described in this specification. In some embodiments, the storage device 150 can include a mass storage, a removable storage, a volatile read / write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 150 can be implemented on a cloud platform.

[0036] In some embodiments, the storage device 150 can be connected to the network 120 to communicate with at least one other component (e.g., the imaging device 110, the at least one terminal device 130, the processing device 140) in the vascular occlusion location determination system 100. At least one component in the vascular occlusion location determination system 100 can access data (e.g., target images of target objects, the first identification model, the second identification model, the third identification model, etc.) stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 can be part of the processing device 140.

[0037] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those of ordinary skill in the art under the guidance of the content of this specification. The features, structures, methods, and other characteristics of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the storage device 150 can be a data storage device including a cloud computing platform (e.g., public cloud, private cloud, community and hybrid cloud, etc.). However, these changes and modifications will not depart from the scope of this specification.

[0038] Figure 2 is a block diagram of a vascular occlusion location determination system according to some embodiments of the present specification.

[0039] As Figure 2 shown, in some embodiments, the vascular occlusion location determination system 200 can include an image acquisition module 210, an ischemic region determination module 220, and an occlusion location determination module 230. In some embodiments, the functions corresponding to the vascular occlusion location determination system 200 can be implemented by the processing device 140.

[0040] Image acquisition module 210 can be used to acquire an image of a target object. The target object may include the brain, and the image may include a brain image. For more information on image acquisition, please refer to [link to relevant documentation]. Figure 3 Step 310 and its related description.

[0041] The ischemic region determination module 220 can be used to determine ischemic regions in an image. An ischemic region can refer to a region on the image corresponding to an area with insufficient blood supply to the target object. In some embodiments, the ischemic region may exclude old ischemic regions. More information on ischemic region determination can be found in [reference needed]. Figure 3 Step 320 and its related description.

[0042] The occlusion location determination module 230 can be used to determine the occlusion location of a blood vessel in a target object based on an ischemic region. The blood vessel may include cerebral blood vessels. In some embodiments, the occlusion location determination module 230 can determine the blood supply region of the blood vessel based on an image, and determine the occlusion location of the blood vessel based on the ischemic region and the blood supply region. For example, the occlusion location determination module 230 can input the ischemic region and the blood supply region into a trained first recognition model, and determine the occlusion location of the blood vessel based on the output of the first recognition model. In some embodiments, the occlusion location determination module 230 can determine whether the blood supply region is in an ischemic state based on the ischemic region; and determine the occlusion location of the blood vessel based on the blood supply region in an ischemic state. For example, the occlusion location determination module 230 can determine the occlusion location of the blood vessel based on the blood supply region in an ischemic state and a mapping relationship, wherein the mapping relationship reflects the correspondence between the blood supply region in an ischemic state and the occlusion location of the blood vessel. For example, the occlusion location determination module 230 can input the ischemic blood supply area into a trained second recognition model and determine the occlusion location of the blood vessel based on the output of the second recognition model. In some embodiments, the occlusion location determination module 230 can input the ischemic area into a trained third recognition model and determine the occlusion location of the blood vessel based on the output of the third recognition model. More information on the occlusion location of blood vessels can be found in [reference needed]. Figure 3 Step 330 and its related description.

[0043] It should be understood that Figure 2 The illustrated system 200 for determining the location of vascular occlusion and its modules can be implemented in various ways, such as by hardware, software, or a combination of both. The system and its modules described herein can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field-programmable gate arrays or programmable logic devices, but also by software, for example, executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0044] It is to be noted that the above description of the vessel occlusion site determination system 200 and its modules is for convenience of description only and is not intended to limit the scope of the present specification to the embodiments shown. It is to be understood that, for those skilled in the art, after understanding the principles of the system, various modules can be combined in any manner or connected with other modules to form subsystems without departing from the principles.

[0045] Figure 3 is an exemplary flowchart of determining a vessel occlusion site according to some embodiments of the present specification. In some embodiments, the flow 300 can be performed by the processing device 140 or the vessel occlusion site determination system 200. For example, the flow 300 can be stored in the form of a program or instructions in a storage device (e.g., a storage unit of the processing device 140, the storage device 150), and when a processor or Figure 2 executes the program or instructions, the flow 300 can be implemented. In some embodiments, the flow 300 can utilize one or more additional operations not described below and / or be completed without one or more of the operations discussed below. In addition, the order of the operations as shown is not limiting. Figure 3

[0046] At step 310, an image of a target object is acquired. In some embodiments, this step 310 can be performed by the processing device 140 or the vessel occlusion site determination system 200 (e.g., the image acquisition module 210).

[0047] In some embodiments, the target object can include a biological object and / or a non-biological object. For example, the target object can be a living or non-living organic and / or inorganic matter. For another example, the target object can include a portion of a patient, an organ, and / or a tissue. As an example only, the target object can include a brain of a patient.

[0048] The image can refer to an image containing the target object. For example, the target object is a brain, the image can include a brain image.

[0049] In some embodiments, the image can include a two-dimensional (2D) image, a three-dimensional (3D) image, a four-dimensional (4D) image (e.g., a time series of 3D images), or the like or any combination thereof. In some embodiments, the image can include a CT image, a diffusion-weighted imaging (DWI) image, an MR image, a PET image, a SPECT image, an ultrasound image, an X-ray image, or the like or any combination thereof.

[0050] ​In some embodiments, the image acquisition module 210 can acquire imaging data of the target subject from an imaging device (e.g., the imaging device 110) and determine the image based on the imaging data. In some embodiments, the image acquisition module 210 can also perform correction (e.g., random correction, detector normalization, scatter correction, attenuation correction, etc.) or pre-processing operation (e.g., resizing, image resampling, image normalization, etc.) on the original image determined based on the original imaging data to determine the image. In some embodiments, the image acquisition module 210 can determine the image based on the imaging data by an image reconstruction algorithm. Taking a CT image as an example, exemplary CT image reconstruction algorithms can include back-projection algorithm, iterative reconstruction algorithm, analytical method (e.g., filtered back-projection algorithm or Fourier transform algorithm), etc. In some embodiments, the image acquisition module 210 can acquire a pre-stored image from a storage device (e.g., the storage device 150) or an external storage device (e.g., a medical image database).

[0051] At step 320, ischemic regions in the image are determined. In some embodiments, this step 320 can be performed by the processing device 140 or the vessel occlusion location determination system 200 (e.g., the ischemic region determination module 220).

[0052] An ischemic region can refer to a region on the image corresponding to a region of insufficient blood supply of the target subject. By way of example only, Figure 4 is a schematic diagram of exemplary images according to some embodiments of the present disclosure. As shown in Figure 4 column A is a schematic diagram of occlusion locations of blood vessels of the brain, column B is a schematic diagram of a corresponding surface of the brain, and column C is a corresponding CT image of the brain. The regions 431, 432, 433, 434, and 435 represented by the dashed lines in the image of column C are ischemic regions. In some embodiments, the ischemic regions can include all ischemic regions of the target subject involved in the image.

[0053] In some embodiments, the processing device 140 can determine the ischemic region in the image using image recognition techniques (e.g., image segmentation techniques, machine learning models, etc.). For example, the processing device 140 can process based on image segmentation techniques to determine the ischemic region in the image. Exemplary image segmentation techniques can include region-based segmentation, edge-based segmentation, wavelet transform segmentation, mathematical morphology segmentation, artificial neural network-based segmentation, genetic algorithm-based segmentation, etc., or any combination thereof. For another example, the processing device 140 can process the image based on a trained machine learning model (which can also be referred to as an ischemic region determination model). Exemplary machine learning models can include Vnet, Unet, etc. models. In some embodiments, the processing device 140 can call the ischemic region determination model from a storage device (e.g., the terminal device 130, the storage device 150, or any other storage device). For example, the ischemic region determination model can be determined by training a machine learning model based on a plurality of training samples offline using the processing device 140 or a processing device other than the processing device 140. The ischemic region determination model can be stored in the terminal device 130, the storage device 150, or any other storage device. For example, the processing device 140 can call the ischemic region determination model from the terminal device 130, the storage device 150, or any other storage device. In some embodiments, the processing device 140 can input the image of the target object into the ischemic region determination model. The ischemic region determination model can generate an output result. The output result of the ischemic region determination model can include an image in which the ischemic region is recognized (or marked, or segmented).

[0054] In some embodiments, the method of determining the ischemic region in the image can also include other manners, which are not limited in the present specification.

[0055] In some embodiments, the ischemic region can not include a previous ischemic region. The previous ischemic region can refer to an ischemic region that has been determined in a previous detection. For example, before determining the ischemic region, the processing device 140 can call the previous ischemic region of the target object from a storage device (e.g., the terminal device 130, the storage device 150, or any other storage device). When determining the ischemic region, the processing device 140 can not process the region in the image corresponding to the previous ischemic region. For another example, after determining the ischemic region, the processing device 140 can call the previous ischemic region of the target object from a storage device (e.g., the terminal device 130, the storage device 150, or any other storage device), delete the part of the ischemic region overlapping with the previous ischemic region, and retain the part of the ischemic region not overlapping with the previous ischemic region as the ischemic region.

[0056] In some embodiments, the processing device 140 can determine the ischemic region and the old ischemic region in the image directly using image recognition techniques. For example, when training the ischemic region determination model, each training sample can further include a difference between the ischemic region and the old ischemic region. The difference can embody the distinction between the ischemic region and the old ischemic region in various dimensions or aspects (e.g., spatial position, grayscale value, gradient value, resolution, brightness, etc.) in the image. The trained ischemic region determination model can be stored in the terminal device 130, the storage device 150, or any other storage device. In some embodiments, the processing device 140 can input the image of the target object into the ischemic region determination model. The ischemic region determination model can generate an output result. The output result of the ischemic region determination model can include an image in which the ischemic region is recognized (or marked, or segmented) or an image with the ischemic region and the old ischemic region.

[0057] At step 330, based on the ischemic region, an occlusion position of a blood vessel of the target object is determined. In some embodiments, this step 330 can be performed by the processing device 140 or the blood vessel occlusion position determination system 200 (e.g., the occlusion position determination module 230).

[0058] In some embodiments, the blood vessel can include a brain blood vessel. For example, the exemplary blood vessel can include the anterior cerebral artery, the middle cerebral artery, the posterior cerebral artery, the superior cerebellar artery, the inferior posterior cerebellar artery, the inferior anterior cerebellar artery, the vertebral-basilar artery, etc., or any combination thereof.

[0059] In some embodiments, the occlusion of the blood vessel can refer to the formation of a local thrombus in the blood vessel due to various factors (e.g., hypertension, coronary heart disease, diabetes, overweight, hyperlipidemia, fatty meat, family history, etc.), resulting in stenosis or complete occlusion of the blood vessel. The occlusion position of the blood vessel can refer to the position and / or name of the site where the occlusion occurs in the blood vessel. For example, the occlusion position of the blood vessel can include the anterior cerebral artery main region 411, the anterior cerebral artery upper region 412, the anterior cerebral artery lateral fissure region 413, the anterior cerebral artery branch region 414, and the anterior cerebral artery lower branch region 415 as shown by the dashed lines in column A of the image in FIG. 11. In some embodiments, the occlusion position can include the occlusion positions involved by all blood vessels of the target object. Figure 4

[0060] ​In some embodiments, the processing device 140 can determine the blood supply area of one or more blood vessels (e.g., all blood vessels) based on the image. The blood supply area can be one-to-one corresponding to the brain blood vessels. That is, different blood vessels of the brain can correspond to different blood supply areas. Exemplary blood supply areas can include the anterior cerebral artery area, the middle cerebral artery area, the posterior cerebral artery area, the superior cerebellar artery area, the inferior posterior cerebellar artery area, the inferior anterior cerebellar artery area, the vertebrobasilar artery area, etc., or any combination thereof. For example only, the anterior cerebral artery can correspond to the anterior cerebral artery area, the middle cerebral artery can correspond to the middle cerebral artery area, the posterior cerebral artery can correspond to the posterior cerebral artery area, the superior cerebellar artery can correspond to the superior cerebellar artery area, the inferior posterior cerebellar artery can correspond to the inferior posterior cerebellar artery area, the inferior anterior cerebellar artery can correspond to the inferior anterior cerebellar artery area, and the vertebrobasilar artery can correspond to the vertebrobasilar artery area. In some embodiments, the blood supply area can include the blood supply area involved by all blood vessels of the target subject.

[0061] In some embodiments, the processing device 140 can determine the blood supply area of the blood vessels by a registration method. For example, the processing device 140 can establish a standard template. In the standard template, each blood vessel of the brain has a corresponding blood supply area. The standard template can be stored in the terminal device 130, the storage device 150, or any other storage device. The processing device 140 can call the standard template from the terminal device 130, the storage device 150, or any other storage device. In some embodiments, the processing device 140 can match the image of the target subject with the standard template, thereby determining the blood supply area of the blood vessels. For example, by matching the image of the target subject with the standard template, the processing device 140 can determine the blood supply area corresponding to each blood vessel of the brain on the image of the target subject.

[0062] In some embodiments, the processing device 140 can determine the blood supply area of the blood vessels using image recognition techniques (e.g., image segmentation techniques, machine learning models, etc.). The manner of determining the blood supply area of the blood vessels using image recognition techniques is similar to the manner of determining the ischemic area using image recognition techniques, which will not be described here.

[0063] In some embodiments, the processing device 140 can determine the occlusion position of the blood vessels based on the ischemic area and the blood supply area.

[0064] For example, the processing device 140 can input the ischemic area and the blood supply area into a trained first recognition model, and determine the occlusion position of the blood vessels based on the output of the first recognition model. For more information about the first recognition model, see Figure 5 and the related description thereof.

[0065] For example, the processing device 140 can determine whether the blood supply area is in ischemic state based on the ischemic area. Further, the processing device 140 can determine the occlusion position of the blood vessel based on the blood supply area in ischemic state. For example, the processing device 140 can determine the occlusion position of the blood vessel based on the blood supply area in ischemic state and the mapping relationship. For another example, the processing device 140 can input the blood supply area in ischemic state into the trained second identification model, and determine the occlusion position of the blood vessel based on the output of the second identification model. For more information about determining the occlusion position of the blood vessel based on the blood supply area in ischemic state, see Figure 6A , Figure 6B and the related description.

[0066] In some embodiments, the processing device 140 can input the ischemic area into the trained third identification model, and determine the occlusion position of the blood vessel based on the output of the third identification model. For more information about the third identification model, see Figure 7 and the related description.

[0067] In some embodiments, the processing device 140 can output the occlusion position of the blood vessel. For example, the processing device 140 can send the occlusion position of the blood vessel to an output device (e.g., a display, a printer, a plotter, an image output system, a voice output system, a magnetic recording device, etc.) in the form of an image, text, sound (e.g., voice broadcast), etc. In some embodiments, the output image can be a two-dimensional image, a three-dimensional image, etc. Different occlusion positions can be represented by different legends. For example only, Figure 8 is a schematic diagram of an exemplary occlusion position of a blood vessel according to some embodiments of the present specification. As shown in Figure 8 , the occlusion position of the blood vessel is represented by different legends as M1 pre-bifurcation segment, M1 post-bifurcation segment, M2 segment, M3 segment, and M4 segment, respectively. The three-dimensional image can simulate the occlusion position of the blood vessel, thereby intuitively showing the occlusion position of the blood vessel. In some embodiments, the output text and / or sound can be consistent with the preset blood vessel (e.g., name, segment, etc.). For example, when training the model, the middle cerebral artery is divided into M1 pre-bifurcation segment, M1 post-bifurcation segment, M2 segment, M3 segment, and M4 segment. When the occlusion position of the blood vessel is determined as M1 pre-bifurcation segment and M1 post-bifurcation segment of the middle cerebral artery, the output text and / or sound can be “the occlusion position of the blood vessel includes M1 pre-bifurcation segment and M1 post-bifurcation segment of the middle cerebral artery”.

[0068] According to the embodiments of the present specification, the ischemic area in the image can be determined based on the CT, DWI and other brain images of the target object, and the occlusion position of the blood vessel can be determined based on the ischemic area. Various brain images can be used to determine the occlusion position of the blood vessel, improving the efficiency of determining the occlusion position. At the same time, brain blood vessel images do not need to be obtained, reducing the difficulty of determining the occlusion position. In addition, by combining the method of deep learning, the occlusion position of the blood vessel can be determined intelligently, reducing the demand for experience and improving the subsequent possible diagnosis and treatment effect.

[0069] It should be noted that the above description of the process 300 is only for example and illustration, and does not limit the scope of the present specification. Those skilled in the art can make various modifications and changes to the process 300 under the guidance of the present specification. However, these modifications and changes are still within the scope of the present specification.

[0070] Figure 5 is a schematic diagram of an exemplary process 500 for determining the occlusion position of the blood vessel according to some embodiments of the present specification.

[0071] As Figure 5 shown, in some embodiments, the ischemic area 510 and the blood supply area 515 can be input into the first identification model 520, and based on the output of the first identification model 520, the occlusion position 530 of the blood vessel can be determined.

[0072] In some embodiments, the first identification model 520 can be a convolutional neural network model (CNN), a deep neural network model (DNN), a recurrent neural network model (RNN), a graph neural network model (GNN), a generative adversarial network model (GAN) or any combination thereof.

[0073] In some embodiments, the first identification model 520 can be determined based on a plurality of sets of first training samples 540. Each set of first training samples 540 can include a sample ischemic area 541, a sample blood supply area 542 and a corresponding sample occlusion position 545 of the sample image, wherein the sample ischemic area 541 and the sample blood supply area 542 are training data, and the corresponding sample occlusion position 545 is a label.

[0074] In some embodiments, the processing device 140 may use image recognition techniques (e.g., image segmentation techniques, machine learning models, etc.) to determine the ischemic region 541 in the sample image. In some embodiments, the processing device 140 may use image recognition techniques or registration methods to determine the blood supply region 542. The determination of the ischemic region 541 and the blood supply region 542 is similar to the determination of the ischemic region and the blood supply region; a more detailed description can be found in [link to relevant documentation]. Figure 3 .

[0075] In some embodiments, the sample occlusion location 545 corresponding to the sample ischemia region 541 and the sample blood supply region 542 can be manually marked by the user or automatically marked by the vascular occlusion location determination system 100 or other systems.

[0076] In some embodiments, the processing device 140 (or other processing device) can use the sample ischemic region 541 and the sample blood supply region 542 as inputs, and the corresponding sample occlusion position 545 as supervision, to train the first recognition model 520. The parameters of the first recognition model 520 are updated by a machine learning algorithm (e.g., stochastic gradient descent) to minimize the first loss function until the model training is completed; or the training stops after a certain number of iterations.

[0077] In some embodiments, the first loss function may be a perceptual loss function. In some embodiments, the first loss function may also be other loss functions, such as a squared loss function, a logistic regression loss function, etc.

[0078] Figure 6A This is an exemplary flowchart illustrating the determination of the location of a blood vessel occlusion according to some embodiments of this specification. In some embodiments, process 600 may be executed by processing device 140 or blood vessel occlusion location determination system 200. For example, process 600 may be stored in a storage device (e.g., storage unit of processing device 140, storage device 150) in the form of a program or instructions, and executed by the processor or... Figure 2 When the module shown executes a program or instructions, it can implement process 600. In some embodiments, process 600 may be completed using one or more additional operations not described below, and / or not through one or more operations discussed below. Additionally, as Figure 6A The order of operations shown is not restrictive. In some embodiments, Figure 3 The determination of the occlusion location of the blood vessel, as described in operation 330, can be performed according to procedure 600.

[0079] At step 610, based on the ischemic region, it is determined whether the blood supply region is in an ischemic state. In some embodiments, the step 610 can be performed by the processing device 140 or the vessel occlusion location determination system 200 (e.g., the occlusion location determination module 230).

[0080] The ischemic state can refer to a blood supply insufficient state caused by the occlusion of a blood vessel in the brain.

[0081] In some embodiments, the processing device 140 can determine an intersection region (or an overlapping region) of the blood supply region and the ischemic region. For example, the processing device 140 can process based on an image matching technique to determine the intersection region of the blood supply region and the ischemic region. Exemplary image matching techniques can include a template matching algorithm, a feature matching algorithm, an artificial neural network based matching algorithm, or the like, or any combination thereof. For another example, the processing device 140 can overlap the blood supply region and the ischemic region to determine the intersection region of the blood supply region and the ischemic region. In some embodiments, for each blood supply region, the processing device 140 can determine a proportion of the intersection region in the blood supply region, and further determine whether the proportion exceeds a preset threshold. The preset threshold can be a maximum proportion of the intersection region in the blood supply region when the blood supply region is not in the ischemic state. For example, the preset threshold can be 1%, 5%, 10%, 15%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, or the like. In some embodiments, the preset threshold can be manually determined by a user, or automatically determined by the vessel occlusion location determination system 100 or other systems. When the proportion exceeds the preset threshold, the processing device 140 can determine that the blood supply region is in the ischemic state. When the proportion does not exceed the preset threshold, the processing device 140 can determine that the blood supply region is not in the ischemic state.

[0082] In some embodiments, the processing device 140 can determine whether each blood supply region is in the ischemic state based on the blood supply region of each blood vessel. For example, the processing device 140 can overlap each of all blood supply regions and the ischemic region respectively, determine one or more blood supply regions containing the intersection region among all blood supply regions and a proportion of the intersection region in the blood supply region in each blood supply region, and determine whether each blood supply region is in the ischemic state based on the proportion of the intersection region in the blood supply region in each blood supply region and the preset threshold.

[0083] In some embodiments, the processing device 140 can determine whether a blood supply area is in a state of ischemia based on intersecting regions. For example, the processing device 140 can determine one or more blood supply areas containing intersecting regions and the area ratio of the intersecting region to the blood supply area in each blood supply area based on the intersecting region to the blood supply area in each blood supply area and a preset threshold, and determine whether one or more blood supply areas containing intersecting regions are in a state of ischemia.

[0084] Step 620: Determine the occlusion location of the blood vessel based on the blood supply area in an ischemic state. In some embodiments, step 620 may be performed by processing device 140 or blood vessel occlusion location determination system 200 (e.g., occlusion location determination module 230).

[0085] In some embodiments, the processing device 140 can determine the location of vascular occlusion based on the blood supply area in an ischemic state and a mapping relationship. The mapping relationship can reflect the correspondence between the blood supply area in an ischemic state and the location of vascular occlusion. This is merely an example. Figure 4 As shown, when the ischemic blood supply area is region 431, the occlusion location of the vessel is the main region 411 of the anterior cerebral artery. When the ischemic blood supply area is region 432, the occlusion location of the vessel is a portion of the superior region 412 of the anterior cerebral artery. When the ischemic blood supply area is region 433, the occlusion location of the vessel is the lateral fissure region 413 of the anterior cerebral artery. When the ischemic blood supply area is region 434, the occlusion location of the vessel is the branch region 414 of the anterior cerebral artery. When the ischemic blood supply area is region 435, the occlusion location of the vessel is the inferior branch region 415 of the anterior cerebral artery. In some embodiments, the mapping relationship can be determined based on clinical experience and the structure of the target object. For example, the mapping relationship can be determined manually by the user or automatically by the vessel occlusion location determination system 100 or other systems.

[0086] In some embodiments, the processing device 140 can acquire feature values ​​(e.g., statistical values, feature vectors) of the blood supply area in an ischemic state, and determine the occlusion location of the blood vessel based on the feature values. For example, the processing device 140 can arrange the feature values ​​into a vector in sequence and determine the occlusion location of the blood vessel through preset logical rules.

[0087] In some embodiments, the processing device 140 can input the ischemic blood supply area into a trained second recognition model and determine the location of vascular occlusion based on the output of the second recognition model. For more information on the second recognition model, see [link to relevant documentation]. Figure 6B And its related descriptions.

[0088] In some embodiments, the occlusion position of the blood vessel can be determined by using the mapping relationship and the machine learning model respectively, and by comparing the occlusion positions determined by different manners, the mapping relationship and the machine learning model can be continuously improved, and the accuracy of determining the occlusion position can be further improved.

[0089] Figure 6B is a schematic diagram of an exemplary flow 650 of determining the occlusion position of the blood vessel according to some embodiments of the present specification.

[0090] As shown in Figure 6B , in some embodiments, the blood supply area in ischemic state 660 can be input into the second identification model 670, and based on the output of the second identification model 670, the occlusion position 680 of the blood vessel can be determined.

[0091] In some embodiments, the second identification model 670 can be a convolutional neural network model (CNN), a deep neural network model (DNN), a recurrent neural network model (RNN), a graph neural network model (GNN), a generative adversarial network model (GAN), or any combination thereof.

[0092] In some embodiments, the second identification model 670 can be trained based on a plurality of sets of second training samples 690. Each set of second training samples 690 can include a sample blood supply area in ischemic state 691 and a corresponding sample occlusion position 695, wherein the sample blood supply area in ischemic state 691 is training data, and the corresponding sample occlusion position 695 is a label.

[0093] In some embodiments, the processing device 140 can determine the sample blood supply area in ischemic state 691 using image matching technology, image overlay technology, or the like. The determination manner of the sample blood supply area in ischemic state 691 is similar to the determination manner of the lesion area, and more specific description can be found in Figure 6A .

[0094] In some embodiments, the sample blood supply area in ischemic state 691 can be manually labeled by a user, or can be automatically labeled by the blood vessel occlusion position determination system 100 or other systems.

[0095] In some embodiments, the processing device 140 (or other processing device) can train the second identification model 670 by inputting the sample blood supply area 691 in the ischemic state as input, the corresponding sample occlusion position 695 as supervision, updating the parameters of the second identification model 670 through a machine learning algorithm (for example, a stochastic gradient descent method) to minimize the second loss function until the model training is completed; or stop training after a certain number of iterations.

[0096] In some embodiments, the second loss function can be a perception loss function. In some embodiments, the second loss function can also be other loss functions, such as a square loss function, a logistic regression loss function, etc.

[0097] In some embodiments, the blood supply area 660 in the ischemic state and the image 665 of the target object can be input into the second identification model 670 together, and based on the output of the second identification model 670, the occlusion position 680 of the blood vessel can be determined. Correspondingly, each set of second training samples 690 of the plurality of sets of second training samples 690 for training the second identification model 670 can include a sample blood supply area 691 in the ischemic state, a sample image 692, and a corresponding sample occlusion position 695, wherein the sample blood supply area 691 in the ischemic state and the sample image 692 are training data, and the corresponding sample occlusion position 695 is a label. The sample image 692 can be obtained in a similar manner to the image, and more specific descriptions can be found in Figure 3 During training, the processing device 140 (or other processing device) can train the second identification model 670 by inputting the sample blood supply area 691 in the ischemic state and the sample image 692 as input, the corresponding sample occlusion position 695 as supervision, updating the parameters of the second identification model 670 through a machine learning algorithm (for example, a stochastic gradient descent method) to minimize the second loss function until the model training is completed; or stop training after a certain number of iterations.

[0098] Figure 7 is a schematic diagram of an exemplary flow 700 of determining the occlusion position of the blood vessel according to some embodiments of the present specification.

[0099] As Figure 7 shown, in some embodiments, the ischemic area 710 can be input into the third identification model 720, and based on the output of the third identification model 720, the occlusion position 730 of the blood vessel can be determined.

[0100] In some embodiments, the third identification model 720 can be a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a graph neural network (GNN), a generative adversarial network (GAN), or the like, or any combination thereof.

[0101] In some embodiments, the third identification model 720 can be determined based on a plurality of sets of third training samples 740. Each set of third training samples 740 can include a sample ischemic region 741 and a corresponding sample occlusion location 745, where the sample ischemic region 741 is the training data and the corresponding sample occlusion location 745 is the label.

[0102] In some embodiments, the processing device 140 can determine the sample ischemic region 741 in the sample image using image recognition techniques (e.g., image segmentation techniques, machine learning models, etc.). The determination of the sample ischemic region 741 is similar to the determination of the ischemic region, and more specific descriptions can be found in Figure 3 .

[0103] In some embodiments, the sample ischemic region 741 can be manually labeled by a user, or automatically labeled by the vessel occlusion location determination system 100 or other systems.

[0104] In some embodiments, the processing device 140 (or other processing devices) can train the third identification model 720 by taking the sample ischemic region 741 as input and the corresponding sample occlusion location 745 as supervision, updating the parameters of the third identification model 720 through a machine learning algorithm (e.g., stochastic gradient descent), and minimizing the third loss function until the model training is completed; or stopping training after a certain number of iterations.

[0105] In some embodiments, the third loss function can be a perception loss function. In some embodiments, the third loss function can also be other loss functions, such as a square loss function, a logistic regression loss function, etc.

[0106] In some embodiments, the ischemic region 710 and the image 715 of the target object can be input into a third recognition model 720 together, and based on the output of the third recognition model 720, the occlusion position 730 of the blood vessel can be determined. Correspondingly, each of a plurality of third training samples 740 used to train the third recognition model 720 can include a sample ischemic region 741, a sample image 742, and a corresponding sample occlusion position 745, where the sample ischemic region 741 and the sample image 742 are training data, and the corresponding sample occlusion position 745 is a label. The sample image 742 can be obtained in a manner similar to that of the image, and more specific descriptions can be found in Figure 3 During training, the processing device 140 (or other processing device) trains the third recognition model 720 by taking the sample ischemic region 741 and the sample image 742 as input and the corresponding sample occlusion position 745 as supervision, updates the parameters of the third recognition model 720 through a machine learning algorithm (for example, a stochastic gradient descent method), and minimizes a third loss function until the model training is completed; or stops training after a certain number of iterations. For example only, a convolutional neural network (CNN) can be used to extract features of the sample image 742, and the sample ischemic region 741 can be down-sampled in multiple scales to ensure that the dimension of the sample ischemic region 741 is consistent with the dimension of the features output by the CNN. Masked pooling processing can be used to focus on the blood supply region in the features of the sample image 742. The masked pooling processing can include masked average pooling. For example only, the masked average pooling processing of the features of the sample image 742 can be as shown in equation (1):

[0107]

[0108] wherein, the features of the sample image 742 extracted using the CNN can be the masked average pooling matrix can be

[0109] Specifically, if the features of the sample image 742 are After the masked average pooling processing, the features of the sample image 742 can be 43. It can be understood that equation (1) is only for example and illustration, and is not intended to limit the calculation manner of the masked pooling processing (for example, the masked average pooling).

[0110] Further, the sample image 742 can be input into the third recognition model 720, and a loss function loss 1 of the sample image 742 can be determined through an activation function; and the features after the mask pooling processing can be input into the third recognition model 720, and a loss function loss 2 of the features after the mask pooling processing can be determined through an activation function. The parameters of the third recognition model 720 are iteratively updated, so that the sum of the loss function loss 1 and the loss function loss 2 has a minimum value, thereby stopping the training of the third recognition model 720. The trained third recognition model 720 can determine the occlusion position of the blood vessel through classification or regression.

[0111] In some embodiments of the present specification, (1) based on the CT, DWI, etc. brain image of the target object, the ischemic area in the image is determined, thereby determining the occlusion position of the blood vessel, and the occlusion position of the blood vessel can be determined through various brain images, thereby improving the efficiency of determining the occlusion position; at the same time, the brain blood vessel image does not need to be extracted, thereby reducing the difficulty of determining the occlusion position; (2) through the machine learning model, the occlusion position of the blood vessel can be intelligently determined, thereby reducing the demand for experience and improving the subsequent possible diagnosis and treatment effect; (3) the occlusion position of the blood vessel can be determined through various ways, thereby improving the accuracy of determining the occlusion position.

[0112] Some embodiments of the present specification also provide an image processing device, which comprises: at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement the occlusion position determination method described in the present specification. For more technical details, please refer to the related description of Figures 1 to 8 , which will not be repeated here.

[0113] Some embodiments of the present specification also provide a computer readable storage medium storing computer instructions, when the computer reads the computer instructions, the computer executes the occlusion position determination method described in the present specification. For more technical details, please refer to the related description of Figures 1 to 8 , which will not be repeated here.

[0114] The above has described the basic concept, and it is obvious that the above detailed disclosure is only as an example and does not constitute a limitation on the present specification for those skilled in the art. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present specification. Such modifications, improvements and corrections are suggested in the present specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0115] Also, the use of "a" or "an" or "the" are intended to include both singular and plural, unless the context clearly indicates otherwise. Additionally, the use of "one or more" or "at least one" is intended to include one, two, three, four, or more, unless the context clearly indicates otherwise. Furthermore, the making and using of a specific embodiment are intended to include any and all combinations of one or more of the associated features, functions, components, and / or elements, including those associated with currently known or future yet to be known and / or devised elements.

[0116] Also, the order of presentation of the processes and procedures described in this specification is not intended to be limiting unless otherwise indicated. Although the above disclosure discusses some presently preferred embodiments of the application, the present application should not be limited to these embodiments alone. Many variations and modifications, as well as many implementations of the present application will be apparent to those having ordinary skill in the art once they access the full disclosure. For example, although the system components described above can be implemented by hardware devices, they can also be implemented by software solutions, such as installing the described system on an existing server or mobile device.

[0117] Similarly, it is noted that the various illustrative blocks described in this specification can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and / or algorithms have been described above generally in terms of their functionality, rather than their specific arrangement of components. Persons skilled in the art will appreciate that any system configured to perform the described functionality or operations would be a satisfying implementation. As used in this specification, "exemplary" merely means "serving as an example of," and not "preferred" over other implementations. Moreover, although the present application has been described in terms of what is presently considered to be the most practical and preferred implementations, it is to be understood that the application needs not be limited to the disclosed implementations.

[0118] In some embodiments, numerical ranges are used to describe quantities of ingredients, properties, and the like. It should be understood that such numerical ranges are used to describe the embodiments of the application in some examples using the modifier "about," "approximately," or "substantially" to modify the numerical values. Unless otherwise indicated, "about," "approximately," or "substantially" indicates that the value of the numerical value can vary by ±20%. Accordingly, numerical values used in the specification and claims are approximations that can vary depending on the desired properties of the individual embodiments. In some embodiments, numerical values should be considered to be defined with the specified number of significant digits and rounded to the common significant figures. Although the numerical ranges and parameters setting forth the broadest scope of the application are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values set forth in the specific examples are provided to more clearly describe the application.

[0119] Each patent, patent application, patent publication, and other material cited in this specification is hereby incorporated by reference in its entirety herein for the teachings relevant to the sentence and / or paragraph in which the reference is presented. Document histories, to the extent not inconsistent with the pertinent U.S. patent application file history, are also incorporated by reference herein. To the extent that material incorporated by reference contradicts or contradicts any portion of this specification, including definition, the portion of the material incorporated by reference prevails. Note, however, that in the event of inconsistencies between any such material and the present specification, including definitions, the present specification, including definitions, will control.

[0120] Finally, it should be understood that the embodiments described herein are merely exemplary of the principles of the present description. Other embodiments can be devised without departing from the scope of the present description. Accordingly, the embodiments described herein are not intended to limit the scope of the present description, but rather are intended to be exemplary thereof.

Claims

1. A vascular occlusion site determination system, characterized by, The system comprises a processor configured to perform the following method: obtain an image of a target object; determine an ischemic region and a blood supply region in the image; determine a blood supply region in an ischemic state based on the ischemic region and the blood supply region; determine an occlusion position of a blood vessel of the target object based on the blood supply region in the ischemic state and a mapping relationship, the mapping relationship reflecting a correspondence between the blood supply region in the ischemic state and the occlusion position of the blood vessel.

2. The system of claim 1, wherein, The method further comprises: inputting the ischemic region and the blood supply region into a trained first identification model; and determining the occlusion position of the blood vessel based on an output of the first identification model.

3. The system of claim 1, wherein, The determination of the blood supply region in the ischemic state based on the ischemic region and the blood supply region comprises: determining whether the blood supply region is in an ischemic state based on the ischemic region.

4. The system of claim 3, wherein, The determination of whether the blood supply region is in an ischemic state based on the ischemic region comprises: determining an intersection region of the blood supply region and the ischemic region; determining a proportion of the intersection region in the blood supply region; determining whether the proportion exceeds a preset threshold value; in response to determining that the proportion exceeds the preset threshold value, determining that the blood supply region is in an ischemic state; or in response to determining that the proportion does not exceed the preset threshold value, determining that the blood supply region is not in an ischemic state.

5. The system of claim 1, further comprising: inputting the blood supply region in the ischemic state into a trained second identification model; and determining the occlusion position of the blood vessel based on an output of the second identification model.

6. The system of claim 1, further comprising: inputting the ischemic region into a trained third identification model; and determining the occlusion position of the blood vessel based on an output of the third identification model. The target object comprises a brain, the image comprises a brain image, and the blood vessel comprises a brain blood vessel. The image comprises a computed tomography image or a diffusion-weighted imaging image.

7. The system of claim 1, wherein, The determination of the ischemic region in the image comprises:

8. The system of claim 1, wherein, determining the ischemic region and an old ischemic region in the image; 9. The system of claim 1, wherein, deleting a part of the ischemic region that overlaps with the old ischemic region; and retaining a part of the ischemic region that does not overlap with the old ischemic region as the ischemic region. comprise an image acquisition module, an ischemic region determination module, and an occlusion position determination module; the image acquisition module is configured to obtain an image of a target object; 10. A vascular occlusion site determination system, characterized by, the ischemic region determination module is configured to determine an ischemic region and a blood supply region in the image; the occlusion position determination module is configured to determine a blood supply region in an ischemic state based on the ischemic region and the blood supply region; and determine an occlusion position of a blood vessel of the target object based on the blood supply region in the ischemic state and a mapping relationship, the mapping relationship reflecting a correspondence between the blood supply region in the ischemic state and the occlusion position of the blood vessel. ​ ​ ​ 11. A computer readable storage medium storing computer instructions, which, when read by a computer, cause the computer to perform the method of any one of claims 1-9 in a blood vessel occlusion site determination system.

Images