CN114783595A

CN114783595A - Acute stroke analysis system, method and storage medium

Info

Publication number: CN114783595A
Application number: CN202210590930.1A
Authority: CN
Inventors: 房文慧; 李阳; 刘超然
Original assignee: Shanghai United Imaging Healthcare Co Ltd
Current assignee: Shanghai United Imaging Healthcare Co Ltd
Priority date: 2022-05-27
Filing date: 2022-05-27
Publication date: 2022-07-22

Abstract

The embodiment of the specification provides an acute stroke analysis system and method. The acquisition module may be used to acquire a brain scan protocol of a target subject. The scan execution module may be configured to instruct to perform a scan of the brain of the target subject to acquire a brain scan image of the target subject based on the brain scan protocol of the target subject. The stroke analysis module may be configured to determine stroke information corresponding to the brain scan image based on the brain scan image of the target subject. The scan execution module and the stroke analysis module are automatically activated after the acquisition module acquires a brain scan protocol of the target subject.

Description

Acute stroke analysis system, method and storage medium

Technical Field

The present disclosure relates to the field of medical technology, and in particular, to an acute stroke analysis system, method and storage medium.

Background

Acute stroke, also known as acute stroke or cerebral apoplexy, is an acute cerebrovascular disease in which cerebral tissue is damaged due to sudden rupture of cerebral vessels or failure of blood flow into the brain caused by vessel occlusion. Can be divided into hemorrhagic stroke and ischemic stroke according to the pathogenesis. Different treatment modes are adopted clinically for different types and different degrees of severity of acute stroke, for example, for ischemic stroke, thrombolysis, mechanical thrombus removal, conservative treatment and the like are adopted. How to quickly and accurately identify the type of stroke and determine the severity of the stroke is very important for the selection of the next treatment modality and for the prognosis of the patient.

Disclosure of Invention

One of the embodiments of the present specification provides an acute stroke analysis system, which includes an acquisition module, a scan execution module, and a stroke analysis module. The acquisition module may be used to acquire a brain scan protocol of a target subject. The scan execution module may be configured to instruct to perform a scan of the brain of the target subject to acquire a brain scan image of the target subject based on the brain scan protocol of the target subject. The stroke analysis module may be configured to determine stroke information corresponding to the brain scan image based on the brain scan image of the target subject. . The scan execution module and the stroke analysis module are automatically activated after the acquisition module acquires a brain scan protocol of the target subject.

In some embodiments, the stroke analysis module comprises: the stroke type judging unit is used for judging the stroke type corresponding to the brain scanning image; and/or an ischemic function unit, configured to determine ischemic stroke related information corresponding to the brain scan image when the stroke type is ischemic stroke; and/or a bleeding function unit, configured to determine information related to hemorrhagic stroke corresponding to the brain scan image when the stroke type is hemorrhagic stroke; and/or a severity determination unit, configured to determine a severity of stroke corresponding to the brain scan image based on the ischemic stroke related information or the hemorrhagic stroke related information.

In some embodiments, the ischemic Stroke related information includes at least one of an ASPECTS (ASPECTS) Score, a location of an ischemic area, a size of the ischemic area, a blood supply vessel corresponding to the ischemic area, a core infarct volume of the ischemic area.

In some embodiments, the ischemia function unit is further configured to determine a blood supply vessel corresponding to the ischemic region using a blood supply vessel determination model based on the brain scan image of the target subject.

In some embodiments, the ischemic function unit further includes a training sample acquisition subunit and a model training subunit. The training sample obtaining subunit is configured to obtain a plurality of training samples, wherein each of the plurality of training samples includes a first sample brain image of a sample object, a second sample brain image, and at least one brain blood vessel of the sample object and a blood supply area of each brain blood vessel. The model training subunit is used for obtaining a blood supply vessel determination model by training an initial model based on the training samples.

In some embodiments, the hemorrhagic stroke related information includes a bleeding volume and a bleeding location corresponding to the brain scan image.

In some embodiments, the severity level comprises a critical level, and the determining the severity level of stroke corresponding to the brain scan image based on the ischemic stroke related information or hemorrhagic stroke related information comprises: performing a threshold comparison on the ischemic stroke-related information or the hemorrhagic stroke-related information to obtain a comparison result; based on the comparison, determining a criticality rating of the stroke to which the brain scan image corresponds.

In some embodiments, the acute stroke analysis system further comprises a report generation module. The report generation module is used for generating a structural analysis report related to the target object based on a preset generation mode and the severity of the ischemic stroke or the severity of the hemorrhagic stroke.

One of the embodiments of the present specification provides an acute stroke analysis method, which is performed by using the acute stroke analysis system as described above. The method comprises the following steps: acquiring a brain scanning protocol of a target object; automatically instructing to perform a scan of the brain of the target subject to obtain a brain scan image of the target subject based on the brain scan protocol of the target subject; and determining stroke information corresponding to the brain scan image based on the brain scan image of the target object.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions which, when read by a computer, cause the computer to perform the acute stroke analysis method as described above.

The acute stroke analysis system and/or the method provided by the embodiment of the specification can quickly and automatically execute scanning and automatically determine the severity of the acute stroke based on the acquired brain scanning protocol, and shorten the time of the whole work flow and greatly improve the efficiency of stroke analysis by saving the time for receiving user instructions or waiting for judgment results and the like.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

fig. 1 is a schematic diagram of an application scenario of an exemplary acute stroke analysis system in accordance with some embodiments herein;

fig. 2 is a schematic diagram of an exemplary acute stroke analysis system shown in accordance with some embodiments herein;

fig. 3 is a schematic flow diagram of an exemplary acute stroke analysis method according to some embodiments herein;

fig. 4A and 4B are schematic diagrams of exemplary brain regions, according to some embodiments herein.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, without inventive effort, the present description can also be applied to other similar contexts on the basis of these drawings. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system," "device," "unit," and/or "module" as used herein is a method for distinguishing between different components, elements, parts, portions, or assemblies of different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not to be taken in a singular sense, but rather are to be construed to include a plural sense unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of the present specification. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to or removed from these processes.

Fig. 1 is a schematic diagram of an application scenario of an exemplary acute stroke analysis system according to some embodiments of the present description.

As shown in fig. 1, the acute stroke analysis system 100 can include a medical device 110, a processing device 120, a terminal device 130, a storage device 140, and a network 150. In some embodiments, the processing device 120 may be part of the medical device 110.

The medical device 110 may be a non-invasive scanning imaging device for disease diagnosis or research purposes. In some embodiments, the medical device 110 may scan a target object in the detection area or the scanning area, obtaining scan data of the target object. In some embodiments, the medical device 110 may include a single modality scanner and/or a multi-modality scanner. The single modality scanner may include, for example, an ultrasound scanner, an X-ray scanner, a Computed Tomography (CT) scanner, a Magnetic Resonance Imaging (MRI) scanner, an Optical Coherence Tomography (OCT) scanner, an Ultrasound (US) scanner, an intravascular ultrasound (IVUS) scanner, or the like, or any combination thereof. The multi-modality scanner may 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. In some embodiments, the processing device 120 may be integrated on the medical device 110, or the medical device 110 and the processing device 120 may perform their functions through the same entity. The medical devices provided above are for illustrative purposes only and are not intended to limit the scope of the present description.

Processing device 120 may process data and/or information obtained from medical device 110, terminal device 130, storage device 140, or other components of system 100. For example, the processing device 120 may obtain a brain scan protocol of the target subject from the terminal device 130. The processing device 120 may automatically instruct the medical device 110 to perform a scan on the brain of the target subject to acquire a brain scan image, such as a CT scan image, an MRI scan image, etc., of the target subject based on the acquired brain scan protocol of the target subject, and automatically analyze a stroke type corresponding to the brain scan image. If it is determined that the stroke type is ischemic stroke, the processing device 120 may determine ischemic stroke related information corresponding to the brain scan image. If the type of the stroke is determined to be hemorrhagic stroke, the processing equipment can determine the hemorrhagic stroke related information corresponding to the brain scanning image. The processing device 120 may further determine a severity of stroke corresponding to the brain scan image based on the ischemic stroke related information or hemorrhagic stroke related information. For another example, the processing device 120 may obtain a preset generation manner of the stroke analysis structured report from the terminal device 130. The processing device 120 may further generate a structured analysis report related to the target object based on the preset generation mode and the severity of ischemic stroke or the severity of hemorrhagic stroke. In some embodiments, the processing device 120 may be local or remote. For example, processing device 120 may access information and/or data from medical device 110, terminal device 130, and/or storage device 140 via network 150.

In some embodiments, the terminal device 130 may be a request terminal for acute stroke analysis and/or a processing terminal for acute stroke analysis results. For example, the user may send an instruction through the terminal device 130 requesting to perform a brain scan and an acute stroke analysis. As another example, the terminal device 130 can present the generated/obtained stroke analysis result (e.g., stroke analysis structured report) on a display interface for output to a user. In embodiments of the present description, the terminal device 130 may include a mobile device 131, a tablet computer 132, a notebook computer 133, and the like, or any combination thereof.

Storage device 140 may store data, instructions, and/or any other information. In some embodiments, the storage device 140 may store data obtained from the medical device 110, the processing device 120, and/or the terminal device 130, such as a brain scan image of the target object, stroke analysis results, structural analysis reports related to the target object, preset generation modes of the structural analysis reports, and the like.

In some embodiments, storage device 140 may include one or more storage components, each of which may be a stand-alone device or part of another device. In some embodiments, storage device 140 may include Random Access Memory (RAM), Read Only Memory (ROM), mass storage, removable storage, volatile read and write memory, and the like, or any combination thereof. Illustratively, the mass storage may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, the storage device 140 may be implemented on a cloud platform.

Network 150 may include any suitable network capable of facilitating information and/or data exchange. In some embodiments, at least one component of the acute stroke analysis system 100 (e.g., the medical device 110, the processing device 120, the terminal device 130, the storage device 140) may exchange information and/or data with at least one other component in the system 100 via the network 150. For example, the processing device 120 may obtain a brain scanning protocol of the target subject from the terminal device 130 via the network 150. As another example, the terminal device 130 may obtain a structured analysis report related to the target object from the processing device 120 via the network 150.

It should be noted that the acute stroke analysis system 100 is provided for illustrative purposes only and is not intended to limit the scope of the present description. It will be apparent to those skilled in the art that various modifications and variations can be made in light of the description of the present specification. For example, the acute stroke analysis system 100 can also include an input device and/or an output device. As another example, the acute stroke analysis system 100 can implement similar or different functionality on other devices. However, such changes and modifications do not depart from the scope of the present specification.

Fig. 2 is a schematic diagram of an exemplary acute stroke analysis system, shown in accordance with some embodiments herein.

As shown in fig. 2, in some embodiments, the acute stroke analysis system 200 can include an acquisition module 210, a scan execution module 220, a stroke analysis module 230, and a report generation module 240. In some embodiments, the corresponding functions of the acute stroke analysis system 200 may be performed by the processing device 120, such as the acquisition module 210, the scan execution module 220, the stroke analysis module 230, and the report generation module 240 may be modules in the processing device 120.

The acquisition module 210 may be used to acquire a brain scan protocol of a target subject. For a description of a brain scan protocol for acquiring a target object, reference may be made to step 305 in fig. 3, which is not repeated herein.

The scan execution module may be configured to instruct to perform a scan of the brain of the target subject based on a brain scan protocol of the target subject to acquire a brain scan image of the target subject, e.g., CT scan data of the patient, etc. For a description of obtaining a brain scan image of a target object, reference may be made to step 310 in fig. 3, which is not described herein again.

The stroke analysis module 230 may be configured to determine stroke information corresponding to the brain scan image based on the brain scan image of the target subject. Stroke information corresponding to the brain scan image includes at least a type and severity of the stroke. In some embodiments, the stroke analysis module 230 may include a stroke type determination unit 231, a bleeding function unit 232, an ischemia function unit 233, and a severity determination unit 234.

The stroke type determining unit 231 may be configured to determine a stroke type corresponding to the brain scan image. The stroke types may include hemorrhagic stroke, ischemic stroke, and stroke-free. For a description about determining the stroke type corresponding to the brain scan image, reference may be made to step 320 in fig. 3, which is not described herein again.

The bleeding function unit 232 may be configured to determine information related to a hemorrhagic stroke corresponding to the brain scan image when the stroke type is a hemorrhagic stroke. In some embodiments, hemorrhagic stroke related information can include the amount and location of bleeding corresponding to a brain scan image. For a description of determining hemorrhagic stroke related information corresponding to the brain scan image, reference may be made to step 330 in fig. 3, which is not described herein again.

The ischemic function unit 233 may be configured to determine ischemic stroke related information corresponding to the brain scan image when the stroke type is ischemic stroke. In some embodiments, the ischemic Stroke related information may include at least one of an ASPECTS (ASPECTS) Score, a location of an ischemic area, a size of the ischemic area, a blood supply vessel corresponding to the ischemic area, a core infarct volume of the ischemic area. In some embodiments, the ischemia function unit 233 may be configured to determine, based on the brain scan image of the target object, a blood supply vessel corresponding to the ischemic region using a blood supply vessel determination model. In some embodiments, the ischemia function unit 233 may include a training sample acquisition subunit and a model training subunit. The training sample obtaining subunit may be configured to obtain a plurality of training samples, wherein each of the plurality of training samples may include a first sample brain image of the sample subject, a second sample brain image, and at least one brain blood vessel of the sample subject and a blood supply area of each brain blood vessel. The model training subunit may be configured to obtain a blood supply vessel determination model by training the initial model based on a plurality of training samples. For a description of determining ischemic stroke related information corresponding to the brain scan image, reference may be made to step 350 in fig. 3, which is not described herein again.

The severity determination unit 234 may be configured to determine a severity of stroke corresponding to the brain scan image based on the ischemic stroke related information or hemorrhagic stroke related information. In some embodiments, the severity of stroke may be characterized by a quantitative indicator. For example, the severity of stroke can be expressed as a number between 1-15, with different numbers representing different degrees of severity of stroke. As another example, the severity of stroke can be expressed as a critical level of stroke. Such as mild, moderate, and severe symptoms. The severity of stroke, for example, can be expressed as a risk level of stroke, e.g., low risk, medium risk, high risk, and the like. In some embodiments, the severity determination unit 234 can threshold the ischemic stroke related information or hemorrhagic stroke related information to obtain a comparison result. The severity determination unit 234 may further determine a severity level of stroke corresponding to the brain scan image based on the comparison. For a description related to determining the severity of stroke corresponding to the brain scan image, reference may be made to steps 340 and 360 in fig. 3, which are not repeated herein.

The report generation module 240 may be configured to generate a structured analysis report related to the target object based on a preset generation manner and the severity of ischemic stroke or the severity of hemorrhagic stroke. For a description of generating the structured analysis report, reference may be made to step 370 in fig. 3, which is not described herein again.

In some embodiments, the scan execution module 220 and the stroke analysis module 230 may be automatically activated after the acquisition module 210 acquires the brain scan protocol of the target subject, so as to automatically perform step 310 and step 360 in the flowchart 3. The term "automatically activate" may refer to that, in some scenarios, the execution components of the system (e.g., the scan execution module 220 and the stroke analysis module 230) may directly begin functioning (i.e., may automatically receive data and process the received data) without intervention or operation by a user. For example, after the acquisition module 210 acquires a brain scan protocol of the target subject, the scan execution module 220 is automatically activated. The acquisition module 210 may transmit the acquired brain scan protocol of the target subject to the scan execution module 220, and the scan execution module 220 may automatically instruct to execute a scan on the brain of the target subject to acquire a brain scan image of the target subject based on the acquired brain scan protocol of the target subject. For another example, after acquiring the brain scan image of the target object, the scan execution module 220 may transmit the brain scan image of the target object to the stroke type determination unit 231, and the stroke type determination unit 231 may automatically determine the stroke type corresponding to the received brain scan image.

In the conventional method, a target object is generally scanned according to an instruction to acquire a scan image of the target object. And determining whether stroke analysis is needed according to the scanned image. After the fact that the stroke analysis is needed is determined, judging the type of the stroke, and then carrying out subsequent different processing based on the judged type of the stroke. Each step in the whole workflow needs to determine whether to execute the next step according to the user instruction and/or waiting for the judgment result, which results in long time consumption and low efficiency of the whole workflow, and especially in the case of emergency treatment of acute stroke diagnosis, the long time consumption and the low efficiency of the workflow may cause serious consequences to the patient. In the application, after the acquisition module acquires the brain scanning protocol, the scanning execution module 220 and the stroke analysis module 230 are automatically activated to automatically execute subsequent steps, so that the time for receiving user instructions or waiting for judgment results and the like can be greatly saved, the time of the whole work flow is shortened, the efficiency of stroke analysis is greatly improved, especially in an emergency scene, an acute stroke analysis result can be obtained as soon as possible, and a proper treatment measure can be taken for a patient as soon as possible.

It should be understood that the system and its modules shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments the system and its modules may be implemented in hardware, software, or a combination of software and hardware.

It should be noted that the above description of the system and its modules is for convenience of description only and is not intended to limit the present disclosure to the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the system, any combination of modules or sub-system may be configured to interface with other modules without departing from such teachings. For example, in some embodiments, the above modules disclosed in fig. 2 may be different modules in a system, or may be a module that implements the functions of two or more of the above modules. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

Fig. 3 is a schematic flow diagram of an exemplary acute stroke analysis method according to some embodiments of the present description. In some embodiments, the process 300 can be performed by the acute stroke analysis system 100 (e.g., the processing device 120) or the acute stroke analysis system 200, e.g., by respective modules within the processing device 120. As shown in fig. 3, the process 300 may include the following steps.

Step 305, a brain scan protocol of the target subject is acquired. In some embodiments, step 305 may be performed by the processing device 120 or the acquisition module 210.

The target object may comprise the whole or part of a biological object and/or a non-biological object involved in the scanning process. For example, the target object may be an organic and/or inorganic substance, living or non-living, such as head, ear-nose, neck, chest, abdomen, liver, gall, pancreas, spleen, kidney, spine, and the like. In some embodiments, the target object may be a human brain.

The brain scanning protocol may include information on the scanning mode, scanning parameters, and possibly a stroke prompt for the target object. In some embodiments, a user (e.g., an emergency doctor) may manually set up and upload at least a portion of the brain scan protocol (e.g., whether there may be a stroke). In some embodiments, the brain scan protocol may be generated in advance and stored in the storage device, and the processing device 120 may automatically acquire the brain scan protocol based on a user indication. For example, the user may indicate that the target object may have a stroke, and the processing device 120 may automatically retrieve the relevant brain scanning protocol.

Step 310 and 370 will be performed automatically after the processing device 120 acquires the brain scan protocol.

At step 310, a scan of the brain of the target subject is automatically instructed to acquire a brain scan image of the target subject based on the brain scan protocol of the target subject. In some embodiments, step 310 may be performed by the processing device 120 or the scan execution module 220.

The brain scan image may be an image obtained by scanning the brain of a human body, for example, a tomographic image, a PET scan image, or the like. In some embodiments, after acquiring the brain scan protocol of the target subject, the processing device 120 may instruct a medical device (e.g., medical device 110), such as a CT scanning device, a PET scanning device, an MRI scanning device, etc., to perform a scan of the brain of the target subject to acquire a brain scan image.

And step 320, automatically judging the stroke type corresponding to the brain scanning image. In some embodiments, step 320 can be performed by the processing device 120 or the stroke analysis module 230 (e.g., stroke type determination unit 231).

Stroke type can be a classification of stroke based on the cause and clinical manifestation. In some embodiments, stroke types can include hemorrhagic stroke, ischemic stroke, and no stroke. Hemorrhagic stroke can be a stroke resulting from bleeding from a blood vessel within or on the surface of the brain. For example, hemorrhage of brain parenchyma, subarachnoid hemorrhage, etc. Ischemic stroke can be stroke caused by stenosis or occlusion of cerebral blood supply arteries (such as carotid and vertebral arteries) or cerebral blood supply insufficiency. For example, lacunar infarction, leukodegeneration, etc. No stroke may be a normal condition of the brain.

In some embodiments, the processing device 120 may automatically determine a focal region in the brain scan image and analyze the focal region in the brain scan image to determine a stroke type corresponding to the brain scan image. The term "automatically" in this specification may refer to that in some scenarios, an executing component of the system (e.g., the processing device 120 or the stroke type determination unit 231) may directly begin functioning to perform the predetermined method steps (i.e., may receive data and process the received data) without requiring intervention or operation by a user. For example, after acquiring the brain scan image of the target object, the processing device 120 may directly determine the stroke type corresponding to the brain scan image by using the trained stroke recognition model. In some embodiments, the processing device 120 may semi-automatically determine the stroke type corresponding to the brain scan image based on relevant information provided by a user (e.g., a physician). For example, the focal region and the related information in the brain scan image may be displayed on a user interface, and the user may determine the stroke type and/or the related information corresponding to the brain scan image and manually input the determined stroke type and/or the related information through the user interface. The processing device 120 may obtain a user determined stroke type or determine a stroke type based on relevant information input by the user.

In some embodiments, step 330 may be performed when the stroke type corresponding to the brain scan image is determined to be hemorrhagic stroke. Step 350 can be performed when it is determined that the stroke type corresponding to the brain scan image is an ischemic stroke. Step 370 can be performed when it is determined that the stroke type corresponding to the brain scan image is stroke-free.

And step 330, determining the hemorrhagic stroke related information corresponding to the brain scanning image when the stroke type is hemorrhagic stroke. In some embodiments, step 330 may be performed by the processing device 120 or the stroke analysis module 230 (e.g., the bleeding function 232).

In some embodiments, hemorrhagic stroke related information may include the amount and location of bleeding corresponding to the brain scan image.

In some embodiments, processing device 120 may use an image analysis algorithm (e.g., an image segmentation algorithm) to segment multiple brain regions from the brain scan image. Exemplary brain regions may include right frontal lobe, left frontal lobe, midbrain, right parietal lobe, left parietal lobe, lumbricus, right temporal lobe, left temporal lobe, pons, right occipital lobe, left occipital lobe, right cerebellum, left cerebellum, right basal ganglia, left basal ganglia, right outer capsule, left outer capsule, right thalamus, and left thalamus, among others. Exemplary image segmentation algorithms may include a threshold segmentation algorithm, an edge detection algorithm, a machine learning based segmentation algorithm, or the like, or any combination thereof. In some embodiments, segmenting the brain scan image may also result in an eye mask, which may be used to estimate the hemorrhage volume.

In some embodiments, the bleeding site may be a specific site of hemorrhagic stroke blood outflow. In some embodiments, the processing device 120 may determine the bleeding location of the target object based on the locations of the plurality of brain regions resulting from the above-described segmentation. For example, the processing device may segment the bleed area using the image segmentation techniques described above. The processing device 120 may establish a brain coordinate system and determine the coordinates of each brain region in the brain coordinate system and the coordinates of the bleeding region in the brain coordinate system. The processing device 120 may further compare the coordinates of each brain region in the brain coordinate system with the coordinates of the bleeding region in the brain coordinate system to determine the location of the bleeding region (i.e., bleeding location) of the target subject.

In some embodiments, the amount of bleeding may be the amount of bleeding from a blood vessel or heart that bleeds blood from a hemorrhagic stroke. The amount of bleeding can be expressed by the volume of bleeding. The bleeding volume may be determined based on the size of the bleeding area in the brain scan image. For example, the amount of bleeding can be calculated using a multi-field formula. In some embodiments, processing device 120 may estimate the hemorrhage volume based on the spatial background size of the brain scan image and the spatial size of the eye membrane.

In some embodiments, after determining that the stroke type corresponding to the brain scan image is hemorrhagic stroke, the processing device 120 may automatically segment a plurality of brain regions from the brain scan image and determine blood stroke related information based on the segmented plurality of brain regions, thereby automatically performing step 340 to determine the severity of hemorrhagic stroke corresponding to the brain scan image.

And step 340, determining the severity of the hemorrhagic stroke corresponding to the brain scanning image based on the information related to the hemorrhagic stroke. In some embodiments, step 340 can be performed by the processing device 120 or the stroke analysis module 230 (e.g., the severity determination unit 234).

In some embodiments, the severity of stroke (e.g., the severity of hemorrhagic stroke or the severity of ischemic stroke) can be characterized by a quantitative indicator. In some embodiments, the quantization index may be a number. For example, the severity of stroke can be expressed as a number between 1-15, with different numbers representing different degrees of severity of stroke. For example, 1 indicates the lowest severity of stroke, 15 indicates the highest severity of stroke, and the numbers between 1 and 15 increase in order as the severity of stroke increases. In some embodiments, the quantitative indicator may be a criticality rating, i.e., the severity of stroke may be represented as a criticality rating of stroke. Such as mild case, moderate case, and severe case. In some embodiments, the quantitative indicator may be a risk level, i.e. the severity of stroke may be expressed as a risk level of stroke, e.g. low risk, medium risk, high risk, etc. In some embodiments, the quantization index may also be represented by other manners, for example, a letter is used to represent a quantization value, and the like, which are not described herein again. For convenience of description, the following is an example illustrating the severity of stroke as a critical grade.

In some embodiments, the processing device 120 may threshold the hemorrhagic stroke related information to obtain a comparison result. The processing device 120 may further determine a criticality rating of the stroke based on the comparison. For example, the processing device 120 may obtain a first threshold and a second threshold. The processing device 120 may compare the amount of bleeding to a first threshold and a second threshold to obtain a bleeding amount comparison result, wherein the first threshold is smaller than the second threshold. When the amount of bleeding is less than the first threshold, the processing device 120 may determine that the critical level of a hemorrhagic stroke is mild. When the amount of bleeding is greater than or equal to the first threshold value and less than the second threshold value, the processing device 120 may determine that the critical grade of the bloody stroke is a medium. When the amount of bleeding is greater than or equal to the second threshold, the processing device 120 may determine that the critical level of the hemorrhagic stroke is severe.

In some embodiments, the first threshold and the second threshold may be manually set by a user (e.g., a clinician) according to empirical values, or set according to default parameters of the acute stroke analysis 100 system, or determined by the processing device 120 according to actual needs. In some embodiments, the first and second thresholds may be determined based on the bleeding location, i.e., different first and second thresholds may be set for different bleeding locations. For example, the second threshold for the basal ganglia region of the brain may be 30 ml. As another example, the second threshold for the thalamic region of the brain may be 15 ml. In some embodiments, the first threshold and the second threshold may be determined based on the bleeding location and the size of the bleeding area. For example, the second threshold may be 10ml when the bleeding diameter of the cerebellar region of the brain is greater than 3 cm.

In some embodiments, the processing device 120 may determine whether to send risk alert information based on preset pre-alarm conditions. When the processing device determines that hemorrhagic stroke meets the early warning condition, the processing device 120 may generate and send risk prompting information to the user to prompt the user to proceed as soon as possible. The pre-alarm condition may be set manually by a user (e.g., a clinician) based on experience, or set based on default parameters of the acute stroke analysis system 100, or determined by the processing device 120 based on actual needs. In some embodiments, a plurality of different warning conditions may be set for the severity of hemorrhagic stroke, amount of bleeding, location of bleeding, and the like. For example, the warning condition corresponding to the hemorrhagic stroke critical grade may be set to the critical grade of the intermediate disease or more. As another example, the pre-warning condition corresponding to the bleeding location may be set such that the bleeding location is located in at least two brain regions (e.g., at least two brain regions segmented in step 330) or in a significant region of the brain.

In some embodiments, the processing device 120 may generate adjacent tissue risk prompting information for the bleeding area based on the bleeding location to prompt the user whether there is a risk of infection for important brain organs or tissues adjacent to the bleeding area. For example, if the bleeding area is in close proximity to a vital organ or tissue, the processing device 120 may generate a risk alert message to alert the nearby vital brain organ or tissue of the risk of infection. By sending risk cues to the user, the user may take appropriate treatment options as early as possible to reduce or avoid damage to nearby organs or tissues.

And step 350, when the stroke type is ischemic stroke, determining ischemic stroke related information corresponding to the brain scanning image. In some embodiments, step 350 may be performed by processing device 120 or stroke analysis module 230 (e.g., ischemic function 233).

In some embodiments, the ischemic stroke related information may include at least one of an ASPECTS score, a location of an ischemic area, a size of an ischemic area, a blood supply vessel corresponding to the ischemic area, a core infarct volume of the ischemic area.

The ASPECTS score may also be referred to as an Alberta stroke project early electron computed tomography score, which may include a pre-cycle ASPECTS score, a post-cycle ASPECTS score, and the like. In some embodiments, the ASPECTS scores corresponding to brain scan images of ischemic stroke may be achieved by scoring different parts of the cerebral cortex. By way of example only, fig. 4A and 4B are schematic diagrams of exemplary brain regions according to some embodiments herein. As shown in fig. 4A and 4B, the subcortical region may include the caudate nucleus C, the lenticular nucleus L, and the inner capsule IC. The middle cerebral artery cortical regions may include the anterior cerebral artery cortical region M1, the islet cortex I, the lateral cerebral artery islet cortex region M2, the posterior cerebral artery cortical region M3, the middle cerebral artery cortical region M4 over M1, the middle cerebral artery cortical region M5 over M2, and the middle cerebral artery cortical region M6 over M3. Each of the subcortical structure region and the middle cerebral artery cortical region may correspond to 1 point, with a total of 10 points. The anterior circulating ASPECTS score may correspond to areas of subcortical structures and cerebral mid-arterial cortical areas. Early ischemic changes were scored less than 1 per involvement of one of the subcortical regions and the cerebral middle artery cortical regions by the anterior circulating ASPECTS score. The pre-cycle ASPECTS score is 10-number of affected regions. A higher ASPECTS score indicates a better prognosis.

The location of the ischemic region (also referred to as the ischemic location) may be a specific site of ischemic stroke with insufficient blood supply. In some embodiments, the location of the ischemic region may be determined in a manner similar to the determination of the location of bleeding, and the related description may refer to step 330, which is not repeated herein.

The size of the ischemic area may be the size of the specific site of ischemic stroke insufficiency. In some embodiments, the processing device 120 may determine the size of the ischemic area by calculating the number of pixel points or voxel points corresponding to the ischemic area. For example, the processing device 120 may determine the number of pixels in the brain scan image that correspond to the brain region of the target subject, as well as the number of pixels that correspond to the ischemic region. The processing device 120 may further determine the size of the ischemic region based on the size of the brain and a ratio between the number of pixels corresponding to the ischemic region and the number of pixels corresponding to the brain region. For example, the processing device 120 may multiply the size of the brain of the target object by the ratio between the number of pixels corresponding to the ischemic area and the number of pixels corresponding to the brain area of the target object to obtain the size of the ischemic area.

The blood supply vessel corresponding to the ischemic region may be a vessel supplying blood to the ischemic region. In ischemic stroke, the ischemic region is partially or completely occluded by a blood supply vessel corresponding to the ischemic region, resulting in insufficient blood supply to the ischemic region. In some embodiments, the processing device 120 may determine the donor vessel corresponding to the ischemic area using a donor vessel determination model based on the brain scan image of the target subject. In some implementations, the donor vessel determination model can include a first portion, a second portion, and a third portion. The first part may be used to determine the ischemic region to which the brain scan corresponds. The second portion may be used to extract image features. Exemplary image features may include color features, texture features, shape features, size features, spatial relationship features, and the like. The third portion may provide a correspondence between each cerebral blood vessel and its blood-feeding area. For example only, the processing device 120 may input a scan image of the brain of the target subject into the feeding blood vessel determination model. The first part of the blood supply vessel determination model may determine the ischemic area corresponding to the input brain scan. The second section of the blood supply vessel determination model may extract image features of the ischemic region and input the extracted image features into the third section. The third part of the blood-supply vessel determination model may output the blood-supply vessel corresponding to the ischemic region based on the acquired image features and the correspondence between each cerebral vessel and its blood-supply region.

In some embodiments, the blood supply vessel determination model may include only the second and third portions described above. By way of example only, after acquiring a brain scan image of a target subject, the processing device may determine an ischemic region corresponding to the brain scan image. The processing device 120 may enter the brain scan image labeled with the ischemic region into the feeding blood vessel determination model. The second section of the blood-supply vessel determination model may extract image features of the ischemic region and input the extracted image features into the third section. The third section of the blood-supply-vessel determination model may output a blood supply vessel corresponding to the ischemic region based on the acquired image features and the correspondence between each cerebral vessel and its blood supply region.

In some embodiments, the processing device 120 can obtain the feeding blood vessel determination model from one or more components of the acute stroke analysis system 100 (e.g., the storage device 140) or an external device. In some embodiments, the donor vessel determination model may be obtained by training a machine learning model based on a plurality of training samples.

For example only, the processing device 120 may obtain a plurality of training samples. Each training sample may comprise a first sample brain image of the sample subject, a second sample brain image and at least one brain blood vessel of the sample subject and a blood supply area for each brain blood vessel. The first sample brain image may be used to display the brain blood vessels of the sample subject. Exemplary first sample images may include CTA images, DSA images, and the like. The second sample brain image may be used to display the brain region of the sample subject. Exemplary second sample images may include CT scout images, MRI images, and the like. At least one cerebral blood vessel of the sample object in each training sample and the blood supply area of each cerebral blood vessel may be used as training labels. The processing device 120 may train the initial model through a plurality of iterations based on a plurality of training samples to obtain the donor vessel determination model. In some embodiments, the trained machine learning model (e.g., the second portion of the feeding blood vessel determination model) may provide a correspondence between at least one sample vessel in the first sample image and at least one sample region in the second sample image of the sample object in each training sample, i.e., a correspondence between each cerebral vessel and its feeding blood region of each sample object.

The core infarct volume in the ischemic zone may be the volume of brain tissue in which irreversible damage has occurred. In some embodiments, the core infarct volume may be an area where cerebral blood flow is reduced by more than 30% compared to normal brain tissue. In some embodiments, the core infarct volume may be calculated by brain perfusion means. In some embodiments, the processing device 120 may determine the region of the core infarct of the ischemic region using the image segmentation technique described in step 330. Processing device 120 may determine the volume of the core infarct zone (i.e., the core infarct volume) by calculating the number of pixel points or voxel points corresponding to the core infarct zone. For example, the processing device 120 may determine the number of pixels in the brain scan image that correspond to the brain region of the target subject, as well as the number of pixels that correspond to the core infarct region. Processing device 120 may further determine the core infarct volume based on the brain volume of the target subject and the ratio between the number of pixels corresponding to the core infarct region and the number of pixels corresponding to the brain region. For example, the processing device 120 may multiply the target subject's brain volume by the ratio between the number of pixels corresponding to the core infarct region and the number of pixels corresponding to the target subject's brain region to obtain the core infarct volume.

In some embodiments, after determining that the stroke type corresponding to the brain scan image is an ischemic stroke, the processing device 120 may automatically segment a plurality of brain regions from the brain scan image and determine ischemic stroke related information based on the segmented plurality of brain regions, thereby automatically performing step 360 to determine the severity of ischemic stroke corresponding to the brain scan image.

And step 360, when the stroke type is ischemic stroke, determining ischemic stroke related information corresponding to the brain scanning image. In some embodiments, step 350 may be performed by the processing device 120 or the stroke analysis module 230 (e.g., the severity determination unit 234).

In some embodiments, the severity of stroke may be characterized by a quantitative indicator. For a description of the quantitative indicator of the severity of stroke, reference may be made to step 340, which is not described herein again.

In some embodiments, the processing device 120 may perform a threshold comparison on the ischemic stroke related information to obtain a comparison result. The processing device 120 can further determine a criticality rating of the ischemic stroke based on the comparison. In some embodiments, the processing device 120 may obtain a threshold value corresponding to the volume of the core infarct, a threshold value corresponding to the ASPECTS score, and a threshold value corresponding to the size of the ischemic area. In some embodiments, the threshold corresponding to the volume of the core infarct, the threshold corresponding to the ASPECTS score, and the threshold corresponding to the size of the ischemic area may be manually set by a user (e.g., a clinician) based on empirical values, or set based on default parameters of the acute stroke analysis 100 system, or determined by the processing device 120 based on actual needs. In some embodiments, the threshold corresponding to the volume of the core infarct and the threshold corresponding to the size of the ischemic area may be determined based on the location of the ischemic area and the blood supply vessels corresponding to the ischemic area, i.e., the threshold corresponding to the volume of the core infarct and the threshold corresponding to the size of the ischemic area may be different in different parts of the brain.

In some embodiments, the processing device 120 may compare the core infarct volume of the ischemic area to a threshold value corresponding to the core infarct volume to determine a first severity of ischemic stroke. The processing device 120 may compare the ASPECTS score of the ischemic area to a threshold value corresponding to the ASPECTS score to determine a second severity of the ischemic stroke. The processing device 120 can compare the size of the ischemic area to a threshold corresponding to the size of the ischemic area to determine a third severity of ischemic stroke. For example, the processing device 120 may obtain a third threshold value (e.g., 20ml) and a fourth threshold value (e.g., 30ml) corresponding to the volume of the core infarct. The processing device 120 may compare the core infarct volume of the ischemic area to a third threshold and a fourth threshold to obtain a core infarct volume comparison, where the third threshold is less than the fourth threshold. When the core infarct volume is less than the third threshold, the processing device 120 can determine the criticality rating of the ischemic stroke as mild case. When the core infarct volume is equal to or greater than the third threshold value and less than the fourth threshold value, the processing device 120 may determine the criticality rating of ischemic stroke as moderate. When the core infarct volume is greater than or equal to the fourth threshold value, the processing device 120 can determine the criticality rating of the ischemic stroke as severe.

In some embodiments, the processing device 120 can specify one of the first severity, the second severity, and the third severity as a final severity of the ischemic stroke. In some embodiments, the processing device 120 may obtain a first weight corresponding to the first severity, a second weight corresponding to the second severity, and a third weight corresponding to the third severity. The processing device 120 may perform a weighted summation of the first severity, the first weight, the second severity, the second weight, the third severity, and the third weight to determine a final severity of the ischemic stroke.

In some embodiments, the processing device 120 may determine whether to send risk alert information based on preset pre-alarm conditions. When the processing device determines that the ischemic stroke meets the pre-warning condition, the processing device 120 may generate and send risk-prompting information to the user to prompt the user to treat as soon as possible. The pre-alarm condition may be set manually by a user (e.g., a clinician) based on experience, or set based on default parameters of the acute stroke analysis system 100, or determined by the processing device 120 based on actual needs. In some embodiments, a plurality of different pre-warning conditions may be set for the severity of ischemic stroke, the ASPECTS score, the location of the ischemic area, the size of the ischemic area, the blood supply vessels corresponding to the ischemic area, the core infarct volume of the ischemic area, and the like. For example, the early warning condition corresponding to the critical level of ischemic stroke may be set to the critical level of moderate disease or above. For another example, the pre-alarm condition corresponding to the location of the ischemic region may be set such that the location of the ischemic region is in at least two brain regions (e.g., at least two brain regions segmented in step 330) or in a significant region of the brain. For another example, the early warning condition of the blood supply vessel corresponding to the ischemic area may be set such that the blood supply vessel corresponding to the ischemic area includes at least two blood supply vessels or a key blood supply vessel for which the blood supply vessel is preset. For another example, the warning condition corresponding to the size of the ischemic area may be set such that the size of the ischemic area is larger than a certain size threshold. As another example, an early warning condition corresponding to a core infarct volume may be set to be the core infarct volume being greater than a volume threshold.

In some embodiments, similar to hemorrhagic stroke, the processing device 120 may generate a tissue risk indication message adjacent to the ischemic region based on the ischemic location to indicate to the user whether a significant organ or tissue of the brain adjacent to the ischemic region is at risk of infection, and the related description may refer to step 340, which is not repeated herein.

Step 370, generating a structured analysis report related to the target object based on a preset generation mode. In some embodiments, step 370 may be performed by processing device 120 or report generation module 240.

The preset generation mode may be a report generation built-in rule preset for the stroke analysis result. For example, format information such as analysis content of the preset report, placement order of the analysis content, highlighting manner, and the like.

In some embodiments, the preset generation mode may include a generation mode of user-defined editing. The custom editing can be that the user determines the format information of the structured analysis report by means of manual setting. In some embodiments, custom editing may include: editing at least one of analysis content of the structured analysis report, placement sequence of the analysis content, highlighting manner, and the like. The disease conditions (such as stroke types) of different patients (namely target objects) have uniqueness, and the targeted customization of the structured analysis report can be realized by enabling a user to fill in or select the content displayed by the report, so that the disease diagnosis requirements of different users (such as doctors) on different patients are met, and the disease diagnosis efficiency is improved.

In some embodiments, the processing device 120 may generate a structured analysis report related to the target subject based on the preset generation pattern and the severity of ischemic stroke or hemorrhagic stroke. In some embodiments, after determining that the stroke type corresponding to the brain scan image is no stroke or determining the severity of ischemic stroke or hemorrhagic stroke, the processing device 120 may automatically generate a structural analysis report related to the target object based on a preset generation manner.

In some embodiments, the analysis content of the structured analysis report may include stroke type, and corresponding relevant information. For example, if it is determined that the stroke type corresponding to the brain scan image is stroke-free, the analysis content of the structural analysis report may include related information indicating that the brain is normal. For another example, if the stroke type corresponding to the brain scan image is determined to be hemorrhagic stroke, the analysis content of the structural analysis report may include the severity of the hemorrhagic stroke and information related to the hemorrhagic stroke (e.g., volume of hemorrhage, location of hemorrhage, etc. in step 340). As another example, if it is determined that the stroke type corresponding to the brain scan image is ischemic stroke, the analysis content of the structural analysis report may include the severity of ischemic stroke and information related to ischemic stroke (e.g., ASPECTS score in step 350, location of ischemic region, size of ischemic region, blood supply vessels corresponding to ischemic region, core infarct volume of ischemic region, etc.). In some embodiments, the user may determine the content contained in the structured analysis report that is actually generated by modifying at least one of the analysis content automatically generated by the processing device 120 described above.

The placement order of the analysis content may be an arrangement order of the analysis content in the structured analysis report, such as up, down, left, and right. Highlighting content may refer to content that requires emphasis. For example, the severity of stroke and risk cues corresponding to the brain scan image may be highlighted. The highlighting may be a reminder to highlight the content. For example, the display may be made in a larger font, in a conspicuous color (e.g., red), in other text formats (e.g., underlined or circled text), and the like.

In some embodiments, the acute stroke analysis system 100 may be remotely connected to other analysis centers (e.g., hospitals), and the brain scan image and/or the structural analysis report of the target object may be transmitted to the other analysis centers according to the requirements of the analysis centers. In some embodiments, the brain scan image of the target object, the severity of stroke corresponding to the brain scan image, and at least a portion of the structural analysis report, may be sent to a database (e.g., Picture Archiving and Communication Systems (PACS), Radiology Information System (RIS), etc.) for archival storage.

It should be noted that the above description of the process 300 is for illustration and description only and is not intended to limit the scope of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are still within the scope of the present specification.

In some embodiments of the present description, with the system and the method for analyzing acute stroke, (1) scanning can be performed quickly and automatically and the severity of acute stroke can be determined automatically based on the acquired brain scanning protocol, and by saving the time for receiving user instructions or waiting for judgment results, the time of the whole workflow is shortened, the efficiency of stroke analysis is greatly improved, especially in an emergency scene, the analysis result of acute stroke can be obtained as soon as possible, and appropriate treatment measures can be taken for the patient as soon as possible; (2) the severity of stroke determined based on a variety of information is accurate. For example, for ischemic stroke, the severity of stroke can be determined based on the assessment of stroke, the location of the ischemic region, the size of the ischemic region, the blood supply vessels corresponding to the ischemic region, the volume of the core infarct in the ischemic region, etc., and compared with the traditional method which determines the severity of stroke only according to single or little information such as assessment of stroke, the severity of stroke can be determined more accurately; (3) different early warning conditions can be set for different information of apoplexy, so that risk prompt is diversified. The doctor can be prompted rapidly according to risks caused by different reasons, so that the doctor can diagnose in time conveniently, and the condition of the patient is prevented from being delayed; (4) the intelligent analysis of acute stroke is combined with a report structured processing method, so that the workload of a user is reduced; (5) the structured report is generated in a preset mode, the targeted customization of the structured report can be realized, and the system has high flexibility and strong adaptability.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, though not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested in this specification, and are intended to be within the spirit and scope of the exemplary embodiments of this specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which elements and sequences are described in this specification, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods described in this specification, unless explicitly stated in the claims. While certain presently contemplated useful embodiments of the invention have been discussed in the foregoing disclosure by way of various examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein described. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single disclosed embodiment.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range in some embodiments of the specification are approximations, in specific embodiments, such numerical values are set forth as precisely as possible within the practical range.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into the specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present specification can be seen as consistent with the teachings of the present specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. An acute stroke analysis system, the system comprising:

the acquisition module is used for acquiring a brain scanning protocol of a target object;

a scan execution module for instructing to execute a scan on the brain of the target subject based on the brain scan protocol of the target subject to obtain a brain scan image of the target subject; and

a stroke analysis module for determining stroke information corresponding to the brain scan image based on the brain scan image of the target object;

wherein the scan execution module and the stroke analysis module are automatically activated after the acquisition module acquires a brain scan protocol of the target subject.

2. The system of claim 1, wherein the stroke analysis module comprises:

the stroke type judging unit is used for judging the stroke type corresponding to the brain scanning image; and/or

The ischemia function unit is used for determining the cerebral apoplexy type as the ischemic apoplexy related information corresponding to the cerebral scanning image; and/or

The bleeding function unit is used for determining information related to hemorrhagic stroke corresponding to the brain scanning image when the stroke type is the hemorrhagic stroke; and/or

A severity determination unit, configured to determine a severity of stroke corresponding to the brain scan image based on the ischemic stroke related information or the hemorrhagic stroke related information.

3. The system of claim 2, wherein the ischemic Stroke related information includes at least one of an ASPECTS (Alberta Stroke Program Early CT Score, ASPECTS) Score, a location of an ischemic area, a size of the ischemic area, a blood supply vessel corresponding to the ischemic area, a core infarct volume of the ischemic area.

4. The system of claim 2, wherein the ischemia function unit is further configured to:

determining a blood supply vessel corresponding to an ischemic area using a blood supply vessel determination model based on the brain scan image of the target object.

5. The system of claim 2, wherein the ischemic function unit further comprises:

a training sample obtaining subunit configured to obtain a plurality of training samples, wherein each of the plurality of training samples includes a first sample brain image of a sample object, a second sample brain image, and at least one brain blood vessel of the sample object and a blood supply region of each brain blood vessel; and

and the model training subunit is used for acquiring a blood supply vessel determination model by training the initial model based on the plurality of training samples.

6. The system of claim 2, wherein:

the hemorrhagic stroke related information comprises the corresponding hemorrhage amount and hemorrhage position of the brain scanning image.

7. The system of claim 2, wherein the severity level comprises a criticality rating, and wherein determining the severity level of stroke corresponding to the brain scan image based on the ischemic stroke related information or hemorrhagic stroke related information comprises:

performing a threshold comparison on the ischemic stroke-related information or the hemorrhagic stroke-related information to obtain a comparison result;

based on the comparison, determining a criticality rating of the stroke to which the brain scan image corresponds.

8. The system of claim 7, further comprising:

a report generation module for generating a structured analysis report related to the target object based on a preset generation mode and the severity of the ischemic stroke or the severity of hemorrhagic stroke.

9. An acute stroke analysis method performed with the acute stroke analysis system of any one of claims 1-8, the method comprising:

acquiring a brain scanning protocol of a target object;

automatically instructing to perform a scan of the target subject's brain based on the target subject's brain scan protocol to acquire a target subject's brain scan image; and

determining stroke information corresponding to the brain scan image based on the brain scan image of the target object, wherein the stroke information corresponding to the brain scan image comprises at least a type and a severity of the stroke.

10. A computer readable storage medium storing computer instructions which, when read by a computer, cause the computer to perform the method of claim 9.