Method and device for simulating blood perfusion and electronic equipment

Abstract

The invention relates to a method and device for simulating blood perfusion and electronic equipment. The method comprises the following steps: acquiring multi-stage CT angiography data of a target tissue, and extracting a plurality of time sequence vascular images; based on the plurality of time sequence blood vessel images, extracting blood vessel structure information of the target tissue, and determining a time sequence CT value of the target tissue; and inputting the blood vessel structure information and the time sequence CT value into a pre-trained blood perfusion prediction model to generate a corresponding blood perfusion image and perfusion parameters. The present disclosure helps to reduce radiation exposure of a patient, reduce medical cost, and improve imaging efficiency of a blood perfusion image.

Description

Technical Field

[0001] The present disclosure relates to the field of CT imaging technology, and particularly to a method for simulating blood perfusion, a device for simulating blood perfusion, and an electronic device. Background Art

[0002] Computerized Tomography (CT) is a medical imaging technology. It uses an X-ray beam to perform tomographic scanning on the human body and can generate detailed images of the internal structure of the body with the aid of computer processing. The principle of computerized tomography mainly includes: based on the absorption and attenuation characteristics of X-rays penetrating human tissues, after the emitted X-ray beam penetrates the human body, the detector receives and records the attenuation signals at different angles. Since different tissues have different absorption degrees of X-rays, the attenuation signals received by the detector will vary. Based on the above attenuation signals, the CT value of each voxel in the cross-section of the human body can be calculated, and the cross-sectional image of the human body can be further reconstructed using the CT value.

[0003] Using computerized tomography, CT angiography (CTA) can be performed to examine abnormalities in the vascular morphology or vascular structure of a patient's specific tissue, such as vascular stenosis, aneurysm, vascular malformation, etc.

[0004] In addition, using computerized tomography, CT perfusion imaging (CTP) can also be performed to obtain the blood perfusion information of a patient's specific tissue, so as to evaluate the blood flow function of the patient, which is helpful for the accurate diagnosis and treatment of the patient's vascular diseases.

[0005] However, due to the large radiation dose, expensive imaging equipment, and low imaging efficiency of CTP perfusion imaging, the vast majority of patients are not suitable for CTP perfusion imaging examinations in clinical practice.

[0006] Therefore, there is an urgent need for a method for simulating blood perfusion, which needs to reduce the radiation exposure of patients, reduce medical costs, and improve the imaging efficiency of blood perfusion images. Summary of the Invention

[0007] In view of this, according to one aspect of the present disclosure, there is provided a method for simulating blood perfusion, including: obtaining multi-phase CT angiography data of a target tissue and extracting a plurality of time-series vascular images; based on the plurality of time-series vascular images, extracting the vascular structure information of the target tissue and determining the time-series CT values of the target tissue; and inputting the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

[0008] According to another aspect of the present disclosure, there is provided an apparatus for simulating blood perfusion, the apparatus comprising: a first unit configured to acquire multi-phase CT angiography data of a target tissue and extract a plurality of time-series vascular images; a second unit configured to extract vascular structure information of the target tissue and determine time-series CT values of the target tissue based on the plurality of time-series vascular images; and a third unit configured to input the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

[0009] According to yet another aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and at least one memory communicatively connected to the at least one processor; wherein the at least one memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, enable the at least one processor to perform the method for simulating blood perfusion.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings exemplarily illustrate embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments of the embodiments. The illustrated embodiments are only for illustrative purposes and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0012] Embodiments of the present disclosure will be described in detail below with reference to the drawings, so that those of ordinary skill in the art can more clearly understand the above and other features and advantages of the present disclosure. In the drawings:

[0013] Figure 1 shows a flowchart of a method for simulating blood perfusion according to an embodiment of the present disclosure;

[0014] Figure 2 shows a flowchart of a method for training a blood perfusion prediction model according to an embodiment of the present disclosure;

[0015] Figure 3 shows a structural block diagram of an apparatus for simulating blood perfusion according to an embodiment of the present disclosure; and

[0016] Figure 4 shows a block diagram of an exemplary electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] In the present disclosure, unless otherwise specified, the terms "first", "second", etc. are used to describe various elements and are not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, and in certain cases, based on the context description, they may also refer to different instances.

[0019] In the descriptions of various examples in the present disclosure, the terms used are only for the purpose of describing specific examples and are not intended to be restrictive. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in the present disclosure covers any one of the listed items and all possible combinations.

[0020] As described above, professionals can use computed tomography perfusion (CTP) imaging to obtain blood perfusion information of a patient's specific tissue, thereby evaluating the patient's blood flow function. In some scenarios, the patient does not have the conditions for CTP perfusion imaging. For example, the patient's physical condition does not allow the injection of a large dose of contrast agent, the patient's condition is urgent and cannot wait for the results of perfusion imaging, or the medical facilities in the patient's area are relatively backward and there is no medical equipment required for CTP perfusion imaging. The situations cited are often common, resulting in professionals being able to only judge the patient's vascular condition through the structural images obtained by CT angiography, and thus unable to make an accurate judgment on the patient's vascular lesion situation in a timely manner.

[0021] Based on this, the present disclosure provides a method for simulating blood perfusion, a device for simulating blood perfusion, and an electronic device.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 A flowchart of a method 100 for simulating blood perfusion according to an embodiment of the present disclosure is shown.

[0024] Refer to Figure 1 , the method 100 for simulating blood perfusion includes:

[0025] Step S110: Obtain multi-phase CT angiography data of the target tissue and extract multiple time-series vascular images;

[0026] Step S120: Based on the multiple time-series vascular images, extract the vascular structure information of the target tissue and determine the time-series CT values of the target tissue; and

[0027] Step S130: Input the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

[0028] In the example of Step S110, multi-phase CT angiography is also known as multi-temporal CT angiography. Compared with general single-phase CT angiography techniques, this technique acquires CT angiography data at multiple time points (phases) instead of a single phase. Therefore, multi-phase CT angiography has temporal resolution, that is, it can display the filling state of blood vessels and hemodynamic changes more comprehensively, so as to better dynamically evaluate the collateral circulation state. Especially in diseases such as acute ischemic stroke, it can more accurately reflect the compensatory level of collateral circulation.

[0029] In addition, in the method for simulating blood perfusion according to the embodiments of the present disclosure, the different time points for acquiring CT angiography data in multi-phase CT angiography may at least include the arterial peak phase, the venous peak phase, and the late venous phase. Among them, the arterial peak phase refers to the time point when the contrast agent reaches the maximum density in the arterial system of the target tissue. At this time, the arterial system is most clearly visualized, so that the anatomical structure and blood flow state of the artery can be clearly displayed; the venous peak phase refers to the time point when the contrast agent reaches the maximum density in the venous system of the target tissue. The venous system is most clearly visualized, so that the venous system is well filled during this period, and the hemodynamic state of the vein and the venous outflow can be better evaluated; the late venous phase refers to the stable period after the contrast agent density in the venous system begins to decline, usually after the venous peak phase. During this period, the visualization of the venous system gradually weakens, but the delayed visualization of the venous system can be observed, so as to evaluate the state of the venous collateral circulation. When the CT angiography data simultaneously includes data at the above three time points, the vascular state can be comprehensively evaluated, and the dynamic changes of blood flow can be captured to a certain extent.

[0030] It should be noted that whether the contrast agent reaches the maximum density or remains stable in the arterial and venous systems is determined based on the change in CT values in specific regions of the arterial and venous systems. The specific region can be obtained by automatically identifying the arterial / venous system region in the target tissue or by a professional designating the region of interest (ROI) corresponding to the arterial / venous system of the target tissue. After determining the specific region, the change in CT values of the specific region over time can be obtained and recorded by scanning to obtain the time-density curve of the specific region. When the CT value of the time-density curve reaches the peak, it can be determined that the contrast agent reaches the maximum density, and when the CT value drops to almost unchanged, it can be determined that the density of the contrast agent remains stable. It is also possible to preset the arterial density peak threshold, venous density peak threshold, and venous density stability threshold. When the obtained CT values reach the above thresholds respectively, it can be determined as the arterial peak phase, venous peak phase, and venous late phase. It is also possible to determine the arterial peak phase, venous peak phase, and venous late phase and collect the corresponding CT angiography data according to clinical data or experience after delaying a specific duration after injecting the contrast agent into the patient.

[0031] In the example of step S110, the target tissue refers to the tissue to be detected in the patient. Since multi-phase CT angiography has the time resolution as described above and has important value in the diagnosis and treatment decision-making of diseases such as acute ischemic stroke and cerebrovascular diseases, the target tissue is generally the brain tissue of the patient. However, it should be understood that the method for simulating blood perfusion in the embodiments of the present disclosure is not limited to simulating the blood perfusion of the brain tissue, and can also simulate the blood perfusion information of tissues such as the heart and liver to assist in the diagnosis and treatment of related diseases.

[0032] Based on this, when obtaining the multi-phase CT angiography data of the target tissue, multiple time-series vascular images can be extracted. Among them, each acquisition time point (phase) contains at least one corresponding vascular image.

[0033] In the example of step S120, the vascular structure information of the target tissue is extracted from the multiple time-series vascular images, and the time-series CT values of the target tissue are determined.

[0034] In this example, according to the characteristics of CT angiography technology, the time-series CT values of the target tissue only include the CT values of the acquired time points (phases), and for other time points (phases), they are not acquired. The extracted vascular structure information can be a fused image generated from multiple time-series vascular images, or an image selected from multiple time-series vascular images that best reflects the vascular structure of the target tissue. In addition, the vascular structure information can also be presented in other forms, for example, in the form of a set of CT values or linear attenuation coefficients.

[0035] In the example of step S130, the vascular structure information and time-series CT values are input into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

[0036] In the example, no specific limitation is imposed on the pre-trained blood perfusion prediction model employed. For example, a model based on a convolutional neural network (CNN), long short-term memory network (LSTM), gated recurrent unit (GRU), graph convolutional network (GCN), or a hybrid model can be used.

[0037] In addition, in the example of step S130, the generated blood perfusion image can be a dynamic image or a static image generated based on the vascular structure information of the target tissue extracted from multiple time-series vascular images and the perfusion parameters predicted by the blood perfusion prediction model. When the target tissue is the heart, a bull's-eye diagram that can effectively reflect myocardial perfusion can also be generated.

[0038] The collected perfusion parameters may include: blood volume (BV), which is the amount of blood contained in a unit mass of tissue, with the unit of mL / 100g; blood flow (BF), which refers to the amount of blood flowing through a unit mass of tissue per unit time, with the unit of mL / min / 100g; mean transit time (MTT), which refers to the average time for blood to pass through the capillary bed from the arterial side to the venous side, with the unit of seconds (s) or minutes (min). When the target tissue is the brain tissue, the collected perfusion parameters are cerebral blood volume, cerebral blood flow, and mean transit time.

[0039] Compared with the traditional CTP perfusion imaging method that requires collecting the time-density curve of the entire period of the target tissue, the method of the embodiments of the present disclosure only needs to collect data at a plurality of pre-determined time points (periods), thereby effectively reducing the dose of the contrast agent required, reducing radiation exposure, and significantly shortening the time required for data collection and post-processing to improve the imaging efficiency. In addition, since the traditional CTP perfusion imaging method requires specialized equipment and the cost of this equipment is high, the price of CTP perfusion imaging is high and the popularity is poor. However, the method of the embodiments of the present disclosure only relies on the general equipment for CT angiography, thereby effectively reducing the cost of obtaining blood perfusion information.

[0040] Figure 2 The flowchart of a method 200 for training a blood perfusion prediction model is shown. As Figure 2 shown, according to some embodiments, method S200 may include:

[0041] Step S210, initialize the blood perfusion prediction model;

[0042] Step S220: Obtain multiple training sample data. Each training sample data includes: first image data collected through multi-phase CT angiography, where the first image data includes vascular structure information and time-series CT values; and second image data collected through corresponding CTP perfusion imaging, where the second image data includes CTP perfusion images and perfusion parameters calculated based on the CTP perfusion images. The acquisition time and acquisition location of the first image data and the second image data are the same; and

[0043] Step S240: Use the first image data as input to train the blood perfusion prediction model to optimize the model parameters of the blood perfusion prediction model.

[0044] In the example of step S210, initializing the blood perfusion prediction model may include initializing the model parameters. For example, all model parameters can be initialized to zero using the zero-initialization method, or the parameters of the model can be randomly assigned initial values using a random distribution method such as a uniform distribution or a Gaussian distribution. It should be noted that the method of initialization is not specifically limited here, and the initialization strategy can be selected according to the actual situation.

[0045] In the example of step S220, each training sample contains an image pair, specifically including a first image data collected through multi-phase CT angiography and a second image data collected through corresponding CTP perfusion imaging. Among them, in order to ensure that the data in the image pair is in one-to-one correspondence, the first image data and the second image data in each image pair need to be collected at the same acquisition location and acquisition time.

[0046] In the example of step S240, use the first image data in multiple training samples as input to train the blood perfusion prediction model, thereby optimizing the initialized model parameters.

[0047] As mentioned above, multi-phase CT angiography has time resolution and can capture the dynamic changes of blood flow, which matches the dynamic characteristics of blood perfusion information. Therefore, using the first image data collected through multi-phase CT angiography as input to train the blood perfusion prediction model can obtain a blood perfusion prediction model with relatively accurate prediction ability.

[0048] Continue to refer to Figure 2 , the method 200 for training the blood perfusion prediction model may further include:

[0049] Step S250: Input the first image data into the blood perfusion prediction model to enable the blood perfusion prediction model to generate corresponding blood perfusion images and simulated perfusion parameters;

[0050] Step S260: Verify the blood perfusion prediction model by comparing the generated blood perfusion image and the simulated perfusion parameters with the second image data.

[0051] In the examples of steps S250 and S260, in addition to optimizing the model parameters, the first image data as input can also generate corresponding blood perfusion images and simulated perfusion parameters. Then, by comparing the generated blood perfusion images and simulated perfusion parameters with the second image data, the blood perfusion prediction model can be verified. The advantage of doing this is that since the second image data corresponds to the first image data, the second image data can evaluate the accuracy of the model prediction and further optimize the model parameters.

[0052] Continue to refer to Figure 2 , before step S230, the method 200 for training the blood perfusion prediction model may further include:

[0053] Step S230: Preprocess the first image data, and the preprocessing includes image alignment, image denoising, and / or normalization processing.

[0054] In the example of step S230, preprocessing the first image data can improve the training effect of the prediction model and the accuracy of generating blood perfusion images and simulated perfusion parameters.

[0055] Among them, image alignment may include aligning the first image data collected at different acquisition time points so that the corresponding points of multiple first image data exactly coincide in the same coordinate system. Image alignment may also include aligning the first image data with a pre-specified standard image. Image denoising is a process of reducing image noise through specific algorithms or techniques, aiming to improve the image quality to make it clearer and easier to analyze. Normalization processing is a process of converting multiple first image data to a unified scale or range, aiming to ensure the comparability and consistency between different images. For example, mean normalization can be achieved by subtracting the mean value of each pixel of the first image data and then dividing by the standard deviation, so that the pixel value distribution of the image is more balanced.

[0056] In addition, in some embodiments of the present disclosure, for a pre-trained blood perfusion prediction model, the model parameters can also be automatically adjusted based on the patient's pathological data, so as to be able to comprehensively consider the physical conditions of each patient individual and more accurately predict the patient's blood perfusion information.

[0057] According to another aspect of the present disclosure, a device for simulating blood perfusion is provided.

[0058] Figure 3 The structural block diagram of the device 300 for simulating blood perfusion according to an embodiment of the present disclosure is shown. AsFigure 3 As shown in Figure 3 , the device 300 for simulating blood perfusion includes:

[0059] A first unit 310 configured to acquire multi-phase CT angiography data of a target tissue and extract a plurality of time-series vascular images;

[0060] A second unit 320 configured to extract vascular structure information of the target tissue based on the plurality of time-series vascular images and determine time-series CT values of the target tissue; and

[0061] A third unit 330 configured to input the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

[0062] It should be understood that Figure 3 each unit of the device 300 shown in Figure 3 may correspond to steps S110-S130 in the method 100 described with reference to Figure 1 Accordingly, the operations, features, and advantages described above for the method 100 also apply to the device 300 and the units included therein. For the sake of brevity, certain operations, features, and advantages are not described herein again.

[0063] Although specific functions have been discussed above with reference to specific units, it should be noted that the functions of the various units discussed herein can be divided into multiple units, and / or at least some of the functions of multiple units can be combined into a single unit. The actions performed by a specific unit discussed herein include that the specific unit itself performs the action, or alternatively the specific unit calls or otherwise accesses another component or unit that performs the action (or performs the action in combination with the specific unit). Thus, a specific unit that performs an action may include the specific unit itself that performs the action and / or another unit that the specific unit calls or otherwise accesses and that performs the action.

[0064] It should also be understood that various techniques may be described herein in the general context of software-hardware elements or program units. Regarding the above Figure 3The described units can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these units can be implemented as computer program code / instructions configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of the first unit 310, the second unit 320, and the third unit 330 can be implemented together in a System on Chip (SoC). The SoC can include an integrated circuit chip (which includes one or more components such as a processor (e.g., a Central Processing Unit (CPU), a microcontroller, a microprocessor, a Digital Signal Processor (DSP), etc.), a memory, one or more communication interfaces, and / or other circuits), and can optionally execute the received program code and / or include embedded firmware to perform functions.

[0065] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method for simulating blood perfusion as described above.

[0066] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing a computer program, where the computer program is used to cause a computer to execute the method for simulating blood perfusion as described above.

[0067] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, where the computer program implements the method for simulating blood perfusion as described above when executed by a processor.

[0068] Figure 4 FIG. is a block diagram showing an example of an electronic device 400 according to an exemplary embodiment of the present disclosure. It should be noted that Figure 4 The structure shown is only an example, and according to specific implementation manners, the electronic device of the present disclosure can include only Figure 4 one or more of the components shown.

[0069] The electronic device 400 can be, for example, a general-purpose computer (such as various computers like a laptop computer, a tablet computer, etc.), a mobile phone, or a personal digital assistant. According to some embodiments, the electronic device 400 can be a cloud computing device and an intelligent device. According to some embodiments, the electronic device 400 can be an X-ray imaging device, such as a Computed Tomography (CT) device.

[0070] According to some embodiments, the electronic device 400 may be configured to process at least one of an image, text, and audio, and transmit the processing result to an output device for providing to a user. The output device may be, for example, a display screen, a device including a display screen, or a sound output device such as headphones, speakers, or an oscillator. For example, the electronic device 400 may be configured to perform object detection on an image, transmit the object detection result to a display device for display, and the electronic device 400 may also be configured to perform enhancement processing on the image and transmit the enhancement result to the display device for display. The electronic device 400 may also be configured to recognize text in the image, transmit the recognition result to the display device for display and / or convert the recognition result into sound data and transmit it to a sound output device for playback. The electronic device 400 may also be configured to recognize and process audio, transmit the recognition result to the display device for display and / or convert the processing result into sound data and transmit it to a sound output device for playback.

[0071] The electronic device 400 may include an image processing circuit 403, and the image processing circuit 403 may be configured to perform various image processing operations on an image. The image processing circuit 403 may be configured to perform at least one of the following image processing operations on the image: noise reduction of the image, normalization processing of the image, registration of the image, geometric correction of the image, feature extraction of the image, detection and / or recognition of an object in the image, enhancement processing of the image, and detection and / or recognition of text included in the image, etc.

[0072] The electronic device 400 may further include a text recognition circuit 404, and the text recognition circuit 404 is configured to perform text detection and / or recognition (such as OCR processing) on a text area in an image to obtain text data. The text recognition circuit 404 may be implemented by, for example, a dedicated chip. The electronic device 400 may also include a sound conversion circuit 405, and the sound conversion circuit 405 is configured to convert the text data into sound data. The sound conversion circuit 405 may be implemented by, for example, a dedicated chip.

[0073] The electronic device 400 may further include an audio processing circuit 406, and the audio processing circuit 406 is configured to convert audio into text to obtain text data corresponding to the audio. The audio processing circuit 406 may also be configured to process the text data corresponding to the audio, for example, it may include keyword extraction, intent recognition, intelligent recommendation, and intelligent question and answer, etc. The audio processing circuit 406 may be implemented by, for example, a dedicated chip. The sound conversion circuit 405 may also be configured to convert the audio processing result into sound data to be applicable to application scenarios such as voice assistants or virtual customer services.

[0074] One or more of the various circuits described above (such as the image processing circuit 403, the character recognition circuit 404, the voice conversion circuit 405, and the audio processing circuit 406) may use custom hardware and / or may be implemented in hardware, software, firmware, middleware, microcode, a hardware description language, or any combination thereof. For example, one or more of the various circuits described above may be implemented by programming hardware (such as a programmable logic circuit including a field programmable gate array (FPGA) and / or a programmable logic array (PLA)) using assembly language or a hardware programming language (such as VERILOG, VHDL, C++) according to the logic and algorithms of the present disclosure.

[0075] According to some embodiments, the electronic device 400 may further include an output device 407, and the output device 407 may be any type of device for presenting information, and may include but is not limited to a display screen, a terminal with a display function, headphones, speakers, a vibrator, and / or a printer, etc.

[0076] According to some embodiments, the electronic device 400 may further include an input device 408, and the input device 408 may be any type of device for inputting information to the electronic device 400, and may include but is not limited to various sensors, a mouse, a keyboard, a touch screen, buttons, a joystick, a microphone, and / or a remote control, etc.

[0077] According to some embodiments, the electronic device 400 may further include a communication device 409, and the communication device 409 may be any type of device or system that enables communication with an external device and / or with a network, and may include but is not limited to a modem, a network card, an infrared communication device, a wireless communication device, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0078] According to some embodiments, the electronic device 400 may further include a processor 401. The processor 401 may be any type of processor, and may include but is not limited to one or more general-purpose processors and / or one or more dedicated processors (such as a special processing chip). The processor 401 may be, for example, but is not limited to a central processing unit CPU, a graphics processing unit GPU, or various dedicated artificial intelligence (AI) computing chips, etc.

[0079] The electronic device 400 may further include a working memory 402 and a storage device 411. The processor 401 may be configured to be able to obtain and execute computer-readable instructions stored in the working memory 402, the storage device 411, or other computer-readable media, such as the program code of the operating system 402a, the program code of the application 402b, etc. The working memory 402 and the storage device 411 are examples of computer-readable storage media for storing instructions, and the stored instructions can be executed by the processor 401 to implement the various functions described above. The working memory 402 may include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). The storage device 411 may include a hard disk drive, a solid-state drive, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical discs (e.g., CD, DVD), storage arrays, network-attached storage, storage area networks, etc. The working memory 402 and the storage device 411 may both be collectively referred to as memory or computer-readable storage media in this article, and may be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code, and the computer program code may be executed by the processor 401 as a specific machine configured to implement the operations and functions described in the examples in this article.

[0080] According to some embodiments, the processor 401 may control and schedule at least one of the image processing circuit 403, the character recognition circuit 404, the voice conversion circuit 405, the audio processing circuit 406, and various other devices and circuits included in the electronic device 400. According to some embodiments, Figure 4 at least some of the various components described above may be interconnected and / or communicate with each other via the bus 410.

[0081] Software elements (programs) may be located in the working memory 402, including but not limited to the operating system 402a, one or more applications 402b, drivers, and / or other data and code.

[0082] According to some embodiments, the instructions for performing the foregoing control and scheduling may be included in the operating system 402a or one or more applications 402b.

[0083] According to some embodiments, the instructions for performing the method steps described in the present disclosure may be included in one or more application programs 402b, and each module of the electronic device 400 may be implemented by the processor 401 reading and executing the instructions of one or more application programs 402b. In other words, the electronic device 400 may include a processor 401 and a memory for storing programs (such as the working memory 402 and / or the storage device 411), and the programs include instructions that, when executed by the processor 401, cause the processor 401 to execute the methods described in various embodiments of the present disclosure.

[0084] According to some embodiments, part or all of the operations performed by at least one of the image processing circuit 403, the character recognition circuit 404, the voice conversion circuit 405, and the audio processing circuit 407 may be implemented by the processor 401 reading and executing the instructions of one or more application programs 402b.

[0085] The executable code or source code of the instructions of the software element (program) may be stored in a non-transitory computer-readable storage medium (such as the storage device 411), and when executed, may be loaded into the working memory 402 (possibly compiled and / or installed). Therefore, the present disclosure provides a computer-readable storage medium storing a program, the program including instructions that, when executed by a processor of an electronic device, cause the electronic device to execute the methods described in various embodiments of the present disclosure. According to another embodiment, the executable code or source code of the instructions of the software element (program) may also be downloaded from a remote location.

[0086] It should also be understood that various modifications can be made according to specific requirements. For example, custom hardware may also be used, and / or each circuit, unit, module, or component may be implemented using hardware, software, firmware, middleware, microcode, a hardware description language, or any combination thereof. For example, some or all of the circuits, units, modules, or components included in the disclosed methods and devices may be implemented by programming hardware (such as programmable logic circuits including field programmable gate arrays (FPGAs) and / or programmable logic arrays (PLAs)) using the logic and algorithms according to the present disclosure, with an assembly language or a hardware programming language (such as VERILOG, VHDL, C ++).

[0087] According to some embodiments, the processor 401 in the electronic device 400 may be distributed over a network. For example, one processor may be used to perform some processing, while another processor located away from the one processor may perform other processing simultaneously. Other modules of the electronic device 400 may be similarly distributed. In this way, the electronic device 400 can be interpreted as a distributed computing system that performs processing at multiple locations. The processor 401 of the electronic device 400 may also be a processor of a cloud computing system or a processor incorporating a blockchain.

[0088] Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above methods, systems, and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only defined by the authorized claims and their equivalent scope. Various elements in the embodiments or examples may be omitted or replaced by their equivalent elements. In addition, the steps may be executed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, with the evolution of technology, many of the elements described herein may be replaced by equivalent elements that emerge after the present disclosure.

Claims

1. A method for simulating blood perfusion, comprising: Obtaining multi-phase CT angiography data of a target tissue, and extracting a plurality of time-series vascular images; Based on the plurality of time-series vascular images, extracting vascular structure information of the target tissue, and determining time-series CT values of the target tissue; And Inputting the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

2. The method according to claim 1, wherein The training of the blood perfusion prediction model includes: Initializing the blood perfusion prediction model; Obtaining a plurality of training sample data, each training sample data including: First image data collected by the multi-phase CT angiography, the first image data including vascular structure information and time-series CT values; and Second image data collected by corresponding CTP perfusion imaging, the second image data including CTP perfusion images and perfusion parameters calculated based on the CTP perfusion images, wherein the acquisition time and acquisition position of the first image data are the same as those of the second image data; and Using the first image data as input to train the blood perfusion prediction model to optimize the model parameters of the blood perfusion prediction model.

3. The method according to claim 2, wherein, The training of the blood perfusion prediction model further includes: Inputting the first image data into the blood perfusion prediction model to cause the blood perfusion prediction model to generate corresponding blood perfusion images and simulated perfusion parameters; Verifying the blood perfusion prediction model by comparing the generated blood perfusion images and simulated perfusion parameters with the second image data.

4. The method according to claim 3, wherein Before inputting the first image data into the blood perfusion prediction model for training, it further includes: Preprocessing the first image data, the preprocessing including image alignment, image denoising, and / or normalization processing.

5. The method according to any one of claims 1 to 4, wherein, The multi-phase CT angiography data includes CT angiography data collected at different time points, and the different time points at least include arterial peak phase, venous peak phase, and venous late phase.

6. The method according to any one of claims 1 to 4, wherein, Obtaining multi-phase CT angiography data of a target tissue includes obtaining multi-phase CT angiography data of a brain tissue.

7. The method according to claim 6, wherein, The perfusion parameters generated by the blood perfusion prediction model include blood flow, blood volume, and mean transit time.

8. The method according to claim 2, wherein, The blood perfusion prediction model automatically adjusts the model parameters based on the patient's pathological data.

9. A device for simulating blood perfusion, the device comprising: A first unit configured to obtain multi-phase CT angiography data of a target tissue and extract a plurality of time-series vascular images; A second unit configured to extract vascular structure information of the target tissue and determine time-series CT values of the target tissue based on the plurality of time-series vascular images; And A third unit configured to input the vascular structure information and the time-series CT values into a pre-trained blood perfusion prediction model to generate corresponding blood perfusion images and perfusion parameters.

10. An electronic device, comprising: At least one processor; And At least one memory communicatively connected to the at least one processor; Wherein The at least one memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-8.

Images