Image processing method, system, storage medium and electronic device

Abstract

The application provides an image processing method, system, storage medium and electronic device. The image processing method comprises: generating a second mask according to a first mask, the second mask comprising the first mask and a small blood vessel mask; modifying corresponding voxel points in a first image according to the small blood vessel mask to obtain a second image; and training a blood vessel segmentation model using the second image and the second mask. The image processing method can improve the sensitivity of the blood vessel segmentation model to small blood vessels.

Description

Technical Field

[0001] This application belongs to the field of image processing technology, and relates to an image processing method, system, storage medium and electronic device. Background Technology

[0002] Vascular segmentation is a crucial task in medical image processing, aiming to accurately extract and separate vascular structures from medical images. Taking coronary CTA (Computed Tomography Angiography) segmentation as an example, coronary CTA segmentation requires accurately segmenting the vascular mask, and the segmentation result should include as many complete arterial vessels as possible. However, the segmentation accuracy of existing vascular segmentation models is generally low. Summary of the Invention

[0003] This application provides an image processing method, system, storage medium, and electronic device for improving the segmentation accuracy of a blood vessel segmentation model.

[0004] In a first aspect, embodiments of this application provide an image processing method, the image processing method comprising: generating a second mask based on a first mask, the second mask including the first mask and a small blood vessel mask; modifying corresponding voxel points in a first image based on the small blood vessel mask to obtain a second image; and training a blood vessel segmentation model using the second image and the second mask.

[0005] In one implementation of the first aspect, the image processing method further includes: eroding the first mask to obtain a third mask; and obtaining the fine blood vessel mask based on the first mask and the third mask.

[0006] In one implementation of the first aspect, obtaining the microvascular mask based on the first mask and the third mask includes: subtracting the third mask from the first mask to obtain a set of vessel wall points; obtaining the starting growth point of the microvascular from the set of vessel wall points; and growing the microvascular based on the starting growth point to obtain the microvascular mask.

[0007] In one implementation of the first aspect, the growth of small blood vessels based on the starting growth point includes: growing small blood vessels iteratively starting from the starting growth point, wherein the direction of blood vessel growth is randomly selected according to a preset probability, the blood vessel diameter is a preset value, and after a certain number of iterations, the probability of selecting the main growth direction increases and the blood vessel diameter decreases.

[0008] In one implementation of the first aspect, modifying corresponding voxel points in a first image according to the small blood vessel mask to obtain a second image includes: obtaining the blood vessel distribution in the first image; and filling the voxel points in the first image corresponding to the small blood vessel mask according to the blood vessel distribution to obtain the second image.

[0009] In one implementation of the first aspect, the image processing method further includes: performing Gaussian filtering on the second image.

[0010] In one implementation of the first aspect, the image processing method further includes: processing the third image using the blood vessel segmentation model to achieve blood vessel segmentation of the third image.

[0011] Secondly, embodiments of this application provide an image processing system, the image processing system comprising: a mask generation module, configured to generate a second mask based on a first mask, the second mask including the first mask and a small blood vessel mask; an image generation module, configured to modify corresponding voxel points in a first image based on the small blood vessel mask to obtain a second image; and a model training module, configured to train a blood vessel segmentation model using the second image and the second mask.

[0012] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any one of the first aspects of this application.

[0013] Fourthly, embodiments of this application provide an electronic device, the electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, which executes the method described in any one of the first aspects of this application when the computer program is invoked.

[0014] This application provides an image processing method. The second mask includes an original mask for blood vessels and a mask for small blood vessels. The second segmented image is obtained by further processing the original image, making it more realistic. Therefore, the blood vessel segmentation model trained using the second mask and the second image has higher sensitivity to small blood vessels and higher segmentation accuracy. Attached Figure Description

[0015] Figure 1 The diagram shown is a hardware architecture diagram of the electronic device involved in the embodiments of this application.

[0016] Figure 2A The flowchart shown is an example of an image processing method provided in this application.

[0017] Figure 2BThe diagram shown is an example of the first mask in an embodiment of this application.

[0018] Figure 2C The diagram shown is an example of the second mask in an embodiment of this application.

[0019] Figure 3A The flowchart shown is a process for obtaining a small blood vessel mask in an embodiment of this application.

[0020] Figure 3B The flowchart shown is a process for obtaining a small blood vessel mask in an embodiment of this application.

[0021] Figure 4A The flowchart shown is a process for obtaining the second image in an embodiment of this application.

[0022] Figure 4B The image shown is an example of the first image in an embodiment of this application.

[0023] Figure 4C The image shown is an example of the second image in an embodiment of this application.

[0024] Figure 4D The image shown is an example of the fused image in an embodiment of this application.

[0025] Figure 5 The diagram shown is a schematic representation of the image processing system in an embodiment of this application.

[0026] Figure 6 The diagram shown is a structural schematic of an electronic device in an embodiment of this application.

[0027] Component designation explanation

[0028] 100 Electronic devices

[0029] 101 processor

[0030] 102 Output devices

[0031] 103 Input Devices

[0032] 104 memory units

[0033] 105 Communication Interface

[0034] 106 Storage Media

[0035] 107 processor

[0036] 5 Image Processing System

[0037] 51 Mask Generation Module

[0038] 52 Image Generation Module

[0039] 53 Model Training Module

[0040] 6 Electronic devices

[0041] 61 Memory

[0042] 62 processor

[0043] 63 Monitors

[0044] Steps S21 to S23

[0045] Steps S31 to S32

[0046] Steps S321~S323

[0047] Steps S41 to S42 Detailed Implementation

[0048] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0049] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the illustrations only show the components related to this application and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0050] Vascular segmentation is a crucial task in medical image processing, aiming to accurately extract and separate vascular structures from medical images. Taking coronary CTA segmentation as an example, it requires accurately segmenting the vascular mask, with the segmentation result needing to include as many complete arterial vessels as possible. However, numerous small vessels often exist at the distal ends of blood vessels. These small vessels are relatively small in size and generally have low CT values, making them easily overlooked during annotation. This results in poor recognition of small vessels by vascular segmentation models, thus affecting the accuracy of the segmentation results. Therefore, how to increase the number and size of small vessels in the segmentation results, thereby improving the recognition performance of vascular segmentation models for small vessels, has become one of the urgent technical problems to be solved by relevant technicians.

[0051] To address at least the aforementioned problems, embodiments of this application provide an image processing method. The second mask includes an original mask for blood vessels and a mask for small blood vessels. The second segmented image is an image obtained through further processing of the original image, making it closer to the original image. Therefore, the blood vessel segmentation model trained using the second mask and the second image has higher sensitivity to small blood vessels and achieves higher segmentation accuracy.

[0052] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0053] The image processing method provided in this application can be applied to electronic devices. Figure 1 The diagram shown is a structural schematic of an electronic device 100 in an embodiment of this application. Figure 1 As shown, the electronic device 100 includes a processor 101 connected to one or more data storage units. The data storage units may include a storage medium 106 and a memory unit 104. The storage medium 106 may be read-only, such as read-only memory (ROM), or read-write, such as a hard disk or flash memory. The memory unit 104 may be random access memory (RAM). The memory unit 104 may be integrated with the processor 101 or may be a separate component. The processor 101 is the control center of the electronic device 100, used to execute program code to implement functions corresponding to the program instructions. In some possible implementations, the processor 101 includes one or more central processing units (CPUs), for example, such as... Figure 1 CPU0 and CPU1 are shown. In some possible implementations, the electronic device 100 includes more than one processor, for example, such as... Figure 1 Processors 101 and 107 are shown. Both processors 101 and 107 can be single-core or multi-core processors. It should be noted that the term "processor" as used herein refers to one or more devices, circuits, and / or processing cores used to process data such as computer program instructions.

[0054] The CPU of processors 101 and / or 107 stores the program code to be executed in memory unit 104 or storage medium 106. In some possible implementations, the program code stored in storage medium 106 can be copied to memory unit 104 for processor execution. The processor can control the operation of electronic device 100 by controlling the execution of other programs, controlling communication with peripheral devices, and controlling the use of resources of electronic device 100 through the kernel.

[0055] The electronic device 100 may also include a communication interface 105 through which the electronic device 100 can communicate directly with another device or system or through an external network.

[0056] In some possible implementations, the electronic device 100 also includes an output device 102 and an input device 103. The output device 102 is connected to the processor 101 and is capable of displaying output information in one or more ways. An example of the output device 102 is a visual display device, such as a liquid crystal display (LCD), a light-emitting diode (LED) display, a cathode ray tube (CRT), or a projector. The input device 103 is connected to the processor 101 and is capable of receiving user input in one or more ways. Examples of the input device 103 include a mouse, keyboard, touchscreen device, sensing device, and so on.

[0057] The aforementioned components of electronic device 100 can be interconnected through any one or more combinations of buses such as data bus, address bus, control bus, expansion bus, and local bus.

[0058] Electronic device 100 can be a general-purpose electronic device or an application-specific electronic device. As a practical example, the aforementioned electronic device 100 can be a storage array, application server, supercomputer, desktop computer, laptop computer, personal digital assistant (PDA), mobile phone, tablet computer, wireless terminal device, telecommunications equipment, or have similar functions. Figure 1 Any other device with a similar structure as shown. However, this application is not limited to any particular type of electronic device. After the program code with different functions stored in memory 104 is run by the processor (processor 101 or processor 107), a process is formed. During process execution, the processor needs to allocate a memory space to each process to store the data generated during process execution. To facilitate data communication between processes, the processor (processor 101 or processor 107) typically allocates a shared memory segment in memory and distributes the shared memory to multiple processes that need to share data. The processes in the embodiments of this application can be virtual machines, containers, and any other processes with data sharing requirements.

[0059] Figure 2A The flowchart shown is an example of an image processing method provided in this application. Figure 2A As shown, the image processing method includes the following steps S21 to S23.

[0060] S21, Generate a second mask based on the first mask, the second mask comprising the first mask and the small blood vessel mask.

[0061] Exemplarily, the first mask is an original mask generated from the original image. This original mask can be obtained by processing the original image. Adding a small blood vessel mask to the first mask yields a second mask. Example diagrams of the first and second masks in embodiments of this application are shown below. Figure 2B and Figure 2C As shown.

[0062] S22, Modify the corresponding voxel points in the first image according to the small blood vessel mask to obtain the second image.

[0063] For example, the first image is the original image. A second image can be obtained by modifying the corresponding voxel points in the first image using a fine blood vessel mask. The second image is very close to the first image in appearance.

[0064] S23, a blood vessel segmentation model is trained using the second image and the second mask. The blood vessel segmentation model may be, for example, U-Net, V-Net, VGG16, etc., but this application is not limited to these models.

[0065] Please see Figure 3A In some possible implementations, the image processing method may also include the following steps S31 and S32.

[0066] S31, perform etching on the first mask to obtain the third mask. Etching is a mathematical morphological operation that can shrink the foreground region in the first mask, thereby obtaining the third mask.

[0067] For example, during the etching process described in step S31, a convolution kernel can be used to slide through the first mask. During the traversal, if the convolution kernel matches a voxel in the first mask, that voxel will be retained; otherwise, it will be eliminated. After sliding through all voxels in the first mask using the convolution kernel, the third mask is obtained.

[0068] S32, obtain the small blood vessel mask based on the first mask and the third mask.

[0069] Figure 3B This is a flowchart illustrating the process of obtaining a small blood vessel mask based on a first mask and a third mask, as shown in an embodiment of this application. Figure 3B As shown, obtaining a small blood vessel mask based on the first mask and the third mask includes the following steps S321 to S323.

[0070] S321, use the first mask to subtract the third mask to obtain the blood vessel wall point set.

[0071] S322, obtain the initial growth point of small blood vessels from the concentration of blood vessel wall points.

[0072] For example, in step S322, several points can be randomly selected from the set of blood vessel wall points as the starting growth points of small blood vessels.

[0073] For example, in step S322, the sensitivity of the blood vessel segmentation model to small blood vessels can be improved by increasing the number of starting growth points.

[0074] S323, based on the starting growth point, grows small blood vessels to obtain a small blood vessel mask.

[0075] In some possible implementations, the growth of small blood vessels based on the starting growth point includes: growing small blood vessels iteratively starting from the starting growth point, wherein the initial main growth direction of each small blood vessel is randomly determined, the growth direction of the blood vessel is randomly selected according to a preset probability, the blood vessel diameter is a preset value, and after a certain number of iterations, the probability of selecting the main growth direction increases and the blood vessel diameter decreases.

[0076] For example, for any starting growth point, a preset blood vessel diameter and an initial main growth direction are randomly determined, and small blood vessels are grown according to the randomly determined initial main growth direction. During the small blood vessel growth process, a growth direction is randomly selected according to a specific probability, and a circular blood vessel cross-section is generated according to the preset blood vessel diameter. For example, if the randomly determined main growth direction is the X direction, the growth probabilities in the X, Y, and Z directions can be 0.6, 0.2, and 0.2, respectively. After several iterations, the probability of selecting the main growth direction is increased and the probability of other directions is decreased. For example, at a certain moment, the growth probabilities in the X, Y, and Z directions can be modified to 0.7, 0.15, and 0.15. After the stopping condition is met, the small blood vessel growth ends, and a small blood vessel mask can be obtained. The stopping condition can be set according to actual needs, such as reaching a preset number of iterations.

[0077] Figure 4A This is a flowchart illustrating how, in an embodiment of this application, corresponding voxel points in a first image are modified based on a small blood vessel mask to obtain a second image. For example... Figure 4A As shown, modifying the corresponding voxel points in the first image according to the small blood vessel mask to obtain the second image includes the following steps S41 and S42.

[0078] S41, Obtain the blood vessel distribution in the first image. For example, the blood vessel distribution in the first image can be represented by the mean and variance to reflect the true blood vessel distribution in the first image.

[0079] S42, based on the distribution of blood vessels, fill the voxel points in the first image that correspond to the small blood vessel mask to obtain the second image.

[0080] In some possible implementations, the blood vessel distribution in the first image is determined by the blood vessel mean μ and variance σ. 2 Let's represent it. For any voxel point A in the small blood vessel mask where the value is not 0, its coordinates are (x... A y A , z A A value is randomly sampled within the range that satisfies the blood vessel distribution, and this value is used to fill the first image (x). A y A , z A The first image is filled in this way to obtain the second image. In one example, the mean of the blood vessels is 500, the variance is 50, the coordinates of voxel point A are [255, 130, 79], and the value randomly sampled within the range that satisfies the distribution of blood vessels is 510. In step S42, the value 510 is filled into the position [255, 130, 79] in the first image.

[0081] In some possible implementations, after obtaining the second image, the image processing method may also include: applying Gaussian filtering to the second image to smooth the boundaries so that the blood vessels can better blend with the background, thereby obtaining a more realistic second image.

[0082] For example, Figure 4B The example image shown is the first image. Figure 4C The example image shown is the second image. Figure 4D Example image shown is the fused image. Figure 4B , 4C As shown in 4D, compared to image 4C obtained by direct filling, the fused image 4D is closer to image 4B.

[0083] In some possible implementations, the image processing method may further include: processing the third image using a vessel segmentation model to achieve vessel segmentation of the third image. The third image may be, for example, a coronary CTA image, but this application is not limited thereto.

[0084] The scope of protection of the image processing method provided in this application is not limited to the execution order of the steps listed in this application. Any solution implemented by adding, subtracting or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0085] This application also provides an image processing system that can implement the image processing method described in this application. However, the implementation apparatus of the image processing method described in this application includes, but is not limited to, the structure of the image processing system listed in this embodiment. Any structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0086] Figure 5 The diagram shown is a structural schematic of the image processing system 5 provided in an embodiment of this application. Figure 5 As shown, the image processing system 5 includes a mask generation module 51, an image generation module 52, and a model training module 53. The mask generation module 51 generates a second mask based on a first mask, the second mask comprising the first mask and a small blood vessel mask. The image generation module 52 modifies corresponding voxel points in the first image based on the small blood vessel mask to obtain the second image. The model training module 53 trains a blood vessel segmentation model using the second image and the second mask.

[0087] It should be noted that the modules included in the image processing system 5 correspond one-to-one with steps S21 to S23 in the image processing method shown in Figure 2, which will not be elaborated here.

[0088] In some possible implementations, the image processing system may also include a small blood vessel mask generation module. This module is used to etch a first mask to obtain a third mask, and to acquire the small blood vessel mask based on the first and third masks.

[0089] In some possible implementations, the small blood vessel mask generation module includes a blood vessel wall point set generation unit, a starting growth point generation unit, and a small blood vessel mask acquisition unit. The blood vessel wall point set generation unit is used to obtain a blood vessel wall point set by subtracting a third mask from a first mask. The starting growth point generation unit is used to obtain the starting growth points of the small blood vessels from the blood vessel wall point set. The small blood vessel mask acquisition unit is used to grow small blood vessels based on the starting growth points to obtain the small blood vessel mask.

[0090] In some possible implementations, the growth of small blood vessels based on the starting growth point includes: growing small blood vessels iteratively starting from the starting growth point, wherein the direction of blood vessel growth is randomly selected according to a preset probability, the blood vessel diameter is a preset value, and after a certain number of iterations, the probability of selecting the main growth direction increases and the blood vessel diameter decreases.

[0091] In some possible implementations, the image generation module includes a blood vessel distribution acquisition unit and a second image acquisition unit. The blood vessel distribution acquisition unit acquires the blood vessel distribution in the first image. The second image acquisition unit fills in the voxel points in the first image corresponding to the small blood vessel mask based on the blood vessel distribution to obtain the second image.

[0092] In some possible implementations, the image generation module may also include a Gaussian filtering unit. The Gaussian filtering unit is used to perform Gaussian filtering on the second image.

[0093] In some possible implementations, the image processing system may also include a blood vessel segmentation module. This module is used to process the third image using a trained blood vessel segmentation model to achieve blood vessel segmentation in the third image.

[0094] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0095] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0096] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0097] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the image processing method provided in this application.

[0098] In some possible implementations, any combination of one or more storage media may be used. The storage media may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), optical fiber, portable compact disk read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0099] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0100] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0101] This application also provides an electronic device. Figure 6 The diagram shown is a structural schematic of electronic device 6 in one embodiment of this application. Figure 6 As shown, in this embodiment, the electronic device 6 includes a memory 61 and a processor 62.

[0102] The memory 61 is used to store computer programs. In some possible implementations, the memory 61 may include various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0103] In this embodiment, memory 61 may include a computer system readable medium in the form of volatile memory, such as RAM and / or cache memory. Electronic device 6 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 61 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0104] The processor 62 is connected to the memory 61 and is used to execute the computer program stored in the memory 61 so that the electronic device 6 performs the image processing method.

[0105] In some embodiments, processor 62 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. In other embodiments, processor 62 may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0106] In some possible implementations, the electronic device 6 provided in this application embodiment may further include a display 63. The display 63 is communicatively connected to the memory 61 and the processor 62, and is used to display a graphical user interface (GUI) related to the image processing method.

[0107] In this embodiment, the display 63 may include a display screen (display panel). In some implementations, a liquid crystal display (LCD), an organic light-emitting diode (OLED), or similar form of display panel may be used. Alternatively, the display 63 may also be a touch panel (touchscreen, touch screen), which may include a display screen and a touch-sensitive surface. When the touch-sensitive surface detects a touch operation on or near it, it transmits the information to the processor 62 to determine the type of touch event. Subsequently, the processor 62 provides corresponding visual output on the display device based on the type of touch event.

[0108] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0109] In summary, the embodiments of this application provide an image processing method, system, storage medium, and electronic device. The image processing method provided in this application can generate a mask of small blood vessels and modify the corresponding voxel points in the original image. By fusing the blood vessels and the background, a more realistic image can be obtained. By using the fused image and the blood vessel mask to train a blood vessel segmentation model, the model can be made more sensitive to small blood vessels, thereby improving segmentation accuracy. Therefore, this application effectively overcomes the various shortcomings of the prior art and has high industrial applicability.

[0110] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. An image processing method, characterized in that, The image processing method includes: A second mask is generated based on the first mask, the second mask comprising the first mask and the small blood vessel mask; The second image is obtained by modifying the corresponding voxel points in the first image according to the small blood vessel mask, wherein the first mask is the original mask generated based on the first image; The blood vessel segmentation model is trained using the second image and the second mask; The method for generating the tiny blood vessel mask includes: The first mask is etched to obtain the third mask; The first mask is used to subtract the third mask to obtain the blood vessel wall point set; The initial growth points of small blood vessels are obtained from the set of blood vessel wall points; The process of growing small blood vessels from the starting growth point to obtain the small blood vessel mask includes: growing small blood vessels iteratively from the starting growth point to obtain the small blood vessel mask, wherein the blood vessel growth direction is randomly selected according to a preset probability, the blood vessel diameter is a preset value, and after a certain number of iterations, the probability of selecting the main growth direction increases and the blood vessel diameter decreases. Modifying corresponding voxel points in the first image based on the small blood vessel mask to obtain the second image includes: Obtain the blood vessel distribution in the first image; Based on the blood vessel distribution, the voxel points in the first image corresponding to the small blood vessel mask are filled to obtain the second image.

2. The image processing method according to claim 1, characterized in that, The image processing method further includes performing Gaussian filtering on the second image.

3. The image processing method according to claim 1, characterized in that, The image processing method further includes: processing the third image using the blood vessel segmentation model to achieve blood vessel segmentation in the third image.

4. An image processing system, characterized in that, For implementing the image processing method according to any one of claims 1 to 3, the image processing system comprises: A mask generation module is used to generate a second mask based on a first mask, the second mask comprising the first mask and a small blood vessel mask; The image generation module is used to modify the corresponding voxel points in the first image according to the small blood vessel mask to obtain the second image; The model training module is used to train a blood vessel segmentation model using the second image and the second mask.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 3.

6. An electronic device, characterized in that, The electronic device includes: A memory that stores a computer program; The processor, which is communicatively connected to the memory, executes the method of any one of claims 1 to 3 when the computer program is invoked.

Images