Contrast image two-level segmentation method, electronic device, processing system, and storage medium

Abstract

The application provides a contrast image two-stage segmentation method, an electronic device, a processing system and a storage medium. First, an initial contrast image is acquired. Then, the initial contrast image is segmented according to a matched filter algorithm to obtain a first segmentation result. Finally, the initial contrast image and the first segmentation result are input into a pre-established segmentation model to obtain a second segmentation result of the contrast image. The pre-established segmentation model is used for denoising and breakpoint completion of the first segmentation result according to the initial contrast image. The contrast image is segmented according to a traditional matched filter algorithm first, and then the segmented image and the original image are input into the segmentation model for comparison, so as to remove the noise generated in the segmentation process and make up for the breakpoints caused by pixel loss, thereby effectively improving the accuracy of contrast image segmentation.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and particularly relates to a two-level segmentation method for imaging images, an electronic device, a processing system, and a storage medium. Background Technology

[0002] Contrast imaging is a widely used type of medical imaging. Specifically, cardiovascular contrast imaging involves inserting a catheter through the femoral artery or other peripheral arteries in the thigh, advancing to the ascending aorta, and then inserting it into the left or right coronary artery ostium. Contrast agent is then injected, allowing the coronary arteries to be visualized under X-rays, thus obtaining the contrast image. Because other tissues in the body, such as bones, are also imaged by X-rays, contrast images often contain significant noise and are prone to blurring; therefore, image processing is necessary.

[0003] Contrast image segmentation is the foundation of contrast image processing. Current techniques typically employ methods such as thresholding, region growing, statistical region fusion, and matched filtering to segment contrast images. However, due to the complexity of contrast images, traditional methods often result in images with significant noise or missing pixels, leading to low segmentation accuracy. Summary of the Invention

[0004] In view of this, the present invention provides a two-level segmentation method for contrast imaging images, an electronic device, a processing system, and a storage medium, aiming to solve the problem of low accuracy in contrast imaging image segmentation in the prior art.

[0005] A first aspect of this invention provides a two-level segmentation method for imaging images, comprising:

[0006] Obtain the initial contrast images;

[0007] The initial angiography image is segmented using a matched filtering algorithm to obtain the first segmentation result;

[0008] The initial contrast image and the first segmentation result are input into a pre-established segmentation model to obtain the second segmentation result of the contrast image; wherein, the pre-established segmentation model is used to denoise and fill in the breakpoints of the first segmentation result based on the initial contrast image.

[0009] A second aspect of the present invention provides a two-stage segmentation apparatus for contrast imaging images, comprising:

[0010] The image acquisition module is used to acquire the initial contrast images;

[0011] The first segmentation module is used to segment the initial angiography image according to the matched filtering algorithm to obtain the first segmentation result;

[0012] The second segmentation module is used to input the initial contrast image and the first segmentation result into a pre-established segmentation model to obtain the second segmentation result of the contrast image; wherein, the pre-established segmentation model is used to denoise and fill in the breakpoints of the first segmentation result based on the initial contrast image.

[0013] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the two-level segmentation method for imaging images as described in the first aspect above.

[0014] A fourth aspect of the present invention provides an imaging image processing system, including a medical X-ray examination device and the electronic device described in the third aspect above.

[0015] A fifth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the two-level segmentation method for imaging images as described in the first aspect above.

[0016] This invention provides a two-stage segmentation method, electronic device, processing system, and storage medium for contrast-enhanced images. First, an initial contrast-enhanced image is acquired. Then, the initial contrast-enhanced image is segmented using a matched filtering algorithm to obtain a first segmentation result. Finally, the initial contrast-enhanced image and the first segmentation result are input into a pre-established segmentation model to obtain a second segmentation result for the contrast-enhanced image. The pre-established segmentation model is used to denoise and fill in gaps in the first segmentation result based on the initial contrast-enhanced image. By first segmenting the contrast-enhanced image using a traditional matched filtering algorithm, and then comparing the segmented image and the original image with the segmentation model, noise generated during the segmentation process is removed, and gaps caused by missing pixels are filled, effectively improving the accuracy of contrast-enhanced image segmentation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is an application scenario diagram of the two-level segmentation method for imaging images provided in the embodiments of the present invention;

[0019] Figure 2 This is a flowchart illustrating the implementation of the two-level segmentation method for imaging images provided in this embodiment of the invention.

[0020] Figure 3This is a schematic diagram of the structure of the two-stage imaging image segmentation device provided in an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0023] Figure 1 This is an application scenario diagram of the two-level segmentation method for imaging images provided in this embodiment of the invention. For example... Figure 1 As shown, in some embodiments, the two-level segmentation method for contrast images provided by the present invention can be applied to, but is not limited to, this application scenario. The system may include: a medical X-ray examination device 11 and an electronic device 12.

[0024] First, a catheter needs to be inserted through the patient's femoral artery or other peripheral arteries and advanced to the ascending aorta. Then, the left or right coronary artery orifice is located and inserted. Contrast agent is then injected into the coronary artery. At this time, the medical X-ray examination device 11 captures the contrast image and sends it to the electronic device 12. The electronic device 12 segments the contrast image to obtain a clear cardiovascular segmentation map.

[0025] Among them, electronic device 12 can be a terminal or a server. The terminal can be an examination terminal equipped on medical X-ray examination equipment 11, a doctor's office terminal, etc., and the server can be the management server of the hospital's hospital information management system or a cloud server, which is not limited here.

[0026] Figure 2 This is a flowchart illustrating the implementation of the two-level segmentation method for contrast images provided in this embodiment of the invention. Figure 2 As shown, the two-level segmentation method for contrast images is applied to... Figure 1 The method of the electronic device 12 shown may include:

[0027] S210, Obtain the initial contrast image.

[0028] In this embodiment of the invention, the initial contrast image may be Figure 1 The images can be taken in real time by the medical X-ray examination equipment 11, or they can be obtained from the hospital's information management system; there is no limitation on this.

[0029] S220, The initial angiography image is segmented according to the matched filtering algorithm to obtain the first segmentation result.

[0030] In this embodiment of the invention, the blood vessel walls are nearly parallel, so the blood vessel can be segmented into multiple small parallel line segments. These segments are then simulated using Gaussian curves to obtain a matched filter describing the blood vessel features. The blood vessel image is then filtered using this matched filter to obtain the first segmentation result. However, the matched filtering algorithm is an existing algorithm. While it can segment angiographic images, its segmentation results contain a large number of misidentified noise pixels. Furthermore, due to its low recognition accuracy, it is prone to failing to identify some blood vessels, resulting in problems such as blood vessel breakpoints and missing details.

[0031] S230, the initial contrast image and the first segmentation result are input into the pre-established segmentation model to obtain the second segmentation result of the contrast image; wherein, the pre-established segmentation model is used to denoise and fill in the breakpoints of the first segmentation result based on the initial contrast image.

[0032] In this embodiment of the invention, the contrast image is first segmented according to the traditional matched filtering algorithm, and then the segmented image and the original image are input into the segmentation model for comparison, thereby removing noise generated during the segmentation process and filling in the gaps caused by missing pixels, effectively improving the accuracy of contrast image segmentation.

[0033] In some embodiments, S230 may include: inputting an initial contrast image and a first segmentation result into a pre-established segmentation model to obtain a noisy image and a missing pixel-filled image; and determining a second segmentation result of the contrast image based on the first segmentation result, the noisy image, and the missing pixel-filled image.

[0034] In this embodiment of the invention, the segmentation model can be a supervised learning model, a transfer learning model, etc., and is not limited thereto. The segmentation model can be divided into two parts. One part is mainly used for noise removal, that is, comparing the initial angiography image with the first segmentation result to identify the misidentified noise in the first segmentation result and obtain a noisy image. The other part is mainly used for filling missing pixels, that is, comparing the initial angiography image with the first segmentation result to identify the unidentified vascular details and de-energized pixels in the first segmentation result and obtain a missing pixel filled image.

[0035] In this embodiment of the invention, the missing pixel filling image is filled into the first segmentation result to supplement the cardiovascular details. Then, the noise image is subtracted from the filled first segmentation result to obtain the second segmentation result of the angiography image.

[0036] In some embodiments, the training process of the segmentation model may include: acquiring a sampled image of an angiography image; segmenting the sampled image of the angiography image according to a matched filtering algorithm to obtain a first segmentation result of the sampled image of the angiography image; acquiring a label image corresponding to the sampled image of the angiography image; using the sampled image of the angiography image and the first segmentation result of the sampled image of the angiography image as input values ​​and the label image corresponding to the sampled image of the angiography image as output values ​​to form a training set for training the segmentation model.

[0037] In this embodiment of the invention, before training the segmentation model, training images of angiography images (i.e., original angiography images stored in the database) are first obtained. The angiography image sampling images are obtained by sampling the training images of angiography images. Then, experts manually segment the training images of angiography images and mark the blood vessels in the form of label values ​​to obtain labeled images.

[0038] In some embodiments, acquiring contrast image sampling images includes: acquiring contrast image training images; dividing the contrast image training images into foreground regions and background regions; and acquiring the same number of contrast image sampling images in the foreground regions and background regions.

[0039] In this embodiment of the invention, cardiovascular angiography image segmentation differs from conventional vascular image segmentation, such as retinal vascular segmentation. In retinal vascular images, blood vessels are present in the vast majority of areas, so each sampled image contains both blood vessels and background, effectively training the segmentation model. However, for cardiovascular angiography images, there are fewer blood vessels and a large amount of background; blood vessels do not fill the entire image. Therefore, random sampling can easily lead to an imbalance between positive samples (sampling of the foreground region) and negative samples (sampling of the background region). A large number of negative samples reduces the segmentation model's sensitivity to vascular segmentation, resulting in poor segmentation results. While sampling only blood vessels can effectively improve segmentation accuracy, the lack of negative samples in the training samples prevents the segmentation model from effectively recognizing the background, resulting in a large amount of background noise in the final segmented angiography image.

[0040] In this embodiment of the invention, by dividing the contrast image training image into a foreground region and a background region, and then collecting the same number of contrast image sampling images in the foreground region and the background region, it is possible to ensure that the positive and negative samples in the training samples are balanced, so that the segmentation model trained can effectively segment the contrast image without generating a large amount of background noise, thereby providing a good segmentation effect for the contrast image.

[0041] In some embodiments, after dividing the contrast-enhanced image training image into a foreground region and a background region, the method further includes: dividing the foreground region into a simple foreground region and a difficult foreground region; dividing the background region into a simple background region, a first complex background region, and a second complex background region; acquiring a first preset number of contrast-enhanced image samples in the simple foreground region; acquiring a second preset number of contrast-enhanced image samples in the difficult foreground region; acquiring a third preset number of contrast-enhanced image samples in the simple background region; acquiring a fourth preset number of contrast-enhanced image samples in the first complex background region; and acquiring a fifth preset number of contrast-enhanced image samples in the second complex background region; wherein the sum of the first preset number and the second preset number is equal to the sum of the third preset number, the fourth preset number, and the fifth preset number.

[0042] In some embodiments, the first preset number is less than the second preset number; the third preset number is less than the fourth preset number; and the third preset number is less than the fifth preset number.

[0043] In this embodiment of the invention, based on the above-described foreground and background region division, further sampling division can be performed to adjust the proportion of various types of images in the training set and improve the segmentation effect of the segmentation model.

[0044] In this embodiment of the invention, cardiovascular vessels with small curvature and large thickness are often the easiest to identify, and are therefore classified as simple foregrounds. However, angiographic images with large curvature, multiple turns within a small range, thinness, or at the junction of blood vessels are often difficult to identify, and are therefore classified as difficult foregrounds. The number of simple foregrounds collected during sampling should be less than the number of difficult foregrounds to improve the recognition accuracy of difficult foregrounds.

[0045] In this embodiment of the invention, the original contrast image is a black and white image with high grayscale values ​​for blood vessels. Therefore, regions with very low grayscale values ​​in the background have good segmentation results and will not be misidentified as blood vessels, thus they are classified as simple backgrounds. However, there are often regions in the background with overall high grayscale values, which are easily misidentified as blood vessels, and are therefore classified as the first complex background region. Additionally, there are regions in the contrast image with overall low grayscale values ​​but containing some pixels with high grayscale values. These high-grayscale background noises are also prone to misidentification, and are therefore classified as the second complex background region. The number of simple background samples in the training samples needs to be less than any of the aforementioned complex backgrounds to ensure the segmentation effect of the contrast image. The fourth and fifth preset numbers can be determined based on the actual image; for example, the ratio of the first and second complex background regions can be used as the ratio of the fourth and fifth preset numbers.

[0046] In some embodiments, after S210, the method further includes: dividing the initial contrast image into a foreground region and a background region; and preprocessing the initial contrast image to improve the contrast between the foreground region and the background region.

[0047] In summary, the beneficial effects of the present invention are as follows:

[0048] 1. By first segmenting the angiography image using the traditional matched filtering algorithm, and then inputting the segmented image and the original image into the segmentation model for comparison, noise generated during the segmentation process is removed and missing pixels are filled in to fill in the gaps, thus effectively improving the accuracy of cardiovascular segmentation.

[0049] 2. By dividing the contrast image training image into a foreground region and a background region, and then collecting the same number of contrast image sampling images in the foreground region and the background region, it is possible to ensure that the positive and negative samples in the training samples are balanced. This allows the trained segmentation model to effectively segment contrast images without generating a large amount of background noise, thereby improving the segmentation effect of contrast images.

[0050] 3. Based on the above foreground and background region division, further sampling division can be performed to adjust the proportion of various types of images in the training set and improve the segmentation effect of the segmentation model.

[0051] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0052] Figure 3 This is a schematic diagram of the structure of the two-stage image segmentation device provided in an embodiment of the present invention. Figure 3 As shown, in some embodiments, the two-stage imaging segmentation device 3 includes:

[0053] Image acquisition module 310 is used to acquire initial contrast images.

[0054] The first segmentation module 320 is used to segment the initial angiographic image according to the matched filtering algorithm to obtain the first segmentation result.

[0055] The second segmentation module 330 is used to input the initial contrast image and the first segmentation result into a pre-established segmentation model to obtain the second segmentation result of the contrast image; wherein, the pre-established segmentation model is used to denoise and fill in the breakpoints of the first segmentation result based on the initial contrast image.

[0056] Optionally, the second segmentation module 330 is specifically used to input the initial contrast image and the first segmentation result into a pre-established segmentation model to obtain a noisy image and a missing pixel-filled image; and to determine the second segmentation result of the contrast image based on the first segmentation result, the noisy image and the missing pixel-filled image.

[0057] Optionally, the two-stage contrast image segmentation device 3 further includes a training module, which is used to acquire a contrast image sample image; segment the contrast image sample image according to a matched filtering algorithm to obtain a first segmentation result of the contrast image sample image; acquire a label image corresponding to the contrast image sample image; and use the contrast image sample image and the first segmentation result of the contrast image sample image as input values ​​and the label image corresponding to the contrast image sample image as output values ​​to form a training set for training the segmentation model.

[0058] Optionally, the training module is specifically used for: acquiring contrast image training images; dividing the contrast image training images into foreground and background regions; and acquiring the same number of contrast image sampling images in the foreground and background regions.

[0059] Optionally, the training module is specifically used for: dividing the foreground region into a simple foreground region and a difficult foreground region; dividing the background region into a simple background region, a first complex background region, and a second complex background region; acquiring a first preset number of contrast-enhanced image samples in the simple foreground region; acquiring a second preset number of contrast-enhanced image samples in the difficult foreground region; acquiring a third preset number of contrast-enhanced image samples in the simple background region; acquiring a fourth preset number of contrast-enhanced image samples in the first complex background region; and acquiring a fifth preset number of contrast-enhanced image samples in the second complex background region; wherein the sum of the first preset number and the second preset number is equal to the sum of the third preset number, the fourth preset number, and the fifth preset number.

[0060] Optionally, the first preset number is less than the second preset number; the third preset number is less than the fourth preset number; and the third preset number is less than the fifth preset number.

[0061] Optionally, the two-stage imaging image segmentation device 3 also includes a preprocessing module for dividing the initial imaging image into a foreground region and a background region; and preprocessing the initial imaging image to improve the contrast between the foreground region and the background region.

[0062] The two-level segmentation device for contrast images provided in this embodiment can be used to execute the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0063] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. For example... Figure 4As shown, an embodiment of the present invention provides an electronic device 4, which includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps in the various embodiments of the two-level segmentation method for contrast images described above, for example... Figure 1 Steps 110 to 130 are shown. Alternatively, when processor 40 executes computer program 42, it implements the functions of each module / unit in the above system embodiments, for example... Figure 3 The functions of modules 310 to 330 are shown.

[0064] For example, computer program 42 may be divided into one or more modules / units, one or more of which are stored in memory 41 and executed by processor 40 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0065] Electronic device 4 can be a terminal or a server. The terminal can be a mobile phone, MCU, ECU, etc., and the server can be a physical server or a cloud server; no limitation is made here. Electronic device 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic devices may also include input / output devices, network access devices, buses, etc.

[0066] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0067] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store computer programs and other programs and data required by the electronic device. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0068] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the embodiments of the two-level segmentation method for contrast images.

[0069] A computer-readable storage medium stores a computer program 42. The computer program 42 includes program instructions. When executed by the processor 40, the program instructions implement all or part of the processes in the methods described in the above embodiments. The computer program 42 can also instruct related hardware to complete the process. The computer program 42 can be stored in a computer-readable storage medium. When executed by the processor 40, the computer program 42 can implement the steps of the various method embodiments described above. The computer program 42 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0070] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0071] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0073] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0074] Those skilled in the art will 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, or a combination of computer software and electronic hardware. 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 implementations should not be considered beyond the scope of this invention.

[0075] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components 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 between devices or units may be electrical, mechanical, or other forms.

[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0079] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A two-level segmentation method for contrast-enhanced images, characterized in that, include: Obtain the initial contrast images; The initial contrast image is segmented according to the matched filtering algorithm to obtain the first segmentation result of the contrast image; The initial contrast image and the first segmentation result are input into a pre-established segmentation model to obtain a second segmentation result of the contrast image; wherein, the pre-established segmentation model is used to denoise and fill in the breakpoints of the first segmentation result based on the initial contrast image; The step of inputting the initial contrast image and the first segmentation result into a pre-established segmentation model to obtain a second segmentation result for the contrast image includes: The initial contrast image and the first segmentation result are input into a pre-established segmentation model to obtain a noisy image and a missing pixel-filled image; Based on the first segmentation result, the noisy image, and the missing pixel-filled image, a second segmentation result of the imaging image is determined.

2. The two-level segmentation method for contrast-enhanced images according to claim 1, characterized in that, The method further includes: Acquire contrast-sampled images; The contrast-enhanced sampled image is segmented according to the matched filtering algorithm to obtain the first segmentation result of the contrast-enhanced sampled image; Obtain the label image corresponding to the contrast-sampled image; The segmentation model is trained by using the contrast-enhanced sampled image and the first segmentation result of the contrast-enhanced sampled image as input values ​​and the label image corresponding to the contrast-enhanced sampled image as output values ​​to form a training set.

3. The two-level segmentation method for contrast images according to claim 2, characterized in that, The acquisition of the contrast-enhanced sample image includes: Acquire training images for angiography; The imaging training image is divided into a foreground region and a background region; The same number of imaging sample images are acquired in both the foreground and background regions.

4. The two-level segmentation method for contrast images according to claim 3, characterized in that, After dividing the imaging training image into foreground and background regions, the method further includes: The foreground region is divided into a simple foreground region and a difficult foreground region; The background region is divided into a simple background region, a first complex background region, and a second complex background region. A first preset number of angiographic sampling images are acquired in the simple foreground region; Acquire a second preset number of angiographic sampling images in the difficult foreground region; A third preset number of contrast-enhanced images are acquired in the simple background area; A fourth preset number of contrast-enhanced images are acquired in the first complex background region; A fifth preset number of contrast-enhanced images are acquired in the second complex background region; Wherein, the sum of the first preset number and the second preset number is equal to the sum of the third preset number, the fourth preset number, and the fifth preset number.

5. The two-level segmentation method for contrast-enhanced images according to claim 4, characterized in that, The first preset number is less than the second preset number; The third preset number is less than the fourth preset number; the third preset number is less than the fifth preset number.

6. The two-level segmentation method for contrast images according to any one of claims 1-5, characterized in that, After acquiring the initial contrast image, the method further includes: The initial contrast image is divided into a foreground region and a background region; The initial contrast image is preprocessed to improve the contrast between the foreground and background regions.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the two-level segmentation method for imaging images as described in any one of claims 1 to 6.

8. An imaging processing system comprising a medical X-ray examination device and the electronic device as described in claim 7 above.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the two-stage segmentation method for imaging images as described in any one of claims 1 to 6.

Images