Endoleak Diagnosis System Based on Ultrasound Contrast Imaging After Endovascular Repair of Abdominal Aortic Aneurysm

Abstract

This invention relates to the field of image processing technology, and more particularly to a diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysms based on ultrasound angiography images. The invention acquires ultrasound images of the same location with different parameters. First, a first ultrasound image is acquired at a high operating frequency, followed by a second ultrasound image acquired at a low operating frequency. Then, different preprocessing methods are used to preprocess the first and second ultrasound images. The first ultrasound image is then input into an artificial intelligence model to determine the aortic aneurysm location. Based on this location, the aortic aneurysm location in the second ultrasound image is obtained, and the aortic aneurysm in the second image is then input into the artificial intelligence model, thereby achieving endoleak diagnosis. This method avoids the complex image fusion algorithms used in existing technologies for diagnosing two ultrasound images, simplifying the process and improving diagnostic efficiency.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images. Background Technology

[0002] Endoleak is a unique complication following endovascular repair (EVAR) of abdominal aortic aneurysms. It occurs when the stent fails to completely isolate the lesion, allowing blood flow to still enter the aneurysm cavity. Type I endoleaks are the most common, caused by poor adhesion between the proximal or distal stent and the vessel. Type II endoleaks are the second most common, caused by reflux from branch vessels within the aneurysm. Literature reports that Type I endoleaks pose a higher risk of aneurysm rupture and should be treated promptly upon discovery. Type II endoleaks have a relatively lower risk of rupture, but treatment is more difficult and often requires close imaging monitoring. If a progressive increase in aneurysm diameter is observed, aggressive intervention is necessary.

[0003] CTA has long been considered the gold standard for detecting endoleaks after EVAR (endovascular aspiration). Its wide scanning range and clear visualization of stent structures are advantages. However, it is an intermittent computed tomography (CT) scan, unable to fully observe the dynamic process of lesion enhancement, and is relatively expensive. It also carries risks such as X-ray exposure, contrast agent nephrotoxicity, and allergic reactions, which limit its use to some extent. Color Doppler ultrasound is another commonly used postoperative examination method besides CTA. It is simple to operate, inexpensive, and radiation-free. However, it is not good at displaying blood flow in low-velocity and deep lesions and cannot dynamically observe the blood perfusion process. Studies have reported significant differences in the sensitivity and specificity of color Doppler ultrasound in diagnosing endoleaks, with most studies suggesting that using Doppler ultrasound alone is ineffective in detecting endoleaks. Contrast-enhanced ultrasound has been increasingly used in EVAR follow-up in recent years. It is an emerging technology that enhances the scattered blood flow signal by intravenously injecting ultrasound contrast agents, based on routine ultrasound examination, thereby improving the resolution, sensitivity, and specificity of ultrasound diagnosis. Currently, a novel ultrasound contrast agent—SonoVue—is widely used in clinical practice. Its main component is the inert gas sulfur hexafluoride, which is metabolized by the lungs and has no hepatotoxicity or nephrotoxicity. It can be used in patients with renal insufficiency.

[0004] Current technology for diagnosing endoleaks after endovascular repair of abdominal aortic aneurysms using contrast-enhanced ultrasound images typically involves acquiring two ultrasound images, then fusing them using complex algorithms before inputting them into a model or sending them to the physician for endoleak diagnosis. This method requires complex algorithms for image fusion, making the process extremely complicated, and the quality of the fusion directly affects the accuracy of endoleak diagnosis. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images. The process is relatively simple and highly accurate.

[0006] This invention provides a diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography, comprising:

[0007] The system includes:

[0008] An ultrasound image acquisition module is used to acquire a first ultrasound image and a second ultrasound image for the diagnosis of endoleak after endovascular repair of abdominal aortic aneurysm.

[0009] The first ultrasound image preprocessing module is used to perform preprocessing operations on the first ultrasound image to obtain a preprocessed first ultrasound image.

[0010] The second ultrasound image preprocessing module is used to perform preprocessing operations on the second ultrasound image to obtain a preprocessed second ultrasound image.

[0011] The first ultrasound image abdominal aortic aneurysm image acquisition module is used to input the preprocessed first ultrasound image into the first artificial intelligence model to acquire the abdominal aortic aneurysm image in the first ultrasound image.

[0012] The second ultrasound image abdominal aortic aneurysm image acquisition module is used to perform an image alignment operation between the first ultrasound image and the second ultrasound image, thereby obtaining the position of the abdominal aortic aneurysm image in the first ultrasound image in the second ultrasound image, and obtaining the abdominal aortic aneurysm image in the second ultrasound image.

[0013] The endoleak detection module is used to input the abdominal aortic aneurysm image from the second ultrasound image into the second artificial intelligence model to detect whether an endoleak occurs after the abdominal aortic aneurysm isolation procedure.

[0014] Preferably, the process of the ultrasound image acquisition module acquiring ultrasound contrast images is as follows:

[0015] Set the ultrasound diagnostic instrument to the first operating frequency, and acquire the first ultrasound contrast image according to the first operating frequency;

[0016] The ultrasound diagnostic instrument is set to a second operating frequency, and a second ultrasound contrast image is acquired according to the second operating frequency.

[0017] Preferably, the first operating frequency is 8MHz.

[0018] Preferably, the second operating frequency is 4MHz.

[0019] Preferably, the process of the first ultrasound image preprocessing module performing preprocessing operations on the first ultrasound image is as follows:

[0020] Perform a first filtering operation on the first ultrasound image;

[0021] A second filtering operation is performed on the first ultrasound image.

[0022] Preferably, the second filtering operation is to process the first ultrasound image using wavelet transform, specifically: to filter the low-frequency noise components in the first ultrasound image using wavelet transform; in this process, the high-frequency information in the first ultrasound image is retained.

[0023] Preferably, the process of the second ultrasound image preprocessing module performing preprocessing operations on the second ultrasound image to obtain the preprocessed second ultrasound image is as follows: firstly, adaptive filtering is used to filter the second ultrasound image, and then the filtered second ultrasound image is input to a low-pass filter to filter out the high-frequency components in the second ultrasound image, thereby increasing the proportion of information reflected by the ultrasound contrast suspension.

[0024] Preferably, the first artificial intelligence model is one of a neural network model, a convolutional neural network model, or a YOLO-5 model.

[0025] Preferably, the second artificial intelligence model is one of a neural network model, a convolutional neural network model, or a YOLO-5 model.

[0026] The embodiments of the present invention have the following technical effects:

[0027] This invention acquires ultrasound images of the same location with different parameters. First, a first ultrasound image is acquired using a high operating frequency, followed by a second ultrasound image acquired using a low operating frequency. Then, different preprocessing methods are used to preprocess the first and second ultrasound images. The first ultrasound image is then input into an artificial intelligence model to determine the location of the aortic aneurysm. Based on this location, the aortic aneurysm location in the second ultrasound image is obtained, and the aortic aneurysm in the second image is then input into the artificial intelligence model, thereby achieving endoleak diagnosis. This method avoids the complex image fusion algorithms used in existing technologies for diagnosing two ultrasound images, resulting in a simpler process and improved diagnostic efficiency.

[0028] In the image preprocessing process, since the first ultrasound image is mainly used to obtain the location of the aortic aneurysm, wavelet transform is used to preprocess it to retain as much high-frequency information as possible that can reflect human tissue information. For the second ultrasound image, a low-pass filter is used to preprocess it to retain as much information as possible that can reflect the ultrasound contrast suspension. The different preprocessing methods are used to ensure that the preprocessing process retains and reflects useful information as much as possible, laying a good data foundation for subsequent endoleak detection.

[0029] This invention employs two artificial intelligence models. First, the first artificial intelligence model is used to determine the location of the aortic aneurysm. Then, the alignment of two ultrasound images is performed. Next, the location of the aortic aneurysm in the second ultrasound image is obtained based on the location of the aortic aneurysm in the first ultrasound image. Since the second ultrasound image contains more information about the ultrasound angiography suspension, it is more helpful for the diagnosis of endoleak. Therefore, the second ultrasound image is input into the second artificial intelligence model, which improves the accuracy of endoleak diagnosis from both the input data and the diagnostic model. Attached Figure Description

[0030] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of the endoleak diagnosis system after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images provided by the present invention.

[0032] Figure 2 This is the first ultrasound contrast image provided by the present invention;

[0033] Figure 3 This is the second ultrasound contrast image provided by the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0035] Example 1: A method for diagnosing endoleak after endovascular repair of abdominal aortic aneurysm based on contrast-enhanced ultrasound images, specifically including:

[0036] S1: Acquire the first and second ultrasound images for diagnosis of endoleak after endovascular repair of abdominal aortic aneurysm.

[0037] In this embodiment, an Esaote MyLab Class C ultrasound diagnostic instrument was used for acquiring ultrasound contrast images. The ultrasound diagnostic instrument used a convex array frequency converter probe with a working frequency of 3-8 MHz, and the ultrasound contrast agent used was an ultrasound contrast agent manufactured by SonoVue (Bracco). Before acquiring the ultrasound contrast images used for diagnosing endoleak after endovascular aortic aneurysm repair, the ultrasound contrast agent was diluted with 5 ml of normal saline, shaken to form an ultrasound contrast agent microbubble suspension, and the patient to be tested orally administered 1.5 ml before ultrasound image acquisition.

[0038] Specifically, S1 is as follows:

[0039] S1.1: Set the ultrasound diagnostic instrument to a first operating frequency, and acquire a first ultrasound contrast image according to the first operating frequency;

[0040] The first operating frequency is 8MHz, using a low mechanical index (MI: 0.01~0.04) and real-time angiography imaging mode. The scan extends from the origin of the abdominal aorta to the bifurcation of the bilateral iliac arteries. The upper, middle, and lower segments of the abdominal aorta are observed on both the horizontal and vertical axes, with a focus on the proximal and distal ends of the stents and their branches. After satisfactory observation, the scan proceeds longitudinally downwards to below the umbilicus to display the bifurcation of the bilateral iliac arteries. The probe is then moved left and right to display the internal and external iliac arteries, and finally moved upwards to locate the bilateral renal arteries. Multiple sections and angles are scanned. Since the first operating frequency is relatively high, the ultrasound angiography images are more sensitive to human information at this frequency. Therefore, the first ultrasound angiography image primarily reflects human information. Figure 2 The first ultrasound contrast image is shown.

[0041] S1.2: Set the ultrasound diagnostic instrument to the second working frequency, and acquire the second ultrasound contrast image according to the second working frequency;

[0042] The second operating frequency is 4MHz. When the operating frequency of the ultrasound diagnostic instrument is low, during the actual acquisition process, the ultrasound contrast suspension in the blood greatly enhances the ability of the capillaries in the area to be tested in the human body to reflect low-frequency ultrasound signals. As a result, the signal reflecting the ultrasound contrast suspension accounts for a relatively large proportion of the signal received by the receiver of the ultrasound diagnostic instrument. Therefore, this embodiment sets a low operating frequency of the ultrasound diagnostic instrument to acquire the second ultrasound contrast image that mainly reflects the information of the ultrasound contrast suspension.

[0043] It is worth emphasizing that if the signal-to-noise ratio of the second ultrasound contrast-enhanced image is low, it is highly likely that the ultrasound contrast agent microbubble suspension consumed by the patient has not flowed to the target location, resulting in insufficient wavelength of the reflected echo. In this case, the patient should repeatedly drink the ultrasound contrast agent microbubble suspension, 1.5 ml per dose, with each dose spaced 5-10 minutes apart, until the previous contrast agent has largely disappeared. Through the above operation, the acquired second ultrasound contrast-enhanced image can reflect the information of the ultrasound contrast suspension to the greatest extent. Figure 3 The second ultrasound contrast image is shown;

[0044] It is worth noting that the first ultrasound image and the second ultrasound image are ultrasound images acquired with different acquisition parameters at the same location of the patient.

[0045] S2: Perform preprocessing on the first ultrasound image to obtain a preprocessed first ultrasound image;

[0046] When acquiring ultrasound images, various kinds of noise are inevitably introduced, such as machine operating noise and environmental noise. In order to obtain better diagnostic results for internal leaks, ultrasound images need to be preprocessed. The guiding principle of preprocessing is to eliminate interference information as much as possible and highlight the proportion of useful information in the image.

[0047] Therefore, the preprocessing operation of the first ultrasound image specifically includes:

[0048] S2.1: Perform a first filtering operation on the first ultrasound image;

[0049] The filtering operation is to perform a filtering operation on the first ultrasound image using one of the following: mean filtering, Gaussian filtering, median filtering, bilateral filtering, and adaptive filtering.

[0050] In this embodiment, the noise in the ultrasound image is mainly manifested as speckles in the ultrasound image. Adaptive filtering has a good performance in removing speckle noise caused by various reasons. Therefore, in this embodiment, the first ultrasound image is filtered by adaptive filtering.

[0051] S2.2: Perform a second filtering operation on the first ultrasound image;

[0052] The first ultrasound image is acquired using a higher working frequency, and the information of human tissues and organs is more prominent in the image. Therefore, a second filtering operation is performed on the first ultrasound image to enhance its ability to reflect human tissue information.

[0053] The second filtering operation involves processing the first ultrasound image using wavelet transform. Wavelet transform (WT) is a novel transform analysis method that inherits and develops the idea of ​​localization in short-time Fourier transform while overcoming the shortcomings of window size not changing with frequency. It can provide a "time-frequency" window that changes with frequency, making it an ideal tool for time-frequency analysis and processing of signals. The main characteristics of wavelet transform are that it can fully highlight certain features of a problem through transformation, enable localized analysis of time (space) and frequency, and gradually refine the signal (function) at multiple scales through scaling and translation operations, ultimately achieving the effect of high-frequency subdivision or low-frequency subdivision as needed.

[0054] Specifically, S2.2 involves using wavelet transform to filter low-frequency noise components in the first ultrasound image. During this process, high-frequency information in the first ultrasound image is preserved as much as possible, while low-frequency noise information in the introduced noise is removed, thereby achieving the goal of preserving as much high-frequency information as possible.

[0055] S3: Perform preprocessing on the second ultrasound image to obtain a preprocessed second ultrasound image;

[0056] The second ultrasound image was acquired at a lower operating frequency. As mentioned above, the second ultrasound image contains a larger proportion of information reflecting the ultrasound contrast suspension. Therefore, the preprocessing operation for the second ultrasound image is as follows:

[0057] First, adaptive filtering is used to filter the second ultrasound image. Then, the filtered second ultrasound image is input into a low-pass filter to filter out the high-frequency components in the second ultrasound image as much as possible, thereby increasing the proportion of information reflected by the ultrasound contrast suspension.

[0058] Ultrasound contrast suspension is better able to reflect whether an internal leak has occurred. Therefore, the above steps S2-S3 lay a good data foundation for accurately detecting whether an internal leak has occurred.

[0059] S4: Input the preprocessed first ultrasound image into the first artificial intelligence model to obtain the abdominal aortic aneurysm image in the first ultrasound image;

[0060] The first artificial intelligence model is one of the following: neural network model, convolutional neural network model, and YOLO-5 model;

[0061] Specifically, obtaining the location of the abdominal aortic aneurysm using the first artificial intelligence model involves training the first artificial intelligence model by collecting a training set until the training meets the stopping condition, and then inputting the preprocessed first ultrasound image into the first artificial intelligence model to obtain the location of the abdominal aortic aneurysm.

[0062] S5: Perform an image alignment operation on the first ultrasound image and the second ultrasound image to obtain the position of the abdominal aortic aneurysm image in the first ultrasound image in the second ultrasound image, thereby obtaining the abdominal aortic aneurysm image in the second ultrasound image.

[0063] Among them, a similarity measurement method is used to perform image alignment operation between the first ultrasound image and the second ultrasound image;

[0064] S6: Input the abdominal aortic aneurysm image from the second ultrasound image into the second artificial intelligence model to detect whether endoleak occurs after abdominal aortic aneurysm isolation surgery;

[0065] The second artificial intelligence model is one of the following: neural network model, convolutional neural network model, and YOLO-5 model;

[0066] Specifically, the second artificial intelligence model is used to obtain the location of the abdominal aortic aneurysm. This involves training the second artificial intelligence model by collecting a training set until the training meets the stopping condition, and then inputting the preprocessed second ultrasound image into the second artificial intelligence model to detect whether endoleak occurs after the abdominal aortic aneurysm isolation procedure.

[0067] This embodiment acquires ultrasound images of the same location with different parameters. First, a high operating frequency is used to acquire a first ultrasound image, and then a low operating frequency is used to acquire a second ultrasound image. Then, different preprocessing methods are used to preprocess the first and second ultrasound images. The first ultrasound image is then input into an artificial intelligence model to determine the location of the aortic aneurysm. Based on this location, the location of the aortic aneurysm in the second ultrasound image is obtained. The aortic aneurysm in the second image is then input into the artificial intelligence model, thereby achieving endoleak diagnosis. This method avoids the need for complex image fusion algorithms to perform diagnosis on two ultrasound images, as is done in existing technologies, thus improving diagnostic efficiency.

[0068] In addition, during image preprocessing, since the first ultrasound image is mainly used to obtain the location of the aortic aneurysm, wavelet transform is used to preprocess it to retain as much high-frequency information as possible that can reflect human tissue information. For the second ultrasound image, a low-pass filter is used to preprocess it to retain as much information as possible that can reflect the ultrasound contrast suspension. The different preprocessing methods are used to ensure that the preprocessing process retains and reflects useful information as much as possible, laying a good data foundation for subsequent endoleak detection.

[0069] Example 2, see Figure 1 This embodiment discloses a diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images. The system includes:

[0070] An ultrasound image acquisition module is used to acquire a first ultrasound image and a second ultrasound image for the diagnosis of endoleak after endovascular repair of abdominal aortic aneurysm.

[0071] The process of acquiring ultrasound contrast images by the ultrasound image acquisition module is as follows:

[0072] Set the ultrasound diagnostic instrument to the first operating frequency, and acquire the first ultrasound contrast image according to the first operating frequency;

[0073] The ultrasound diagnostic instrument is set to a second operating frequency, and a second ultrasound contrast image is acquired according to the second operating frequency.

[0074] Furthermore, the first operating frequency is 8MHz.

[0075] Furthermore, the second operating frequency is 4MHz.

[0076] The first ultrasound image preprocessing module is used to perform preprocessing operations on the first ultrasound image to obtain a preprocessed first ultrasound image; the process of the first ultrasound image preprocessing module performing preprocessing operations on the first ultrasound image is as follows:

[0077] Perform a first filtering operation on the first ultrasound image;

[0078] A second filtering operation is performed on the first ultrasound image; the second filtering operation is to process the first ultrasound image using wavelet transform, and to filter the low-frequency noise components in the first ultrasound image using wavelet transform; in this process, the high-frequency information in the first ultrasound image is preserved.

[0079] The second ultrasound image preprocessing module is used to perform preprocessing operations on the second ultrasound image to obtain a preprocessed second ultrasound image.

[0080] The second ultrasound image preprocessing module performs preprocessing operations on the second ultrasound image to obtain the preprocessed second ultrasound image. The process is as follows: first, adaptive filtering is used to filter the second ultrasound image, and then the filtered second ultrasound image is input to a low-pass filter to filter out the high-frequency components in the second ultrasound image, thereby increasing the proportion of information reflected by the ultrasound contrast suspension.

[0081] The first ultrasound image abdominal aortic aneurysm image acquisition module is used to input the preprocessed first ultrasound image into the first artificial intelligence model to acquire the abdominal aortic aneurysm image in the first ultrasound image; the first artificial intelligence model is one of a neural network model, a convolutional neural network model, and a YOLO-5 model.

[0082] The second ultrasound image abdominal aortic aneurysm image acquisition module is used to perform an image alignment operation between the first ultrasound image and the second ultrasound image, thereby obtaining the position of the abdominal aortic aneurysm image in the first ultrasound image in the second ultrasound image, and obtaining the abdominal aortic aneurysm image in the second ultrasound image.

[0083] The endoleak detection module is used to input the abdominal aortic aneurysm image from the second ultrasound image into the second artificial intelligence model to detect whether an endoleak occurs after the abdominal aortic aneurysm isolation procedure.

[0084] The second artificial intelligence model is one of the following: neural network model, convolutional neural network model, or YOLO-5 model.

[0085] Example 3: This example discloses an electronic device, which includes one or more processors and a memory.

[0086] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0087] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions to implement the above-described method for diagnosing endoleak after endovascular repair of abdominal aortic aneurysms based on ultrasound angiography images, and / or other desired functions. Various contents such as initial extrinsic parameters and thresholds may also be stored in the computer-readable storage medium.

[0088] In one example, the electronic device may also include input and output devices, which are interconnected via a bus system and / or other forms of connection (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including warning messages, braking force, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0089] In addition, depending on the specific application, electronic devices may include any other suitable components.

[0090] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform any or all of the steps of the method for diagnosing endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images provided in any embodiment of this application.

[0091] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0092] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of a brain-computer interaction-based game character control method provided in any embodiment of this application.

[0093] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0094] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0095] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography, characterized in that, The system includes: The ultrasound image acquisition module is used to acquire a first ultrasound image and a second ultrasound image for diagnosing endoleak after endovascular repair of an abdominal aortic aneurysm; the process of acquiring ultrasound contrast images by the ultrasound image acquisition module is as follows: The ultrasound diagnostic instrument is set to a first operating frequency, and a first ultrasound contrast image is acquired according to the first operating frequency; the first operating frequency is 8MHz. The ultrasound diagnostic instrument is set to a second operating frequency, and a second ultrasound contrast image is acquired according to the second operating frequency; the second operating frequency is 4MHz. The first ultrasound image preprocessing module is used to perform preprocessing operations on the first ultrasound image to obtain a preprocessed first ultrasound image. The second ultrasound image preprocessing module is used to perform preprocessing operations on the second ultrasound image to obtain a preprocessed second ultrasound image. The first ultrasound image abdominal aortic aneurysm image acquisition module is used to input the preprocessed first ultrasound image into the first artificial intelligence model to acquire the abdominal aortic aneurysm image in the first ultrasound image. The second ultrasound image abdominal aortic aneurysm image acquisition module is used to perform an image alignment operation between the first ultrasound image and the second ultrasound image, thereby obtaining the position of the abdominal aortic aneurysm image in the first ultrasound image in the second ultrasound image, and obtaining the abdominal aortic aneurysm image in the second ultrasound image. The endoleak detection module is used to input the abdominal aortic aneurysm image from the second ultrasound image into the second artificial intelligence model to detect whether an endoleak occurs after the abdominal aortic aneurysm isolation procedure.

2. The diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound contrast imaging as described in claim 1, characterized in that, The process of the first ultrasound image preprocessing module performing preprocessing operations on the first ultrasound image is as follows: Perform a first filtering operation on the first ultrasound image; A second filtering operation is performed on the first ultrasound image.

3. The diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound contrast imaging as described in claim 2, characterized in that, The second filtering operation involves processing the first ultrasound image using wavelet transform. Specifically, wavelet transform is used to filter low-frequency noise components in the first ultrasound image while retaining high-frequency information in the first ultrasound image.

4. The diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound contrast imaging as described in claim 1, characterized in that, The second ultrasound image preprocessing module performs preprocessing operations on the second ultrasound image to obtain the preprocessed second ultrasound image. The process is as follows: first, adaptive filtering is used to filter the second ultrasound image, and then the filtered second ultrasound image is input to a low-pass filter to filter out the high-frequency components in the second ultrasound image, thereby increasing the proportion of information reflected by the ultrasound contrast suspension.

5. The diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images according to claim 1, characterized in that, The first artificial intelligence model is one of the following: neural network model, convolutional neural network model, and YOLO-5 model.

6. The diagnostic system for endoleak after endovascular repair of abdominal aortic aneurysm based on ultrasound angiography images according to claim 1, characterized in that, The second artificial intelligence model is one of the following: neural network model, convolutional neural network model, or YOLO-5 model.

Images