CN116491983A - Vascular imaging method and related device of artificial arteriovenous arm - Google Patents

Abstract

The application relates to an artificial artery and vein arm blood vessel imaging method and a related device, wherein the method comprises the following steps: acquiring a shallow near infrared image and a deep near infrared image, layering the deep near infrared image based on the shallow near infrared image to obtain venous vessel image information and arterial vessel image information; acquiring a pulse Doppler ultrasonic image, and acquiring the relative position relationship between a vein and a vein based on the pulse Doppler ultrasonic image; calculating theoretical arterial vessel image information from venous vessel image information based on the relative positional relationship; and matching the theoretical arterial blood vessel image with the arterial blood vessel image, and complementing the arterial blood vessel image based on a matching result. The imaging device has the advantage of improving the imaging effect of the blood vessel imaging instrument.

Description

Vascular imaging method and related device of artificial arteriovenous arm

technical field

The present application relates to the field of medical imaging, in particular to an artificial arteriovenous arm blood vessel imaging method and related devices.

Background technique

Vascular Imaging Instrument is a medical device that is mainly used to clearly display the vascular structure of the patient's skin surface or near the surface in real time through advanced imaging technology. This device is very helpful for medical staff, especially when it is necessary to perform procedures such as venipuncture, catheter insertion, and blood drawing.

The working principle of angiography is usually based on near-infrared light (NIR) technology. Under this technology, a blood vessel imaging device emits near-infrared light of a specific wavelength, and then captures the reflected light through a high-resolution imaging system. Because hemoglobin has a strong absorption capacity for near-infrared light, the blood in the blood vessel has very different absorption and scattering characteristics of light compared with the surrounding tissue, which makes the blood vessel clearly displayed in the image.

A fistula is an artificially created connection between an artery and a vein, usually in hemodialysis patients. In the clinic, the doctor needs to observe the location of the internal fistula, the direction of the blood vessels and the blood flow. However, the vascular imaging instrument is mainly used to display the vascular structure on the skin surface or near the surface. For deeper blood vessels, especially arteries, because near-infrared light is not easy to penetrate to its depth, the arterial imaging may be shallow and thin, or Present intermittent state, it is difficult to meet the clinical requirements.

Contents of the invention

In order to improve the imaging effect of a blood vessel imaging device, the present application provides a blood vessel imaging method and a related device of an artificial arteriovenous arm.

In the first aspect, the present application provides a method for angiography of an artificial arteriovenous arm, which adopts the following technical scheme:

A method for angiography of an artificial arteriovenous arm, comprising the following steps:

Acquire shallow near-infrared images and deep near-infrared images, wherein the shallow near-infrared images contain venous blood vessel image information, and the deep near-infrared images contain venous blood vessel image information and arterial blood vessel image information; the shallow near-infrared images are based on the equipment received The image generated by the near-infrared light of the first light intensity emitted by the device itself in the reflected light of the target object; the deep near-infrared image is generated by the device based on the received near-infrared light of the second light intensity emitted by the device itself in the reflected light of the target object of images, the second intensity is greater than the first intensity.

Based on the shallow near-infrared image, the deep near-infrared image is layered to obtain venous blood vessel image information and arterial blood vessel image information;

Obtaining a pulsed Doppler ultrasound image, and obtaining the relative positional relationship between the venous vessel and the venous vessel based on the pulsed Doppler ultrasound image;

Based on the relative positional relationship, the theoretical arterial blood vessel image information is calculated from the venous blood vessel image information;

Match the theoretical arterial image and the arterial image, and complete the arterial image based on the matching result.

By adopting the above technical solution, the light intensity of the shallow near-infrared image is relatively low, so the imaging obtained by the device basically only contains the image of the veins and blood vessels. After the near-infrared light increases the irradiation power, the deep near-infrared image can contain clearer venous blood vessel images and relatively blurred and incomplete arterial blood vessel images, so arterial blood vessel images need to be processed. Pulse Doppler ultrasound images can accurately obtain arterial and venous blood vessel images. However, pulse Doppler ultrasound images have certain shortcomings. Although they have a large imaging range, their images need to keep the probe in the same direction as the blood flow. At a certain angle, and the time resolution of the imaging is low, it may not be able to capture the rapidly changing blood flow velocity and flow direction in real time. Therefore, it cannot be compared with near-infrared images in this regard. Therefore, this solution calculates the relative positional relationship between venous vessels and venous vessels by using the device to obtain pulsed Doppler ultrasound images at a suitable position, and then uses the relative positional relationship and clear real-time venous vessel image information to calculate Obtain real-time theoretical arterial blood vessel image information. Since the shooting position of the near-infrared image is prone to large changes, that is, it is not obtained at the same position as the pulse Doppler ultrasound image, and due to the existence of the phase difference, the relative positional relationship corresponding to different positions may be deviated. Therefore, the theoretical arterial vessel image will actually deviate from the actual position. Therefore, the theoretical arterial image can be matched with the arterial image, and the matching part in the arterial image can be completed to obtain a complete arterial image. Since the arterial blood vessel image and the venous blood vessel image are captured at the same position and at the same time, the difference is very small, which can meet the clinical use requirements. In the same way, through this technology, internal fistulas between deep and superficial layers can be clearly imaged at the same time.

Optionally, the step of layering the deep near-infrared image based on the shallow near-infrared image to obtain venous blood vessel image information and arterial blood vessel image information includes:

Image alignment of shallow near-infrared images and deep near-infrared images;

Using the shallow near-infrared image to perform image difference on the deep near-infrared image;

Perform threshold processing and noise reduction processing on the deep near-infrared image after the difference;

The processed differential image is analyzed to obtain venous blood vessel image information and arterial blood vessel image information.

By adopting the above technical scheme, the shallow near-infrared image is spatially aligned with the deep near-infrared image. If the two are not aligned, try to use feature point matching (such as SIFT, SURF, etc.) and affine transformation to align them. Subtract the aligned shallow near-infrared image from the deep near-infrared image pixel by pixel, which will generate a difference image that contains the content that the shallow near-infrared image does not have in the deep near-infrared image. Thresholding is applied to the difference image so that it is easier to distinguish the content that is not in the shallow near-infrared image in the deep near-infrared image, and the appropriate threshold is selected to adjust according to the actual situation and needs of the image. Since the differential image may contain noise, the differential image can be processed using median filtering, Gaussian filtering and other noise reduction methods to obtain a clearer result. The processed differential image is analyzed to extract the content that is not in the shallow near-infrared image in the deep near-infrared image. This can be achieved through morphological operations, contour detection, region growing, etc.

Optionally, the step of analyzing the result of the processed differential image to obtain venous blood vessel image information and arterial blood vessel image information includes:

Taking the processed difference image as the first image, taking the deep near-infrared image to differentiate the first image and processing the result image as the second image, and extracting the blood vessel centerlines of the first image and the second image;

detecting vessel branch points of the vessel centerlines of the first image and the second image;

performing vessel segmentation on the vessel centerlines of the first image and the second image;

Blood vessel feature extraction is performed to obtain blood vessel feature information of the first image and the second image as arterial vessel image information and venous vessel image information, wherein the vessel feature information includes length information, curvature information, and width information.

By adopting the above technical solution, the centerline of the blood vessel image is extracted, and branch points on the centerline of the blood vessel are detected, and these points can be found by using methods such as endpoint detection and branch point detection. According to the branch points, the blood vessel centerline is divided into several segments, and each segment represents a blood vessel path between two branch points. For each vascular path, extract its features, such as length, curvature, width, etc. These features can be used to describe the relative positional relationship between blood vessels. According to the extracted features, a feature matrix is generated, and each row of the matrix represents a feature vector of a blood vessel path. Through this feature matrix, the relative positional relationship between blood vessels can be represented.

Optionally, the step of acquiring the pulsed Doppler ultrasound image, and acquiring the relative positional relationship between the venous blood vessel and the venous blood vessel based on the pulsed Doppler ultrasound image includes:

Obtain a pulsed Doppler ultrasound image and mark the venous part, arterial part and stoma part on the pulsed Doppler ultrasound image;

Extraction of vessel centerlines based on pulsed Doppler ultrasound images and corresponding to veins, arteries and ostomy tubes;

A relative position feature matrix is generated based on each vessel centerline.

Optionally, the pulse Doppler ultrasound probe is set from the proximal end of the target to the distal end, or is set from the distal end of the target to the proximal end.

By adopting the above technical solution, the pulse Doppler ultrasound equipment transmits short-time pulse ultrasound through a probe. These ultrasound waves travel through different tissues and are eventually reflected back by red blood cells in the bloodstream. According to the Doppler effect, when ultrasound waves bounce off a moving object, such as red blood cells in the bloodstream, their frequency changes. This change in frequency is proportional to the speed and direction of the object. Pulse Doppler ultrasound equipment calculates the velocity and direction of blood flow by measuring the frequency change of the echo signal. When the probe is completely facing the direction of blood flow (that is, the included angle is 0 degrees), the Doppler frequency shift will reach the maximum, and the measured blood flow velocity will be higher than the actual value at this time. Conversely, if the probe faces away from the direction of blood flow (that is, the included angle is 180 degrees), the Doppler frequency shift will reach the minimum, and the measured blood flow velocity will be lower than the actual value at this time. Therefore, the pulse Doppler ultrasound probe can be set from the proximal end of the target to the distal end, or from the distal end of the target to the proximal end, to distinguish veins, arteries, and ostomy tubes, and to obtain their relative Location feature matrix.

Optionally, the step of matching the theoretical arterial image and the arterial image, and completing the arterial image based on the matching result includes:

Perform feature extraction and matching on the theoretical arterial image and the arterial image to generate a set of matching point pairs;

Screen the matching point pairs based on the random sampling consensus algorithm;

Based on the filtered matching point pairs, calculating a transformation matrix between the theoretical arterial vessel image and the arterial vessel image;

transforming the theoretical arterial image based on the transformation matrix to align with the arterial image, and performing region matching on the transformed theoretical arterial image and the arterial image;

Obtain the region in the arterial image whose matching degree is greater than the matching threshold for optimal completion.

By adopting the above technical solution, features are extracted from the blood vessel centerline image. These features can be the geometric shape of blood vessels (such as length, curvature, etc.), the topological structure of blood vessels (such as bifurcation points, connection relationships, etc.), or the spatial location information of blood vessels. Use feature matching algorithms (such as SIFT, SURF, etc.) to match the features in the two images. This will generate a set of matching point pairs that can be used to calculate the degree of matching. Because feature matching may produce some wrong matching point pairs, it is necessary to filter these matching point pairs. This can be achieved with the Random Sample Consensus (RANSAC) algorithm or other robust methods. Based on the filtered matching point pairs, calculate the matching degree between two blood vessel centerline images, which can be calculated by calculating the average distance between matching point pairs, the ratio of matching point pairs to the total number of points, the spatial distribution of matching point pairs, etc. method to achieve. The degree of matching can be represented by a numerical value, the higher the numerical value, the better the degree of matching. Evaluate the similarity between two vessel centerline images based on the degree of match value. A threshold can be set, and when the matching degree is higher than the threshold, it is considered that the two images have a higher matching degree. The region where the matching degree is greater than the matching threshold means that the aberration of the near-infrared image and the Doppler ultrasound image has little influence on the region, and a good arterial image can be obtained by optimizing and complementing it.

In the second aspect, an artificial arteriovenous arm vascular imaging device provided by the present application adopts the following technical solution:

An artificial arteriovenous arm vascular imaging device, comprising:

A near-infrared image acquisition module, configured to acquire a shallow near-infrared image and a deep near-infrared image, wherein the shallow near-infrared image includes venous blood vessel image information, and the deep near-infrared image includes venous blood vessel image information and arterial blood vessel image information;

The image layering module is used to layer the deep near-infrared image based on the shallow near-infrared image to obtain venous blood vessel image information and arterial blood vessel image information;

The image acquisition and calculation module is used to acquire the pulse Doppler ultrasound image, and obtain the relative position relationship between the venous blood vessel and the venous blood vessel based on the pulse Doppler ultrasound image;

The theoretical image generation module is used to calculate the theoretical arterial image information from the venous image information based on the relative positional relationship;

The matching completion module is used for matching the theoretical arterial vessel image and the arterial vessel image, and completing the arterial vessel image based on the matching result.

In the third aspect, a computer device provided by the present application adopts the following technical solution:

A computer device comprising:

one or more processors;

memory;

one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more program programs are configured to: execute The above-mentioned artificial arteriovenous arm angiography method.

In the fourth aspect, a computer-readable storage medium provided by the present application adopts the following technical solution:

A computer-readable storage medium stores a computer program capable of being loaded by a processor and executing the above-mentioned method.

The storage medium stores at least one instruction, at least one section of program, code set or instruction set, and the at least one instruction, the at least one section of program, the code set or instruction set are loaded and executed by the processor to implement: Arteriovenous arm vascular imaging method as described above.

Description of drawings

FIG. 1 is a flow chart of a method for imaging blood vessels in an artificial arteriovenous arm according to an embodiment of the present invention.

FIG. 2 is a flow chart of sub-step S2 in an embodiment of the present invention.

FIG. 3 is a flow chart of sub-step S24 in an embodiment of the present invention.

FIG. 4 is a flow chart of sub-step S3 in an embodiment of the present invention.

FIG. 5 is a flow chart of sub-step S5 in an embodiment of the present invention.

FIG. 6 is a schematic diagram of a computer device in an embodiment of the present invention.

Implementation

The present application will be described in further detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of inventive concepts. As part of this specification, some of the drawings of the present disclosure represent structures and devices in block diagram form in order to avoid obscuring the principles of the disclosure. In the interest of clarity, not all features of an actual implementation are necessarily described. In addition, the language used in this disclosure has been chosen primarily for readability and instructional purposes, and may not have been chosen to delineate or delimit the inventive subject matter, so that recourse to the claims is necessary to determine such subject of invention. Reference in this disclosure to "an implementation" or "an implementation" means that a particular feature, structure, or characteristic described in connection with that implementation is included in at least one implementation, and reference to "an implementation" or Multiple references to "an implementation" should not be read as necessarily all referring to the same implementation.

Unless expressly limited, the terms "a", "an" and "the" are not intended to refer to a singular entity but rather include the general class of which specific instances may be used for illustration. Thus, use of the terms "a" or "an" may mean any number of at least one, including "one", "one or more", "at least one" and "one or more than one". The term "or" means any of the alternatives and any combination of the alternatives, including all alternatives, unless the alternatives are expressly stated to be mutually exclusive. The phrase "at least one of" when combined with a list of items means a single item in the list or any combination of items in the list. The phrase does not require all of the listed items, unless expressly so limited.

The embodiment of the present application discloses a method for imaging blood vessels in an artificial arteriovenous arm. Referring to Fig. 1, the artificial arteriovenous arm angiography method includes

S1. Obtain a shallow near-infrared image and a deep near-infrared image, wherein the shallow near-infrared image includes venous blood vessel image information, and the deep near-infrared image includes venous blood vessel image information and arterial blood vessel image information. The shallow near-infrared image is the image generated by the device based on the reflected light of the near-infrared light of the first light intensity emitted by the device on the target object; the deep near-infrared image is the image generated by the device based on the received second light intensity emitted by itself In an image generated by the reflected light of the near-infrared light on the target object, the second intensity is greater than the first intensity.

Near-Infrared Vascular Imaging System (NIRVIS) is a medical imaging technique that visualizes the vascular structure under the skin by using a near-infrared light source. The basic principle is to use the penetration of near-infrared light in tissues and the absorption characteristics of hemoglobin in blood to near-infrared light. Near-infrared light has a wavelength in the roughly 700-900 nanometer range, which allows it to penetrate skin and other biological tissues. In this wavelength range, hemoglobin in blood has a high absorption rate of near-infrared light, while skin, muscle and other tissues have relatively low absorption of near-infrared light. Therefore, when near-infrared light hits the surface of the skin, it can penetrate the skin and be absorbed by the hemoglobin in blood vessels. Light that is not absorbed scatters back to the skin surface and is captured by the imager's detectors.

Therefore, due to the relatively low light intensity of the shallow near-infrared image, the imaging obtained by the device basically only contains images of veins and blood vessels. After the near-infrared light increases the irradiation power, the deep near-infrared image can contain clearer venous blood vessel images and relatively blurred and incomplete arterial blood vessel images, so arterial blood vessel images need to be processed.

It should be noted that, in different embodiments, the near-infrared image can be processed by using the projection device, and then the processed image can be projected on the target object, so as to realize the visualization inside the blood vessel. Or use the display screen to superimpose the recognized blood vessel image on the natural light imaging photo to realize the visualization of the blood vessel. Of course, other methods can also be used, as long as the images that can be easily obtained can be visualized.

S2. Layering the deep near-infrared image based on the shallow near-infrared image to obtain venous blood vessel image information and arterial blood vessel image information.

Since the deep near-infrared image can contain a clearer venous image and a blurred and less complete arterial image, the deep near-infrared image can be processed by a differential method to obtain the venous image information and arterial image information.

Specifically, referring to FIG. 2 , in an embodiment, S2 includes the following sub-steps S21-S24.

S21. Perform image alignment on the shallow near-infrared image and the deep near-infrared image.

The shallow near-infrared image is spatially aligned with the deep near-infrared image. If the two are not aligned, try to use feature point matching (such as SIFT, SURF, etc.) and affine transformation to align them.

S22. Using the shallow near-infrared image to perform image difference on the deep near-infrared image.

Subtract the aligned shallow near-infrared image from the deep near-infrared image pixel by pixel, which will generate a difference image that contains the content that the shallow near-infrared image does not have in the deep near-infrared image.

S23. Perform threshold value processing and noise reduction processing on the deep near-infrared image after the difference.

Thresholding is applied to the difference image so that it is easier to distinguish the content that is not in the shallow near-infrared image in the deep near-infrared image, and the appropriate threshold is selected to adjust according to the actual situation and needs of the image. Since the differential image may contain noise, the differential image can be processed using median filtering, Gaussian filtering and other noise reduction methods to obtain a clearer result.

S24. Perform result analysis on the processed differential image to obtain venous blood vessel image information and arterial blood vessel image information.

The processed differential image is analyzed to extract the content that is not in the shallow near-infrared image in the deep near-infrared image. This can be achieved through morphological operations, contour detection, region growing, etc.

Specifically, referring to FIG. 3, in a certain embodiment, S24 may include the following steps:

S241. Using the processed difference image as the first image, taking the deep near-infrared image to differentiate the first image and processing the resulting image as the second image, extracting the blood vessel centerlines of the first image and the second image.

Extract the centerline of the vessel image and detect the branch points on the vessel centerline, which can be found using morphological operations such as endpoint detection, branch point detection, etc.

S242. Detect blood vessel branch points of the blood vessel centerlines in the first image and the second image.

According to the branch points, the blood vessel centerline is divided into several segments, and each segment represents a blood vessel path between two branch points.

S243. Perform blood vessel segmentation on the blood vessel centerlines in the first image and the second image.

For each vascular path, extract its features, such as length, curvature, width, etc. These features can be used to describe the relative positional relationship between blood vessels.

S244. Perform blood vessel feature extraction to obtain blood vessel feature information of the first image and the second image as arterial blood vessel image information and venous blood vessel image information, wherein the blood vessel feature information includes length information, curvature information, and width information.

According to the extracted features, a feature matrix is generated, and each row of the matrix represents a feature vector of a blood vessel path. Through this feature matrix, the relative positional relationship between blood vessels can be represented.

S3. Obtaining a pulsed Doppler ultrasound image, and acquiring a venous vessel and a relative positional relationship of the venous vessel based on the pulsed Doppler ultrasound image. The pulse Doppler ultrasonic probe is set from the proximal end of the target to the distal end, or is set from the distal end of the target to the proximal end.

Pulse Doppler ultrasound equipment sends short bursts of ultrasound waves through a probe. These ultrasound waves travel through different tissues and are eventually reflected back by red blood cells in the bloodstream. According to the Doppler effect, when ultrasound waves bounce off a moving object, such as red blood cells in the bloodstream, their frequency changes. This change in frequency is proportional to the speed and direction of the object. Pulse Doppler ultrasound equipment calculates the velocity and direction of blood flow by measuring the frequency change of the echo signal. When the probe is completely facing the direction of blood flow (that is, the included angle is 0 degrees), the Doppler frequency shift will reach the maximum, and the measured blood flow velocity will be higher than the actual value at this time. Conversely, if the probe faces away from the direction of blood flow (that is, the included angle is 180 degrees), the Doppler frequency shift will reach the minimum, and the measured blood flow velocity will be lower than the actual value at this time. Therefore, the pulse Doppler ultrasound probe can be set from the proximal end of the target to the distal end, or from the distal end of the target to the proximal end, to distinguish veins, arteries, and ostomy tubes, and to obtain their relative Location feature matrix.

It should be noted that the pulse Doppler ultrasound device and the near-infrared vascular imager can be integrated, can also be completely separated, or can be separated but connected by cables, and there can be differences in different embodiments. As long as the imaging process of the pulse Doppler ultrasound equipment and the near-infrared photovascular imager does not affect each other.

Specifically, referring to FIG. 4, in a certain embodiment, S3 may include the following steps:

S31. Acquire a pulsed Doppler ultrasound image, and mark the vein part, the artery part and the ostomy tube part on the pulse Doppler ultrasound image.

It should be noted that because the pulsed Doppler ultrasound image is relatively local and will continue to move during pulse Doppler ultrasound, it is possible to conduct a comprehensive scan of the arm and then perform vascular modeling, and mark it on the basis of the vascular modeling Venous part, arterial part and fistula part. However, the modeling process is not necessary every time, it only needs to be carried out during the initialization process, that is to say, the modeling can be obtained through data import without the need for patients to operate by themselves. The data source can be obtained by pulse Doppler ultrasound imaging performed by professionals, or obtained by other methods.

S32. Extracting the centerline of blood vessels based on the pulsed Doppler ultrasound image, and corresponding to veins, arteries and ostomy tubes.

Specifically, the pulse Doppler ultrasound image may be preprocessed first, such as operations such as smoothing filtering and noise reduction, to improve image quality. Then, the preprocessed vascular image is binarized, and the vascular area is set to 1 (white), and the non-vascular area is set to 0 (black). Perform distance transformation on the binarized image. The purpose of the distance transformation is to set the value of each pixel in the binary image to the distance from the point to the nearest background (non-vascular area) pixel. In this way, the pixel values in the centerline region of the blood vessel will be higher. Find the local maximum. These local maximum points are the centerline of the blood vessel. This is the skeletonization, which can be achieved by non-maximum suppression or other methods. Then repair the possible skeleton fractures, for example, the fractures of the skeleton can be repaired by morphological operations (such as dilation, erosion, opening and closing operations).

S33. Generate a relative position feature matrix based on the centerline of each blood vessel.

Detecting branch points on the centerline of vessels, these points can be found using morphological operations such as endpoint detection, branch point detection, etc. According to the branch point, the vessel centerline is divided into several segments. Each segment represents a vessel path between two branch points. For each vascular path, extract its features, such as length, curvature, width, etc. These features can be used to describe the relative positional relationship between blood vessels. According to the extracted features, a feature matrix is generated, and each row of the matrix represents a feature vector of a blood vessel path. Through this feature matrix, the relative positional relationship between blood vessels can be represented.

S4. Based on the relative positional relationship, calculate theoretical arterial blood vessel image information from the venous blood vessel image information.

In order to use the venous vessel centerline and the relative position feature matrix on the venous vessel image to generate the predicted arterial vessel centerline on the venous vessel image, the following methods can be used:

The position of the centerline of the predicted arterial vessel is estimated using the relative position feature matrix. This matrix contains the relative positional relationship between the centerline of the venous vessel and the centerline of the predicted arterial vessel on the deep near-infrared vessel image. Applying this matrix around venous vessel centerlines on deep near-infrared vessel images predicts the approximate location of predicted arterial vessel centerlines. For example, if the relative position feature matrix indicates that the centerline of the predicted artery is located 10 pixels to the left of the centerline of the venous vessel, then the predicted centerline of the arterial vessel can be found at the position 10 pixels to the left of the centerline of the venous vessel on the venous vessel image .

S5. Matching the theoretical arterial image and the arterial image, and completing the arterial image based on the matching result.

S51. Perform feature extraction and matching on the theoretical arterial image and the arterial image to generate a set of matching point pairs.

Extract features from vessel centerline images. These features can be the geometric shape of blood vessels (such as length, curvature, etc.), the topological structure of blood vessels (such as bifurcation points, connection relationships, etc.), or the spatial location information of blood vessels. Use feature matching algorithms (such as SIFT, SURF, etc.) to match the features in the two images. This will generate a set of matching point pairs that can be used to calculate the degree of matching.

S52. Screen the matching point pairs based on the random sampling consensus algorithm.

Because feature matching may produce some wrong matching point pairs, it is necessary to filter these matching point pairs. This can be achieved with the Random Sample Consensus (RANSAC) algorithm or other robust methods.

S53. Based on the filtered matching point pairs, calculate a transformation matrix between the theoretical arterial vessel image and the arterial vessel image.

Based on the filtered matching point pairs, calculate the matching degree between two blood vessel centerline images, which can be calculated by calculating the average distance between matching point pairs, the ratio of matching point pairs to the total number of points, the spatial distribution of matching point pairs, etc. method to achieve.

S54. Transform the theoretical arterial vessel image based on the transformation matrix to align with the arterial vessel image, and then perform region matching on the transformed theoretical arterial vessel image and the arterial vessel image.

The degree of matching can be represented by a numerical value, the higher the numerical value, the better the degree of matching. Evaluate the similarity between two vessel centerline images based on the degree of match value. A threshold can be set, and when the matching degree is higher than the threshold, it is considered that the two images have a higher matching degree.

S55. Obtain an area in the arterial image whose matching degree is greater than a matching threshold for optimization and completion.

The region where the matching degree is greater than the matching threshold means that the aberration of the near-infrared image and the Doppler ultrasound image has little influence on the region, and a good arterial image can be obtained by optimizing and complementing it.

In order to calculate the matching degree of the two blood vessel centerline images, the matching degree between the two blood vessel centerline images may be calculated based on the filtered matching point pairs. This can be achieved by calculating the average distance between matching point pairs, the ratio of matching point pairs to the total number of points, and the spatial distribution of matching point pairs. The degree of matching can be represented by a numerical value, the higher the numerical value, the better the degree of matching. Evaluate the similarity between two vessel centerline images based on the degree of match value. A threshold can be set, and when the matching degree is higher than the threshold, it is considered that the two images have a higher matching degree.

S6. The differentiated venous blood vessel image, the optimized and completed arterial blood vessel image, and the ostomy tube are used as different layers, and output to the outside according to requirements.

It should be noted that since the ostomy tube is between the deep layer and the superficial layer, it can be obtained through the method of difference and completion. In some embodiments, the image of the ostomy tube may be recognized as a blood vessel. In other embodiments, The image of the ostomy tube can be obtained by Doppler ultrasound image, the principle is similar to the above, and will not be repeated here.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present invention.

In one embodiment, an artificial arteriovenous arm vascular imaging device is provided, and the artificial arteriovenous arm vascular imaging device is one-to-one corresponding to the artificial arteriovenous arm vascular imaging method in the above embodiment. Each functional module of the artificial arteriovenous arm vascular imaging device is described in detail as follows:

A near-infrared image acquisition module, configured to acquire a shallow near-infrared image and a deep near-infrared image, wherein the shallow near-infrared image includes venous blood vessel image information, and the deep near-infrared image includes venous blood vessel image information and arterial blood vessel image information;

The image layering module is used to layer the deep near-infrared image based on the shallow near-infrared image to obtain venous blood vessel image information and arterial blood vessel image information;

The image acquisition and calculation module is used to acquire the pulse Doppler ultrasound image, and obtain the relative position relationship between the venous blood vessel and the venous blood vessel based on the pulse Doppler ultrasound image;

A theoretical image generation module, used for calculating theoretical arterial image information from venous image information based on the relative positional relationship;

The matching completion module is used for matching the theoretical arterial vessel image and the arterial vessel image, and completing the arterial vessel image based on the matching result.

For the specific limitations of the artificial arteriovenous arm vascular imaging device, please refer to the above-mentioned definition of the artificial arteriovenous arm vascular imaging method, which will not be repeated here. Each module in the above artificial arteriovenous arm vascular imaging device can be fully or partially realized by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In an embodiment, a computer device is provided, which may be a server, and its internal structure may be as shown in FIG. 6 . The computer device includes a processor, memory, network interface and database connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for data related to the vascular imaging method of the artificial arteriovenous arm. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an artificial arteriovenous arm blood vessel imaging method is realized.

In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the artificial arteriovenous arm angiography method of the above-mentioned embodiment is realized. , such as S1-S6 shown in Figure 1. Alternatively, when the processor executes the computer program, the functions of the various modules/units of the artificial arteriovenous arm vessel imaging device in the above-mentioned embodiments are realized. To avoid repetition, details are not repeated here.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for angiography of an artificial arteriovenous arm of the above-mentioned embodiment is implemented, such as S1-S6 shown in FIG. 1 . Alternatively, when the computer program is executed by the processor, the functions of the various modules/units in the artificial arteriovenous arm angiography device in the above device embodiments are realized. To avoid repetition, details are not repeated here.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium , when the computer program is executed, it may include the procedures of the embodiments of the above-mentioned methods. Wherein, any reference to memory, storage, database or other media used in various embodiments of the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be described in the foregoing embodiments Modifications to the technical solutions recorded, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should be included in the scope of the present invention. within the scope of protection.

Claims (10)

1. an artificial arteriovenous arm angiography method, is characterized in that, comprises the following steps: Obtain a shallow near-infrared image and a deep near-infrared image, wherein the shallow near-infrared image contains venous blood vessel image information, and the deep near-infrared image contains venous blood vessel image information and arterial blood vessel image information; Based on the shallow near-infrared image, the deep near-infrared image is layered to obtain venous blood vessel image information and arterial blood vessel image information; Obtaining a pulsed Doppler ultrasound image, and obtaining the relative positional relationship between the venous vessel and the venous vessel based on the pulsed Doppler ultrasound image; Based on the relative positional relationship, the theoretical arterial blood vessel image information is calculated from the venous blood vessel image information; Match the theoretical arterial image and the arterial image, and complete the arterial image based on the matching result. 2. The artificial arteriovenous arm vascular imaging method according to claim 1, wherein the shallow near-infrared image is the reflection of the near-infrared light on the target object based on the received first light intensity emitted by the device itself The image generated by light; the deep near-infrared image is an image generated by the device based on the received reflected light of the near-infrared light of the second illumination intensity emitted by the device itself on the target object, and the second intensity is greater than the first intensity. 3. The artificial arteriovenous arm vascular imaging method according to claim 2, characterized in that, the deep near-infrared image is layered based on the shallow near-infrared image, and the step of obtaining venous blood vessel image information and arterial blood vessel image information ,include: Image alignment of shallow near-infrared images and deep near-infrared images; Using the shallow near-infrared image to perform image difference on the deep near-infrared image; Perform threshold processing and noise reduction processing on the deep near-infrared image after the difference; The processed differential image is analyzed to obtain venous blood vessel image information and arterial blood vessel image information. 4. The artificial arteriovenous arm vascular imaging method according to claim 3, wherein the step of performing result analysis on the processed differential image to obtain venous vessel image information and arterial vessel image information comprises: Taking the processed difference image as the first image, taking the deep near-infrared image to differentiate the first image and processing the result image as the second image, and extracting the blood vessel centerlines of the first image and the second image; detecting vessel branch points of the vessel centerlines of the first image and the second image; performing vessel segmentation on the vessel centerlines of the first image and the second image; Blood vessel feature extraction is performed to obtain blood vessel feature information of the first image and the second image as arterial vessel image information and venous vessel image information, wherein the vessel feature information includes length information, curvature information, and width information. 5. artificial arteriovenous arm blood vessel imaging method according to claim 4, is characterized in that, described acquisition pulse Doppler ultrasonic image, and based on pulse Doppler ultrasonic image, obtains the relative positional relationship of venous blood vessel and venous blood vessel steps, including: Obtain a pulsed Doppler ultrasound image and mark the venous part, arterial part and stoma part on the pulsed Doppler ultrasound image; Extraction of vessel centerlines based on pulsed Doppler ultrasound images and corresponding to veins, arteries and ostomy tubes; A relative position feature matrix is generated based on each vessel centerline. 6. The artificial arteriovenous arm vascular imaging method according to claim 5, wherein the step of matching the theoretical arterial vessel image and the arterial vessel image, and completing the arterial vessel image based on the matching result includes: Perform feature extraction and matching on the theoretical arterial image and the arterial image to generate a set of matching point pairs; Screen the matching point pairs based on the random sampling consensus algorithm; Based on the filtered matching point pairs, calculating a transformation matrix between the theoretical arterial vessel image and the arterial vessel image; transforming the theoretical arterial image based on the transformation matrix to align with the arterial image, and performing region matching on the transformed theoretical arterial image and the arterial image; Obtain the region in the arterial image whose matching degree is greater than the matching threshold for optimal completion. 7. artificial arteriovenous arm angiography method according to claim 6, is characterized in that, pulse Doppler ultrasonic probe is arranged by the direction of the proximal end of the target to the far-center end, or by the far-center end of the target to the proximal end End orientation setting. 8. An artificial arteriovenous arm vascular imaging device, characterized in that it comprises: A near-infrared image acquisition module, configured to acquire a shallow near-infrared image and a deep near-infrared image, wherein the shallow near-infrared image includes venous blood vessel image information, and the deep near-infrared image includes venous blood vessel image information and arterial blood vessel image information; The image layering module is used to layer the deep near-infrared image based on the shallow near-infrared image to obtain venous blood vessel image information and arterial blood vessel image information; The image acquisition and calculation module is used to acquire the pulse Doppler ultrasound image, and obtain the relative position relationship between the venous blood vessel and the venous blood vessel based on the pulse Doppler ultrasound image; The theoretical image generation module is used to calculate the theoretical arterial image information from the venous image information based on the relative positional relationship; The matching completion module is used for matching the theoretical arterial vessel image and the arterial vessel image, and completing the arterial vessel image based on the matching result. 9. A computer device, characterized in that it comprises: one or more processors; memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more program programs are configured to: execute The artificial arteriovenous arm angiography method according to any one of claims 1 to 7. 10. A computer-readable storage medium, characterized in that, the storage medium stores at least one instruction, at least one section of program, code set or instruction set, and the at least one instruction, the at least one section of program, the code set Or the instruction set is loaded and executed by the processor to realize: the artificial arteriovenous arm blood vessel imaging method according to any one of claims 1 to 7.