Method, apparatus, computer device and readable storage medium for determining blood vessel centerline

Abstract

The present application relates to a method, apparatus, computer device, and readable storage medium for determining a blood vessel centerline. The method includes obtaining black-blood medical images and bright-blood medical images; performing blood vessel identification processing on the black-blood medical images and the bright-blood medical images respectively to obtain black-blood vessel identification images and bright-blood vessel identification images, performing registration and fusion processing on the black-blood vessel identification images and the bright-blood vessel identification images to obtain a fused blood vessel identification image; extracting the segmented centerlines of each segment of blood vessels in the fused blood vessel identification image, and determining the centerline of the blood vessels in the black-blood medical images or the bright-blood medical images according to the segmented centerlines of each segment of blood vessels. The method for determining a blood vessel centerline provided by the present application can improve the accuracy of extracting the blood vessel centerline.

Description

Technical Field

[0001] The present application relates to the field of image processing technologies, and particularly to a method, apparatus, computer device, and readable storage medium for determining a blood vessel centerline. Background Art

[0002] In recent years, in China and worldwide, the incidence and mortality rates of cerebrovascular diseases have been increasing year by year and have gradually become one of the leading causes of death. The extraction of blood vessel centerlines is of great significance for the treatment of blood vessel diseases, and the extracted blood vessel centerlines can be used for the analysis and diagnosis of blood vessel diseases. With the development of magnetic resonance imaging technology, how to accurately extract blood vessel centerlines based on magnetic resonance blood vessel images is a problem to be solved.

[0003] In traditional technologies, the common way to extract blood vessel centerlines is to manually or interactively extract blood vessel centerlines in blood vessel images. However, the accuracy of the blood vessel centerlines extracted in this way is relatively low. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, computer device, and readable storage medium for determining a blood vessel centerline for the above technical problems.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a blood vessel centerline, including:

[0006] Obtain a black-blood medical image and a bright-blood medical image;

[0007] Perform blood vessel identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vessel identification image and a bright-blood vessel identification image, and perform registration and fusion processing on the black-blood vessel identification image and the bright-blood vessel identification image to obtain a fused blood vessel identification image;

[0008] Extract the segmented centerlines of each blood vessel in the fused blood vessel identification image, and determine the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of each blood vessel.

[0009] In one of the embodiments, performing blood vessel identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vessel identification image and a bright-blood vessel identification image, and performing registration and fusion processing on the black-blood vessel identification image and the bright-blood vessel identification image to obtain a fused blood vessel identification image includes:

[0010] Input the black-blood medical image and the bright-blood medical image into an image fusion model to obtain a fused blood vessel identification image.

[0011] In one embodiment, vascular identification processing is performed on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, including:

[0012] Input the black-blood medical image into the first identification model to obtain the black-blood vascular identification image;

[0013] Input the bright-blood medical image into the second identification model to obtain the bright-blood vascular identification image.

[0014] In one embodiment, before performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain the fused vascular identification image, the method for determining the vascular centerline further includes:

[0015] According to the vascular architecture, the interference regions in the black-blood vascular identification image and the bright-blood vascular identification image are removed respectively.

[0016] In one embodiment, according to the segmented centerline of each segment of the blood vessel, determining the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image includes:

[0017] Based on the black-blood medical image or the bright-blood medical image, processing the segmented centerline of each segment of the blood vessel to obtain an initial centerline;

[0018] According to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline, determining the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image.

[0019] In one embodiment, according to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline, determining the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image includes:

[0020] According to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline, determining the bifurcation points on the initial centerline;

[0021] According to the initial centerline and the bifurcation points on the initial centerline, determining the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image.

[0022] In one embodiment, based on the black-blood medical image or the bright-blood medical image, connecting and extending the segmented centerline of each segment of the blood vessel to obtain an initial centerline includes:

[0023] Based on the black-blood medical image or the bright-blood medical image, connecting the segmented centerline of each segment of the blood vessel to obtain a connected centerline;

[0024] According to a preset length threshold, performing extension processing on the connected centerline to obtain the initial centerline.

[0025] Second aspect, an embodiment of the present application provides a vascular centerline determination device, including:

[0026] An acquisition module, configured to acquire black-blood medical images and bright-blood medical images;

[0027] A fusion module, configured to perform vascular identification processing on the black-blood medical images and the bright-blood medical images respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and perform registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image;

[0028] A determination module, configured to extract the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determine the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of the blood vessels.

[0029] Third aspect, an embodiment of the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the above embodiment are implemented.

[0030] Fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0031] An embodiment of the present application provides a method, device, computer device, and readable storage medium for determining a vascular centerline. The method includes acquiring black-blood medical images and bright-blood medical images; performing vascular identification processing on the black-blood medical images and the bright-blood medical images respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image; extracting the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of each segment of blood vessels. The method for determining a vascular centerline provided in this embodiment determines the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image by extracting the segmented centerlines of each segment of blood vessels in the fused vascular identification image. The fused vascular identification image is obtained by registering and fusing the black-blood medical identification image and the bright-blood vascular identification image. The fused medical image corresponding to multiple medical images contains the features corresponding to multiple medical images. Then, the segmented centerlines can be determined more quickly and accurately through the fused medical image corresponding to multiple medical images (black-blood medical images and bright-blood medical images), thereby improving the accuracy and efficiency of determining the centerline of the blood vessels in each medical image (black-blood medical image or bright-blood medical image). Description of the Drawings

[0032] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0033] Figure 1 An application environment diagram of the blood vessel centerline determination method provided for an embodiment;

[0034] Figure 2 A schematic flowchart of the steps of the blood vessel centerline determination method provided for an embodiment;

[0035] Figure 3 A schematic diagram of a medical image provided for an embodiment;

[0036] Figure 4 A schematic diagram of a medical image with blood vessel markings provided for an embodiment;

[0037] Figure 5 A schematic flowchart of the steps of the blood vessel centerline determination method provided for another embodiment;

[0038] Figure 6 A schematic flowchart of the steps of the blood vessel centerline determination method provided for another embodiment;

[0039] Figure 7 A schematic flowchart of the steps of the blood vessel centerline determination method provided for another embodiment;

[0040] Figure 8 A schematic flowchart of the steps of the blood vessel centerline determination method provided for another embodiment;

[0041] Figure 9 A schematic diagram of the blood vessel centerline provided for an embodiment;

[0042] Figure 10 A schematic structural diagram of the blood vessel centerline determination device provided for an embodiment;

[0043] Figure 11 A schematic structural diagram of a computer device provided for an embodiment. Detailed implementation manners

[0044] To make the above objects, features, and advantages of the present application more apparent and understandable, the following provides a detailed description of the specific embodiments of the present application with reference to the accompanying drawings. Many specific details are set forth in the following description to facilitate a thorough understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0045] The method for determining the blood vessel centerline provided by the embodiment of the present application can be applied to an application environment as shown in Figure 1 The application environment includes a terminal 100 and a medical scanning device 200. Among them, the terminal can communicate with the medical scanning device 200 through a network. The terminal 100 can be, but is not limited to, various personal computers, laptop computers, and tablet computers. The medical scanning device 200 can be, but is not limited to, various magnetic resonance devices. The type of the medical scanning device 200 is not limited in this embodiment, as long as its function can be achieved.

[0046] In one embodiment, as shown in Figure 2 A method for determining the blood vessel centerline is provided. Taking the method applied to the terminal in Figure 1 as an example, the method includes the following steps:

[0047] Step 200: Obtain a black-blood medical image and a bright-blood medical image.

[0048] The black-blood medical image can be a medical image obtained by a medical scanning device using black-blood technology. Black-blood technology means that when using a medical scanning device for blood vessel imaging, a saturation radiofrequency pulse is applied before the blood flow enters the imaging volume to pre-saturate the blood flow. When the blood flow enters the imaging volume, a radiofrequency pulse is applied again. Since the longitudinal magnetization vector of the pre-saturated blood flow is very small and almost no magnetic resonance signal is generated, the blood flow appears as a black low signal, while the surrounding tissues are high signals, and a black-blood medical image can be formed.

[0049] The bright-blood medical image can be a medical image obtained by a medical scanning device using bright-blood technology. Bright-blood technology means that acquisition is performed in a fast spoiled GRE T1W1 sequence with a short TR. The stationary tissues within the imaging volume or slice are repeatedly excited and in a saturated state, with a very small magnetization vector, thus suppressing the stationary background tissues. The blood outside the imaging area is not saturated by the radiofrequency pulse. When the blood flows into the imaging volume or slice, it has a high signal, forming a good contrast with the stationary tissues, and a bright-blood medical image can be formed.

[0050] Specifically, the black-blood medical image and the bright-blood medical image corresponding to the cerebral blood vessels are as shown in Figure 3 Figure 3 ​Figure A in [the figure] shows a black-blood medical image, and Figure B shows a bright-blood medical image.

[0051] The black-blood medical image and the bright-blood medical image can be obtained by using a medical scanning device and stored in the memory of the terminal. When needed, the terminal directly obtains the black-blood medical image and the bright-blood medical image from the memory. This embodiment does not limit the specific method for obtaining the black-blood medical image and the bright-blood medical image, as long as its function can be realized.

[0052] Step 210: Perform vascular identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and perform registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image;

[0053] After the terminal obtains the black-blood medical image, performing vascular identification processing on it can obtain a black-blood vascular identification image. In other words, the terminal marks different types of vascular regions in the black-blood medical image in a preset manner, and a medical image with vascular markings, that is, the black-blood vascular identification image, can be obtained. The black-blood vascular identification image may include one or more types of vascular regions. Performing the marking in a preset manner may refer to marking different types of vascular regions in the black-blood medical image with different colors, and one color represents one vascular region.

[0054] After the terminal obtains the bright-blood medical image, performing vascular identification processing on it can obtain a bright-blood vascular identification image. That is to say, the terminal marks different types of vascular regions in the bright-blood medical image in a preset manner, and a medical image with vascular markings, that is, the bright-blood vascular identification image, can be obtained. Performing the marking in a preset manner may be to mark different types of vascular regions in the bright-blood medical image with different colors, and one color represents one vascular region. This embodiment does not limit the specific method for performing vascular identification processing on the black-blood medical image and the bright-blood medical image respectively, as long as its function can be realized.

[0055] After the terminal obtains the black-blood vascular identification image and the bright-blood vascular identification image, performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image can obtain a fused vascular identification image after the fusion of the black-blood vascular identification image and the bright-blood vascular identification image. Specifically, the terminal can use a rigid registration method to register the black-blood vascular identification image and the bright-blood vascular identification image, and the terminal can fuse the black-blood vascular identification image and the bright-blood vascular identification image according to the registration result to obtain a fused vascular identification image. This embodiment does not limit the specific method for registration and fusion, as long as its function can be realized.

[0056] In a specific embodiment, the black-blood vessel identification image, bright-blood vessel identification image, and fused vessel identification image are as Figure 4 shown, Figure 4 wherein, FIG. A represents the black-blood vessel identification image, FIG. B represents the bright-blood vessel identification image, and FIG. C represents the fused vessel identification image.

[0057] Step 220: Extract the segmented centerline of each blood vessel in the fused vessel identification image, and determine the centerline of the blood vessel in the black-blood medical image or bright-blood medical image according to the segmented centerline of each blood vessel.

[0058] Each blood vessel in the fused vessel identification image refers to each blood vessel region in the fused vessel identification image. The fused medical vessel identification image is obtained by registering and fusing the bright-blood vessel identification image and the black-blood vessel identification image. After the terminal obtains the fused vessel identification image, it extracts the segmented centerline of each blood vessel therein, that is, the centerline of each blood vessel region. The specific method for extracting the segmented centerline in this embodiment is not limited as long as its function can be realized.

[0059] In an optional embodiment, the terminal can extract the segmented centerline of each blood vessel from the fused vessel identification image through a skeletonization extraction method, or can also extract the segmented centerline of each blood vessel from the fused vessel identification image through an optimal path algorithm.

[0060] After the terminal obtains the segmented centerline of each blood vessel in the fused vessel identification image, it can determine the centerline of the blood vessel region in the black-blood medical image according to the segmented centerline, or can also determine the centerline of the blood vessel region in the bright-blood medical image according to the segmented centerline. The specific method for determining the centerline of the blood vessel in the black-blood medical image or bright-blood medical image according to the segmented centerline of each blood vessel in this embodiment is not limited as long as its function can be realized.

[0061] Both the bright-blood vessel identification image and the black-blood vessel identification image include markings of multiple blood vessel regions. Then the fused vessel identification image also includes markings of multiple blood vessel regions. Then the centerlines of the blood vessels in the finally determined black-blood medical image or bright-blood medical image also include markings of multiple blood vessel centerlines.

[0062] The method for determining the blood vessel centerline provided by the embodiment of the present application obtains black blood medical images and bright blood medical images; performs blood vessel identification processing on the black blood medical images and bright blood medical images respectively to obtain black blood vessel identification images and bright blood vessel identification images, and performs registration and fusion processing on the black blood vessel identification images and bright blood vessel identification images to obtain a fused blood vessel identification image; extracts the segmented centerlines of each blood vessel in the fused blood vessel identification image, and determines the centerline of the blood vessel in the black blood medical image or the bright blood medical image according to the segmented centerlines of each blood vessel. The method for determining the blood vessel centerline provided by this embodiment determines the centerline of the blood vessel in the black blood medical image or the bright blood medical image by extracting the segmented centerlines of each blood vessel in the fused blood vessel identification image. The fused blood vessel identification image is obtained by registering and fusing the black blood medical identification image and the bright blood vessel identification image. The fused medical image corresponding to multiple medical images contains the features corresponding to multiple medical images. Therefore, the segmented centerline can be determined more quickly and accurately through the fused medical image corresponding to multiple medical images (black blood medical images and bright blood medical images), thereby improving the accuracy and efficiency of determining the centerline of the blood vessel in each medical image (black blood medical image or bright blood medical image).

[0063] In one embodiment, a possible implementation manner for performing blood vessel identification processing on the black blood medical image and the bright blood medical image respectively to obtain black blood vessel identification images and bright blood vessel identification images, and performing registration and fusion processing on the black blood vessel identification images and the bright blood vessel identification images to obtain a fused blood vessel identification image includes the steps of:

[0064] Input the black blood medical image and the bright blood medical image into an image fusion model to obtain a fused blood vessel identification image.

[0065] After obtaining the black blood medical image and the bright blood medical image, the terminal inputs both of them into a pre-trained image fusion model, and the fused blood vessel identification image can be output through this image fusion model.

[0066] Specifically, the training process of the fused blood vessel identification image includes: obtaining black blood medical image samples and bright blood medical image samples; inputting the black blood medical image samples and the bright blood medical image samples into a neural network model for training to obtain a fused blood vessel identification image. The types of the black blood medical image samples are the same as those of the black blood medical images, and the types of the bright blood medical image samples are the same as those of the bright blood medical images. The descriptions of the black blood medical image samples and the bright blood medical image samples can refer to the specific descriptions of the black blood medical images and the bright blood medical images above, and will not be elaborated here.

[0067] In an alternative embodiment, the neural network model can be trained in a supervised manner. That is, by obtaining fused vascular label images, inputting both the black-blood medical image samples and the bright-blood medical image samples, as well as the fused vascular label images, into the neural network model for training, a fused vascular label image can be obtained.

[0068] In this embodiment, the fused vascular label image is obtained through a pre-trained image fusion model, which improves the efficiency of determining the fused vascular label image and thus the efficiency of determining the vascular centerline.

[0069] In one embodiment, as Figure 5 shown, a possible implementation of separately performing vascular labeling processing on black-blood medical images and bright-blood medical images to obtain black-blood vascular label images and bright-blood vascular label images includes the steps of:

[0070] Step 500: Input the black-blood medical image into the first labeling model to obtain a black-blood vascular label image.

[0071] After obtaining the black-blood medical image, the terminal inputs it into the pre-trained first labeling model to obtain a black-blood vascular label image. The first labeling model can be obtained by training a neural network model using black-blood medical image samples. The black-blood medical image samples are of the same type as the black-blood medical images.

[0072] Step 510: Input the bright-blood medical image into the second labeling model to obtain a bright-blood vascular label image.

[0073] After obtaining the bright-blood medical image, the terminal inputs it into the pre-trained first labeling model to obtain a bright-blood vascular label image. The second labeling model can be obtained by training a neural network model using bright-blood medical image samples. The bright-blood medical image samples are of the same type as the bright-blood medical images.

[0074] In this embodiment, the black-blood vascular label image is determined through the first labeling model, and the bright-blood vascular label image is determined through the second labeling model, which can improve the efficiency of determining the black-blood vascular label image and the bright-blood vascular label image, and thus the efficiency of the fused vascular label image.

[0075] In one embodiment, before performing registration and fusion processing on the black-blood vascular label image and the bright-blood vascular label image to obtain a fused vascular label image, the steps for determining the vascular centerline further include:

[0076] According to the vascular architecture, remove the interference regions in the black-blood vascular label image and the bright-blood vascular label image respectively.

[0077] Before the terminal performs registration and fusion processing on the black-blood vessel identification image and the bright-blood vessel identification image, it can remove the interference regions in the black-blood vessel identification image according to the blood vessel structure in the blood vessel region of the black-blood vessel identification image, and at the same time, remove the interference regions in the black-blood vessel identification image according to the blood vessel structure in the blood vessel region of the bright-blood vessel identification image. That is to say, the terminal can remove the regions (interference regions) in the black-blood vessel identification image and the bright-blood vessel identification image that do not belong to the blood vessel structure. This embodiment does not limit the specific method for removing the interference regions, as long as its function can be achieved.

[0078] In an optional embodiment, the terminal can register the blood vessel structure with the blood vessel regions marked in the black-blood vessel identification image and the blood vessel regions marked in the bright-blood vessel identification image, and remove the regions that do not belong to the blood vessel structure.

[0079] In this embodiment, performing interference region removal processing on the black-blood vessel identification image and the bright-blood vessel identification image before registration and fusion can ensure the accuracy of the registration and fusion of the black-blood vessel identification image and the bright-blood vessel identification image, thereby improving the accuracy of determining the blood vessel centerline.

[0080] In one embodiment, as Figure 6 shown, it relates to a possible implementation manner of determining the centerline of blood vessels in a black-blood medical image or a bright-blood medical image according to the segmented centerlines of each segment of blood vessels. The steps include:

[0081] Step 600: Based on the black-blood medical image or the bright-blood medical image, connect and extend the segmented centerlines of each segment of blood vessels to obtain an initial centerline.

[0082] The segmented centerlines of each segment of blood vessels are extracted from the fused blood vessel identification image, and the fused blood vessel identification image is obtained by registering and fusing the black-blood identification image and the bright-blood identification image. Then, the segmented centerlines of each segment of blood vessels extracted from the fused blood vessel identification image are also the segmented centerlines of each segment of blood vessels in the black-blood medical image or the bright-blood medical image.

[0083] When the terminal needs to determine the initial centerline of the black-blood medical image, by connecting and extending the segmented centerlines of each segment of blood vessels obtained based on the black-blood medical image, the initial centerline can be obtained. In other words, the terminal connects the segmented centerlines of multiple segments of blood vessels corresponding to the black-blood medical image and extends the connected centerline, then the initial centerline corresponding to the black-blood medical image can be obtained. When the terminal needs to determine the initial centerline of the bright-blood medical image, the initial centerline corresponding to the bright-blood medical image can be obtained using the same method as for determining the initial centerline corresponding to the black-blood medical image.

[0084] Step 610: Determine the centerline of the blood vessels in the black-blood medical image or bright-blood medical image based on the black-blood vessel identification image or bright-blood vessel identification image, and the initial centerline.

[0085] When the terminal determines the centerline of the black-blood medical image, based on the marked blood vessel regions in the obtained black-blood vessel identification image and the initial centerline corresponding to the black-blood medical image, the centerline of the blood vessels in the black-blood medical image can be determined. Specifically, for each blood vessel region in the black-blood vessel identification image, a mark is made, and then the centerline of each blood vessel in the black-blood medical image determined according to the black-blood vessel identification image and the initial centerline is also marked. When the terminal determines the centerline of the bright-blood medical image, the same method as that for determining the centerline of the blood vessels in the bright-blood medical image can be used, and the initial centerline corresponding to the bright-blood medical image can be obtained.

[0086] The method provided in this embodiment can determine the segmented centerlines of each blood vessel determined by fusing the blood vessel identification images, which can not only determine the centerline of the blood vessels in the black-blood medical image, but also determine the centerline of the blood vessels in the bright-blood medical image, and has high practicability. Moreover, the method provided in this embodiment is simple, fast, and easy to implement.

[0087] In one embodiment, as Figure 7 shown, a possible implementation manner of determining the centerline of the blood vessels in the black-blood medical image or bright-blood medical image according to the black-blood vessel identification image or bright-blood vessel identification image, and the initial centerline includes the steps of:

[0088] Step 700: Determine the bifurcation points on the initial centerline according to the black-blood vessel identification image or bright-blood vessel identification image, and the initial centerline.

[0089] The bifurcation points of the initial centerline refer to the connection points between each segment of the centerline of the blood vessels in the initial centerline. The initial centerline is the centerline obtained by connecting the segmented centerlines. For the black-blood vessel identification image, the terminal can determine the bifurcation points on the initial centerline corresponding to the black-blood medical image according to the marks of each blood vessel in the black-blood vessel identification image and the initial centerline corresponding to the black-blood medical image. Similarly, for the bright-blood vessel identification image, the terminal can determine the bifurcation points on the initial centerline corresponding to the bright-blood medical image according to the marks of each blood vessel in the bright-blood vessel identification image. This embodiment does not limit the specific method for determining the bifurcation points, as long as its function can be realized.

[0090] In an optional embodiment, the terminal can determine the position of the first bifurcation point in the black-blood vessel identification and the position of the second bifurcation point in the initial centerline; determine whether the position of the second bifurcation point is within the preset range of the position of the second bifurcation point, and if so, determine the position of the second bifurcation point as the finally determined bifurcation point.

[0091] Step 710: Determine the centerline of the blood vessels in the black blood medical image or bright blood medical image according to the initial centerline and the bifurcation points on the initial centerline.

[0092] After the terminal obtains the bifurcation points on the initial centerline corresponding to the black blood medical image, it can determine the complete centerline of the blood vessels in the black blood medical image according to the bifurcation points and the initial centerline corresponding to the black blood medical image. The complete centerlines of the blood vessels in the black blood medical image have different markings for different blood vessels.

[0093] After the terminal obtains the bifurcation points on the initial centerline corresponding to the bright blood medical image, it can determine the complete centerline of the blood vessels in the bright blood medical image according to the bifurcation points and the initial centerline corresponding to the black blood medical image. The complete centerlines of the blood vessels in the bright blood medical image have different markings for different blood vessels.

[0094] The method for determining the centerline of blood vessels provided in this embodiment is easy to implement and has strong practicability.

[0095] In one embodiment, as Figure 8 shown, it involves connecting and extending the segmented centerlines of each segment of blood vessels based on the black blood medical image or bright blood medical image to obtain the initial centerline, including:

[0096] Step 800: Connect the segmented centerlines of each segment of blood vessels based on the black blood medical image or bright blood medical image to obtain the connected centerline.

[0097] Based on the black blood medical image, the terminal connects all the obtained segmented centerlines to obtain the connected centerline corresponding to the black blood medical image. Based on the bright blood medical image, the terminal connects all the obtained segmented centerlines to obtain the connected centerline corresponding to the bright blood medical image. This embodiment does not limit the method for connecting the segmented centerlines of each segment of blood vessels, as long as its function can be achieved.

[0098] Step 810: Extend the connected centerline according to a preset length threshold to obtain the initial centerline.

[0099] The preset length threshold can be set by the staff according to the actual application. After the terminal obtains the connected centerline, it extends it according to the preset length threshold to obtain the initial centerline. In other words, the connected centerline obtained by the terminal may only be a part of the initial centerline, and the complete initial centerline can be obtained by connecting the connected centerline.

[0100] In this embodiment, by extending the connection centerline, it is possible to avoid the connection centerline not being a complete centerline of the blood vessel corresponding to the black blood medical image or the bright blood medical image. In addition, the method for determining the initial centerline provided in this embodiment is simple, understandable, and easy to implement.

[0101] In a specific embodiment, Figure 9 As shown, Figure 9 Figure A in the figure represents the segmented centerline of each blood vessel extracted from the fused blood vessel identification image, Figure B is the connection centerline, Figure C is the centerline after the connection centerline is extended (initial centerline), and Figure D is the centerline of the blood vessel in the black blood medical image or the bright blood medical image.

[0102] In an optional embodiment, when extending the connection center line, the terminal can directly extend the connection center line to the boundary of the black blood medical image or the boundary of the bright blood medical image to obtain the initial center line corresponding to the black blood medical image or the initial center line corresponding to the bright blood medical image.

[0103] In one embodiment, after obtaining the center line of the blood vessel in the black blood medical image or the bright blood medical image, the terminal can obtain multiple blood vessel cross-sectional images corresponding to multiple points on the center line; for each blood vessel cross-sectional image, the blood vessel cross-sectional image is segmented, and the contours of the lumen and the wall in the blood vessel cross-sectional image can be obtained according to the segmentation result; by analyzing the contours of the lumen and the wall in the blood vessel cross-sectional image, it is possible to detect whether there is a plaque in the blood vessel in the black blood medical image or the bright blood medical image. In addition, when there is a plaque in the blood vessel in the black blood medical image or the bright blood medical image, it can be segmented to obtain the plaque area. In addition, the plaque area can be analyzed to determine parameters such as the composition, area, and volume of the plaque.

[0104] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0105] Based on the same inventive concept, an embodiment of the present application further provides a blood vessel centerline determination device for implementing the blood vessel centerline determination method involved above. The implementation solutions provided by this device for solving problems are similar to those recorded in the above method. Therefore, the specific limitations in one or more embodiments of the blood vessel centerline determination device provided below can refer to the limitations on the blood vessel centerline determination method in the above text, and will not be elaborated here.

[0106] In one embodiment, as Figure 10 shown, a blood vessel centerline determination device 10 is provided. This device includes an acquisition module 11, a fusion module 12, and a determination module 13. Among them,

[0107] The acquisition module 11 is used to acquire black blood medical images and bright blood medical images.

[0108] The fusion module 12 is used to perform blood vessel identification processing on the black blood medical image and the bright blood medical image respectively to obtain a black blood vessel identification image and a bright blood vessel identification image, and perform registration and fusion processing on the black blood vessel identification image and the bright blood vessel identification image to obtain a fused blood vessel identification image.

[0109] The determination module 13 is used to extract the segmented centerlines of each segment of blood vessels in the fused blood vessel identification image, and determine the centerline of the blood vessels in the black blood medical image or the bright blood medical image according to the segmented centerlines of each segment of blood vessels.

[0110] In one embodiment, the fusion module 12 is specifically used to input the black blood medical image and the bright blood medical image into an image fusion model to obtain a fused blood vessel identification image.

[0111] In one embodiment, the fusion module 12 includes a first determination unit and a second determination unit. The first determination unit is used to input the black blood medical image into a first identification model to obtain a black blood vessel identification image; the second determination unit is used to input the bright blood medical image into a second identification model to obtain a bright blood vessel identification image.

[0112] In one embodiment, the blood vessel centerline determination device 10 further includes a removal module. The removal module is used to remove the interference regions in the black blood vessel identification image and the bright blood vessel identification image respectively according to the blood vessel architecture.

[0113] In one embodiment, the determination module 13 includes a processing unit and a third determination unit. The processing unit is used to connect and extend the segmented centerlines of each segment of blood vessels based on the black blood medical image or the bright blood medical image to obtain an initial centerline; the third determination unit is used to determine the centerline of the blood vessels in the black blood medical image or the bright blood medical image according to the black blood vessel identification image or the bright blood vessel identification image, and the initial centerline.

[0114] In one embodiment, the third determination unit is specifically configured to determine a bifurcation point on the initial centerline according to the black-blood vessel identification image or the bright-blood vessel identification image, and the initial centerline; and determine the centerline of the blood vessel in the black-blood medical image or the bright-blood medical image according to the initial centerline and the bifurcation point on the initial centerline.

[0115] In one embodiment, the processing unit is specifically configured to connect the segmented centerlines of each segment of the blood vessel based on the black-blood medical image or the bright-blood medical image to obtain a connected centerline; and perform an extension process on the connected centerline according to a preset length threshold to obtain an initial centerline.

[0116] Each module in the above-mentioned blood vessel centerline determination device 10 can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above-mentioned modules.

[0117] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 11 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for determining a blood vessel centerline. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0118] Those skilled in the art can understand that Figure 11 the structure shown in

[0119] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0120] Obtain black-blood medical images and bright-blood medical images;

[0121] Perform vascular identification processing on the black-blood medical images and the bright-blood medical images respectively to obtain black-blood vascular identification images and bright-blood vascular identification images, and perform registration and fusion processing on the black-blood vascular identification images and the bright-blood vascular identification images to obtain a fused vascular identification image;

[0122] Extract the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the segmented centerlines of each segment of blood vessels.

[0123] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Input the black-blood medical images and the bright-blood medical images into an image fusion model to obtain a fused vascular identification image.

[0124] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Input the black-blood medical images into a first identification model to obtain black-blood vascular identification images; Input the bright-blood medical images into a second identification model to obtain bright-blood vascular identification images.

[0125] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Remove the interference regions in the black-blood vascular identification images and the bright-blood vascular identification images respectively according to the vascular architecture.

[0126] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Based on the black-blood medical images or the bright-blood medical images, connect and extend the segmented centerlines of each segment of blood vessels to obtain an initial centerline; Determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the black-blood vascular identification images or the bright-blood vascular identification images, and the initial centerline.

[0127] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Determine the bifurcation points on the initial centerline according to the black-blood vascular identification images or the bright-blood vascular identification images, and the initial centerline; Determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the initial centerline and the bifurcation points on the initial centerline.

[0128] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Based on the black-blood medical images or the bright-blood medical images, connect the segmented centerlines of each segment of blood vessels to obtain a connected centerline; Extend the connected centerline according to a preset length threshold to obtain an initial centerline.

[0129] 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 following steps are implemented:

[0130] Obtain black-blood medical images and bright-blood medical images;

[0131] Perform vascular identification processing on the black-blood medical images and the bright-blood medical images respectively to obtain black-blood vascular identification images and bright-blood vascular identification images, and perform registration and fusion processing on the black-blood vascular identification images and the bright-blood vascular identification images to obtain a fused vascular identification image;

[0132] Extract the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the segmented centerlines of each segment of blood vessels.

[0133] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Input the black-blood medical images and the bright-blood medical images into an image fusion model to obtain a fused vascular identification image.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Input the black-blood medical images into a first identification model to obtain black-blood vascular identification images; Input the bright-blood medical images into a second identification model to obtain bright-blood vascular identification images.

[0135] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Remove the interference regions in the black-blood vascular identification images and the bright-blood vascular identification images respectively according to the vascular architecture.

[0136] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Based on the black-blood medical images or the bright-blood medical images, connect and extend the segmented centerlines of each segment of blood vessels to obtain an initial centerline; Determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the black-blood vascular identification images or the bright-blood vascular identification images, and the initial centerline.

[0137] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Determine the bifurcation points on the initial centerline according to the black-blood vascular identification images or the bright-blood vascular identification images, and the initial centerline; Determine the centerlines of the blood vessels in the black-blood medical images or the bright-blood medical images according to the initial centerline and the bifurcation points on the initial centerline.

[0138] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: Connect the segmented centerlines of each segment of blood vessels based on the black-blood medical images or the bright-blood medical images to obtain a connected centerline; Extend the connected centerline according to a preset length threshold to obtain an initial centerline.

[0139] 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 completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0140] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0141] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for determining the centerline of a blood vessel, characterized in that, Including: Obtaining a black-blood medical image and a bright-blood medical image; Performing vascular identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image; Extracting the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of each segment of blood vessels.

2. The method for determining the blood vessel centerline according to claim 1, characterized in that, The performing vascular identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image includes: Inputting the black-blood medical image and the bright-blood medical image into an image fusion model to obtain the fused vascular identification image.

3. The method for determining the blood vessel centerline according to claim 1, wherein The performing vascular identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image includes: Inputting the black-blood medical image into a first identification model to obtain the black-blood vascular identification image; Inputting the bright-blood medical image into a second identification model to obtain the bright-blood vascular identification image.

4. The method for determining the vascular centerline according to claim 3, wherein, Before the performing registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image, the method further includes: Removing the interference regions in the black-blood vascular identification image and the bright-blood vascular identification image respectively according to the vascular architecture.

5. The method for determining the vascular centerline according to claim 3, wherein The determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of each segment of blood vessels includes: Processing the segmented centerlines of each segment of blood vessels based on the black-blood medical image or the bright-blood medical image to obtain an initial centerline; Determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline.

6. The method for determining the blood vessel centerline according to claim 5, wherein, The determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline includes: Determining the bifurcation points on the initial centerline according to the black-blood vascular identification image or the bright-blood vascular identification image, and the initial centerline; Determining the centerline of the blood vessels in the black-blood medical image or the bright-blood medical image according to the initial centerline and the bifurcation points on the initial centerline.

7. The method for determining the blood vessel centerline according to claim 5, characterized in that The processing the segmented centerlines of each segment of blood vessels based on the black-blood medical image or the bright-blood medical image to obtain an initial centerline includes: Connecting the segmented centerlines of each segment of blood vessels based on the black-blood medical image or the bright-blood medical image to obtain a connected centerline; Performing an extension process on the connected centerline according to a preset length threshold to obtain the initial centerline.

8. A device for determining the centerline of a blood vessel, characterized in that, Including: An obtaining module, configured to obtain a black-blood medical image and a bright-blood medical image; A fusion module, configured to perform vascular identification processing on the black-blood medical image and the bright-blood medical image respectively to obtain a black-blood vascular identification image and a bright-blood vascular identification image, and perform registration and fusion processing on the black-blood vascular identification image and the bright-blood vascular identification image to obtain a fused vascular identification image; A determination module, configured to extract the segmented centerlines of each segment of blood vessels in the fused vascular identification image, and determine the centerlines of the blood vessels in the black-blood medical image or the bright-blood medical image according to the segmented centerlines of each segment of blood vessels.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images