Medical equipment, blood vessel and internal plaque three-dimensional reconstruction method and device
Through the three-dimensional reconstruction method of blood vessels and internal plaques, the problem of unclear judgment of carotid plaques in ultrasound examinations was solved, and a clear three-dimensional model was generated, which improved the accuracy of surgical evaluation and patient medical experience.
Patent Information
- Application Number
- CN202111425153.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-27
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2041-11-27
AI Technical Summary
The existing ultrasound examination is not clear enough in the judgment of carotid plaques, which affects surgical evaluation and decision-making, and the operation is at risk and cannot accurately reflect the overall picture and size of the plaque.
The three-dimensional reconstruction method of blood vessels and internal plaques is used to obtain image information of the radial section of the blood vessels, and the contour information is obtained using the blood vessel and plaque segmentation model, and the scanning trajectory is combined for screening and three-dimensional reconstruction to generate a clear three-dimensional model of blood vessels and plaques.
It realizes the clear and intuitive three-dimensional structural display of blood vessels and plaques, improves the accuracy of display of carotid plaques, facilitates doctors to judge and measure, and reduces the risk of unnecessary or unnecessary surgery.
Smart Images

Figure CN114170378B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical ultrasound technology, and in particular to a medical device, a method and a device for three-dimensional reconstruction of blood vessels and internal plaques. Background Art
[0002] Currently, ultrasound examination is generally used when scanning the carotid artery. The echo condition is used to determine whether it is a stable plaque or an unstable plaque. If it is low echo or no echo, it may be an unstable plaque.
[0003] However, the judgment result is not clear and can only give a rough situation. It also needs to be combined with blood lipid tests, such as detecting the parameter range of low-density lipoprotein. Even so, it still cannot clearly reflect the overall picture of the plaque, and the retrieval process is cumbersome. In addition, general carotid plaques do not require surgery, but severe carotid plaques require evaluation before determining whether surgery is necessary. The unclear ultrasound examination also affects the doctor's assessment of whether surgery is necessary. Moreover, there are risks in current surgery for carotid plaques, which is a problem for patients who do not need surgery or who do not have surgery when they need it. Making the display of carotid plaques clearer and more intuitive will help solve these problems. Summary of the invention
[0004] In order to solve the problem that the plaques in blood vessels are not presented clearly and intuitively in the prior art, the purpose of the present invention is to provide a method and device for three-dimensional reconstruction of blood vessels and internal plaques.
[0005] To achieve the above-mentioned purpose, an embodiment of the present invention provides a method for three-dimensional reconstruction of blood vessels and internal plaques, comprising the steps of:
[0006] Acquire a set of blood vessel image information of radial sections of the blood vessel, wherein the plurality of blood vessel image information are arranged in sequence along a scanning track;
[0007] Passing the blood vessel image information through a blood vessel segmentation model to obtain blood vessel contour information corresponding to each blood vessel image information;
[0008] Filtering the blood vessel contour information based on the scanning trajectory;
[0009] Passing at least part of the blood vessel image information through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information;
[0010] Filtering the plaque contour information based on the positional relationship between the plaque and the blood vessel contour;
[0011] Taking a set of the blood vessel contour information along the scanning direction as input, three-dimensional reconstruction is performed through surface rendering to generate a three-dimensional model of the blood vessel;
[0012] The filtered contour information of each plaque is traversed through the three-dimensional blood vessel model to generate a three-dimensional blood vessel model with plaques.
[0013] As a further improvement of the present invention, the step of "obtaining a set of vascular image information of radial sections of the vascular" includes:
[0014] Acquire a set of original images and length and depth information of the three-dimensional model arranged in sequence along the scanning trajectory;
[0015] The original image is resampled to obtain blood vessel image information, where the blood vessel image information is a set of grayscale images.
[0016] As a further improvement of the present invention, the step of "obtaining a set of original images and length and depth information of the three-dimensional model arranged in sequence along the scanning trajectory" includes:
[0017] Acquire scanning parameter information, wherein the scanning parameter information includes scanning distance information and scanning depth information;
[0018] The length information and depth information of the three-dimensional model are calculated according to the scanning distance information, the scanning depth information and the number of original images.
[0019] As a further improvement of the present invention, the step of "re-sampling the original image to obtain vascular image information" includes:
[0020] Graying and compressing the original image into a resampled image, wherein the original image is a set of transverse scanning color images perpendicular to the extension direction of the blood vessel;
[0021] Taking the resampled image as a data source, a set of blood vessel image information is generated through a linear interpolation algorithm according to the length information and the depth information.
[0022] As a further improvement of the present invention, the step of "obtaining blood vessel contour information corresponding to each blood vessel image information through a blood vessel segmentation model" includes:
[0023] The blood vessel image information is detected by a blood vessel segmentation model, pixels whose grayscale values of the blood vessel image information are greater than or equal to a preset blood vessel confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset blood vessel confidence value are replaced with a second value, to generate blood vessel contour information.
[0024] As a further improvement of the present invention, the step of "screening the blood vessel contour information based on the scanning trajectory" includes:
[0025] A region on the blood vessel contour information replaced with the first value is used as a circumscribed rectangle, and the center point of the circumscribed rectangle is determined. Further, a plurality of center points of the blood vessel contour information sequentially arranged along the scanning trajectory are obtained. The blood vessel extension trajectory is fitted according to a least squares algorithm. If a deviation value between a center point of a certain blood vessel contour information and the blood vessel extension trajectory exceeds a preset blood vessel deviation value, the blood vessel contour information is screened out.
[0026] As a further improvement of the present invention, the step of "passing at least part of the vascular image information through a plaque segmentation model to obtain plaque contour information corresponding to each vascular image information" includes:
[0027] The blood vessel image information corresponding to the filtered blood vessel contour information is passed through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information.
[0028] As a further improvement of the present invention, the step of "using the filtered blood vessel image information corresponding to the blood vessel contour information through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information" includes:
[0029] The vascular image information corresponding to the filtered vascular contour information is detected through a plaque segmentation model, and pixels of the vascular image information whose grayscale values are greater than or equal to a preset plaque confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset plaque confidence value are replaced with a second value to generate plaque contour information.
[0030] As a further improvement of the present invention, the step of "screening the plaque contour information based on the positional relationship between the plaque and the blood vessel contour" includes:
[0031] If the degree of deviation between the area of the first value on a piece of plaque contour information and the area of the first value in the corresponding blood vessel contour information is greater than a preset plaque deviation value, the plaque contour information is screened out.
[0032] As a further improvement of the present invention, the step of "taking a set of the blood vessel contour information along the scanning direction as input, performing three-dimensional reconstruction by surface rendering, and generating a three-dimensional model of the blood vessel" includes:
[0033] Determine a first isosurface based on the boundary contour of the first value and the second value in the blood vessel contour information, and generate a closed grayscale isosurface by a marching cube algorithm, wherein the grayscale isosurface is a three-dimensional model of the blood vessel;
[0034] The three-dimensional model of the blood vessel is generated in a first color.
[0035] As a further improvement of the present invention, the step of "traversing the three-dimensional blood vessel model with each of the filtered plaque contour information to generate a three-dimensional blood vessel model with plaques" includes:
[0036] A second isosurface is determined based on the boundary contour of the first value and the second value in the plaque contour information along the scanning trajectory, the second isosurface is traversed through the three-dimensional model of the blood vessel, the area where the second isosurface is located is replaced with a second color different from the first color, and a three-dimensional model of the blood vessel with plaque is generated.
[0037] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a device for three-dimensional reconstruction of blood vessels and internal plaques, comprising:
[0038] An acquisition module, used for acquiring a set of vascular image information of radial sections of the vascular, wherein the plurality of vascular image information are arranged in sequence along a scanning track;
[0039] a blood vessel contour recognition module, used to obtain blood vessel contour information corresponding to each blood vessel image information by passing the blood vessel image information through a blood vessel segmentation model, and to filter the blood vessel contour information based on a scanning trajectory;
[0040] a plaque recognition module, used to obtain plaque contour information corresponding to each vascular image information by passing at least part of the vascular image information through a plaque segmentation model, and to filter the plaque contour information based on the positional relationship between the plaque and the vascular contour;
[0041] A blood vessel modeling module, used to take a set of blood vessel contour information along the scanning direction as input, perform three-dimensional reconstruction through surface rendering, and generate a three-dimensional model of the blood vessel;
[0042] The plaque modeling module is used to traverse the three-dimensional blood vessel model by passing the contour information of each of the screened plaques to generate a three-dimensional blood vessel model with plaques.
[0043] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides an electronic device, characterized in that it includes:
[0044] A storage module storing a computer program;
[0045] The processing module can implement the steps in the above-mentioned method for three-dimensional reconstruction of blood vessels and internal plaques when executing the computer program.
[0046] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a readable storage medium storing a computer program, which, when executed by a processing module, can implement the steps in the above-mentioned method for three-dimensional reconstruction of blood vessels and internal plaques.
[0047] Compared with the prior art, the present invention has the following beneficial effects: the method and device can clearly draw the three-dimensional structure of blood vessels and internal plaques, and obtain multiple longitudinal sections by ultrasound, which is consistent with the existing scanning method and is particularly suitable for scanning the carotid artery. It can clearly display the bifurcation of the internal carotid artery and the external carotid artery, making it easier to find the location of the carotid sinus. Moreover, because the presentation is more direct, it is also easier to more accurately measure the specific size of the plaque, which helps doctors make more accurate judgments and improves the patient's medical experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 is a flow chart of a method for three-dimensional reconstruction of blood vessels and internal plaques according to an embodiment of the present invention;
[0049] Figure 2 is a schematic diagram of an original image of a radial section of a blood vessel according to an embodiment of the present invention;
[0050] Figure 3 is a schematic diagram of blood vessel contour information according to an embodiment of the present invention;
[0051] Figure 4 is a schematic diagram of plaque contour information according to an embodiment of the present invention;
[0052] Figure 5 is a schematic diagram of a three-dimensional model of a blood vessel with plaque according to an embodiment of the present invention;
[0053] Figure 6 FIG. 4 is a schematic diagram of modules of a 3D reconstruction device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0054] The present invention will be described in detail below in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.
[0055] It should be understood that the terms used herein, such as "upper", "above", "lower", "below", etc., indicating spatial relative positions, are used for the purpose of convenience to describe the relationship of one unit or feature relative to another unit or feature as shown in the drawings. The terms of spatial relative positions may be intended to include different orientations of the device in use or operation other than the orientation shown in the drawings.
[0056] An embodiment of the present invention provides a method and apparatus for three-dimensional reconstruction of medical equipment, blood vessels, and internal plaques. The method can be used to clearly and intuitively draw a three-dimensional model of the blood vessel and present the specific structure of the plaque on the blood vessel, making it easier for doctors and patients to more accurately understand the blood vessels, especially the condition of the carotid artery plaque.
[0057] Figure 1 A three-dimensional reconstruction method of blood vessels and internal plaques is provided in one embodiment of the present application. The three-dimensional reconstruction method is based on a longitudinal cross-sectional image obtained by ultrasound scanning as a data source. This embodiment can be illustrated by taking scanning of the carotid artery as an example.
[0058] Although the present application provides method operation steps as described in the following implementation manner or flowchart, based on routine or no creative labor, in the steps of the method where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the implementation manner of the present application.
[0059] Specifically, the steps include:
[0060] Step 101: acquiring a set of vascular image information of radial sections of the vascular, wherein the plurality of vascular image information are arranged in sequence along a scanning track;
[0061] Step 102: applying the blood vessel image information to a blood vessel segmentation model to obtain blood vessel contour information corresponding to each blood vessel image information;
[0062] Step 103: filtering the blood vessel contour information based on the scanning trajectory;
[0063] Step 104: passing at least part of the blood vessel image information through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information;
[0064] Step 105: filtering the plaque contour information based on the positional relationship between the plaque and the blood vessel contour;
[0065] Step 106: taking a set of the blood vessel contour information along the scanning direction as input, performing three-dimensional reconstruction through surface rendering to generate a three-dimensional model of the blood vessel;
[0066] Step 107: traverse the three-dimensional blood vessel model with each of the filtered plaque contour information to generate a three-dimensional blood vessel model with plaques.
[0067] For step 101, in an implementation of the present invention, a set of original images and scanning parameter information arranged in sequence along the scanning trajectory can be first obtained, wherein the original image is a plurality of continuous transverse scanning ultrasound images perpendicular to the direction of the carotid artery, and the scanning parameter information includes scanning distance information and scanning depth information. The original image can be a 32-bit RGBA color image or a grayscale image. Figure 2The grayscale image is input as the original image. The scanned ultrasound image completely covers the patient's carotid artery, including the aorta, bifurcation, internal carotid artery and external carotid artery, so that the full picture of the patient's carotid artery is fully presented in the three-dimensional model after three-dimensional reconstruction, especially showing the plaque situation in the entire carotid artery.
[0068] After the original image is obtained, the original image is resampled to obtain blood vessel image information, which is a set of grayscale images. The blood vessel image can also be compressed to a certain extent to reduce the amount of calculation.
[0069] The length information and depth information of the three-dimensional model are calculated according to the scanning distance information, the scanning depth information and the number of original images.
[0070] Then, the resampled image is used as a data source, and a set of blood vessel image information is generated through a linear interpolation algorithm according to the length information and depth information. The data volume of the original image is supplemented by linear interpolation, and the generated three-dimensional model is also made smoother.
[0071] For step 102, the blood vessel image information is detected by a blood vessel segmentation model, pixels whose grayscale values of the blood vessel image information are greater than or equal to a preset blood vessel confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset blood vessel confidence value are replaced with a second value, to generate blood vessel contour information.
[0072] Vascular contour information such as Figure 3 As shown, based on vascular deep learning, it can be judged Figure 2 The possibility that each pixel is a blood vessel or in a blood vessel is calculated, and then the contour of the blood vessel is determined. The first value can be 255 and the second value can be 0, so that the blood vessel is distinguished from the original image.
[0073] in addition, Figure 3 The blood vessel may be the common carotid artery. If the image is above the bifurcation position, it may include the internal carotid artery and the external carotid artery. The cross-section showing the gradual transition from one blood vessel to two blood vessels is shown at the Y-shaped bifurcation position, so that the Y-shaped bifurcation can be clearly reflected in the final three-dimensional model, making it easier for doctors to find the bifurcation position.
[0074] For step 103, the area replaced with the first value on the vascular contour information is used as a circumscribed rectangle, and the center point of the circumscribed rectangle is determined, and the center points of the multiple vascular contour information arranged in sequence along the scanning trajectory are further obtained. The vascular extension trajectory is fitted according to the least squares algorithm. If the deviation value between the center point on a certain image and the vascular extension trajectory exceeds the preset vascular deviation value, the image is screened out. Through the least squares algorithm, a curve can be fitted for multiple center points in space, and the fitted curve is the extension direction of the blood vessel. Then, the image where the center point is too discrete is removed, and the image consistent with the direction of blood vessel extension is retained, so as to avoid excessive shaking of the doctor's hand during ultrasound scanning, or distortion of the detection of the vascular contour model, resulting in distortion of the three-dimensional model.
[0075] In addition, when there are multiple connected areas in the image, the number of blood vessels on the image is determined according to the location of the image. If the number of connected areas that appear is greater than the number of blood vessels, the area of the circumscribed rectangle is determined for the multiple connected areas, and the connected areas with smaller areas are excluded. For example, there is only the common carotid artery in the image, but there are three connected areas. Only the area with the largest area is retained as the first value, and the pixels of the remaining two connected areas with smaller areas are replaced with the second value. If there are internal carotid arteries and external carotid arteries in the image, but there are five connected areas, only the two areas with larger areas are retained as the first value, and the pixels of other connected areas with smaller areas than the two largest areas are replaced with the second value.
[0076] For step 104, at least part of the vascular image information may be all of the vascular image information that passes through the plaque segmentation model, or part of it, specifically, the vascular image information corresponding to the vascular contour information screened in step 103, which can reduce the amount of calculation.
[0077] The vascular image information corresponding to the filtered vascular contour information is detected through a plaque segmentation model, and pixels of the vascular image information whose grayscale values are greater than or equal to a preset plaque confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset plaque confidence value are replaced with a second value to generate plaque contour information.
[0078] Plaque contour information such as Figure 4 As shown, based on the deep learning of patches, we can judge Figure 2 The probability that each pixel point is a plaque is calculated, and then the outline of the plaque is determined. The first value can be 255 and the second value can be 0, so as to distinguish the plaque from the original image.
[0079] For step 105, if the deviation between the area with the first value on the plaque contour information and the area with the first value in the corresponding blood vessel contour information is greater than a preset plaque deviation value, the image is screened out.
[0080] Theoretically, the plaque determined in step 105 should be completely within the blood vessel determined in step 103. Figure 3 and Figure 4 For example, when the plaque is completely inside the blood vessel, the judgment of the plaque is reliable; when the plaque is completely outside the blood vessel, there is a problem with the judgment and the image is removed; when the plaque is not completely inside the blood vessel, the judgment is made according to the preset plaque deviation value. According to the required accuracy, the preset plaque deviation value is set to different sizes to adjust the precision of the judgment of plaques of different sizes.
[0081] For step 106, surface drawing can use a variety of algorithms, such as the marching cube algorithm, to determine the first isosurface based on the boundary contour of the first value and the second value in the blood vessel contour information, and then generate a closed grayscale isosurface through the marching cube algorithm, and the grayscale isosurface is the three-dimensional model of the blood vessel.
[0082] The three-dimensional model of the blood vessel is generated in a first color, which may be red.
[0083] For step 107, a second isosurface is determined based on the boundary contour of the first value and the second value in the plaque contour information in sequence along the scanning trajectory, and the second isosurface is traversed over the three-dimensional blood vessel model, and the area where the second isosurface is located is replaced with a second color different from the first color, and the second color can be yellow or black; a three-dimensional blood vessel model with plaque is generated, such as Figure 5 As shown, the plaque can also be generated into a continuous and complete closed shape through the algorithm of moving cubes, and the color of the position of the plaque in the blood vessel is replaced, and finally a three-dimensional model of the blood vessel with the plaque is presented.
[0084] The method and device can clearly draw the three-dimensional structure of blood vessels and internal plaques, and obtain multiple longitudinal sections by ultrasound, which is consistent with the existing scanning method. It is particularly suitable for scanning the carotid artery and can clearly show the bifurcation of the internal carotid artery and the external carotid artery, making it easier to find the location of the carotid sinus. Because the presentation is more direct, it is also easier to more accurately measure the specific size of the plaque, allowing doctors to make more accurate judgments and improving the patient's medical experience.
[0085] In an implementation mode of the present invention, after obtaining a three-dimensional model of a blood vessel with plaques, the size and hardness of the blood vessel can be further conveniently calculated, so as to provide doctors with more specific and accurate data.
[0086] The width and height of the plaque can be obtained by calculating the minimum circumscribed rectangle of the plaque outline. The stenosis rate of the plaque can also be calculated by the area method, calculating the ratio of the area of the plaque outline to the area of the blood vessel outline. The hardness of the plaque can also be calculated according to the proportion of pixel points within the plaque outline whose brightness is greater than a certain threshold.
[0087] like Figure 6 As shown, in one embodiment, a 3D reconstruction device for blood vessels and internal plaques is provided. The 3D reconstruction device can be integrated in a medical device or a server, and specifically can include an acquisition module, a blood vessel contour recognition module, a plaque recognition module, a blood vessel modeling module, and a plaque modeling module. The specific functions of each module are as follows:
[0088] An acquisition module, used for acquiring a set of vascular image information of radial sections of the vascular, wherein the plurality of vascular image information are arranged in sequence along a scanning track;
[0089] a blood vessel contour recognition module, used to obtain blood vessel contour information corresponding to each blood vessel image information by passing the blood vessel image information through a blood vessel segmentation model, and to filter the blood vessel contour information based on a scanning trajectory;
[0090] a plaque recognition module, used to obtain plaque contour information corresponding to each vascular image information by passing at least part of the vascular image information through a plaque segmentation model, and to filter the plaque contour information based on the positional relationship between the plaque and the vascular contour;
[0091] A blood vessel modeling module, used to take a set of blood vessel contour information along the scanning direction as input, perform three-dimensional reconstruction through surface rendering, and generate a three-dimensional model of the blood vessel;
[0092] The plaque modeling module is used to traverse the three-dimensional blood vessel model by passing the contour information of each of the screened plaques to generate a three-dimensional blood vessel model with plaques.
[0093] In one embodiment, the acquisition module further includes a resampling module, and the acquisition module is used to acquire a set of original images and length and depth information of the three-dimensional model arranged in sequence along the scanning trajectory;
[0094] The resampling module resamples the original image to obtain blood vessel image information, where the blood vessel image information is a set of grayscale images.
[0095] In one embodiment, the acquisition module is used to acquire scanning parameter information, wherein the scanning parameter information includes scanning distance information and scanning depth information;
[0096] The three-dimensional reconstruction device also includes a processing module, which is used to calculate the length information and depth information of the three-dimensional model based on the scanning distance information, the scanning depth information and the number of original images.
[0097] In one embodiment, the resampling module is used to grayscale and compress the original image into a resampled image, wherein the original image is a set of transverse scanning color images perpendicular to the extension direction of the blood vessel;
[0098] The processing module is used to use the resampled image as a data source and generate a set of blood vessel image information through a linear interpolation algorithm according to the length information and the depth information.
[0099] In one embodiment, the blood vessel contour recognition module is used to detect the blood vessel image information through a blood vessel segmentation model, replace pixels of the blood vessel image information whose grayscale values are greater than or equal to a preset blood vessel confidence value with a first value, and replace pixels whose grayscale values are less than the preset blood vessel confidence value with a second value, to generate blood vessel contour information.
[0100] In one embodiment, the blood vessel contour recognition module is used to make a circumscribed rectangle of the area replaced with the first value on the blood vessel contour information, and determine the center point of the circumscribed rectangle, further obtain the center points of multiple blood vessel contour information arranged in sequence along the scanning trajectory, and fit the blood vessel extension trajectory according to the least squares algorithm. If the deviation value between the center point on a certain image and the blood vessel extension trajectory exceeds a preset blood vessel deviation value, the image is screened out.
[0101] In one embodiment, the plaque recognition module is used to detect the vascular image information corresponding to the filtered vascular contour information through a plaque segmentation model, replace the pixels of the vascular image information whose grayscale value is greater than or equal to the preset plaque confidence value with a first value, and replace the pixels whose grayscale value is less than the preset plaque confidence value with a second value, to generate plaque contour information.
[0102] In one embodiment, the plaque identification module is used to screen out the image if the deviation between the area with the first value on the plaque contour information and the area with the first value in the corresponding blood vessel contour information is greater than a preset plaque deviation value.
[0103] In one embodiment, the blood vessel modeling module is used to determine a first isosurface based on the boundary contour of a first value and a second value in the blood vessel contour information, and generate a closed grayscale isosurface through a moving cube algorithm, wherein the grayscale isosurface is a three-dimensional model of the blood vessel; and the three-dimensional model of the blood vessel is generated as a first color.
[0104] In one embodiment, the plaque modeling module is used to determine a second isosurface based on the boundary contour of the first value and the second value in the plaque contour information along the scanning trajectory, traverse the second isosurface through the three-dimensional model of the blood vessel, and replace the area where the second isosurface is located with a second color different from the first color, thereby generating a three-dimensional model of the blood vessel with plaque.
[0105] The three-dimensional reconstruction device may be a computing device such as a medical device, a desktop computer, a notebook, a PDA, and a cloud server. The three-dimensional reconstruction device may include, but is not limited to, a processing module and a storage module. Those skilled in the art may understand that the schematic diagram is only an example of a three-dimensional reconstruction device and does not constitute a limitation on the terminal device of the three-dimensional reconstruction device. It may include more or less components than shown in the figure, or combine certain components, or different components. For example, the three-dimensional reconstruction device may also include input and output devices, network access devices, buses, etc.
[0106] It should be noted that for details not disclosed in the three-dimensional reconstruction device of the embodiment of the present invention, please refer to the details disclosed in the three-dimensional reconstruction method of the embodiment of the present invention.
[0107] According to the three-dimensional reconstruction device of the present invention, the three-dimensional structure of the blood vessels and the internal plaques can be clearly drawn, and multiple longitudinal sections can be obtained by ultrasound, which is consistent with the existing scanning method and is particularly suitable for scanning the carotid artery. It can clearly display the bifurcation of the internal carotid artery and the external carotid artery, making it easier to find the location of the carotid sinus. Moreover, because the presentation is more direct, it is also easier to more accurately measure the specific size of the plaque, which helps doctors make more accurate judgments and improves the patient's medical experience.
[0108] The medical device of this embodiment includes: a processing module, a storage module, and a computer program stored in the storage module and executable on the processing module, such as the above-mentioned 3D reconstruction method program. When the processing module executes the computer program, the steps in each of the above-mentioned 3D reconstruction method embodiments are implemented, such as Figure 1 Steps shown.
[0109] In addition, the present invention also proposes an electronic device, which includes a storage module and a processing module. When the processing module executes the computer program, it can implement the steps in the above-mentioned three-dimensional reconstruction method of the medical device, that is, implement the steps in any one of the technical solutions in the above-mentioned three-dimensional reconstruction method of the medical device.
[0110] The electronic device may be a part integrated into the medical device, or a local terminal device, or a part of a cloud server.
[0111] The processing module may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processing module is the control center of the medical device, and uses various interfaces and lines to connect various parts of the entire medical device.
[0112] The storage module can be used to store the computer program and / or module, and the processing module realizes various functions of the medical device by running or executing the computer program and / or module stored in the storage module, and calling the data stored in the storage module. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone, such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0113] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the storage module and executed by the processing module to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the medical device.
[0114] Furthermore, an embodiment of the present invention provides a readable storage medium storing a computer program, which, when executed by a processing module, can implement the steps in the above-mentioned three-dimensional reconstruction method of the medical device, that is, implement the steps in any one of the technical solutions in the above-mentioned three-dimensional reconstruction method.
[0115] If the module integrated in the three-dimensional reconstruction device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each of the above-mentioned method embodiments can be implemented.
[0116] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.
[0117] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
[0118] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for three-dimensional reconstruction of blood vessels and internal plaques, characterized in that: Includes steps: Acquire a set of blood vessel image information of radial sections of the blood vessel, wherein the plurality of blood vessel image information are arranged in sequence along a scanning track; Passing the blood vessel image information through a blood vessel segmentation model to obtain blood vessel contour information corresponding to each blood vessel image information; Filtering the blood vessel contour information based on the scanning trajectory; Passing at least part of the blood vessel image information through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information; Filtering the plaque contour information based on the positional relationship between the plaque and the blood vessel contour; Taking a set of the blood vessel contour information along the scanning direction as input, performing three-dimensional reconstruction through surface rendering to generate a three-dimensional model of the blood vessel; The filtered contour information of each plaque is traversed through the three-dimensional blood vessel model to generate a three-dimensional blood vessel model with plaques.
2. The three-dimensional reconstruction method according to claim 1, characterized in that: The step of "obtaining a set of vascular image information of radial sections of the blood vessels" includes: Acquire a set of original images and length and depth information of the three-dimensional model arranged in sequence along the scanning trajectory; The original image is resampled to obtain blood vessel image information, where the blood vessel image information is a set of grayscale images.
3. The three-dimensional reconstruction method according to claim 2, characterized in that: The step of "obtaining a set of original images and length and depth information of the three-dimensional model arranged in sequence along the scanning trajectory" includes: Acquire scanning parameter information, wherein the scanning parameter information includes scanning distance information and scanning depth information; The length information and depth information of the three-dimensional model are calculated according to the scanning distance information, the scanning depth information and the number of original images.
4. The three-dimensional reconstruction method according to claim 3, characterized in that: The step of "re-sampling the original image to obtain vascular image information" includes: Graying and compressing the original image into a resampled image, wherein the original image is a set of transverse scanning color images perpendicular to the extension direction of the blood vessel; Taking the resampled image as a data source, a set of blood vessel image information is generated through a linear interpolation algorithm according to the length information and the depth information.
5. The three-dimensional reconstruction method according to claim 1, characterized in that: The step of "obtaining blood vessel contour information corresponding to each blood vessel image information through a blood vessel segmentation model" includes: The blood vessel image information is detected by a blood vessel segmentation model, pixels whose grayscale values of the blood vessel image information are greater than or equal to a preset blood vessel confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset blood vessel confidence value are replaced with a second value, to generate blood vessel contour information.
6. The three-dimensional reconstruction method according to claim 5, characterized in that: The step of "screening the blood vessel contour information based on the scanning trajectory" includes: A region on the blood vessel contour information replaced with the first value is used as a circumscribed rectangle, and the center point of the circumscribed rectangle is determined. Further, a plurality of center points of the blood vessel contour information sequentially arranged along the scanning trajectory are obtained. The blood vessel extension trajectory is fitted according to a least squares algorithm. If a deviation value between a center point of a certain blood vessel contour information and the blood vessel extension trajectory exceeds a preset blood vessel deviation value, the blood vessel contour information is screened out.
7. The three-dimensional reconstruction method according to claim 6, characterized in that: The step of "passing at least part of the blood vessel image information through the plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information" includes: The blood vessel image information corresponding to the filtered blood vessel contour information is passed through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information.
8. The three-dimensional reconstruction method according to claim 7, characterized in that: The step of "using the blood vessel image information corresponding to the filtered blood vessel contour information through a plaque segmentation model to obtain plaque contour information corresponding to each blood vessel image information" includes: The vascular image information corresponding to the filtered vascular contour information is detected through a plaque segmentation model, and pixels of the vascular image information whose grayscale values are greater than or equal to a preset plaque confidence value are replaced with a first value, and pixels whose grayscale values are less than the preset plaque confidence value are replaced with a second value to generate plaque contour information.
9. The three-dimensional reconstruction method according to claim 8, characterized in that: The step of "screening the plaque contour information based on the positional relationship between the plaque and the blood vessel contour" includes: If the degree of deviation between the area of the first value on a piece of plaque contour information and the area of the first value in the corresponding blood vessel contour information is greater than a preset plaque deviation value, the plaque contour information is screened out.
10. The three-dimensional reconstruction method according to claim 9, characterized in that: The step of "taking a set of the blood vessel contour information along the scanning direction as input, performing three-dimensional reconstruction through surface rendering, and generating a three-dimensional model of the blood vessel" includes: Determine a first isosurface based on the boundary contour of the first value and the second value in the blood vessel contour information, and generate a closed grayscale isosurface by a marching cube algorithm, wherein the grayscale isosurface is a three-dimensional model of the blood vessel; The three-dimensional model of the blood vessel is generated in a first color.
11. The three-dimensional reconstruction method according to claim 10, characterized in that: The step of "traversing the three-dimensional blood vessel model with each of the filtered plaque contour information to generate a three-dimensional blood vessel model with plaques" includes: A second isosurface is determined based on the boundary contour of the first value and the second value in the plaque contour information along the scanning trajectory, the second isosurface is traversed through the three-dimensional model of the blood vessel, the area where the second isosurface is located is replaced with a second color different from the first color, and a three-dimensional model of the blood vessel with plaque is generated.
12. A three-dimensional reconstruction device for blood vessels and internal plaques, characterized in that: include: An acquisition module, used for acquiring a set of vascular image information of radial sections of the vascular, wherein the plurality of vascular image information are arranged in sequence along a scanning track; A blood vessel contour recognition module, used to obtain blood vessel contour information corresponding to each blood vessel image information through a blood vessel segmentation model, and to filter the blood vessel contour information based on a scanning trajectory; a plaque recognition module, used to obtain plaque contour information corresponding to each vascular image information by passing at least part of the vascular image information through a plaque segmentation model, and to filter the plaque contour information based on the positional relationship between the plaque and the vascular contour; A blood vessel modeling module, used to take a set of blood vessel contour information along the scanning direction as input, perform three-dimensional reconstruction through surface rendering, and generate a three-dimensional model of the blood vessel; The plaque modeling module is used to traverse the three-dimensional blood vessel model by passing the contour information of each of the screened plaques to generate a three-dimensional blood vessel model with plaques.
13. A medical device, characterized in that: include: The device for three-dimensional reconstruction of blood vessels and internal plaques as claimed in claim 12.
14. An electronic device, characterized in that: include: A storage module storing a computer program; The processing module can implement the steps of the method for three-dimensional reconstruction of blood vessels and internal plaques as described in any one of claims 1 to 11 when executing the computer program.
15. A readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processing module, the steps in the method for three-dimensional reconstruction of blood vessels and internal plaques described in any one of claims 1 to 11 can be implemented.
