Prosthetic heart valve quality inspection method, system, electronic device, and storage medium

Abstract

The application provides a prosthetic heart valve quality inspection method, system, electronic equipment and storage medium, the quality inspection method comprises the following steps: acquiring an image of a to-be-detected prosthetic heart valve; identifying the image of the to-be-detected prosthetic heart valve to identify each valve leaflet of the to-be-detected prosthetic heart valve; calculating the quality inspection characteristic parameters of each valve leaflet; and obtaining the quality inspection result of the to-be-detected prosthetic heart valve according to the quality inspection characteristic parameters of each valve leaflet. The application can realize automatic detection of the quality of the prosthetic heart valve, effectively improve the accuracy of the quality inspection result of the prosthetic heart valve, and reduce the quality inspection cost of the prosthetic heart valve.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, system, electronic device, and storage medium for quality inspection of artificial heart valves. Background Technology

[0002] The tricuspid valve (right atrioventricular valve) is a "valve" that controls the unidirectional flow of blood from the right atrium to the right ventricle. It consists of three triangular leaflet-shaped leaflets, called the anterior leaflet, posterior leaflet, and septal leaflet according to their location. When the right ventricle relaxes, the tricuspid valve opens, pumping blood from the right atrium into the right ventricle. When the right ventricle contracts, it squeezes blood into the pulmonary artery, and the tricuspid valve closes to prevent blood from flowing back into the right atrium. Therefore, with each heartbeat, all valves, including the tricuspid valve, undergo a cycle of opening and closing, highlighting the crucial role of the tricuspid valve in cardiac function.

[0003] Medical data shows that the tricuspid valves are generally of uniform thickness, with the posterior leaflet being slightly thicker than the other two by about 0.1 mm. Please refer to this information. Figure 1 It schematically provides a geometric model diagram of the tricuspid valve. For example... Figure 1 As shown, the geometric model of the tricuspid valve can be viewed as a splice of two ellipses. In its fully open state, the anterior leaflet 110 is part of a single elliptical cylinder, while the septal leaflet 120 and posterior leaflet 130 are each half of an elliptical cylinder with the major axis of the anterior leaflet 110 as its minor axis. During systole, the tricuspid valve should be completely closed to prevent backflow of blood; similarly, during diastole, the curvature of the three leaflets should be similar.

[0004] The most common and curable treatment for tricuspid valve disease is transcatheter tricuspid valve replacement (TCVPR), leading to an increasing demand for artificial heart valves. Quality control is an essential step before artificial heart valves leave the factory. Currently, quality control primarily relies on inspectors visually assessing the valve assembly for quality. However, this manual inspection method has several drawbacks:

[0005] 1. Quality inspectors can only give a qualitative conclusion, i.e., qualified or unqualified, for each group of valves on the production line based on the indicators in the quality inspection training.

[0006] 2. The work experience of quality inspectors reflects their work efficiency and accuracy. Once a quality inspector leaves, it is necessary to recruit a new quality inspector and train them.

[0007] 3. As the production of artificial heart valves increases, the number of quality inspectors required and the training costs also increase. However, when market production fluctuates, it is impossible to respond in a timely manner, thus making it impossible to control the cost of quality inspection.

[0008] It should be noted that the information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0009] The purpose of this invention is to provide a method, system, electronic device, and storage medium for quality inspection of artificial heart valves, which can automatically detect the quality of artificial heart valves and effectively improve the accuracy of artificial heart valve quality inspection results.

[0010] To achieve the above objectives, the present invention provides a method for quality inspection of artificial heart valves, comprising:

[0011] Acquire images of the artificial heart valve to be tested;

[0012] The image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested;

[0013] Calculate the quality inspection characteristic parameters of each of the aforementioned leaflets;

[0014] The quality inspection results of the artificial heart valve to be tested are obtained based on the quality inspection characteristic parameters of each of the valve leaflets.

[0015] Optionally, before recognizing the image of the artificial heart valve to be tested, the quality inspection method further includes:

[0016] Determine whether a curtain is present in the image of the artificial heart valve to be tested;

[0017] If so, the identification of the image of the artificial heart valve to be detected includes:

[0018] Machine learning algorithms are used to identify the image of the artificial heart valve to be detected;

[0019] If not, then the identification of the image of the artificial heart valve to be detected includes:

[0020] A deep learning algorithm is used to identify the image of the artificial heart valve to be detected.

[0021] Optionally, determining whether a curtain exists in the image of the artificial heart valve to be detected includes:

[0022] The image of the artificial heart valve to be tested is converted from the RGB channel to the HSV channel to obtain an HSV channel image;

[0023] Traverse every pixel in the HSV channel image to find the first target pixel whose H component is in a first preset range, whose S component is in a second preset range, and whose V component is in a third preset range.

[0024] Determine whether the ratio between the number of the first target pixels and the total number of pixels in the HSV channel image is greater than or equal to a ratio threshold.

[0025] If yes, it is determined that a curtain exists in the image of the artificial heart valve to be tested; otherwise, it is determined that no curtain exists in the image of the artificial heart valve to be tested.

[0026] Optionally, the quality inspection characteristic parameter is curvature;

[0027] The curvature of the leaflet is calculated using the following steps:

[0028] Locate the three vertices of the inscribed triangle of the leaflet;

[0029] Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle;

[0030] The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet.

[0031] Optionally, finding the three vertices of the inscribed triangle of the leaflet includes:

[0032] A rectangular coordinate system is established with the width direction of the image of the artificial heart valve to be tested as the X-axis and the height direction of the image of the artificial heart valve to be tested as the Y-axis.

[0033] Based on the coordinates of each pixel of the petal in the Cartesian coordinate system of the image, the lower left and lower right pixels of the petal are found as the two lower vertices of the inscribed triangle of the petal.

[0034] The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point.

[0035] The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate.

[0036] Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the leaflet region horizontally until the leaflet regions explored at both ends of the horizontal line merge into a continuous region. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet to find the upper vertex of the inscribed triangle of the leaflet.

[0037] Optionally, obtaining the quality inspection result of the artificial heart valve under test based on the curvature of each of the leaflets includes:

[0038] Based on the curvature of each leaflet of the artificial heart valve to be tested, the two leaflets with the largest difference in curvature are identified as the two target leaflets.

[0039] Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold.

[0040] If so, the artificial heart valve to be tested is deemed unqualified.

[0041] Optionally, acquiring an image of the artificial heart valve to be detected includes:

[0042] Acquire a first image of the artificial heart valve under test when the smooth surfaces of each leaflet are naturally drooping and / or acquire a second image of the artificial heart valve under test when the rough surfaces of each leaflet are naturally drooping.

[0043] The step of recognizing the image of the artificial heart valve to be tested, in order to identify the individual leaflets of the artificial heart valve to be tested, includes:

[0044] The first image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested; and / or the second image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested;

[0045] The calculation of the quality inspection characteristic parameters of each of the leaflets includes:

[0046] Calculate the first quality inspection characteristic parameter of each of the valve leaflets; and / or calculate the second quality inspection characteristic parameter of each of the valve leaflets;

[0047] The step of obtaining the quality inspection results of the artificial heart valve under test based on the quality inspection characteristic parameters of each of the valve leaflets includes:

[0048] The smooth surface of the artificial heart valve to be tested is determined to be qualified based on the first quality inspection characteristic parameter of each of the valve leaflets; and / or the rough surface of the artificial heart valve to be tested is determined to be qualified based on the second quality inspection characteristic parameter of each of the valve leaflets.

[0049] Optionally, the method further includes:

[0050] When the artificial heart valve to be tested is found to be unqualified, a notification message indicating the unqualified valve leaflet is sent.

[0051] To achieve the above objectives, the present invention also provides an artificial heart valve quality inspection system, including a valve fixation device, an image acquisition device, and a controller. The image acquisition device is disposed opposite to the valve fixation device, and the image acquisition device is communicatively connected to the controller.

[0052] The valve fixation device is configured to fix the artificial heart valve to be tested, and the artificial heart valve to be tested includes multiple leaflets;

[0053] The image acquisition device is configured to acquire an image of the artificial heart valve to be tested and transmit the acquired image of the artificial heart valve to be tested to the controller;

[0054] The controller is configured to recognize the image of the artificial heart valve to be tested, identify each leaflet of the artificial heart valve to be tested, calculate the quality inspection characteristic parameters of each leaflet, and obtain the quality inspection result of the artificial heart valve to be tested based on the quality inspection characteristic parameters of each leaflet.

[0055] Optionally, the valve fixing device includes a first lifting platform and a placement module installed on the first lifting platform. The placement module includes a plurality of placement rods arranged parallel to each other. Each placement rod corresponds to a valve leaflet, and the front end of each placement rod is suspended in the air to fix the valve leaflet.

[0056] Optionally, the image acquisition device includes a second lifting platform and a camera mounted on the second lifting platform. The camera is used to acquire images of the artificial heart valve to be tested and transmit the acquired images of the artificial heart valve to be tested to the controller.

[0057] Optionally, the artificial heart valve quality inspection system further includes a linear guide rail with graduations. The valve fixation device is located at one end of the linear guide rail, and the image acquisition device is located at the other end of the linear guide rail. Both the valve fixation device and the image acquisition device can reciprocate on the linear guide rail.

[0058] Optionally, the artificial heart valve quality inspection system further includes a screen, and the valve fixing device is disposed between the screen and the image acquisition device;

[0059] The controller is further configured to determine whether a curtain exists in the image of the artificial heart valve to be detected. If so, a machine learning algorithm is used to identify the image of the artificial heart valve to be detected; otherwise, a deep learning algorithm is used to identify the image of the artificial heart valve to be detected.

[0060] Optionally, the quality inspection characteristic parameter is curvature, and the controller is configured to calculate the curvature of the leaflet through the following steps:

[0061] Locate the three vertices of the inscribed triangle of the leaflet;

[0062] Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle;

[0063] The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet.

[0064] Optionally, the controller is configured to obtain the quality inspection results of the artificial heart valve to be tested through the following steps:

[0065] Based on the curvature of each leaflet of the artificial heart valve to be tested, the two leaflets with the largest difference in curvature are identified as the two target leaflets.

[0066] Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold.

[0067] If so, the artificial heart valve to be tested is deemed unqualified.

[0068] Optionally, the controller is configured to find the three vertices of the inscribed triangle of the leaflet by the following steps:

[0069] A rectangular coordinate system is established with the width direction of the image of the artificial heart valve to be tested as the X-axis and the height direction of the image of the artificial heart valve to be tested as the Y-axis.

[0070] Based on the coordinates of each pixel of the petal in the Cartesian coordinate system of the image, the lower left and lower right pixels of the petal are found as the two lower vertices of the inscribed triangle of the petal.

[0071] The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point.

[0072] The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate.

[0073] Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the leaflet region horizontally until the leaflet regions explored at both ends of the horizontal line merge into a continuous region. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet to find the upper vertex of the inscribed triangle of the leaflet.

[0074] To achieve the above objectives, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the artificial heart valve quality inspection method described above.

[0075] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the artificial heart valve quality inspection method described above.

[0076] Compared with existing technologies, the artificial heart valve quality inspection method, system, electronic device, and storage medium provided by this invention have the following advantages:

[0077] The artificial heart valve quality inspection method provided by this invention first acquires an image of the artificial heart valve to be inspected; then, it identifies the individual leaflets of the artificial heart valve in the image; next, it calculates the quality inspection characteristic parameters of each leaflet; finally, it obtains the quality inspection result of the artificial heart valve based on the quality inspection characteristic parameters of each leaflet. Therefore, the artificial heart valve quality inspection method provided by this invention can achieve automatic detection of artificial heart valve quality, effectively improve the accuracy of artificial heart valve quality inspection results, and reduce the quality inspection cost of artificial heart valves. The artificial heart valve quality inspection system provided by this invention can be practically applied to the quality inspection process of artificial heart valves, meeting the actual needs of artificial heart valve production inspection.

[0078] Since the artificial heart valve quality inspection system, electronic device and storage medium provided by this invention belong to the same inventive concept as the artificial heart valve quality inspection method provided by this invention, the artificial heart valve quality inspection system, electronic device and storage medium provided by this invention have all the advantages of the artificial heart valve quality inspection method provided by this invention. Therefore, the beneficial effects of the artificial heart valve quality inspection system, electronic device and storage medium provided by this invention will not be described in detail here. Attached Figure Description

[0079] Figure 1 This is a schematic diagram of the geometric model of the tricuspid valve;

[0080] Figure 2 A schematic diagram of the overall structure of an artificial heart valve quality inspection system provided in one embodiment of the present invention;

[0081] Figure 3 This is a schematic diagram of an image of an artificial heart valve to be tested, provided as a specific example of the present invention.

[0082] Figure 4 A schematic diagram illustrating the principle of calculating the curvature of each leaflet, provided as a specific example of the present invention;

[0083] Figure 5 A schematic diagram illustrating the exploration process of the upper vertex according to one embodiment of the present invention;

[0084] Figure 6 A distribution diagram of the maximum first curvature difference for a qualified artificial heart valve with a smooth surface;

[0085] Figure 7 This is a distribution diagram of the maximum second curvature difference of a qualified artificial heart valve with a rough surface.

[0086] Figure 8 This is a distribution diagram of the maximum first curvature difference for an artificial heart valve with a non-compliant smooth surface.

[0087] Figure 9 This is a flowchart illustrating a method for quality inspection of artificial heart valves according to an embodiment of the present invention.

[0088] Figure 10 This is a block diagram of an electronic device provided according to an embodiment of the present invention.

[0089] The accompanying figure is labeled as follows:

[0090] Anterior leaflet -110; septate leaflet -120; posterior leaflet -130;

[0091] Valve fixation device-200; First lifting platform-210; Placement module-220; Placement rod-221;

[0092] Image acquisition device-30; Second lifting platform-310; Camera-320;

[0093] Controller-400;

[0094] Artificial heart valve to be tested -500; leaflet -510;

[0095] Linear guide rail - 610; Curtain - 620;

[0096] Input devices - 710; Output devices - 720;

[0097] Processor-810; Communication interface-820; Memory-830; Communication bus-840. Detailed Implementation

[0098] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, further illustrates the artificial heart valve quality inspection method, system, electronic device, and storage medium proposed in this invention. The advantages and features of this invention will become clearer from the following description. It should be noted that the drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clarify the illustration of the embodiments of this invention. Please refer to the drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for illustrative purposes and to enable those skilled in the art to understand and read them, and are not intended to limit the implementation conditions of this invention. Any modifications to the structure, changes in proportions, or adjustments to the size, provided that the effects and objectives achieved by this invention are the same or similar, should still fall within the scope of the technical content disclosed in this invention.

[0099] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0100] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0101] In the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0102] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0103] The core idea of ​​this invention is to provide a method, system, electronic device, and storage medium for quality inspection of artificial heart valves, which can automatically detect the quality of artificial heart valves and effectively improve the accuracy of the quality inspection results. For ease of understanding, this paper first describes the artificial heart valve quality inspection system provided by this invention, and then describes the artificial heart valve quality inspection method provided by this invention.

[0104] It should be noted that the artificial heart valve quality inspection method provided by this invention can be applied to the artificial heart valve quality inspection system provided by this invention. The controller in the artificial heart valve quality inspection system provided by this invention can be configured on an electronic device, which can be a personal computer, a mobile terminal, etc. The mobile terminal can be a mobile phone, tablet computer, or other hardware device with various operating systems. Furthermore, it should be noted that although this article uses the artificial tricuspid valve as an example of the artificial heart valve to be tested, as those skilled in the art will understand, this invention does not limit the specific type of artificial heart valve to be tested. The artificial heart valve quality inspection system and method provided by this invention can be applied not only to the quality inspection of the artificial tricuspid valve, but also to the quality inspection of artificial mitral valves, artificial aortic valves, and artificial pulmonary valves. Additionally, it should be noted that although this article uses curvature as a quality inspection characteristic parameter as an example, as those skilled in the art will understand, the quality inspection characteristic parameter can also be other parameters besides curvature that can evaluate the quality of the artificial heart valve. The type of the quality inspection characteristic parameter is related to the quality inspection indicators of the artificial heart valve, and the specific type of the quality inspection characteristic parameter can be determined according to the specific quality inspection indicators.

[0105] To achieve the above-mentioned goals, this invention provides an artificial heart valve quality inspection system. Please refer to [the relevant documentation]. Figure 2 The diagram illustrates the overall structure of an artificial heart valve quality inspection system according to an embodiment of the present invention. Figure 2 As shown, the artificial heart valve quality inspection system provided by the present invention includes a valve fixation device 200, an image acquisition device 300, and a controller 400. The image acquisition device 300 is disposed opposite to the valve fixation device 200 and is communicatively connected to the controller 400. The valve fixation device 200 is configured to fix an artificial heart valve 500 to be inspected, the artificial heart valve 500 to be inspected including multiple leaflets 510. The image acquisition device 300 is configured to acquire images of the artificial heart valve 500 to be inspected and transmit the acquired images of the artificial heart valve 500 to be inspected to the controller 400. The controller 400 is configured to recognize the images of the artificial heart valve 500 to be inspected, to identify each leaflet 510 of the artificial heart valve 500 to be inspected, to calculate the quality inspection characteristic parameters of each leaflet 510, and to obtain the quality inspection result of the artificial heart valve 500 to be inspected based on the quality inspection characteristic parameters of each leaflet 510.

[0106] Therefore, the artificial heart valve quality inspection system provided by this invention acquires images of the artificial heart valve 500 to be inspected, and identifies the leaflets 510 and calculates the quality inspection characteristic parameters of the leaflets 510 based on the acquired images of the artificial heart valve 500 to obtain the quality inspection results of the artificial heart valve 500. This enables automatic detection of artificial heart valve quality, effectively improving the accuracy of artificial heart valve quality inspection results and reducing the quality inspection cost of artificial heart valves. The artificial heart valve quality inspection system provided by this invention can be practically applied to the quality inspection process of artificial heart valves, meeting the actual needs of artificial heart valve production inspection.

[0107] It should be noted that, as those skilled in the art will understand, the image acquisition device 300 can communicate with the controller 400 via Bluetooth short-range link, wireless LAN, or data cable. In practical applications, a suitable communication method can be selected based on the specific functions of the image acquisition device 300 and the controller 400. For example, when both the image acquisition device 300 and the controller 400 have wireless functions such as Bluetooth, they can communicate with each other via Bluetooth short-range link or wireless LAN; when one of the image acquisition device 300 and the controller 400 does not have wireless functions, they can communicate with each other via a wired connection such as a data cable.

[0108] In one exemplary embodiment, the controller 400 is further configured to name, store, and archive the acquired images of the artificial heart valve 500 to be tested. Thus, by naming, storing, and archiving the acquired images of the artificial heart valve 500 to be tested, it is easier to record and trace the artificial heart valve production process, and this further helps to increase the production volume of artificial heart valves.

[0109] Please continue to refer to this. Figure 2 ,like Figure 2As shown, in an exemplary embodiment, the valve fixation device 200 includes a first lifting platform 210 and a placement module 220 mounted on the first lifting platform 210. The placement module 220 includes a plurality of parallel placement rods 221, each corresponding to a leaflet 510. The front end of each placement rod 221 is suspended to fix the leaflet 510. Thus, the height of the placement module 220 can be adjusted by adjusting the height of the first lifting platform 210, so that the optical axis of the image acquisition device 300 and the placement position of the artificial heart valve 500 to be tested (i.e., the placement rod 221) are at the same horizontal level. This improves the image quality of the artificial heart valve 500 acquired by the image acquisition device 300, laying a good foundation for obtaining accurate quality inspection results later. It should be noted that, as those skilled in the art will understand, the specific structure and working principle of the first lifting platform 210 can be found in existing lifting platforms, and therefore will not be described in detail here. Furthermore, it should be noted that, as those skilled in the art will understand, the leaflet 510 of the artificial heart valve can be fixed to the placement rod 221 by suspending it at the front end of the placement rod 221.

[0110] Preferably, the length and radius of each of the placement rods 221 are equal, and the placement rods 221 are arranged at equal intervals. This arrangement effectively avoids interference from external factors with the quality inspection results of the artificial heart valve, further improving the accuracy of the quality inspection results.

[0111] Please continue to refer to this. Figure 2 ,like Figure 2 As shown, in one exemplary embodiment, the image acquisition device 300 includes a second lifting platform 310 and a camera 320 mounted on the second lifting platform 310. The camera 320 is used to acquire images of the artificial heart valve 500 to be tested and transmit the acquired images of the artificial heart valve 500 to the controller 400. Thus, the height of the camera 320 can be adjusted by adjusting the height of the second lifting platform 310, thereby ensuring that the optical axis of the camera 320 is at the same horizontal level as the placement position of the artificial heart valve 500 to be tested.

[0112] In one exemplary embodiment, the first lifting platform 210 and the second lifting platform 310 are made of the same material and have the same dimensions. This arrangement can reduce costs.

[0113] Please continue to refer to this. Figure 2 ,like Figure 2As shown, in an exemplary embodiment, the artificial heart valve quality inspection system further includes a linear guide rail 610 with graduations. The valve fixation device 200 is located at one end of the linear guide rail 610, and the image acquisition device 300 is located at the other end. Both the valve fixation device 200 and the image acquisition device 300 can reciprocate on the linear guide rail 610. Therefore, by setting the linear guide rail 610, it is easy to ensure that both the valve fixation device 200 and the image acquisition device 300 are in a horizontal position, thereby further improving the image quality of the artificial heart valve 500 to be inspected acquired by the image acquisition device 300, laying a good foundation for obtaining accurate quality inspection results. Furthermore, by setting a scale on the linear guide rail 610, it is easier to confirm the fixed positions of the valve fixation device 200 and the image acquisition device 300 on the linear guide rail 610, and it is convenient to calculate and record the distance d between the valve fixation device 200 and the image acquisition device 300.

[0114] Specifically, the linear guide 610 is set with scale lines starting from one end, with the scale value starting from 0cm and increasing at preset intervals (e.g., 1cm).

[0115] Furthermore, before acquiring images of the artificial heart valve 500 to be tested using the artificial heart valve quality inspection system provided by this invention, system calibration is required. Image acquisition can only proceed after system calibration is completed. The purpose of system calibration is to quantify and standardize the image acquisition process, ensuring uniform image quality of the acquired artificial heart valve 500. The system calibration process includes hardware calibration and image calibration. Hardware calibration includes calibration of the linear guide rail 610, calibration of the valve fixation device 200, and calibration of the image acquisition device 300. Calibration of the linear guide rail 610 ensures that it is placed on a platform (e.g., a rectangular platform) with a horizontal inclination angle of 0, guaranteeing that the linear guide rail 610 is horizontal. The horizontal inclination angle of the platform can be measured using tools such as a level or spirit level. Calibration of the valve fixation device 200 ensures that the front ends of each placement rod 221 of the placement module 220 extend out of the first lifting platform 210 by the same length. The calibration of the image acquisition device 300 is to ensure that the camera 320 is fixed in the center of the second lifting platform 310.

[0116] After hardware calibration is completed, image calibration begins. The purpose of image calibration is to ensure that the optical axis of the camera 320 and the placement module 220 are on the horizontal calibration line (i.e., to ensure that the optical axis of the camera 320 and the placement module 220 are at the same horizontal height). During image calibration, the distance between the first lifting platform 210 and the second lifting platform 310 needs to be recorded first. Then, the camera 320 is used to observe whether each placement rod 221 of the placement module 220 appears as a dot. Since the linear guide rail 610 is in a horizontal state after hardware calibration, the placement module 220 and the camera 320 are also in a horizontal state. If each placement rod 221 of the placement module 220 appears as a dot in the image of the camera 320, it indicates that the optical axis of the camera 320 and the placement module 220 are on the horizontal calibration line.

[0117] Please refer to Figure 3 The diagram illustrates an image of an artificial heart valve 500 to be tested, provided in a specific example of the present invention. Figure 3 As shown, after the system calibration is completed, in the image of the artificial heart valve 500 to be tested acquired by the image acquisition device 300, each of the placement rods 221 is set in a dot-like manner.

[0118] Please continue to refer to this. Figure 2 ,like Figure 2 As shown, in an exemplary embodiment, the artificial heart valve quality inspection system further includes a screen 620, with the valve fixing device 200 disposed between the screen 620 and the image acquisition device 300. Thus, by setting up the screen 620, environmental background interference during image acquisition can be avoided, which would affect the distinction between the leaflet 510 area and the background area in the acquired image of the artificial heart valve 500 under test. This ensures that the controller 400 can accurately identify each leaflet 510 in the image of the artificial heart valve 500 under test. It should be noted that, as those skilled in the art will understand, if there is no space to place the screen 620 in the installation environment of the artificial heart valve quality inspection system, the screen 620 may be omitted.

[0119] Preferably, the valve fixation device 200, the image acquisition device 300, the controller 400, the linear guide rail 610, and the screen 620 are all black. This arrangement effectively avoids the problems of poor image quality and difficulty in valve recognition caused by ambient light interference during image acquisition.

[0120] In one exemplary embodiment, the controller 400 is further configured to determine whether a curtain 620 exists in the image of the artificial heart valve 500 to be tested. If so, a machine learning algorithm is used to identify the image of the artificial heart valve 500 to be tested; otherwise, a deep learning algorithm is used to identify the image of the artificial heart valve 500 to be tested. Since the presence of the curtain 620 in the image of the artificial heart valve 500 to be tested effectively avoids environmental background interference during image acquisition, it makes it easier to distinguish the leaflet 510 area from the background area. Therefore, the machine learning algorithm can accurately identify each leaflet 510 in the image of the artificial heart valve 500 to be tested. When the backdrop 620 is absent from the image of the artificial heart valve 500 to be tested, the environmental background interference during image acquisition results in low differentiation between the leaflet 510 region and the background region in the image of the artificial heart valve 500 to be tested. In this case, machine learning algorithms may not be able to accurately identify the leaflets 510 in the image of the artificial heart valve 500 to be tested. However, since deep learning algorithms are more accurate than machine learning algorithms, deep learning algorithms can accurately identify each leaflet 510 in the image of the artificial heart valve 500 to be tested. It should be noted that, as those skilled in the art will understand, if the controller 400 is not equipped with a GPU capable of performing deep learning algorithms, machine learning algorithms will be used to identify the image of the artificial heart valve 500 to be tested regardless of whether the backdrop 620 is present in the image.

[0121] Furthermore, the controller 400 is configured to determine whether a curtain 620 exists in the image of the artificial heart valve 500 to be detected through the following steps:

[0122] The image of the artificial heart valve 500 to be tested is converted from the RGB channel to the HSV channel to obtain the HSV channel image;

[0123] Traverse every pixel in the HSV channel image to find the first target pixel whose H component is in a first preset range, whose S component is in a second preset range, and whose V component is in a third preset range.

[0124] Determine whether the ratio between the number of the first target pixels and the total number of pixels in the HSV channel image is greater than or equal to a ratio threshold.

[0125] If yes, then it is determined that the image of the artificial heart valve 500 to be tested contains the curtain 620; otherwise, it is determined that the image of the artificial heart valve 500 to be tested does not contain the curtain 620.

[0126] Specifically, when the screen 620 is black, the first preset range is [0, 180], the second preset range is [0, 255], and the third preset range is [0, 46]. Therefore, pixels with the H component in the first preset range (i.e., H∈[0, 180]), the S component in the second preset range (i.e., S∈[0, 255]), and the V component in the third preset range (i.e., V∈[0, 46]) are the first target pixels (pixels with the same color as the screen 620, i.e., black pixels). Since the screen 620 occupies a very large area in the image of the artificial heart valve 500 when it is present, the presence of the screen 620 can be accurately determined by judging whether the ratio between the number of the first target pixels and the total number of pixels in the HSV channel image is greater than or equal to a ratio threshold. It should be noted that, as those skilled in the art will understand, the range of the ratio threshold is (0,1). The present invention does not limit the specific value of the ratio threshold, which can be set according to the actual situation. For example, the ratio threshold can be set to 0.95.

[0127] In one exemplary embodiment, the controller 400 is configured to identify each leaflet 510 of the artificial heart valve 500 by employing a machine learning algorithm that binarizes an image of the artificial heart valve 500 to be detected.

[0128] Specifically, binarization methods include, but are not limited to, OTSU method, HSV channel extraction of white regions (valve appears white), bimodal threshold segmentation, etc.

[0129] Furthermore, the controller 400 is configured to identify an image of the artificial heart valve 500 to be detected through the following process:

[0130] The image of the artificial heart valve to be detected is binarized to obtain a binary image;

[0131] Perform connected component analysis on the binary image and calculate the area of ​​each connected component;

[0132] Extract the target connected regions whose area is greater than a preset area threshold or whose area is within a preset number of positions, and use them as the regions where each lobe 510 is located.

[0133] Specifically, when the artificial heart valve 500 to be tested includes three leaflets 510, the preset number of bits is the top three, and three target connected components are extracted, with one target connected component corresponding to one leaflet 510; when the artificial heart valve 500 to be tested includes two leaflets 510, the preset number of bits is the top two, and two target connected components are extracted, with one target connected component corresponding to one leaflet 510. It should be noted that, as those skilled in the art will understand, the specific value of the preset area threshold can be set according to actual conditions, and this invention does not limit it in this regard.

[0134] In one exemplary embodiment, the controller 400 is further configured to send a leaflet 510 missing information when the number of target connected regions is less than the theoretical number of leaflets 510 of the artificial heart valve 500 to be detected.

[0135] Specifically, when the artificial heart valve 500 to be tested is an artificial heart valve with three leaflets 510, such as the tricuspid valve, aortic valve, or pulmonary valve (i.e., an artificial heart valve with a theoretical number of 3 leaflets 510), if the number of extracted target connected regions is less than 3, it indicates that the leaflets 510 of the artificial heart valve 500 to be tested are missing. At this time, the controller 400 will send a prompt message to the user indicating that the leaflets 510 are missing, prompting the user to fix the missing leaflets 510 on the corresponding placement rod 221 and re-acquire the image of the artificial heart valve 500 to be tested for detection.

[0136] In one exemplary embodiment, the controller 400 is configured to identify each leaflet 510 of the artificial heart valve 500 by employing a deep learning algorithm that first performs target detection on the image of the artificial heart valve 500 to detect the region of interest of each leaflet 510, and then segments the leaflet 510 within the region of interest of each leaflet 510.

[0137] Therefore, by object detection, the approximate area of ​​each leaflet 510 can be roughly located (that is, the region of interest of each leaflet 510 can be detected), so as to greatly reduce the interference of the background. By segmenting the region of interest of each leaflet 510, the computing power of the deep learning network can be focused on the identification of the valve edge, so as to accurately identify (segment) each leaflet 510.

[0138] Specifically, the coordinates of the minimum bounding rectangle of each leaflet 510 can be calculated through object detection. The region defined by the minimum bounding rectangle is the region of interest of the corresponding leaflet 510. The coordinates of the minimum bounding rectangle are shown in equations (1) and (2) below:

[0139] bounding_box=[x_min,y_min,x_max,y_max] (1)

[0140] bounding_box=[x_center,y_center,width_ratio,height_ratio] (2)

[0141] Where x_min represents the minimum X-coordinate of the minimum bounding rectangle, x_max represents the maximum X-coordinate of the minimum bounding rectangle, y_min represents the minimum Y-coordinate of the minimum bounding rectangle, and y_max represents the maximum Y-coordinate of the minimum bounding rectangle. x_center represents the X-coordinate of the center point of the minimum bounding rectangle, y_center represents the Y-coordinate of the center point of the minimum bounding rectangle, width_ratio represents the ratio of the width bw of the minimum bounding rectangle to the width w of the image, and height_ratio represents the ratio of the height bh of the minimum bounding rectangle to the height h of the image.

[0142] in:

[0143] bw = x_max - x_min (3)

[0144] bh=y_max-y_min (4)

[0145] x_center=(x_min+bw / 2) / w (5)

[0146] y_center=(y_min+bh / 2) / h (6)

[0147] width_ratio = bw / w (7)

[0148] height_ratio=bh / h (8)

[0149] Furthermore, a trained object detection network can be used to perform object detection on the image of the artificial heart valve 500 to be detected. Object detection networks include, but are not limited to, the YOLO series (YOLOv1 to YOLOv7), Fast R-CNN, Faster R-CNN, Mask R-CNN, and Mask Scoring R-CNN. Specifically, the samples used during the training of the object detection network are artificial heart valve sample images with the regions of interest of each leaflet 510 annotated. These artificial heart valve sample images can be acquired using the artificial heart valve quality inspection system provided by this invention, or they can be obtained by other methods; this invention does not limit the methods used. Specifically, the edges of each leaflet 510 in the acquired artificial heart valve sample image can be delineated and labeled. Then, based on the labeled edges of each leaflet 510, the coordinates of the minimum bounding rectangle of each leaflet 510 can be calculated. Thus, based on the coordinates of the minimum bounding rectangle of each leaflet 510, the region of interest of each leaflet 510 can be labeled in the artificial heart valve sample image to obtain the samples required for training the object detection network.

[0150] Furthermore, a trained segmentation network can be used to segment the regions of interest (ROIs) of each leaflet 510. The segmentation network includes, but is not limited to, variations of Unet networks such as Unet, Unet++, and nnUnet, which use ResNet, DenseNet, and EfficientNet as backbones. Specifically, artificial heart valve sample images with pre-delineated and labeled edges and ROIs of each leaflet 510 can be used to extract the ROIs and uniformly adjust their sizes to a preset size for use as samples for training the segmentation network. The preset size includes, but is not limited to, 224×224. The size of the preset size depends on the GPU capacity for training the segmentation network; as the GPU capacity increases, the preset size can be increased. It should be noted that, as those skilled in the art will understand, before segmenting each of the regions of interest of the leaflets 510 using the trained segmentation network, the size of each region of interest of the leaflets 510 needs to be adjusted to a preset size. After segmenting each region of interest of the leaflets 510 adjusted to the preset size using the segmentation network, the size of the segmentation result needs to be adjusted to the original size of the corresponding region of interest of the leaflets 510.

[0151] In one exemplary embodiment, the quality control characteristic parameter is curvature, and the controller 400 is configured to calculate the curvature of the leaflet 510 through the following steps:

[0152] Locate the three vertices of the inscribed triangle of the leaflet 510;

[0153] Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle;

[0154] The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet 510.

[0155] Since the leaflets 510 can only form a complete artificial heart valve if their curvature is similar in their natural downward position, the similarity of curvature among the leaflets 510 is an important evaluation indicator in the quality inspection process of artificial heart valves. For details, please refer to... Figure 4 The diagram illustrates the principle of calculating the curvature of each leaflet 510 according to a specific example of the present invention. Figure 4 As shown, the angle of the vertex of the inscribed triangle of the leaflet 510 can accurately reflect the curvature of the leaflet 510. In the figure, θ1 represents the curvature of the first leaflet 510, θ2 represents the curvature of the second leaflet 510, and θ3 represents the curvature of the first leaflet 510. For each leaflet 510, based on the coordinates of the three vertices of the inscribed triangle of the leaflet 510, the side lengths a, b, and c of the three sides of the inscribed triangle of the leaflet 510 can be calculated. Then, the cosine formula c... 2 =a 2 +b 2 -2ab·cosθ can be used to calculate the vertex angle θ of the inscribed triangle of the leaf 510. It should be noted that, as those skilled in the art will understand, the three black areas in the figure each correspond to a leaf 510. The rectangle outside the first leaf 510 is the smallest bounding rectangle corresponding to that leaf 510; the rectangle outside the second leaf 510 is the smallest bounding rectangle corresponding to that leaf 510; and the rectangle outside the third leaf 510 is the smallest bounding rectangle corresponding to that leaf 510.

[0156] In one exemplary embodiment, the controller 400 is configured to find the three vertices of the inscribed triangle of the leaflet 510 by means of the following steps:

[0157] A rectangular coordinate system is established with the width direction of the image of the artificial heart valve 500 to be tested as the X-axis and the height direction of the image of the artificial heart valve 500 to be tested as the Y-axis.

[0158] Based on the coordinates of each pixel of the leaflet 510 in the Cartesian coordinate system of the image, the lower left and lower right pixels of the leaflet 510 are found as the two lower vertices of the inscribed triangle of the leaflet 510.

[0159] The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point.

[0160] The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate.

[0161] Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the area of ​​the leaflet 510 horizontally until the leaflet 510 areas explored at both ends of the horizontal line merge into a continuous area. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet 510 to find the upper vertex of the inscribed triangle of the leaflet 510.

[0162] For details, please refer to Figure 5 The diagram illustrates the exploration process of the upper vertex according to an embodiment of the present invention. Figure 5 As shown in the figure, in this embodiment, the coordinate system XOY is the established image rectangular coordinate system, that is, in Figure 5 In the illustrated embodiment, an image Cartesian coordinate system is established with the upper left corner of the image of the artificial heart valve 500 to be tested as the origin. Point A in the figure is the explored lower left vertex (the pixel with the largest Y-coordinate on the left), and point B in the figure is the explored lower right vertex (the pixel with the largest Y-coordinate on the right). The upper vertex of lower vertex A and lower vertex B refers to the one with the smaller Y-coordinate. Since the Y-coordinate of lower vertex A is smaller than that of lower vertex B, the position of lower vertex A is the initial position of the horizontal exploration point. The position of point D in the figure is the initial position of the anchor point, and the straight line between points A and D is the horizontal line at the initial position. Figure 5 As shown, the horizontal line is a straight line parallel to the X-axis. During the upward movement of the horizontal line along the Y-axis from its initial position (with the anchor point moving accordingly), each end of the horizontal line should explore a continuous leaflet 510 region. When the two leaflet 510 regions explored at the left and right ends of the horizontal line merge into one continuous region, it indicates that the top of the inner curve of the leaflet 510 has been explored, that is, the position of the upper vertex C of the inscribed triangle of the leaflet 510 has been explored. It should be noted that, as those skilled in the art will understand, Figure 5Using the upper left corner of the image of the artificial heart valve 500 to be tested as the origin of the image rectangular coordinate system is merely an illustrative example and does not constitute a limitation of the present invention. In some other embodiments, the upper right corner of the image of the artificial heart valve 500 to be tested can also be used as the origin of the image rectangular coordinate system. In this case, the one located above the two lower vertices is also the one with the smaller Y-coordinate. Alternatively, the lower left or lower right corner of the image of the artificial heart valve 500 to be tested can also be used as the origin of the image rectangular coordinate system. In this case, the one located above the two lower vertices is also the one with the larger Y-coordinate.

[0163] In one exemplary embodiment, the controller 400 is configured to obtain the quality control results of the artificial heart valve 500 under test through the following steps:

[0164] Based on the curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in curvature are identified as the two target leaflets.

[0165] Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold.

[0166] If so, the artificial heart valve 500 to be tested is deemed unqualified.

[0167] Specifically, the difference in curvature between two leaflets 510 can be calculated pairwise, and the two leaflets 510 with the largest absolute value of the difference in curvature are the two target leaflets with the largest difference in curvature. Figure 4 For example, assuming the artificial heart valve 500 to be tested includes three leaflets 510, and the curvatures of these three leaflets 510 are θ1, θ2, and θ3 respectively, then |θ1-θ2|, |θ2-θ3|, and |θ3-θ1| are calculated respectively. If |θ1-θ2| is the largest, then the two leaflets 510 corresponding to θ1 and θ2 are taken as target leaflets. Furthermore, if |θ1-θ2| is greater than the curvature threshold, then the artificial heart valve 500 to be tested is determined to be unsuitable. If |θ2-θ3| is the largest, then the two leaflets 510 corresponding to θ2 and θ3 are taken as target leaflets. Further, if |θ2-θ3| is greater than the curvature threshold, then the artificial heart valve 500 to be tested is determined to be unqualified. If |θ3-θ1| is the largest, then the two leaflets 510 corresponding to θ1 and θ3 are taken as target leaflets. Further, if |θ3-θ1| is greater than the curvature threshold, then the artificial heart valve 500 to be tested is determined to be unqualified. Specifically, the relevant content on how to determine the curvature threshold can be referred to in the relevant description below, and will not be repeated here.

[0168] In one exemplary embodiment, the image acquisition device 300 is configured to acquire a first image of the artificial heart valve under test when the smooth surfaces of the leaflets 510 of the artificial heart valve under test are naturally drooping and / or acquire a second image of the artificial heart valve under test when the rough surfaces of the leaflets 510 of the artificial heart valve under test are naturally drooping.

[0169] The controller 400 is configured to recognize the first image of the artificial heart valve to be tested, to identify each leaflet 510 of the artificial heart valve 500 to be tested, and to calculate a first quality inspection feature parameter for each leaflet 510, and to determine whether the smooth surface of the artificial heart valve 500 to be tested is qualified based on the first quality inspection feature parameter of each leaflet 510; and / or

[0170] The controller 400 is configured to recognize the second image of the artificial heart valve to be tested, to identify each leaflet 510 of the artificial heart valve 500 to be tested, to calculate the second quality inspection feature parameters of each leaflet 510, and to determine whether the rough surface of the artificial heart valve 500 to be tested is qualified based on the second quality inspection feature parameters of each leaflet 510.

[0171] Specifically, the smooth surface represents the flexibility of the leaflet 510, while the rough surface represents the hardness of the leaflet 510. Thus, by acquiring a first image of the artificial heart valve 500 under test with the smooth surfaces of each leaflet 510 naturally drooping, it can be determined whether the flexibility of the artificial heart valve 500 under test is up to standard. By acquiring a second image of the artificial heart valve 500 under test with the rough surfaces of each leaflet 510 naturally drooping, it can be determined whether the hardness of the artificial heart valve 500 under test is up to standard.

[0172] Furthermore, since a complete artificial heart valve can only be formed when the flexibility and hardness of each leaflet 510 are similar (that is, when the curvature of the smooth surface and the curvature of the rough surface are similar), the controller 400 is preferably configured to determine that the artificial heart valve 500 under test is qualified only when both the smooth surface and the rough surface of the artificial heart valve 500 under test are qualified.

[0173] It should be noted that, as those skilled in the art will understand, the relevant descriptions above regarding how to identify the first image of the artificial heart valve to be tested in order to identify each leaflet 510 of the artificial heart valve 500 to be tested, and how to identify the second image of the artificial heart valve to be tested in order to identify each leaflet 510 of the artificial heart valve 500 to be tested, can be found here, and will not be repeated here.

[0174] In one exemplary embodiment, the controller 400 is configured to determine whether the smooth surface of the artificial heart valve 500 under test is acceptable based on a first curvature of each of the leaflets 510; and / or

[0175] The controller 400 is configured to determine whether the rough surface of the artificial heart valve 500 to be tested is qualified based on the second curvature of each of the leaflets 510.

[0176] For details on how to calculate the first curvature and the second curvature of each of the leaflets 510, please refer to the relevant description above, which will not be repeated here.

[0177] Furthermore, the controller 400 is configured to determine whether the smooth surface of the artificial heart valve 500 to be tested is qualified through the following steps:

[0178] Based on the first curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in first curvature are identified as the two first target leaflets.

[0179] Determine whether the absolute value of the difference in the first curvature of the two first target leaflets is greater than the first curvature threshold.

[0180] If so, the smooth surface of the artificial heart valve 500 to be tested is deemed unqualified;

[0181] If not, the smooth surface of the artificial heart valve 500 to be tested is deemed qualified; and / or

[0182] The controller 400 is configured to determine whether the rough surface of the artificial heart valve 500 to be tested is qualified through the following steps:

[0183] Based on the second curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in second curvature are identified as the two second target leaflets.

[0184] Determine whether the absolute value of the difference in the second curvature of the two second target leaflets is greater than the second curvature threshold;

[0185] If so, the rough surface of the artificial heart valve 500 to be tested is deemed unqualified;

[0186] If not, the rough surface of the artificial heart valve 500 to be tested is deemed qualified.

[0187] Specifically, the first curvature threshold and the second curvature threshold can be obtained through statistical analysis of experimental data. Please refer to [reference needed]. Figures 6 to 8,in Figure 6 A schematic diagram of the distribution of the maximum first curvature difference of a qualified artificial heart valve with a smooth surface is given (the horizontal axis represents the maximum first curvature difference); Figure 7 A schematic diagram of the distribution of the maximum second curvature difference of a qualified artificial heart valve with a rough surface is given (the horizontal axis represents the maximum second curvature difference). Figure 8 A schematic diagram illustrating the distribution of the maximum first curvature difference in artificial heart valves with defective smooth surfaces is provided (the horizontal axis represents the maximum first curvature difference). For example... Figures 6 to 8 As shown, during the experiment, a total of 683 images of tricuspid valves with either smooth or rough surfaces were collected, along with 26 images of tricuspid valves with unsmooth surfaces. By statistically analyzing the maximum first curvature difference (the absolute value of the difference in the first curvature of the first target leaflet) and the maximum second curvature difference (the absolute value of the difference in the second curvature of the second target leaflet) calculated from these 683 images of tricuspid valves with either smooth or rough surfaces, the following results can be obtained: Figure 6 and Figure 7 The distribution diagram shown; the maximum first curvature difference calculated from these 26 images of substandard artificial heart valves with smooth surfaces can be statistically analyzed to obtain... Figure 8 The distribution map shown. Figure 6 As shown, the maximum first curvature difference of a qualified artificial heart valve with a smooth surface is generally less than 30°; for example... Figure 7 As shown, the maximum second curvature difference of qualified rough-surfaced artificial heart valves is generally less than 30°; Figure 8As shown, the maximum first curvature difference of unqualified artificial heart valves with non-smooth surfaces is generally greater than 30°. Therefore, the first curvature threshold can be set to 30°, and the second curvature threshold can also be set to 30°. It should be noted that, as those skilled in the art will understand, the first curvature threshold of 30° and the second curvature threshold of 30° are merely illustrative examples. In practical applications, the first curvature threshold and the second curvature threshold can also be other values, and the first curvature threshold and the second curvature threshold may be equal or unequal. Furthermore, it should be noted that, as those skilled in the art will understand, the first curvature threshold can be determined based on the largest first curvature difference among all qualified artificial heart valves with smooth surfaces and the smallest first curvature difference among all unqualified artificial heart valves with smooth surfaces; similarly, the second curvature threshold can be determined based on the largest second curvature difference among all qualified artificial heart valves with rough surfaces and the smallest second curvature difference among all unqualified artificial heart valves with rough surfaces.

[0188] In one exemplary embodiment, the controller 400 is further configured to output a notification message indicating that the valve leaflet 510 is defective when the artificial heart valve 500 under test is detected to be defective.

[0189] Therefore, by outputting a prompt message indicating the defective leaflet 510 when the artificial heart valve 500 to be tested is deemed unqualified, users can quickly locate the unqualified leaflet 510 and replace it with a new leaflet 510 to form a new artificial heart valve 500 to be tested. Then, an image of the new artificial heart valve 500 to be tested is acquired and retested until the test result is qualified, which helps to increase the production volume of artificial heart valves and reduce production costs.

[0190] Specifically, if the absolute value of the difference in curvature between the two target leaflets (first target leaflet / second target leaflet) (first curvature / second curvature) is greater than the curvature threshold (first curvature threshold / second curvature threshold), then the one with the larger absolute value of the difference in curvature between the two target leaflets (first target leaflet / second target leaflet) and the non-target leaflet is determined to be an unqualified leaflet 510.

[0191] Please continue to refer to this. Figure 2 ,like Figure 2As shown, in an exemplary embodiment, the artificial heart valve quality inspection system provided by the present invention further includes an input device 710 and an output device 720 communicatively connected to the controller 400. The input device 710 includes, but is not limited to, a keyboard and a mouse. The functions of the input device 710 include, but are not limited to, receiving user naming operations on the image of the artificial heart valve to be inspected and confirmation operations on the image acquisition device 300's photographing action. The output device 720 includes, but is not limited to, a display and a projector. The functions of the output device 720 include, but are not limited to, displaying the image of the artificial heart valve 500 to be inspected, the file name of the image of the artificial heart valve 500 to be inspected, the leaflet 510 identification results of the image of the artificial heart valve 500 to be inspected, the quality inspection feature parameters of each leaflet 510 in the image of the artificial heart valve 500 to be inspected, and the quality inspection results of the artificial heart valve 500 to be inspected corresponding to the image of the artificial heart valve 500 to be inspected.

[0192] Corresponding to the aforementioned artificial heart valve quality inspection system, this invention also provides an artificial heart valve quality inspection method, please refer to [reference needed]. Figure 9 The diagram illustrates a flowchart of an artificial heart valve quality inspection method according to an embodiment of the present invention. Figure 9 As shown, the artificial heart valve quality inspection method provided by the present invention includes the following steps:

[0193] Step S100: Obtain an image of the artificial heart valve 500 to be tested.

[0194] Step S200: Recognize the image of the artificial heart valve 500 to be tested, so as to identify each leaflet 510 of the artificial heart valve 500 to be tested.

[0195] Step S300: Calculate the quality inspection characteristic parameters of each of the leaflets 510.

[0196] Step S400: Obtain the quality inspection results of the artificial heart valve 500 to be tested based on the quality inspection characteristic parameters of each leaflet 510.

[0197] Therefore, the artificial heart valve quality inspection method provided by this invention can realize the automatic detection of artificial heart valve quality, effectively improve the accuracy of artificial heart valve quality inspection results, and reduce the quality inspection cost of artificial heart valves.

[0198] In one exemplary embodiment, the quality control method further includes, prior to identifying the image of the artificial heart valve 500 to be tested:

[0199] Determine whether a curtain 620 exists in the image of the artificial heart valve 500 to be tested;

[0200] If so, the identification of the image of the artificial heart valve 500 to be detected includes:

[0201] Machine learning algorithms are used to identify the image of the artificial heart valve 500 to be detected;

[0202] If not, then the identification of the image of the artificial heart valve 500 to be detected includes:

[0203] A deep learning algorithm is used to identify the image of the artificial heart valve 500 to be detected.

[0204] In one exemplary embodiment, the step of using a machine learning algorithm to identify the image of the artificial heart valve 500 to be detected includes:

[0205] A machine learning algorithm with binarization processing is used to identify the image of the artificial heart valve 500 to be detected.

[0206] In one exemplary embodiment, the step of using a deep learning algorithm to identify the image of the artificial heart valve 500 to be detected includes:

[0207] A deep learning algorithm is used to identify the image of the artificial heart valve 500 to be detected by first performing target detection on the image of the artificial heart valve 500 to detect the region of interest of each leaflet 510, and then segmenting the leaflet 510 into the region of interest of each leaflet 510.

[0208] In one exemplary embodiment, the quality inspection characteristic parameter is curvature;

[0209] The curvature of the leaflet 510 is calculated using the following steps:

[0210] Locate the three vertices of the inscribed triangle of the leaflet 510;

[0211] Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle;

[0212] The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet 510.

[0213] In one exemplary embodiment, finding the three vertices of the inscribed triangle of the leaflet 510 includes:

[0214] A rectangular coordinate system is established with the width direction of the image of the artificial heart valve 500 to be tested as the X-axis and the height direction of the image of the artificial heart valve 500 to be tested as the Y-axis.

[0215] Based on the coordinates of each pixel of the leaflet 510 in the Cartesian coordinate system of the image, the lower left and lower right pixels of the leaflet 510 are found as the two lower vertices of the inscribed triangle of the leaflet 510.

[0216] The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point.

[0217] The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate.

[0218] Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the area of ​​the leaflet 510 horizontally until the leaflet 510 areas explored at both ends of the horizontal line merge into a continuous area. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet 510 to find the upper vertex of the inscribed triangle of the leaflet 510.

[0219] In one exemplary embodiment, obtaining the quality inspection result of the artificial heart valve 500 under test based on the curvature of each of the leaflets 510 includes:

[0220] Based on the curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in curvature are identified as the two target leaflets.

[0221] Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold.

[0222] If so, the artificial heart valve 500 to be tested is deemed unqualified.

[0223] In one exemplary embodiment, acquiring an image of the artificial heart valve 500 to be tested includes:

[0224] Acquire a first image of the artificial heart valve 500 under test when the smooth surfaces of each leaflet 510 are naturally drooping; and / or

[0225] Acquire a second image of the artificial heart valve 500 under test when the rough surfaces of each leaflet 510 are naturally drooping.

[0226] The step of recognizing the image of the artificial heart valve 500 to be tested, in order to identify each leaflet 510 of the artificial heart valve 500 to be tested, includes:

[0227] The first image of the artificial heart valve to be tested is identified to identify each leaflet 510 of the artificial heart valve 500 to be tested; and / or

[0228] The image of the second artificial heart valve to be tested is identified to identify each leaflet 510 of the artificial heart valve 500 to be tested.

[0229] The calculation of the quality inspection characteristic parameters of each of the leaflets 510 includes:

[0230] Calculate the first quality control characteristic parameters of each of the said leaflets 510; and / or

[0231] Calculate the second quality inspection characteristic parameters of each of the leaflets 510.

[0232] The process of obtaining the quality inspection results of the artificial heart valve 500 under test based on the quality inspection characteristic parameters of each of the valve leaflets 510 includes:

[0233] The smoothness of the artificial heart valve 500 to be tested is determined based on the first quality inspection characteristic parameters of each of the leaflets 510; and / or

[0234] The roughness of the artificial heart valve 500 to be tested is determined based on the second quality inspection characteristic parameters of each of the leaflets 510.

[0235] In one exemplary embodiment, the first quality inspection feature parameter is a first curvature; the second quality inspection feature parameter is a second curvature.

[0236] The step of determining whether the smooth surface of the artificial heart valve 500 to be tested is qualified based on the first quality inspection characteristic parameters of each of the valve leaflets 510 includes:

[0237] Based on the first curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in first curvature are identified as the two first target leaflets.

[0238] Determine whether the absolute value of the difference in the first curvature of the two first target leaflets is greater than the first curvature threshold.

[0239] If so, the smooth surface of the artificial heart valve 500 to be tested is deemed unqualified;

[0240] If not, the smooth surface of the artificial heart valve 500 to be tested is deemed qualified.

[0241] The step of determining whether the roughness of the artificial heart valve 500 to be tested is qualified based on the second quality inspection characteristic parameters of each of the valve leaflets 510 includes:

[0242] Based on the second curvature of each leaflet 510 of the artificial heart valve 500 to be tested, the two leaflets 510 with the largest difference in second curvature are identified as the two second target leaflets.

[0243] Determine whether the absolute value of the difference in the second curvature of the two second target leaflets is greater than the second curvature threshold;

[0244] If so, the rough surface of the artificial heart valve 500 to be tested is deemed unqualified;

[0245] If not, the rough surface of the artificial heart valve 500 to be tested is deemed qualified.

[0246] In one exemplary embodiment, the quality inspection method further includes:

[0247] When the artificial heart valve 500 under test is found to be unqualified, a prompt message indicating that the valve leaflet 510 is unqualified is output.

[0248] Based on the same inventive concept, the present invention also provides an electronic device, please refer to... Figure 10 A block diagram illustrating an embodiment of the electronic device provided by the present invention is shown. Figure 10 As shown, the electronic device includes a processor 810 and a memory 830. The memory 830 stores a computer program. When the computer program is executed by the processor 810, it implements the artificial heart valve quality inspection method described above. Since the electronic device provided by this invention and the artificial heart valve quality inspection method provided by this invention belong to the same inventive concept, the electronic device provided by this invention has all the advantages of the artificial heart valve quality inspection method provided by this invention. Therefore, the beneficial effects of the electronic device provided by this invention will not be elaborated further here.

[0249] like Figure 10 As shown, the electronic device also includes a communication interface 820 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The communication bus 840 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 840 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 820 is used for communication between the above-mentioned electronic device and other devices.

[0250] The processor 810 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 810 is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0251] The memory 830 can be used to store the computer program, and the processor 810 implements various functions of the electronic device by running or executing the computer program stored in the memory 830 and calling the data stored in the memory 830.

[0252] The memory 830 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0253] This invention also provides a readable storage medium storing a computer program that, when executed by a processor, can implement the artificial heart valve quality inspection method described above. Since the readable storage medium provided by this invention and the artificial heart valve quality inspection method provided by this invention belong to the same inventive concept, the readable storage medium provided by this invention possesses all the advantages of the artificial heart valve quality inspection method provided by this invention. Therefore, the beneficial effects of the readable storage medium provided by this invention will not be elaborated further here.

[0254] The readable storage medium of embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0255] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0256] It should be noted that, as those skilled in the art will understand, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0257] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0258] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0259] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for quality inspection of artificial heart valves, characterized in that, include: Acquire images of the artificial heart valve to be tested; The image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested; Calculate the quality inspection characteristic parameters of each of the aforementioned leaflets; The quality inspection results of the artificial heart valve to be tested are obtained based on the quality inspection characteristic parameters of each of the valve leaflets. The quality inspection characteristic parameter is curvature; The curvature of the leaflet is calculated using the following steps: Locate the three vertices of the inscribed triangle of the leaflet; Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle; The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet.

2. The method for quality inspection of artificial heart valves according to claim 1, characterized in that, Before recognizing the image of the artificial heart valve to be tested, the quality inspection method further includes: Determine whether a curtain is present in the image of the artificial heart valve to be tested; If so, the identification of the image of the artificial heart valve to be detected includes: Machine learning algorithms are used to identify the image of the artificial heart valve to be detected; If not, then the identification of the image of the artificial heart valve to be detected includes: A deep learning algorithm is used to identify the image of the artificial heart valve to be detected.

3. The method for quality inspection of artificial heart valves according to claim 2, characterized in that, The determination of whether a curtain exists in the image of the artificial heart valve to be detected includes: The image of the artificial heart valve to be tested is converted from the RGB channel to the HSV channel to obtain an HSV channel image; Traverse every pixel in the HSV channel image to find the first target pixel whose H component is in a first preset range, whose S component is in a second preset range, and whose V component is in a third preset range. Determine whether the ratio between the number of the first target pixels and the total number of pixels in the HSV channel image is greater than or equal to a ratio threshold. If yes, it is determined that a curtain exists in the image of the artificial heart valve to be tested; otherwise, it is determined that no curtain exists in the image of the artificial heart valve to be tested.

4. The method for quality inspection of artificial heart valves according to claim 1, characterized in that, Finding the three vertices of the inscribed triangle of the leaflet includes: A rectangular coordinate system is established with the width direction of the image of the artificial heart valve to be tested as the X-axis and the height direction of the image of the artificial heart valve to be tested as the Y-axis. Based on the coordinates of each pixel of the petal in the Cartesian coordinate system of the image, the lower left and lower right pixels of the petal are found as the two lower vertices of the inscribed triangle of the petal. The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point. The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate. Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the leaflet region horizontally until the leaflet regions explored at both ends of the horizontal line merge into a continuous region. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet to find the upper vertex of the inscribed triangle of the leaflet.

5. The method for quality inspection of artificial heart valves according to claim 1, characterized in that, The quality inspection results of the artificial heart valve under test are obtained based on the curvature of each leaflet, including: Based on the curvature of each leaflet of the artificial heart valve to be tested, the two leaflets with the largest difference in curvature are identified as the two target leaflets. Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold. If so, the artificial heart valve to be tested is deemed unqualified.

6. The method for quality inspection of artificial heart valves according to claim 1, characterized in that, The acquisition of images of the artificial heart valve to be tested includes: Acquire a first image of the artificial heart valve under test when the smooth surfaces of each leaflet are naturally drooping and / or acquire a second image of the artificial heart valve under test when the rough surfaces of each leaflet are naturally drooping. The step of recognizing the image of the artificial heart valve to be tested, in order to identify each leaflet of the artificial heart valve to be tested, includes: The first image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested; and / or the second image of the artificial heart valve to be tested is identified to identify each leaflet of the artificial heart valve to be tested; The calculation of the quality inspection characteristic parameters of each of the leaflets includes: Calculate the first quality inspection characteristic parameter of each of the said leaflets; and / or calculate the second quality inspection characteristic parameter of each of the said leaflets; The step of obtaining the quality inspection results of the artificial heart valve under test based on the quality inspection characteristic parameters of each of the valve leaflets includes: The smooth surface of the artificial heart valve to be tested is determined to be qualified based on the first quality inspection characteristic parameter of each of the valve leaflets; and / or the rough surface of the artificial heart valve to be tested is determined to be qualified based on the second quality inspection characteristic parameter of each of the valve leaflets.

7. The method for quality inspection of artificial heart valves according to claim 1, characterized in that, The method further includes: When the artificial heart valve to be tested is found to be unqualified, a notification message indicating the unqualified valve leaflet is sent.

8. A quality inspection system for artificial heart valves, characterized in that, It includes a valve fixation device, an image acquisition device, and a controller. The image acquisition device is disposed opposite to the valve fixation device, and the image acquisition device is communicatively connected to the controller. The valve fixation device is configured to fix the artificial heart valve to be tested, and the artificial heart valve to be tested includes multiple leaflets; The image acquisition device is configured to acquire an image of the artificial heart valve to be tested and transmit the acquired image of the artificial heart valve to be tested to the controller; The controller is configured to recognize the image of the artificial heart valve to be tested, to identify each leaflet of the artificial heart valve to be tested, to calculate the quality inspection feature parameters of each leaflet, and to obtain the quality inspection result of the artificial heart valve to be tested based on the quality inspection feature parameters of each leaflet. The quality inspection characteristic parameter is curvature, and the controller is configured to calculate the curvature of the leaflet through the following steps: Locate the three vertices of the inscribed triangle of the leaflet; Based on the position information of the three vertices, calculate the angle of the vertex angle of the inscribed triangle; The angle of the vertex of the inscribed triangle is taken as the curvature of the leaflet.

9. The artificial heart valve quality inspection system according to claim 8, characterized in that, The valve fixing device includes a first lifting platform and a placement module installed on the first lifting platform. The placement module includes a plurality of parallel placement rods, each placement rod corresponding to a valve leaflet. The front end of each placement rod is suspended in the air to fix the valve leaflet.

10. The artificial heart valve quality inspection system according to claim 8, characterized in that, The image acquisition device includes a second lifting platform and a camera mounted on the second lifting platform. The camera is used to acquire images of the artificial heart valve to be tested and transmit the acquired images of the artificial heart valve to be tested to the controller.

11. The artificial heart valve quality inspection system according to claim 8, characterized in that, The artificial heart valve quality inspection system also includes a linear guide rail with graduations. The valve fixation device is located at one end of the linear guide rail, and the image acquisition device is located at the other end of the linear guide rail. Both the valve fixation device and the image acquisition device can reciprocate on the linear guide rail.

12. The artificial heart valve quality inspection system according to claim 8, characterized in that, The artificial heart valve quality inspection system also includes a screen, and the valve fixing device is located between the screen and the image acquisition device; The controller is further configured to determine whether a curtain exists in the image of the artificial heart valve to be detected. If so, a machine learning algorithm is used to identify the image of the artificial heart valve to be detected; otherwise, a deep learning algorithm is used to identify the image of the artificial heart valve to be detected.

13. The artificial heart valve quality inspection system according to claim 8, characterized in that, The controller is configured to obtain the quality inspection results of the artificial heart valve under test through the following steps: Based on the curvature of each leaflet of the artificial heart valve to be tested, the two leaflets with the largest difference in curvature are identified as the two target leaflets. Determine whether the absolute value of the difference in curvature between the two target leaflets is greater than a curvature threshold. If so, the artificial heart valve to be tested is deemed unqualified.

14. The artificial heart valve quality inspection system according to claim 8, characterized in that, The controller is configured to find the three vertices of the inscribed triangle of the leaflet by the following steps: A rectangular coordinate system is established with the width direction of the image of the artificial heart valve to be tested as the X-axis and the height direction of the image of the artificial heart valve to be tested as the Y-axis. Based on the coordinates of each pixel of the petal in the Cartesian coordinate system of the image, the lower left and lower right pixels of the petal are found as the two lower vertices of the inscribed triangle of the petal. The position of the upper of the two lower vertices is taken as the initial position of the horizontal exploration point. The initial position of the anchor point is determined by taking the average of the X coordinates of the two lower vertices as the target X coordinate and the Y coordinate of the horizontal exploration point as the target Y coordinate. Using the straight line where the horizontal exploration point and the anchor point are located as the horizontal line, move the horizontal line upward along the Y-axis to explore the leaflet region horizontally until the leaflet regions explored at both ends of the horizontal line merge into a continuous region. Then, take the position of the anchor point as the position of the upper vertex of the inscribed triangle of the leaflet to find the upper vertex of the inscribed triangle of the leaflet.

15. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the artificial heart valve quality inspection method according to any one of claims 1 to 7.

16. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the artificial heart valve quality inspection method according to any one of claims 1 to 7.

Images