Method, device, electronic device and storage medium for positioning animal retinal injection point

Abstract

The present application provides a method, device, electronic device and storage medium for positioning animal retinal injection points, including: performing image processing on retinal images based on a watershed algorithm to segment the optic disc image area and multiple blood vessel image areas around it in the retinal image; analyzing multiple blood vessel image areas and optic disc image areas to determine the target injection area of ​​the microneedle; determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring in the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the real-time retinal image to determine the injection point at the preset injection depth of the target injection area where the microneedle reaches; evaluating the injection point to determine whether the injection point is the final injection point. The retinal injection point of the mouse can be quickly and accurately determined, providing a guarantee for the subsequent injection of the mouse eye.

Description

Technical Field

[0001] The present application relates to the technical field of eye injection point positioning, and in particular to a method, device, electronic device and storage medium for positioning an animal retinal injection point. Background Art

[0002] Mice are experimental animals with highly similar genotypes to humans and are widely used in medical research, including basic ophthalmic research. At present, during microneedle injections into the mouse retina, operators directly determine the injection point based on their work experience. Determining the injection point based on work experience will lead to inaccurate positioning of the retinal injection point, which in turn makes it impossible to accurately inject drugs into the mouse eye. Therefore, how to quickly and accurately determine the retinal injection point has become a technical issue that cannot be underestimated. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a method, device, electronic device and storage medium for locating animal retinal injection points, so as to quickly and accurately determine the retinal injection points of mice and provide guarantee for subsequent injections of mouse eyes.

[0004] The present application embodiment provides a method for locating an animal retinal injection point, the method comprising:

[0005] Acquire a retinal image of a mouse, perform image processing on the retinal image based on a watershed algorithm, and segment an optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a state where the eyeball of the mouse is not displaced;

[0006] Analyzing the plurality of blood vessel image regions and optic disc image regions to determine a target injection region for the microneedle;

[0007] Determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring while controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area;

[0008] The injection point is evaluated to determine an evaluation result, and whether the injection point is a final injection point is determined based on a preset expected result and the evaluation result.

[0009] In a possible implementation manner, analyzing the plurality of blood vessel image regions and optic disc image regions to determine the target injection region of the microneedle includes:

[0010] Processing the plurality of blood vessel image regions based on a morphological analysis method and a region growing algorithm to identify a plurality of closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each of the blood vessel image regions;

[0011] A morphological feature analysis is performed on each of the closed image regions, and a closed image region with the largest area and relatively far away from the optic disc image region is screened out from the multiple closed image regions, and the closed image region is used as the target injection region of the microneedle.

[0012] In a possible implementation manner, determining the puncture angle information of the microneedle based on the target injection area includes:

[0013] Analyze the edge features and blood vessel distribution density in the target injection area to determine the center point of the target injection area;

[0014] Based on the three-dimensional geometric analysis method, the line connecting the center point of the target injection area and the center point of the eyeball and the depth information of the retinal image are calculated to determine the puncture angle information of the microneedle while meeting the preset puncture requirements.

[0015] In a possible implementation, the correction of the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area includes:

[0016] Performing image matching between the real-time injection area in the real-time retinal image and the target injection area, and if the matching is unsuccessful, determining the offset between the real-time injection area and the target injection area;

[0017] Adjusting the insertion direction of the microneedle in real time based on the offset, and determining the adjusted insertion direction;

[0018] The injection point is determined based on the adjusted needle insertion direction reaching a preset injection depth in the target injection area.

[0019] In a possible implementation manner, evaluating the injection point to determine an evaluation result, and determining whether the injection point is a final injection point based on a preset expected result and the evaluation result, includes:

[0020] Evaluating the injection point in terms of safety, shortest path to the injection point, and avoiding vascular damage, and determining the evaluation result;

[0021] Detecting whether the evaluation result meets the expected result;

[0022] If yes, then determining the retinal injection point as the final retinal injection point;

[0023] If not, it is determined that the retinal injection point is not the final retinal injection point.

[0024] In a possible implementation manner, after determining that the retinal injection point is not the final retinal injection point, the positioning method further includes:

[0025] The insertion direction of the microneedle is readjusted to determine a new injection point.

[0026] The present application also provides a device for positioning an animal retinal injection point, the device comprising:

[0027] An image segmentation module, used for acquiring a retinal image of a mouse, performing image processing on the retinal image based on a watershed algorithm, and segmenting an optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a mouse when the eyeball is not deviated;

[0028] An injection area determination module, used for analyzing the plurality of blood vessel image areas and optic disc image areas to determine a target injection area for the microneedle;

[0029] An injection point determination module, for determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring during the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image, to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area;

[0030] The injection point evaluation module is used to evaluate the injection point to determine an evaluation result, and determine whether the injection point is the final injection point based on a preset expected result and the evaluation result.

[0031] In a possible implementation manner, when the injection area determination module is used to analyze the plurality of blood vessel image areas and the optic disc image area to determine the target injection area of ​​the microneedle, the injection area determination module is specifically used to:

[0032] Processing the plurality of blood vessel image regions based on a morphological analysis method and a region growing algorithm to identify a plurality of closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each of the blood vessel image regions;

[0033] A morphological feature analysis is performed on each of the closed image regions, and a closed image region with the largest area and relatively far away from the optic disc image region is screened out from the multiple closed image regions, and the closed image region is used as the target injection region of the microneedle.

[0034] An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for locating the animal retinal injection point as described above are performed.

[0035] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for locating an animal retinal injection point as described above are executed.

[0036] The present application provides a method, device, electronic device and storage medium for positioning an animal retinal injection point. The positioning method includes: obtaining a mouse retinal image, performing image processing on the retinal image based on a watershed algorithm, and segmenting the optic disc image area and multiple blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to the mouse eyeball when it is not offset; analyzing multiple blood vessel image areas and optic disc image areas to determine the target injection area of ​​the microneedle; determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring in the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area; evaluating the injection point to determine the evaluation result, and determining whether the injection point is the final injection point based on the preset expected result and the evaluation result. The retinal injection point of the mouse is quickly and accurately determined, providing a guarantee for the subsequent injection of the mouse eye.

[0037] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A flow chart of a method for locating an animal retinal injection point provided in an embodiment of the present application;

[0040] Figure 2 This is one of the structural schematic diagrams of a device for locating an animal retinal injection point provided in an embodiment of the present application;

[0041] Figure 3 The second structural schematic diagram of a device for locating an animal retinal injection point provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0044] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0045] In order to enable those skilled in the art to use the contents of this application, the following implementation is given in combination with the specific application scenario of "locating the injection point of the animal retina". For those skilled in the art, the general principles defined here can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0046] The following methods, systems, electronic devices or computer-readable storage media of the embodiments of the present application can be applied to any scenario where the injection point of the animal retina needs to be located. The embodiments of the present application are not limited to specific application scenarios. Any solution using the method, device, electronic device and storage medium for locating the injection point of the animal retina provided by the embodiments of the present application is within the scope of protection of the present application.

[0047] First, the application scenarios to which the present application is applicable are introduced. The present application can be applied to the technical field of eye injection point positioning.

[0048] Studies have found that mice, as experimental animals with highly similar genotypes to humans, are widely used in medical research, including basic ophthalmic research. At present, during microneedle injections into the mouse retina, operators directly determine the injection point based on their work experience. Determining the injection point based on work experience will lead to inaccurate positioning of the retinal injection point, which in turn makes it impossible to accurately inject drugs into the mouse eye. Therefore, how to quickly and accurately determine the retinal injection point has become a technical issue that cannot be underestimated.

[0049] Based on this, an embodiment of the present application provides a method for locating an animal retinal injection point, which can quickly and accurately determine the retinal injection point of a mouse, thereby providing a guarantee for subsequent injections of the mouse eye.

[0050] See also Figure 1 , Figure 1 This is a flow chart of a method for locating an animal retinal injection point provided in an embodiment of the present application. Figure 1 As shown in , the positioning method provided in the embodiment of the present application includes:

[0051] S101: Obtain a retinal image of a mouse, perform image processing on the retinal image based on a watershed algorithm, and segment an optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a state where the eyeball of the mouse is not deviated.

[0052] In this step, a retinal image of a mouse is acquired, and the retinal image is processed according to a watershed algorithm to segment the optic disc image area and a plurality of blood vessel image areas around the retinal image.

[0053] Here, the mouse is fixed on the operating table, a high-resolution microscope system is aimed at the mouse's eye area, and a high-definition camera is used to obtain local images of the eye. To ensure image quality, the high-resolution microscope system will automatically adjust the lighting and focus to obtain a clear retinal image.

[0054] First, the image is preprocessed to enhance the image contrast, and the captured image is processed using the watershed algorithm. The watershed algorithm automatically segments the optic disc and blood vessels of the fundus based on the image gradient, and then calculates the image gradient, regards the image as terrain, and divides the image into multiple regions by simulating the filling process of water flow. Based on the marked image, the optic disc image region and multiple blood vessel image regions around it are segmented.

[0055] S102: Analyze the plurality of blood vessel image regions and optic disc image regions to determine a target injection region of the microneedle.

[0056] In this step, multiple blood vessel image regions and optic disc image regions are analyzed to determine the target injection region of the microneedle.

[0057] In a possible implementation manner, analyzing the plurality of blood vessel image regions and optic disc image regions to determine the target injection region of the microneedle includes:

[0058] A: The multiple blood vessel image regions are processed based on a morphological analysis method and a region growing algorithm to identify multiple closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each blood vessel image region.

[0059] Here, multiple blood vessel image regions are processed according to a morphological analysis method and a region growing algorithm, and multiple closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each blood vessel image region are identified.

[0060] B: Perform morphological feature analysis on each of the closed image regions, select a closed image region with the largest area and relatively far away from the optic disc image region from among the multiple closed image regions, and use the closed image region as the target injection region of the microneedle.

[0061] Here, a morphological feature analysis is performed on each closed image region, and the closed image region with the largest area and relatively far away from the optic disc image region is screened out from multiple closed image regions, and the closed image region with the largest area and relatively far away from the optic disc image region is used as the target injection area of ​​the microneedle.

[0062] In a specific embodiment, a morphological analysis method and a region growing algorithm are used on the segmented image to identify closed image areas surrounded by blood vessels and blood vessels and other fundus organs. By analyzing the morphological features (such as area, shape, position, etc.) of these closed image areas, the area with the largest area and relatively far from the optic disc is selected as the target injection area. This area should avoid the main blood vessel trunk to reduce the risk of bleeding.

[0063] S103: Determine the puncture angle information of the microneedle based on the target injection area, perform real-time monitoring while controlling the microneedle to penetrate the target injection area based on the puncture angle information at the puncture point, correct the insertion direction of the microneedle based on the monitored real-time retinal image, and determine the injection point at which the microneedle reaches the preset injection depth of the target injection area.

[0064] In this step, the puncture angle information of the microneedle is determined according to the target injection area, and real-time monitoring is performed while controlling the microneedle to penetrate the target injection area at the puncture point according to the puncture angle information. The insertion direction of the microneedle is corrected according to the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area.

[0065] Here, the puncture point is the center point of the target injection area.

[0066] Among them, since microneedle puncture may cause a slight deviation of the eyeball and cause the injection area to shift, the needle insertion direction needs to be corrected in real time.

[0067] In a possible implementation manner, determining the puncture angle information of the microneedle based on the target injection area includes:

[0068] a: Analyze the edge features and blood vessel distribution density in the target injection area to determine the center point of the target injection area.

[0069] Here, the edge features and blood vessel distribution density in the target injection area are analyzed to determine the regional center point of the target injection area.

[0070] Among them, by further analyzing the edge characteristics of the region, the density of blood vessel distribution, etc., the center point of the injection area is optimized to ensure the safety of the injection process. The center point of the region is usually selected away from the area with dense blood vessels, and there should be enough area for safe injection.

[0071] b: Based on the three-dimensional geometric analysis method, the line connecting the center point of the target injection area and the center point of the eyeball and the depth information of the retinal image are calculated to determine the puncture angle information of the microneedle while meeting the preset puncture requirements.

[0072] Here, the line connecting the center point of the target injection area and the center point of the eyeball and the depth information of the retinal image are calculated according to the three-dimensional geometric analysis method to determine the puncture angle information of the microneedle while meeting the preset puncture requirements.

[0073] Among them, after determining the target injection area, the microneedle insertion angle needs to be adjusted according to the position of the injection area. First, the line connecting the center point of the target injection area and the center point of the eyeball is calculated, and the puncture angle of the microneedle is determined based on the line. The specific calculation of the angle can be done by a three-dimensional geometric analysis method. According to the relative position of the center point of the area and the geometric center of the eyeball, combined with the depth information in the microscope image, the pitch angle and rotation angle of the microneedle are adjusted to determine the puncture angle information. The puncture angle information usually refers to the angle between the microneedle puncture direction and the surface of the eyeball, ensuring that the microneedle can reach the injection area at a predetermined angle to avoid unnecessary tissue damage.

[0074] Among them, the preset puncture requirement is that the microneedle reaches the injection area at a predetermined angle to avoid unnecessary tissue damage.

[0075] In a possible implementation, the correction of the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area includes:

[0076] (1): Performing image matching between the real-time injection area and the target injection area in the real-time retinal image. If the matching is unsuccessful, determining the offset between the real-time injection area and the target injection area.

[0077] Here, image matching is performed between the real-time injection area and the target injection area in the real-time retinal image. If the matching is unsuccessful, the offset between the real-time injection area and the target injection area is determined.

[0078] (2): Based on the offset, the insertion direction of the microneedle is adjusted in real time to determine the adjusted insertion direction; based on the adjusted insertion direction reaching a preset injection depth of the target injection area, the injection point is determined.

[0079] Here, the insertion direction of the microneedle is adjusted in real time according to the offset, and the adjusted insertion direction is determined. When the adjusted insertion direction reaches a preset injection depth of the target injection area, the injection point is determined.

[0080] In a specific embodiment, since microneedle puncture may cause a slight deviation of the eyeball, the injection area needs to be corrected in real time. Use an image matching algorithm to match the injection area in the current real-time image with the previously set target injection area. If the injection area is found to be offset, the offset is calculated, and the direction and angle of the microneedle are adjusted in real time to realign the injection area with the originally set target injection area. If the offset is too large to be corrected, it is necessary to reselect the injection area and repeat the aforementioned injection area selection and microneedle angle adjustment steps to ensure that the new injection area also meets the requirements for safe injection.

[0081] S104: Evaluate the injection point to determine an evaluation result, and determine whether the injection point is a final injection point based on a preset expected result and the evaluation result.

[0082] In this step, the injection point is evaluated to determine an evaluation result, and whether the injection point is the final injection point is determined based on the preset expected result and the evaluation result.

[0083] In a possible implementation manner, evaluating the injection point to determine an evaluation result, and determining whether the injection point is a final injection point based on a preset expected result and the evaluation result, includes:

[0084] I: The injection point is evaluated in three dimensions: safety, shortest path to the injection point, and avoidance of vascular damage, to determine the evaluation result.

[0085] Here, the injection point is evaluated in three dimensions: safety, shortest path to reach, and avoidance of vascular damage, and the evaluation results are determined.

[0086] The arrival path is the path that the microneedle moves to the operable injection area.

[0087] II: Detecting whether the evaluation result meets the expected result; if so, determining that the retinal injection point is the final retinal injection point; if not, determining that the retinal injection point is not the final retinal injection point.

[0088] Here, it is detected whether the evaluation result meets the expected result; if so, the retinal injection point is determined to be the final retinal injection point; if not, it is determined that the retinal injection point is not the final retinal injection point.

[0089] Among them, the expected results are the shortest path to reach, no blood vessel loss, and high safety.

[0090] In a possible implementation manner, after determining that the retinal injection point is not the final retinal injection point, the positioning method further includes:

[0091] The insertion direction of the microneedle is readjusted to determine a new injection point.

[0092] Here, if the evaluation results are not satisfactory, it is necessary to reselect the injection point and adjust the microneedle.

[0093] In a specific embodiment, after the microneedle reaches the injection area, the injection point is finally evaluated. The evaluation criteria include the safety of the injection point, the shortest path to the injection point, and the effect of avoiding vascular damage. If the evaluation result meets expectations, the point is confirmed as the final injection point, and the injection operation is then performed. If the evaluation result does not meet expectations, the injection point selection and microneedle adjustment need to be re-performed.

[0094] The present application provides a method for locating an animal retinal injection point, the method comprising: obtaining a mouse retinal image, performing image processing on the retinal image based on a watershed algorithm, and segmenting an optic disc image area and multiple blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to the mouse eyeball when it is not offset; analyzing multiple blood vessel image areas and optic disc image areas to determine a target injection area for a microneedle; determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring in the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches a preset injection depth of the target injection area; evaluating the injection point to determine an evaluation result, and determining whether the injection point is the final injection point based on the preset expected result and the evaluation result. The retinal injection point of the mouse can be quickly and accurately determined, providing a guarantee for subsequent injections of the mouse eye.

[0095] See also Figure 2 , Figure 3 , Figure 2 This is one of the structural schematic diagrams of a device for locating an animal retinal injection point provided in an embodiment of the present application; Figure 3 This is a second structural schematic diagram of a device for locating an animal retinal injection point provided in an embodiment of the present application. Figure 2 As shown in , the positioning device 200 includes:

[0096] The image segmentation module 210 is used to obtain a retinal image of a mouse, perform image processing on the retinal image based on a watershed algorithm, and segment the optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a mouse when the eyeball is not shifted;

[0097] An injection area determination module 220 is used to analyze the plurality of blood vessel image areas and optic disc image areas to determine a target injection area of ​​the microneedle;

[0098] An injection point determination module 230 is used to determine the puncture angle information of the microneedle based on the target injection area, perform real-time monitoring during the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correct the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area;

[0099] The injection point evaluation module 240 is used to evaluate the injection point to determine an evaluation result, and determine whether the injection point is the final injection point based on a preset expected result and the evaluation result.

[0100] Furthermore, when the injection area determination module 220 is used to analyze the plurality of blood vessel image areas and the optic disc image area to determine the target injection area of ​​the microneedle, the injection area determination module 220 is specifically used to:

[0101] Processing the plurality of blood vessel image regions based on a morphological analysis method and a region growing algorithm to identify a plurality of closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each of the blood vessel image regions;

[0102] A morphological feature analysis is performed on each of the closed image regions, and a closed image region with the largest area and relatively far away from the optic disc image region is screened out from the multiple closed image regions, and the closed image region is used as the target injection region of the microneedle.

[0103] Furthermore, when the injection point determination module 230 is used to determine the puncture angle information of the microneedle based on the target injection area, the injection point determination module 230 is specifically used to:

[0104] Analyze the edge features and blood vessel distribution density in the target injection area to determine the center point of the target injection area;

[0105] Based on the three-dimensional geometric analysis method, the line connecting the center point of the target injection area and the center point of the eyeball and the depth information of the retinal image are calculated to determine the puncture angle information of the microneedle while meeting the preset puncture requirements.

[0106] Furthermore, when the injection point determination module 230 is used to correct the insertion direction of the microneedle based on the monitored real-time retinal image and determine the injection point at which the microneedle reaches the preset injection depth of the target injection area, the injection point determination module 230 is specifically used to:

[0107] Performing image matching between the real-time injection area in the real-time retinal image and the target injection area, and if the matching is unsuccessful, determining the offset between the real-time injection area and the target injection area;

[0108] Adjusting the insertion direction of the microneedle in real time based on the offset, and determining the adjusted insertion direction;

[0109] The injection point is determined based on the adjusted needle insertion direction reaching a preset injection depth in the target injection area.

[0110] Further, when the injection point evaluation module 240 is used to evaluate the injection point to determine the evaluation result, and to determine whether the injection point is the final injection point based on the preset expected result and the evaluation result, the injection point evaluation module 240 is specifically used to:

[0111] Evaluating the injection point in terms of safety, shortest path to the injection point, and avoiding vascular damage, and determining the evaluation result;

[0112] Detecting whether the evaluation result meets the expected result;

[0113] If yes, then determining the retinal injection point as the final retinal injection point;

[0114] If not, it is determined that the retinal injection point is not the final retinal injection point.

[0115] Further, such as Figure 3 As shown, the positioning device 200 further includes a re-determination module 250, and the re-determination module 250 is used to:

[0116] The insertion direction of the microneedle is readjusted to determine a new injection point.

[0117] The embodiment of the present application provides a positioning device for animal retinal injection points, the positioning device comprising: an image segmentation module, used to obtain a retinal image of a mouse, perform image processing on the retinal image based on a watershed algorithm, and segment an optic disc image area and multiple blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to the mouse eyeball when it is not offset; an injection area determination module, used to analyze the multiple blood vessel image areas and the optic disc image area to determine the target injection area of ​​the microneedle; an injection point determination module, used to determine the puncture angle information of the microneedle based on the target injection area, perform real-time monitoring during the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correct the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area; an injection point evaluation module, used to evaluate the injection point to determine an evaluation result, and determine whether the injection point is the final injection point based on the preset expected result and the evaluation result. It is possible to quickly and accurately determine the injection point of the mouse's retina, providing a guarantee for subsequent injections of the mouse's eyes.

[0118] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0119] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 The steps of the method for locating the animal retinal injection point in the method embodiment shown, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0120] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the method for locating the animal retinal injection point in the method embodiment shown, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0125] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0126] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for locating an animal retinal injection point, characterized in that: The positioning method comprises: Acquire a retinal image of a mouse, perform image processing on the retinal image based on a watershed algorithm, and segment an optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a state where the eyeball of the mouse is not displaced; Analyzing the plurality of blood vessel image regions and optic disc image regions to determine a target injection region for the microneedle; Determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring while controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area; The injection point is evaluated to determine an evaluation result, and whether the injection point is a final injection point is determined based on a preset expected result and the evaluation result.

2. The positioning method according to claim 1, characterized in that: The analyzing the plurality of blood vessel image regions and the optic disc image region to determine the target injection region of the microneedle comprises: Processing the plurality of blood vessel image regions based on a morphological analysis method and a region growing algorithm to identify a plurality of closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each of the blood vessel image regions; A morphological feature analysis is performed on each of the closed image regions, and a closed image region with the largest area and relatively far away from the optic disc image region is screened out from the multiple closed image regions, and the closed image region is used as the target injection region of the microneedle.

3. The positioning method according to claim 1, characterized in that: The step of determining the puncture angle information of the microneedle based on the target injection area includes: Analyze the edge features and blood vessel distribution density in the target injection area to determine the center point of the target injection area; Based on the three-dimensional geometric analysis method, the line connecting the center point of the target injection area and the center point of the eyeball and the depth information of the retinal image are calculated to determine the puncture angle information of the microneedle while meeting the preset puncture requirements.

4. The positioning method according to claim 1, characterized in that: The method of correcting the insertion direction of the microneedle based on the monitored real-time retinal image to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area includes: Performing image matching between the real-time injection area in the real-time retinal image and the target injection area, and if the matching is unsuccessful, determining the offset between the real-time injection area and the target injection area; Adjusting the insertion direction of the microneedle in real time based on the offset, and determining the adjusted insertion direction; The injection point is determined based on the adjusted needle insertion direction reaching a preset injection depth in the target injection area.

5. The positioning method according to claim 1, characterized in that: The step of evaluating the injection point to determine an evaluation result, and determining whether the injection point is a final injection point based on a preset expected result and the evaluation result, includes: Evaluating the injection point in terms of safety, shortest path to the injection point, and avoiding vascular damage, and determining the evaluation result; Detecting whether the evaluation result meets the expected result; If yes, then determining the retinal injection point as the final retinal injection point; If not, it is determined that the retinal injection point is not the final retinal injection point.

6. The positioning method according to claim 5, characterized in that: After determining that the retinal injection point is not the final retinal injection point, the positioning method further includes: The insertion direction of the microneedle is readjusted to determine a new injection point.

7. A device for locating an animal retinal injection point, characterized in that: The positioning device comprises: An image segmentation module, used for acquiring a retinal image of a mouse, performing image processing on the retinal image based on a watershed algorithm, and segmenting an optic disc image area and a plurality of blood vessel image areas around the retinal image; wherein the retinal image is a retinal image corresponding to a mouse when the eyeball is not deviated; An injection area determination module, used for analyzing the plurality of blood vessel image areas and optic disc image areas to determine a target injection area for the microneedle; An injection point determination module, for determining the puncture angle information of the microneedle based on the target injection area, performing real-time monitoring during the process of controlling the microneedle to insert the needle into the target injection area based on the puncture angle information at the puncture point, and correcting the insertion direction of the microneedle based on the monitored real-time retinal image, to determine the injection point at which the microneedle reaches the preset injection depth of the target injection area; The injection point evaluation module is used to evaluate the injection point to determine an evaluation result, and determine whether the injection point is the final injection point based on a preset expected result and the evaluation result.

8. The positioning device according to claim 7, characterized in that: The injection area determination module, when used to analyze the plurality of blood vessel image areas and the optic disc image area to determine the target injection area of ​​the microneedle, includes: Processing the plurality of blood vessel image regions based on a morphological analysis method and a region growing algorithm to identify a plurality of closed image regions surrounded by blood vessels and blood vessels and other fundus organs in each of the blood vessel image regions; A morphological feature analysis is performed on each of the closed image regions, and a closed image region with the largest area and relatively far away from the optic disc image region is screened out from the multiple closed image regions, and the closed image region is used as the target injection region of the microneedle.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to implement the method for locating an animal retinal injection point as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for locating an animal retinal injection point according to any one of claims 1 to 6 is executed.

Images