Adaptive patch sealing method and device based on three-dimensional reconstruction and fluid diffusion simulation

Abstract

The scheme provides an adaptive sealing method and device based on three-dimensional reconstruction and fluid diffusion simulation, comprising: obtaining a three-dimensional terrain distribution map of a pathological sample on a slide, regarding a region containing sample tissue in the three-dimensional terrain distribution map as a core region, regarding the remaining region as a guide region, and regarding a pixel point with a height difference greater than a preset threshold from any adjacent pixel in the core region as a thickness mutation point; obtaining a glue dropping path based on the three-dimensional terrain distribution map, and running a piezoelectric glue dropping valve along the glue dropping path and dropping glue to obtain a glue dropping slide; and obtaining a sealed sample by tilting and pressing the glue dropping slide with a cover slide adsorbed by a sealing head. When the piezoelectric glue dropping valve runs to the top of the thickness mutation point, the valve opening is increased, so as to locally increase the glue dropping amount and the glue dropping pressure, overcome the fluid resistance at the thickness mutation point, fill the gap formed by the thickness mutation of the tissue, and reduce the formation of the air lock region from the root.

Description

Technical Field

[0001] This application relates to the fields of computer vision and precision control, and in particular to an adaptive sealing method and apparatus based on three-dimensional reconstruction and fluid diffusion simulation. Background Technology

[0002] In the automated workflow of digital pathology laboratories, mounting is a crucial step in the preparation of pathological slides, and its operational quality directly affects the accuracy of pathological diagnosis. Existing automated mounting machines have become the mainstream equipment in laboratories. However, these machines generally use a fixed path such as single point and straight line to dispensing mounting adhesive. The dispensing head can only complete a uniform linear motion, and the core execution parameters lack dynamic adjustment capabilities. It is impossible to compensate for the mounting adhesive flow rate in real time according to the actual morphology and thickness characteristics of the pathological tissue. For special tissues such as overlapping sections with uneven thickness, the fixed pressure dispensing operation is prone to trapping air bubbles at the abrupt change in tissue thickness, resulting in quality problems that are difficult to eliminate.

[0003] The natural characteristics of pathological tissues and environmental factors further amplify the shortcomings of traditional mounting techniques. On the one hand, the morphology of pathological tissues is highly diverse, and their irregular shapes make it difficult to adapt to the fixed dispensing method. This easily leads to glue overflow in small tissues and insufficient coverage of large tissues. Specimens with uneven thickness, such as punctured samples and overlapping tissues, can also form air-locked areas during the pressing of coverslips, becoming a major cause of air bubbles. On the other hand, the viscosity of the mounting adhesive changes with temperature and humidity. The fixed pressure spraying method of existing equipment cannot adapt to this change, making it difficult to ensure the consistency of adhesive application. At the same time, glue overflow can contaminate equipment components such as scanner lenses, increasing equipment maintenance costs. Excessive dispensing also results in a large waste of mounting adhesive reagent.

[0004] In summary, existing mounting techniques based on fixed paths and parameters have many limitations and cannot meet the high-quality mounting requirements of digital pathology laboratories. Therefore, there is an urgent need for a mounting method and device that can adaptively adjust according to the actual morphology, thickness characteristics, and environmental factors of pathological tissues, in order to improve the quality and efficiency of mounting operations, reduce air bubble formation, and lower mounting glue waste and equipment maintenance costs. Summary of the Invention

[0005] This application provides an adaptive sealing method and apparatus based on three-dimensional reconstruction and fluid diffusion simulation. By increasing the valve opening when the piezoelectric dispensing valve is running directly above the thickness abrupt change point, the dispensing volume and dispensing pressure are locally increased, overcoming the fluid resistance at the thickness abrupt change point, filling the gaps formed by the tissue thickness abrupt change, and reducing the formation of air-locked areas from the root cause.

[0006] In a first aspect, embodiments of this application provide an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation, the method comprising:

[0007] A three-dimensional topographic distribution map of the pathological sample on a glass slide is obtained. The area containing the sample tissue in the three-dimensional topographic distribution map is taken as the core area, and the remaining areas are taken as the guide area. Pixels in the core area whose height difference with any adjacent pixel is greater than a preset threshold are taken as thickness change points. The dispensing path is obtained based on the three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The opening of the piezoelectric dispensing valve is adjusted to a first opening only when the piezoelectric dispensing valve is directly above the thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing head adsorbs the cover glass and tilts and presses it against the dispensing glass to obtain a sealed sample. During the tilting and pressing process, the diffusion leading edge on the dispensing glass is detected based on a visual detection algorithm. When the diffusion leading edge is recessed or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass where the adhesive diffuses forward.

[0008] Secondly, embodiments of this application provide an adaptive sealing device based on three-dimensional reconstruction and fluid diffusion simulation, comprising: The acquisition module is used to acquire a three-dimensional topographic distribution map of the pathological sample on the slide, and to take the area containing the sample tissue in the three-dimensional topographic distribution map as the core area, the remaining area as the guide area, and the pixel in the core area whose height difference with any adjacent pixel is greater than a preset threshold as the thickness change point. The dispensing module obtains the dispensing path based on a three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The piezoelectric dispensing valve is adjusted to a first opening only when it is directly above a thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing module uses a sealing head to adsorb a cover glass slide and tilt and press it onto the dispensing glass slide to obtain a sealed sample. During the tilting and pressing process, a visual detection algorithm is used to detect the diffusion leading edge on the dispensing glass slide. When the diffusion leading edge becomes concave or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass slide where the adhesive diffuses forward.

[0009] Thirdly, embodiments of this application provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to execute an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation.

[0010] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation.

[0011] The main contributions and innovations of this invention are as follows: This application employs a linear laser scanner to acquire a three-dimensional topographic distribution map of pathological samples. The map is then divided into core / guide zones, and thickness abrupt change points are identified. This allows for precise characterization of the morphology and thickness distribution of pathological tissues, pinpointing thickness abrupt change sites prone to air bubbles. This provides accurate morphological data support for the entire adaptive dispensing and pressing process. In this application, when the piezoelectric dispensing valve reaches directly above a thickness abrupt change point, the valve opening is adjusted to a first opening greater than the default. By locally increasing the dispensing volume and pressure, the fluid resistance at the thickness abrupt change point is overcome, filling the gaps formed by the tissue thickness abrupt change and reducing the formation of air-locked areas at the source. Based on a preset viscosity-temperature-humidity mapping curve for the adhesive components, this application collects the adhesive temperature and humidity in real time and maps it to obtain the real-time adhesive viscosity. The movement speed of the piezoelectric dispensing valve is dynamically adjusted based on the real-time viscosity to offset viscosity fluctuations caused by temperature and humidity changes. This ensures the stability and consistency of adhesive application per unit area, avoiding insufficient application due to increased viscosity and overflow problems caused by decreased viscosity. This improves the yield and environmental adaptability of mounting operations under different environments.

[0012] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0013] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to an embodiment of this application. Figure 2 This is a schematic diagram of a device for mounting pathological samples according to an embodiment of this application; Figure 3 This is a schematic diagram of a linear laser scanner scanning a pathological sample on a glass slide according to an embodiment of this application; Figure 4 This is a schematic diagram of the simulation results of a three-dimensional terrain distribution map according to an embodiment of this application; Figure 5 This is a schematic diagram of a method for tilting and pressing an adhesive glass slide by adsorbing a cover glass slide with a sealing head according to an embodiment of this application; Figure 6 This is a structural block diagram of a data entry device according to an embodiment of this application; Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0014] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0015] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0016] Example 1 This application provides an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation. By increasing the valve opening when the piezoelectric dispensing valve is directly above the thickness abrupt change point, the dispensing volume and pressure are locally increased. This overcomes the fluid resistance at the thickness abrupt change point, fills the gaps formed by the tissue thickness abrupt change, and fundamentally reduces the formation of air-locked zones. Specifically, refer to... Figure 1 The method includes: A three-dimensional topographic distribution map of the pathological sample on a glass slide is obtained. The area containing the sample tissue in the three-dimensional topographic distribution map is taken as the core area, and the remaining areas are taken as the guide area. Pixels in the core area whose height difference with any adjacent pixel is greater than a preset threshold are taken as thickness change points. The dispensing path is obtained based on the three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses adhesive to obtain a dispensing glass slide. The opening of the piezoelectric dispensing valve is adjusted to a first opening only when the piezoelectric dispensing valve is directly above the thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing head adsorbs the cover glass and tilts and presses it against the dispensing glass to obtain a sealed sample. During the tilting and pressing process, the diffusion leading edge on the dispensing glass is detected based on a visual detection algorithm. When the diffusion leading edge is recessed or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass where the adhesive diffuses forward.

[0017] In the current embodiment, a schematic diagram of the device for mounting pathological samples is shown below. Figure 2 As shown, in Figure 2In this process, various visual analysis algorithms are deployed in digital cameras, LED ring lights illuminate pathological samples to enable digital cameras to obtain better imaging results, pathological samples are placed on glass slides, linear laser scanners are used to obtain three-dimensional topographic distribution maps of pathological samples on glass slides, dispensing nozzles are controlled by piezoelectric dispensing valves to achieve dispensing, and after dispensing is completed, coverslips are automatically adsorbed by the sealing head to tilt and press the dispensing glass slide.

[0018] In the current embodiment, a linear laser scanner is used to perform high-speed cruise scanning of the Z-axis of the pathological sample on the slide to obtain point cloud data of the pathological sample, and the point cloud data of the pathological sample is interpolated and reconstructed to obtain a three-dimensional terrain distribution map.

[0019] Specifically, a deep learning model is used to interpolate and denoise the point cloud data of pathological samples, thereby reconstructing a three-dimensional topographic distribution map of the pathological sample surface. The deep learning model used in this scheme is a U-Net structure. A schematic diagram of scanning the pathological sample on a glass slide using a linear laser scanner is shown below. Figure 3 As shown.

[0020] In the current embodiment, the core area and the guide area are identified in the three-dimensional terrain distribution map based on the simulation engine.

[0021] Specifically, a simulation engine is used to simulate the 3D terrain distribution map, and the simulation results of the 3D terrain distribution map are as follows: Figure 4 As shown, the region containing the sample tissue is selected as the core region based on the simulation results, and other regions on the slide are selected as the guide region.

[0022] In the current embodiment, the dispensing path is obtained by using a path planning algorithm with the optimization goal of fully covering the core area after the adhesive spreads. Specifically, bubble visual detection is performed on the core area of ​​each historical sealing sample, and the path planning algorithm is optimized based on the bubble visual detection results.

[0023] Furthermore, in the step of the piezoelectric dispensing valve running along the dispensing path and dispensing adhesive, the dispensing rate when the piezoelectric dispensing valve is above the core area is set as a first rate, and the dispensing rate when the piezoelectric dispensing valve is above the guide area is set as a second rate, wherein the first rate is greater than the second rate.

[0024] Specifically, a deep learning algorithm is used to predict the diffusion path of the adhesive in different areas of a 3D terrain distribution map, and a path planning algorithm is used to obtain the adhesive diffusion path with the goal of fully covering the core area after diffusion.

[0025] Specifically, a six-axis motion platform is used to drive the piezoelectric dispensing valve to move along the dispensing path, and the dispensing rate of the piezoelectric dispensing valve is controlled by adjusting the pulse frequency of the piezoelectric dispensing valve.

[0026] This method creates a pressure gradient for fluid diffusion by dripping resin at a high rate in the core area and at a low rate in the guide area, allowing air bubbles in the core area to escape from the edge of the slide along the pressure gradient through the guide area.

[0027] In other words, by setting a smaller amount of glue in the guide zone than in the core zone, the glue in the guide zone forms a guide track to accelerate the diffusion of the glue and better expel air bubbles. If the same amount of glue is set for the guide zone and the core zone, then air bubbles generated by the complex structure of the core area are very likely to remain in the core area, thus affecting the observation of pathological sections.

[0028] In the current embodiment, when the piezoelectric dispensing valve is directly above the thickness abrupt change point, a high-frequency pulse signal is output to the piezoelectric dispensing valve. After receiving the high-frequency pulse signal, the piezoelectric dispensing valve adjusts the valve opening to the first opening degree.

[0029] Specifically, since there are a large number of thickness abrupt change points in the core area, these thickness abrupt change points will have fluid resistance to block the diffusion of the adhesive, resulting in the generation of bubbles. This solution is to send a high-frequency pulse signal to the piezoelectric dispensing valve based on the signal control system when the piezoelectric dispensing valve is directly above the thickness abrupt change point, thereby adjusting the valve opening of the piezoelectric dispensing valve to the first opening degree, and increasing the dispensing pressure by increasing the dispensing amount, thereby overcoming the fluid resistance at the thickness abrupt change point.

[0030] In the current embodiment, based on the preset viscosity-temperature and humidity mapping curve of the adhesive components, a temperature and humidity sensor is integrated into the piezoelectric dispensing valve to obtain the temperature and humidity of the adhesive in real time. The temperature and humidity of the adhesive are mapped onto the viscosity-temperature and humidity mapping curve to obtain the real-time viscosity of the adhesive. Based on the real-time viscosity of the adhesive, the movement speed of the piezoelectric dispensing valve is adjusted to meet the amount of adhesive applied per unit area.

[0031] In addition, the real-time viscosity can be estimated by monitoring the fluctuations in the current and pressure sensors required to drive the piezoelectric ceramic and utilizing the flow characteristics of the adhesive in the microtube.

[0032] Specifically, the viscosity of the adhesive affects the dispensing efficiency of the piezoelectric dispensing valve. To reduce insufficient adhesive application per unit area due to increased adhesive viscosity, or adhesive overflow causing contamination of the scanner or lens due to decreased adhesive viscosity, this solution adjusts the movement speed of the piezoelectric dispensing valve based on real-time adhesive viscosity. This ensures that the adhesive application per unit area always meets the preset requirements and prevents adhesive overflow. The underlying formula is as follows:

[0033] in, This refers to the actual amount of adhesive dispensed by the piezoelectric dispensing valve. For experimental correction coefficients, This corresponds to the tissue thickness of the sample region. The movement speed of the piezoelectric dispensing valve, This represents the real-time viscosity of the adhesive.

[0034] In other words, when the viscosity of the adhesive changes in real time, the movement speed of the piezoelectric dispensing valve is also affected. Make corresponding changes so that the actual glue output of the corresponding sample area is at least [amount missing]. .

[0035] In the current embodiment, the shape and movement vector of the diffusion front on the epoxy resin slide are identified based on a visual inspection model. The shape of the diffusion front is used to determine whether a depression has appeared in the diffusion front, and the movement vector of the diffusion front is used to determine whether the diffusion front has stopped moving.

[0036] Specifically, when the diffusion front is concave, it indicates that air tends to be trapped in the concave area, making it easy for bubbles to form. When the diffusion front stops moving, it indicates that the adhesive is blocked by the thickness abrupt change point in the pathological sample on the slide. Therefore, by reducing the angular velocity of the tilting and pressing, more time is given for the adhesive to fill the tissue gaps, thereby avoiding the formation of bubbles.

[0037] Specifically, the angular velocity of the coverslip's tilting and pressing is reduced by a servo motor in the sealing head. A schematic diagram illustrating the tilting and pressing of the coverslip onto the epoxy resin slide by the sealing head is shown below. Figure 5 As shown.

[0038] Specifically, this method reduces the bubble occurrence rate from >5% in traditional methods to <0.1% for overlapping slices or puncture samples with uneven thickness.

[0039] Example 2 Based on the same concept, referencing Figure 6 This application also proposes an adaptive sealing device based on three-dimensional reconstruction and fluid diffusion simulation, comprising: The acquisition module is used to acquire a three-dimensional topographic distribution map of the pathological sample on the slide, and to take the area containing the sample tissue in the three-dimensional topographic distribution map as the core area, the remaining area as the guide area, and the pixel in the core area whose height difference with any adjacent pixel is greater than a preset threshold as the thickness change point. The dispensing module obtains the dispensing path based on a three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The piezoelectric dispensing valve is adjusted to a first opening only when it is directly above a thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing module uses a sealing head to adsorb a cover glass slide and tilt and press it onto the dispensing glass slide to obtain a sealed sample. During the tilting and pressing process, a visual detection algorithm is used to detect the diffusion leading edge on the dispensing glass slide. When the diffusion leading edge becomes concave or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass slide where the adhesive diffuses forward.

[0040] Example 3 This embodiment also provides an electronic device, see reference. Figure 7 It includes a memory 404 and a processor 402, the memory 404 storing a computer program and the processor 402 being configured to run the computer program to perform the steps in any of the above method embodiments.

[0041] Specifically, the processor 402 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0042] Memory 404 may include a mass storage device for data or instructions. For example, and not limitingly, memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may be internal or external to a data processing device. In a particular embodiment, memory 404 is non-volatile memory. In a particular embodiment, memory 404 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0043] The memory 404 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 402.

[0044] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any of the adaptive sealing methods based on three-dimensional reconstruction and fluid diffusion simulation in the above embodiments.

[0045] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408, wherein the transmission device 406 is connected to the processor 402, and the input / output device 408 is connected to the processor 402.

[0046] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 406 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0047] The input / output device 408 is used to input or output information. In this embodiment, the input information may be images of rice planthoppers, category information of rice planthopper images, etc., and the output information may be detailed results of rice planthoppers, etc.

[0048] Optionally, in this embodiment, the processor 402 can be configured to perform the following steps via a computer program: A three-dimensional topographic distribution map of the pathological sample on a glass slide is obtained. The area containing the sample tissue in the three-dimensional topographic distribution map is taken as the core area, and the remaining areas are taken as the guide area. Pixels in the core area whose height difference with any adjacent pixel is greater than a preset threshold are taken as thickness change points. The dispensing path is obtained based on the three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The opening of the piezoelectric dispensing valve is adjusted to a first opening only when the piezoelectric dispensing valve is directly above the thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing head adsorbs the cover glass and tilts and presses it against the dispensing glass to obtain a sealed sample. During the tilting and pressing process, the diffusion leading edge on the dispensing glass is detected based on a visual detection algorithm. When the diffusion leading edge is recessed or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass where the adhesive diffuses forward.

[0049] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0050] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented by firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0051] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets, and / or macros can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. The computer program product may include one or more computer-executable components configured to perform the embodiments when the program is run. The one or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted in this respect that, as Figure 7 Any box in the logical flow can represent a program step, or interconnected logic circuits, boxes and functions, or a combination of program steps and logic circuits, boxes and functions. Software can be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.

[0052] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation, characterized in that, Includes the following steps: A three-dimensional topographic distribution map of the pathological sample on a glass slide is obtained. The area containing the sample tissue in the three-dimensional topographic distribution map is taken as the core area, and the remaining areas are taken as the guide area. Pixels in the core area whose height difference with any adjacent pixel is greater than a preset threshold are defined as thickness mutation points. The dispensing path is obtained based on the three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The opening of the piezoelectric dispensing valve is adjusted to a first opening only when the piezoelectric dispensing valve is directly above the thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing head adsorbs the cover glass and tilts and presses it against the dispensing glass to obtain a sealed sample. During the tilting and pressing process, the diffusion leading edge on the dispensing glass is detected based on a visual detection algorithm. When the diffusion leading edge is recessed or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass where the adhesive diffuses forward.

2. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, A linear laser scanner is used to perform high-speed cruise scanning of the Z-axis of the pathological sample on a glass slide to obtain point cloud data of the pathological sample. The point cloud data of the pathological sample is then interpolated and reconstructed to obtain a three-dimensional terrain distribution map.

3. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, The dispensing path is obtained by using a path planning algorithm with the optimization goal of fully covering the core area after the adhesive spreads. In this process, the core area of ​​each historical sealing sample is visually inspected for bubbles, and the path planning algorithm is optimized based on the results of the bubble visual inspection.

4. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, In the step of the piezoelectric dispensing valve running along the dispensing path and dispensing adhesive, the dispensing rate when the piezoelectric dispensing valve is above the core area is set as the first rate, and the dispensing rate when the piezoelectric dispensing valve is above the guide area is set as the second rate, wherein the first rate is greater than the second rate.

5. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, When the piezoelectric dispensing valve is directly above the thickness abrupt change point, a high-frequency pulse signal is output to the piezoelectric dispensing valve. After receiving the high-frequency pulse signal, the piezoelectric dispensing valve adjusts the valve opening to the first opening degree.

6. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, Based on the pre-set viscosity-temperature and humidity mapping curve of the adhesive components, a temperature and humidity sensor is integrated into the piezoelectric dispensing valve to obtain the temperature and humidity of the adhesive in real time. The temperature and humidity of the adhesive are mapped onto the viscosity-temperature and humidity mapping curve to obtain the real-time viscosity of the adhesive. Based on the real-time viscosity of the adhesive, the movement speed of the piezoelectric dispensing valve is adjusted to meet the adhesive application amount per unit area.

7. The adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation according to claim 1, characterized in that, The shape and movement vector of the diffusion front on the epoxy resin slide are identified by a visual inspection model. The shape of the diffusion front is used to determine whether there is a depression in the diffusion front, and the movement vector of the diffusion front is used to determine whether the diffusion front has stopped moving.

8. An adaptive sealing device based on three-dimensional reconstruction and fluid diffusion simulation, characterized in that, include: The acquisition module is used to acquire a three-dimensional topographic distribution map of the pathological sample on the slide. The area containing the sample tissue in the three-dimensional topographic distribution map is taken as the core area, the remaining area is taken as the guide area, and the pixel in the core area whose height difference with any adjacent pixel is greater than a preset threshold is defined as a thickness change point. The dispensing module obtains the dispensing path based on a three-dimensional terrain distribution map. The piezoelectric dispensing valve runs along the dispensing path and dispenses dispensing to obtain a dispensing glass slide. The piezoelectric dispensing valve is adjusted to a first opening only when it is directly above a thickness change point. The first opening is greater than the default opening of the piezoelectric dispensing valve. The sealing module uses a sealing head to adsorb a cover glass slide and tilt and press it onto the dispensing glass slide to obtain a sealed sample. During the tilting and pressing process, a visual detection algorithm is used to detect the diffusion leading edge on the dispensing glass slide. When the diffusion leading edge becomes concave or stops moving, the angular velocity of the tilting and pressing is reduced. The diffusion leading edge is the edge on the dispensing glass slide where the adhesive diffuses forward.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to execute an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements an adaptive sealing method based on three-dimensional reconstruction and fluid diffusion simulation as described in any one of claims 1-7.

Images