Laboratory environment monitoring system and method for immunohistochemical antigen repair

Abstract

The embodiment of the invention provides a laboratory environment monitoring system and method for immunohistochemical antigen repair, and belongs to the technical field of data monitoring. The system comprises a data determination module for determining a target protein of a target tissue and determining a target antibody of the target protein; the data acquisition module obtains a target image of a target tissue and a target signal of the target tissue; the data prediction module obtains a historical tissue image, a historical signal and historical PH data of the target protein, and obtains a target PH value by combining a target image and a target signal according to the historical PH data, the historical tissue image and the historical signal; the temperature prediction module obtains historical temperature data of the target protein and obtains target temperature data according to the historical temperature data, the historical tissue image and the historical signal in combination with the target image and the target signal; and the data monitoring module performs repair environment monitoring on the target tissue by using immunohistochemistry according to the target antibody, the target PH value and the target temperature data to obtain a target monitoring result.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and in particular to a laboratory environment monitoring system and method for immunohistochemical antigen repair. Background Art

[0002] In immunohistochemistry experiments, how to efficiently and accurately restore epitopes in tissue fluid is directly related to the accuracy and reliability of the experiment. During the fixation and preservation of tissue samples, protein epitopes may be masked by cross-linking bonds, resulting in the inability of antibodies to recognize target proteins. To solve this problem, laboratories usually use thermal energy to undo these cross-linking bonds and restore protein epitopes. This process is called heat-induced epitope retrieval. Heat-induced epitope retrieval involves the process of heating and cooling tissue sections while immersing them in a solution with a clear buffering capacity. The pH value and heating temperature of the buffer solution are key factors affecting the antigen retrieval effect. However, existing related technologies have deficiencies in the setting of buffer pH and heating temperature, and there is a problem of inaccurate restoration effect.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a laboratory environment monitoring system and method for immunohistochemical antigen repair, aiming to solve the problems in the related art of the insufficiency in the setting of buffer pH value and heating temperature, and the inaccurate restoration effect.

[0005] In a first aspect, an embodiment of the present invention provides a laboratory environment monitoring system for immunohistochemical antigen repair, comprising:

[0006] A data determination module, used to determine the target protein corresponding to the target tissue, and determine the target antibody corresponding to the target protein;

[0007] A data acquisition module, used for obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue;

[0008] A data prediction module, used to obtain historical tissue images, historical signals and corresponding historical PH data corresponding to the target protein, and obtain a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images and the historical signals in combination with the target image and the target signal;

[0009] A temperature prediction module, used to obtain historical temperature data corresponding to the target protein, and obtain target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image and the historical signal in combination with the target image and the target signal;

[0010] The data monitoring module is used to monitor the repair environment of the target tissue using immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

[0011] In a second aspect, an embodiment of the present invention provides a laboratory environment monitoring method for immunohistochemical antigen repair, comprising:

[0012] Determining the target protein corresponding to the target tissue, and determining the target antibody corresponding to the target protein;

[0013] Obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue;

[0014] Obtaining historical tissue images, historical signals, and corresponding historical PH data corresponding to the target protein, and obtaining a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images, and the historical signals in combination with the target image and the target signal;

[0015] Obtaining historical temperature data corresponding to the target protein, and obtaining target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image, and the historical signal in combination with the target image and the target signal;

[0016] The target tissue is repaired and monitored by immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

[0017] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any one of the laboratory environment monitoring systems for immunohistochemical antigen repair provided in the specification of the present invention are realized.

[0018] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of a laboratory environment monitoring system for immunohistochemical antigen repair as provided in the specification of the present invention.

[0019] The embodiment of the present invention provides a laboratory environment monitoring system and method for immunohistochemical antigen repair, the system comprising a data determination module for determining a target protein corresponding to a target tissue and determining a target antibody corresponding to the target protein; a data acquisition module for obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue; a data prediction module for obtaining historical tissue images, historical signals and corresponding historical pH data corresponding to the target protein, and obtaining a target pH value corresponding to the target protein based on the historical pH data, historical tissue images and historical signals combined with the target image and the target signal; a temperature prediction module for obtaining historical temperature data corresponding to the target protein, and obtaining target temperature data corresponding to the target protein based on the historical temperature data, historical tissue images and historical signals combined with the target image and the target signal; and a data monitoring module for performing repair environment monitoring on the target tissue using immunohistochemistry according to the target antibody, target pH value and target temperature data to obtain a target monitoring result. The system accurately predicts the target pH value based on historical pH data, historical signals, historical tissue images, target images and target signals, and obtains the target temperature data corresponding to the target protein based on historical temperature data, historical tissue images and historical signals, target images and target signals, thereby providing good support for the subsequent use of immunohistochemistry technology to comprehensively monitor and evaluate the repair environment of the target tissue and provide accurate target monitoring results, further improving the accuracy and reliability of the research and reducing human errors. This can significantly improve the accuracy, efficiency and reliability of biological tissue repair and regeneration research. It also solves the problems of deficiencies in the setting of buffer pH value and heating temperature in related technologies, and the problem of inaccurate recovery effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A schematic diagram of the module structure of a laboratory environment monitoring system for immunohistochemical antigen repair provided by an embodiment of the present invention;

[0022] Figure 2 A schematic flow chart of a laboratory environment monitoring method for immunohistochemical antigen repair provided by an embodiment of the present invention;

[0023] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0026] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0027] The embodiment of the present invention provides a laboratory environment monitoring system and method for immunohistochemical antigen repair. The laboratory environment monitoring system for immunohistochemical antigen repair can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0028] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] Please refer to Figure 1 , Figure 1 A schematic diagram of the module structure of a laboratory environment monitoring system for immunohistochemical antigen repair provided by an embodiment of the present invention.

[0030] like Figure 1As shown, the laboratory environment monitoring system 200 for immunohistochemical antigen repair includes: a data determination module 201, a data acquisition module 202, a data prediction module 203, a temperature prediction module 204, and a data monitoring module 205, wherein the data determination module 201 is used to determine the target protein corresponding to the target tissue and determine the target antibody corresponding to the target protein; the data acquisition module 202 is used to obtain the target image corresponding to the target tissue and the target signal corresponding to the target tissue; the data prediction module 203 is used to obtain the historical tissue image, historical signal and corresponding historical pH data corresponding to the target protein, and The target pH value corresponding to the target protein is obtained according to the historical pH data, the historical tissue image and the historical signal in combination with the target image and the target signal; the temperature prediction module 204 is used to obtain the historical temperature data corresponding to the target protein, and obtain the target temperature data corresponding to the target protein according to the historical temperature data, the historical tissue image and the historical signal in combination with the target image and the target signal; the data monitoring module 205 is used to perform repair environment monitoring of the target tissue using immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

[0031] Exemplarily, the data determination module 201 queries the target protein corresponding to the target tissue from the database, and determines the target antibody corresponding to the target protein from the database.

[0032] Exemplarily, the data acquisition module 202 uses a microscope or other equipment to acquire a high-quality image of the target tissue to obtain a target image, and uses a sensor or detection equipment to acquire a target signal of the target tissue. The target signal may be a target signal corresponding to the molecular structure information obtained by detecting the vibration and rotation energy level changes of specific molecules in the target tissue through Raman spectroscopy technology, or may be a target signal by detecting the resonance signal of specific atomic nuclei (such as hydrogen, carbon, etc.) in the target tissue in a magnetic field through nuclear magnetic resonance technology, or may be a target signal by detecting the echo signal of the target tissue through ultrasonic technology, thereby obtaining the internal structure and composition information of the target tissue, etc. The target signal may be a target signal of the target tissue acquired using mass spectrometry, Raman spectroscopy, nuclear magnetic resonance, thermal imaging, ultrasonic wave, optical coherence tomography, electron microscope, and other technologies.

[0033] Exemplarily, the data prediction module 203 obtains historical tissue images, historical signals, and corresponding historical pH data corresponding to the target protein from a database or historical experimental data, and predicts the target pH value accordingly.

[0034] Exemplarily, the data prediction module 203 obtains a first similarity value by performing similarity calculation on the historical tissue image and the target image, and obtains a second similarity value by performing similarity calculation on the historical signal and the target signal, thereby fusing the first similarity value and the second similarity value to obtain a third similarity value, thereby determining the historical PH data corresponding to the maximum third similarity value as the target PH value corresponding to the target tissue.

[0035] Exemplarily, the temperature prediction module 204 obtains historical temperature data of the target protein from a database or historical experimental data.

[0036] Exemplarily, the temperature prediction module 204 obtains a first similarity value by performing similarity calculation on the historical tissue image and the target image, and obtains a second similarity value by performing similarity calculation on the historical signal and the target signal, thereby fusing the first similarity value and the second similarity value to obtain a third similarity value, thereby determining the historical temperature data corresponding to the maximum third similarity value as the target temperature data corresponding to the target tissue.

[0037] Exemplarily, the data monitoring module 205 uses immunohistochemistry to monitor the repair environment of the target tissue according to the target antibody, target pH value and target temperature data to obtain the target monitoring result.

[0038] For example, a suitable buffer is prepared according to the target pH value (such as pH 6.0 to 8.0). Commonly used buffers include citrate buffer and Tris-EDTA buffer. Ensure that the chemical composition of the buffer is stable and the pH value is accurate. Dilute the antibody to a suitable working concentration according to the instructions of the target antibody and the experimental requirements. The commonly used diluent is a PBS solution containing 0.1% BSA and 0.05% Tween-20 to ensure the stability and binding efficiency of the target antibody. Place the target tissue slice in a heating plate or water bath and set the target temperature data (such as 100°C). Ensure that the target tissue slice is completely immersed in the buffer for uniform heating to avoid local overheating or overcooling. According to the target temperature data and the target pH value, set a suitable heating time (such as 10 to 30 minutes). During the heating process, keep the pH value of the buffer stable to avoid protein denaturation due to pH fluctuations. After heating is completed, quickly cool the tissue slice to room temperature. Usually, the slice is immersed in a cold buffer for cooling to prevent protein denaturation due to rapid cooling and ensure the stability and recovery effect of the epitope. Remove the cooled target tissue slices from the buffer and wash them with a PBS solution containing 0.1% BSA and 0.05% Tween-20. Then place the slices in a working concentration solution containing the target antibody and incubate them overnight at 4°C to ensure that the antibody is fully bound to the target protein. The next day, wash the tissue slices with PBS to remove unbound primary antibodies. Then, place the slices in a solution containing a fluorescent or enzyme-labeled secondary antibody and incubate for a period of time, usually 30 minutes to 1 hour. After the incubation is completed, wash the slices again with PBS to remove unbound secondary antibodies. Use a fluorescence microscope to perform fluorescent image recognition on the target tissue slices to obtain target monitoring results. By analyzing the intensity and distribution of the fluorescent signal, the expression of the target protein can be quantified and located.

[0039] In some embodiments, the data prediction module includes: a first processing module, which is used to extract color features of the historical tissue image to obtain a corresponding first feature vector, and to perform masking processing on the first feature vector to obtain a corresponding first masked feature vector; a second processing module, which is used to extract color features of the target image to obtain a corresponding second feature vector, and to perform masking processing on the second feature vector to obtain a corresponding second masked feature vector; a first adjacent processing module, which is used to calculate the similarity of any two historical tissue images according to the first masked feature vector to obtain a first similarity, and to obtain a first adjacent image corresponding to the historical tissue image according to the first similarity; a first adjustment module, which is used to adjust the first masked feature vector according to the first adjacent image to obtain a first target feature vector corresponding to the historical tissue image; and a second adjacent processing module , used to perform similarity calculation based on the first masked feature vector and the second masked feature vector to obtain a second similarity, and obtain a second adjacent image corresponding to the target image based on the second similarity; a second adjustment module, used to adjust the second masked feature vector based on the second adjacent image to obtain a second target feature vector corresponding to the target image; a similarity calculation module, used to perform similarity calculation based on the first target feature vector and the second target feature vector to obtain a third similarity corresponding to the target image and the historical tissue image; a similarity fusion module, used to calculate a fourth similarity between the historical signal and the target signal, and fuse the third similarity and the fourth similarity to obtain the first target similarity; a target determination module, used to obtain the target pH value corresponding to the target protein from the historical PH data based on the first target similarity.

[0040] Exemplarily, the first processing module extracts color features from the historical tissue image and generates a corresponding first feature vector. The color features may include color statistics of RGB, HSV or other color spaces of the image. Thus, the first color mean and the first color maximum in the first feature vector are obtained, and then each dimension value in the first feature vector is divided by the first color mean to obtain a first numerical value, each dimension value in the first feature vector is divided by the first color maximum to obtain a second numerical value, and the first color mean is divided by the first color maximum to obtain a third numerical value, and then the first numerical value, the second numerical value and the third numerical value are summed to obtain a target sum value corresponding to each dimension value in the first feature vector, and then the natural logarithm of the target sum value is taken to obtain a target result, and then the target result is replaced by the corresponding dimension value in the first feature vector to achieve masking processing of the first feature vector and generate a first masked feature vector.

[0041] Exemplarily, the second processing module extracts color features from the target image and generates a corresponding second feature vector. The color features may include color statistics of RGB, HSV or other color spaces of the image. Thus, the second color mean and the second color maximum in the second feature vector are obtained, and then each dimension value in the second feature vector is divided by the second color mean to obtain a fourth value, each dimension value in the second feature vector is divided by the second color maximum to obtain a fifth value, and the second color mean is divided by the second color maximum to obtain a sixth value, and then the fourth value, the fifth value and the sixth value are summed to obtain the target and value corresponding to each dimension value in the second feature vector, and then the natural logarithm of the target and value is taken to obtain the target result, and then the target result is replaced by the corresponding dimension value in the second feature vector to achieve the masking processing of the second feature vector and generate a second masked feature vector.

[0042] Exemplarily, the first adjacent processing module calculates the similarity of any two historical tissue images using methods such as cosine similarity and Euclidean distance according to the first masked feature vector to obtain a first similarity. And according to the first similarity, the first adjacent image corresponding to each historical tissue image is determined. Usually, several images with the highest similarity to the current historical tissue image are selected as adjacent images.

[0043] Exemplarily, the first adjustment module adjusts the first shielding feature vector according to the shielding feature vector corresponding to the first adjacent image by weighted averaging, maximum value fusion, etc., to generate a first target feature vector corresponding to the historical tissue image.

[0044] Exemplarily, the second adjacent processing module performs similarity calculation based on the first masked feature vector and the second masked feature vector to obtain a second similarity. The calculation method is similar to that of the first adjacent processing module. Thus, according to the second similarity, the second adjacent image corresponding to the target image is determined. Several historical tissue images with the highest similarity to the target image are selected as adjacent images.

[0045] Exemplarily, the second adjustment module adjusts the second masking feature vector according to the second adjacent image to generate a second target feature vector corresponding to the target image. The adjustment method is consistent with that of the first adjustment module.

[0046] Exemplarily, the similarity calculation module performs similarity calculation based on the first target feature vector and the second target feature vector using cosine similarity, Euclidean distance, etc. to obtain a third similarity corresponding to the target image and the historical tissue image.

[0047] Exemplarily, the similarity fusion module calculates the fourth similarity between the historical signal and the target signal by comparing the signal strength, frequency component and other features, thereby fusing the third similarity and the fourth similarity by weighted average or other fusion algorithms to generate the first target similarity.

[0048] Exemplarily, the target determination module selects, according to the first target similarity, a historical PH value corresponding to a historical tissue image that is most similar to the target image as the target PH value.

[0049] Specifically, by masking the image features, the interference of background information can be significantly reduced, and irrelevant information in the background can be effectively filtered out, so that feature extraction is more focused on the target area, making feature extraction more targeted and efficient, thereby improving the accuracy of similarity calculation, providing support for the subsequent acquisition of reliable target pH values.

[0050] In some embodiments, the similarity calculation module includes: a data comparison module, used to compare the first data corresponding to each dimension in the first target feature vector and the second data corresponding to each dimension in the second target feature vector to obtain the minimum dimension value and the maximum dimension value corresponding to each dimension; a vector determination module, used to determine the first dimension vector according to the minimum dimension value corresponding to each dimension and determine the second dimension vector according to the maximum dimension value corresponding to each dimension; a vector fusion module, used to fuse the first dimension vector and the second dimension vector to obtain the third similarity corresponding to the target image and the historical tissue image; wherein the third similarity is obtained according to the following formula:

[0051]

[0052] Among them, sim3 represents the third similarity corresponding to the target image and the historical tissue image, v1 represents the first dimensional vector, v2 represents the second dimensional vector, max(v1) represents the maximum value in the first dimensional vector, min(v2) represents the minimum value corresponding to the second dimensional vector, and α and β represent adjustment parameters.

[0053] Exemplarily, the first data corresponding to each dimension in the first target feature vector is compared with each dimension data corresponding to the second target feature vector one by one. In each dimension, the dimension minimum value and the dimension maximum value are determined respectively. The dimension minimum value reflects the minimum value of the two feature vectors in the dimension, and the dimension maximum value reflects the maximum value of the two feature vectors in the dimension.

[0054] Exemplarily, the vector determination module determines the first dimension vector according to the dimension minimum value corresponding to each dimension according to the dimension position. That is, the minimum values ​​of all dimensions are combined into a new vector, which is the first dimension vector. The second dimension vector is determined according to the dimension maximum value corresponding to each dimension according to the dimension position. That is, the maximum values ​​of all dimensions are combined into a new vector, which is the second dimension vector.

[0055] Exemplarily, the vector fusion module fuses the first dimension vector and the second dimension vector according to the following formula to obtain the third similarity:

[0056]

[0057] Among them, sim3 represents the corresponding third similarity between the target image and the historical tissue image, v1 represents the first dimension vector, v2 represents the second dimension vector, max(v1) represents the maximum value in the first dimension vector, min(v2) represents the minimum value corresponding to the second dimension vector, and α and β represent adjustment parameters.

[0058] For example, according to the above formula, we can ignore the pixel position and only consider the pixel distribution, so as to pay more attention to the overall structure and content of the image, and can more effectively handle the situation of complex background and noise interference. Therefore, the pixel distribution is not affected by the change of pixel position, so in the case of incomplete image alignment or slight offset, the stability of similarity calculation can still be maintained. This improves the robustness of the similarity calculation, thereby ensuring the comprehensiveness and accuracy of the similarity calculation, and provides a reliable basis for image analysis and comparison.

[0059] In some embodiments, the temperature prediction module includes: a multi-scale sampling module, which is used to perform multi-scale sampling on the historical tissue image to obtain a first multi-scale feature, and to perform multi-scale sampling on the target image to obtain a second multi-scale feature; a first reconstruction module, which is used to perform deconvolution processing on the first multi-scale feature to obtain a first reconstructed image corresponding to the historical tissue image, and to perform deconvolution processing on the second multi-scale feature to obtain a second reconstructed image corresponding to the target image; a first extraction module, which is used to perform feature extraction on the first reconstructed image using a shallow feature extraction network to obtain first feature information, and to perform feature extraction on the first feature information using a deep feature extraction network to obtain second feature information; a first screening module, which is used to perform feature screening on the second feature information using a pruning network to obtain third feature information, and to screen the historical tissue image according to the third feature information. The image is reconstructed to obtain a corresponding third reconstructed image; a second extraction module is used to use the shallow feature extraction network to perform feature extraction on the second reconstructed image to obtain fourth feature information, and use the deep feature extraction network to perform feature extraction on the fourth feature information to obtain fifth feature information; a second screening module is used to use the pruning network to perform feature screening on the fifth feature information to obtain sixth feature information, and reconstruct the target image according to the sixth feature information to obtain a corresponding fourth reconstructed image; an image similarity module is used to calculate the fifth similarity corresponding to the third reconstructed image and the fourth reconstructed image; a data fusion module is used to fuse the fifth similarity and the fourth similarity to obtain the second target similarity; a temperature determination module is used to obtain the target temperature data corresponding to the target protein from the historical temperature data according to the second target similarity.

[0060] Exemplarily, the multi-scale sampling module can obtain the first multi-scale feature and the second multi-scale feature by performing multi-scale sampling on the historical tissue image and the target image. This method can capture the details and structural information of the target image and the historical tissue image at different scales, making the feature extraction more comprehensive and detailed. This can better reflect the overall structure and local details of the image and improve the comprehensiveness of feature extraction.

[0061] Exemplarily, the first reconstruction module performs deconvolution processing according to the first multi-scale feature and the second multi-scale feature, respectively, to obtain a first reconstructed image corresponding to the historical tissue image and a second reconstructed image corresponding to the target image. Deconvolution processing can restore the details and structure of the image, improve the accuracy of the reconstructed image, make the reconstructed image closer to the original image, and provide a more reliable basis for subsequent feature extraction and similarity calculation.

[0062] Exemplarily, the first extraction module uses a shallow feature extraction network to extract features from the first reconstructed image to obtain first feature information. The first feature information is further extracted using a deep feature extraction network to obtain second feature information. Shallow feature extraction focuses on the basic structure of the image, while deep feature extraction focuses on the high-level semantic information of the image.

[0063] Exemplarily, the first screening module uses a pruning network to perform feature screening on the second feature information to obtain third feature information, and reconstructs the historical tissue image according to the third feature information to obtain a corresponding third reconstructed image. The pruning network can remove redundant and irrelevant features, retain the most representative feature information, and improve the targeted nature of feature screening, thereby reducing the interference of redundant information and making subsequent similarity calculations more accurate.

[0064] Exemplarily, the second extraction module uses a shallow feature extraction network to perform feature extraction on the second reconstructed image to obtain fourth feature information, and uses a deep feature extraction network to perform feature extraction on the fourth feature information to obtain fifth feature information; the shallow feature extraction focuses on the basic structure of the image, and the deep feature extraction focuses on the high-level semantic information of the image.

[0065] Exemplarily, the second screening module uses a pruning network to perform feature screening on the fifth feature information to obtain the sixth feature information, and reconstructs the target image according to the sixth feature information to obtain the corresponding fourth reconstructed image; the pruning network can remove redundant and irrelevant features, retain the most representative feature information, improve the targeted feature screening, thereby reducing the interference of redundant information, and making subsequent similarity calculations more accurate.

[0066] Exemplarily, the image similarity module calculates the fifth similarity between the third reconstructed image and the fourth reconstructed image using Euclidean distance, cosine similarity, etc., so that the fifth similarity can be effectively evaluated between the two historical tissue images and the target image while reducing the interference of redundant information, thereby providing a reliable basis for determining the target temperature data.

[0067] Exemplarily, the data fusion module selects weighted average, maximum value selection, etc. to fuse the fifth similarity and the fourth similarity to obtain the second target similarity, thereby making the second target similarity more comprehensive and accurate, providing a more reliable reference for determining temperature data.

[0068] Exemplarily, the temperature determination module determines the historical tissue image that is closest to the target image according to the second target similarity, thereby determining the historical temperature data corresponding to the historical tissue image as the target temperature data.

[0069] In some embodiments, the first screening module includes: a first calculation module, which is used to obtain the first sub-information from the second characteristic information and reconstruct the image according to the first sub-information to obtain the first image, and then calculate the first signal entropy value corresponding to the first image; a second calculation module, which is used to obtain the second sub-information from the second characteristic information, and reconstruct the image according to the first sub-information and the second sub-information to obtain the second image, and then calculate the second signal entropy value corresponding to the second image; a first comparison module, which is used to filter the second sub-information according to the first signal entropy value and the second signal entropy value to obtain a first screening result; a third calculation module, which is used to obtain the third sub-information from the second characteristic information, and reconstruct the image according to the first screening result and the third sub-information to obtain the third image, and then calculate the third signal entropy value corresponding to the third image; a second comparison module, which is used to filter the third sub-information according to the second signal entropy value and the third signal entropy value to obtain a second screening result; and a target screening module, which is used to filter the second characteristic information according to the first screening result and the second screening result to obtain the third characteristic information.

[0070] Exemplarily, the first calculation module extracts the first sub-information from the second feature information. The first sub-information may be a partial eigenvalue or eigenvector in the second feature information. Image reconstruction is performed based on the extracted first sub-information to generate a first image. The image reconstruction method may be a deconvolution, interpolation or other technique. Thus, the first signal entropy value corresponding to the reconstructed first image is calculated based on the image grayscale histogram. The first signal entropy value reflects the information richness and complexity of the first image.

[0071] Exemplarily, the second calculation module extracts the second sub-information from the second feature information. The second sub-information may be another part of the eigenvalue or eigenvector in the second feature information, so as to reconstruct the image by combining the first sub-information and the second sub-information to generate the second image, and then calculate the second signal entropy value corresponding to the reconstructed second image according to the image grayscale histogram. The second signal entropy value reflects the information richness and complexity of the second image.

[0072] Exemplarily, the first comparison module compares the first signal entropy value and the second signal entropy value of the first image and the second image to determine the information richness and complexity difference between the first image and the second image, and then screens the second sub-information according to the comparison result of the first signal entropy value and the second signal entropy value. When the difference between the first signal entropy value and the second signal entropy value is less than a threshold, the second sub-information is deleted; when the difference between the first signal entropy value and the second signal entropy value is greater than or equal to the threshold, the second sub-information is retained.

[0073] Exemplarily, the third calculation module extracts the third sub-information from the second feature information. The third sub-information may be another part of the eigenvalue or eigenvector in the second feature information except the first sub-information and the second sub-information. Thus, the image is reconstructed in combination with the first screening result and the third sub-information to generate a third image. For example, when the first screening result is to delete the second sub-information, the image is reconstructed according to the first sub-information and the third sub-information to generate the third image; when the first screening result is to retain the second sub-information, the image is reconstructed according to the first sub-information, the second sub-information and the third sub-information to generate the third image. Thus, the third signal entropy value corresponding to the reconstructed third image is calculated.

[0074] Exemplarily, the difference between the second signal entropy value and the third signal entropy value of the second image and the third image is compared according to the second comparison module to determine the difference in information richness and complexity between the second image and the third image, and then the third sub-information is screened according to the comparison result of the second signal entropy value and the third signal entropy value. When the difference between the second signal entropy value and the third signal entropy value is less than a threshold, the third sub-information is deleted; when the difference between the second signal entropy value and the third signal entropy value is greater than or equal to the threshold, the third sub-information is retained.

[0075] Exemplarily, by analogy, when the second feature information further includes other features, the above steps are continued to be performed until a screening result corresponding to each feature in the second feature information is obtained.

[0076] Exemplarily, the target screening module screens the second characteristic information according to the first screening result and the second screening result to obtain the third characteristic information. When the first screening result and the second screening result are to retain corresponding sub-information, the corresponding sub-information is retained to obtain the screened third characteristic information.

[0077] It should be noted that the above steps can also be used to perform feature screening on the fifth feature information using a pruning network to obtain the sixth feature information, and this application will not repeat them again.

[0078] Specifically, through the above steps, the signal entropy value is used for multi-level information screening and image reconstruction, which can effectively extract and optimize the feature information and obtain high-quality third feature information, thereby enhancing the robustness of image reconstruction and reducing the interference of redundant data to provide support for the subsequent improvement of image similarity, and further provide a basis for the subsequent improvement of the reliability of temperature data determination.

[0079] In some embodiments, the data monitoring module includes: a data preparation module, used to determine a first buffer according to the target pH value, and place the target tissue and the target antibody in the first buffer to obtain a second buffer; a data heating module, used to heat the second buffer according to the target temperature data to obtain a target heating result; a data cooling module, used to determine a third buffer, and cool the target heating result according to the third buffer to obtain a target cooling result; a staining processing module, used to stain the target cooling result to obtain the target monitoring result corresponding to the target tissue.

[0080] Exemplarily, the data preparation module selects a suitable first buffer according to the target pH value. The selection of the buffer needs to ensure that its pH value matches the target pH value. The target tissue and the target antibody are placed in the first buffer. Ensure that the target tissue and the antibody are evenly distributed in the buffer to promote subsequent reactions. Through the above operations, a second buffer containing the target tissue and the target antibody is obtained. The second buffer should maintain a stable target pH value and a suitable reaction environment.

[0081] Exemplarily, the data heating module uses a heating device (such as a hot plate, a water bath, etc.) to heat the second buffer until the target temperature data is reached. The heating process needs to be slow and steady to avoid damage to the tissue caused by drastic temperature changes. By heating, the target heating result is obtained. The target heating result should include the binding state of the target tissue and the target antibody at the target temperature.

[0082] Exemplarily, the data cooling module determines a third buffer solution according to a target pH value, and then places the target heating result into the third buffer solution, thereby obtaining a target cooling result.

[0083] Exemplarily, the staining processing module selects a suitable stain according to the characteristics of the target antibody. The stain should be able to specifically label the target antibody for subsequent microscopic observation. The target cooling result is mixed with the stain and stained. The staining process must ensure that the stain is fully combined with the target antibody while avoiding non-specific background caused by excessive staining. Through the staining process, the target monitoring result corresponding to the target tissue is obtained.

[0084] In some embodiments, the staining processing module includes: an image acquisition module, which is used to obtain a target staining image corresponding to the target cold zone result after staining processing; a result determination module, which is used to determine a staining control group, and determine the target monitoring result corresponding to the target tissue based on the target staining image and the staining control group.

[0085] Exemplarily, the image acquisition module performs staining on the target cold zone results. This step usually uses specific dyes, such as hematoxylin-eosin staining (H&E staining), immunofluorescence staining or tissue-specific staining, to highlight the color and morphology of the target structure. After the staining process is completed, the focus and magnification of the microscope are adjusted through an imaging device (such as a high-resolution digital camera or an imaging system that comes with the microscope) to ensure that the image clarity is optimal. During the acquisition process, it may be necessary to adjust the light, focus, and exposure time multiple times to ensure that the image quality meets the requirements, so that a high-quality target staining image of the target cold zone result after staining can be obtained.

[0086] Exemplarily, the result determination module prepares a set of standard control samples with known results, which have been stained and have known monitoring results. These control samples are determined as the dyeing control group for comparison with the target dyeing image. In specific operations, professional image analysis software or tools, such as ImageJ, CellProfiler or a customized image analysis system, can be used to compare the target dyeing image with the dyeing control group in detail. During the comparison process, focus on features such as color, shape, and density. For example, the color and morphology of the nucleus in the target dyeing image are highly consistent with a certain pattern in the control group, or the density distribution of the target area is consistent with a known result in the control group, which can be used as a basis for judgment. By comparing these features, the target monitoring result corresponding to the target tissue can be determined.

[0087] See also Figure 2 , Figure 2 A laboratory environment monitoring method for immunohistochemical antigen retrieval provided in an embodiment of the present application includes steps S101 to S105.

[0088] Step S101, determining a target protein corresponding to a target tissue, and determining a target antibody corresponding to the target protein.

[0089] Step S102: Obtain a target image corresponding to the target tissue and a target signal corresponding to the target tissue.

[0090] Step S103, obtaining historical tissue images, historical signals and corresponding historical PH data corresponding to the target protein, and obtaining a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images and the historical signals combined with the target image and the target signal.

[0091] Step S104, obtaining historical temperature data corresponding to the target protein, and obtaining target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image and the historical signal combined with the target image and the target signal.

[0092] Step S105: Perform repair environment monitoring on the target tissue using immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

[0093] In some embodiments, the target pH value corresponding to the target protein is obtained according to the historical pH data, the historical tissue image, and the historical signal in combination with the target image and the target signal, and the following steps are performed:

[0094] Performing color feature extraction on the historical tissue image to obtain a corresponding first feature vector, and performing masking processing on the first feature vector to obtain a corresponding first masked feature vector;

[0095] Performing color feature extraction on the target image to obtain a corresponding second feature vector, and performing masking processing on the second feature vector to obtain a corresponding second masked feature vector;

[0096] Calculating the similarity of any two of the historical tissue images according to the first masked feature vector to obtain a first similarity, and obtaining a first adjacent image corresponding to the historical tissue image according to the first similarity;

[0097] Adjusting the first masking feature vector according to the first adjacent image to obtain a first target feature vector corresponding to the historical tissue image;

[0098] Performing similarity calculation based on the first masking feature vector and the second masking feature vector to obtain a second similarity, and obtaining a second adjacent image corresponding to the target image based on the second similarity;

[0099] Adjusting the second masking feature vector according to the second adjacent image to obtain a second target feature vector corresponding to the target image;

[0100] Performing similarity calculation based on the first target feature vector and the second target feature vector to obtain a third similarity corresponding to the target image and the historical tissue image;

[0101] Calculating a fourth similarity between the historical signal and the target signal, and fusing the third similarity and the fourth similarity to obtain the first target similarity;

[0102] The target pH value corresponding to the target protein is obtained from the historical pH data according to the first target similarity.

[0103] In some implementations, the similarity calculation is performed based on the first target feature vector and the second target feature vector to obtain a third similarity corresponding to the target image and the historical tissue image, and the following is performed:

[0104] Compare the first data corresponding to each dimension in the first target feature vector with the second data corresponding to each dimension in the second target feature vector to obtain a minimum dimension value and a maximum dimension value corresponding to each dimension;

[0105] Determine a first dimensional vector according to the minimum dimensional value corresponding to each dimension and determine a second dimensional vector according to the maximum dimensional value corresponding to each dimension;

[0106] fusing the first dimensional vector and the second dimensional vector to obtain the third similarity corresponding to the target image and the historical tissue image;

[0107] The third similarity is obtained according to the following formula:

[0108]

[0109] Among them, sim3 represents the third similarity corresponding to the target image and the historical tissue image, v1 represents the first dimensional vector, v2 represents the second dimensional vector, max(v1) represents the maximum value in the first dimensional vector, min(v2) represents the minimum value corresponding to the second dimensional vector, and α and β represent adjustment parameters.

[0110] In some embodiments, the target temperature data corresponding to the target protein is obtained according to the historical temperature data, the historical tissue image, and the historical signal in combination with the target image and the target signal, and the following steps are performed:

[0111] Performing multi-scale sampling on the historical tissue image to obtain a first multi-scale feature, and performing multi-scale sampling on the target image to obtain a second multi-scale feature;

[0112] Performing deconvolution processing according to the first multi-scale feature to obtain a first reconstructed image corresponding to the historical tissue image, and performing deconvolution processing according to the second multi-scale feature to obtain a second reconstructed image corresponding to the target image;

[0113] Using a shallow feature extraction network to perform feature extraction on the first reconstructed image to obtain first feature information, and using a deep feature extraction network to perform feature extraction on the first feature information to obtain second feature information;

[0114] Using a pruning network to perform feature screening on the second feature information to obtain third feature information, and reconstructing the historical tissue image according to the third feature information to obtain a corresponding third reconstructed image;

[0115] Using the shallow feature extraction network to perform feature extraction on the second reconstructed image to obtain fourth feature information, and using the deep feature extraction network to perform feature extraction on the fourth feature information to obtain fifth feature information;

[0116] Using the pruning network to perform feature screening on the fifth feature information to obtain sixth feature information, and reconstructing the target image according to the sixth feature information to obtain a corresponding fourth reconstructed image;

[0117] calculating a fifth similarity corresponding to the third reconstructed image and the fourth reconstructed image;

[0118] fusing the fifth similarity and the fourth similarity to obtain the second target similarity;

[0119] The target temperature data corresponding to the target protein is obtained from the historical temperature data according to the second target similarity.

[0120] In some implementations, the step of using a pruning network to perform feature screening on the second feature information to obtain third feature information comprises:

[0121] A first calculation module, configured to obtain first sub-information from the second feature information and reconstruct an image according to the first sub-information to obtain a first image, and then calculate a first signal entropy value corresponding to the first image;

[0122] a second calculation module, configured to obtain second sub-information from the second feature information, and to reconstruct an image according to the first sub-information and the second sub-information to obtain a second image, and further calculate a second signal entropy value corresponding to the second image;

[0123] A first comparison module, configured to filter the second sub-information according to the first signal entropy value and the second signal entropy value to obtain a first filtering result;

[0124] a third calculation module, configured to obtain third sub-information from the second feature information, and to reconstruct an image according to the first screening result and the third sub-information to obtain a third image, and then calculate a third signal entropy value corresponding to the third image;

[0125] A second comparison module, configured to filter the third sub-information according to the second signal entropy value and the third signal entropy value to obtain a second filtering result;

[0126] A target screening module is used to screen the second characteristic information according to the first screening result and the second screening result to obtain the third characteristic information.

[0127] In some embodiments, the target tissue is repaired and monitored using immunohistochemistry according to the target antibody, the target pH value, and the target temperature data to obtain a target monitoring result, and then:

[0128] Determine a first buffer according to the target pH value, and place the target tissue and the target antibody in the first buffer to obtain a second buffer;

[0129] heating the second buffer solution according to the target temperature data to obtain a target heating result;

[0130] determining a third buffer solution, and cooling the target heating result according to the third buffer solution to obtain a target cooling result;

[0131] The target cooling result is dyed to obtain the target monitoring result corresponding to the target tissue.

[0132] In some embodiments, the target cooling result is stained to obtain the target monitoring result corresponding to the target tissue, and the following steps are performed:

[0133] A target staining image corresponding to the target cold area result after staining;

[0134] A staining control group is determined, and the target monitoring result corresponding to the target tissue is determined according to the target staining image and the staining control group.

[0135] In some embodiments, the laboratory environment monitoring method 200 for immunohistochemical antigen retrieval can be applied to a terminal device.

[0136] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the laboratory environment monitoring method 200 for immunohistochemical antigen repair described above can refer to the corresponding process in the aforementioned embodiment of the laboratory environment monitoring system for immunohistochemical antigen repair, and will not be repeated here.

[0137] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0138] like Figure 3As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0139] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0140] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0141] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] The processor is used to run a computer program stored in the memory, and implement any one of the laboratory environment monitoring systems for immunohistochemical antigen repair provided by the embodiments of the present invention when executing the computer program.

[0143] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0144] A data determination module, used to determine the target protein corresponding to the target tissue, and determine the target antibody corresponding to the target protein;

[0145] A data acquisition module, used for obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue;

[0146] A data prediction module, used to obtain historical tissue images, historical signals and corresponding historical PH data corresponding to the target protein, and obtain a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images and the historical signals in combination with the target image and the target signal;

[0147] A temperature prediction module, used to obtain historical temperature data corresponding to the target protein, and obtain target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image and the historical signal in combination with the target image and the target signal;

[0148] The data monitoring module is used to monitor the repair environment of the target tissue using immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

[0149] In some implementations, the processor 301, in the data prediction module process, executes:

[0150] A first processing module, configured to perform color feature extraction on the historical tissue image to obtain a corresponding first feature vector, and perform masking processing on the first feature vector to obtain a corresponding first masked feature vector;

[0151] A second processing module, configured to perform color feature extraction on the target image to obtain a corresponding second feature vector, and perform masking processing on the second feature vector to obtain a corresponding second masked feature vector;

[0152] A first adjacent processing module, configured to calculate the similarity of any two of the historical tissue images according to the first masking feature vector to obtain a first similarity, and to obtain a first adjacent image corresponding to the historical tissue image according to the first similarity;

[0153] A first adjustment module, configured to adjust the first masking feature vector according to the first adjacent image to obtain a first target feature vector corresponding to the historical tissue image;

[0154] A second adjacent processing module, configured to perform similarity calculation based on the first masking feature vector and the second masking feature vector to obtain a second similarity, and obtain a second adjacent image corresponding to the target image based on the second similarity;

[0155] A second adjustment module, configured to adjust the second masking feature vector according to the second adjacent image to obtain a second target feature vector corresponding to the target image;

[0156] A similarity calculation module, configured to perform similarity calculation based on the first target feature vector and the second target feature vector to obtain a third similarity between the target image and the historical tissue image;

[0157] a similarity fusion module, configured to calculate a fourth similarity between the historical signal and the target signal, and fuse the third similarity and the fourth similarity to obtain the first target similarity;

[0158] A target determination module is used to obtain the target pH value corresponding to the target protein from the historical pH data according to the first target similarity.

[0159] In some implementations, the processor 301 executes, in the similarity calculation module process:

[0160] A data comparison module, used to compare the first data corresponding to each dimension in the first target feature vector with the second data corresponding to each dimension in the second target feature vector, to obtain a minimum dimension value and a maximum dimension value corresponding to each dimension;

[0161] A vector determination module, used to determine a first dimensional vector according to the minimum dimensional value corresponding to each dimension and to determine a second dimensional vector according to the maximum dimensional value corresponding to each dimension;

[0162] A vector fusion module, used for fusing the first dimensional vector and the second dimensional vector to obtain the third similarity corresponding to the target image and the historical tissue image;

[0163] The third similarity is obtained according to the following formula:

[0164]

[0165] Among them, sim3 represents the third similarity corresponding to the target image and the historical tissue image, v1 represents the first dimensional vector, v2 represents the second dimensional vector, max(v1) represents the maximum value in the first dimensional vector, min(v2) represents the minimum value corresponding to the second dimensional vector, and α and β represent adjustment parameters.

[0166] In some implementations, the processor 301, in the temperature prediction module process, executes:

[0167] A multi-scale sampling module, configured to perform multi-scale sampling on the historical tissue image to obtain a first multi-scale feature, and perform multi-scale sampling on the target image to obtain a second multi-scale feature;

[0168] a first reconstruction module, configured to perform deconvolution processing according to the first multi-scale feature to obtain a first reconstructed image corresponding to the historical tissue image, and perform deconvolution processing according to the second multi-scale feature to obtain a second reconstructed image corresponding to the target image;

[0169] A first extraction module, configured to perform feature extraction on the first reconstructed image using a shallow feature extraction network to obtain first feature information, and to perform feature extraction on the first feature information using a deep feature extraction network to obtain second feature information;

[0170] A first screening module, configured to perform feature screening on the second feature information using a pruning network to obtain third feature information, and reconstruct the historical tissue image according to the third feature information to obtain a corresponding third reconstructed image;

[0171] A second extraction module, configured to perform feature extraction on the second reconstructed image using the shallow feature extraction network to obtain fourth feature information, and to perform feature extraction on the fourth feature information using the deep feature extraction network to obtain fifth feature information;

[0172] A second screening module is used to perform feature screening on the fifth feature information using the pruning network to obtain sixth feature information, and reconstruct the target image according to the sixth feature information to obtain a corresponding fourth reconstructed image;

[0173] an image similarity module, configured to calculate a fifth similarity corresponding to the third reconstructed image and the fourth reconstructed image;

[0174] A data fusion module, used for fusing the fifth similarity and the fourth similarity to obtain the second target similarity;

[0175] A temperature determination module is used to obtain the target temperature data corresponding to the target protein from the historical temperature data according to the second target similarity.

[0176] In some implementations, the processor 301 executes, during the first screening module process:

[0177] A first calculation module, configured to obtain first sub-information from the second feature information and reconstruct an image according to the first sub-information to obtain a first image, and then calculate a first signal entropy value corresponding to the first image;

[0178] a second calculation module, configured to obtain second sub-information from the second feature information, and to reconstruct an image according to the first sub-information and the second sub-information to obtain a second image, and further calculate a second signal entropy value corresponding to the second image;

[0179] A first comparison module, configured to filter the second sub-information according to the first signal entropy value and the second signal entropy value to obtain a first filtering result;

[0180] a third calculation module, configured to obtain third sub-information from the second feature information, and to reconstruct an image according to the first screening result and the third sub-information to obtain a third image, and then calculate a third signal entropy value corresponding to the third image;

[0181] A second comparison module, configured to filter the third sub-information according to the second signal entropy value and the third signal entropy value to obtain a second filtering result;

[0182] A target screening module is used to screen the second characteristic information according to the first screening result and the second screening result to obtain the third characteristic information.

[0183] In some implementations, the processor 301, during the data monitoring module process, executes:

[0184] A data preparation module, configured to determine a first buffer according to the target pH value, and place the target tissue and the target antibody in the first buffer to obtain a second buffer;

[0185] A data heating module, used for heating the second buffer solution according to the target temperature data to obtain a target heating result;

[0186] A data cooling module, used for determining a third buffer, and cooling the target heating result according to the third buffer to obtain a target cooling result;

[0187] A dyeing processing module is used to perform dyeing processing on the target cooling result to obtain the target monitoring result corresponding to the target tissue.

[0188] In some embodiments, the processor 301 performs, during the dyeing process module:

[0189] An image acquisition module, used for obtaining a corresponding target staining image after staining the target cold zone result;

[0190] The result determination module is used to determine a staining control group, and determine the target monitoring result corresponding to the target tissue according to the target staining image and the staining control group.

[0191] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned laboratory environment monitoring system embodiment for immunohistochemical antigen repair, and will not be repeated here.

[0192] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of a laboratory environment monitoring system for immunohistochemical antigen repair as provided in the description of the embodiment of the present invention.

[0193] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0194] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0195] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0196] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A laboratory environment monitoring system for immunohistochemical antigen retrieval, characterized in that: The system comprises: A data determination module, used to determine the target protein corresponding to the target tissue, and determine the target antibody corresponding to the target protein; A data acquisition module, used for obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue; A data prediction module, used to obtain historical tissue images, historical signals and corresponding historical PH data corresponding to the target protein, and obtain a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images and the historical signals in combination with the target image and the target signal; A temperature prediction module, used to obtain historical temperature data corresponding to the target protein, and obtain target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image and the historical signal in combination with the target image and the target signal; The data monitoring module is used to monitor the repair environment of the target tissue using immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

2. The system according to claim 1, characterized in that The data prediction module comprises: A first processing module, configured to perform color feature extraction on the historical tissue image to obtain a corresponding first feature vector, and perform masking processing on the first feature vector to obtain a corresponding first masked feature vector; A second processing module, configured to perform color feature extraction on the target image to obtain a corresponding second feature vector, and perform masking processing on the second feature vector to obtain a corresponding second masked feature vector; A first adjacent processing module, configured to calculate the similarity of any two of the historical tissue images according to the first masking feature vector to obtain a first similarity, and to obtain a first adjacent image corresponding to the historical tissue image according to the first similarity; A first adjustment module, configured to adjust the first masking feature vector according to the first adjacent image to obtain a first target feature vector corresponding to the historical tissue image; A second adjacent processing module, configured to perform similarity calculation based on the first masking feature vector and the second masking feature vector to obtain a second similarity, and obtain a second adjacent image corresponding to the target image based on the second similarity; A second adjustment module, configured to adjust the second masking feature vector according to the second adjacent image to obtain a second target feature vector corresponding to the target image; A similarity calculation module, configured to perform similarity calculation based on the first target feature vector and the second target feature vector to obtain a third similarity between the target image and the historical tissue image; a similarity fusion module, configured to calculate a fourth similarity between the historical signal and the target signal, and fuse the third similarity and the fourth similarity to obtain the first target similarity; A target determination module is used to obtain the target pH value corresponding to the target protein from the historical pH data according to the first target similarity.

3. The system according to claim 2, characterized in that The similarity calculation module comprises: A data comparison module, used to compare the first data corresponding to each dimension in the first target feature vector with the second data corresponding to each dimension in the second target feature vector, to obtain a minimum dimension value and a maximum dimension value corresponding to each dimension; A vector determination module, used to determine a first dimensional vector according to the minimum dimensional value corresponding to each dimension and to determine a second dimensional vector according to the maximum dimensional value corresponding to each dimension; A vector fusion module, used for fusing the first dimensional vector and the second dimensional vector to obtain the third similarity corresponding to the target image and the historical tissue image; The third similarity is obtained according to the following formula: Among them, sim3 represents the third similarity corresponding to the target image and the historical tissue image, v1 represents the first dimensional vector, v2 represents the second dimensional vector, max(v1) represents the maximum value in the first dimensional vector, min(v2) represents the minimum value corresponding to the second dimensional vector, and α and β represent adjustment parameters.

4. The system according to claim 2, characterized in that The temperature prediction module comprises: A multi-scale sampling module, configured to perform multi-scale sampling on the historical tissue image to obtain a first multi-scale feature, and perform multi-scale sampling on the target image to obtain a second multi-scale feature; a first reconstruction module, configured to perform deconvolution processing according to the first multi-scale feature to obtain a first reconstructed image corresponding to the historical tissue image, and perform deconvolution processing according to the second multi-scale feature to obtain a second reconstructed image corresponding to the target image; A first extraction module, configured to perform feature extraction on the first reconstructed image using a shallow feature extraction network to obtain first feature information, and to perform feature extraction on the first feature information using a deep feature extraction network to obtain second feature information; A first screening module, configured to perform feature screening on the second feature information using a pruning network to obtain third feature information, and reconstruct the historical tissue image according to the third feature information to obtain a corresponding third reconstructed image; A second extraction module, configured to perform feature extraction on the second reconstructed image using the shallow feature extraction network to obtain fourth feature information, and to perform feature extraction on the fourth feature information using the deep feature extraction network to obtain fifth feature information; A second screening module is used to perform feature screening on the fifth feature information using the pruning network to obtain sixth feature information, and reconstruct the target image according to the sixth feature information to obtain a corresponding fourth reconstructed image; an image similarity module, configured to calculate a fifth similarity corresponding to the third reconstructed image and the fourth reconstructed image; A data fusion module, used for fusing the fifth similarity and the fourth similarity to obtain the second target similarity; A temperature determination module is used to obtain the target temperature data corresponding to the target protein from the historical temperature data according to the second target similarity.

5. The system according to claim 4, characterized in that The first screening module comprises: A first calculation module, configured to obtain first sub-information from the second feature information and reconstruct an image according to the first sub-information to obtain a first image, and then calculate a first signal entropy value corresponding to the first image; a second calculation module, configured to obtain second sub-information from the second feature information, and to reconstruct an image according to the first sub-information and the second sub-information to obtain a second image, and further calculate a second signal entropy value corresponding to the second image; A first comparison module, configured to filter the second sub-information according to the first signal entropy value and the second signal entropy value to obtain a first filtering result; a third calculation module, configured to obtain third sub-information from the second feature information, and to reconstruct an image according to the first screening result and the third sub-information to obtain a third image, and then calculate a third signal entropy value corresponding to the third image; A second comparison module, configured to filter the third sub-information according to the second signal entropy value and the third signal entropy value to obtain a second filtering result; A target screening module is used to screen the second characteristic information according to the first screening result and the second screening result to obtain the third characteristic information.

6. The system according to claim 1, characterized in that The data monitoring module comprises: A data preparation module, configured to determine a first buffer according to the target pH value, and place the target tissue and the target antibody in the first buffer to obtain a second buffer; A data heating module, used for heating the second buffer solution according to the target temperature data to obtain a target heating result; A data cooling module, used for determining a third buffer, and cooling the target heating result according to the third buffer to obtain a target cooling result; A dyeing processing module is used to perform dyeing processing on the target cooling result to obtain the target monitoring result corresponding to the target tissue.

7. The system according to claim 6, characterized in that The dyeing processing module comprises: An image acquisition module, used for obtaining a corresponding target staining image after staining the target cold zone result; The result determination module is used to determine a staining control group, and determine the target monitoring result corresponding to the target tissue according to the target staining image and the staining control group.

8. A laboratory environment monitoring method for immunohistochemical antigen retrieval, characterized in that: The method comprises: Determining the target protein corresponding to the target tissue, and determining the target antibody corresponding to the target protein; Obtaining a target image corresponding to the target tissue and a target signal corresponding to the target tissue; Obtaining historical tissue images, historical signals, and corresponding historical PH data corresponding to the target protein, and obtaining a target PH value corresponding to the target protein based on the historical PH data, the historical tissue images, and the historical signals in combination with the target image and the target signal; Obtaining historical temperature data corresponding to the target protein, and obtaining target temperature data corresponding to the target protein based on the historical temperature data, the historical tissue image, and the historical signal in combination with the target image and the target signal; The target tissue is repaired and monitored by immunohistochemistry according to the target antibody, the target pH value and the target temperature data to obtain a target monitoring result.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the laboratory environment monitoring system for immunohistochemical antigen retrieval according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the laboratory environment monitoring system for immunohistochemical antigen repair described in any one of claims 1 to 7.

Images