Dissection specimen storage and sampling control method and system

Abstract

The invention provides an anatomical specimen storage and sampling control method and system. A target anatomical specimen is divided into a plurality of sampling areas; extracting histomorphological characteristics of the anatomical specimen in the sampling area, determining a dominant temperature based on the temperature data of the sampling area, and performing linear correlation on the dominant temperature and the histomorphological characteristics of the sampling area to obtain a thermal stability coefficient of the sampling area; determining the texture features of the sampling area, and determining the feature retention degree of the surface texture of the target anatomical specimen based on all the texture features and the local humidity gradient of the sampling area; determining the cell structure entropy of the sampling area according to the thermal stability coefficient of the sampling area and the feature retention degree of the surface texture of the target anatomical specimen; and determining the sampling priority of the sampling area based on the cell structure entropy, and sampling according to the sampling priority. By adopting the scheme of the invention, the dynamic optimization of the sampling sequence can be realized based on the monitoring condition of the material structure change of each sampling part of the anatomical specimen in the storage process.

Description

Technical Field

[0001] The present application relates to the technical field of specimen sampling, and more specifically, to a method and system for controlling the storage and sampling of anatomical specimens. Background Art

[0002] Specimen analysis is one of the core technologies in life sciences, medical research, and disease diagnosis. By studying the physical, chemical, and biological properties of various biological specimens, it reveals the health status, metabolic processes, and potential pathological mechanisms of organisms. Biological specimens include biopsy tissues, anatomical specimens, etc. Among them, anatomical specimens have become an important resource for disease mechanism research and pathological diagnosis because they retain the integrity and spatial distribution characteristics of biological tissues. In the future, the analysis and storage technology of anatomical specimens will further develop towards micro-quantification, automation, and intelligence, providing more accurate research tools for medicine and life sciences.

[0003] In terms of technological development, the storage and analysis of anatomical specimens are gradually adopting more sophisticated processing methods. For example, storage techniques such as cryogenic freezing or chemical fixation can effectively preserve the structure and molecular composition of the specimens and prevent degradation. Combined with advanced technologies such as high-throughput sequencing, mass spectrometry analysis, and microscopic imaging, researchers can conduct multi-dimensional analysis of anatomical specimens, from the cellular tissue level to the molecular level, revealing their dynamic changes in disease. In addition, the application of artificial intelligence and image processing technology has opened up the possibility of automated analysis of anatomical specimens, helping to improve research efficiency and the accuracy of results. However, in existing technologies, when anatomical specimens are stored for a long time, the tissue characteristics of anatomical specimens may degrade due to the instability of temperature fluctuations and humidity changes. In addition, the loss rate of specimen components (such as cellular structure and molecular integrity) in different parts of the specimen varies. The traditional fixed sampling sequence may lead to the loss of high-value data or the inability to trace the true state of the specimen. Therefore, how to dynamically optimize the sampling sequence based on the monitoring of material structure changes at each sampling site of the anatomical specimen during storage has become a difficult problem facing the industry. Summary of the Invention

[0004] The present application provides a method and system for controlling the storage and sampling of anatomical specimens, which can realize dynamic optimization of the sampling sequence based on the monitoring of changes in the material structure of each sampling part of the anatomical specimen during the storage process.

[0005] In a first aspect, the present application provides a method for controlling storage and sampling of anatomical specimens, comprising the following steps: Divide the target anatomical specimen into multiple sampling areas; extracting the histomorphological characteristics of the anatomical specimen in each sampling area, determining the prevailing temperature of each sampling area based on the temperature data of each sampling area under the current storage environment, and performing a linear correlation between the prevailing temperature and the histomorphological characteristics of each sampling area to obtain the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of the storage temperature; Determining the texture characteristics of the surface of the anatomical specimen in each sampling area, and determining the characteristic retention of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all the texture characteristics and the local humidity gradient of each sampling area; determining the cell structure entropy of the anatomical specimen in each sampling area according to the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity; The sampling priority of each sampling region is determined based on the cell structure entropy of the anatomical specimen in each sampling region, and the target anatomical specimen is sampled according to the sampling priority of each sampling region.

[0006] In some embodiments, dividing the target anatomical specimen into a plurality of sampling regions specifically includes: Acquire monitoring images of target anatomical specimens while they are in storage; extracting a boundary contour of the target anatomical specimen from the monitoring image; The target anatomical specimen is divided into a plurality of sampling areas based on the boundary contour.

[0007] In some embodiments, extracting the histomorphological characteristics of the anatomical specimen in each sampling region specifically includes: Obtain the image block corresponding to each sampling area; The tissue morphological features of the anatomical specimen in each sampling area are extracted from the image block.

[0008] In some embodiments, determining the texture characteristics of the surface of the anatomical specimen in each sampling region specifically includes: Selecting a sampling area as a selected sampling area, and obtaining an image block corresponding to the selected sampling area; extracting a plurality of texture pixels on the surface of the selected sampling area from the image block; determining a plurality of texture indices of a surface of a selected sampling area based on all texture pixels; Determine the texture characteristics of the anatomical specimens in the selected sampling area based on all texture indicators and the humidity gradient of the storage environment where the target anatomical specimens are located; Continue to determine the textural features of the anatomical specimens in the remaining sampling areas.

[0009] In some embodiments, extracting a plurality of texture pixels on the surface of the selected sampling area from the image block specifically includes: Determining a texture judgment value for each pixel in the image block; A plurality of texture pixels on the surface of the selected sampling area are extracted based on all texture judgment values and a preset texture pixel threshold.

[0010] In some embodiments, determining the sampling priority of each sampling region based on the cell structure entropy of the anatomical specimen in each sampling region specifically includes: Determine the normalized parameter corresponding to the cytoarchitectonic entropy of the anatomical specimen in each sampling area; Determining a priority score for each sampling area based on a normalized parameter corresponding to each sampling area; The sampling priority of each sampling area is determined according to the priority score of each sampling area.

[0011] In some embodiments, the target anatomical specimens are stored in specimen cabinets.

[0012] In a second aspect, the present application provides an anatomical specimen storage and sampling control system, comprising: a pre-processing module for dividing the target anatomical specimen into multiple sampling areas; a processing module configured to extract the histomorphological characteristics of the anatomical specimen in each sampling region, determine the prevailing temperature of each sampling region based on the temperature data of each sampling region under the current storage environment, perform a linear correlation between the prevailing temperature and the histomorphological characteristics of each sampling region, and obtain a thermal stability coefficient of the anatomical specimen in each sampling region under the influence of the storage temperature; The processing module is further configured to determine texture features of the surface of the anatomical specimen in each sampling region, and determine a feature retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all the texture features and the local humidity gradient of each sampling region; The processing module is further configured to determine the cell structure entropy of the anatomical specimen in each sampling area based on the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity; The execution module is used to determine the sampling priority of each sampling area based on the cell structure entropy of the anatomical specimen in each sampling area, and sample the target anatomical specimen according to the sampling priority of each sampling area.

[0013] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned anatomical specimen storage sampling control method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which implements the above-mentioned anatomical specimen storage and sampling control method when executed by a processor.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In the anatomical specimen storage sampling control method and system provided in the present application, first, a target anatomical specimen is divided into multiple sampling areas; second, the histomorphological characteristics of the anatomical specimen in each sampling area are extracted, the dominant temperature of each sampling area is determined based on the temperature data of each sampling area under the current storage environment, and the dominant temperature and the histomorphological characteristics of each sampling area are linearly correlated to obtain the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of the storage temperature; further, the texture characteristics of the anatomical specimen surface in each sampling area are determined, and the feature retention degree of the texture of the target anatomical specimen surface under the influence of the storage humidity is determined based on all the texture characteristics and the local humidity gradient of each sampling area; then, the cellular structure entropy of the anatomical specimen in each sampling area is determined based on the thermal stability coefficient of the anatomical specimen under the influence of the storage temperature and the feature retention degree of the texture of the target anatomical specimen surface under the influence of the storage humidity; finally, the sampling priority of each sampling area is determined based on the cellular structure entropy of the anatomical specimen in each sampling area, and the target anatomical specimen is sampled according to the sampling priority of each sampling area.

[0016] It can be seen that the present application can realize dynamic optimization of the sampling sequence based on the monitoring of the changes in the material structure of each sampling part of the anatomical specimen during the storage process; first, the target anatomical specimen is divided into multiple sampling areas, which is conducive to the study and extraction of local characteristics of the specimen, thereby providing data support for subsequent sampling; secondly, based on the dominant temperature of the sampling area in the current storage environment combined with the tissue morphological characteristics of the anatomical specimen in the sampling area, the thermal stability coefficient of the sampling area during the storage process is determined to measure the response ability of the sampling area of the target anatomical specimen to temperature changes in the storage environment; further, the texture characteristics of the surface of the anatomical specimen in each sampling area are determined to reflect the intensity of the influence of humidity changes on the structural characteristics of the target anatomical specimen, thereby improving the reliability of subsequent material analysis; then, based on all the texture characteristics and each The local humidity gradient in the sampling area determines the characteristic retention of the texture of the target anatomical specimen's surface under the influence of storage humidity, so as to reflect the material properties of the specimen's surface structure, thereby providing data support for subsequent sampling work; in addition, the cell structure entropy of the anatomical specimen in the sampling area is determined based on the thermal stability coefficient and the characteristic retention, so as to reflect the interaction between the target anatomical specimen and the storage environment, thereby providing data guidance for subsequent sampling work; finally, the sampling priority of the sampling area is determined based on the cell structure entropy, and the target anatomical specimen is sampled according to the sampling priority, which can ensure that key samples can be processed in a timely manner, thereby avoiding the loss of high-value data; in summary, the technical solution provided in this application can realize dynamic optimization of the sampling sequence based on the monitoring of the changes in the material structure of each sampling part of the anatomical specimen during storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flow chart of an anatomical specimen storage and sampling control method according to some embodiments of the present application; Figure 2 is a schematic structural diagram of a specimen cabinet according to some embodiments of the present application; Figure 3 is an exemplary flow chart of determining texture features according to some embodiments of the present application; Figure 4 is a schematic structural diagram of an anatomical specimen storage and sampling control system according to some embodiments of the present application; Figure 5 It is a structural diagram of a computer device for implementing an anatomical specimen storage and sampling control method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1, which is an exemplary flow chart of an anatomical specimen storage and sampling control method according to some embodiments of the present application. The anatomical specimen storage and sampling control method 100 mainly includes the following steps: In step 101 , a target anatomical specimen is divided into a plurality of sampling regions.

[0020] In some embodiments, the target anatomical specimen may be divided into a plurality of sampling regions in the following manner: Acquire monitoring images of target anatomical specimens while they are in storage; extracting a boundary contour of the target anatomical specimen from the monitoring image; The target anatomical specimen is divided into a plurality of sampling areas based on the boundary contour.

[0021] In a specific implementation, monitoring images of the target anatomical specimen during storage are obtained, that is, monitoring images of the target anatomical specimen during storage are obtained through a high-definition camera. By obtaining the monitoring images, the morphological changes of the target anatomical specimen during storage can be monitored, thereby providing data support for subsequent sampling. In addition, in other embodiments, other methods can also be used to obtain monitoring images of the target anatomical specimen during storage, which are not limited here.

[0022] It should be noted that, in this embodiment, the target anatomical specimens are stored in a specimen cabinet, which includes a cabinet body, storage compartments, partitions and cabinet doors. Figure 2 As shown in FIG, this figure is a schematic structural diagram of a specimen cabinet according to some embodiments of the present application.

[0023] In a specific implementation, the boundary contour of the target anatomical specimen is extracted from the monitoring image, that is, the monitoring image is converted into a binary edge map using the Canny edge detection algorithm, and connectivity analysis is performed on the binary edge map to obtain the boundary contour of the target anatomical specimen. Specifically, the Flood Fill algorithm can be used for connectivity analysis, and the specific analysis steps are not repeated here. In addition, in other embodiments, other methods can also be used for edge detection and connectivity analysis, which are not limited here.

[0024] In a specific implementation, the target anatomical specimen is divided into multiple sampling areas based on the boundary contour, that is, multiple regular grids are divided within the boundary contour based on an equidistant grid division strategy, each regular grid corresponds to a sampling area of the target anatomical specimen, and the target anatomical specimen is then divided into multiple sampling areas. Specifically, the number of rows and columns to be divided is first preset according to the sampling accuracy, for example, 10×10, so as to obtain several rectangular regular grids of the same size; secondly, the cells that fall completely within the boundary contour are retained as valid sampling areas, and the cells that fall completely outside the contour are eliminated; further, for cells that partially contain edges, if the area proportion of the target anatomical specimen in the cell exceeds a set threshold, for example, 50%, the cell is considered valid; finally, all the valid sampling areas divided are numbered and named in order from top to bottom and from left to right, for example, A1, A2, ..., B1, B2, etc., to facilitate subsequent information labeling, feature extraction and sample management.

[0025] It should be noted that the sampling area in this application represents an independent unit on the specimen. Dividing the sampling area is conducive to studying and extracting local features of the specimen, thereby providing data support for subsequent sampling.

[0026] In step 102, the histomorphological characteristics of the anatomical specimen in each sampling area are extracted, the dominant temperature of each sampling area is determined based on the temperature data of each sampling area under the current storage environment, and a linear correlation is performed between the dominant temperature and the histomorphological characteristics of each sampling area to obtain the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of the storage temperature.

[0027] In some embodiments, the following methods may be used to extract the histomorphological characteristics of the anatomical specimen in each sampling area: Obtain the image block corresponding to each sampling area; The tissue morphological features of the anatomical specimen in each sampling area are extracted from the image block.

[0028] In specific implementation, the image block corresponding to each sampling area is obtained, that is, the binary edge map of the target anatomical specimen is obtained, and the regular grid area corresponding to each sampling area on the binary edge map is used as the image block of each sampling area, thereby obtaining the image block corresponding to each sampling area.

[0029] In a specific implementation, the histomorphological features of the anatomical specimen in each sampling area are extracted from the image block, that is: the shape information of the anatomical specimen in each sampling area is extracted from the image block by a morphological algorithm, the shape information including area, perimeter and curvature, the structural complexity of the surface of the anatomical specimen in the sampling area corresponding to each image block is calculated based on fractal dimension analysis, and the shape information and the structural complexity are combined into the histomorphological features of the anatomical specimen in each sampling area. Specifically, the countNonZero function of Open CV can be used to count the number of foreground pixels (i.e., pixels representing the anatomical specimen) in the image block as area information; then the boundary information is extracted by findContours of Open CV, and the perimeter information is extracted by arcLength function; secondly, the scikit-image The measure.approximate_polygon function in

[15] counts the frequency of angle changes of the anatomical specimen boundary in the image block to extract the curvature. Furthermore, the linear fitting slope of the anatomical specimen edge in the image block is calculated using the Box-counting algorithm based on fractal theory to obtain the fractal dimension, which is used as the structural complexity of the anatomical specimen surface in the sampling area corresponding to the image block.

[0030] It should be noted that the tissue morphological characteristics in this application represent quantitative descriptive indicators that describe the spatial structure, morphological contours, surface complexity and tissue distribution of anatomical specimens. By determining the tissue morphological characteristics, the local structural laws, physiological morphological characteristics or anatomical distribution characteristics of the specimen can be reflected, which is beneficial to subsequent analysis work.

[0031] In some embodiments, the dominant temperature of each sampling area may be determined based on the temperature data of each sampling area under the current storage environment in the following manner, namely: Collect temperature data of each sampling area under the current storage environment; The prevailing temperature in each sampling area is determined based on the temperature data.

[0032] In specific implementation, the temperature data of each sampling area in the current storage environment is collected, that is: in the storage environment of the target anatomical specimen, the temperature data of each sampling area in the current storage environment is collected by a temperature sensor, and the temperature data includes multiple temperature values of the sampling area.

[0033] In specific implementation, the dominant temperature of each sampling area is determined based on the temperature data, that is, the temperature data is analyzed by a time series analysis method. Specifically, the temperature value with the highest frequency of occurrence during the monitoring time is extracted, and the extracted temperature value is used as the dominant temperature of each sampling area.

[0034] It should be noted that the dominant temperature in this application refers to the temperature value that plays a dominant role. Specifically, the dominant temperature in this application is the temperature value that has a major impact on the changes in the tissue structure of the target anatomical specimen during the storage process.

[0035] It should also be noted that the thermal stability coefficient in this application represents a parameter that measures the responsiveness of a sample to temperature changes. Specifically, the thermal stability coefficient in this application is a parameter that measures the responsiveness of the sampling area of the target anatomical specimen to temperature changes in the storage environment. The larger the thermal stability coefficient, the stronger the responsiveness of the sampling area of the target anatomical specimen to temperature changes in the storage environment. The smaller the thermal stability coefficient, the weaker the responsiveness of the sampling area of the target anatomical specimen to temperature changes in the storage environment. By determining the thermal stability coefficient, the degree to which the sample maintains structural stability during storage can be reflected, thereby providing a technical basis for subsequent sampling evaluation. As a preferred embodiment, a linear correlation is performed between the dominant temperature and tissue morphological characteristics of each sampling area to obtain the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of the storage temperature. The following method can be used, namely: Call the multiple linear regression model; The prevailing temperature of each sampling area and various parameters of the tissue morphological characteristics of each sampling area were used as input variables; Perform normalization preprocessing on input variables; The normalized pre-processed input variables are fitted using the multivariate regression model, and the fitting results are used as the thermal stability coefficients of the anatomical specimens in each sampling area under the influence of storage temperature.

[0036] In the specific implementation, the Z-Score standardization method is used to perform normalization preprocessing on the input variables. Specifically, taking the normalization preprocessing of the dominant temperature of each sampling area as an example, first, the variable mean and variable variance of all input variables in each sampling area are calculated; then, the difference between the dominant temperature of each sampling area and the variable mean is calculated; finally, the quotient of the difference result and the variable variance is used as the normalization preprocessing result of the dominant temperature of each sampling area. Similarly, the normalization preprocessing results of various parameters in the tissue morphological characteristics of each sampling area are calculated according to the above steps, which will not be repeated here.

[0037] It should be noted that the multivariate linear regression model in this embodiment belongs to the existing technology. In this embodiment, only the selection of input variables and the output of results are optimized, and the specific implementation process will not be repeated here.

[0038] In step 103, the texture features of the anatomical specimen surface in each sampling area are determined, and the feature retention of the texture of the target anatomical specimen surface under the influence of storage humidity is determined based on all the texture features and the local humidity gradient of each sampling area.

[0039] In some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart of determining texture features according to some embodiments of the present application. In this embodiment, determining the texture features of the surface of the anatomical specimen in each sampling area can be achieved by using the following steps: First, in step 1031, a sampling area is selected as a selected sampling area, and an image block corresponding to the selected sampling area is obtained; Then, in step 1032, a plurality of texture pixels on the surface of the selected sampling area are extracted from the image block; Then, in step 1033 , a plurality of texture indices of the surface of the selected sampling area are determined based on all texture pixels; Additionally, in step 1034 , the texture characteristics of the anatomical specimen in the selected sampling area are determined based on all the texture indices and the humidity gradient of the storage environment where the target anatomical specimen is located; Finally, in step 1035 , the texture features of the anatomical specimen in the remaining sampling regions are continuously determined.

[0040] In some embodiments, extracting a plurality of texture pixels on the surface of the selected sampling area from the image block may be performed in the following manner: Determining a texture judgment value for each pixel in the image block; A plurality of texture pixels on the surface of the selected sampling area are extracted based on all texture judgment values and a preset texture pixel threshold.

[0041] In a specific implementation, the texture judgment value of each pixel in the image block is determined, that is, a pixel is selected in the image block, the longitudinal gradient and the transverse gradient of the pixel are calculated by using the Sobel gradient operator, the square value of the longitudinal gradient and the square value of the transverse gradient are summed, and the arithmetic square root of the sum is used as the texture judgment value of the pixel, thereby obtaining the texture judgment value of each pixel in the image block. In addition, in other embodiments, other methods can be used to calculate the longitudinal gradient and the transverse gradient, for example, the Laplacian gradient operator, etc., which are not limited here.

[0042] It should be noted that the texture judgment value in this embodiment represents the judgment parameter of the texture pixel. Specifically, the texture judgment value in this embodiment is represented by the gradient amplitude of the pixel point. By determining the texture judgment value, the characteristics of the pixel point at a special position of the specimen (such as a crack, a fold, etc.) can be reflected, thereby improving the accuracy of subsequent physical analysis of the specimen.

[0043] In a specific implementation, multiple texture pixels on the surface of the selected sampling area are extracted based on all texture judgment values and a preset texture pixel threshold, that is: a texture pixel threshold is preset, all texture judgment values are compared with the texture pixel threshold, all pixel points whose texture judgment values are greater than the texture pixel threshold are extracted, and the extracted pixel points are used as texture pixels, thereby obtaining multiple texture pixels on the surface of the selected sampling area. The value of the texture pixel threshold can be set according to actual application requirements and is not limited here.

[0044] It should be noted that, in this embodiment, texture pixels represent pixel points that reflect the texture characteristics of the specimen surface. Specifically, the texture pixels represent important pixel points that can reflect the texture characteristics of the target anatomical specimen surface. Determining the texture pixels is helpful in revealing the regularity of the surface structure of the target anatomical specimen.

[0045] In a specific implementation, multiple texture indices of the surface of the selected sampling area are determined based on all texture pixels, that is, all texture pixels are clustered using a K-means clustering algorithm to obtain multiple cluster groups. The specific clustering process is not repeated here. A cluster group is selected, and the variance of the grayscale values of all texture pixels in the cluster group is used as the texture index of the cluster group, thereby obtaining multiple texture indices of the surface of the selected sampling area. In addition, in other embodiments, other clustering algorithms can also be used for processing, such as a hierarchical clustering algorithm, etc., which are not limited here.

[0046] It should be noted that, in this embodiment, the texture index represents a statistical index of texture pixels. Specifically, the texture index represents a statistical index of texture pixels within the sampling area. By determining the texture index, the texture properties of the surface structure of the target anatomical specimen can be reflected, thereby providing a basis for further physical analysis.

[0047] In some embodiments, the texture characteristics of the anatomical specimen in the selected sampling area can be determined based on all texture indicators and the humidity gradient of the storage environment where the target anatomical specimen is located in the following manner, namely: Collect humidity information of the storage environment where the target anatomical specimen is stored; determining a humidity gradient of a storage environment where the target anatomical specimen is located based on the humidity information; extracting a reference texture index corresponding to each texture index based on the humidity gradient; Determining a similarity index between each reference texture index and a texture feature corresponding to each reference texture index; The texture features of the anatomical specimens in the selected sampling regions were determined based on all similarity metrics.

[0048] In specific implementation, the humidity information of the storage environment where the target anatomical specimen is located is collected, that is, humidity sensors are arranged at different locations in the storage environment where the target anatomical specimen is located, the humidity value of each point is collected, and the collected multiple discrete humidity values are combined into the humidity information of the storage environment where the target anatomical specimen is located.

[0049] In specific implementation, the humidity gradient of the storage environment where the target anatomical specimen is located is determined based on the humidity information, that is: according to the humidity information, the humidity changes at each monitoring position in the storage environment where the target anatomical specimen is located are calculated by an interpolation algorithm to obtain the humidity gradient of the storage environment where the target anatomical specimen is located. Specifically, based on the humidity information, a bilinear interpolation algorithm is used to construct a continuous field of humidity distribution in the space of the entire storage environment; then the gradient of the continuous humidity field is calculated in different directions by the finite difference method, that is, the derivative value of the humidity in the local space with the change of position is calculated to obtain the spatial change trend of the humidity in the storage environment, that is, the humidity gradient; in addition, in actual deployment, in order to suppress local anomalies caused by sensor errors or uneven distribution, the humidity field can be preprocessed in combination with a smoothing algorithm, such as a Gaussian filtering algorithm, a Laplace smoothing algorithm, etc., so as to ensure the physical rationality and spatial continuity of the humidity gradient, and provide quantitative support for subsequent specimen environment stability analysis and regulation.

[0050] In a specific implementation, the reference texture index corresponding to each texture index is extracted based on the humidity gradient. An empirically based linear response model can be used to convert the environmental variable of humidity into a quantitative influence on the texture characteristics of the specimen through a three-step method of "coefficient calibration - gradient quantification - recoverable transformation". That is, first, a humidity adjustment coefficient is set based on historical experimental data. This coefficient is an empirical quantitative parameter of the degree of influence of humidity on the surface texture properties of the sample. In a specific implementation, this coefficient is a dimensionless empirical parameter used to quantify the degree of influence of humidity on the surface texture properties of a specific specimen. Secondly, a linear adjustment model is used to multiply the humidity adjustment coefficient by the humidity gradient to reflect the intensity of the sample's influence by humidity. A construction adjustment factor is added to the product to make the adjustment process recoverable and proportional. The addition of one ensures that when the humidity gradient is zero, the adjustment factor is always 1. At this time, the reference texture index is equal to the original texture index. That is, the original data is not changed when humidity has no effect, ensuring recoverability in a physical sense. Finally, the adjustment factor is multiplied by each texture index item by item to obtain the reference texture index corresponding to each texture index after being corrected for humidity influence, thereby introducing the factor of the influence of humidity change on the sample texture structure while maintaining the original relative distribution structure of the texture index.

[0051] It should be noted that, in this embodiment, the reference texture index represents a reference value of the texture index. Specifically, the reference texture index is a new parameter obtained after the texture index is adjusted by humidity. By determining the reference texture index, comparative data can be provided for subsequent analysis.

[0052] In specific implementation, the similarity index between each reference texture indicator and the texture feature corresponding to each reference texture indicator is determined, that is, the cosine similarity between each reference texture indicator and the texture indicator corresponding to each reference texture indicator is calculated, and the calculation result is used as the similarity index between each reference texture indicator and the texture indicator corresponding to each reference texture indicator.

[0053] It should be noted that the similarity index in this embodiment represents a quantitative value of the similarity between texture indices. Specifically, the similarity index in this embodiment represents the cosine similarity between the reference texture index and the texture index corresponding to the reference texture index. By determining the similarity index, the similarity of the texture indicators before and after humidity adjustment can be measured.

[0054] In a specific implementation, the texture features of the anatomical specimen in the selected sampling area are determined based on all similarity indices, that is, the average of all similarity indices is used as the texture features of the anatomical specimen in the selected sampling area. In addition, in other embodiments, other methods can also be used to determine the texture features, which are not limited here.

[0055] It should be noted that the texture feature in this application represents an indicator used to quantify the extent to which the surface texture maintains its original characteristics. Specifically, the texture feature in this application is an indicator of the stability of the texture of the anatomical specimen in the sampling area under a humidity changing environment. The larger the texture feature, the stronger the stability of the texture of the anatomical specimen in the sampling area under a humidity changing environment. The smaller the texture feature, the weaker the stability of the texture of the anatomical specimen in the sampling area under a humidity changing environment. By determining the texture feature, the intensity of the impact of humidity changes on the structural characteristics of the target anatomical specimen can be reflected, thereby improving the reliability of subsequent material analysis.

[0056] In some embodiments, determining the feature retention of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all texture features and the local humidity gradient of each sampling area can be performed in the following manner, namely: Determining a dynamic adaptation coefficient corresponding to each texture feature; Acquiring humidity information of a storage environment where the target anatomical specimen is located, and extracting humidity data of each sampling area from the humidity information, wherein the humidity data includes multiple humidity values of the sampling area; Determining a local humidity gradient corresponding to each sampling area based on the humidity data of each sampling area; The characteristic retention of the texture of the target anatomical specimen surface under the influence of storage humidity is determined based on all dynamic adaptation coefficients and all local humidity gradients.

[0057] In specific implementation, the dynamic adaptation coefficient corresponding to each texture feature is determined, that is, each texture feature is normalized, and the result obtained by the processing is used as the dynamic adaptation coefficient corresponding to each texture feature. The specific normalization process is not repeated here. The dynamic adaptation coefficient represents the normalization result of the texture feature. By determining the dynamic adaptation coefficient, the dynamic adjustment process of the texture features of the sampling area during the storage process can be reflected.

[0058] In specific implementation, the local humidity gradient corresponding to each sampling area is determined based on the humidity data of each sampling area, that is: the humidity data of each sampling area is calculated by an interpolation algorithm to obtain the local humidity gradient corresponding to each sampling area. The specific local humidity gradient calculation process can be referred to step 103 of this application and will not be repeated here.

[0059] In specific implementation, the characteristic retention degree of the texture of the target anatomical specimen surface under the influence of storage humidity is determined based on all dynamic adaptation coefficients and all local humidity gradients, that is: all dynamic adaptation coefficients are weighted averaged, the weight of each dynamic adaptation coefficient is the local humidity gradient of the sampling area corresponding to each dynamic adaptation coefficient, and the result of the weighted average is used as the characteristic retention degree of the texture of the target anatomical specimen surface under the influence of storage humidity.

[0060] It should be noted that the feature retention degree in this application refers to the degree to which the specimen maintains its original feature state. Specifically, the feature retention degree in this application is the ability of the surface texture of the target anatomical specimen to maintain its original state under the influence of storage humidity. The greater the feature retention degree, the stronger the ability of the surface texture of the target anatomical specimen to maintain its original state under the influence of storage humidity. The smaller the feature retention degree, the weaker the ability of the surface texture of the target anatomical specimen to maintain its original state under the influence of storage humidity. By determining the feature retention degree, the material properties of the specimen surface structure can be reflected, thereby providing data support for subsequent sampling work.

[0061] In step 104, the cell structure entropy of the anatomical specimen in each sampling area is determined based on the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity.

[0062] In some embodiments, the cellular structural entropy of the anatomical specimen in each sampling region may be determined based on the thermal stability coefficient of the anatomical specimen in each sampling region under the influence of storage temperature and the characteristic retention of the texture of the surface of the target anatomical specimen under the influence of storage humidity in the following manner, namely: Determine the stability weight corresponding to the thermal stability coefficient of the anatomical specimens in each sampling area under the influence of storage temperature; The cell structure entropy of the anatomical specimen in each sampling area is determined based on the stability weight and the feature retention of the texture of the surface of the target anatomical specimen under the influence of storage humidity.

[0063] In specific implementation, the stability weight corresponding to the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature is determined, that is: all thermal stability coefficients are summed, and the quotient of the thermal stability coefficient corresponding to each sampling area and the summation result is calculated, and the quotient value result is used as the stability weight corresponding to the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature.

[0064] In a specific implementation, the cell structure entropy of the anatomical specimen in each sampling area is determined based on the stability weight and the feature retention degree of the texture of the target anatomical specimen surface under the influence of storage humidity, that is: the thermal stability coefficient corresponding to each sampling area is obtained, and the thermal stability coefficient corresponding to each sampling area and the feature retention degree of the texture of the target anatomical specimen surface under the influence of storage humidity are weightedly summed, wherein the weight of the thermal stability coefficient of each sampling area is the stability weight corresponding to each sampling area, and the weight of the feature retention degree is the difference between 1 and the stability weight corresponding to each sampling area.

[0065] It should be noted that the cell structure entropy in the present application represents the degree of deterioration of the sample tissue structure. Specifically, the cell structure entropy in the present application is the degree to which the tissue structure of the sampling area in the storage environment of the target anatomical specimen is affected by humidity and temperature and deteriorates. The greater the cell structure entropy, the greater the degree to which the tissue structure of the sampling area in the storage environment of the target anatomical specimen is affected by humidity and temperature and deteriorates. The smaller the cell structure entropy, the smaller the degree to which the tissue structure of the sampling area in the storage environment of the target anatomical specimen is affected by humidity and temperature and deteriorates. By determining the cell structure entropy, the interaction between the target anatomical specimen and the storage environment can be reflected, thereby providing data guidance for subsequent sampling work.

[0066] In step 105, a sampling priority of each sampling region is determined based on the cell structure entropy of the anatomical specimen in each sampling region, and the target anatomical specimen is sampled according to the sampling priority of each sampling region.

[0067] In some embodiments, the sampling priority of each sampling region may be determined based on the cell structure entropy of the anatomical specimen in each sampling region in the following manner: Determine the normalized parameter corresponding to the cytoarchitectonic entropy of the anatomical specimen in each sampling area; Determining a priority score for each sampling area based on a normalized parameter corresponding to each sampling area; The sampling priority of each sampling area is determined according to the priority score of each sampling area.

[0068] In specific implementation, the normalization parameter corresponding to the cell structure entropy of the anatomical specimen in each sampling area is determined, that is: the cell structure entropy may have orders of magnitude differences in different sampling areas. If it is directly used for subsequent comparison, it will lead to result deviation. The cell structure entropy of each sampling area can be converted into a unified scale through normalization processing, so that the values of different areas are comparable. The basic idea of normalization is to eliminate the dimensional influence between physical quantities, so that the scoring model is more universal and stable. Therefore, the cell structure entropy of the anatomical specimen in each sampling area is normalized by the Z-Score algorithm to obtain the normalization parameter corresponding to the cell structure entropy of the anatomical specimen in each sampling area. Each normalization parameter corresponds to a sampling area. The specific normalization processing process will not be repeated here. In addition, in other embodiments, other algorithms can also be used for normalization, such as the Min-Max algorithm, etc., which are not limited here.

[0069] In specific implementation, the priority score of each sampling area is determined based on the normalized parameter corresponding to each sampling area, that is, the normalized parameter corresponding to each sampling area is reverse mapped. Specifically, the priority score of each sampling area is determined by calculating the difference between 1 and the normalized parameter. Because the larger the parameter value after normalization, the more serious the sample deterioration. In order to match the logic of "the larger the priority score, the earlier the sampling", the above-mentioned reverse mapping method is used to convert the area with a high degree of deterioration into the area with a low priority score, so as to quickly identify the sampling area that needs sampling most during sorting, thereby optimizing the strategy orientation of risk control.

[0070] In specific implementation, the sampling priority of each sampling area is determined based on the priority score of each sampling area, that is: all priority scores are sorted in ascending order, and the sorting position of each priority score is used as the sampling priority of the sampling area corresponding to each priority score, thereby obtaining the sampling priority of each sampling area.

[0071] It should be noted that the sampling priority in this application represents an indicator for measuring the priority of sampling. The higher the sampling priority, the higher the deterioration risk of the corresponding sampling area, and priority sampling is required. The lower the sampling priority, the lower the deterioration risk of the corresponding sampling area, and sampling needs to be waited. By determining the sampling priority, the deterioration risk of the sampling area can be quantified, thereby ensuring that key samples can be processed in a timely manner.

[0072] In specific implementation, the target anatomical specimen is sampled according to the sampling priority of each sampling area, that is: through the specimen sampling technology, the target anatomical specimen is sampled according to the sampling priority of each sampling area to ensure that each sampling does not cause excessive damage to the target anatomical specimen. After each sampling operation, the automated system is used to record relevant data, including but not limited to sampling time, location, sampling priority, sampling volume, etc., for subsequent analysis and tracing.

[0073] In addition, in another aspect of the present application, in some embodiments, the present application provides an anatomical specimen storage and sampling control system, referring to Figure 4 This figure is a schematic structural diagram of an anatomical specimen storage and sampling control system according to some embodiments of the present application. The anatomical specimen storage and sampling control system 200 includes: a pre-processing module 201, a processing module 202, and an execution module 203, which are described as follows: Preprocessing module 201, in this application, the preprocessing module 201 is mainly used to divide the target anatomical specimen into multiple sampling areas; Processing module 202, in the present application, is primarily used to extract the histomorphological characteristics of the anatomical specimen in each sampling region, determine the prevailing temperature of each sampling region based on the temperature data of each sampling region under the current storage environment, perform a linear correlation between the prevailing temperature and the histomorphological characteristics of each sampling region, and obtain a thermal stability coefficient of the anatomical specimen in each sampling region under the influence of the storage temperature; The processing module 202 is further configured to determine texture features of the surface of the anatomical specimen in each sampling region, and determine a feature retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all the texture features and the local humidity gradient of each sampling region; In addition, the processing module 202 is further configured to determine the cell structure entropy of the anatomical specimen in each sampling region based on the thermal stability coefficient of the anatomical specimen in each sampling region under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity; The execution module 203 in this application is mainly used to determine the sampling priority of each sampling area based on the cell structure entropy of the anatomical specimen in each sampling area, and sample the target anatomical specimen according to the sampling priority of each sampling area.

[0074] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned anatomical specimen storage sampling control method.

[0075] In some embodiments, reference Figure 5, which is a schematic diagram of the structure of a computer device for implementing the anatomical specimen storage and sampling control method according to some embodiments of the present application. The anatomical specimen storage and sampling control method in the above embodiment can be achieved by Figure 5 The computer device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer device 300 includes at least one processor 301 , a communication bus 302 , a memory 303 , and at least one communication interface 304 .

[0076] The processor 301 may be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more processors for controlling the execution of the anatomical specimen storage and sampling control method of the present application.

[0077] The communication bus 302 may be used to transmit information between the aforementioned components.

[0078] Memory 303 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 303 may be independent and connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0079] Memory 303 is used to store program code for executing the present invention, and is controlled by processor 301. Processor 301 is used to execute the program code stored in memory 303. The program code may include one or more software modules. The determination of the anatomical specimen storage and sampling control method in the above embodiment can be implemented by processor 301 and one or more software modules in the program code in memory 303.

[0080] The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0081] In a specific implementation, as an example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0082] The aforementioned computer device can be a general-purpose computer device or a dedicated computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer device.

[0083] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned anatomical specimen storage and sampling control method.

[0084] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0085] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for controlling the storage and sampling of anatomical specimens, characterized in that: The steps include: Divide the target anatomical specimen into multiple sampling areas; extracting the histomorphological characteristics of the anatomical specimen in each sampling area, determining the prevailing temperature of each sampling area based on the temperature data of each sampling area under the current storage environment, and performing a linear correlation between the prevailing temperature and the histomorphological characteristics of each sampling area to obtain the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of the storage temperature; Determining the texture characteristics of the surface of the anatomical specimen in each sampling area, and determining the characteristic retention of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all the texture characteristics and the local humidity gradient of each sampling area; determining the cell structure entropy of the anatomical specimen in each sampling area according to the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity; The sampling priority of each sampling region is determined based on the cell structure entropy of the anatomical specimen in each sampling region, and the target anatomical specimen is sampled according to the sampling priority of each sampling region.

2. The method according to claim 1, wherein Dividing the target anatomical specimen into multiple sampling areas specifically includes: Acquire monitoring images of target anatomical specimens while they are in storage; extracting a boundary contour of the target anatomical specimen from the monitoring image; The target anatomical specimen is divided into a plurality of sampling areas based on the boundary contour.

3. The method according to claim 1, wherein The histomorphological characteristics of the anatomical specimens in each sampling area were extracted, including: Obtain the image block corresponding to each sampling area; The tissue morphological features of the anatomical specimen in each sampling area are extracted from the image block.

4. The method according to claim 1, wherein Determining the textural characteristics of the anatomical specimen surface in each sampling area specifically includes: Selecting a sampling area as a selected sampling area, and obtaining an image block corresponding to the selected sampling area; extracting a plurality of texture pixels on the surface of the selected sampling area from the image block; determining a plurality of texture indices of a surface of a selected sampling area based on all texture pixels; Determine the texture characteristics of the anatomical specimens in the selected sampling area based on all texture indicators and the humidity gradient of the storage environment where the target anatomical specimens are located; Continue to determine the textural features of the anatomical specimens in the remaining sampling areas.

5. The method according to claim 4, wherein Extracting a plurality of texture pixels on the surface of the selected sampling area from the image block specifically includes: Determining a texture judgment value for each pixel in the image block; A plurality of texture pixels on the surface of the selected sampling area are extracted based on all texture judgment values and a preset texture pixel threshold.

6. The method according to claim 1, wherein Determining the sampling priority of each sampling area based on the cell structure entropy of the anatomical specimen in each sampling area specifically includes: Determine the normalized parameter corresponding to the cytoarchitectonic entropy of the anatomical specimen in each sampling area; Determining a priority score for each sampling area based on a normalized parameter corresponding to each sampling area; The sampling priority of each sampling area is determined according to the priority score of each sampling area.

7. The method according to claim 1, wherein Targeted anatomical specimens are stored in specimen cabinets.

8. An anatomical specimen storage and sampling control system, characterized in that: include: a pre-processing module for dividing the target anatomical specimen into multiple sampling areas; a processing module configured to extract the histomorphological characteristics of the anatomical specimen in each sampling region, determine the prevailing temperature of each sampling region based on the temperature data of each sampling region under the current storage environment, perform a linear correlation between the prevailing temperature and the histomorphological characteristics of each sampling region, and obtain a thermal stability coefficient of the anatomical specimen in each sampling region under the influence of the storage temperature; The processing module is further configured to determine texture features of the surface of the anatomical specimen in each sampling region, and determine a feature retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity based on all the texture features and the local humidity gradient of each sampling region; The processing module is further configured to determine the cell structure entropy of the anatomical specimen in each sampling area based on the thermal stability coefficient of the anatomical specimen in each sampling area under the influence of storage temperature and the characteristic retention degree of the texture of the surface of the target anatomical specimen under the influence of storage humidity; The execution module is used to determine the sampling priority of each sampling area based on the cell structure entropy of the anatomical specimen in each sampling area, and sample the target anatomical specimen according to the sampling priority of each sampling area.

9. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores codes, and the processor is configured to acquire the codes and execute the anatomical specimen storage and sampling control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the anatomical specimen storage and sampling control method according to any one of claims 1 to 7 is implemented.

Images