A quality detection method, device and medium for biological cell detection microscope

Abstract

The present invention discloses a quality detection method, equipment and medium for a biological cell detection microscope, which belongs to the field of microscope detection, wherein the method includes: setting an optical performance detection factor; performing optical performance detection on a biological cell detection microscope to obtain a microscope optical performance quality coefficient; performing multimodal stability detection to obtain a microscope stability quality coefficient; setting a microscope application scenario factor; performing application scenario performance detection and analysis on the biological cell detection microscope according to the microscope application scenario factor to obtain a microscope application performance quality coefficient; and generating a microscope quality detection report. The present application solves the technical problem in the prior art that the quality detection of biological cell detection microscopes is not comprehensive and systematic, and it is difficult to comprehensively evaluate the performance of the microscope. By setting various detection factors and conducting comprehensive analysis, a comprehensive quality detection report is generated, thereby achieving the technical effect of comprehensively and systematically evaluating the performance of the microscope.

Description

Technical Field

[0001] The present invention relates to the field of microscope detection, and in particular to a quality detection method, equipment and medium of a biological cell detection microscope. Background Art

[0002] The quality of biological cell detection directly affects the accuracy and reliability of the test results. Therefore, it is very important to conduct comprehensive and systematic quality inspection of biological cell detection microscopes. In the prior art, the quality inspection of biological cell detection microscopes usually only focuses on a single or a few performance indicators, such as optical resolution, imaging quality, etc. This local and unsystematic detection method cannot fully evaluate the comprehensive performance of the microscope. In addition, the existing detection methods ignore the actual application scenarios of the microscope and fail to fully consider the specific requirements for microscope performance in different application environments, resulting in the test results being out of touch with the actual performance. Therefore, the quality inspection of biological cell detection microscopes in the prior art is not comprehensive and systematic, and it is difficult to fully evaluate the performance of the microscope. Summary of the invention

[0003] The present application provides a quality inspection method, device and medium for a biological cell inspection microscope, aiming to solve the technical problems in the prior art that the quality inspection of biological cell inspection microscopes is not comprehensive and systematic, and it is difficult to comprehensively evaluate the performance of the microscope.

[0004] In view of the above problems, the present application provides a quality detection method, device and medium for a biological cell detection microscope.

[0005] In a first aspect, the present application provides a quality inspection method for a biological cell detection microscope, the method comprising: setting an optical performance inspection factor, wherein the optical performance inspection factor includes resolution, focusing accuracy and focusing sensitivity; based on the optical performance inspection factor, performing an optical performance inspection on the biological cell detection microscope in combination with an optical performance feature evaluation model to obtain a microscope optical performance quality coefficient; performing a multimodal stability inspection based on the biological cell detection microscope to obtain a microscope stability quality coefficient; setting a microscope application scenario factor, wherein the microscope application scenario factor includes a detection object, detection requirements and a detection environment; performing an application scenario performance inspection and analysis on the biological cell detection microscope according to the microscope application scenario factor to obtain a microscope application performance quality coefficient; and generating a microscope quality inspection report based on the microscope optical performance quality coefficient, the microscope stability quality coefficient and the microscope application performance quality coefficient.

[0006] In a second aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a quality detection method for a biological cell detection microscope provided in the present application.

[0007] In a third aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a quality detection method for a biological cell detection microscope provided in the present application.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The optical performance detection factors, including resolution, focusing accuracy and focusing sensitivity, are set to comprehensively evaluate the imaging quality and focusing performance of the microscope, providing a basis for subsequent optical performance detection; based on the set optical performance detection factors, the optical performance of the microscope is detected in combination with the optical performance characteristic evaluation model to obtain the optical performance quality coefficient of the microscope, making the detection result more accurate and reliable; multi-modal stability detection is performed on the microscope to obtain the microscope stability quality coefficient, comprehensively evaluate the stability performance of the microscope in different working modes, and ensure the stable operation of the microscope in actual use; on the basis of stability detection, the microscope application scenario factors are introduced, including the detection object, detection requirements and detection environment, to simulate the actual application scenario of the microscope, making the detection closer to Actual needs; Based on the microscope application scenario factors, the microscope is tested and analyzed for application scenario performance, and the microscope application performance quality coefficient is obtained. The microscope is placed in a simulated application scenario for testing, and its adaptability and performance in actual applications are evaluated to make the test results more valuable for reference; Comprehensively consider the microscope optical performance quality coefficient, stability quality coefficient and application performance quality coefficient, generate a microscope quality test report, and comprehensively and objectively evaluate the overall quality of the microscope. This technical solution solves the technical problems in the existing technology that the quality test of biological cell detection microscopes is not comprehensive and systematic, and it is difficult to comprehensively evaluate the performance of the microscope. By setting various detection factors and comprehensively analyzing them, a comprehensive quality test report is generated, and the technical effect of comprehensively and systematically evaluating the performance of the microscope is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a quality detection method of a biological cell detection microscope is provided for this application;

[0012] Figure 2 A schematic diagram of the structure of an electronic device provided in this application.

[0013] Description of the reference numerals: processor 21 , memory 22 , input device 23 , output device 24 . DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The embodiments of the present application provide a quality detection method, equipment and medium for a biological cell detection microscope. First, by setting the optical performance detection factor and combining the optical performance characteristic evaluation model for detection, the imaging quality and focusing performance of the microscope are comprehensively evaluated. Secondly, a multimodal stability test is performed to comprehensively evaluate the stability performance of the microscope under different working modes to ensure its stable operation in actual use. Thirdly, a microscope application scenario factor is introduced, and application scenario performance detection and analysis are performed based on this to evaluate the adaptability and performance of the microscope in actual applications, so that the detection results are more valuable for reference. Afterwards, the test results of various aspects are comprehensively considered, and a microscope quality detection report is generated to comprehensively and objectively evaluate the overall quality of the microscope, so as to achieve a comprehensive evaluation of the performance of the microscope.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a quality detection method of a biological cell detection microscope, the method comprising:

[0018] S1: Setting optical performance detection factors, wherein the optical performance detection factors include resolution, focusing accuracy and focusing sensitivity.

[0019] Specifically, three key optical performance detection factors are selected, namely resolution, focusing accuracy and focusing sensitivity. Among them, resolution refers to the ability of the microscope to distinguish between two adjacent points, and is an important indicator for measuring the clarity of microscope imaging; the higher the resolution, the smaller the smallest detail that the microscope can distinguish, and the better the imaging quality. Focusing accuracy reflects the ability of the microscope optical system to accurately focus on a specific level of the sample when focusing; the higher the focusing accuracy, the better the clarity of the microscopic image. In actual operation, if the focusing accuracy of the microscope is not high enough, problems such as image blur or focus shift may occur, affecting the accuracy of observation and analysis. Focusing sensitivity indicates the responsiveness of the microscope to changes in the position of the focal plane, that is, the sensitivity of the microscope image clarity to changes when fine focusing is performed; the higher the focusing sensitivity, the easier it is to control the focusing process, and the higher the efficiency of obtaining a clear image. On the contrary, if the focusing sensitivity is low, it takes more time and effort to adjust the focal length, and it may even be difficult to find a suitable focal plane position, affecting the user experience and work efficiency of the microscope.

[0020] By setting the three optical performance detection factors of resolution, focusing accuracy and focusing sensitivity, the optical quality of the biological cell detection microscope can be evaluated from different angles, its imaging performance and usage characteristics can be fully understood, and a clear direction can be provided for the quality detection of the microscope.

[0021] S2: Based on the optical performance detection factor, the optical performance detection of the biological cell detection microscope is performed in combination with the optical performance characteristic evaluation model to obtain the optical performance quality coefficient of the microscope.

[0022] Specifically, first, for the three optical performance detection factors of resolution, focusing accuracy and focusing sensitivity, design and perform corresponding test experiments to obtain the performance data of the microscope in these aspects. For example, for the resolution factor, the resolution ability of the microscope is tested through standard samples or specific optical patterns; for focusing accuracy and sensitivity, the focusing performance parameters of the microscope are recorded and analyzed through focusing experiments. Through a series of tests and analyses of optical performance detection, the actual performance data of the microscope in terms of resolution, focusing accuracy and focusing sensitivity are obtained as the optical performance detection data of the microscope, which reflects the imaging quality and usage characteristics of the microscope optical system to evaluate its optical performance.

[0023] After obtaining the optical performance test data, the optical performance characteristic evaluation model is used to process and analyze the optical performance test data. The optical performance characteristic evaluation model is a mathematical model that comprehensively evaluates the optical quality of the microscope based on multiple optical performance test factors. By inputting the microscope's resolution, focusing accuracy, focusing sensitivity and other test data, the optical performance characteristic evaluation model calculates a quantitative optical performance quality coefficient, which is used to measure the comprehensive optical performance of the microscope. Among them, the optical performance quality coefficient is a normalized dimensionless indicator, and its value range is between 0 and 1. The closer the value is to 1, the better the optical performance of the microscope; the closer the value is to 0, the worse the optical performance. By calculating the optical performance quality coefficient, you can intuitively understand the optical performance of the microscope.

[0024] Through optical performance testing and optical performance characteristic evaluation model, the optical performance quality coefficient of the biological cell detection microscope is obtained, which provides an important evaluation index for subsequent quality inspection and helps to comprehensively evaluate the optical performance and imaging quality of the microscope.

[0025] S3: Perform multimodal stability testing based on the biological cell detection microscope to obtain a microscope stability quality coefficient.

[0026] Specifically, the stability of a microscope refers to its ability to maintain constant imaging quality and performance during actual use, without being affected by external environmental factors or long-term work. Good stability is an important quality of a biological cell detection microscope, which is directly related to the reliability and repeatability of the test results. The multimodal stability detection method is used to evaluate the stability performance of the microscope from different angles and conditions. Among them, multimodality means that the stability test includes multiple different test modes or condition settings, such as temperature changes, vibration interference, long-term continuous work, etc. By testing the microscope under multimodality, we can fully understand its stability performance in various working environments and usage conditions.

[0027] During the stability test, the changes in the imaging quality of the microscope in different modes and the fluctuations of various performance parameters (such as resolution, contrast, background noise, etc.) are recorded. By statistically analyzing these data, the stability score of the microscope in each mode is obtained. After obtaining the stability scores in each mode, the microscope stability quality coefficient is used as a comprehensive evaluation of the stability performance of the microscope in multiple modes, for example, calculated by weighted average or other mathematical methods. The value range of the microscope stability quality coefficient is 0 to 1, and the larger the value, the better the overall stability of the microscope. When calculating the microscope stability quality coefficient, different weights are assigned to the stability scores of different modes according to actual needs. For example, if the microscope is mainly used in a constant temperature environment, the weight of temperature stability can be appropriately increased; if the microscope needs to be moved frequently or work continuously for a long time, the weights of vibration stability and long-term working stability should be increased.

[0028] Through multimodal stability testing and calculation of microscope stability quality coefficient, the stability performance of biological cell detection microscope under different usage conditions was evaluated, providing an important basis for microscope quality testing.

[0029] S4: Setting microscope application scenario factors, wherein the microscope application scenario factors include detection objects, detection requirements and detection environment.

[0030] Specifically, biological cell detection microscopes face different application requirements and working environments. These differences will affect the performance and use of the microscope. Therefore, the application scenario factors of the microscope are clarified to evaluate the actual application of the microscope in a targeted manner. Among them, the application scenario factors of the microscope include detection object, detection requirements and detection environment. The detection object refers to the type of biological cell sample observed and analyzed by the microscope. Different types of cells differ in morphology, size, optical properties, etc., and different requirements are put forward for the resolution, contrast, fluorescence detection and other performance of the microscope. Detection requirements refer to the goals and requirements to be achieved by using a microscope for biological cell detection, such as observing cell morphology, analyzing cell structure, detecting specific substances, and performing quantitative measurements. Different detection requirements put forward different requirements for the imaging quality, analysis function, degree of automation, etc. of the microscope. The detection environment refers to the external conditions under which the microscope actually works, such as temperature, humidity, vibration, electromagnetic interference, etc. These environmental factors will affect the imaging stability, accuracy and reliability of the microscope.

[0031] By setting three microscope application scenario factors, namely, detection object, detection requirement and detection environment, we can comprehensively describe the actual application of biological cell detection microscopes, provide a specific framework and reference standards for evaluating microscope performance, and make the quality inspection of microscopes more targeted and effective.

[0032] S5: According to the microscope application scenario factor, perform application scenario performance detection and analysis on the biological cell detection microscope to obtain a microscope application performance quality coefficient.

[0033] Specifically, application scenario performance testing is to evaluate the actual working performance of the microscope under specific application conditions, including imaging quality, analysis accuracy, ease of operation, etc. Different from optical performance testing and stability testing, application scenario performance testing emphasizes the performance of the microscope in actual application, taking into account the influence of factors such as the test object, test requirements and test environment.

[0034] First, according to the three application scenario factors set, the corresponding performance test experiments are designed and implemented. For example, for different detection objects, the corresponding sample preparation methods and observation techniques are selected to evaluate the imaging quality and resolution of the microscope; for different detection requirements, the image analysis function and quantitative measurement accuracy of the microscope are tested; for different detection environments, temperature, humidity and other conditions are simulated to evaluate the adaptability and stability of the microscope. Through a series of performance test experiments, the performance data and evaluation results of the microscope in various application scenarios are obtained, reflecting the advantages and disadvantages of the microscope in practical applications. After obtaining the application scenario performance test results, the concept of microscope application performance quality coefficient is introduced to comprehensively evaluate the performance of the microscope in various application scenarios. For example, the microscope application performance quality coefficient is calculated by weighted average or other mathematical methods. The value range of the microscope application performance quality coefficient is 0 to 1. The larger the value, the better the overall application performance of the microscope. When calculating the microscope application performance quality coefficient, different weights are given to the performance evaluation results of each scenario according to the importance of different application scenarios and user needs. For example, if the microscope is mainly used to observe a specific type of cells, the performance evaluation weight under the corresponding detection object can be appropriately increased; if the user has special requirements for a certain detection indicator, the weight of the relevant performance should be increased. By setting the weight, a performance evaluation result that better meets the actual application needs can be obtained.

[0035] Through application scenario performance testing and microscope application performance quality coefficient, the performance and utility of the biological cell detection microscope are evaluated from the perspective of practical application, fully considering the application scenario factors of the microscope, and providing comprehensive, objective and quantitative performance analysis results.

[0036] S6: Generate a microscope quality inspection report based on the microscope optical performance quality coefficient, the microscope stability quality coefficient and the microscope application performance quality coefficient.

[0037] Specifically, the obtained microscope optical performance quality coefficient, microscope stability quality coefficient and microscope application performance quality coefficient are integrated into a comprehensive microscope quality inspection report to comprehensively evaluate the performance and quality level of the microscope, and accurately and comprehensively reflect the various performance indicators and comprehensive quality of the microscope. At the same time, the microscope quality inspection report includes the description of the inspection method and process, the description of the inspection conditions and environment, the analysis and interpretation of the inspection results, etc., which helps to understand the source, reliability and significance of the inspection results.

[0038] By generating a microscope quality inspection report, the inspection results of the microscope's optical performance, stability performance and application performance are presented in a centralized manner, providing a comprehensive, objective and quantitative microscope quality assessment.

[0039] Furthermore, the embodiment of the present application also includes:

[0040] Based on the optical performance detection factor, performing optical characteristic expected deviation detection on the biological cell detection microscope to obtain a multi-feature optical expected deviation detection result;

[0041] The optical performance characteristic evaluation model includes a resolution characteristic evaluation model, a focusing accuracy characteristic evaluation model and a focusing sensitivity characteristic evaluation model;

[0042] Based on the multi-feature optical expected deviation detection result, and according to the optical performance characteristic evaluation model, a multi-feature optical performance evaluation result is obtained, wherein the multi-feature optical performance evaluation result includes a resolution characteristic evaluation coefficient, a focusing accuracy characteristic evaluation coefficient, and a focusing sensitivity characteristic evaluation coefficient;

[0043] Based on the optical performance detection factors, setting multi-feature optical performance evaluation weights;

[0044] The multi-feature optical performance evaluation results are weightedly calculated based on the multi-feature optical performance evaluation weights to generate the microscope optical performance quality coefficient.

[0045] In a feasible implementation, first, based on the preset optical performance detection factors, the optical characteristics expected deviation detection of the biological cell detection microscope is performed. Specifically, the expected value of each optical performance detection factor (such as resolution, focusing accuracy, and focusing sensitivity) is first determined; then the actual performance data of the microscope on these factors is obtained through actual measurement to obtain the actual measurement value; the actual measurement value is compared with the expected value, and the degree of deviation is calculated to obtain the multi-feature optical expected deviation detection result, which reflects the gap between the actual performance of the microscope on each optical performance detection factor and the ideal performance. Subsequently, an optical performance feature evaluation model is introduced to convert the multi-feature optical expected deviation detection result into a corresponding performance evaluation coefficient. Among them, the optical performance feature evaluation model includes three sub-models, namely, a resolution feature evaluation model, a focusing accuracy feature evaluation model, and a focusing sensitivity feature evaluation model, which correspond to three optical performance detection factors respectively. These sub-models can be constructed based on empirical formulas, data fitting, or machine learning methods, and the deviation detection results are mapped to evaluation coefficients between 0 and 1 to quantify the performance of the microscope on each factor.

[0046] Afterwards, the optical performance characteristic evaluation model is used to process the multi-feature optical expected deviation detection results to obtain the multi-feature optical performance evaluation results, including three evaluation coefficients, namely, the resolution characteristic evaluation coefficient, the focusing accuracy characteristic evaluation coefficient, and the focusing sensitivity characteristic evaluation coefficient, which respectively characterize the performance level of the microscope on the corresponding optical performance factors. The closer the evaluation coefficient is to 1, the closer the performance of the microscope on this factor is to the ideal value; the closer the evaluation coefficient is to 0, the worse the performance is. Considering that the contribution of different optical performance detection factors to the overall performance of the microscope may be different, a multi-feature optical performance evaluation weight is introduced, and a weight value is assigned to the evaluation coefficient of each factor according to the importance of the optical performance detection factor. The larger the weight value, the higher the importance of the factor in the performance evaluation of the microscope. The setting of the weight is determined according to the design requirements, application scenarios and other factors of the microscope to reflect the priority of different factors. Then, the weighted average method is used to combine the multi-feature optical performance evaluation results with their corresponding weight values ​​to generate the microscope optical performance quality coefficient, which comprehensively reflects the overall performance of the microscope on each optical performance detection factor. The closer the microscope optical performance quality coefficient is to 1, the better the optical performance of the microscope is; the closer it is to 0, the worse the performance is.

[0047] Furthermore, the embodiment of the present application also includes:

[0048] Obtaining multiple magnifications of the biological cell detection microscope;

[0049] Based on the multi-level magnification, combined with the optical performance detection factor, the biological cell detection microscope is expected to be analyzed to obtain multi-level resolution expected information, multi-level focusing accuracy expected information and multi-level focusing sensitivity expected information;

[0050] Based on the multiple levels of magnification, performing resolution confidence detection on the biological cell detection microscope to obtain multiple levels of resolution confidence detection information;

[0051] Performing deviation analysis on the multi-level resolution confidence detection information based on the multi-level resolution expectation information to obtain a resolution expectation deviation detection result;

[0052] Based on the multi-level magnification and the multi-level focusing accuracy expected information, performing focusing accuracy detection and analysis on the biological cell detection microscope to obtain a focusing accuracy expected deviation detection result;

[0053] Based on the multi-level magnification and the multi-level focus sensitivity expected information, performing focus sensitivity detection and analysis on the biological cell detection microscope to obtain a focus sensitivity expected deviation detection result;

[0054] The resolution expected deviation detection result, the focus accuracy expected deviation detection result, and the focus precision expected deviation detection result are added to the multi-feature optics expected deviation detection result.

[0055] In a preferred embodiment, the microscope usually has multiple objective lenses, which can provide different magnifications to meet different observation requirements. First, the multi-level magnification of the biological cell detection microscope is obtained to understand the magnification range and level of the microscope. Next, based on the multi-level magnification, combined with the preset optical performance detection factors (resolution, focusing accuracy, focusing sensitivity), the microscope is expected to be analyzed. Specifically, according to the design parameters, theoretical models or empirical data of the microscope, the ideal performance of the microscope on each optical performance factor at different magnifications is predicted, and multi-level resolution expectation information, multi-level focusing accuracy expectation information and multi-level focusing sensitivity expectation information are obtained to provide a reference benchmark for subsequent deviation detection. Then, at each level of magnification, a standard resolution test sample (such as a grating ruler, a glass slide with a scale, etc.) is used to measure the actual resolution of the microscope multiple times, and the average value is calculated to obtain multi-level resolution confidence detection information. In order to ensure the reliability of the test results, the control variable method is adopted to keep other conditions (such as light, temperature, etc.) unchanged during the measurement process, and only change the variable of magnification. The method of taking the average value of multiple measurements can reduce the influence of random errors and improve the confidence of the test results.

[0056] Afterwards, the multi-level resolution confidence detection information is compared with the obtained multi-level resolution expectation information, and the deviation between the actual resolution and the expected resolution is calculated to obtain the resolution expectation deviation detection result, which quantitatively reflects the gap between the actual performance and the ideal performance of the resolution of the microscope at different magnifications. Similarly, the focus accuracy and focus sensitivity of the microscope are respectively tested for expected deviations. Similar to the resolution detection process, firstly, the focus accuracy and sensitivity test experiments are designed according to the multi-level magnifications and the corresponding expected information. By actually measuring the focusing performance of the microscope at different magnifications and comparing it with the expected values, the focus accuracy expected deviation detection results and the focus sensitivity expected deviation detection results are obtained, which respectively reflect the difference between the accuracy and responsiveness of the microscope in the focusing process and the ideal level. Afterwards, the expected deviation detection results of resolution, focus accuracy and focus sensitivity are summarized to obtain a complete multi-feature optical expected deviation detection result, which comprehensively reflects the deviation between the actual performance and the expected performance of the microscope in each optical performance detection factor.

[0057] Through the refinement of the optical characteristics of the biological cell detection microscope and the multi-level expected deviation detection, the multi-level magnification characteristics of the microscope are fully considered. By comparing with the theoretical expected values, the actual optical performance of the microscope at different magnifications is objectively evaluated. At the same time, the control variable method and the strategy of taking the average value of multiple measurements are adopted to effectively improve the reliability and confidence of the test results. The multi-feature optical expected deviation detection results lay a data foundation for the subsequent optical performance evaluation and quality assessment.

[0058] Furthermore, the embodiment of the present application also includes:

[0059] Obtain multi-level predetermined time windows and non-interference biological cell detection scenarios;

[0060] Based on the multi-level predetermined time windows and the non-interference biological cell detection scenario, biological cell detection is performed according to the biological cell detection microscope to obtain biological cell detection results of multiple nodes;

[0061] Perform imaging quality comparison based on the biological cell detection results of the multiple nodes to obtain imaging quality comparison results of the multiple node detections;

[0062] A stability evaluation is performed based on the comparison results of the imaging qualities detected at the multiple nodes to obtain a static stability coefficient of the microscope, and the static stability coefficient of the microscope is added to the stability quality coefficient of the microscope.

[0063] In a feasible implementation, first, a multi-level predetermined time window and a non-interference biological cell detection scene are obtained. The multi-level predetermined time window refers to selecting different time intervals (such as 30 minutes, 1 hour, 2 hours, etc.) as the time nodes of the detection. The non-interference biological cell detection scene refers to eliminating interference factors of the external environment (such as temperature changes, vibrations, etc.) during the stability detection process to ensure the reliability of the detection results. Next, based on the multi-level predetermined time window and the non-interference detection scene, the sample is continuously imaged using the biological cell detection microscope to be detected. Specifically, at the magnification set in the non-interference detection scene, the biological cell sample in the same field of view is imaged for a long time, and the imaging result is recorded once in each predetermined time window. In this way, a series of biological cell images at different times are obtained, and multiple node biological cell detection results are obtained as the data basis for stability evaluation.

[0064] Subsequently, the imaging quality comparison analysis of the biological cell detection results of multiple nodes was carried out, and the images obtained at different time nodes were compared one by one, paying attention to the changes in quality indicators such as image displacement, clarity, and contrast, and obtaining the comparison results of the imaging quality of multiple node detections. By analyzing the fluctuations and differences in image quality in the time series, the imaging stability of the microscope can be intuitively evaluated. Afterwards, based on the comparison results of the imaging quality of multiple node detections, the stability performance of the microscope was quantitatively evaluated, and the fluctuations in image quality were converted into the static stability coefficient of the microscope based on the evaluation of multiple expert scores. The higher the score, the more stable the imaging quality of the microscope is during long-term use, and the less affected by external factors.

[0065] Through the stability detection method, the biological cell imaging results at multiple time nodes are obtained. Combined with the image quality comparison analysis and evaluation, the static stability coefficient of the microscope is obtained, providing reliable data support for the judgment of the stability quality of the microscope.

[0066] Furthermore, the embodiment of the present application also includes:

[0067] Based on the biological cell detection microscope, test interference information is collected to establish multiple interference biological cell detection scenes, wherein the biological cell samples of the multiple interference biological cell detection scenes are the same;

[0068] obtaining a sample reference image of the biological cell sample;

[0069] Based on the multiple interfering biological cell detection scenes, performing biological cell detection according to the biological cell detection microscope to obtain multiple interfering scene detection images;

[0070] Based on the sample reference imaging, performing imaging quality change recognition on the multiple interference scene detection imaging to obtain multiple imaging quality change recognition results;

[0071] A stability evaluation is performed based on the multiple imaging quality change identification results to obtain a microscope dynamic stability coefficient, and the microscope dynamic stability coefficient is added to the microscope stability quality coefficient.

[0072] In a preferred embodiment, first, based on the biological cell detection microscope to be detected, the test interference information is collected. Specifically, a vibration platform or other mechanical devices are used to simulate various vibration conditions that may occur in the laboratory, such as ground vibrations, vibrations caused by equipment operation, etc. By adjusting the frequency and amplitude of the vibration source, multiple biological cell detection scenes with interference of different intensities are established. Among them, the same biological cell sample is used in all interference scenes to ensure that the interference condition is the only variable affecting the imaging quality. At the same time, before the vibration starts, the biological cell sample is precisely focused and an initial image is taken as the sample baseline imaging. The sample baseline imaging records the imaging quality of the sample under interference-free conditions, providing a reference for subsequent quality change analysis.

[0073] Subsequently, the biological cell detection microscope was placed in different interference biological cell detection scenes. Sample images were continuously taken during the continuous vibration process, and the imaging effects of the microscope under different interference intensities were recorded to obtain a series of detection imaging results under interference scenes, and multiple interference scene detection imaging was obtained. Then, based on the sample benchmark imaging, the quality change of multiple interference scene detection imaging was identified, and the multiple interference scene detection imaging obtained under interference conditions was compared with the sample benchmark imaging one by one to analyze the image displacement, clarity reduction, contrast change and other quality deterioration phenomena. By calculating the degree of image quality change, multiple imaging quality change identification results were obtained, reflecting the difference in imaging stability of the microscope under different interference intensities. Subsequently, based on multiple imaging quality change identification results, the dynamic stability of the microscope was comprehensively evaluated through expert scoring, and the degree of image quality change was converted into a quantitative stability score. The higher the score, the better the imaging stability of the microscope in a dynamic interference environment, and the less affected by interference factors such as vibration. Through this evaluation process, the dynamic stability coefficient of the microscope was obtained and incorporated into the overall microscope stability quality coefficient.

[0074] By simulating external interference, the biological cell imaging results under interference conditions are obtained, and combined with image quality change analysis and comprehensive evaluation, the dynamic stability coefficient of the microscope is obtained. This fully takes into account the interference factors such as vibration and movement faced by biological cell detection microscopes in actual applications, and provides a basis for the quantitative characterization of the stability quality of the microscope.

[0075] Furthermore, the embodiment of the present application also includes:

[0076] Based on the microscope application scene factor, application scene information of the biological cell detection microscope is collected and sorted to obtain a microscope application scene space;

[0077] Based on the microscope application scenario space, M test application scenarios satisfying the application scenario comparison constraint are established, where M is a positive integer greater than 1;

[0078] Performing application performance testing and analysis on the biological cell detection microscope based on the M test application scenarios to obtain M scenario application performance coefficients;

[0079] Performing importance evaluation based on the M test application scenarios, obtaining application scenario importance evaluation results, and setting application performance weights of the M scenarios according to the application scenario importance evaluation results;

[0080] The M scene application performance coefficients are weightedly calculated based on the M scene application performance weights to generate the microscope application performance quality coefficient.

[0081] In a feasible implementation, first, based on the set microscope application scenario factors, the application scenario information of the biological cell detection microscope to be detected is collected and sorted. Specifically, by analyzing the design parameters, usage requirements, etc. of the microscope, various application scenarios that it may face are sorted out, such as the observation of different types of samples, the use in a specific environment, the requirements of special analysis functions, etc., and the microscope application scenario space covering the main application fields and conditions of the microscope is obtained. Next, based on the obtained microscope application scenario space, M test application scenarios that meet the application scenario comparison constraint are established. Among them, the application scenario comparison constraint means that the selected test scenario needs to have sufficient differences and representativeness in terms of application conditions, performance requirements, etc., so as to effectively evaluate the adaptability of the microscope in different application environments. M test application scenarios are selected from the microscope application scenario space as the test basis for subsequent application performance detection. Among them, M is a positive integer greater than 1, and its specific value is determined according to the application complexity and detection requirements of the microscope.

[0082] Then, the biological cell detection microscope to be detected is placed in M ​​test application scenarios, and actual observation, analysis and operation are carried out respectively, and its performance in each scenario is evaluated. By recording key performance indicators (such as imaging quality, analysis speed, ease of operation, etc.) and comparing them with the scenario requirements, the application performance coefficient of the microscope in each test scenario is obtained. M test scenarios will generate M scenario application performance coefficients, reflecting the adaptability and performance level of the microscope under different application conditions. Since different test application scenarios have different degrees of importance for evaluating the overall application performance of the microscope. Therefore, by analyzing factors such as the frequency of occurrence of each test scenario in the actual application of the microscope and the importance of the use requirements, the application scenario importance evaluation results are obtained. Based on the results, corresponding scenario application performance weights are set for the M test application scenarios to reflect the relative importance of each scenario in the comprehensive performance evaluation. Afterwards, based on the M scenario application performance weights, the M test application scenario application performance coefficients are weighted and calculated to obtain the microscope application performance quality coefficient.

[0083] Furthermore, the embodiment of the present application also includes:

[0084] Extracting the mth test application scenario according to the M test application scenarios, where m is a positive integer, 1≤m≤M;

[0085] Based on the mth test application scenario, performing biological cell detection according to the biological cell detection microscope to obtain an mth test result;

[0086] Load the microscope test result record set and the microscope application performance evaluation record set;

[0087] Performing integrated learning based on the microscope detection result record set and the microscope application performance evaluation record set to generate a microscope application performance evaluation channel;

[0088] Based on the mth test detection result, according to the microscope application performance evaluation channel, the mth scene application performance coefficient is obtained, and the mth scene application performance coefficient is added to the M scene application performance coefficients.

[0089] In a preferred embodiment,

[0090] First, from the established M test application scenarios, the mth test application scenario is extracted, where m is a positive integer and 1≤m≤M, and the overall application performance detection task is decomposed into detection subtasks for each specific scenario, laying the foundation for the subsequent one-by-one analysis. Next, based on the mth test application scenario, the biological cell detection microscope to be detected is used to perform actual biological cell detection operations, and the relevant performance parameters and result data are recorded to obtain the mth test detection result, which reflects the actual application performance of the microscope in the test application scenario and contains rich performance feature information. Subsequently, ensemble learning is introduced to build an intelligent microscope application performance evaluation channel. First, two types of historical data are loaded, namely, microscope detection result record sets and microscope application performance evaluation record sets. The former contains a large number of original result data of different microscopes in various detection scenarios, and the latter records the performance evaluation and feedback of experts or users on these detection results. By performing correlation analysis and machine learning on these two types of data, the intrinsic mapping relationship between microscope detection results and application performance evaluation is summarized, and an intelligent microscope application performance evaluation channel is established. This channel can automatically convert microscope detection results into corresponding performance evaluations, and it becomes more and more accurate and comprehensive with the continuous accumulation and learning of historical data. After obtaining the microscope application performance evaluation channel, the mth test detection result is input into the evaluation channel. The channel automatically extracts the key performance features and gives a performance evaluation score between 0 and 1 based on the learned mapping relationship, that is, the mth scenario application performance coefficient. Subsequently, the coefficient is added to the set of M scenario application performance coefficients, and repeated until all M test application scenarios have obtained the corresponding performance coefficients.

[0091] By introducing integrated learning and building intelligent evaluation channels, the efficiency and accuracy of application performance evaluation are improved. Key performance features can be extracted from massive test results, and the rules and models of performance evaluation can be continuously learned and optimized, making the evaluation results more comprehensive, accurate and reliable. At the same time, the intelligent evaluation channel also greatly simplifies the process of application performance analysis, reduces dependence on professionals, and improves the efficiency and repeatability of detection.

[0092] In summary, the quality inspection method of a biological cell inspection microscope provided in the embodiment of the present application has the following technical effects:

[0093] The optical performance detection factor is set, where the optical performance detection factor includes resolution, focusing accuracy and focusing sensitivity, which provides an evaluation basis for subsequent optical performance detection and helps to comprehensively evaluate the imaging quality and focusing performance of the microscope. Based on the optical performance detection factor, the optical performance of the biological cell detection microscope is tested in combination with the optical performance characteristic evaluation model to obtain the optical performance quality coefficient of the microscope, which provides an important reference for the subsequent comprehensive evaluation of the microscope performance. Based on the biological cell detection microscope, multimodal stability detection is performed to obtain the microscope stability quality coefficient. By evaluating the stability performance of the microscope under different working modes, its reliability and consistency in actual use are comprehensively examined to provide a basis for ensuring the stable operation of the microscope. The microscope application scenario factor is set, where the microscope application scenario factor includes the detection object, detection requirements and detection environment, simulating the actual application scenario of the microscope, making the quality detection closer to the actual needs, and improving the pertinence and reference value of the detection results. According to the microscope application scenario factor, the application scenario performance detection and analysis of the biological cell detection microscope is performed to obtain the microscope application performance quality coefficient, evaluate the performance of the microscope in the simulated actual application scenario, examine its adaptability to different application requirements, and obtain the quality coefficient reflecting the actual application performance. Based on the microscope optical performance quality factor, microscope stability quality factor and microscope application performance quality factor, a microscope quality inspection report is generated to comprehensively and systematically evaluate the microscope performance.

[0094] Embodiment 2: Figure 2 The schematic diagram of the structure of the electronic device provided in the third embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 2 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 2 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 2 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 2 The example of connecting through bus is taken in the following.

[0095] The memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a quality detection method for a biological cell detection microscope in an embodiment of the present application. The processor 21 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 22, that is, realizing the quality detection method for a biological cell detection microscope described above.

[0096] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0097] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A quality detection method for a biological cell detection microscope, characterized in that: The method comprises: Setting optical performance detection factors, wherein the optical performance detection factors include resolution, focusing accuracy and focusing sensitivity; Based on the optical performance detection factor, the optical performance of the biological cell detection microscope is tested in combination with the optical performance characteristic evaluation model to obtain the optical performance quality coefficient of the microscope; Performing multimodal stability testing based on the biological cell detection microscope to obtain a microscope stability quality coefficient; Setting microscope application scenario factors, wherein the microscope application scenario factors include detection objects, detection requirements and detection environment; According to the microscope application scenario factor, performing application scenario performance detection and analysis on the biological cell detection microscope to obtain a microscope application performance quality coefficient; Generate a microscope quality inspection report based on the microscope optical performance quality coefficient, the microscope stability quality coefficient and the microscope application performance quality coefficient; Among them, based on the optical performance detection factor, combined with the optical performance characteristic evaluation model, the optical performance detection of the biological cell detection microscope is carried out to obtain the optical performance quality coefficient of the microscope, including: Based on the optical performance detection factor, performing optical characteristic expected deviation detection on the biological cell detection microscope to obtain a multi-feature optical expected deviation detection result; The optical performance characteristic evaluation model includes a resolution characteristic evaluation model, a focusing accuracy characteristic evaluation model and a focusing sensitivity characteristic evaluation model; Based on the multi-feature optical expected deviation detection result, and according to the optical performance characteristic evaluation model, a multi-feature optical performance evaluation result is obtained, wherein the multi-feature optical performance evaluation result includes a resolution characteristic evaluation coefficient, a focusing accuracy characteristic evaluation coefficient, and a focusing sensitivity characteristic evaluation coefficient; Based on the optical performance detection factors, setting multi-feature optical performance evaluation weights; Performing weighted calculation on the multi-feature optical performance evaluation result based on the multi-feature optical performance evaluation weight to generate the optical performance quality coefficient of the microscope; Based on the optical performance detection factor, the optical characteristic expected deviation detection is performed on the biological cell detection microscope to obtain a multi-feature optical expected deviation detection result, including: Obtaining multiple magnifications of the biological cell detection microscope; Based on the multi-level magnification, combined with the optical performance detection factor, the biological cell detection microscope is expected to be analyzed to obtain multi-level resolution expected information, multi-level focusing accuracy expected information and multi-level focusing sensitivity expected information; Based on the multiple levels of magnification, performing resolution confidence detection on the biological cell detection microscope to obtain multiple levels of resolution confidence detection information; Performing deviation analysis on the multi-level resolution confidence detection information based on the multi-level resolution expectation information to obtain a resolution expectation deviation detection result; Based on the multi-level magnification and the multi-level focusing accuracy expected information, performing focusing accuracy detection and analysis on the biological cell detection microscope to obtain a focusing accuracy expected deviation detection result; Based on the multi-level magnification and the multi-level focus sensitivity expected information, performing focus sensitivity detection and analysis on the biological cell detection microscope to obtain a focus sensitivity expected deviation detection result; adding the resolution expected deviation detection result, the focus accuracy expected deviation detection result and the focus precision expected deviation detection result to the multi-feature optics expected deviation detection result; Wherein, performing multimodal stability detection based on the biological cell detection microscope to obtain the microscope stability quality coefficient includes: Obtain multi-level predetermined time windows and non-interference biological cell detection scenarios; Based on the multi-level predetermined time windows and the non-interference biological cell detection scenario, biological cell detection is performed according to the biological cell detection microscope to obtain biological cell detection results of multiple nodes; Perform imaging quality comparison based on the biological cell detection results of the multiple nodes to obtain imaging quality comparison results of the multiple node detections; Perform stability evaluation based on the comparison results of the imaging qualities detected by the multiple nodes, obtain a static stability coefficient of the microscope, and add the static stability coefficient of the microscope to the stability quality coefficient of the microscope; Wherein, performing multimodal stability detection based on the biological cell detection microscope to obtain the microscope stability quality coefficient includes: Based on the biological cell detection microscope, test interference information is collected to establish multiple interference biological cell detection scenes, wherein the biological cell samples of the multiple interference biological cell detection scenes are the same; obtaining a sample reference image of the biological cell sample; Based on the multiple interfering biological cell detection scenes, performing biological cell detection according to the biological cell detection microscope to obtain multiple interfering scene detection images; Based on the sample reference imaging, performing imaging quality change recognition on the multiple interference scene detection imaging to obtain multiple imaging quality change recognition results; Performing stability evaluation based on the multiple imaging quality change identification results to obtain a microscope dynamic stability coefficient, and adding the microscope dynamic stability coefficient to the microscope stability quality coefficient; According to the microscope application scenario factor, the biological cell detection microscope is subjected to application scenario performance detection and analysis to obtain the microscope application performance quality coefficient, including: Based on the microscope application scene factor, application scene information of the biological cell detection microscope is collected and sorted to obtain a microscope application scene space; Based on the microscope application scenario space, M test application scenarios satisfying the application scenario comparison constraint are established, where M is a positive integer greater than 1; Performing application performance testing and analysis on the biological cell detection microscope based on the M test application scenarios to obtain M scenario application performance coefficients; Performing importance evaluation based on the M test application scenarios, obtaining application scenario importance evaluation results, and setting application performance weights of the M scenarios according to the application scenario importance evaluation results; The M scene application performance coefficients are weightedly calculated based on the M scene application performance weights to generate the microscope application performance quality coefficient.

2. The method according to claim 1, characterized in that Based on the M test application scenarios, the biological cell detection microscope is subjected to application performance detection and analysis to obtain M scenario application performance coefficients, including: Extracting the mth test application scenario according to the M test application scenarios, where m is a positive integer, 1≤m≤M; Based on the mth test application scenario, performing biological cell detection according to the biological cell detection microscope to obtain an mth test result; Load the microscope test result record set and the microscope application performance evaluation record set; Performing integrated learning based on the microscope detection result record set and the microscope application performance evaluation record set to generate a microscope application performance evaluation channel; Based on the mth test detection result, according to the microscope application performance evaluation channel, the mth scene application performance coefficient is obtained, and the mth scene application performance coefficient is added to the M scene application performance coefficients.

3. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; Wherein, the processor is used to execute the quality detection method of a biological cell detection microscope as described in any one of claims 1 to 2.

4. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, so that the computer program is used to execute the quality detection method of a biological cell detection microscope as described in any one of claims 1 to 2.

Images