A data processing method and system applied to a flow cytometer

Abstract

The present invention discloses a data processing method and system applied to a flow cytometer, which relates to the technical field of data processing; the system includes a sorting module, a collection module, a screening module, a filtering module, and a statistics module: Sorting module: Obtain the photoacoustic signal data of the cells of the type to be collected from the database, process the photoacoustic signal data, calculate the standard threshold range, and obtain the characteristic screening categories; the technical key points are: analyze and process the characteristics of the cells of the type to be collected, formulate a multi-level screening scheme for the characteristics, use the multi-level screening method to realize the recognition and judgment of the cells, and based on the characteristic screening, most of the data can be screened out, greatly reducing the amount of data for subsequent data processing, thereby effectively reducing the equipment cost required for processing data, and also greatly improving the efficiency, with good use effects and good application prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a data processing method and system applied to a flow cytometer. Background Art

[0002] A flow cytometer is a device for automatically analyzing and sorting cells. It can quickly measure, store, and display a series of important biophysical and biochemical characteristic parameters of dispersed cells suspended in a liquid, and can sort out a specified cell subset according to a preselected parameter range.

[0003] In recent years, cell detection methods based on fluorescence effects have developed rapidly. People have invented a method for detecting a certain cell population with cell markers. The specific method is to label cells with fluorescent molecules in vitro and then inject the cells into the body for detection. The markers on the target cells can achieve optical absorption detection. This method is suitable for the early diagnosis of major diseases such as malignant tumors in the laboratory. However, since this detection method requires various staining agents or markers, and the injection after labeling will produce toxicity to the normal internal environment in the animal body, the reliability of the measurement results decreases.

[0004] Currently, a Chinese patent with the patent literature number "CN116698709B" discloses a data processing method for a flow cytometer and a flow cytometer. It records the imaging test parameters of different lasers of the flow cytometer in advance and constructs a labeling template under different test parameters; among them, the labeling template is used to label the cell data detected by the flow cytometer; obtain the image signal data output by the flow cytometer, and import the image signal data into the labeling template according to the laser type to generate multiple image data sets, and calculate the portrait deviation; among them, each image data set is set with the particle time coding of the cells; determine the cell images cut under different lasers through the image data sets; count different cells according to the cell coding images and particle time coding, and determine the counting deviation between the particle counting data and the mean data under different lasers; judge the cell detection data corresponding to the closest portrait deviation and counting deviation, and use it as the final detection data.

[0005] However, in the process of implementing the above technical solution, it is found that there are at least the following technical problems:

[0006] First, the flow cytometer used is an image-based flow cytometer. This kind of flow cytometer is suitable for the early diagnosis of major diseases such as malignant tumors in the laboratory. However, since this detection method requires various staining agents or markers, and the injection after labeling will produce toxicity to the normal internal environment in the animal body, the reliability of the measurement results decreases. Similarly, because it requires pre-treatment, it is not applicable in many scenarios, so its applicability is low;

[0007] Second, for a photoacoustic flow cytometer, the scheme it adopts for cell recognition is to process the collected data and then input it into a neural network model for a comprehensive comparison with all the data of this type of cell, and then output the recognition result. Since the data collection of a photoacoustic flow cytometer is based on the time domain, the photoacoustic data of a cell is very complex. This type of recognition method requires a very large amount of data to be processed and a lot of data to be compared, resulting in very low data processing efficiency and very high requirements for related equipment, which does not meet the needs of those skilled in the art. Therefore, a data processing method and system for a flow cytometer are provided. Summary of the Invention

[0008] To achieve the above objectives, the present invention is realized through the following technical solutions:

[0009] A data processing system for a flow cytometer, the system includes an arrangement module, a collection module, a screening module, a selection module, and a statistics module:

[0010] Arrangement module: Obtain the photoacoustic signal data of the cells to be collected of the type from the database, process the photoacoustic signal data, calculate the standard threshold interval, and obtain the characteristic screening categories;

[0011] Collection module: Preprocess the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal data set;

[0012] Screening module: Screen the preprocessed photoacoustic signal data set by means of the standard threshold interval, eliminate the photoacoustic signals that do not meet the standard threshold interval, and obtain the remaining photoacoustic signal set;

[0013] Selection module: Obtain the number of recognition acquisition points corresponding to the characteristic screening categories of the cells to be collected, and the corresponding data interval, obtain the data corresponding to the number of recognition acquisition points of the photoacoustic signals in the remaining photoacoustic signal set, and compare it with the data interval, count the comparison results, and calculate the compliance;

[0014] Statistics module: Compare the compliance with a preset interval, use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and an elimination set. Here, the classification algorithm adopts a common threshold comparison classification method, and comprehensively analyzes the photoacoustic signals in the suspected set for reclassification, count the number of photoacoustic signals in the standard set, and mark the data and compliance to generate a detection data report.

[0015] Furthermore, the photoacoustic signal data of the type of cells to be collected is a certified real photoacoustic signal set containing the type of cells to be collected, the number of real photoacoustic signals in the real photoacoustic signal set is M groups, and the photoacoustic signal data includes but is not limited to average signal intensity, signal integral value, pulse height, pulse width and pulse area.

[0016] Furthermore, the steps of processing the photoacoustic signal data and calculating the standard threshold interval are as follows:

[0017] Obtain the type of collected cells, obtain the preset category ranking of the cell type based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics from the database, and select the first K screening categories, 3≤K≤5;

[0018] A feature extraction algorithm is used to extract M groups of photoacoustic signal data according to the screening categories to obtain K data sets;

[0019] Use statistical methods to process the data in K data sets one by one to generate K standard intervals;

[0020] The K standard intervals are aggregated to obtain the standard threshold interval.

[0021] Furthermore, the steps of using statistical methods to process the data in the K data sets one by one and generate K standard intervals are as follows:

[0022] Calculate the average value of K data sets , where is the average value of the ith data set, for The result is rounded to 3 decimal places. is the jth group of data in the i-th data set;

[0023] Determine the maximum and minimum values ​​of the data in the K data sets, and calculate the difference ratios between the maximum and minimum values ​​and the average value, compare the difference ratios, obtain the maximum difference ratio Q, and calculate the adjusted ratio Qt. , where To adjust the ratio, 3%≤ ≤6%;

[0024] Calculate K standard intervals based on Qt .

[0025] Furthermore, the preprocessing of the photoacoustic signal collected in real time by the flow cytometer is to perform wavelet analysis denoising on the collected photoacoustic signal, and the wavelet analysis denoising adopts a default threshold denoising.

[0026] Further, the steps for screening the preprocessed photoacoustic signal dataset are as follows:

[0027] Obtain the photoacoustic signal data corresponding to the collected photoacoustic signals. Compare each of the K groups of data in the photoacoustic signal data with the K standard intervals recorded in the standard threshold interval. Calculate the Euclidean distance between the feature vector and the boundaries of the standard interval through the boundary recognition model, and determine whether the K groups of data are within the corresponding K standard intervals;

[0028] If it is outside the standard interval, delete the photoacoustic signal;

[0029] If it is within the standard interval, retain the photoacoustic signal. Randomly select C groups of pulse height data from the retained photoacoustic signals and the M groups of real photoacoustic signal data. Perform similarity analysis on each of the C groups of data extracted from the retained photoacoustic signals and the C groups of data randomly selected from the M groups of real photoacoustic signals to obtain M groups of similarity data. The formula for calculating similarity is as follows;

[0030] In the formula, is the similarity between the detected photoacoustic signal and the i-th group of real photoacoustic signals, is the photoacoustic signal data of the j-th type in the collected photoacoustic signals, is the photoacoustic signal data of the j-th type extracted from the i-th group of real photoacoustic signals, is the adjustment coefficient;

[0031] Obtain the maximum value among the M groups of similarity data, that is, the maximum similarity, and compare the maximum similarity with the standard similarity. If the maximum similarity is less than the standard similarity, delete the photoacoustic signal;

[0032] If the maximum similarity is greater than or equal to the standard similarity, retain the photoacoustic signal;

[0033] Summarize the retained photoacoustic signals after deletion to form the remaining photoacoustic signal set.

[0034] Further, the characteristic screening categories include but are not limited to instantaneous intensity, instantaneous frequency, and instantaneous phase. The acquisition type cell characteristic screening category is one of them. The value range of the identified number of acquisition points L is from 30 to 50, and the data interval corresponding to the identified acquisition points is , is the characteristic screening category data of the i-th identified acquisition point in the photoacoustic signal corresponding to the maximum similarity, B is the fluctuation coefficient, 2% ≤ B ≤ 5%, count the comparison results, the number of data that do not conform to the data interval is P groups, and the calculated conformity .

[0035] Further, the preset intervals include the standard data interval and the suspected data interval and the data rejection interval , ;

[0036] Compare the compliance with a preset interval, and use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and a rejection set.

[0037] Further, the steps for comprehensively analyzing the photoacoustic signals in the suspected set are as follows:

[0038] Use signal processing technology to equally divide the photoacoustic signals in the suspected set and their corresponding photoacoustic signals with the maximum similarity into E segments;

[0039] Compare the pulse heights in the E segments, and obtain the full width at half maximum value and the frequency bandwidth of the photoacoustic signal in the segment with the highest pulse height;

[0040] Compare the full width at half maximum value and the frequency bandwidth of the photoacoustic signals in the suspected set with those of the photoacoustic signals corresponding to the maximum similarity, and calculate the cell similarity index;

[0041] The specific calculation formula is as follows:

[0042] In the formula, is the cell similarity index, is the full width at half maximum value of the photoacoustic signal in the suspected set, the full width at half maximum value of the photoacoustic signal corresponding to the maximum similarity, is the weight ratio corresponding to the ratio of the difference in full width at half maximum values, is the frequency bandwidth of the photoacoustic signal in the suspected set, is the frequency bandwidth of the photoacoustic signal corresponding to the maximum similarity, is the weight ratio corresponding to the ratio of the difference in frequency bandwidths;

[0043] If the calculated cell similarity index is less than the set value, then divide the photoacoustic signal into the rejection set;

[0044] If the calculated cell similarity index is greater than or equal to the set value, then divide the photoacoustic signal into the standard set.

[0045] Further, a data processing method applied to a flow cytometer includes the following steps:

[0046] Obtain the photoacoustic signal data of the cells to be collected from the database, process the photoacoustic signal data, calculate the standard threshold interval, and obtain the characteristic screening category;

[0047] Preprocess the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal dataset;

[0048] Sieve the preprocessed photoacoustic signal dataset with a standard threshold range, eliminate the photoacoustic signals that do not meet the standard threshold range, and obtain the remaining photoacoustic signal set;

[0049] Obtain the number of recognition acquisition points corresponding to the cell characteristic screening category of the acquisition type, and the corresponding data range. Obtain the data corresponding to the number of recognition acquisition points of the photoacoustic signals in the remaining photoacoustic signal set, compare it with the data range, count the comparison results, and calculate the compliance;

[0050] Compare the compliance with a preset range, use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and an elimination set, comprehensively analyze the photoacoustic signals in the suspected set for reclassification, count the number of photoacoustic signals in the standard set, and mark the data and compliance to generate a detection data report.

[0051] The present invention provides a data processing method and system applied to a flow cytometer, which has the following beneficial effects:

[0052] (1). The present invention provides a data processing method and system applied to a flow cytometer, which analyzes and processes the characteristics of the cells to be collected, formulates a multi-level screening scheme for the characteristics, and uses the multi-level screening method to realize the identification and judgment of the cells. Based on the characteristic screening, most of the data can be screened out, greatly reducing the amount of data for subsequent data processing, thereby effectively reducing the equipment cost required for data processing, greatly improving the efficiency, having a good use effect, having a good use prospect, and solving the problems proposed in the background technology.

[0053] (2). The present invention provides a data processing method and system applied to a flow cytometer. In the process of screening data, it does not adopt the way of complete data comparison. It processes the real-time monitored photoacoustic data based on the commonality of the characteristic data. This way greatly reduces the amount of data comparison, and then uses the way of randomly extracting data for comparison to obtain the closest recognized photoacoustic signal. Finally, through further analysis and judgment, through this multi-level screening method, the data processing volume can be reduced by 65%, having a good use effect and having a good application prospect.

[0054] (3). The present invention provides a data processing method and system applied to a flow cytometer. It sets a suspected set, increases the analysis and determination scheme for the suspected set, makes a separate judgment on the photoacoustic signals in the suspected set, and uses the full width at half maximum value and frequency bandwidth of the most obvious characteristic time period for screening. It can more accurately and quickly realize the identification of cells, and using this method, the amount of data operation increases less, but the accuracy rate of cell identification is greatly improved, basically reaching more than 96%, having a good use effect, so this scheme has a good application prospect. Brief Description of the Drawings

[0055] Figure 1 is the overall flow block diagram of the present invention;

[0056] Figure 2 is the step diagram for calculating the standard threshold interval in the present invention;

[0057] Figure 3 is the step diagram for screening the preprocessed photoacoustic signal dataset in the present invention. Detailed Embodiments

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] With the development of society, cell detection methods based on fluorescence effects have developed rapidly. People have invented a method for detecting a certain cell population using cell markers. The specific method is to label cells with fluorescent molecules in vitro and then inject the cells into the body for detection. The markers on the target cells can achieve optical absorption detection. This method is suitable for the early diagnosis of major diseases such as malignant tumors in the laboratory. However, since this detection method requires various staining agents or markers, and the injection after labeling will be toxic to the normal internal environment in the animal body, resulting in a decrease in the reliability of the measurement results.

[0060] In the photoacoustic detection of biological tissues, researchers use pulsed lasers of a certain wavelength. Through a series of optical path modulations, the laser spot is irradiated on the tissue of a living animal. Due to the photoacoustic effect in the biological tissue, photoacoustic signals will be generated in the target cells in the animal body. Different target cells have differences in the absorption of the laser, so the ultrasonic signals they emit will also be different in some aspects. The in-vivo photoacoustic detection method can avoid various defects of in-vitro labeling and maintain the stability of the internal environment of the experimental individual.

[0061] In short, researching and developing a data processing method for in-vivo photoacoustic flow cytometry has the advantages of real-time cell monitoring, non-invasive cell diagnosis, and no need for labeling, and also avoids the inaccuracy caused by in-vitro detection; in addition, it combines the advantages of ultrasonic signals such as no cytotoxicity and deep penetration depth in living tissues, especially can be used for the identification of special cells such as cancer cells.

[0062] As Figure 1 shown, the specific implementation plan is as follows:

[0063] In terms of instrument selection:

[0064] The core of this solution lies in the innovation of the data processing method for cell photoacoustic signals. It is a data processing method proposed based on solving the current problems encountered in the analysis and processing of photoacoustic signals. The photoacoustic signals generated in the experiment come from a living photoacoustic flow cytometer, and relevant data is directly obtained through the Internet of Things.

[0065] When different cells are irradiated by pulsed lasers, due to the different internal structures of the cells, the light absorption of the cells is also different. After absorbing light, the temperature inside the cells will change, resulting in changes in regional structure or volume. Therefore, when we irradiate cells with a pulsed light source, the continuous change in temperature will cause the cells to expand and contract in volume, and then enable the cells to emit sound waves outward.

[0066] When cells flow through the focal plane of the focused laser, since the excitation light of the cells in this wavelength band has a high absorption spectrum different from the background, it will absorb electromagnetic wave energy, the tissue temperature rises, local volume expansion occurs, and then ultrasonic waves are generated by vibration. Different cells will radiate ultrasonic signals of different frequencies due to their respective characteristics, so quantitative detection of cells can be achieved.

[0067] In terms of data reception:

[0068] First, data arrangement:

[0069] In this invention, the data acquisition is to connect the server to the database through the Internet of Things, and the recognized standard cell database collected historically can be directly collected. There are various types of data stored in the standard cell database, and they are classified, that is, the photoacoustic data of the same type of cells collected under the same collection parameters of the living photoacoustic flow cytometer.

[0070] When the standard cell database is constructed, through relevant analysis, the obvious characteristics of the photoacoustic data of different cell types are marked, and these data are summarized and sorted to form a category sorting based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics, and the characteristic screening categories are marked.

[0071] Before use, it is necessary to know the type of cells to be identified, then know the collection parameters set by the living photoacoustic flow cytometer for this collection, and then find the classified data set corresponding to its collection parameters. For example: the number of sampling points collected per unit time is the same. If it is different, comparison cannot be carried out, so preprocessing is required. This process is based on the arrangement module of this solution.

[0072] The arrangement module obtains the photoacoustic signal data of the cells to be collected from the database, processes the photoacoustic signal data, calculates the standard threshold interval, and obtains the characteristic screening category.

[0073] The photoacoustic signal is the basic data collected by the in-vivo photoacoustic flow cytometer, while the photoacoustic signal data is the data obtained after processing the photoacoustic signal.

[0074] The steps to process the photoacoustic signal data and calculate the standard threshold interval are as follows:

[0075] Obtain the type of the collected cells, obtain the preset category ranking based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics from the database, and select the top K screening categories, where 3 ≤ K ≤ 5; for example, for tumor cells, the top 3 categories with high correlation with tumor characteristics can be selected.

[0076] The photoacoustic signals exhibited by different types of cells show different situations, that is, there are some obvious characteristics. For example, there are many types of cell sizes, so there are many cases where the cell sizes are relatively close. At this time, the number of pulse areas close to each other is relatively large. Therefore, using the pulse area for screening has poor effects. Therefore, corresponding evaluations are made during the construction of the database, and the category ranking based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics is listed to facilitate subsequent comparisons, so it is more convenient to use later.

[0077] The selection of the top K screening categories can be further participated by humans. For example, the external environment during this batch of detections is different, and the category ranking based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics is not completely applicable to a certain extent. Therefore, the external environment and the cells to be collected can also be input into the computer in advance, and the category ranking based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics in this case is retrieved from the database. The category rankings based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics are not completely the same. They are generated during historical detections, aiming to facilitate subsequent detections more conveniently.

[0078] Such as Figure 2 As shown, use the feature extraction algorithm to extract the M groups of photoacoustic signal data according to the screening categories to obtain K data sets. This step classifies the data and makes it more convenient for comparison. Each set corresponds to a screening category, reflecting specific cell information; such as principal component analysis, linear discriminant analysis, etc., to screen and reduce the dimensions of the features, remove redundant or irrelevant features, and retain the most representative and discriminative features for subsequent classification and recognition tasks;

[0079] Use statistical methods to process the data in the K data sets one by one to generate K standard intervals. The specific steps are as follows:

[0080] Calculate the average value of the K data sets , where is the average value of the i-th data set, For the result is rounded to three decimal places, where [[ ]] is the j-th group of data in the i-th data set. The main effect of designing decimals is to facilitate calculations and reduce the amount of data processing;

[0081] Determine the maximum and minimum values among the data in K data sets, and calculate the difference ratios between the maximum and minimum values and the average value respectively. Compare the magnitudes of the difference ratios to obtain the maximum difference ratio Q. For example, if the calculated maximum value is 25, the calculated average value is 20, and the calculated minimum value is 16, then the difference ratio calculated between the maximum value and the average value is (25 - 20) / 20×100% = 25%, and the difference ratio calculated between the minimum value and the average value is (20 - 16) / 20×100% = 20%. Then the maximum difference ratio Q is 25%;

[0082] And calculate the adjusted ratio Qt, , where is the adjustment ratio, 3% ≤ [[ ]] ≤ 6%; ≤ 6%;

[0083] Summarize the K standard intervals to obtain the standard threshold interval.

[0084] Based on Qt, calculate the K standard intervals , each interval is used for separate comparison. This step is set in advance and can be directly called during subsequent comparison without on-site calculation during data comparison, thus improving the efficiency of data comparison.

[0085] Secondly, data acquisition: In the present invention, data acquisition is achieved by using a server to dock with a living photoacoustic flow cytometer through the Internet of Things to obtain the photoacoustic data collected by the living photoacoustic flow cytometer, and this process is based on the existing acquisition module.

[0086] Acquisition module: Preprocess the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal data set;

[0087] The photoacoustic signal data of the cells to be collected is a certified set of real photoacoustic signals containing the cells of the collection type. The number of real photoacoustic signals in the real photoacoustic signal set is M groups. The photoacoustic signal data includes but is not limited to average signal intensity, signal integral value, pulse height, pulse width, and pulse area.

[0088] Preprocessing the photoacoustic signals collected by the flow cytometer in real time is to perform wavelet analysis denoising on the collected photoacoustic signals, and the wavelet analysis denoising uses default threshold denoising.

[0089] Wavelet analysis is used to denoise the collected photoacoustic signals to ensure the purity and accuracy of the signal data and improve the reliability of subsequent analysis. The signal is decomposed by wavelet transform to remove the noise components and retain the effective signal features, and finally a high-quality photoacoustic signal is obtained, laying a solid foundation for the accurate identification and analysis of subsequent cells. High-quality data ensures the accuracy of the analysis and improves the reliability and scientific nature of the experimental results.

[0090] Wavelet denoising can characterize and represent the local feature information of the signal both in the time domain and the frequency domain. The theoretical basis of wavelet analysis is to perform various analyses using wavelet functions. After the signal is decomposed by wavelet, the amplitude of its wavelet coefficients will be higher than that of the noise wavelet coefficients. When denoising, the wavelet coefficients of the signal are preserved and the wavelet coefficients of the noise are removed. The denoised signal is obtained by performing an inverse transform on the retained wavelet coefficients.

[0091] The process of wavelet analysis denoising generally can be divided into the following three steps: wavelet decomposition of the signal, threshold quantization of the high-frequency coefficients obtained by wavelet decomposition, and wavelet reconstruction of the coefficients. The key is how to select the threshold and perform threshold quantization. To some extent, the selection of the threshold is related to the quality of wavelet denoising.

[0092] The default threshold denoising process selects the wdencmp function, which performs excellently in compressing or denoising one-dimensional and two-dimensional signals.

[0093] Regarding the above wavelet analysis denoising scheme, this application does not improve its method. It is only a related application of the existing technology, and those skilled in the art also have the scheme of using wavelet analysis denoising for photoacoustic processing. Therefore, it will not be described in detail, and those skilled in the art clearly understand how to implement the related technology.

[0094] Secondly, data screening: After the complete photoacoustic signal is collected and further processed to remove a part of the interference signals, the photoacoustic signal of the cell is obtained. For further analysis, the obtained photoacoustic signal of the cell needs to be further screened to obtain a more standard photoacoustic signal, and the screening of the photoacoustic signal of the cell depends on the screening module.

[0095] Screening module: Screen the preprocessed photoacoustic signal dataset by means of a standard threshold interval, remove the photoacoustic signals that do not meet the standard threshold interval, and obtain the remaining photoacoustic signal set;

[0096] As Figure 3 shown, the steps of screening the preprocessed photoacoustic signal dataset are as follows:

[0097] Obtain the photoacoustic signal data corresponding to the collected photoacoustic signals, compare each of the K groups of data in the photoacoustic signal data with the K standard intervals recorded in the standard threshold interval one by one, calculate the Euclidean distance between the feature vector and the boundary of the standard interval through the boundary recognition model, and determine whether the K groups of data are within the corresponding K standard intervals;

[0098] The boundary recognition model uses the K standard intervals recorded in the standard threshold interval as prior knowledge. Input the converted feature vector into the model, and the model quickly calculates the Euclidean distance between the feature vector and the boundary of the standard interval through the internal calculation logic, and then accurately determines whether the K groups of data are within the corresponding K standard intervals.

[0099] If it is outside the standard interval, it indicates that the data belongs to a very large difference from the required data, so it is not the required data. Therefore, delete the photoacoustic signal. Because the standard interval is formulated based on all data, its range is very wide. If the photoacoustic signal does not meet the requirements in this case, it means that the photoacoustic signal definitely does not belong to the photoacoustic signal of the collected cells. Therefore, delete the photoacoustic signal of this cell, thereby reducing the subsequent data processing volume, which is convenient to use and has a good use effect.

[0100] If it is within the standard interval, retain the photoacoustic signal. In this case, it indicates that the signal may meet the requirements, but it is not certain whether it is specifically. Therefore, secondary verification still needs to be carried out later, so subsequent steps are required to process the photoacoustic data;

[0101] Randomly select C types of photoacoustic signal data from the retained photoacoustic signals and the M groups of real photoacoustic signal data, and perform similarity analysis on each of the C groups of data extracted from the retained photoacoustic signals and the C groups of data randomly extracted from the M groups of real photoacoustic signals one by one; when extracting, extract C types, and then retrieve the photoacoustic signal data corresponding to the C types of photoacoustic signals and real photoacoustic signals, so as to obtain C groups of data;

[0102] Adopting the method of randomly extracting data and the method of local comparison can greatly reduce the data comparison volume. The main reason is that the amount of normal cell photoacoustic signal data is very large. Using the methods of complete comparison or waveform comparison, the amount of data to be compared is relatively large; obtain M groups of similarity data, and the formula for calculating similarity is as follows;

[0103] In the formula, is the similarity between the detected photoacoustic signal and the i-th group of real photoacoustic signals, is the photoacoustic signal data of the j-th type in the collected photoacoustic signals, is the photoacoustic signal data of the j-th type extracted from the i-th group of real photoacoustic signals, is the adjustment coefficient, C>K;

[0104] The above similarity calculation formula is mainly obtained by improving the existing Pearson correlation coefficient. It mainly uses the Pearson correlation coefficient to calculate the correlation of each data after correction. The higher the correlation, the closer the two data are, and thus the higher the similarity.

[0105] The calculation of similarity is mainly to determine which identified photoacoustic data the photoacoustic data of this cell is close to, facilitating subsequent comparison and judgment, which is equivalent to a basic identification process, and the purpose is also to screen.

[0106] The scheme for calculating similarity in this collection adds the corresponding adjustment coefficient, and the comparison effect is better.

[0107] The adjustment coefficient is to correct the data.

[0108] The adjustment coefficient is not weight data. The adjustment coefficient is set according to the characteristics of the photoacoustic signal data type of this cell. Different types of data are different, and at different times, the same type also has a large gap. Therefore, adjustment is required.

[0109] For example, the basis of the pulse height data in the cell photoacoustic signal is in the thousands level, while some data are in the hundreds level or single digits. If the similarity is calculated directly, the gap is very large. Therefore, separate correction is required to ensure the accuracy of the calculation. Regarding the large gap of the same type at different times, for example, the pulse height data of the cell photoacoustic signal is completely different in different stages, which is mainly set based on the current detection results. For example, there are two sets of data, 6000 and 2000, in the pulse height of a single cell photoacoustic signal. Since the same ratio is used, the adjustment coefficient will make the data of 6000 have a greater impact. Therefore, when designing, the corresponding to 6000 is smaller, and the

[0110] corresponding to 2000 is

[0111] larger, so as to eliminate the influence of data fluctuations in different stages and improve the accuracy of similarity analysis. For the convenience of calculation, when the pulse height is selected, generally the maximum pulse height is used for calculation.

[0112] Obtain the maximum value among the M groups of similarity data, that is, the maximum similarity, and compare the maximum similarity with the standard similarity. If the maximum similarity is less than the standard similarity, then delete this photoacoustic signal. This situation is mainly due to the relatively low data similarity, indicating that it is not similar to the data, so it is excluded.For example, when M is taken as 5, the calculated similarity data are 0.65, 0.68, 0.72, 0.61, and 0.68 respectively. The maximum value is 0.72. If the standard similarity is 0.70, then this data is retained. If the standard similarity is 0.75, then this data is excluded. This method effectively screens high-quality data and ensures the accuracy of subsequent analysis. By continuously optimizing and adjusting the coefficients, the recognition accuracy is improved, laying a solid foundation for subsequent in-depth research.

[0113] If the maximum similarity is greater than or equal to the standard similarity, then the photoacoustic signal is retained, indicating that they are relatively similar and there is a certain possibility that it is the photoacoustic signal to be collected.

[0114] The remaining photoacoustic signals after deletion are summarized to form the remaining photoacoustic signal set.

[0115] The present invention provides a data processing method and system applied to a flow cytometer, which analyzes and processes the characteristics of cells to be collected, formulates a multi-level screening scheme for the characteristics, and realizes the recognition and judgment of cells by means of multi-level screening. Based on the characteristic screening, most of the data can be screened out, greatly reducing the amount of data for subsequent data processing, thereby effectively reducing the equipment cost required for processing data and greatly improving the efficiency. It has a good use effect and a good application prospect, and solves the problems raised in the background technology.

[0116] After that, data screening: After collecting the complete photoacoustic signal, and further processing the collected photoacoustic signal to remove a part of the interference signals, the photoacoustic signal of the cell is obtained. After further analysis, the obtained photoacoustic signal of the cell is further screened to obtain the remaining photoacoustic signal set. Then, it is further judged to determine whether the photoacoustic signals in the remaining photoacoustic signal set meet the collection requirements. Therefore, it is necessary to further screen the photoacoustic signals in the remaining photoacoustic signal set, and this process is based on the screening module.

[0117] Screening module: Obtain the recognition acquisition bit numbers corresponding to the characteristic screening categories of the cells to be collected, and the corresponding data intervals. Obtain the data corresponding to the recognition acquisition bit numbers of the photoacoustic signals in the remaining photoacoustic signal set, and compare it with the data intervals, count the comparison results, and calculate the compliance.

[0118] The characteristic screening categories include but are not limited to instantaneous intensity, instantaneous frequency, and instantaneous phase. The characteristic screening categories mainly focus on real-time data. Instead of comparing from the overall data globally, they focus on the characteristic changes at specific instants, so as to more accurately capture the dynamic characteristics of cells. Through this meticulous screening, it is ensured that the collected photoacoustic signals are both real and representative, providing reliable data support for subsequent in-depth analysis and research.

[0119] The acquisition type cell characteristic screening category is one of them. The value range of the recognized acquisition point number L is from 30 to 50. The higher the acquisition point number L, the higher the accuracy, but the data processing volume will also increase, and the data processing time will also increase accordingly, thus affecting the overall efficiency. In the existing solution, when using a convolutional neural network for one-time determination, usually more than 512 data points are taken from the photoacoustic signal, and then each is compared with the recognized photoacoustic data in the database one by one. The amount of data to be compared is very large. Moreover, when there is a local data mismatch, multiple data items need to be compared, that is, repeatedly compared with more than five hundred groups of data, which is rather cumbersome and involves a large amount of data processing. Therefore, the corresponding hardware requirements are relatively high;

[0120] The data interval corresponding to the recognized acquisition point is , is the characteristic screening category data of the i-th recognized acquisition point in the photoacoustic signal corresponding to the maximum similarity. B is the fluctuation coefficient, 2% ≤ B ≤ 5%. The comparison results are statistically analyzed. The number of data that do not conform to the data interval is P groups. The calculated conformity , and it can also be directly acquired.

[0121] The higher the conformity, the closer the acquired photoacoustic signal is to the recognized photoacoustic signal, indicating a higher similarity, and the greater the possibility of being the required type of cells for acquisition.

[0122] The present invention provides a data processing method and system applied to a flow cytometer. In the process of screening data, it does not adopt the way of complete data comparison. It processes the real-time monitored photoacoustic data based on the commonality of characteristic data. This way greatly reduces the amount of data comparison. Then, the method of randomly extracting data for comparison is used to obtain the closest recognized photoacoustic signal, and finally further analysis and judgment are carried out. Through this multi-level screening method, the data processing volume can be reduced by 65%, and the use effect is good, having a good application prospect.

[0123] Finally, data statistics: After analyzing the conformity of the photoacoustic signal, it is necessary to further compare and judge in combination with the conformity to identify the photoacoustic signal, and this process is based on the screening module.

[0124] Statistics module: Compare the conformity with a preset interval, and use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and a rejection set. Here, the classification algorithm adopts the common method of threshold comparison classification, and comprehensively analyzes the photoacoustic signals in the suspected set for further division, counts the number of photoacoustic signals in the standard set, and marks the data and conformity to generate a detection data report.

[0125] Compare the conformity with a preset interval, and use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and a rejection set.

[0126] The preset intervals include the standard data interval , the suspected data interval and the excluded data interval , ; , the photoacoustic signals within the standard data interval are regarded as high-confidence samples, those within the suspected data interval need to be further verified, and those within the excluded data interval are excluded. Through this process, the accuracy and reliability of the final determination of photoacoustic signals are ensured.

[0127] The steps for comprehensively analyzing the photoacoustic signals concentrated in the suspected cases are as follows:

[0128] Using signal processing techniques, the photoacoustic signals concentrated in the suspected cases and their corresponding photoacoustic signals with the maximum similarity are equally divided into E segments; for example, in this process, a Gaussian model can be used to describe the distribution characteristics of the signals to ensure the scientificity and accuracy of signal segmentation;

[0129] Compare the pulse heights in the E segments to obtain the full width at half maximum value and the frequency bandwidth of the photoacoustic signal in the segment with the highest pulse height; the full width at half maximum value can directly reflect the time width of the signal pulse at half of the intensity, while the frequency bandwidth reflects the frequency range covered by the signal;

[0130] Compare the full width at half maximum value and the frequency bandwidth of the photoacoustic signal concentrated in the suspected cases with those of the photoacoustic signal with the maximum similarity, and calculate the cell similarity index;

[0131] The specific calculation formula is as follows:

[0132] In the formula, is the cell similarity index, is the full width at half maximum value of the photoacoustic signal concentrated in the suspected cases, the full width at half maximum value of the photoacoustic signal with the maximum similarity, is the weight ratio corresponding to the full width at half maximum value difference ratio, is the frequency bandwidth of the photoacoustic signal concentrated in the suspected cases, is the frequency bandwidth of the photoacoustic signal with the maximum similarity, is the weight ratio corresponding to the frequency bandwidth difference ratio, < , + = 1;

[0133] If the calculated cell similarity index is less than the set value, the photoacoustic signal is classified into the exclusion set;

[0134] If the calculated cell similarity index is greater than or equal to the set value, the photoacoustic signal is classified into the standard set.

[0135] Mark the data and compliance. When generating the detection data report, the data of the degree of uniform distribution can be marked, which is beneficial to subsequent further detection.

[0136] The detection data report also contains the final ratio data, that is, the ratio of the number of cells of this type detected to the total number of cells; the data obtained by screening the preprocessed photoacoustic signal dataset through the standard threshold interval is the photoacoustic signal of the cells, and the number of photoacoustic signals can be counted.

[0137] For the existing convolutional neural network model, if it wants to achieve this aspect, it is necessary to increase the output structure, and in addition, it is necessary to increase the calculation layer corresponding to cell recognition, which makes the amount of data processing even more huge, greatly reducing the efficiency and significantly increasing the cost. Therefore, the existing convolutional neural network model does not involve the data output in this aspect, so this aspect is difficult to achieve by the existing convolutional neural network model.

[0138] In actual use, since the photoacoustic signals concentrated in the suspected cases are less than the original data, basically less than 10%, therefore, a convolutional neural network processing model can also be constructed for the identification and authentication of photoacoustic signals. Through the convolutional neural network model, the features of the photoacoustic signals are further extracted to improve the recognition accuracy.

[0139] For example, an M-P neuron model is constructed. That is, when a neuron receives the input signal after the weighted addition calculation of the transmission paths from multiple other neurons in front, it will calculate the total input value received by the current neuron and compare it with the excitation threshold of this neuron, and use the activation function to judge whether this neuron is activated, that is, whether the neuron is excited, and it will be transmitted in turn according to this rule. Similar to logistic regression, the sigmoid function is used as the activation function in the neural network model.

[0140] In this solution, the neural network function package provided by MATLAB is used to build and train the feedforward neural network. The feedforward neural network is constructed by calling the newff() function, which includes three parameters, namely the normalized training samples, the output of the normalized training samples, and the number of neurons in the hidden layer.

[0141] The training set is a mixed data set of 20 - 30% authenticated photoacoustic data and 70 - 80% photoacoustic data authenticated as other cells.

[0142] During the training process, the input matrix is divided and randomly divided into a training set, a validation set, and a test set. After one training of the training set, the error is calculated on the validation set. If the training requirements are met, the training will stop; otherwise, the learning will continue to optimize the parameters. This process is repeated until the training result, until the recognition accuracy rate reaches more than 95%.

[0143] The present invention provides a data processing method and system applied to a flow cytometer, which sets a suspected set, increases the analysis and identification scheme for the suspected set, makes a separate judgment on the photoacoustic signals in the suspected set, and uses the full width at half maximum value and the frequency bandwidth of the most obvious characteristic time period for screening. It can accurately and quickly identify cells. Moreover, in this way, the amount of data operation increases less, but the accuracy rate of cell identification is greatly improved, basically reaching more than 96%, and the use effect is good. Therefore, this scheme has good application prospects.

[0144] The weight coefficient is determined by the coefficient of variation method. The coefficient of variation method is a method of assigning weights to each evaluation index according to the variation degree of the current value and the target value of each evaluation index; if the numerical difference of a certain index is large and can clearly distinguish each evaluated object, it means that the resolution information of this index is rich, so a larger weight should be given to this index; on the contrary, if the numerical differences of each evaluated object on a certain index are small, then the ability of this index to distinguish each evaluation object is weak, so a smaller weight should be given to this index; this method directly uses the information contained in each index and calculates the weight of the index through calculation, so it has objectivity.

[0145] A data processing method applied to a flow cytometer includes the following steps:

[0146] Obtain the photoacoustic signal data of the cells to be collected from the database, process the photoacoustic signal data, calculate the standard threshold interval, and obtain the characteristic screening category;

[0147] Preprocess the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal data set;

[0148] Use the standard threshold interval to screen the preprocessed photoacoustic signal data set, eliminate the photoacoustic signals that do not meet the standard threshold interval, and obtain the remaining photoacoustic signal set;

[0149] Obtain the number of recognition acquisition points corresponding to the characteristic screening category of the collected type of cells and the corresponding data interval, obtain the data corresponding to the number of recognition acquisition points of the photoacoustic signals in the remaining photoacoustic signal set, compare it with the data interval, count the comparison results, and calculate the compliance;

[0150] Compare the compliance with a preset interval, use a classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set, and an elimination set, conduct a comprehensive analysis of the photoacoustic signals in the suspected set for reclassification, count the number of photoacoustic signals in the standard set, and mark the data and compliance to generate a detection data report.

[0151] In the application, several formulas involved are calculated by taking their numerical values after dimensionless treatment. The establishment of the formulas is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. Some coefficients or weights in the formulas are set by those skilled in the art according to the actual situation, so no more details will be given here.

[0152] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application.

Claims

1. A data processing system for a flow cytometer, characterized in that: The system includes: Arrangement module: obtain the photoacoustic signal data of the type of cells to be collected from the database, process the photoacoustic signal data, calculate the standard threshold interval, and obtain the characteristic screening category; Acquisition module: pre-processing the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal data set; Screening module: Screen the preprocessed photoacoustic signal data set with the help of the standard threshold interval, remove the photoacoustic signals that do not meet the standard threshold interval, and obtain the remaining photoacoustic signal set; Screening module: obtain the number of identification collection points and the corresponding data interval corresponding to the collection type cell characteristic screening category, obtain the data corresponding to the number of identification collection points of the photoacoustic signal in the remaining photoacoustic signal set, and compare it with the data interval, statistically compare the results, and calculate the degree of conformity; Statistics module: compares the conformity with the preset interval, uses the classification algorithm to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set and a rejection set, and performs a comprehensive analysis on the photoacoustic signals in the suspected set for further division, counts the number of photoacoustic signals in the standard set, marks the data and conformity, and generates a test data report; The characteristic screening categories include but are not limited to instantaneous intensity, instantaneous frequency and instantaneous phase. The acquisition type cell characteristic screening category is one of them. The value range of the number of identification acquisition points L is 30 to 50. The data interval corresponding to the identification acquisition point is , The characteristic screening category data of the i-th identification collection point in the photoacoustic signal corresponding to the maximum similarity, B is the fluctuation coefficient, 2%≤B≤5%, and the statistical comparison results are compared. The number of data that do not meet the data interval is P group, and the calculated compliance .

2. A data processing system for flow cytometer according to claim 1, characterized in that: The photoacoustic signal data of the type of cells to be collected is a certified real photoacoustic signal set containing the type of cells to be collected. The number of real photoacoustic signals in the real photoacoustic signal set is M groups. The photoacoustic signal data includes but is not limited to average signal intensity, signal integral value, pulse height, pulse width and pulse area.

3. A data processing system for flow cytometer according to claim 2, characterized in that: The steps for processing the photoacoustic signal data and calculating the standard threshold range are as follows: Obtain the type of collected cells, obtain the preset category ranking of the cell type based on cell biological characteristics and the correlation between photoacoustic signals and cell characteristics from the database, and select the first K screening categories, 3≤K≤5; A feature extraction algorithm is used to extract M groups of photoacoustic signal data according to the screening categories to obtain K data sets; Use statistical methods to process the data in K data sets one by one to generate K standard intervals; The K standard intervals are aggregated to obtain the standard threshold interval.

4. A data processing system for flow cytometer according to claim 3, characterized in that: The steps of using statistical methods to process the data in K data sets one by one and generate K standard intervals are as follows: Calculate the average value of K data sets ; Determine the maximum and minimum values ​​of the data in the K data sets, and calculate the difference ratios between the maximum and minimum values ​​and the average value, compare the difference ratios, obtain the maximum difference ratio Q, and calculate the adjusted ratio Qt. , where To adjust the ratio, 3%≤ ≤6%; Based on Qt, we can get K standard intervals .

5. A data processing system for flow cytometer according to claim 4, characterized in that: The preprocessing of the photoacoustic signal collected in real time by the flow cytometer is to perform wavelet analysis denoising on the collected photoacoustic signal, and the wavelet analysis denoising adopts the default threshold denoising.

6. A data processing system for flow cytometer according to claim 5, characterized in that: The steps for screening the preprocessed photoacoustic signal data set are as follows: Acquire photoacoustic signal data corresponding to the collected photoacoustic signal, compare K groups of data in the photoacoustic signal data with the K standard intervals recorded in the standard threshold interval one by one, calculate the Euclidean distance between the feature vector and the boundary of the standard interval through the boundary recognition model, and determine whether the K groups of data are located in the corresponding K standard intervals; If it is outside the standard interval, the photoacoustic signal is deleted; If it is within the standard interval, the photoacoustic signal is retained, and the retained photoacoustic signal is analyzed for similarity with the M groups of real photoacoustic signals one by one to obtain M groups of similarity data. The formula for calculating the similarity is as follows; In the formula, is the similarity between the detected photoacoustic signal and the i-th group of real photoacoustic signals, C is the number of photoacoustic signal data types for calculating similarity comparison, is the photoacoustic signal data of the jth type in the collected photoacoustic signal, is the j-th type of photoacoustic signal data extracted from the i-th group of real photoacoustic signals, is the adjustment factor; Obtaining the maximum value among the M groups of similarity data, that is, the maximum similarity, and comparing the maximum similarity with the standard similarity, if the maximum similarity is less than the standard similarity, deleting the photoacoustic signal; If the maximum similarity is greater than or equal to the standard similarity, the photoacoustic signal is retained; The photoacoustic signals retained after the deletion are aggregated to form a set of remaining photoacoustic signals.

7. A data processing system for flow cytometer according to claim 6, characterized in that: The preset intervals include standard data intervals , suspected data interval and remove data intervals , ; The conformity is compared with the preset interval, and the classification algorithm is used to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set and a rejection set.

8. A data processing system for flow cytometer according to claim 7, characterized in that: The steps for comprehensive analysis of the suspected concentrated photoacoustic signal are as follows: The photoacoustic signal in the suspected concentration and its corresponding photoacoustic signal with the maximum similarity are equally divided into E segments by using signal processing technology; Compare the pulse heights in segment E to obtain the half-maximum full width and frequency bandwidth of the photoacoustic signal in the segment with the highest pulse height; The half-width value and frequency bandwidth of the suspected concentrated photoacoustic signal are compared with the half-width value and frequency bandwidth of the photoacoustic signal corresponding to the maximum similarity, and the cell similarity index is calculated. ; The specific calculation formula is as follows: In the formula, is the half-maximum full width of the suspected concentrated photoacoustic signal, The maximum similarity corresponds to the half-maximum full width of the photoacoustic signal. and are weight ratios, is the frequency bandwidth of the suspected concentrated photoacoustic signal, is the frequency bandwidth of the photoacoustic signal corresponding to the maximum similarity; If the cell similarity index is less than the set value, the photoacoustic signal is divided into a rejection set; If the cell similarity index is greater than or equal to the set value, the photoacoustic signal is classified into the standard set.

9. A data processing method for flow cytometer, using any system of claims 1 to 8, characterized in that: The steps include: Acquire photoacoustic signal data of the type of cells to be collected from the database, process the photoacoustic signal data, calculate the standard threshold interval, and obtain the characteristic screening category; Preprocessing the photoacoustic signals collected by the flow cytometer to obtain a photoacoustic signal data set; The preprocessed photoacoustic signal data set is screened by using the standard threshold interval, and the photoacoustic signals that do not meet the standard threshold interval are eliminated to obtain the remaining photoacoustic signal set; Obtain the number of identification collection points and the corresponding data interval corresponding to the collection type cell characteristic screening category, obtain the data corresponding to the number of identification collection points of the photoacoustic signal in the remaining photoacoustic signal set, and compare it with the data interval, statistically compare the results, and calculate the degree of conformity; The conformity is compared with the preset interval, and the classification algorithm is used to divide the photoacoustic signals in the photoacoustic signal set into a standard set, a suspected set and a rejection set. The photoacoustic signals in the suspected set are comprehensively analyzed and divided again. The number of photoacoustic signals in the standard set is counted, and the data and conformity are marked to generate a detection data report.

Images