Multivariable-based pathological data analysis method

Abstract

The invention provides a pathological data analysis method based on multiple variables, and relates to the technical field of pathological data processing. The method comprises the following steps: acquiring a storage quality index; obtaining preprocessed pathological data; obtaining a preprocessing quality index; and obtaining a comprehensive evaluation index. The acquired initial pathological data are transmitted to the preset storage position, the storage quality index is acquired, then the initial pathological data are preprocessed to acquire the preprocessed pathological data and further acquire the preprocessed quality index, and finally the comprehensive evaluation index is acquired according to the storage quality index and the preprocessed quality index. The effect of improving the accuracy of pathological data analysis is achieved, and the problem that in the prior art, the accuracy of pathological data analysis is not high in the pathological data analysis process is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of brain disease pathological data processing, and in particular to a multivariate-based pathological data analysis method. Background Art

[0002] With the rapid development of mass spectrometry, bioinformatics and computer technology, pathological data analysis methods based on multivariate analysis are also constantly improving. However, they are also facing some challenges. For example, multivariate analysis involves a lot of mathematical knowledge and high computational complexity, and requires the help of professional statistical software and computer equipment for processing; in addition, the collection and organization of pathological data also requires a lot of human and material resources. Multivariate analysis, or multivariate analysis, is a statistical analysis method for studying multi-factor and multi-index problems. In the field of medicine, especially in pathological data analysis, multivariate analysis plays a vital role. Since the pathological process is often affected by multiple factors, and there may be complex interactions between these factors, the use of multivariate analysis can reveal the nature and laws of pathological phenomena more comprehensively and deeply. Pathological data analysis is an important means to improve the accuracy of pathological diagnosis and clinical treatment effects. By collecting and organizing pathological specimens, clinical data and related reports, a large data set can be established, which contains rich pathological information. In-depth analysis of these data can help medical staff to promptly discover problems in pathological diagnosis, optimize clinical treatment plans, and thus improve medical quality.

[0003] Existing methods use cluster analysis and other methods to classify pathological samples, and use regression analysis and other methods to establish prediction models, which helps to discover the pathological characteristics of different disease types and predict the progression trend of the disease.

[0004] For example, the pathology data processing method, device and electronic device announced in the invention patent with announcement number CN110517747B include: obtaining multiple pathology reports to be processed; preprocessing the multiple pathology reports to be processed to obtain multiple pathology corpus data; vectorizing the multiple pathology corpus data to obtain pathology matrices of the multiple pathology reports to be processed; performing dimensionality reduction processing on the pathology matrix to determine the pathology representation matrix corresponding to the multiple pathology reports to be processed, each row vector in the pathology representation matrix represents a representation vector of a pathology report to be processed; vectorizing the multiple pathology corpus data to obtain the pathology matrix of the multiple pathology reports to be processed, including: for each pathology corpus data in the multiple pathology corpus data, using the bag-of-words model to vectorize each word in each pathology corpus data to obtain the word vector of each word in the pathology corpus data; calculating the average value of all word vectors in the pathology corpus data to obtain the pathology pathological vectors in corpus data; multiple pathological vectors corresponding to multiple pathological corpus data form a first pathological matrix; for each pathological corpus data in the multiple pathological corpus data, each word in each pathological corpus data is vectorized using a bag-of-words model to obtain a word vector for each word in the pathological corpus data; the weight corresponding to each word vector is determined according to multiple pathological reports to be processed; all word vectors in the pathological corpus data are weighted summed to obtain the pathological vector in the pathological corpus data; multiple pathological vectors corresponding to multiple pathological corpus data form a second pathological matrix; for each pathological corpus data in the multiple pathological corpus data, each pathological corpus data is vectorized using a bag-of-words model to obtain a sentence vector of the pathological corpus data; multiple sentence vectors corresponding to multiple pathological corpus data form a third pathological matrix; weighted summation of the first pathological matrix, the second pathological matrix and the third pathological matrix is ​​performed to obtain a pathological matrix.

[0005] For example, a data stream processing system for digital pathology images announced in the invention patent with announcement number CN114038541 B includes: an acquisition unit for acquiring digital pathology images; a first storage unit for reading metadata of digital pathology images, performing byte-level blocking of the digital pathology images in byte order based on the metadata to acquire multiple sub-blocks of multiple image sub-slices including adjacent areas, and then storing the multiple sub-blocks and generating sub-slice information of each image sub-slice; a metadata unit for recording metadata and sub-slice information; and a parsing unit for acquiring the data stream corresponding to at least one image sub-slice at a time in a manner of sharing a sub-block open handle based on the metadata, the byte offset and the byte size of the image sub-slice after receiving a data request for acquiring the data stream.

[0006] However, in the process of implementing the technical solution of the present invention, the present invention finds that the above technology has at least the following technical problems:

[0007] In the prior art, due to problems such as squeezing and burning of tissues, the sampling of pathological samples is not accurate enough, resulting in low accuracy of pathological data analysis. Summary of the invention

[0008] The embodiment of the present invention solves the problem of low accuracy of pathological data analysis in the prior art by providing a multivariate-based pathological data analysis method, thereby improving the accuracy of pathological data analysis.

[0009] The embodiment of the present invention provides a multivariate-based pathological data analysis method, comprising the following steps:

[0010] S1, transmitting initial pathology data acquired according to preset pathology data to a preset storage location, and acquiring a storage quality index according to the initial pathology data, wherein the storage quality index is used to evaluate the integrity of the initial pathology data stored in the preset storage location;

[0011] S2, preprocessing the initial pathology data to obtain preprocessed pathology data, wherein the preprocessing is used to ensure that the initial pathology data meets the storage integrity requirement;

[0012] S3, acquiring a preprocessing quality index according to the preprocessed pathological data, wherein the preprocessing quality index includes a noise elimination quality index and a noise improvement quality index, wherein the noise elimination quality index is used to evaluate the error level in the preprocessing process of the initial pathological data, and the noise improvement quality index is used to evaluate the improvement degree of the quality of the initial pathological data;

[0013] S4, obtaining a comprehensive evaluation index according to the storage quality index and the preprocessing quality index, wherein the comprehensive evaluation index is used to reflect the overall quality of the pathology data.

[0014] Optionally, the specific acquisition process of the storage quality index is as follows: obtaining storage data through a storage measurement device during a preset storage time period, the storage data including storage rate measurement values ​​and transmission rate measurement values, and the storage measurement device including a network protocol analyzer and a timer; obtaining storage rate measurement values ​​based on standard storage capacity and standard storage time, and obtaining transmission rate measurement values ​​based on standard transmission data volume and standard transmission time; obtaining a preset storage data group from a preset database, and obtaining a storage quality index in combination with the storage data, the preset storage data group including a storage rate threshold, a transmission rate threshold, a preset first storage weight and a preset second storage weight.

[0015] Optionally, the storage quality index is calculated using the following formula:

[0016]

[0017] In the formula, represents the storage quality index of the mth storage preset time period, m=1,2,...,n, m represents the number of the storage preset time period, n represents the total number of storage preset time periods, V 1m represents the storage rate measurement value in the mth storage preset time period, V 2m represents the transmission rate measurement value in the mth storage preset time period, V0 represents the storage rate threshold, V1 represents the transmission rate threshold, δ1 represents the preset first storage weight, and δ2 represents the preset second storage weight.

[0018] Optionally, the specific process of obtaining the preprocessed pathology data is as follows: comparing the storage quality index with a preset storage quality range to obtain first preprocessed data, wherein the first preprocessed data represents initial pathology data corresponding to the storage quality index within the preset storage quality range; performing missing value processing on the first preprocessed data to obtain second preprocessed data; and performing normalization processing on the second preprocessed data to obtain preprocessed pathology data.

[0019] Optionally, the specific acquisition process of the noise elimination quality index is as follows: obtaining noise temperature data through a preprocessing measurement device during a preprocessing preset time period, the noise temperature data including standard noise power, standard bandwidth and standard coefficient, the preprocessing measurement device including a power meter and a spectrum analyzer; obtaining noise temperature measurement values ​​according to the standard noise power, standard bandwidth and standard coefficient; obtaining a preset noise temperature threshold from a preset database, and obtaining the noise elimination quality index in combination with the noise temperature measurement value.

[0020] Optionally, the noise cancellation quality index is calculated using the following formula:

[0021]

[0022] In the formula, represents the noise elimination quality index in the sth preprocessing preset time period, s=1, 2, ..., t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, T S represents the noise temperature measurement value in the sth preprocessing preset time period, T0 represents the preset noise temperature threshold, and e represents a natural constant.

[0023] Optionally, the specific acquisition process of the noise improvement quality index is as follows: obtaining a signal-to-noise ratio measurement value through a preprocessing measurement device during a preprocessing preset time period; obtaining a signal-to-noise ratio measurement value based on a standard signal power and a standard noise power; obtaining a preset signal-to-noise ratio threshold from a preset database, and obtaining the noise improvement quality index in combination with the signal-to-noise ratio measurement value.

[0024] Optionally, the noise improvement quality index is calculated using the following formula:

[0025]

[0026] In the formula, represents the noise improvement quality index in the sth preprocessing preset time period, s=1,2,...,t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, D s represents the signal-to-noise ratio measurement value in the sth preprocessing preset time period, D0 represents the preset signal-to-noise ratio threshold, and e represents a natural constant.

[0027] Optionally, the specific acquisition process of the comprehensive evaluation index is as follows: obtaining the first pathology data analysis weight, the second pathology data analysis weight and the third pathology data analysis weight from a preset database; obtaining the comprehensive evaluation index according to the first pathology data analysis weight, the second pathology data analysis weight, the third pathology data analysis weight, the storage quality index, the noise elimination quality index and the noise improvement quality index.

[0028] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0029] (1) Initial pathology data obtained according to preset pathology data is transmitted to a preset storage location, and a storage quality index is obtained according to the initial pathology data. Then, the initial pathology data is preprocessed to obtain preprocessed pathology data. Then, a preprocessing quality index is obtained according to the preprocessed pathology data. Finally, a comprehensive evaluation index is obtained according to the storage quality index and the preprocessing quality index. Thus, the quality of the pathology data is comprehensively evaluated, and the accuracy of the pathology data analysis is improved. This effectively solves the problem of low accuracy of the pathology data analysis in the prior art.

[0030] (2) By obtaining preset pathological data from a preset database, and then performing a first screening on the data to be detected according to the preset pathological data to obtain first data, then performing a second screening on the data to be detected according to the preset imaging data to obtain second data, and finally performing a second screening on the data to be detected according to the preset biological data to obtain third data, the reliability of the acquired pathological data is improved, and the quality of the acquired pathological data is improved.

[0031] (3) By obtaining a comprehensive evaluation index based on the first pathology data analysis weight, the second pathology data analysis weight, the third pathology data analysis weight, the storage quality index, the noise elimination quality index and the noise improvement quality index, the pathology data quality is improved in all aspects, thereby achieving the comprehensiveness of the pathology data quality improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1A flowchart of a multivariate-based pathology data analysis method provided by an embodiment of the present invention;

[0033] Figure 2 A statistical graph of changes in the storage quality index provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The embodiment of the present invention solves the problem of low accuracy of pathological data analysis in the prior art by providing a pathological data analysis method based on multivariate. The accuracy of pathological data analysis is improved by transmitting the acquired initial pathological data to a preset storage location, acquiring a storage quality index based on the initial pathological data, then preprocessing the initial pathological data to acquire preprocessed pathological data, then acquiring a preprocessing quality index based on the preprocessed pathological data, and finally acquiring a comprehensive evaluation index based on the storage quality index and the preprocessing quality index.

[0035] The technical solution in the embodiment of the present invention is to solve the problem of low quality of pathological data in the above-mentioned pathological data analysis process. The overall idea is as follows:

[0036] The accuracy of pathology data analysis is improved by transferring the acquired initial pathology data to a preset storage location and obtaining a storage quality index, then preprocessing the initial pathology data to obtain preprocessed pathology data and then obtaining a preprocessing quality index, and finally obtaining a comprehensive evaluation index based on the storage quality index and the preprocessing quality index.

[0037] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0038] like Figure 1 FIG. 1 is a flowchart of a multivariate-based pathological data analysis method provided by an embodiment of the present invention, the method comprising the following steps:

[0039] S1, transmitting initial pathology data obtained according to preset pathology data to a preset storage location, and obtaining a storage quality index according to the initial pathology data, the storage quality index being used to evaluate the integrity of the initial pathology data stored in the preset storage location.

[0040] S2, preprocessing the initial pathology data to obtain preprocessed pathology data, where the preprocessing is used to ensure that the initial pathology data meets storage integrity requirements, and the preprocessed pathology data represents the preprocessed initial pathology data.

[0041] S3, obtaining a preprocessing quality index according to the preprocessed pathological data, the preprocessing quality index including a noise elimination quality index and a noise improvement quality index, the noise elimination quality index is used to evaluate the error level in the initial pathological data preprocessing process, and the noise improvement quality index is used to evaluate the improvement degree of the initial pathological data quality.

[0042] S4, obtaining a comprehensive evaluation index according to the storage quality index and the preprocessing quality index, and the comprehensive evaluation index is used to reflect the overall quality of the pathology data.

[0043] In this embodiment, the storage quality index directly reflects the integrity and reliability of the initial pathology data at the preset storage location, and is the basis for ensuring the smooth progress of the subsequent data processing process. The noise elimination quality index evaluates the ability to eliminate noise and errors during the preprocessing process. A high noise elimination quality index means that the preprocessing process effectively reduces the noise and errors in the data, thereby improving the purity and accuracy of the data. The noise improvement quality index further evaluates the overall improvement of the data quality after preprocessing. By optimizing the preprocessing process, the overall quality of the pathology data can be significantly improved. There is a mutually influencing relationship between the storage quality index and the preprocessing quality index. The storage quality directly affects the quality of input data in the preprocessing process, and further affects the preprocessing quality index. The preset pathological data is obtained from the preset database, and the preset pathological data includes preset pathological data, preset imaging data and preset biological data; the data to be detected is screened for the first time according to the preset pathological data to obtain the first data; the data to be detected is screened for the second time according to the preset imaging data to obtain the second data; the data to be detected is screened for the third time according to the preset biological data to obtain the third data, and the third data represents the data to be detected that meets the preset biological data. The preset pathological data includes the pathological diagnosis criteria for hemorrhagic shock and anemia, the pathological image library, the pathological report template, the facial recognition, etc., which are used to judge the samples to be detected. The presence or absence of pathological changes, lesion type and severity are crucial. The preset imaging data include typical imaging manifestations of the disease, imaging diagnostic standards, imaging image library, etc., which are of great significance for discovering, locating and evaluating the location, size, morphology, blood supply, etc. of lesions. The preset biological data include gene sequence, single nucleotide polymorphism data, protein expression spectrum, metabolite spectrum, etc., which are important for revealing the pathogenesis of the disease, predicting disease risk, and evaluating treatment effects. The preset pathological data uses preset pathological, imaging and biological data as screening criteria to exclude data to be tested that do not meet the standards, thereby improving the accuracy and reliability of the initial pathological data finally screened out; the accuracy of pathological data analysis is improved.

[0044] Optionally, the specific acquisition process of the storage quality index is as follows: acquiring storage data through a storage measurement device during a preset storage time period, the storage data including a storage rate measurement value and a transmission rate measurement value, the storage measurement device including a network protocol analyzer and a timer, the preset storage time period representing a preset time period during the transmission and storage process of the initial pathological data; acquiring a storage rate measurement value according to a standard storage capacity and a standard storage time, and acquiring a transmission rate measurement value according to a standard transmission data volume and a standard transmission time, the standard storage capacity representing the storage capacity of the initial pathological data during the preset storage time period, the standard storage time representing the time required for the initial pathological data to store data during the preset storage time period, the standard transmission data volume representing the amount of data transmitted by the initial pathological data during the preset storage time period, and the standard transmission time representing the time required for the initial pathological data to transmit data during the preset storage time period; acquiring a preset storage data group from a preset database, and acquiring a storage quality index in combination with the storage data, the preset storage data group including a storage rate threshold, a transmission rate threshold, a preset first storage weight, and a preset second storage weight, the preset first storage weight being used to evaluate the degree of influence of the storage rate measurement value on the storage quality index, and the preset second storage weight being used to evaluate the degree of influence of the transmission rate measurement value on the storage quality index.

[0045] In this embodiment, the storage rate threshold is represented by the mean of the storage rate data in the preset database, the transmission rate threshold is represented by the mean of the transmission rate data in the preset database, the timer is a device for measuring time, and can be accurate to seconds, milliseconds or even shorter time units, and the network protocol analyzer is a special test tool for monitoring data flows in data communication systems and verifying whether data exchange is carried out correctly in accordance with protocol regulations. By capturing messages, network traffic can be analyzed in detail to understand the data transmission situation on the network, thereby improving the accuracy of pathological data analysis.

[0046] Specifically, the preset first storage weight is obtained from a preset database. In a specific embodiment, a mapping set of storage capacity and storage time and their corresponding weights is constructed by calculating the relationship between the storage capacity and storage time and the corresponding storage quality index in a historical period, and the real-time storage capacity and storage time are input into the mapping set to obtain the corresponding preset first storage weight.

[0047] Specifically, the preset second storage weight is obtained from a preset database. In a specific embodiment, a mapping set of the transmission data volume and transmission time and their corresponding weights is constructed by calculating the relationship between the transmission data volume and transmission time in a historical period and the corresponding storage quality index, and the real-time transmission data volume and transmission time are input into the mapping set to obtain the corresponding preset second storage weight.

[0048] Optionally, the storage quality index is calculated using the following formula:

[0049]

[0050] In the formula, represents the storage quality index of the mth storage preset time period, m=1,2,...,n, m represents the number of the storage preset time period, n represents the total number of storage preset time periods, V 1m represents the storage rate measurement value in the mth storage preset time period, V 2m represents the transmission rate measurement value in the mth storage preset time period, V0 represents the storage rate threshold, V1 represents the transmission rate threshold, δ1 represents the preset first storage weight, and δ2 represents the preset second storage weight.

[0051] In this embodiment, C m represents the standard storage capacity in the mth storage preset time period, t 1m represents the standard storage time in the mth storage preset time period, X m represents the standard transmission data volume in the mth storage preset time period, t 2m Indicates the standard transmission time in the mth storage preset time period.

[0052] Specifically, the algorithm of this embodiment combines the standard storage capacity C m , standard storage time t 1m 、Standard transmission data volume X m and standard transmission time t 2m , comprehensive analysis to obtain the storage quality index, the standard storage capacity C in this formula m , standard storage time t 1m 、Standard transmission data volume X m and standard transmission time t 2m There is a common regulatory relationship between them, with the standard storage capacity C m and standard transfer data volume X m The increase of standard storage time t 1m and standard transmission time t 2m The storage quality index gradually increases as the storage capacity decreases. m and standard transfer data volume X m Positively correlated with the storage quality index, standard storage time t 1m and standard transmission time t 2m It is negatively correlated with the storage quality index, so it is accurately analyzed by establishing a mathematical form.

[0053] Specifically, Figure 2 As shown in the figure, it is a statistical diagram of the storage quality index provided by the embodiment of the present invention. Assuming that the storage rate measurement value V 1mThe range is 100-500 (MB / s), and the transmission rate measurement value V 2m The range is 500-1000 (MB / s), the storage rate threshold V0 is 200 (MB / s), the transmission rate threshold V1 is 300 (MB / s), the first storage weight δ1 is preset to 0.5, and the second storage weight δ2 is preset to 0.5. As can be seen from the figure, as the storage rate measurement value V 1m and the transmission rate measurement value V 2m The storage quality index gradually increases, which means that the initial pathology data stored in the preset storage location has good integrity, and the initial pathology data is saved in the preset storage location with higher quality and reliability. The high storage rate ensures that the data is recorded completely and without omission in a short time, while the high transmission rate ensures that the data can be transmitted to the target location quickly and accurately, reducing the risk of data loss due to delays or interruptions; the accuracy of pathology data analysis is improved.

[0054] Optionally, the specific process of obtaining the preprocessed pathology data is as follows: comparing the storage quality index with a preset storage quality range to obtain first preprocessed data, the first preprocessed data representing initial pathology data corresponding to the storage quality index within the preset storage quality range; performing missing value processing on the first preprocessed data to obtain second preprocessed data, the missing value processing represents filling the missing values ​​with the median of the first preprocessed data, the second preprocessed data representing the initial pathology data after the missing value processing; performing normalization processing on the second preprocessed data to obtain preprocessed pathology data, the normalization processing is used to eliminate the influence of different dimensions.

[0055] In this embodiment, the preset storage quality range is set based on the pathological data in the preset database. The preset storage quality is represented by the mean of the storage quality data in the preset database. The storage quality is divided into different levels according to the preset storage quality threshold, such as "excellent", "good", "general", "poor", etc. Each level corresponds to a specific storage quality range. The normalization process eliminates the influence of different dimensions on data analysis, so that features of different magnitudes can be compared and calculated on the same scale. Through the steps of screening, filling missing values ​​and normalization, the quality and availability of the data are effectively improved; the accuracy of pathological data analysis is improved.

[0056] Optionally, the specific acquisition process of the noise elimination quality index is as follows: obtaining noise temperature data through a preprocessing measurement device during a preprocessing preset time period, the noise temperature data including standard noise power, standard bandwidth and standard coefficient, the preprocessing measurement device including a power meter and a spectrum analyzer; obtaining noise temperature measurement values ​​according to the standard noise power, standard bandwidth and standard coefficient, the preprocessing preset time period represents a preset time period of the initial pathological data during the preprocessing process; the standard noise power represents the power of the noise of the initial pathological data during the preprocessing preset time period, the standard bandwidth represents the spectrum bandwidth of the noise of the initial pathological data during the preprocessing preset time period, and the standard coefficient is obtained from a preset database; obtaining a preset noise temperature threshold from the preset database, and obtaining the noise elimination quality index in combination with the noise temperature measurement value.

[0057] In this embodiment, the preset noise temperature threshold is represented by the mean value of the noise temperature data in the preset database. The working principle of the power meter is based on the electric energy conversion and the law of conservation of energy in the power system. Specifically, the power meter measures the voltage and current values ​​in the circuit and calculates the power value using Ohm's law and the instantaneous power formula. The power meter measures the voltage and current values ​​in the circuit and calculates the power value using the relevant formula. The spectrum analyzer is an instrument for studying the spectrum structure of electrical signals, and is used to measure signal parameters such as signal distortion, modulation, spectral purity, frequency stability and intermodulation distortion; the accuracy of pathological data analysis is improved.

[0058] Optionally, the noise cancellation quality index is calculated using the following formula:

[0059]

[0060] In the formula, represents the noise elimination quality index in the sth preprocessing preset time period, s=1, 2, ..., t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, T S represents the noise temperature measurement value in the sth preprocessing preset time period, T0 represents the preset noise temperature threshold, and e represents a natural constant.

[0061] In this embodiment, P s represents the standard noise power in the sth preprocessing preset time period, B s represents the standard bandwidth in the sth preprocessing preset time period, k represents the standard coefficient, and the algorithm of this embodiment combines the standard noise power P s and standard bandwidth B s , the noise elimination quality index is obtained through comprehensive analysis. The standard noise power P in this formula is s and standard bandwidth B sThere is a common regulatory relationship between s The increase of standard bandwidth B s The noise elimination quality index decreases gradually. At this time, the standard noise power P s Negatively correlated with the noise cancellation quality index, standard bandwidth B s It is positively correlated with the noise cancellation quality index, so it can be accurately analyzed by establishing a mathematical form.

[0062] Specifically, assuming the standard noise power P s The range is 0-100 (nW), standard bandwidth B s The range is 1-500 (Hz), the standard coefficient k is 1 (nW / (Hz*K)), and the preset noise temperature threshold T0 is 50 (K). The statistical change table of the noise elimination quality index is shown in Table 1:

[0063] Table 1 Statistical changes of noise elimination quality index

[0064]

[0065] It can be seen from the table that as the standard noise power P s The standard bandwidth B s The noise elimination quality index gradually decreases, which means that while removing the noise, more useful information in the initial pathology data is retained, and the interference of the noise is effectively suppressed or eliminated. The error level in the initial pathology data preprocessing process gradually decreases, reflecting the improvement of the purity and accuracy of the data after preprocessing; the accuracy of pathology data analysis is improved.

[0066] Optionally, the specific process of obtaining the noise improvement quality index is as follows: obtaining a signal-to-noise ratio measurement value through a preprocessing measurement device during a preprocessing preset time period; obtaining a signal-to-noise ratio measurement value based on a standard signal power and a standard noise power, the standard signal power representing the power of a useful signal of the initial pathological data during the preprocessing preset time period; obtaining a preset signal-to-noise ratio threshold from a preset database, and obtaining the noise improvement quality index in combination with the signal-to-noise ratio measurement value.

[0067] In this embodiment, the preset signal-to-noise ratio threshold is represented by the mean of the signal-to-noise ratio data in a preset database. In each link of signal processing, it is crucial to ensure signal quality. The noise improvement quality index, as an indicator to measure the noise improvement effect, helps to promptly detect and correct noise problems during the signal processing process, thereby ensuring the quality of the final signal; and achieving improved accuracy in pathological data analysis.

[0068] Optionally, the noise improvement quality index is calculated using the following formula:

[0069]

[0070] In the formula, represents the noise improvement quality index in the sth preprocessing preset time period, s=1,2,...,t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, D s represents the signal-to-noise ratio measurement value in the sth preprocessing preset time period, D0 represents the preset signal-to-noise ratio threshold, and e represents a natural constant.

[0071] In this embodiment, P 0S represents the standard signal power in the sth preprocessing preset time period, P s represents the standard noise power in the sth preprocessing preset time period. The algorithm in this embodiment combines the standard signal power P 0S and standard noise power P s , the noise improvement quality index is obtained by comprehensive analysis. The standard signal power P in this formula 0S and standard noise power P s There is a common regulation relationship between them, with the standard signal power P 0S The increase of standard noise power P s The noise improvement quality index gradually increases. At this time, the standard signal power P 0S Positively correlated with the noise improvement quality index, standard noise power P s It is negatively correlated with the noise improvement quality index, so it is accurately analyzed by establishing a mathematical form;

[0072] It should be explained that the standard signal power P 0S The expression is: Among them, P 0S ′ represents the standard signal power data in the sth preprocessing preset time period, P 0S 0 represents the reference standard signal power data in the sth preprocessing preset time period, ΔP 0S Indicates the standard signal power reference deviation, standard noise power P s The expression is: Among them, P s ′ represents the standard noise power data in the sth preprocessing preset time period, P s 0 represents the reference standard noise power data in the sth preprocessing preset time period, ΔP s Indicates the standard noise power reference deviation.

[0073] It should be understood that the standard signal power data of the sth pre-processing preset time period is obtained by measurement, the reference standard signal power data is represented by the result of calculating the average value of the standard signal power data of the sth pre-processing preset time period, the standard noise power reference deviation is obtained by calculating the standard signal power data and the reference standard signal power data through the deviation formula, the standard noise power data of the sth pre-processing preset time period is obtained by measurement, the reference standard noise power data is represented by the result of calculating the average value of the standard noise power data of the sth pre-processing preset time period, the standard noise power reference deviation is obtained by calculating the standard noise power data and the reference standard noise power data through the deviation formula, the deviation formula is used to measure the difference between the reference value and the actual measured value, and is represented by the result of taking the average value of the difference between the reference value and the actual measured value; the accuracy of pathological data analysis is improved.

[0074] Optionally, the specific process of obtaining the comprehensive evaluation index is as follows: obtain the first pathology data analysis weight, the second pathology data analysis weight and the third pathology data analysis weight from a preset database, the first pathology data analysis weight is used to evaluate the influence of the storage quality index on the comprehensive evaluation index, the second pathology data analysis weight is used to evaluate the influence of the noise elimination quality index on the comprehensive evaluation index, and the third pathology data analysis weight is used to evaluate the influence of the noise improvement quality index on the comprehensive evaluation index; obtain the comprehensive evaluation index according to the first pathology data analysis weight, the second pathology data analysis weight, the third pathology data analysis weight, the storage quality index, the noise elimination quality index and the noise improvement quality index.

[0075] In this embodiment, the comprehensive evaluation index is calculated based on the storage quality index and the preprocessing quality index. It comprehensively reflects the overall quality of the pathology data. The comprehensive evaluation index provides a comprehensive evaluation of the overall quality of the pathology data by comprehensively considering the quality evaluation results of the two links of storage and preprocessing, thereby achieving improved accuracy in pathology data analysis.

[0076] Specifically, the comprehensive evaluation index is calculated using the following formula:

[0077]

[0078] In the formula, τ represents the comprehensive evaluation index, represents the storage quality index in the mth storage preset time period, m=1,2,...,n, m represents the number of the storage preset time period, n represents the total number of storage preset time periods, represents the noise elimination quality index in the sth preprocessing preset time period, s=1, 2, ..., t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, represents the noise improvement quality index in the sth preprocessing preset time period, θ1 represents the first pathology data analysis weight, θ2 represents the second pathology data analysis weight, and θ3 represents the third pathology data analysis weight.

[0079] Specifically, the first pathology data analysis weight is obtained from a preset database; in a specific embodiment, a mapping set of storage rate and transmission rate and their corresponding weights is constructed by calculating the relationship between the storage rate and transmission rate and the corresponding storage quality index in a historical period, and the real-time storage rate and transmission rate are input into the mapping set to obtain the corresponding first pathology data analysis weight.

[0080] Specifically, the second pathology data analysis weight is obtained from a preset database; in a specific embodiment, a mapping set of noise power and bandwidth and their corresponding weights is constructed by analyzing the relationship between the noise power and bandwidth and the corresponding noise elimination quality index in a historical period, and the real-time noise power and bandwidth are input into the mapping set to obtain the corresponding second pathology data analysis weight.

[0081] Specifically, the third pathology data analysis weight is obtained from a preset database; in a specific embodiment, a mapping set of signal power and noise power and their corresponding weights is constructed by calculating the relationship between the signal power and noise power and the corresponding noise improvement quality index in a historical period, and the real-time signal power and noise power are input into the mapping set to obtain the corresponding third pathology data analysis weight.

[0082] In summary, the embodiment of the present invention transmits initial pathology data obtained according to preset pathology data to a preset storage location, obtains a storage quality index according to the initial pathology data, then preprocesses the initial pathology data to obtain preprocessed pathology data, then obtains a preprocessing quality index according to the preprocessed pathology data, and finally obtains a comprehensive evaluation index according to the storage quality index and the preprocessing quality index, thereby achieving a comprehensive evaluation of the quality of the pathology data, and further achieving an improvement in the accuracy of pathology data analysis, effectively solving the problem of low accuracy of pathology data analysis in the prior art.

[0083] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0088] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A multivariate-based pathological data analysis method, characterized in that: The following steps are involved: S1, transmitting initial pathology data acquired according to preset pathology data to a preset storage location, and acquiring a storage quality index according to the initial pathology data, wherein the storage quality index is used to evaluate the integrity of the initial pathology data stored in the preset storage location; S2, preprocessing the initial pathology data to obtain preprocessed pathology data, wherein the preprocessing is used to ensure that the initial pathology data meets the storage integrity requirement; S3, acquiring a preprocessing quality index according to the preprocessed pathological data, wherein the preprocessing quality index includes a noise elimination quality index and a noise improvement quality index, wherein the noise elimination quality index is used to evaluate the error level in the preprocessing process of the initial pathological data, and the noise improvement quality index is used to evaluate the improvement degree of the quality of the initial pathological data; S4, obtaining a comprehensive evaluation index according to the storage quality index and the preprocessing quality index, wherein the comprehensive evaluation index is used to reflect the overall quality of the pathology data.

2. The multivariate-based pathological data analysis method according to claim 1, characterized in that: The specific process of obtaining the storage quality index is as follows: Acquiring storage data by means of a storage measurement device during a preset storage time period, wherein the storage data includes a storage rate measurement value and a transmission rate measurement value, and the storage measurement device includes a network protocol analyzer and a timer; Obtaining a storage rate measurement value based on a standard storage capacity and a standard storage time, and obtaining a transmission rate measurement value based on a standard transmission data volume and a standard transmission time; A preset storage data group is obtained from a preset database, and a storage quality index is obtained in combination with the storage data, wherein the preset storage data group includes a storage rate threshold, a transmission rate threshold, a preset first storage weight, and a preset second storage weight.

3. The multivariate-based pathological data analysis method according to claim 2, characterized in that: The storage quality index is calculated using the following formula: In the formula, represents the storage quality index of the mth storage preset time period, m=1,2,...,n, m represents the number of the storage preset time period, n represents the total number of storage preset time periods, V 1m represents the storage rate measurement value in the mth storage preset time period, V 2m represents the transmission rate measurement value in the mth storage preset time period, V0 represents the storage rate threshold, V1 represents the transmission rate threshold, δ1 represents the preset first storage weight, and δ2 represents the preset second storage weight.

4. The multivariate-based pathological data analysis method according to claim 1, characterized in that: The specific process of obtaining the preprocessed pathological data is as follows: Comparing the storage quality index with a preset storage quality range to obtain first preprocessed data, wherein the first preprocessed data represents initial pathological data corresponding to the storage quality index within the preset storage quality range; Performing missing value processing on the first preprocessed data to obtain second preprocessed data; The second preprocessed data is normalized to obtain preprocessed pathological data.

5. The multivariate-based pathological data analysis method according to claim 1, characterized in that: The specific process of obtaining the noise elimination quality index is as follows: Acquiring noise temperature data by a preprocessing measurement device during a preprocessing preset time period, wherein the noise temperature data includes standard noise power, standard bandwidth and standard coefficient, and the preprocessing measurement device includes a power meter and a spectrum analyzer; Obtain noise temperature measurements based on standard noise power, standard bandwidth, and standard coefficients; A preset noise temperature threshold is obtained from a preset database, and a noise cancellation quality index is obtained in combination with the noise temperature measurement value.

6. The multivariate-based pathological data analysis method according to claim 5, characterized in that: The noise cancellation quality index is calculated using the following formula: In the formula, represents the noise elimination quality index in the sth preprocessing preset time period, s=1, 2, ..., t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, T S represents the noise temperature measurement value in the sth preprocessing preset time period, T0 represents the preset noise temperature threshold, and e represents a natural constant.

7. The multivariate-based pathological data analysis method according to claim 1, characterized in that: The specific process of obtaining the noise improvement quality index is as follows: obtaining a signal-to-noise ratio measurement value by a preprocessing measurement device during a preprocessing preset time period; Obtaining a signal-to-noise ratio measurement value based on a standard signal power and a standard noise power; A preset signal-to-noise ratio threshold is obtained from a preset database, and a noise improvement quality index is obtained in combination with the signal-to-noise ratio measurement value.

8. The multivariate-based pathological data analysis method according to claim 7, characterized in that: The noise improvement quality index is calculated using the following formula: In the formula, represents the noise improvement quality index in the sth preprocessing preset time period, s=1,2,...,t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, D s represents the signal-to-noise ratio measurement value in the sth preprocessing preset time period, D0 represents the preset signal-to-noise ratio threshold, and e represents a natural constant.

9. The multivariate-based pathological data analysis method according to claim 1, characterized in that: The specific process of obtaining the comprehensive evaluation index is as follows: Obtaining a first pathology data analysis weight, a second pathology data analysis weight, and a third pathology data analysis weight from a preset database; A comprehensive evaluation index is obtained according to the first pathology data analysis weight, the second pathology data analysis weight, the third pathology data analysis weight, the storage quality index, the noise elimination quality index and the noise improvement quality index.

10. The multivariate-based pathological data analysis method according to claim 9, characterized in that: The comprehensive evaluation index is calculated using the following formula: In the formula, τ represents the comprehensive evaluation index, represents the storage quality index in the mth storage preset time period, m=1,2,...,n, m represents the number of the storage preset time period, n represents the total number of storage preset time periods, represents the noise elimination quality index in the sth preprocessing preset time period, s=1, 2, ..., t, s represents the number of the preprocessing preset time period, t represents the total number of preprocessing preset time periods, represents the noise improvement quality index in the sth preprocessing preset time period, θ1 represents the first pathology data analysis weight, θ2 represents the second pathology data analysis weight, and θ3 represents the third pathology data analysis weight.

Images