Growth curve fitting method and device, equipment and storage medium

Abstract

The invention provides a growth curve fitting method and device, equipment and a storage medium, and the method comprises the steps: receiving a plurality of measurement samples sent by at least one ultrasonic machine, the measurement samples comprising measurement results of biological indexes which are related to the gestational age in pregnant woman information and represent the growth state of a fetus; according to the measurement result of each biological index, adding the plurality of measurement samples into corresponding biological index sets, and grouping the measurement samples in each biological index set according to gestational age; for each biological index, determining probability distribution parameters corresponding to each group of measurement samples in the corresponding biological index set, and fitting the probability distribution parameters to obtain a fetal growth curve under the biological indexes; manual participation is not needed, the efficiency of establishing the fetal growth curve suitable for a certain region is improved, and the accuracy and prediction effect of doctor diagnosis are improved.

Description

Technical Field

[0001] The present application relates to the field of ultrasonic obstetric examination, and in particular to a growth curve fitting method, device, equipment and storage medium. Background Art

[0002] Based on the ultrasonic biometric indicators of the fetus, such as biparietal diameter, head circumference, abdominal circumference, femur length, etc., the fetal growth curve can be obtained through a certain mathematical model calculation, and fetuses with abnormal growth can be screened out based on the fetal growth curve to find high-risk fetuses that may have adverse outcomes; however, because fetal growth is affected by race, gender, parental genetics and other factors, there will be large differences in fetal growth curves in different regions.

[0003] In related technologies, establishing a fetal growth curve suitable for a certain region requires recording a large number of samples, but the traditional method has problems such as many manual participation links, heavy workload and repetitive work. Summary of the invention

[0004] The present application provides a growth curve fitting method, device, equipment and storage medium, which do not require human intervention, improve the efficiency of establishing a fetal growth curve suitable for a certain region, and improve the accuracy of doctors' diagnosis and prediction effect.

[0005] In a first aspect, the present application provides a growth curve fitting method, which is applied to a server and includes:

[0006] Receiving a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators representing the growth status of the fetus, which are associated with the gestational age in the pregnant woman's information;

[0007] According to the measurement results of each biological indicator, the multiple measurement samples are respectively added to the corresponding biological indicator set, and the measurement samples in each biological indicator set are grouped according to the gestational age;

[0008] For each biological indicator, the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set are determined, and the probability distribution parameters are fitted to obtain the fetal growth curve under the biological indicator.

[0009] In one or more possible embodiments, the measurement sample further includes the measurement time of each biological indicator;

[0010] Before grouping the measurement samples in each biological indicator set according to the gestational age, the method further includes:

[0011] For each biological indicator set, comparing the measurement time of the biological indicator of each measurement sample in the biological indicator set with the preset start time, and determining to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the preset start time; or,

[0012] For each biological indicator set, the measurement time of the biological indicator of each measurement sample in the biological indicator set is compared with the current preset start time, and the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time is selected, and the current preset start time is compared with the last preset start time; if the current preset start time is greater than the last preset start time, it is determined to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time; if the current preset start time is not greater than the last preset start time, it is determined to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time and which was not selected last time.

[0013] In one or more possible embodiments, the probability distribution parameters include a mean μ, an upper bound, and a lower bound, and determining the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set includes:

[0014] The mean μ and variance σ of the biological index measurement results in each group of measurement samples are determined according to the maximum likelihood estimation formula;

[0015] Determine an upper bound and a lower bound according to the mean μ and / or the variance σ;

[0016] And, fitting the probability distribution parameters to obtain a fetal growth curve under the biological indicator, including:

[0017] According to the mean μ / upper limit / lower limit corresponding to each group of measurement samples, the least squares method is used for fitting to obtain the fetal growth curve of the mean μ / upper limit / lower limit under the biological indicator.

[0018] In one or more possible embodiments, determining an upper bound and a lower bound according to the mean μ and / or the variance σ includes:

[0019] Determine the reference range of the growth curve in the form of variance, then determine the upper limit according to the formula μ+bσ and the lower limit according to μ-bσ, where b is 1 or 2; or

[0020] The reference range of the growth curve is determined in percentage form, and the upper and lower limits are determined by searching a normal distribution table according to the mean μ or the variance σ.

[0021] In one or more possible embodiments, fitting the probability distribution parameters to obtain the fetal growth curve under the biological indicator includes:

[0022] Determine the coefficients in the target polynomial according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the highest power m preset in the target polynomial for fitting;

[0023] Determine the residual sum of squares according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the coefficients in the target polynomial;

[0024] If it is determined that the residual sum of squares meets the preset deviation requirement, a target polynomial is determined according to the preset highest power m and the coefficients in the target polynomial, and a fetal growth curve under the biological indicator is determined according to the target polynomial;

[0025] If it is determined that the residual sum of squares does not meet the preset deviation requirement, the highest power m is reset, and the step of determining the coefficients in the target polynomial is returned based on the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the highest power m preset in the target polynomial used for fitting.

[0026] In a second aspect, the present application also provides a growth curve fitting method, which is applied to an ultrasound machine, comprising:

[0027] Measuring the pregnant woman with an ultrasound probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus;

[0028] According to the gestational age carried in the pregnant woman's information, the measurement results of each biological indicator are associated with the gestational age into a measurement sample and then sent to the server, so that the server adds the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of each biological indicator, and groups the measurement samples in each biological indicator set according to the gestational age; then, for each biological indicator, the server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set, and fits the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

[0029] In a third aspect, the present application also provides a growth curve fitting device, applied to a server, comprising:

[0030] A sample receiving module, used to receive a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators that are associated with the gestational age in the pregnant woman's information and characterize the growth status of the fetus;

[0031] A sample grouping module, configured to add the plurality of measurement samples to corresponding biological indicator sets according to the measurement results of the biological indicators, and group the measurement samples in each biological indicator set according to the gestational age;

[0032] The growth curve fitting module is used to determine the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fit the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

[0033] In a fourth aspect, the present application further provides a growth curve fitting device, applied to an ultrasound machine, comprising:

[0034] A measuring module, used to measure the pregnant woman using an ultrasonic probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus;

[0035] The sample sending module is used to associate the measurement results of each biological indicator with the gestational age carried in the pregnant woman's information into a measurement sample and then send it to the server, so that the server can add the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of each biological indicator, and group the measurement samples in each biological indicator set according to the gestational age; then, the server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fits the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

[0036] In a fifth aspect, the present application also provides a growth curve fitting device, the device comprising:

[0037] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the growth curve fitting method as described in any one of the first aspect or the second aspect.

[0038] In a sixth aspect, the present application further provides a storage medium storing a computer program, wherein the computer program is used to enable a computer to execute the growth curve fitting method as described in any one of the first aspect or the second aspect.

[0039] The present application provides a growth curve fitting method, device, equipment and storage medium. The server receives measurement samples sent by an ultrasound machine, classifies the measurement results of each biological indicator, and then groups them by gestational age. For each biological indicator, the probability distribution parameters corresponding to each group of measurement samples are determined, and the probability distribution parameters are fitted to obtain the fetal growth curve of the corresponding biological indicator. The above process does not require human participation, improves the efficiency of establishing a fetal growth curve suitable for a certain region, and improves the accuracy of doctors' diagnosis and prediction effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0041] Figure 1 A flow chart of a growth curve fitting method applied to a server according to an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a measurement sample provided according to an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a set of biological indicators provided according to an embodiment of the present application;

[0044] Figure 4 A schematic diagram of probability distribution parameters calculated after grouping according to an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a formula corresponding to a fetal growth curve under various biological indicators provided in an embodiment of the present application;

[0046] Figure 6 A flowchart of a measurement sample selection process provided according to an embodiment of the present application;

[0047] Figure 7 A flowchart for determining probability distribution parameters according to an embodiment of the present application;

[0048] Figure 8 A flowchart for determining an upper bound and a lower bound according to an embodiment of the present application;

[0049] Fig. 9 A flowchart for determining mean and variance according to an embodiment of the present application;

[0050] Fig.10 A flowchart of a fetal growth curve fitting provided according to an embodiment of the present application;

[0051] Fig.11A specific flow chart of fitting a fetal growth curve according to an embodiment of the present application;

[0052] Fig.12 It is a flow chart of a growth curve fitting method applied to an ultrasound machine according to an embodiment of the present application;

[0053] Fig.13 It is a schematic diagram of a framework in which an ultrasound machine provided by an embodiment of the present application is connected to a server via a network;

[0054] Fig.14 A flowchart of interaction between an ultrasound machine and a server according to an embodiment of the present application;

[0055] Fig.15 A schematic diagram of a growth curve fitting device applied to a server according to an embodiment of the present application;

[0056] Fig.16 A schematic diagram of a specific architecture of a growth curve fitting device applied to a server according to an embodiment of the present application;

[0057] Fig.17 It is a schematic diagram of a growth curve fitting device applied to an ultrasound machine according to an embodiment of the present application;

[0058] Fig.18 A schematic diagram of a specific architecture of a growth curve fitting device applied to an ultrasound machine provided according to an embodiment of the present application;

[0059] Fig.19 A schematic diagram of a growth curve fitting device provided according to an embodiment of the present application;

[0060] Fig. 20 A schematic diagram of a storage medium provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0063] When pregnant women have prenatal checkups, they will use ultrasound machines to detect the growth of the fetus. Doctors will diagnose whether the fetus is growing normally based on the fetal growth curve. The above-mentioned fetal growth curve is calculated based on the biological measurement indicators of the fetus and through mathematical models. The above-mentioned biological measurement indicators of the fetus generally include biparietal diameter, head circumference, abdominal circumference, and femur length. The establishment of several well-known fetal intrauterine growth curves is mostly based on more rigorous clinical research designs. However, since the growth of the fetus may be affected by factors such as race, gender, and parental genetics, as well as different research designs and included populations, the established curves are quite different. Based on the above reasons, considering that the fetal growth curve is affected by many factors, especially the large racial and regional differences, the use of regional / ethnic-specific fetal growth curves can improve the accuracy of the examination. However, the establishment of a fetal growth curve formula suitable for the local area requires recording a large amount of sample data to deduce the formula. The traditional method has the problems of many manual participation links, huge workload, and repetitive work.

[0064] Therefore, the present application provides a growth curve fitting method, device, equipment and storage medium, which do not require human intervention, improve the efficiency of establishing a fetal growth curve suitable for a certain region, and improve the accuracy of doctors' diagnosis and prediction effect.

[0065] Example 1

[0066] This application provides a growth curve fitting method, which is applied to a server, such as Figure 1 As shown, including:

[0067] Step 101, receiving a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators representing the growth status of the fetus, which are associated with the gestational age in the pregnant woman's information;

[0068] In one or more possible embodiments, the above-mentioned receiving multiple measurement samples sent by at least one ultrasound machine, the above-mentioned measurement samples are samples of information about the fetus of the pregnant woman; the pregnant woman information includes information such as gestational age, name, age, etc. The gestational age in this application refers to the number of weeks of pregnancy of the pregnant woman, for example, the gestational age is determined to be 1 if the pregnancy is one week, and the gestational age is determined to be 2 if the pregnancy is two weeks; biological indicators include biparietal diameter, head circumference, abdominal circumference, femur length, etc., and a measurement sample in this application is a measurement result of a biological indicator associated with gestational age, such as Figure 2 As shown, it includes gestational age W1 and the corresponding biparietal diameter measurement result, or gestational age W1 and the corresponding head circumference measurement result; wherein all biological indicator measurement results are used to characterize the growth status of the fetus.

[0069] Step 102, according to the measurement results of the biological indicators, the plurality of measurement samples are added to corresponding biological indicator sets respectively, and the measurement samples in each biological indicator set are grouped according to the gestational age;

[0070] In one or more possible embodiments, the measurement results of each biological indicator in the measurement samples received by the server are classified, for example, the measurement samples including the biparietal diameter measurement results are added to the corresponding biparietal diameter set, and the measurement samples including the head circumference measurement results are added to the corresponding head circumference set, such as Figure 3 As shown in the figure, the storage method of the corresponding set of a single biological indicator biparietal diameter includes the measurement value of the biparietal diameter, the measurement time, the gestational age and the ID corresponding to the measurement value. The above ID is calculated starting from 1. When a new measurement sample is added, 1 is added to the previous ID number as the ID of this measurement sample; and the measurement samples in each biological indicator set are grouped according to the gestational age. For example, the gestational age is grouped according to the first week, the second week, the third week to the 42nd week, and the measurement samples of the same gestational age are grouped as one group.

[0071] Step 103, for each biological indicator, determine the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set, and fit the above probability distribution parameters to obtain the fetal growth curve under the above biological indicator.

[0072] In one or more possible embodiments, for each biological indicator, it is necessary to determine the probability distribution parameters corresponding to each group of measurement samples in the set of corresponding biological indicators, and record the results of the probability distribution parameters; the above-mentioned probability distribution parameters include a mean, an upper bound, and a lower bound. For example, first calculate the mean corresponding to each group of measurement samples, such as Figure 4As shown in FIG. 1 , the storage method of the mean corresponding to each group of samples after grouping according to gestational age includes gestational age, the mean corresponding to gestational age, the variance calculated corresponding to gestational age, and the minimum ID and maximum ID corresponding to the samples when calculating the gestational age of this group; and the mean and variance corresponding to each group of samples are determined based on the above mean and variance; the probability distribution parameters of each biological indicator, that is, the mean, upper bound and lower bound are fitted to obtain the corresponding mean formula, upper bound formula and lower bound formula, and finally three fetal growth curves of the corresponding biological indicators are obtained; as shown in FIG. Figure 5 As shown, the upper bound formula, mean formula and lower bound formula stored corresponding to the fetal growth curve under each biological indicator, and the creation time of the corresponding three formulas.

[0073] According to a growth curve fitting method provided by the present application, no human intervention is required, and the efficiency of establishing a fetal growth curve suitable for a certain region can be improved. At the same time, traditional growth curves have racial and regional restrictions. The present application uses local population data, which conforms to the characteristics of the local population. The established fetal growth curve is more in line with the local population, which can improve the accuracy of doctors' diagnosis and predictive effects.

[0074] In one or more possible embodiments, the measurement samples further include the measurement time of each biological indicator. Before the measurement samples in each biological indicator set are grouped according to the gestational age, Figure 6 As shown, it also includes:

[0075] Step 601, for each biological indicator set, compare the measurement time of the biological indicator of each measurement sample in the biological indicator set with the preset start time, and select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the preset start time; or,

[0076] Step 602: for each biological indicator set, compare the biological indicator measurement time of each measurement sample in the biological indicator set with the current preset start time, select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time, and compare the current preset start time with the last preset start time; if the current preset start time is greater than the last preset start time, determine to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time; if the current preset start time is not greater than the last preset start time, determine to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time and which was not selected last time.

[0077] In one or more possible embodiments, any of the following methods may be used to select a measurement sample. For the convenience of description, the biparietal diameter is used as an example. Other biological indicator sets are similar and will not be described in detail:

[0078] Method 1: Compare the measurement time corresponding to each measurement sample in the biparietal diameter set with the preset start time, determine and select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the preset start time, group the selected measurement samples, and then calculate the mean, upper bound, and lower bound corresponding to each group of samples;

[0079] Method 2: Compare the measurement time corresponding to each measurement sample in the biparietal diameter set with the preset start time of this time, determine to select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the preset start time of this time, and compare the preset start time of this time with the last preset start time; if the preset start time of this time is greater than the last preset start time, determine to select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the preset start time of this time; if the preset start time of this time is not greater than the last preset start time, determine to select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the preset start time of this time and which was not selected last time;

[0080] Method three: compare the measurement time corresponding to each measurement sample in the biparietal diameter set with the current preset start time, determine to select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the above-mentioned current preset start time, and compare the current preset start time with the last preset start time. If the current preset start time is greater than the last preset start time, determine to select the measurement sample in the biparietal diameter set whose measurement time is greater than or equal to the above-mentioned current preset start time; if the current preset start time is not greater than the last preset start time, then according to the ID corresponding to each measurement sample, determine to select the measurement sample corresponding to the ID that was not selected last time in the biparietal diameter set.

[0081] In one or more possible embodiments, the above probability distribution parameters include a mean μ, an upper bound, and a lower bound. Then, the above determination of the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set is as follows: Figure 7 As shown, including:

[0082] Step 701, determining the mean μ and variance σ of the biological indicator measurement results in each group of measurement samples according to the maximum likelihood estimation formula;

[0083] Step 702, determining an upper bound and a lower bound according to the mean μ and / or the variance σ;

[0084] In one or more possible embodiments, the upper bound and the lower bound are determined according to the mean μ and / or the variance σ, such as Figure 8 As shown, including:

[0085] Step 801, determine the reference range of the growth curve in the form of variance, then determine the upper limit according to the formula μ+bσ, and determine the lower limit according to μ-bσ, where b is 1 or 2; or,

[0086] Step 802, determine that the reference range of the growth curve is in percentage form, and then look up the normal distribution table according to the above mean μ or the above variance σ to determine the upper and lower limits.

[0087] In one or more possible embodiments, the mean μ and variance σ of the biological indicator measurement results in each group of measurement samples are determined according to the maximum likelihood estimation formula, such as Fig. 9 As shown, including:

[0088] Step 901, if it is the first time to perform statistical calculation for a certain gestational age, the mean μ and variance σ are calculated according to the maximum likelihood estimation formula;

[0089] The specific formula is as follows:

[0090]

[0091]

[0092] Among them, n means that there are n measurement samples participating in this calculation. and μ represents the mean of the biological indicator in the measurement sample of this gestational age, and σ represents the variance of the biological indicator in the measurement sample of this gestational age;

[0093] Step 902, if it is not the first time to perform statistical calculations for a certain gestational age, the mean μ and variance σ can be calculated using the calculation results of the previous mean and variance and the maximum likelihood estimation formula to reduce the amount of calculations.

[0094] The specific formula is as follows:

[0095]

[0096]

[0097] Among them, μ and σ represent the mean and variance calculated last time, μ ′ and σ ′ represents the mean and variance of this calculation, x i represents the biological indicators in the newly added measurement samples in this calculation, k represents the total number of samples measured this time, and n represents the total number of samples measured last time.

[0098] In one or more possible embodiments, the above probability distribution parameters are fitted to obtain the fetal growth curve under the above biological indicators, such as Fig.10 As shown, including:

[0099] Step 1001, using the least square method to fit the mean μ / upper bound / lower bound corresponding to each group of measurement samples;

[0100] Step 1002, obtaining the fetal growth curve of the mean μ / upper limit / lower limit of the above biological indicators.

[0101] In one or more possible embodiments, the above probability distribution parameters are fitted to obtain the fetal growth curve under the above biological indicators, such as Fig.11 As shown, including:

[0102] Step 1101, determining the coefficients in the target polynomial according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the preset highest power m in the target polynomial for fitting;

[0103] Step 1102, determining the residual sum of squares according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the coefficients in the above target polynomial;

[0104] Step 1103, if it is determined that the residual sum of squares meets the preset deviation requirement, a target polynomial is determined according to the preset highest power m and the coefficients in the target polynomial, and a fetal growth curve under the biological indicator is determined according to the target polynomial;

[0105] Step 1104 , if it is determined that the residual sum of squares does not meet the preset deviation requirement, the highest power m is reset and the process returns to step 1101 .

[0106] In one or more possible embodiments, for simplicity of description, the mean of the biparietal diameter is used as an example. After the calculation of all groups of biparietal diameters is completed, (x1, y1), ..., (x n ,y n ), where n represents the biparietal diameter divided into n groups, x represents the gestational age, and y represents the calculated mean; and it is assumed that the target polynomial used for fitting is Where x represents gestational age, y represents the calculated mean, m represents the highest power preset in the fitted target polynomial, and a i is the coefficient that needs to be determined;

[0107] According to the above (x1, y1), ..., (x n ,y n ) data into the following formula:

[0108] A=(X T X) -1 X T Y

[0109] Where A is the coefficient matrix, including all coefficients of the target polynomial used for fitting, X is the (m+1)*n matrix of gestational age, and Y is the mean (y1,…,y n ) is an n*1 matrix; for example, if the preset highest power m is 2, the target polynomial for fitting is y=a0x 0 +a1x 1 +a2x 2 , the coefficient matrix A includes coefficients a0, a1 and a2;

[0110] According to the coefficients in the above coefficient matrix A, the residual sum of squares ε is calculated using the following formula:

[0111]

[0112] Wherein, ε is the residual sum of squares, n represents a total of n groups of data, and m represents a preset highest power. If it is determined that the residual sum of squares ε meets the preset deviation requirement, the target polynomial is determined according to the preset highest power m and the coefficients in the above target polynomial, and the mean fetal growth curve of the above biparietal diameter is determined according to the above target polynomial; if it is determined that the residual sum of squares ε does not meet the preset deviation requirement, the highest power m is reset and the calculation is continued until the residual sum of squares ε meets the preset deviation requirement; the above re-preset highest power m needs to follow the principle of re-presetting from small to large, for example, the first time the highest power m is determined to be 2, it is found that the residual sum of squares ε calculated according to m=2 does not meet the preset deviation requirement, the next preset highest power m is a positive integer greater than 2, and the residual sum of squares ε is recalculated, and it is determined whether the preset deviation requirement is met; similarly, the upper limit fetal growth curve of the biparietal diameter, the lower limit fetal growth curve of the biparietal diameter, and the fetal growth curves under other biological indicators are all determined by the above method, which will not be repeated here.

[0113] In one or more possible embodiments, the present application also provides a growth curve fitting method, which is applied to an ultrasound machine, such as Fig.12 As shown, including:

[0114] Step 1201, measuring the pregnant woman using an ultrasound probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus;

[0115] Step 1202, according to the gestational age carried in the pregnant woman's information, the measurement results of the above-mentioned biological indicators are associated with the above-mentioned gestational age into a measurement sample and then sent to the server, so that the above-mentioned server adds the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of the above-mentioned biological indicators, and groups the measurement samples in each biological indicator set according to the above-mentioned gestational age; then, the above-mentioned server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fits the above-mentioned probability distribution parameters to obtain the fetal growth curve under the above-mentioned biological indicator.

[0116] In one or more possible embodiments, Fig.13 As shown in FIG. 1 , it is a schematic diagram of a framework in which an ultrasound machine and a server are connected via a network. In this embodiment, only one ultrasound machine is shown. In a specific application, the number of ultrasound machines is not limited. Fig.14 The figure shows the interaction flow chart between the ultrasound machine and the server, including:

[0117] Step 1401: The ultrasound machine measures the pregnant woman through an ultrasound probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus, and associates each biological indicator measurement result with the gestational age to form a measurement sample and then sends it to the server;

[0118] Step 1402, the server adds the plurality of measurement samples to corresponding biological indicator sets according to the measurement results of the biological indicators;

[0119] Step 1403, the server selects, for each biological indicator set, a measurement sample whose measurement time is greater than or equal to the preset start time in the biological indicator set;

[0120] Step 1404, the server determines whether the current preset start time is greater than the last preset start time, if so, execute step 1405, otherwise, execute step 1406;

[0121] Step 1405, deleting all probability distribution parameters corresponding to each biological indicator set, and executing step 1407;

[0122] Step 1406, selecting a measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time and less than the previous preset start time;

[0123] Step 1407, grouping the measurement samples in each biological indicator set according to the gestational age;

[0124] Step 1408, calculating the mean, variance, upper bound and lower bound for each group of measurement samples;

[0125] Step 1409, update the usage range of the sample measured this time, and fit the fetal growth curve of the upper limit / upper limit of the mean under each biological indicator according to the least square method.

[0126] According to a growth curve fitting method provided by the present application, the ultrasound machine is no longer a separate individual in traditional applications, but the collected samples are aggregated to the server through the network, and the server completes the calculation of the fetal growth curve formula without human intervention. The access of multiple ultrasound machines can improve the sample collection efficiency and the efficiency of fetal growth curve fitting. At the same time, the ultrasound machine collects fetal biological indicators corresponding to a certain area, and establishes a fetal growth curve belonging to the local area, which is more in line with the characteristics of the local population; at the same time, the traditional fetal growth curve is a fixed curve, and the fetal growth curve provided by the present application can be updated according to the collected measurement samples. The measurement samples will increase with the passage of time, further improving the accuracy of the fetal growth curve; according to the set time conditions, the measurement samples with a long collection time can be eliminated to ensure that the fitting of the fetal growth curve is more in line with the characteristics of the current population.

[0127] Example 2

[0128] Based on the same inventive concept, the present application also provides a growth curve fitting device, which is applied to a server, such as Fig.15 As shown, including:

[0129] The sample receiving module 1501 is used to receive a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators representing the growth status of the fetus, which are associated with the gestational age in the pregnant woman's information;

[0130] The sample grouping module 1502 is used to add the above-mentioned multiple measurement samples to the corresponding biological indicator sets according to the above-mentioned biological indicator measurement results, and group the measurement samples in each biological indicator set according to the above-mentioned gestational age;

[0131] The growth curve fitting module 1503 is used to determine the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fit the above probability distribution parameters to obtain the fetal growth curve under the above biological indicator.

[0132] In one or more possible embodiments, Fig.16 FIG. 1 is a schematic diagram of a specific architecture of the growth curve fitting device applied to the server, including:

[0133] The server network interface module 1601 is included in the sample receiving module and is used for data transmission with the ultrasound machine;

[0134] The server storage module 1602 is used to store the above-mentioned measurement samples, various biological indicator sets, calculated probability distribution parameters and fetal growth curve formulas. For specific storage methods, refer to Figure 2-Figure 5 And the corresponding text description will not be repeated here.

[0135] The server computing module 1603 includes the above-mentioned sample grouping module and growth curve fitting module, and the specific functions are not described here.

[0136] Based on the same inventive concept, the present application also provides a growth curve fitting device, which is applied to an ultrasound machine, such as Fig.17 As shown, including:

[0137] The measuring module 1701 is used to measure the pregnant woman using an ultrasound probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus;

[0138] The sample sending module 1702 is used to associate the measurement results of the above-mentioned biological indicators with the gestational age carried in the pregnant woman's information into a measurement sample and then send it to the server, so that the above-mentioned server can add the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of the above-mentioned biological indicators, and group the measurement samples in each biological indicator set according to the gestational age; then, the above-mentioned server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fits the above-mentioned probability distribution parameters to obtain the fetal growth curve under the above-mentioned biological indicator.

[0139] In one or more possible embodiments, Fig.18 FIG. 1 is a schematic diagram of a specific structure of the growth curve fitting device applied to an ultrasound machine, including:

[0140] The measurement module 1801 scans and measures the biological indicators of the fetus, such as abdominal circumference, biparietal diameter, etc., and sends the measurement results to the acquisition module after the examination is completed;

[0141] Information collection module 1802, collects information of pregnant women, including name, age, gestational age, etc.;

[0142] The collection module 1803 is included in the sample sending module, and is used to associate the measurement results of the above biological indicators with the gestational age according to the gestational age carried in the pregnant woman's information into a measurement sample and then send it to the server;

[0143] Ultrasound machine network interface module 1804, included in the sample sending module, used for data transmission with the server;

[0144] The ultrasound machine storage module 1805 is used to query the fetal growth curve generated by the server through the ultrasound machine network interface module, and store the fetal growth curve formula and the creation time of the formula.

[0145] Example 3

[0146] Based on the same inventive concept, the present application also provides a growth curve fitting device, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned growth curve fitting method.

[0147] like Fig.19 As shown, the device includes a processor 1901, a memory 1902, a communication interface 1903 and a bus 1904. The processor 1901, the memory 1902 and the communication interface 1903 are connected to each other via the bus 1904.

[0148] The processor 1901 is used to read and execute instructions in the memory 1902, so that at least one processor can execute the growth curve fitting method provided in the above embodiment.

[0149] The memory 1902 is used to store various instructions and programs of the growth curve fitting method provided in the above embodiment.

[0150] The bus 1904 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.19 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0151] Processor 1901 may be a central processing unit (CPU), a network processor (NP), a graphic processing unit (GPU), or any combination of CPU, NP, and GPU. It may also be a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0152] Example 4

[0153] The present application also provides a storage medium, such as Fig. 20 As shown, the storage medium stores a computer program, and the computer program is used to enable a computer to execute any one of the methods in the above embodiments.

[0154] The memory may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 2001 and / or a cache memory 2002 , and may further include a read-only memory (ROM) 2003 .

[0155] The memory may also include a program / utility 2005 having a set (at least one) of program modules 2004, such program modules 2004 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0156] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0157] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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.

[0158] 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.

[0159] 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.

[0160] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A growth curve fitting method, characterized in that: Applicable to servers, including: Receiving a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators representing the growth status of the fetus, which are associated with the gestational age in the pregnant woman's information; According to the measurement results of each biological indicator, the multiple measurement samples are respectively added to the corresponding biological indicator set, and the measurement samples in each biological indicator set are grouped according to the gestational age; For each biological indicator, the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set are determined, and the probability distribution parameters are fitted to obtain the fetal growth curve under the biological indicator.

2. The method according to claim 1, characterized in that The measurement sample also includes the measurement time of each biological indicator; Before grouping the measurement samples in each biological indicator set according to the gestational age, the method further includes: For each biological indicator set, comparing the measurement time of the biological indicator of each measurement sample in the biological indicator set with the preset start time, and determining to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the preset start time; or, For each biological indicator set, the measurement time of the biological indicator of each measurement sample in the biological indicator set is compared with the current preset start time, the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time is selected, and the current preset start time is compared with the last preset start time; if the current preset start time is greater than the last preset start time, it is determined to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time; if the current preset start time is not greater than the last preset start time, it is determined to select the measurement sample in the biological indicator set whose measurement time is greater than or equal to the current preset start time and which was not selected last time.

3. The method according to claim 1, characterized in that The probability distribution parameters include a mean μ, an upper bound, and a lower bound. The step of determining the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set includes: The mean μ and variance σ of the biological index measurement results in each group of measurement samples are determined according to the maximum likelihood estimation formula; Determine an upper bound and a lower bound according to the mean μ and / or the variance σ; And, fitting the probability distribution parameters to obtain a fetal growth curve under the biological indicator, including: According to the mean μ / upper limit / lower limit corresponding to each group of measurement samples, the least squares method is used for fitting to obtain the fetal growth curve of the mean μ / upper limit / lower limit under the biological indicator.

4. The method according to claim 3, characterized in that Determining an upper bound and a lower bound according to the mean μ and / or the variance σ includes: Determine the reference range of the growth curve in the form of variance, then determine the upper limit according to the formula μ+bσ and the lower limit according to μ-bσ, where b is 1 or 2; or The reference range of the growth curve is determined in percentage form, and the upper and lower limits are determined by searching a normal distribution table according to the mean μ or the variance σ.

5. The method according to claim 3, characterized in that: The fitting of the probability distribution parameters to obtain the fetal growth curve under the biological indicator includes: Determine the coefficients in the target polynomial according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the highest power m preset in the target polynomial for fitting; Determine the residual sum of squares according to the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the coefficients in the target polynomial; If it is determined that the residual sum of squares meets the preset deviation requirement, a target polynomial is determined according to the preset highest power m and the coefficients in the target polynomial, and a fetal growth curve under the biological indicator is determined according to the target polynomial; If it is determined that the residual sum of squares does not meet the preset deviation requirement, the highest power m is reset, and the step of determining the coefficients in the target polynomial is returned based on the mean μ corresponding to each group of measurement samples, the corresponding gestational age and the highest power m preset in the target polynomial used for fitting.

6. A growth curve fitting method, characterized in that: Applicable to ultrasound machines, including: Measuring the pregnant woman with an ultrasound probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus; According to the gestational age carried in the pregnant woman's information, the measurement results of each biological indicator are associated with the gestational age into a measurement sample and then sent to the server, so that the server adds the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of each biological indicator, and groups the measurement samples in each biological indicator set according to the gestational age; then, for each biological indicator, the server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set, and fits the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

7. A growth curve fitting device, characterized in that: Applicable to servers, including: A sample receiving module, used to receive a plurality of measurement samples sent by at least one ultrasound machine, wherein the measurement samples include measurement results of various biological indicators that are associated with the gestational age in the pregnant woman's information and characterize the growth status of the fetus; A sample grouping module, configured to add the plurality of measurement samples to corresponding biological indicator sets according to the measurement results of the biological indicators, and group the measurement samples in each biological indicator set according to the gestational age; The growth curve fitting module is used to determine the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fit the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

8. A growth curve fitting device, characterized in that: Applicable to ultrasound machines, including: A measuring module, used to measure the pregnant woman using an ultrasonic probe to obtain at least one biological indicator measurement result for characterizing the growth status of the fetus; The sample sending module is used to associate the measurement results of each biological indicator with the gestational age carried in the pregnant woman's information into a measurement sample and then send it to the server, so that the server can add the multiple measurement samples received from at least one ultrasound machine to the corresponding biological indicator set according to the measurement results of each biological indicator, and group the measurement samples in each biological indicator set according to the gestational age; then, the server determines the probability distribution parameters corresponding to each group of measurement samples in the corresponding biological indicator set for each biological indicator, and fits the probability distribution parameters to obtain the fetal growth curve under the biological indicator.

9. A growth curve fitting device, characterized in that: The device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the growth curve fitting method as described in any one of claims 1-5 or 6.

10. A storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to enable a computer to execute the growth curve fitting method as described in any one of claims 1-5 or 6.

Images