Fetal heart ultrasonic sound signal graph imaging method based on artificial intelligence

Abstract

The invention relates to the technical field of fetal heart ultrasonic imaging, in particular to a fetal heart ultrasonic sound signal graph imaging method based on artificial intelligence, which comprises the following steps of: determining a fetal heart area based on a fetal form and acquiring a fetal heart sound signal of a fetus by using a fetal heart detector; determining the qualification of the determination of the fetal heart area according to the definition of the fetal heart sound signal; when the fetal heart area is determined to be qualified, whether the fetal heart activity is in a normal range or not is judged according to the fetal heart rate variation coefficient within the first preset duration; when the fetal heart activity is in a normal range, fetal heart sound signals of different point positions are obtained, and then preprocessing operations such as filtering and denoising are carried out; judging whether the acquisition of the preprocessed fetal heart sound signal meets a preset standard or not based on the signal characteristic value; when the acquired fetal heart sound signal meets the preset standard, the fetal heart sound signal is converted into a visual image by using an image processing algorithm, so that the acquisition accuracy of the fetal heart ultrasonic sound signal is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fetal heart ultrasound imaging, and in particular to a fetal heart ultrasound sound signal graphic imaging method based on artificial intelligence. Background Art

[0002] Fetal ultrasound is a non-invasive prenatal examination method that uses ultrasound to image the fetal heart to evaluate the structure and function of the fetal heart. However, traditional fetal ultrasound imaging technology has many limitations, such as image quality is affected by fetal position, maternal factors and ultrasound equipment performance, and is highly dependent on the operator's technical level. These factors often lead to misdiagnosis or delayed diagnosis of fetal heart disease, which may miss the best time for intervention. Artificial intelligence technology uses advanced computer algorithms to automatically analyze, process and interpret medical imaging data, thereby improving the accuracy and efficiency of diagnosis. Especially in the field of ultrasound imaging, artificial intelligence technology has shown great potential to optimize image acquisition, improve image quality, automatically extract and standardize measurement-related parameters, and assist doctors in the classification and differential diagnosis of diseases.

[0003] Through artificial intelligence technology, the fetal heart ultrasound sound signal can be automatically analyzed, processed and high-quality fetal heart images can be generated. This method uses a deep learning algorithm to train a large amount of fetal heart ultrasound data, enabling it to automatically identify the structural characteristics of the fetal heart and generate clear images.

[0004] Chinese patent application publication number: CN116867440A, discloses a method and system for ultrasonic imaging of fetal heart, including: taking a delay time; controlling multiple three-dimensional ultrasonic scans of the fetal heart to obtain multiple volumes of three-dimensional ultrasonic data containing multiple cardiac cycles; wherein, after each completion of the three-dimensional ultrasonic scan, the next three-dimensional ultrasonic scan is performed after the delay time; rearranging the multiple volumes of the three-dimensional ultrasonic data in the order of cardiac phases to obtain the multiple volumes of the three-dimensional ultrasonic data after the data rearrangement; and displaying the fetal heart according to the multiple volumes of the three-dimensional ultrasonic data after the data rearrangement. It can be seen that in the prior art, the lack of processing and regulation of ultrasonic sound signals may cause the formed image to be unclear or inaccurate. Summary of the invention

[0005] To this end, the present invention provides a fetal heart ultrasound sound signal graphic imaging method based on artificial intelligence to overcome the problem in the prior art of inaccurate images generated due to interference from other factors during the fetal heart ultrasound sound signal acquisition process.

[0006] To achieve the above object, the present invention provides a fetal heart ultrasound sound signal graphic imaging method based on artificial intelligence, comprising: Determine the fetal heart area based on the fetal morphology and use a fetal heart detector to collect the fetal heart sound signal; Determining eligibility of the determination of the fetal heart region according to the clarity of the fetal heart sound signal, determining that the determination of the fetal heart region is unqualified when the signal clarity is less than a preset clarity, and adjusting the fetal heart region according to the fetal position change value; Under the condition that the signal clarity is greater than or equal to the preset clarity, determining that the fetal heart area is qualified, and determining whether the fetal heart activity is within a normal range according to the fetal heart rate variation coefficient within the first preset time length; Under the condition that the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient, the fetal heart activity is determined to be within the normal range, and fetal heart sound signals at different points are obtained and then pre-processed by filtering, denoising and other operations; Under the condition that the fetal heart rate variation coefficient is greater than or equal to the preset fetal heart rate variation coefficient, determining that the fetal heart activity is not within the normal range, and changing the pregnant woman's body position or increasing the fetal heart detection time; Determine whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, determine that the acquisition of the fetal heart sound signal does not meet the preset standard under the condition that the signal characteristic value is less than the preset signal characteristic value, and determine the reason why the acquisition of the fetal heart sound signal does not meet the preset standard based on the signal characteristic difference; Under the condition that the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and the fetal heart sound signal is converted into a visual image using an image processing algorithm.

[0007] Further, the process of determining the fetal heart region based on the fetal morphology includes: Use an ultrasound probe to determine the fetal outline and position; Determine the preset size of the fetal heart based on the size of the fetus, and then determine the preset area of ​​the fetal heart; Use a fetal heart rate detector to collect fetal heart sound signals in a preset area contour; Comparing the received strength of the fetal heart sound signal with a preset sound signal strength; The fetal heart region is determined under the condition that the fetal heart sound signal strength is greater than or equal to the preset sound signal strength.

[0008] Further, the eligibility of the determination of the fetal heart area is determined according to the clarity of the fetal heart sound signal, wherein: If the signal clarity is less than the preset clarity, it is determined that the determination of the fetal heart region is unqualified, and the fetal heart region is adjusted according to the fetal position change value; If the signal clarity is greater than or equal to the preset clarity, it is determined that the fetal heart area is qualified, and whether the fetal heart activity is within a normal range is determined based on the fetal heart rate variation coefficient within the first preset time period.

[0009] Further, the fetal heart region is adjusted according to the fetal position change value, wherein: If the fetal position change value is less than a preset position change value, adjusting the fetal heart region to a corresponding value using a first displacement adjustment coefficient; If the fetal position change value is greater than or equal to the preset position change value, the fetal heart area is adjusted to a corresponding value using a second displacement adjustment coefficient.

[0010] Further, whether the fetal heart rate activity is within a normal range is determined according to the fetal heart rate variation coefficient within the first preset time period, wherein: If the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient, it is determined that the fetal heart activity is within the normal range, and fetal heart sound signals at different points are obtained and then pre-processed by filtering, denoising, etc.; If the fetal heart rate variability coefficient is greater than or equal to the preset fetal heart rate variability coefficient, it is determined that the fetal heart activity is not within the normal range, and the pregnant woman's position is changed or the fetal heart detection time is increased.

[0011] Furthermore, the process of acquiring the fetal heart sound signal includes: Determine the point with the strongest signal in the fetal heart area; With the strongest signal point as the center point, radiate outwards to the surrounding areas and determine a point at each preset distance; After detecting the second preset time at each point, switch to the next point; When the point signal strength value is less than a preset strength value, the detection is stopped and the acquisition of the fetal heart sound signal is completed.

[0012] Further, it is determined whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, wherein: If the signal characteristic value is less than the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal does not meet the preset standard, and the reason for not meeting the preset standard is determined according to the difference between the preset signal characteristic value and the signal characteristic value; If the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and the fetal heart sound signal is converted into a visual image using an image processing algorithm.

[0013] Further, the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is determined according to the signal characteristic difference, wherein: If the signal characteristic difference is less than the preset signal characteristic difference, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the determination of the signal collection points is unqualified, and the spacing of the signal collection points is reduced according to the signal fluctuation value; If the signal characteristic difference is greater than or equal to the preset signal characteristic difference, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the denoising process is unqualified, and the sensitivity of the denoising process is increased according to the proportion of interference signals; The signal characteristic difference value is the difference between the preset signal characteristic value and the signal characteristic value.

[0014] Furthermore, the spacing between signal collection points is reduced according to the signal fluctuation value, wherein: If the signal fluctuation value is less than the preset fluctuation value, the spacing of the signal collection points is adjusted to a corresponding value using the first spacing adjustment coefficient; If the signal fluctuation value is greater than or equal to the preset fluctuation value, the second spacing adjustment coefficient is used to adjust the spacing of the signal collection points to a corresponding value.

[0015] Furthermore, the sensitivity of the denoising process is improved according to the proportion of interference signals, where: If the interference signal ratio is less than the preset interference signal ratio, the sensitivity of the denoising process is adjusted to a corresponding value using the first sensitivity adjustment coefficient; If the interference signal ratio is greater than or equal to the preset interference signal ratio, the sensitivity of the denoising process is adjusted to a corresponding value using the second sensitivity adjustment coefficient.

[0016] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention determines the fetal heart region based on the fetal morphology and uses a fetal heart detector to collect the fetal heart sound signal of the fetus, determines the eligibility of the determination of the fetal heart region according to the clarity of the fetal heart sound signal, determines that the determination of the fetal heart region is unqualified under the condition that the signal clarity is less than the preset clarity, and adjusts the fetal heart region according to the fetal position change value. By determining the fetal heart region, the efficiency of detection can be improved. At the same time, the determination of the fetal heart region is determined to be qualified under the condition that the signal clarity is greater than or equal to the preset clarity, and determines whether the fetal heart activity is within the normal range according to the fetal heart rate variation coefficient within a first preset time length, determines that the fetal heart activity is within the normal range under the condition that the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient, and obtains the fetal heart sound signals at different points and performs preprocessing operations such as filtering and denoising, and determines that the fetal heart activity is not within the normal range under the condition that the fetal heart rate variation coefficient is greater than or equal to the preset fetal heart rate variation coefficient. The method is to determine whether the fetal heart activity is within the normal range, change the pregnant woman's body position or increase the fetal heart detection time. By determining whether the fetal heart activity is within the normal range, the problem of inaccurate detection results caused by abnormal fetal heart activity can be avoided. Then, based on the signal characteristic value, it is determined whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard. Under the condition that the signal characteristic value is less than the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal does not meet the preset standard. According to the signal characteristic difference, the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is determined. Under the condition that the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard. An image processing algorithm is used to convert the fetal heart sound signal into a visualized image. By accurately locating the fetal heart area, dynamically adjusting the fetal heart detection strategy, optimizing the preprocessing of the fetal heart sound signal, realizing the visualization of the fetal heart sound signal, and improving the efficiency and accuracy of fetal heart monitoring, more reliable technical support is provided for fetal health monitoring.

[0017] Furthermore, the present invention determines the eligibility of the determination of the fetal heart area based on the clarity of the fetal heart sound signal, wherein, if the signal clarity is less than a preset clarity, the determination of the fetal heart area is determined to be unqualified, and the fetal heart area is adjusted according to the fetal position change value; if the signal clarity is greater than or equal to the preset clarity, the determination of the fetal heart area is determined to be qualified, and based on the fetal heart rate variation coefficient within a first preset time period, it is determined whether the fetal heart activity is within a normal range. By dynamically adjusting the fetal heart detection strategy, the collection quality of the fetal heart sound signal can be ensured.

[0018] Furthermore, the present invention determines whether the fetal heart activity is within a normal range based on the fetal heart rate variability coefficient within a first preset time period, wherein if the fetal heart rate variability coefficient is less than the preset fetal heart rate variability coefficient, the fetal heart activity is determined to be within the normal range, and the fetal heart sound signals at different points are obtained and then preprocessing operations such as filtering and denoising are performed; if the fetal heart rate variability coefficient is greater than or equal to the preset fetal heart rate variability coefficient, the fetal heart activity is determined to be not within the normal range, and the pregnant woman's body position is changed or the fetal heart detection time is increased, and the signal quality is improved through preprocessing operations such as filtering and denoising, and the accuracy of subsequent image processing is ensured.

[0019] Furthermore, the present invention determines whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, wherein if the signal characteristic value is less than the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal does not meet the preset standard, and the reason for not meeting the preset standard is determined according to the difference between the preset signal characteristic value and the signal characteristic value; if the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and an image processing algorithm is used to convert the fetal heart sound signal into a visual image. Through the image processing algorithm, the fetal heart sound signal can be converted into a visual image, providing doctors with intuitive and clear fetal heart monitoring results, which helps doctors to more accurately judge the health status of the fetus and improve the accuracy and reliability of fetal heart monitoring.

[0020] Furthermore, the present invention determines the reason why the acquisition of fetal heart sound signals does not meet preset standards based on the signal characteristic difference, wherein if the signal characteristic difference is less than the preset signal characteristic difference, then the reason why the acquisition of fetal heart sound signals does not meet preset standards is that the determination of signal collection points is unqualified, and the spacing between signal collection points is reduced according to the signal fluctuation value; if the signal characteristic difference is greater than or equal to the preset signal characteristic difference, then the reason why the acquisition of fetal heart sound signals does not meet preset standards is that the denoising process is unqualified, and the sensitivity of the denoising process is increased according to the proportion of interference signals. By dynamically adjusting the fetal heart detection strategy and optimizing the preprocessing process, it can adapt to the fetal heart monitoring needs in different situations and provide more comprehensive and accurate support for fetal health monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a method for graphical imaging of fetal heart ultrasound sound signals based on artificial intelligence according to an embodiment of the present invention; Figure 2 A flow chart of determining eligibility of a fetal heart region according to an embodiment of the present invention; Figure 3 This is a flow chart of an embodiment of the present invention for determining whether fetal heart activity is within a normal range; Figure 4The present invention is a flowchart for determining whether the acquisition of a preprocessed fetal heart sound signal meets a preset standard. DETAILED DESCRIPTION

[0022] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0024] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical test data of the present invention three months before this test and the corresponding historical test results. It can be understood by those skilled in the art that the method of the present invention can determine the above parameters for a single item by selecting the value with the highest proportion as the preset standard parameter according to the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the method of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0025] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, Figure 1 It is a flow chart of a method for graphical imaging of fetal heart ultrasound sound signals based on artificial intelligence according to an embodiment of the present invention; Figure 2 A flow chart of determining eligibility of a fetal heart region according to an embodiment of the present invention; Figure 3 This is a flow chart of an embodiment of the present invention for determining whether fetal heart activity is within a normal range; Figure 4 The present invention is a flowchart for determining whether the acquisition of a preprocessed fetal heart sound signal meets a preset standard.

[0026] The embodiment of the present invention provides a fetal heart ultrasound sound signal graphic imaging method based on artificial intelligence, comprising: S1, determining the fetal heart region based on the fetal morphology and collecting the fetal heart sound signal using a fetal heart detector; S2, judging the eligibility of the determination of the fetal heart region according to the clarity of the fetal heart sound signal, judging that the determination of the fetal heart region is unqualified under the condition that the signal clarity is less than a preset clarity, and adjusting the fetal heart region according to the fetal position change value; S3, determining that the fetal heart area is qualified under the condition that the signal clarity is greater than or equal to the preset clarity, and determining whether the fetal heart activity is within a normal range according to the fetal heart rate variation coefficient within the first preset time length; S4, under the condition that the fetal heart rate variation coefficient is less than a preset fetal heart rate variation coefficient, determining that the fetal heart activity is within a normal range, and obtaining fetal heart sound signals at different points and performing preprocessing operations such as filtering and denoising; S5, under the condition that the fetal heart rate variation coefficient is greater than or equal to the preset fetal heart rate variation coefficient, determining that the fetal heart activity is not within the normal range, and changing the pregnant woman's body position or increasing the fetal heart detection time; S6, determining whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, determining that the acquisition of the fetal heart sound signal does not meet the preset standard under the condition that the signal characteristic value is less than the preset signal characteristic value, and determining the reason why the acquisition of the fetal heart sound signal does not meet the preset standard based on the signal characteristic difference; S7, under the condition that the signal characteristic value is greater than or equal to the preset signal characteristic value, determining that the acquisition of the fetal heart sound signal meets the preset standard, and using an image processing algorithm to convert the fetal heart sound signal into a visual image.

[0027] Specifically, the process of determining the fetal heart region based on fetal morphology includes: Use an ultrasound probe to determine the fetal outline and position; Determine the preset size of the fetal heart based on the size of the fetus, and then determine the preset area of ​​the fetal heart; Use a fetal heart rate detector to collect fetal heart sound signals in a preset area contour; Comparing the received strength of the fetal heart sound signal with a preset sound signal strength; The fetal heart region is determined under the condition that the fetal heart sound signal strength is greater than or equal to the preset sound signal strength.

[0028] In an embodiment of the present invention, the ultrasound probe is a convex array probe, which is used to detect the contour and position of the fetus inside the abdomen of a pregnant woman, so as to determine the area where the fetal heart is located. The approximate proportion of the fetal heart can be determined according to the size of the fetus, thereby further limiting the fetal heart area.

[0029] Optionally, the fetal heart rate detector is, for example, a Doppler fetal heart rate detector, a stethoscope-type fetal heart rate detector, and an intelligent fetal heart rate monitor. In an embodiment of the present invention, the fetal heart rate detector is a Doppler fetal heart rate detector.

[0030] In the embodiment of the present invention, the area of ​​the preset area is 10 cm×10 cm, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0031] In the embodiment of the present invention, the preset sound signal strength value is 5mW / cm², but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0032] Specifically, the eligibility of the determination of the fetal heart region is determined according to the clarity of the fetal heart sound signal, wherein: If the signal clarity is less than the preset clarity of 0.98, it is determined that the determination of the fetal heart region is unqualified, and the fetal heart region is adjusted according to the fetal position change value; If the signal clarity is greater than or equal to the preset clarity, it is determined that the fetal heart area is qualified, and whether the fetal heart activity is within a normal range is determined based on the fetal heart rate variation coefficient within the first preset time length of 30 minutes.

[0033] Specifically, the signal clarity is determined based on the signal-to-noise ratio and the error vector magnitude, and the determination process includes: The ratio of the signal-to-noise ratio to the signal-to-noise ratio threshold is squared and then multiplied by the first evaluation coefficient to obtain a signal-to-noise ratio evaluation value, wherein the first evaluation coefficient is 0.52 and the signal-to-noise ratio threshold is 20 dB; The ratio of the error vector amplitude threshold to the absolute value of the error vector amplitude is squared and then multiplied by a second evaluation coefficient to obtain an error vector amplitude evaluation value, wherein the second evaluation coefficient is 0.45 and the error vector amplitude threshold is 0.1; The sum of the signal-to-noise ratio evaluation value and the error vector magnitude evaluation value is recorded as the signal clarity.

[0034] In the embodiment of the present invention, the preset clarity value is 0.98, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0035] Specifically, the fetal heart region is adjusted according to the fetal position change value, wherein: If the fetal position change value is less than the preset position change value, the fetal heart region is adjusted to a corresponding value using a first displacement adjustment coefficient of 0.15; If the fetal position change value is greater than or equal to the preset position change value, the fetal heart area is adjusted to a corresponding value using a second displacement adjustment coefficient of 0.18.

[0036] In the embodiment of the present invention, the preset body position change value is 5 cm, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0037] Specifically, the displacement adjustment coefficient is the ratio of the fetal position change value to the maximum distance of the horizontal plane where the displacement direction in the uterus is located.

[0038] Specifically, whether the fetal heart rate activity is within a normal range is determined according to the fetal heart rate variation coefficient within the first preset time period, wherein: If the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient of 5 times / min, it is determined that the fetal heart activity is within the normal range, and the fetal heart sound signals at different points are obtained and then pre-processed by filtering, denoising, etc.; If the fetal heart rate variability coefficient is greater than or equal to the preset fetal heart rate variability coefficient, it is determined that the fetal heart activity is not within the normal range, and the pregnant woman's position is changed or the fetal heart detection time is increased.

[0039] In the embodiment of the present invention, the preset fetal heart rate variation coefficient is 5 times / minute, but the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0040] Specifically, the process of obtaining the fetal heart sound signal includes: Determine the point with the strongest signal in the fetal heart area; With the strongest signal point as the center point, radiate outwards to the surrounding areas and determine a point at a preset distance of 1 cm; After detecting each point for the second preset time of 30 seconds, switch to the next point; When the point signal strength value is less than a preset strength value, the detection is stopped and the acquisition of the fetal heart sound signal is completed.

[0041] In the embodiment of the present invention, the preset distance is 1 cm, and the second preset time is 30 s, but the above values ​​are not limited thereto, and those skilled in the art may also adjust the values ​​according to actual needs.

[0042] Specifically, it is determined whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, wherein: If the signal characteristic value is less than a preset signal characteristic value of 0.95, it is determined that the acquisition of the fetal heart sound signal does not meet the preset standard, and the reason for not meeting the preset standard is determined according to the difference between the preset signal characteristic value and the signal characteristic value; If the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and the fetal heart sound signal is converted into a visual image using an image processing algorithm.

[0043] Specifically, the signal characteristic value is the ratio of the fetal heart signal to all received signals.

[0044] In the embodiment of the present invention, the preset signal characteristic value is 0.95, but the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0045] Specifically, the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is determined according to the signal characteristic difference, wherein: If the signal characteristic difference is less than the preset signal characteristic difference of 0.03, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the determination of the signal collection points is unqualified, and the spacing of the signal collection points is reduced according to the signal fluctuation value; If the signal characteristic difference is greater than or equal to the preset signal characteristic difference, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the denoising process is unqualified, and the sensitivity of the denoising process is increased according to the proportion of interference signals; The signal characteristic difference value is the difference between the preset signal characteristic value and the signal characteristic value.

[0046] In the embodiment of the present invention, the preset signal characteristic difference value is 0.03, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0047] Specifically, the spacing between signal collection points is reduced according to the signal fluctuation value, where: If the signal fluctuation value is less than the preset fluctuation value of 0.12, the spacing of the signal collection points is adjusted to a corresponding value using the first spacing adjustment coefficient of 0.99; If the signal fluctuation value is greater than or equal to the preset fluctuation value, the second spacing adjustment coefficient 0.97 is used to adjust the spacing of the signal collection points to a corresponding value.

[0048] Specifically, the signal fluctuation value is the variance of the signal strength value.

[0049] In the embodiment of the present invention, the preset fluctuation value is 0.12, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0050] Specifically, the sensitivity of the denoising process is improved according to the proportion of interference signals, where: If the interference signal ratio is less than the preset interference signal ratio of 3%, the sensitivity of the denoising process is adjusted to a corresponding value using the first sensitivity adjustment coefficient 1.02; If the interference signal ratio is greater than or equal to the preset interference signal ratio, the sensitivity of the denoising process is adjusted to a corresponding value using the second sensitivity adjustment coefficient 1.05.

[0051] In the embodiment of the present invention, the preset interference signal ratio is 3%, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0052] Specifically, the process of using image processing algorithms to convert fetal heart sound signals into visual images includes: Use a large number of fetal heart sound signals to train artificial intelligence models; An artificial intelligence model capable of identifying the characteristics of fetal heart sound signals is established based on the training data; Use the trained artificial intelligence model to identify and analyze new fetal heart sound signals; Generate a fetal heart image based on the analysis results and mark out key information.

[0053] In an embodiment of the present invention, the artificial intelligence model is a convolutional neural network (CNN).

[0054] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fetal heart ultrasound sound signal graphic imaging method based on artificial intelligence, characterized in that: include: Determine the fetal heart area based on the fetal morphology and use a fetal heart detector to collect the fetal heart sound signal; Determining eligibility of the determination of the fetal heart region according to the clarity of the fetal heart sound signal, determining that the determination of the fetal heart region is unqualified when the signal clarity is less than a preset clarity, and adjusting the fetal heart region according to the fetal position change value; Under the condition that the signal clarity is greater than or equal to the preset clarity, determining that the fetal heart area is qualified, and determining whether the fetal heart activity is within a normal range according to the fetal heart rate variation coefficient within the first preset time length; Under the condition that the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient, the fetal heart activity is determined to be within the normal range, and fetal heart sound signals at different points are obtained and then pre-processed by filtering, denoising and other operations; Under the condition that the fetal heart rate variation coefficient is greater than or equal to the preset fetal heart rate variation coefficient, determining that the fetal heart activity is not within the normal range, and changing the pregnant woman's body position or increasing the fetal heart detection time; Determine whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard based on the signal characteristic value, determine that the acquisition of the fetal heart sound signal does not meet the preset standard under the condition that the signal characteristic value is less than the preset signal characteristic value, and determine the reason why the acquisition of the fetal heart sound signal does not meet the preset standard based on the signal characteristic difference; Under the condition that the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and the fetal heart sound signal is converted into a visual image using an image processing algorithm.

2. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 1, characterized in that: The process of determining the fetal heart region based on fetal morphology includes: Use an ultrasound probe to determine the fetal outline and position; Determine the preset size of the fetal heart based on the size of the fetus, and then determine the preset area of ​​the fetal heart; Use a fetal heart rate detector to collect fetal heart sound signals in a preset area contour; Comparing the received strength of the fetal heart sound signal with a preset sound signal strength; The fetal heart region is determined under the condition that the fetal heart sound signal strength is greater than or equal to the preset sound signal strength.

3. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 2, characterized in that: The eligibility of the fetal heart region is determined according to the clarity of the fetal heart sound signal, wherein: If the signal clarity is less than the preset clarity, it is determined that the determination of the fetal heart region is unqualified, and the fetal heart region is adjusted according to the fetal position change value; If the signal clarity is greater than or equal to the preset clarity, it is determined that the fetal heart area is qualified, and whether the fetal heart activity is within a normal range is determined based on the fetal heart rate variation coefficient within the first preset time period.

4. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 3, characterized in that: The fetal heart region is adjusted according to the fetal position change value, wherein: If the fetal position change value is less than a preset position change value, adjusting the fetal heart region to a corresponding value using a first displacement adjustment coefficient; If the fetal position change value is greater than or equal to the preset position change value, the fetal heart area is adjusted to a corresponding value using a second displacement adjustment coefficient.

5. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 4, characterized in that: Determine whether the fetal heart rate activity is within a normal range according to the fetal heart rate variation coefficient within the first preset time period, wherein: If the fetal heart rate variation coefficient is less than the preset fetal heart rate variation coefficient, it is determined that the fetal heart activity is within the normal range, and fetal heart sound signals at different points are obtained and then pre-processed by filtering, denoising, etc.; If the fetal heart rate variability coefficient is greater than or equal to the preset fetal heart rate variability coefficient, it is determined that the fetal heart activity is not within the normal range, and the pregnant woman's position is changed or the fetal heart detection time is increased.

6. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 5, characterized in that: The process of obtaining the fetal heart sound signal includes: Determine the point with the strongest signal in the fetal heart area; With the strongest signal point as the center point, radiate outwards to the surrounding areas and determine a point at each preset distance; After detecting the second preset time at each point, switch to the next point; When the point signal strength value is less than a preset strength value, the detection is stopped and the acquisition of the fetal heart sound signal is completed.

7. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 6, characterized in that: Based on the signal characteristic value, it is determined whether the acquisition of the preprocessed fetal heart sound signal meets the preset standard, wherein: If the signal characteristic value is less than the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal does not meet the preset standard, and the reason for not meeting the preset standard is determined according to the difference between the preset signal characteristic value and the signal characteristic value; If the signal characteristic value is greater than or equal to the preset signal characteristic value, it is determined that the acquisition of the fetal heart sound signal meets the preset standard, and the fetal heart sound signal is converted into a visual image using an image processing algorithm.

8. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 7, characterized in that: The reason why the acquisition of the fetal heart sound signal does not meet the preset standard is determined according to the signal characteristic difference, wherein: If the signal characteristic difference is less than the preset signal characteristic difference, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the determination of the signal collection points is unqualified, and the spacing of the signal collection points is reduced according to the signal fluctuation value; If the signal characteristic difference is greater than or equal to the preset signal characteristic difference, it is determined that the reason why the acquisition of the fetal heart sound signal does not meet the preset standard is that the denoising process is unqualified, and the sensitivity of the denoising process is increased according to the proportion of interference signals; The signal characteristic difference value is the difference between the preset signal characteristic value and the signal characteristic value.

9. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 8, characterized in that: Reduce the spacing between signal collection points according to the signal fluctuation value, where: If the signal fluctuation value is less than the preset fluctuation value, the spacing of the signal collection points is adjusted to a corresponding value using the first spacing adjustment coefficient; If the signal fluctuation value is greater than or equal to the preset fluctuation value, the second spacing adjustment coefficient is used to adjust the spacing of the signal collection points to a corresponding value.

10. The artificial intelligence-based fetal heart ultrasound sound signal graphic imaging method according to claim 9, characterized in that: The sensitivity of the denoising process is improved according to the proportion of interference signals, where: If the interference signal ratio is less than the preset interference signal ratio, the sensitivity of the denoising process is adjusted to a corresponding value using the first sensitivity adjustment coefficient; If the interference signal ratio is greater than or equal to the preset interference signal ratio, the sensitivity of the denoising process is adjusted to a corresponding value using the second sensitivity adjustment coefficient.

Images