CN109589137B - Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium - Google Patents
Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium Download PDFInfo
- Publication number
- CN109589137B CN109589137B CN201811300989.2A CN201811300989A CN109589137B CN 109589137 B CN109589137 B CN 109589137B CN 201811300989 A CN201811300989 A CN 201811300989A CN 109589137 B CN109589137 B CN 109589137B
- Authority
- CN
- China
- Prior art keywords
- fetal movement
- fetal
- effective
- movement
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0866—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/48—Diagnostic techniques
- A61B8/488—Diagnostic techniques involving Doppler signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Gynecology & Obstetrics (AREA)
- Pregnancy & Childbirth (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the technical field of fetal movement signal analysis, and particularly relates to a method, a device, a terminal and a computer readable storage medium for fetal movement identification, wherein the method comprises the following steps: acquiring a fetal movement signal; extracting an energy envelope of the fetal movement signal; identifying valid fetal movements from the energy envelope; and judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result. The invention improves the accuracy of fetal movement identification.
Description
Technical Field
The invention belongs to the technical field of fetal movement signal analysis, and particularly relates to a method, a device, a terminal and a computer readable storage medium for fetal movement identification.
Background
Fetal movement is the movement of a fetus in the uterus of a pregnant woman and is an important index of the safe state of the fetus in the uterus. During normal pregnancy, pregnant women who are 18-20 weeks pregnant can feel fetal movement, fetal movement increases with the increase of the gestational week after 20 weeks, fetal movement decreases after 32 weeks reach a peak, and overdue pregnancy is obviously reduced. Timor-Tritsch classifies fetal movements into 4 classes: 1) trunk rotation movement, 2) pure limb movement, 3) high-frequency movement, and 4) fetal respiration movement. Sadovsky classifies fetal movement into 3 classes: 1) weak fetal movement for a short time, 2) strong fetal movement for a short time, and 3) rotational fetal movement for an extended time.
At present, the fetal movement detection at home and abroad is mainly realized by adopting a manual marker to count fetal movements of pregnant women according to subjective feeling, and the method is mainly used for recording the sensible fetal movements of the pregnant women. The clinical application shows that the manual marking and counting mode is influenced by factors such as the character, the sensitivity, the amniotic fluid volume, the abdominal wall thickness, the placenta position, the medicine, the fetal activity and the uterine contraction of the pregnant woman, is related to the attention procedure of the pregnant woman, has obvious subjectivity, can generate the phenomena of missed marking and mistaken marking, consumes long time, and can not lead the pregnant woman to engage in other activities in the recording process. In addition, the manual fetal movement detection can only record whether fetal movement exists, and the strength information of the fetal movement cannot be reflected, so that whether the fetal movement occurs or not is difficult to identify.
The ultrasonic Doppler detection method is used as a safe and noninvasive detection means for monitoring the fetus during pregnancy and is widely applied to obstetrical clinic. The ultrasonic Doppler fetal movement detection adopts echo and Doppler principles, extracts frequency shift signals of ultrasonic Doppler, obtains fetal movement signals through a series of signal processing means, and can directly detect all movements of the head, limbs and trunk of a fetus, including fetal movement which can be sensed by a pregnant woman and not sensed by the pregnant woman.
There is no fixed standard for fetal movement counting in clinic, and such intermittent fetal movements which are separated by only a few seconds, whether automatic fetal movement identification or pregnant woman perception, are considered as multiple fetal movements and then marked. Too many fetal movement marks are printed in the fetal heart monitoring process, which may affect the overall attractiveness of the CTG report and may also bring trouble to obstetricians.
Therefore, the existing fetal movement identification mode has low accuracy and leads to clinical judgment of obstetrics.
Disclosure of Invention
The embodiment of the invention provides a method, a device, a terminal and a computer readable storage medium for fetal movement identification, which improve the accuracy of fetal movement identification.
The first aspect of the embodiments of the present invention provides a method for identifying fetal movement, including:
acquiring a fetal movement signal;
extracting an energy envelope of the fetal movement signal;
identifying valid fetal movements from the energy envelope;
and judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result.
A second aspect of the embodiments of the present invention provides a device for recognizing fetal movements, including:
the acquisition module is used for acquiring fetal movement signals;
the extraction module is used for extracting the energy envelope of the fetal movement signal;
a first identification module for identifying valid fetal movements from the energy envelope;
and the second identification module is used for judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result.
A third aspect of the embodiments of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method when executing the computer program.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the above method.
In the embodiment of the invention, after the effective fetal movement is identified, the identified effective fetal movement is secondarily processed according to the attribute information of the effective fetal movement, the effective fetal movements meeting the conditions are combined, the complete fetal movement information is kept, a more accurate fetal movement identification result is provided for a user, and misleading of the fact that the number of fetal movement counting times is too large in the prior art to obstetrical clinical judgment is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of an implementation of a method for fetal movement identification according to an embodiment of the present invention;
FIG. 2 is a flow chart of another implementation of a method for fetal activity identification according to an embodiment of the present invention;
FIG. 3 is a flow chart of another implementation of a method for fetal activity identification according to an embodiment of the present invention;
FIG. 4 is a schematic representation of a fetal movement marking method provided in the prior art;
FIG. 5 is a flow chart of an implementation of another method for fetal activity identification according to an embodiment of the present invention;
FIG. 6 is a schematic representation of a fetal movement marking method provided by an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a fetal movement identification apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The described embodiments are only some embodiments of the invention, not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. Meanwhile, in the description of the present invention, the terms "first", "second", "third", and "fourth", etc. are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
When identifying fetal movement in the prior art, no matter the intensity, duration and interval of single fetal movement with last fetal movement, the fetal movement is identified as an independent fetal movement, and the fetal movement is marked. The manual fetal movement mode is characterized in that the fetal movement of the pregnant woman is counted according to subjective feeling, the pregnant woman is confused about how to mark the fetal movement with relatively short interval, and the fetal movement with short interval time can be marked into independent small fetal movement to form a plurality of fetal movement marks.
Fetal movement is divided into intermittent movement and continuous movement, and clinically, when the fetal movement frequency is calculated, the intermittent fetal movement in a short time is generally regarded as primary fetal movement. During automatic fetal movement identification, if a plurality of small fetal movements within a period of time are represented by a mark with very long duration and cannot be distinguished from the continuous fetal movements within the period of time, therefore, during automatic fetal movement identification, the condition of very large number of fetal movements generally occurs, and the large number of fetal movements possibly causes troubles for the judgment of a clinician, and the lasting duration of single fetal movement is too long, suspected continuous fetal movement is restless, and the clinician can also be alerted.
The application provides a fetal movement identification method, through after the effective fetal movement is identified, namely the fetal movement defined in the prior art, secondary processing is carried out on the identified effective fetal movement according to the fetal movement attribute information of the effective fetal movement, partial effective fetal movements are combined, the complete fetal movement information is kept, meanwhile, a more accurate fetal movement identification mode is provided for a user, and misleading to clinical judgment of obstetrics due to too many fetal movement counting times in the prior art is avoided.
Fig. 1 is a flow chart illustrating an implementation of a method for fetal activity identification according to an embodiment of the present invention, where the method is performed by a fetal activity identification apparatus, which is generally configured as a fetal monitor, and can be implemented by software and/or hardware. Fetal monitoring devices such as fetal heart monitors. As shown in fig. 1, the method includes steps 101 to 104.
And S101, acquiring a fetal movement signal.
The fetal movement signal is fetal monitoring data, including fetal heart rate data.
In one embodiment of the invention, the fetal monitor comprises an ultrasonic Doppler probe, and the ultrasonic Doppler fetal movement detection adopts echo and Doppler principles, so that all movements of the head, limbs and trunk of the fetus, including the sensible fetal movement and the imperceptible fetal movement of the pregnant woman, can be detected relatively sensitively and directly, and are not easily interfered by maternal breathing signals. For example, fetal movement doppler frequency shift signals are acquired from the abdomen of the pregnant woman through an ultrasonic doppler probe, amplified and input to an acquisition device for subsequent fetal movement identification.
In another embodiment of the invention, the fetal monitor comprises a pressure sensor probe, and fetal movement signals can also be acquired from the abdomen of the pregnant woman through the pressure sensor probe, processed by filtering, amplification and the like, and input into the acquisition equipment so as to carry out subsequent effective fetal movement identification.
That is, the fetal monitor acquires fetal movement signals of the pregnant woman in real time through the probe, and then effectively identifies the fetal movement signals in real time.
Optionally, after step 101, the method further includes: and preprocessing the fetal movement signal.
If the fetal movement signal is preprocessed, the preprocessed fetal movement signal is further processed in the subsequent steps so as to identify effective fetal movement and judge the combination of the effective fetal movement.
The preprocessing includes amplification, filtering, smoothing, and the like. Different preprocessing steps can be performed according to different probes for acquiring fetal monitoring data. The fetal movement signal can be amplified through the amplifier, the filtering processing is carried out through the band-pass filter so as to filter a base line and inhibit the interference of fetal heart signals, mother breathing signals and the like, and based on the base line, the preprocessed fetal movement signal is used for subsequently recognizing the fetal movement original signal of effective fetal movement.
S102, extracting the energy envelope of the fetal movement signal.
The energy envelope of the fetal movement signal is extracted mainly for extracting slowly-changing information in the fetal movement signal, but the information which changes rapidly is not very concerned. Because the slowly changing information in the fetal movement signal reflects the fetal movement more accurately, the data processing amount is reduced and the identification accuracy is improved by extracting the energy envelope.
As an embodiment of the present invention, a method for extracting an energy envelope of a fetal movement signal may use a low-pass filter, or may use integral energy.
As another embodiment of the present invention, the fetal movement energy envelope signal is obtained by calculating the normalized average shannon energy. The normalized average shannon energy can inhibit lower and higher interference, highlight partial signals with medium intensity, and is beneficial to identifying fetal movement duration time, and meanwhile, the normalized average shannon energy can quantify the fetal movement intensity to a certain extent, so that the fetal movement counting, merging and marking can be carried out more accurately in the follow-up process.
Specifically, as shown in fig. 2, step 102 includes steps 201 to 206.
S201, performing full-wave rectification on the fetal movement signal to obtain a full-wave rectification signal.
Wherein the fetal movement signal is full-wave rectified to obtain a full-wave rectified signal. And when the fetal movement signal is the preprocessed fetal movement signal, full-wave rectification is carried out on the preprocessed fetal movement signal to obtain a full-wave rectification signal.
S202, normalizing the full-wave rectification signal to obtain a normalized signal.
When calculating the normalized average shannon energy, firstly, normalization processing needs to be performed on the full-wave rectification signal to obtain a normalized signal, wherein the normalization mode is as follows:
xnorm(k)＝x(k)/max(|x(k)|)，
where x (k) is the full-wave rectified signal and max (| x (k) |) is the maximum signal amplitude of the full-wave rectified signal.
S203, calculating the normalized average Shannon energy of each sliding window corresponding to the normalized signal.
The normalized average shannon energy is calculated by carrying out overlapping segmentation processing on the normalized signal, and the normalized average shannon energy of the normalized signal in each T1 sliding window is calculated by taking T1 time as the window length of the sliding window, taking 1/n of the window length as a step length and taking n as a positive integer.
In particular, the amount of the solvent to be used,
wherein, when N is T1Length of signal in between, being a positive integer, Es(t) is the normalized average shannon energy of the s-th sliding window.
S204, judging whether the normalized average Shannon energy of each sliding window is larger than or equal to a first preset threshold value.
S205, if the normalized average Shannon energy of the sliding window is larger than or equal to the first preset threshold value, taking the normalized average Shannon energy as the fetal movement intensity of the sliding window.
S206, if the normalized average Shannon energy of the sliding window is smaller than the first preset threshold value, setting the fetal movement intensity of the sliding window to be zero.
Judging whether the normalized average shannon energy corresponding to each sliding window is greater than or equal to a first preset threshold, and if the normalized average shannon energy corresponding to each sliding window is greater than or equal to the first preset threshold Pre _ Thr1, taking the normalized average shannon energy corresponding to the sliding window as the fetal movement intensity of the sliding window; if the value is less than the first preset threshold value Pre _ Thr1, the fetal movement intensity corresponding to the sliding window is directly set to zero. Further, the fetal activity strength corresponding to each sliding window is stored.
Illustratively, the total number of sampling points of the normalized signal is 1000, the window length T1 of the sliding window is set to 20 sampling points, the window length 1/2 of the sliding window is set to 10, the data in the first sliding window is from 1 to 20, the data in the second sliding window is from 10 to 30, the data in the 3 rd sliding window is from 20 to 40, and so on. The corresponding normalized average shannon energy for each sliding window is then calculated, with a maximum of 1, and Pre _ Thr1 can be set to 0.3. When the corresponding normalized average shannon energy of the sliding window is greater than or equal to 0.3, taking the corresponding normalized average shannon energy of the sliding window as the fetal movement intensity of the sliding window; when the corresponding normalized mean shannon energy of the sliding window is less than 0.3, the fetal activity level of the sliding window is set to 0.
And S103, identifying effective fetal movement according to the energy envelope.
After the energy envelope detection is performed on the fetal movement signal, the fetal movement differential energy signal is calculated according to the energy envelope, the signal input state is judged according to the fetal movement differential energy signal, whether the fetal movement detection processing is performed or not is determined according to the signal input state judgment result, and effective fetal movement is identified.
Specifically, as shown in fig. 3, step 103 includes steps 301 to 303.
S301, calculating a differential energy signal for eliminating a baseline according to the energy envelope;
the weighted value of the mean value of the energy envelopes in the latest T2 time duration is used as a baseline, the energy envelopes and the baseline are subjected to differential operation, the parts smaller than or equal to zero in the differential operation result are set to be zero, the parts larger than zero in the differential operation result are reserved, namely, the parts smaller than or equal to the baseline in the energy envelopes are set to be zero, and the parts higher than the baseline are reserved after the baseline is subtracted, so that the differential energy signal with the baseline eliminated is obtained.
The baseline may be updated in real time over a time sliding window having a window length of duration T2. Illustratively, T2 may be set to 1s, 2s, or 0.5s (seconds), etc.
S302, if the total energy of the differential energy signal within a first preset time length is greater than a second preset threshold, judging whether the differential energy signal exceeds a third preset threshold;
and identifying whether the differential energy signal in the time channel is effectively changed or not according to whether the total energy of the differential energy signal in the first preset time duration exceeds a second preset threshold value Pre _ Thr2 or not, namely judging the signal input state. When the total energy of the differential energy signal in the first preset time length is greater than a second preset threshold value Pre _ Thr2, the differential energy signal in the time channel is considered to have effective change in the time, at the moment, whether the differential energy signal meets the condition of effective fetal movement is judged, namely whether the effective fetal movement is generated is identified; otherwise, the differential energy signal in the time channel is not considered to be effectively changed in the period of time, and at the moment, whether the differential energy signal exceeds a third preset threshold value or not does not need to be judged, namely whether effective fetal movement is generated or not does not need to be identified.
For example, the first preset time period may be 1 minute or 5 minutes, the second preset threshold Pre _ Thr2 is smaller than the first preset threshold Pre _ Thr1, and the second preset threshold Pre _ Thr2 may be 0.1. The probe may be empty or placed on the abdomen of the pregnant woman, the fetal movement signal acquired during the empty is definitely a null signal, if the fetal movement signal acquired by the probe is too small or has no fetal movement, the total energy of the first preset time period is smaller than the second preset threshold value Pre _ Thr 2. When the fetal movement occurs or the interference occurs, the signal is suddenly increased, the total energy of the first preset time period is greater than or equal to the second preset threshold value Pre _ Thr2, at the moment, the effective change is considered to occur, and whether the fetal movement or other interference exists is identified.
S303, if the third preset threshold is exceeded, the duration exceeding the third preset threshold is greater than or equal to a second preset duration, and the slope of the differential energy signal is subjected to forward mutation, the effective fetal movement is identified.
And under the condition that the total energy of the differential energy signal in the first preset time is greater than a second preset threshold, judging whether the differential energy signal meets the condition of effective fetal movement, namely identifying whether the effective fetal movement is generated. And identifying effective fetal movement by judging the duration of the differential energy signal exceeding a third preset threshold, judging whether the slope of the differential energy signal has forward mutation or not when the duration exceeds the third preset threshold and is greater than or equal to a second preset duration, and identifying effective fetal movement if the duration is greater than or equal to the second preset duration and the slope of the differential energy signal has forward mutation.
At this time, fetal movement attribute information for valid fetal movements may be obtained, including start and end times of the fetal movement, duration of a single fetal movement, and the like. The third preset threshold is a fetal movement threshold, and the threshold may be updated according to a mean value of the differential energy signal within a certain time duration, for example, the threshold and the mean value have a forward linear relationship, and the like.
In a fetal resting state, the differential energy signal is relatively gentle, when a fetus has slight fetal movement, although a pregnant woman cannot perceive the signal, a small peak value appears on the differential energy signal, when the peak value appears, the differential energy signals at two adjacent time points have positive abrupt change of slope, namely the slope is changed from zero to positive and the slope change is small; when the fetal movement intensity is larger, the peak value appearing on the fetal movement differential energy signal is more obvious, and when the signals at two adjacent time points generate positive sudden change of the slope, the slope change is more obvious.
Therefore, in the present embodiment, the differential energy signal is compared with a third preset threshold, that is, the fetal movement threshold, the start time Ts and the end time Te of the valid fetal movement are recorded, and the duration T of the valid fetal movement can be obtained by calculating the time difference between the start time Ts and the end time Te of the fetal movement.
Optionally, in order to avoid the influence of the signal error on the identification, the embodiment of the present invention further provides that when the differential energy signal is determined to exceed the third preset threshold for a plurality of consecutive times, for example, two to ten times, it is determined whether the condition of the valid fetal movement is satisfied, that is, it is determined whether the valid fetal movement is generated, until a certain degree of forward mutation occurs in the slope of the differential energy signals acquired in two adjacent times, it is determined that the fetal movement is possible, the current fetal movement value is used as a boundary value of the fetal movement start, the fetal movement start threshold THR _ s is obtained, the start time Ts of the fetal movement is recorded, and the magnitude of the slope change is converted into the fetal movement strength according to the preset mapping relationship, so as to obtain the fetal movement strength in the valid fetal movement process. The forward mutation of a certain degree can be a preset value, a default value or a user-defined setting.
When the possibility of fetal movement is detected, judging whether the fetal movement is finished or not according to a threshold value THR _ s when the fetal movement starts, when the fetal movement strength is lower than a threshold value THR _ s when the fetal movement lasts for T3 time, considering that the fetal movement is finished, recording the fetal movement finishing time Te, taking the time difference between the fetal movement starting time Ts and the fetal movement finishing time Te as the single fetal movement duration time T, if the single fetal movement duration time is smaller than a second preset time T4, considering the single fetal movement as invalid, and otherwise, considering the single fetal movement as valid. And S104, judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result.
Fetal activity is divided into intermittent activity and continuous activity, the existing clinic generally adopts a mode of identifying all valid fetal activity, and a plurality of intermittent fetal activities within a period of time are generally represented by a mark with very long duration, so that the intermittent fetal activity and the continuous fetal activity cannot be distinguished. Therefore, in the conventional fetal movement recognition, the number of fetal movements is usually very large, and the judgment of a clinician may be disturbed due to the excessive number of fetal movements.
Fig. 4 is a diagram illustrating an automatic fetal movement discontinuity marker mapping method in the prior art provided by the present application, wherein the uppermost curve P302 is a fetal heart rate curve, the lowermost black block P303 is a discontinuity marker of valid fetal movements identified by the automatic fetal movement, the black block starts to be drawn when the fetal movement starts and stops to be drawn when the fetal movement ends every time the fetal movement is identified by the automatic fetal movement algorithm, each black block represents a fetal movement, and the last AFM:75 in the first row in fig. 4 represents that 75 fetal movements are identified in total during the fetal heart monitoring period. It can be seen that a plurality of short-time fetal movements can occur within a very short time interval, each small fetal movement is counted independently by automatic fetal movement, so that the total number of fetal movements is very large, the judgment of medical staff is disturbed, the pregnant woman feels anxious, and the identification mode is not accurate enough.
Therefore, after the valid fetal movement is identified, the invention judges whether the valid fetal movement identified at the current time needs to be merged with the previous fetal movement. Therefore, a more accurate fetal movement identification result is provided for a user while the complete fetal movement information is kept.
Specifically, as shown in fig. 5, step 104 includes steps 501 to 502.
S501, obtaining fetal movement attribute information of the effective fetal movement, wherein the fetal movement attribute information at least comprises duration of the effective fetal movement and time interval between the duration of the effective fetal movement and the previous effective fetal movement.
The method comprises the steps of obtaining fetal movement attribute information of effective fetal movement when effective fetal movement identification is carried out, judging whether effective fetal movement is combined or not according to the fetal movement attribute information, combining the effective fetal movement with the identified last effective fetal movement when a certain combination condition is met, and taking the effective fetal movement as an independent fetal movement when the condition is not met.
Furthermore, in other embodiments of the present invention, the fetal movement attribute information includes a duration of an effective fetal movement, start and end times of an effective fetal movement, an intensity of an effective fetal movement, a time interval from a last effective fetal movement, and the like.
S502, if the time interval between the effective fetal movement and the previous effective fetal movement is less than a fourth preset time length within a third preset time length or the duration of the effective fetal movement is less than a fifth preset time length, combining the effective fetal movement and the previous effective fetal movement to be used as a combined fetal movement; otherwise, the effective fetal movement is taken as an independent fetal movement.
And the fourth preset time length and the fifth preset time length are both smaller than the third preset time length.
And judging whether the current effective fetal movement needs to be combined or not. Whether the two fetal movements belong to the same fetal movement or two independent fetal movements is judged mainly according to the current fetal movement duration and the time interval between two adjacent effective fetal movements.
During time T5, if the time interval between the next valid fetal movement and the last valid fetal movement is less than the preset time T6, or if the duration of the next valid fetal movement is less than the preset time T7, then it is considered that the activities of the next valid fetal movement and the last valid fetal movement are the same fetal movement are decomposed, and the fetal movements during the time T5 are merged into an independent fetal movement, otherwise, it is considered that the next valid fetal movement is an independent fetal movement. Illustratively, T5> T6> T7, T5 is 30s, T6 is 15s, and T7 is 2s (seconds), all of which are adjustable parameters.
Optionally, in other embodiments of the present invention, a ratio of the fetal movement intensity to the fetal movement duration may also be used to calculate an average intensity of each valid fetal movement, and then determine whether to perform fetal movement combination according to the average intensity of the fetal movement, for example, when the average intensity of the fetal movement is smaller than a preset threshold, it is determined that the valid fetal movement needs to be combined with the valid fetal movement identified last time.
It should be noted that, if it is determined that the current valid fetal movement needs to be merged with the previous valid fetal movement, if the previous valid fetal movement is also merged with the previous valid fetal movement, the current valid fetal movement is merged with the previous valid fetal movement twice, and the process is repeated as a merged fetal movement.
On the basis of the embodiment shown in fig. 1, after obtaining the fetal movement recognition result in step 104, the method further includes:
marking the identified combined fetal movement and the independent fetal movement, and counting the identified combined fetal movement and the independent fetal movement statistically.
Wherein the identified independent fetal movements and the combined fetal movement are marked. If the next valid fetal movement is an independent fetal movement, the current fetal movement is directly marked, otherwise, the fetal movement with the strongest average fetal movement strength is marked in the T5 time. And regarding that the duration time of the single effective fetal movement is longer than the preset time T7, regarding the current fetal movement as a continuous long fetal movement, namely an independent fetal movement, and marking and prompting at the fetal movement.
For example, in the planar space of the fetal heart rate curve and the automatic fetal movement image, a visual identifier is displayed where the fetal movement marker needs to be added. The identifier is not limited to be drawn at a position, and can be above the fetal heart rate curve or below the fetal heart rate curve, and can be in a drawing area of the automatic fetal movement image. The identifier may be in any shape, may be a static graphic, may be an animation, may be an audio prompt, or the like.
Fig. 6 shows one of the automatic fetal movement combination marker mapping manners provided by the present application, in which the uppermost curve P401 is a fetal heart rate curve, the lowermost curve P402 is an automatic fetal movement curve drawn by a continuous mapping manner, each lift in the automatic fetal movement curve represents a fetal heart, it can be seen that a plurality of short-term fetal movements may occur in a very short time interval, after combining the fetal movements, the combined fetal movement position is marked by an automatic fetal movement combination marker P403 at the intermediate position between the fetal heart rate curve and the automatic fetal movement curve, in this embodiment, an upward arrow is used as the automatic fetal movement combination marker, and other shapes of graphics, animations, sounds, and the like may also be used as the automatic fetal movement combination marker.
Each time a merged fetal movement or an independent fetal movement is identified, the fetal movement counter is incremented by 1.
Fig. 7 shows a schematic structural diagram of a fetal movement identification device provided by an embodiment of the invention, which includes the following modules:
an obtaining module 71, configured to obtain a fetal movement signal;
an extraction module 72 for extracting an energy envelope of the fetal movement signal;
a first identification module 73 for identifying valid fetal movements from the energy envelope;
and a second identification module 74, configured to determine whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements, so as to obtain a fetal movement identification result.
It should be noted that, for convenience and brevity of description, the specific working process of the apparatus 70 described above may refer to the corresponding process of the method described in fig. 1, and will not be described in detail herein.
Fig. 8 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 8, the terminal device 8 of this embodiment includes: a processor 80, a memory 81 and a computer program 82, such as a program for fetal activity recognition, stored in said memory 81 and executable on said processor 80. The processor 80, when executing the computer program 82, implements the steps in the above-described method embodiment of fetal activity identification, such as steps S101 to S104 shown in fig. 1. Alternatively, the processor 80, when executing the computer program 82, implements the functions of the modules/units in the above-described device embodiments, such as the functions of the modules 71 to 74 shown in fig. 7.
Illustratively, the computer program 82 may be partitioned into one or more modules/units that are stored in the memory 81 and executed by the processor 80 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 82 in the terminal device 8.
The terminal device 8 may be a fetal monitor, such as a fetal heart monitor. The terminal device 8 may include, but is not limited to, a processor 80 and a memory 81. It will be appreciated by those skilled in the art that fig. 8 is merely an example of a terminal device 8 and does not constitute a limitation of terminal device 8 and may include more or fewer components than shown, or some components in combination, or different components, for example the terminal device may also include input and output devices such as a monitoring probe, a network access device, a bus, etc.
The Processor 80 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 81 may be an internal storage unit of the terminal device 8, such as a hard disk or a memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 8. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal device 8. The memory 81 is used for storing the computer program and other programs and data required by the terminal device. The memory 81 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (9)
1. A method of fetal activity identification, comprising:
acquiring a fetal movement signal;
extracting an energy envelope of the fetal movement signal;
identifying valid fetal movements from the energy envelope;
judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result;
said identifying valid fetal movement from said energy envelope comprises:
calculating a baseline-eliminated differential energy signal according to the energy envelope;
if the total energy of the differential energy signal within a first preset time length is greater than a second preset threshold, judging whether the differential energy signal exceeds a third preset threshold;
if the slope of the differential energy signal is subjected to forward mutation when the third preset threshold is exceeded and the duration exceeding the third preset threshold is greater than or equal to a second preset duration, effective fetal movement is identified.
2. The method of claim 1, wherein said extracting an energy envelope of said fetal movement signal comprises:
performing full-wave rectification on the fetal movement signal to obtain a full-wave rectification signal;
carrying out normalization processing on the full-wave rectification signal to obtain a normalized signal;
calculating the normalized average shannon energy of each sliding window corresponding to the normalized signal;
judging whether the normalized average shannon energy of each sliding window is greater than or equal to a first preset threshold value or not;
if the normalized average shannon energy of the sliding window is greater than or equal to the first preset threshold value, taking the normalized average shannon energy as the fetal movement intensity of the sliding window;
and if the normalized average shannon energy of the sliding window is smaller than the first preset threshold value, setting the fetal movement intensity of the sliding window to be zero.
3. The method according to claim 1 or 2, wherein the determining whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement recognition result comprises:
acquiring fetal movement attribute information of the effective fetal movement, wherein the fetal movement attribute information at least comprises the duration of the effective fetal movement and the time interval between the effective fetal movement and the previous effective fetal movement;
if the time interval between the effective fetal movement and the previous effective fetal movement is less than a fourth preset time length or the duration of the effective fetal movement is less than a fifth preset time length within a third preset time length, combining the effective fetal movement and the previous effective fetal movement to be used as a combined fetal movement; otherwise, the effective fetal movement is taken as an independent fetal movement.
4. The method of claim 3, wherein after obtaining the fetal activity recognition result, further comprising:
marking the identified combined fetal movement and the independent fetal movement, and counting the identified combined fetal movement and the independent fetal movement statistically.
5. The method of claim 4, wherein said marking the identified merged fetal movement and the independent fetal movement comprises:
marking the identified combined fetal movement at a valid fetal movement with the maximum average intensity included in the combined fetal movement;
marking the identified independent fetal movement at the independent fetal movement.
6. An apparatus for fetal activity identification, comprising:
the acquisition module is used for acquiring fetal movement signals;
the extraction module is used for extracting the energy envelope of the fetal movement signal;
a first identification module for identifying valid fetal movements from the energy envelope;
the second identification module is used for judging whether to merge the effective fetal movements according to the fetal movement attribute information of the effective fetal movements to obtain a fetal movement identification result;
the first identification module is specifically configured to:
calculating a baseline-eliminated differential energy signal according to the energy envelope;
if the total energy of the differential energy signal within a first preset time length is greater than a second preset threshold, judging whether the differential energy signal exceeds a third preset threshold;
if the slope of the differential energy signal is subjected to forward mutation when the third preset threshold is exceeded and the duration exceeding the third preset threshold is greater than or equal to a second preset duration, effective fetal movement is identified.
7. The apparatus of claim 6, wherein the second identification module is specifically configured to:
acquiring fetal movement attribute information of the effective fetal movement, wherein the fetal movement attribute information at least comprises the duration of the effective fetal movement and the time interval between the effective fetal movement and the last effective fetal movement;
if the time interval between two adjacent effective fetal movements is less than a fourth preset time length within a third preset time length, or the duration of a single effective fetal movement is less than a fifth preset time length, combining the effective fetal movements within the third preset time length to serve as a primary combined fetal movement; otherwise, taking each effective fetal movement in the third preset time length as an independent fetal movement.
8. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when executing the computer program.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811300989.2A CN109589137B (en) | 2018-11-02 | 2018-11-02 | Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811300989.2A CN109589137B (en) | 2018-11-02 | 2018-11-02 | Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109589137A CN109589137A (en) | 2019-04-09 |
| CN109589137B true CN109589137B (en) | 2021-10-22 |
Family
ID=65958202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811300989.2A Active CN109589137B (en) | 2018-11-02 | 2018-11-02 | Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109589137B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110236594B (en) * | 2019-05-30 | 2022-06-07 | 暨南大学 | Fetal movement signal identification marking method, system, medium and equipment |
| CN115177245B (en) * | 2021-04-02 | 2024-05-03 | 深圳市理邦精密仪器股份有限公司 | Blood oxygen detection method, fetal heart monitoring device and computer readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1989009027A1 (en) * | 1988-03-22 | 1989-10-05 | Air-Shields, Inc. | Fetal heart rate counting system |
| CN102090883A (en) * | 2010-12-30 | 2011-06-15 | 深圳市理邦精密仪器股份有限公司 | Automatic identification method and device for fetal movement |
| CN102940485A (en) * | 2012-10-10 | 2013-02-27 | 广州三瑞医疗器械有限公司 | Algorithm for automatically recognizing fetal heart rate baseline |
| CN104546007A (en) * | 2015-01-29 | 2015-04-29 | 深圳市理邦精密仪器股份有限公司 | Anti-interference processing method and device for fetal movement detection |
| CN104586434A (en) * | 2015-01-16 | 2015-05-06 | 深圳市理邦精密仪器股份有限公司 | Method and device for improving fetal heart Doppler signal acquisition quality during fetal movement |
| CN104622440A (en) * | 2015-02-09 | 2015-05-20 | 中国科学院深圳先进技术研究院 | Punctuating method and device in pulse wave extraction |
| CN108056773A (en) * | 2017-12-11 | 2018-05-22 | 重庆邮电大学 | Based on the algorithms of QRS complexes detection in electrocardiogram signal for improving variation mode decomposition |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008073491A1 (en) * | 2006-12-11 | 2008-06-19 | University Of Florida Research Foundation, Inc. | System and method for analyzing progress of labor and preterm labor |
| CN103565433B (en) * | 2013-10-30 | 2015-02-25 | 深圳市理邦精密仪器股份有限公司 | Method and device for improving fetal monitoring efficiency |
| CN104367344A (en) * | 2014-10-10 | 2015-02-25 | 广东工业大学 | Method and device for detecting instant heart rate of fetus on basis of Shanon envelope |
| CN105640545B (en) * | 2015-12-31 | 2018-12-14 | 深圳先进技术研究院 | Fetal electrocardiosignal extraction method and device |
-
2018
- 2018-11-02 CN CN201811300989.2A patent/CN109589137B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1989009027A1 (en) * | 1988-03-22 | 1989-10-05 | Air-Shields, Inc. | Fetal heart rate counting system |
| CN102090883A (en) * | 2010-12-30 | 2011-06-15 | 深圳市理邦精密仪器股份有限公司 | Automatic identification method and device for fetal movement |
| CN102940485A (en) * | 2012-10-10 | 2013-02-27 | 广州三瑞医疗器械有限公司 | Algorithm for automatically recognizing fetal heart rate baseline |
| CN104586434A (en) * | 2015-01-16 | 2015-05-06 | 深圳市理邦精密仪器股份有限公司 | Method and device for improving fetal heart Doppler signal acquisition quality during fetal movement |
| CN104546007A (en) * | 2015-01-29 | 2015-04-29 | 深圳市理邦精密仪器股份有限公司 | Anti-interference processing method and device for fetal movement detection |
| CN104622440A (en) * | 2015-02-09 | 2015-05-20 | 中国科学院深圳先进技术研究院 | Punctuating method and device in pulse wave extraction |
| CN108056773A (en) * | 2017-12-11 | 2018-05-22 | 重庆邮电大学 | Based on the algorithms of QRS complexes detection in electrocardiogram signal for improving variation mode decomposition |
Non-Patent Citations (3)
| Title |
|---|
| Methods of fetal movement counting and the detection of fetal compromise;A.E.P.HEAZELL,et al;《Journal of Obstetrics and Gynaecology》;20090102;第28卷(第2期);第147-153页 * |
| Real-time processing of ultrasonic Doppler signals of fetal activity;K.Kaluzynski,et al;《Technical note》;19941130(第32期);第686-688页 * |
| 基于体表心音的左心室血压预测方法研究;张晶慧，唐洪;《生物医学工程杂志》;20170630;第34卷(第3期);第336-338页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109589137A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8764686B2 (en) | Fetal movement information processing device and fetal movement information processing method | |
| US20220110532A1 (en) | Fluid Loss Estimation of Medical Items | |
| US5442940A (en) | Apparatus and method for evaluating the fetal condition | |
| US9801609B2 (en) | Device and method for enhancing accuracy of recognizing fetus heart rate acceleration data | |
| JP5271718B2 (en) | How to identify fetal and maternal ECGs across multiple time segments | |
| CN107518920B (en) | Ultrasonic image processing method and apparatus, ultrasonic diagnostic apparatus, and storage medium | |
| US20170238909A1 (en) | Method and apparatus for video interpretation of carotid intima-media thickness | |
| CN109589137B (en) | Fetal movement identification method, fetal movement identification device, terminal and computer-readable storage medium | |
| CN110613480A (en) | Fetus ultrasonic dynamic image detection method and system based on deep learning | |
| WO2018171202A1 (en) | Method and device for automatic positioning of indwelling needle in punctured vein | |
| CN106923820B (en) | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device | |
| US20190387979A1 (en) | Blood pressure measurement apparatus, method, and program | |
| CN103565426A (en) | Information processing apparatus, program, and biosignal measurement set | |
| CN112494031A (en) | Respiration rate calculation method and device | |
| CN111956193A (en) | Health state detection method, device, medium and equipment applied to intelligent earphone | |
| CN104586379B (en) | Method and device for outputting parameters of fetal heart rate curve | |
| CN109567869B (en) | Method and system for processing accelerated activities on fetal heart rate curve | |
| CN112750099A (en) | Follicle measurement method, ultrasound apparatus, and computer-readable storage medium | |
| CN110236594B (en) | Fetal movement signal identification marking method, system, medium and equipment | |
| WO2020103098A1 (en) | Ultrasonic imaging method and apparatus, storage medium, processor and computer device | |
| CN112716525B (en) | Fetal heart rate processing method and device and readable storage medium | |
| CN109567867A (en) | A kind of processing method of Fetal Heart Rate amplitude-variation | |
| CN112971753B (en) | Fetal heart rate deceleration type identification method and device and fetal monitoring equipment | |
| CN114271799B (en) | Cardiovascular detection method based on intelligent terminal | |
| CN114366082B (en) | Non-invasive fetal movement signal acquisition and processing method, system, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |