CN111938704B - Bladder volume detection method and device and electronic equipment - Google Patents
Bladder volume detection method and device and electronic equipment Download PDFInfo
- Publication number
- CN111938704B CN111938704B CN202010827115.3A CN202010827115A CN111938704B CN 111938704 B CN111938704 B CN 111938704B CN 202010827115 A CN202010827115 A CN 202010827115A CN 111938704 B CN111938704 B CN 111938704B
- Authority
- CN
- China
- Prior art keywords
- bladder
- groups
- echo data
- data
- ultrasonic
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 83
- 238000003062 neural network model Methods 0.000 claims abstract description 49
- 230000000241 respiratory effect Effects 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 93
- 230000015654 memory Effects 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 10
- 230000027939 micturition Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims 2
- 230000029058 respiratory gaseous exchange Effects 0.000 abstract description 33
- 230000005540 biological transmission Effects 0.000 description 26
- 238000002604 ultrasonography Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 4
- 230000001052 transient effect Effects 0.000 description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 206010046543 Urinary incontinence Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004007 neuromodulation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000001991 pathophysiological effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000001635 urinary tract Anatomy 0.000 description 1
- 230000003202 urodynamic effect Effects 0.000 description 1
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
- A61B8/0833—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Radiology & Medical Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to the technical field of bladder detection, in particular to a bladder volume detection method and device and electronic equipment. The method comprises the following steps: detecting respiratory characteristics of a detected user, and determining a respiratory period of the user based on the respiratory characteristics; transmitting N ultrasonic signals to the user's bladder during one respiratory cycle; n is an integer greater than or equal to 1; receiving N groups of ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder wall for N times; based on N groups of ultrasonic echo data, calculating to obtain the volume value of the bladder by utilizing a neural network model obtained through pre-training. According to the bladder volume detection method provided by the invention, ultrasonic signals are emitted in a respiratory cycle, ultrasonic echo data are received, and the influence of respiration on a detection result is eliminated; and analyzing the relation between the ultrasonic echo data with large data volume by utilizing the neural network model obtained by pre-training so as to calculate and obtain the bladder volume value, and the bladder volume value is not influenced by single data, so that the detection accuracy is further improved.
Description
Technical Field
The invention relates to the technical field of bladder detection, in particular to a bladder volume detection method and device and electronic equipment.
Background
As one of common clinical symptoms of urodynamics, the attention of the whole society to the urology is increasingly improved in recent years along with the improvement of the living standard of people, and the epidemic pathology survey in partial areas of China shows that the incidence rate of the urology is 5.9% for people over 18 years old, 1.1% for people over 18-40 years old, 10% for people over 40 years old and even 70% for old women, and the urology not only causes anxiety and embarrassment to patients, but also seriously affects the work and life of the patients. However, increasing attention to urinary incontinence has prompted a more thorough understanding of its epidemiological features, pathophysiological features, and peripheral and central neuromodulation mechanisms of the small urinary tract, which has helped develop new diagnostic devices.
In the propagation process of the biological medium, the ultrasonic signal and the biological medium can interact, and the disease focus of a patient is diagnosed by researching the characteristics and the mechanism of the interaction between the ultrasonic signal and the biological medium and utilizing the corresponding characteristics and the mechanism. Currently, for bladder volume detection, an ultrasonic imaging method is mostly used to obtain an entire ultrasonic image of a bladder, for example, chinese patent CN104546000a, and a method and a device for measuring bladder volume based on an ultrasonic image with shape features disclose: acquiring a two-dimensional bladder ultrasonic image; identifying the shape of the bladder according to the two-dimensional bladder ultrasonic image; the volume of the bladder is measured according to the shape of the bladder. The method needs to acquire the complete ultrasonic two-dimensional image of the bladder, and has large calculation amount and high system requirement.
In addition, the inventor found that in the existing bladder volume detection technology, a plurality of ultrasonic devices are adopted to detect, the mode needs to be performed under the prior condition that the relative positions and angles among the ultrasonic devices are known, and when a detected object moves or breathes, the positions and angles of the ultrasonic devices may change, so that the detection result of the bladder volume is inaccurate.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a bladder volume detection method, a device and an electronic device, which are used for solving the problem that in the prior art, the bladder volume detection is easily affected by the respiration of a detected object, so that the detection result is inaccurate.
According to a first aspect, an embodiment of the present invention provides a bladder volume detection method, including: detecting a respiratory feature of a user under test, determining a respiratory cycle of the user based on the respiratory feature; transmitting N ultrasonic signals to the user's bladder during one of the respiratory cycles; n is an integer greater than or equal to 1; receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall; and calculating the volume value of the bladder by utilizing a neural network model obtained by pre-training based on the N groups of ultrasonic echo data.
According to the bladder volume detection method provided by the embodiment of the invention, in the breathing cycle of a user, the ultrasonic signals are transmitted, and the ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder wall is received, so that the influence of breathing on the detection result can be eliminated; on the other hand, the relation between the ultrasonic echo data with large data volume is analyzed through the neural network model obtained through pre-training, so that the volume value of the bladder is calculated, the influence of single data is avoided, and the detection accuracy is further improved.
Optionally, the calculating, based on the N sets of ultrasonic echo data, the volume value of the bladder by using a neural network model obtained by training in advance includes: carrying out data reconstruction on the N groups of ultrasonic echo data to obtain M groups of matrix data, wherein each group of matrix data comprises N groups of ultrasonic echo data, N is less than or equal to N, and each group of ultrasonic echo data comprises a bladder front wall distance value and a bladder back wall distance value; calculating to obtain M groups of front and rear wall difference matrixes by using the bladder front wall distance values and the bladder rear wall distance values in the M groups of matrix data, wherein each element in the front and rear wall difference matrixes represents the measured front and rear wall distance difference of the bladder; and inputting M groups of front and rear wall difference matrixes into the neural network model to calculate the volume value of the bladder.
According to the bladder volume detection method provided by the embodiment of the invention, the N groups of ultrasonic echo data are subjected to data reconstruction to obtain the M groups of matrix data, so that larger and denser data volume is provided for the subsequent neural network model calculation, the calculation accuracy is ensured, the emission times of ultrasonic signals are reduced, and the detection efficiency is improved; by means of data reconstruction, the influence of external interference factors with high-frequency information on the ultrasonic echo data can be overcome, and detection accuracy is further improved.
Optionally, inputting M sets of the anterior-posterior wall difference matrices into the neural network model to calculate the volumetric value of the bladder, including: inputting M groups of anterior and posterior wall difference matrixes into the neural network model, and outputting a bladder longitudinal incision profile; calculating the longitudinal contour area of the bladder by utilizing the bladder longitudinal contour; and calculating the volume value of the bladder through an ellipsoidal volume calculation formula based on the longitudinal contour area.
Optionally, the calculating by using the distance value of the front wall of the bladder and the distance value of the rear wall of the bladder in the M groups of matrix data obtains M groups of front and rear wall difference matrices, including: acquiring a distance threshold of the front wall and the rear wall of the bladder; for M groups of matrix data, establishing a front wall matrix according to the bladder wall distance value smaller than the distance threshold value in each group of matrix data, and establishing a rear wall matrix according to the bladder wall distance value larger than or equal to the distance threshold value, so as to obtain M groups of front wall matrices and M groups of rear wall matrices corresponding to the M groups of front wall matrices one by one; and respectively differencing each element in the back wall matrix and the corresponding front wall matrix to obtain M groups of front and back wall difference matrices by calculation.
Optionally, said transmitting N ultrasonic signals to the bladder of said user during one of said respiratory cycles comprises: and triggering each transducer one by one according to an interval period in one respiratory period, and transmitting ultrasonic signals to the bladder of the user, wherein the number of the transducers is N, and the number of times of triggering the transducers is N.
According to the bladder volume detection method provided by the embodiment of the invention, each transducer is triggered successively in one respiratory cycle to emit ultrasonic signals to the bladder, so that the problem of crosstalk between ultrasonic signals can be avoided, and meanwhile, compared with the bladder volume detection technology in the prior art, data in one respiratory cycle are acquired, transient errors, such as transient changes of the position and angle of an ultrasonic device caused by movement or respiration, are reduced, and the detection accuracy is affected.
Optionally, the reconstructing the data of the N sets of ultrasonic echo data to obtain M sets of matrix data includes: and selecting N groups of ultrasonic echo data which are continuous in time from the N groups of ultrasonic echo data each time to form a group of matrix data, wherein the selection times are M, and at least one group of ultrasonic echo data in each group of matrix data is different.
According to the bladder volume detection method provided by the embodiment of the invention, through data reconstruction, the frame frequency of ultrasonic echo data is improved, denser and larger data volume can be obtained, the ultrasonic echo data is fully utilized, the transmission times of ultrasonic signals are reduced, the cost is reduced, the influence of external factors is overcome, and the detection accuracy is improved.
Alternatively, the interval period may be calculated by the following formula:
T＝2*D/C s ；
wherein T represents the interval period, D represents the detection depth, C s Representing the speed of sound of the ultrasonic signal.
Optionally, the bladder volume detection method further comprises: and sending a urination early warning signal according to the volume value of the bladder.
According to a second aspect, an embodiment of the present invention provides a bladder volume detection device, comprising: the breath detection module is used for detecting the breath characteristics of a tested user and determining the breath period of the user based on the breath characteristics; an ultrasonic wave transmitting module for transmitting an ultrasonic wave signal to the bladder of the user N times in one of the respiratory cycles; n is an integer greater than or equal to 1; the ultrasonic echo data receiving module is used for receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall; and the calculation module is used for calculating the volume value of the bladder by utilizing a neural network model obtained by pre-training based on the N groups of ultrasonic echo data.
According to the bladder volume detection device provided by the embodiment of the invention, the ultrasonic signals are emitted in the breathing cycle of the user, and the ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder wall is received, so that the influence of breathing on the detection result can be eliminated; on the other hand, the relation between the ultrasonic echo data with large data volume is analyzed through the neural network model obtained through pre-training, so that the volume value of the bladder is calculated, the influence of single data is avoided, and the detection accuracy is further improved.
According to a third aspect, an embodiment of the present invention provides an electronic device, including: the bladder volume detection device comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, so as to execute the bladder volume detection method according to the first aspect or any implementation mode of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, wherein the computer readable storage medium stores computer instructions for causing the computer to perform the bladder volume detection method according to the first aspect or any one of the embodiments of the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic illustration of an application scenario of the present invention;
FIG. 2 is a flow chart of a bladder volume detection method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the composition structure of a neural network model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a training method of a neural network model according to an embodiment of the present invention;
FIG. 5 is a complete flow chart of a bladder volume detection method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of data reconstruction according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an input matrix after data reconstruction according to an embodiment of the present invention;
FIG. 8A is a schematic diagram of a front wall matrix of an embodiment of the present invention;
FIG. 8B is a schematic diagram of a back wall matrix of an embodiment of the present invention;
FIG. 8C is a schematic diagram of a front and back wall difference matrix according to an embodiment of the present invention;
FIG. 9 is a schematic diagram showing the structure of a bladder volume detecting apparatus according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention;
FIG. 11 is a schematic illustration of a training method for a neural network model for fitting a longitudinal bladder contour, in accordance with an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
An embodiment of the present invention provides a bladder volume detection method, which can be used in the bladder volume detection system shown in fig. 1, where the bladder volume detection system includes a gating module 10, an ultrasonic transmitting module 20, an ultrasonic receiving module 30, and an electronic device 40, and the electronic device 40 includes a memory 41 and a processor 42. The gating module 10 is connected with the transducer, the ultrasonic transmitting module 20 and the ultrasonic receiving module 30, and controls the transducer to transmit ultrasonic signals in a channel gating manner, wherein the ultrasonic transmitting module 20 is used for providing excitation signals required for transmitting the ultrasonic signals, and the ultrasonic receiving module 30 is used for receiving ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder of the user. The memory 41 is used for storing the ultrasonic echo data, and the processor 42 is used for performing analysis and calculation on the ultrasonic echo data to obtain a volume value of the bladder of the user. The electronic device 40 is also connected to the gating module 10,
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein. As shown in fig. 2, the process includes the steps of:
s11, detecting the breathing characteristics of a detected user, and determining the breathing period of the user based on the breathing characteristics.
Here, the electronic device 40 may be connected to a breath detection device. After the breath detection device detects the breath characteristics of the user, the breath detection result is sent to the electronic device 40, and the electronic device 40 determines the breath period of the user according to the breath detection result. Alternatively, electronic device 40 may directly acquire the respiratory characteristics of the user, such as the time of expiration and inspiration, to determine the respiratory cycle. The breathing characteristics of the user acquired by the electronic device 40 may also be stored in the electronic device 40; the breathing characteristics of the user can be obtained through an external input mode; still alternatively, the electronic device 40 obtains the user's breathing characteristics, etc., by other means. Regardless of the manner in which the electronic device 40 obtains the user's breathing characteristics, it is only necessary to ensure that the electronic device 40 is able to obtain the user's breathing characteristics. In addition, the electronic device 40 may directly obtain the breathing cycle of the user, which is not limited by the present invention.
The breathing detection device can be a strain sensor, and can detect the breathing cycle of the user by periodically deforming a breathing tube and a chest and abdomen along with the periodic transformation of expiration and inspiration when the user breathes or moves; the respiration detection device can also be an electrocardiograph monitor, and the electrocardiograph is used for converting and processing signals to obtain the respiration characteristics of the user, namely the time of expiration and inspiration, and further obtain the respiration period of the user. The detection of the respiratory characteristics of the user and the determination of the respiratory cycle may also be implemented in other ways, as the invention is not limited in this regard.
S12, transmitting N ultrasonic signals to the bladder of the user in one respiratory cycle. N is an integer greater than or equal to 1.
When the electronic device 40 is connected with a breath detection device, the breath detection device detects the start time of the user's breath cycle, i.e. the expiration start time or inspiration start time, and controls the operation of the transducer by sending a detection start signal to the gating module 10. When one of the user's breathing cycles ends, the electronic device 40 stops the transducer operation by controlling the gating module 10. Here, the end time of one breathing cycle of the user may be determined by means of a timer.
The number of transducers may include a plurality, each connected to the channel gating module 10, which successively controls the plurality of transducers to transmit N ultrasonic signals to the user's bladder in a gating manner. Alternatively, the number of transducers may be one, and N ultrasonic signals are sequentially transmitted to the user's bladder through the gating module 10.
S13, receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall.
The N sets of ultrasonic echo data received by the electronic device 40 may be the N sets of ultrasonic echo data received in one-to-one correspondence with the N ultrasonic signals during real-time detection, or may be stored in the electronic device 40 in advance, or may be received by the electronic device 40 through other external manners, or the like. No matter how the electronic device 40 receives the N sets of ultrasonic echo data formed by the N ultrasonic signals reflected by the bladder wall, it is only necessary to ensure that the electronic device 40 can receive the N sets of ultrasonic echo data formed by the N ultrasonic signals reflected by the bladder wall.
Here, in order to avoid the problem of crosstalk between the N sets of ultrasonic echo data, the ultrasonic receiving module 30 is controlled successively to receive the N sets of ultrasonic echo data in a gating manner by the gating module 10.
And S14, calculating the volume value of the bladder by using a neural network model obtained by pre-training based on the N groups of ultrasonic echo data.
Here, the N sets of ultrasonic echo data correspond to the N ultrasonic signals, and the electronic device 40 may sequentially perform denoising, smoothing, and other processes on the N sets of ultrasonic echo data, and then convert the processed N sets of ultrasonic echo data into a spatial distance, where a specific conversion formula is: distance = propagation time difference of ultrasound echo data x ultrasound wave speed 2. And finally, determining the depth information of the front wall and the depth information of the back wall of the bladder of the N groups of users according to the difference of the distance values after the conversion of the N groups of ultrasonic echo data, and fitting out N groups of three-dimensional depth information of the bladder by combining the depth information of the front wall and the depth information of the back wall of the bladder with the time scale of the N groups of ultrasonic echo data. And inputting the N groups of three-dimensional depth information into the neural network model obtained by training in advance, and calculating to obtain the volume value of the bladder.
Further, as shown in fig. 3, the neural network model includes two fully connected layers FC,60 and FC with the number of neurons being 60 and 5, respectively, 5, a joint layer (concatate layer), SENet (Squeeze-and-Excitation Networks, abbreviated as SENet), a global average pooling layer (Global Average Pooling layers), and a fully connected layer FC with the number of neurons being 1, 1.
The N groups of three-dimensional depth information of the bladder respectively pass through the FC,60 and FC,5 and then become 1 multiplied by 5 vectors; then, outputting an Nx 5 feature matrix after superposition of the Concate layers, screening the Nx 5 feature matrix by using the SENet, and generating weight and bias for each feature channel; combining the characteristic channels through the Global Average Pooling layer, wherein the output tensor is 5; finally, the volume value of the bladder is output through the FC, 1.
According to the bladder volume detection method provided by the embodiment of the invention, in the breathing cycle of a user, the ultrasonic signals are transmitted, and the ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder wall is received, so that the influence of breathing on the detection result can be eliminated; on the other hand, the relation between the ultrasonic echo data with large data volume is analyzed through the neural network model obtained through pre-training, so that the volume value of the bladder is calculated, the influence of single data is avoided, and the detection accuracy is further improved.
Optionally, as shown in fig. 4, the training method of the neural network model may include the following steps:
s101, acquiring three-dimensional depth information of X groups of bladders, and correspondingly marking real volume values corresponding to the three-dimensional depth information of the X groups of bladders to obtain a sample set;
S102, filtering, smoothing, normalizing and the like are carried out on the sample set, so that a training set is obtained, and the training set is input into the FC,60 of the neural network model;
s103, training the neural network model by adopting an Adam algorithm; wherein Adam parameters are set as: learning rate lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=le-0.8;
s104, obtaining an output value of the FC, 1;
s105, calculating the deviation between the output value of the FC,1 and the real volume value, and if the deviation meets the preset error requirement, ending training; if not, correcting the weight and the bias, and returning to the step S103 to continue training.
Fig. 5 is a complete flowchart of a bladder volume detection method according to an embodiment of the present invention, as shown in fig. 5, the method includes the following steps:
s21, detecting the breathing characteristics of the tested user, and determining the breathing period of the user based on the breathing characteristics. Please refer to S11 in fig. 2, which is not described herein.
S22, transmitting N ultrasonic signals to the bladder of the user in one respiratory cycle; n is an integer greater than or equal to 1. Please refer to S12 in fig. 2, and details are not described herein.
As an alternative implementation of the embodiment of the present invention, the S22 may include: and triggering each transducer one by one according to an interval period in one respiratory period, and transmitting ultrasonic signals to the bladder of the user, wherein the number of the transducers is N, and the number of times of triggering the transducers is N.
Taking the n= 5,N =10 as an example, the breathing cycle is 5 seconds. Upon detection of the start of expiration or inspiration, the gating module 10 starts to transmit ultrasonic signals to the user's bladder with successive control of the 5 transducers at intervals of t=0.4 ms (milliseconds), while the timer starts to count for 5 seconds, the total number of transmissions being 10 within these 5 seconds. Here, the ultrasonic signals may be sequentially transmitted at 1 cycle by the 5 transducers, each of the transducers performing 2 transmissions; when there is only one transducer, 10 transmissions are performed by it; when there are 10 transducers, each transducer performs 1 transmission, and so on.
According to the bladder volume detection method provided by the embodiment of the invention, each transducer is triggered successively in one respiratory cycle to emit ultrasonic signals to the bladder, so that the problem of crosstalk between ultrasonic signals can be avoided, and meanwhile, compared with the bladder volume detection technology in the prior art, data in one respiratory cycle are acquired, transient errors, such as transient changes of the position and angle of an ultrasonic device caused by movement or respiration, are reduced, and the detection accuracy is affected.
Alternatively, the interval period may be calculated by the following formula:
T＝2*D/C s ；
wherein T represents the interval period, D represents the detection depth, C s Representing the speed of sound of the ultrasonic signal.
Specifically, at the detection depth d=30 cm (centimeter), the sound velocity C of the ultrasonic signal s For example, =1540m/s, the interval period T is approximately equal to 0.4ms (milliseconds) by the above formula.
S23, receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall. Please refer to S13 in fig. 2, and details are not described herein.
And S24, calculating the volume value of the bladder by using a neural network model obtained by pre-training based on the N groups of ultrasonic echo data. Please refer to S14 in fig. 2, and details are not described herein.
As an alternative implementation manner of the embodiment of the present invention, the S24 includes:
s241, carrying out data reconstruction on the N groups of ultrasonic echo data to obtain M groups of matrix data. Each set of matrix data includes N sets of ultrasound echo data, N being less than or equal to N, each set of ultrasound echo data including a bladder anterior wall distance value and a bladder posterior wall distance value.
Taking a total of 10 transmissions with 5 transducers, 10 sets of ultrasound echo data are obtained as an example. The data reconstruction may be: the ultrasonic echo data transmitted in the first transmission cycle, namely the first to the fifth transmission are taken as a first group of matrix data, the ultrasonic echo data transmitted in the second transmission cycle, namely the sixth to the tenth transmission are taken as a second group of matrix data, and 5 groups of ultrasonic echo data are included in each group of matrix data. Taking 1 transducer as an example, 10 transmissions are performed equally, resulting in 10 sets of ultrasound echo data. The data reconstruction may be: and taking the ultrasonic echo data obtained by each transmission as a group of matrix data, namely, each group of matrix data comprises 1 group of ultrasonic echo data.
Because the front and back walls of the bladder have a certain thickness, the transducer emits an ultrasonic signal once to obtain 4 potential values of the bladder wall, namely, when the ultrasonic signal propagates in the bladder, the ultrasonic signal encounters the front wall of the bladder and is reflected twice to obtain 2 potential values of the front wall of the bladder, and the back wall of the bladder is the same. The bladder anterior wall distance value and the bladder posterior wall distance value can be obtained by performing simple mathematical calculation on the 2 bladder anterior wall potential values and the 2 bladder posterior wall potential values.
According to the bladder volume detection method provided by the embodiment of the invention, the N groups of ultrasonic echo data are subjected to data reconstruction to obtain the M groups of matrix data, so that larger and denser data volume is provided for the subsequent neural network model calculation, the calculation accuracy is ensured, the emission times of ultrasonic signals are reduced, and the detection efficiency is improved; by means of data reconstruction, the influence of external interference factors with high-frequency information on the ultrasonic echo data can be overcome, and detection accuracy is further improved.
As an alternative implementation of the embodiment of the present invention, the S241 may include:
and selecting N groups of ultrasonic echo data which are continuous in time from the N groups of ultrasonic echo data each time to form a group of matrix data, wherein the selection times are M, and at least one group of ultrasonic echo data in each group of matrix data is different.
Taking 5 transducers as an example, N times of transmission are performed, fig. 6 is a schematic diagram of reconstruction of ultrasonic echo data provided by an embodiment of the present invention, and as shown in fig. 6, the N sets of ultrasonic echo data are sequentially arranged according to a time sequence, so as to obtain the first to nth sets of ultrasonic echo data, where an interval period t=0.4 ms (milliseconds) between two adjacent sets of ultrasonic echo data. Taking the first to fifth groups of ultrasonic echo data as first group matrix data, taking the second to sixth groups of ultrasonic echo data as second group matrix data, taking the third to seventh groups of ultrasonic echo data as third group matrix data, taking the fourth to eighth groups of ultrasonic echo data as fourth group matrix data, and so on until the N-4 th to N-th groups of ultrasonic echo data are taken as M-th group matrix data. At least one set of ultrasound echo data in each set of matrix data is different, for example, the different ultrasound echo data in the first set of matrix data and the second set of matrix data are respectively the first set of ultrasound echo data and the sixth set of ultrasound echo data.
In general, after the 5 transducers transmit successively, 5 sets of ultrasonic echo data are obtained, the 5 sets of ultrasonic echo data can represent the bladder form (three-dimensional depth information of the bladder) at the current time, and so on, the bladder form at the next time can be obtained, the time interval between the current time and the next time is 5×t=2 ms (milliseconds), and the frame rate of data calculation is 500 frames/second. After the above data reconstruction is adopted, M groups of matrix data with a time interval of t=0.4 ms (milliseconds) are finally obtained, and the frame rate of data calculation is 2500 frames/second, which is 5 times of the former, so that calculation can be performed by using larger and denser data volume.
Specifically, with 5 transducers, each transducer is sequentially transmitted at intervals of 1ms (millisecond) as one cycle, 10 transmissions are performed for each transducer in 50ms (millisecond), each transducer obtains 4 bladder wall potential values, and after the above data reconstruction scheme is adopted, an input matrix with the size of 50×20 is obtained, as shown in fig. 7, from left to right, and column 1 to column 4 elements represent ultrasonic signals transmitted in 50ms (millisecond) of transducer 1, and 4 bladder wall potential values are obtained. Since transducer No. 1 performs 10 transmissions within 50ms, according to the above data reconstruction scheme, part of the data is reused, and finally 50 lines of data are obtained, and the following is the same: columns 5 through 8 represent potential bladder wall values obtained from 10 shots performed within 50ms of transducer number 2; columns 9 through 12 represent potential bladder wall values obtained from 10 shots performed within 50ms of transducer number 3; column 13 to 16 show potential bladder wall values obtained from 10 transmissions performed within 50ms of transducer number 4; columns 17 through 20 represent potential bladder wall values obtained from 10 shots performed within 50ms of transducer number 5. The range of values of each element of the input matrix shown in fig. 7 is [0, 30cm ], which means that the detection depth range of the transducer is within 30cm (centimeters) of the downward extension of the human epidermis, and the 30cm is recommended by a professional doctor.
Here, when denoising the ultrasonic echo data, the ultrasonic echo data corresponding to more than 30cm can be removed by taking 30cm as a limit, so that the accuracy of detection is ensured.
It should be noted that, here, N may be different from the number of transducers, that is, in the above example, each set of matrix data may include not equal to 5 sets of the ultrasound echo data, for example, may include any one integer set of the ultrasound echo data greater than or equal to 1 and less than or equal to N, which is not limited herein.
According to the bladder volume detection method provided by the embodiment of the invention, through data reconstruction, the frame frequency of ultrasonic echo data is improved, denser and larger data volume can be obtained, the ultrasonic echo data is fully utilized, the transmission times of ultrasonic signals are reduced, the cost is reduced, the influence of external factors is overcome, and the detection accuracy is improved.
S242, calculating M groups of front and rear wall difference matrixes by using the distance values of the front wall of the bladder and the distance values of the rear wall of the bladder in the M groups of matrix data. Each element in the anterior-posterior wall difference matrix represents a measured anterior-posterior wall distance difference of the bladder.
Here, the M groups of matrix data may be combined into one matrix, and the combined matrix may be the input matrix according to the above data reconstruction scheme, as described above.
As an alternative implementation manner of the embodiment of the present invention, the S242 includes:
s2421, acquiring a distance threshold of the anterior and posterior walls of the bladder.
Specifically, each time ultrasonic signal is transmitted, 4 potential values of the bladder wall are obtained, including a distance value of the bladder front wall and a distance value of the bladder back wall, and through a great amount of experimental statistics of the inventor, the distance threshold value of the bladder front wall and the bladder back wall is 6cm (centimeters).
S2422, for M groups of matrix data, establishing a front wall matrix according to the bladder wall distance value smaller than the distance threshold in each group of matrix data, and establishing a rear wall matrix according to the bladder wall distance value larger than or equal to the distance threshold, so as to obtain M groups of front wall matrices and M groups of rear wall matrices corresponding to the M groups of front wall matrices one by one.
Specifically, the bladder wall distance value smaller than the distance threshold in the M groups of matrix data is regarded as the bladder front wall distance value, the bladder wall distance value larger than or equal to the distance threshold is regarded as the bladder back wall distance value, and half of the bladder front wall distance value and half of the bladder back wall distance value are respectively used as the M groups of front wall matrices and the M groups of back wall matrices. Fig. 8A is a schematic view of the front wall matrix, fig. 8B is a schematic view of the back wall matrix, and in the input matrix shown in fig. 7, 2 bladder wall distance values may be obtained from 4 bladder wall potential values, and the 2 bladder wall distance values are divided into a bladder front wall distance value and a bladder back wall distance value according to the distance threshold, and then half of the bladder front wall distance value and the bladder back wall distance value are respectively used as elements in the front wall matrix shown in fig. 8A and elements in the back wall matrix shown in fig. 8B.
Further, X shown in FIG. 7 1,1 、X 1,2 、X 1,3 、X 1,4 The potential values of the bladder wall obtained by the first transmission of the No. 1 transducer are calculated to obtain the corresponding distance value of the bladder front wall and the distance value of the bladder back wall, and the distance value of the bladder front wall and half of the distance value of the bladder back wall are respectively a 1,1 And b 1,1 As elements in the front wall matrix shown in fig. 8A and the back wall matrix shown in fig. 8B, respectively.
S2423, respectively differencing each element in the back wall matrix and the corresponding front wall matrix, and calculating to obtain M groups of front and back wall difference matrixes.
Specifically, in a certain plane of the bladder wall, depth information (front-back wall difference value) on a certain line can be obtained by transmitting ultrasonic signals once, so that M groups of front-back wall difference value matrices can be obtained by respectively differencing each corresponding element in the back wall matrix and the front wall matrix. Along the above example, subtracting each element in fig. 8A from each element in the back wall matrix in fig. 8B correspondingly yields the front and back wall difference matrix in fig. 8C. Specifically, c 1,1 ＝b 1,1 -a 1,1 。
S243, inputting M groups of front and rear wall difference matrixes into the neural network model to calculate the volume value of the bladder.
Specifically, fitting the M sets of front and rear wall difference matrices on a time scale (that is, according to the sequence of ultrasonic signal transmission), three-dimensional depth information of the bladder can be obtained, the three-dimensional depth information is input into the neural network model, and the volume value of the bladder is output. The composition of the neural network model and the training method are shown in fig. 3 and fig. 4, and are not described herein.
As an alternative implementation manner, in the embodiment of the invention, the neural network model can be used for directly calculating and outputting the volume value of the bladder, or can be used for calculating and outputting only the longitudinal cutting contour of the bladder. Specifically, when the neural network model is used only to calculate and output the longitudinal contour of the bladder, the above-mentioned step S243 includes: inputting M groups of anterior and posterior wall difference matrixes into the neural network model, and outputting a bladder longitudinal incision profile; calculating the longitudinal contour area of the bladder by utilizing the bladder longitudinal contour; and calculating the volume value of the bladder through an ellipsoidal volume calculation formula based on the longitudinal contour area.
That is, the embodiment of the invention firstly uses the neural network model to fit the longitudinal cut outline of the bladder: the specific flow is as follows:
and carrying out data reconstruction on the N groups of ultrasonic echo data to obtain M groups of matrix data. Each set of matrix data includes N sets of ultrasound echo data, N being less than or equal to N, each set of ultrasound echo data including a bladder anterior wall distance value and a bladder posterior wall distance value.
Taking a total of 10 transmissions with 5 transducers, 10 sets of ultrasound echo data are obtained as an example. The data reconstruction may be: the ultrasonic echo data transmitted in the first transmission cycle, namely the first to the fifth transmission are taken as a first group of matrix data, the ultrasonic echo data transmitted in the second transmission cycle, namely the sixth to the tenth transmission are taken as a second group of matrix data, and 5 groups of ultrasonic echo data are included in each group of matrix data. Taking 1 transducer as an example, 10 transmissions are performed equally, resulting in 10 sets of ultrasound echo data. The data reconstruction may be: and taking the ultrasonic echo data obtained by each transmission as a group of matrix data, namely, each group of matrix data comprises 1 group of ultrasonic echo data.
Because the front and back walls of the bladder have a certain thickness, the transducer emits an ultrasonic signal once to obtain 4 potential values of the bladder wall, namely, when the ultrasonic signal propagates in the bladder, the ultrasonic signal encounters the front wall of the bladder and is reflected twice to obtain 2 potential values of the front wall of the bladder, and the back wall of the bladder is the same. The bladder anterior wall distance value and the bladder posterior wall distance value can be obtained by performing simple mathematical calculation on the 2 bladder anterior wall potential values and the 2 bladder posterior wall potential values.
After training to obtain a neural network model, carrying out data reconstruction by using the detected ultrasonic echo data to obtain M groups of matrix data, and then calculating to obtain M groups of front and rear wall difference matrixes which are used as input of the neural network model so as to obtain a bladder longitudinal contour output by the neural network model; after the bladder longitudinal contour is obtained, calculating the longitudinal contour area, and calculating the bladder volume through an ellipsoidal volume calculation formula.
As an alternative embodiment of the present invention, a neural network model for fitting the longitudinal contour of the bladder may be further designed, which includes two fully connected layers FC,100 and FC,120 having the number of neurons of 100 and 120, respectively, as a hidden layer, and one fully connected layer FC,100 having the number of neurons of 100 as an output layer. And taking the M groups of matrix data (comprising the distance value of the front wall of the bladder and the distance value of the rear wall of the bladder) as input of the neural network model for fitting the longitudinal cut contour of the bladder, and obtaining a vector of 1 multiplied by 100 after FC,100, FC,120 and FC,100 respectively, thus obtaining the coordinates of 50 points on the longitudinal cut contour of the bladder. Bladder contours were fitted by coordinates of the 50 points.
As shown in fig. 11, the training method for fitting the neural network model of the longitudinal bladder contour according to the embodiment of the present invention may include the following steps:
s201, acquiring front and rear wall distance information of an X group of bladders, preprocessing to obtain bladder longitudinal contour coordinates, and correspondingly marking longitudinal contours of the X group of bladders to obtain a sample set;
s202, inputting the sample set into the FC,100 of the neural network model;
s203, training the neural network model by adopting an Adam algorithm;
s204, obtaining an output value of the FC,100;
s205, calculating the deviation between the output value of the FC,100 and the contour, and if the deviation meets the preset error requirement, ending training; if not, correcting the weight and the bias, and returning to the step S103 to continue training.
And S25, sending a urination warning signal according to the volume value of the bladder.
Specifically, the electronic device 40 may be communicatively connected to an upper computer (including, but not limited to, a mobile phone, a tablet PC, etc.) and configured to compare the volume value with a preset urination threshold, and push a urination early warning on a human-computer interaction interface (a display unit or a sound playing unit) of the upper computer when the volume value is greater than or equal to the preset urination threshold. The urination pre-warning comprises, but is not limited to, modes such as buzzing alarm, message pushing, vibration, bell sound prompt and the like.
According to a second aspect, an embodiment of the present invention provides a bladder volume detecting device, which is used to implement the foregoing embodiments and optional implementations, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
An embodiment of the present invention provides a bladder volume detection device, as shown in fig. 9, the device includes:
a breath detection module 31 for detecting a breath characteristic of a user under test, determining a breath period of the user based on the breath characteristic;
an ultrasonic transmission module 32 for transmitting N ultrasonic signals to the user's bladder during one of the respiratory cycles; n is an integer greater than or equal to 1;
the ultrasonic echo data receiving module 33 is configured to receive N sets of ultrasonic echo data formed by reflecting the N ultrasonic signals through the bladder wall;
the calculation module 34 is configured to calculate a volume value of the bladder using a neural network model obtained by training in advance based on the N sets of ultrasonic echo data.
The bladder volume sensing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory executing one or more software or firmware programs, and/or other devices that can provide the functionality described above. The functional description of each module is the same as that of the corresponding embodiment, and is not repeated here.
According to the bladder volume detection device provided by the embodiment of the invention, the ultrasonic signals are emitted in the breathing cycle of the user, and the ultrasonic echo data formed after the ultrasonic signals are reflected by the bladder wall is received, so that the influence of breathing on the detection result can be eliminated; on the other hand, the relation between the ultrasonic echo data with large data volume is analyzed through the neural network model obtained through pre-training, so that the volume value of the bladder is calculated, the influence of single data is avoided, and the detection accuracy is further improved.
The embodiment of the invention also provides electronic equipment, which is provided with the device shown in fig. 9.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, and as shown in fig. 10, the electronic device may include: at least one processor 41, such as a CPU (Central Processing Unit ), at least one communication interface 43, a memory 44, at least one communication bus 42. Wherein a communication bus 42 is used to enable connected communication between these components. The communication interface 43 may include a Display screen (Display) and a Keyboard (Keyboard), and the optional communication interface 43 may further include a standard wired interface and a wireless interface. The memory 44 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 44 may alternatively be at least one memory device located remotely from the aforementioned processor 41. Wherein the processor 41 may be as described in connection with fig. 9, the memory 44 stores an application program, and the processor 41 invokes the program code stored in the memory 44 for performing any of the method steps described above.
The communication bus 42 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The communication bus 42 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 10, but not only one bus or one type of bus.
Wherein the memory 44 may include volatile memory (English) such as random-access memory (RAM); the memory may also include a nonvolatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated as HDD) or a solid state disk (english: solid-state drive, abbreviated as SSD); memory 44 may also include a combination of the types of memory described above.
The processor 41 may be a central processor (English: central processing unit, abbreviated: CPU), a network processor (English: network processor, abbreviated: NP) or a combination of CPU and NP.
The processor 41 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof (English: programmable logic device). The PLD may be a complex programmable logic device (English: complex programmable logic device, abbreviated: CPLD), a field programmable gate array (English: field-programmable gate array, abbreviated: FPGA), a general-purpose array logic (English: generic array logic, abbreviated: GAL), or any combination thereof.
Optionally, the memory 44 is also used for storing program instructions. Processor 41 may invoke program instructions to implement the bladder volume detection method as shown in the embodiments of fig. 2, 4, 5 of the present application.
Embodiments of the present application also provide a non-transitory computer storage medium storing computer-executable instructions that are operable to perform the bladder volume detection method of any of the method embodiments described above. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
Although embodiments of the present application have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the application, and such modifications and variations are within the scope of the application as defined by the appended claims.
Claims (9)
1. A method of bladder volume measurement, comprising:
Detecting a respiratory feature of a user under test, determining a respiratory cycle of the user based on the respiratory feature;
transmitting N ultrasonic signals to the user's bladder during one of the respiratory cycles; n is an integer greater than or equal to 1;
receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall;
calculating the volume value of the bladder by utilizing a neural network model obtained by pre-training based on the N groups of ultrasonic echo data;
the calculating the volume value of the bladder by using a neural network model obtained by training in advance based on the N groups of ultrasonic echo data comprises the following steps:
carrying out data reconstruction on the N groups of ultrasonic echo data to obtain M groups of matrix data, wherein each group of matrix data comprises N groups of ultrasonic echo data, N is less than or equal to N, and each group of ultrasonic echo data comprises a bladder front wall distance value and a bladder back wall distance value;
calculating to obtain M groups of front and rear wall difference matrixes by using the bladder front wall distance values and the bladder rear wall distance values in the M groups of matrix data, wherein each element in the front and rear wall difference matrixes represents the measured front and rear wall distance difference of the bladder;
inputting M groups of front and rear wall difference matrixes into the neural network model to calculate and obtain the volume value of the bladder;
Inputting M groups of the front wall difference value matrix and the rear wall difference value matrix into the neural network model to calculate the volume value of the bladder, wherein the method comprises the following steps:
inputting M groups of anterior and posterior wall difference matrixes into the neural network model, and outputting a bladder longitudinal incision profile;
calculating the longitudinal contour area of the bladder by utilizing the bladder longitudinal contour;
and calculating the volume value of the bladder through an ellipsoidal volume calculation formula based on the longitudinal contour area.
2. The method for detecting the volume of the bladder according to claim 1, wherein the calculating the M sets of anterior-posterior wall difference matrices using the anterior-bladder wall distance values and the posterior-bladder wall distance values in the M sets of matrix data includes:
acquiring a distance threshold of the front wall and the rear wall of the bladder;
for M groups of matrix data, establishing a front wall matrix according to the bladder wall distance value smaller than the distance threshold value in each group of matrix data, and establishing a rear wall matrix according to the bladder wall distance value larger than or equal to the distance threshold value, so as to obtain M groups of front wall matrices and M groups of rear wall matrices corresponding to the M groups of front wall matrices one by one;
and respectively differencing each element in the back wall matrix and the corresponding front wall matrix to obtain M groups of front and back wall difference matrices by calculation.
3. The bladder volume detection method according to claim 1, wherein said transmitting N ultrasonic signals to the user's bladder during one of the respiratory cycles comprises:
And triggering each transducer one by one according to an interval period in one respiratory period, and transmitting ultrasonic signals to the bladder of the user, wherein the number of the transducers is N, and the number of times of triggering the transducers is N.
4. The bladder volume detection method according to claim 1, wherein the performing data reconstruction on the N sets of ultrasonic echo data to obtain M sets of matrix data comprises:
and selecting N groups of ultrasonic echo data which are continuous in time from the N groups of ultrasonic echo data each time to form a group of matrix data, wherein the selection times are M, and at least one group of ultrasonic echo data in each group of matrix data is different.
5. A bladder volume detection method according to claim 3 wherein the interval period is calculated by the formula:
；
wherein,Twhich represents the period of the interval in question,Dthe depth of the test is indicated and,C s representing the speed of sound of the ultrasonic signal.
6. The bladder volume detection method according to any one of claims 1-5, further comprising:
and sending a urination early warning signal according to the volume value of the bladder.
7. A bladder volume measurement device, comprising:
the breath detection module is used for detecting the breath characteristics of a tested user and determining the breath period of the user based on the breath characteristics;
An ultrasonic wave transmitting module for transmitting an ultrasonic wave signal to the bladder of the user N times in one of the respiratory cycles; n is an integer greater than or equal to 1;
the ultrasonic echo data receiving module is used for receiving N groups of ultrasonic echo data formed after the N ultrasonic signals are reflected by the bladder wall;
the calculation module is used for calculating the volume value of the bladder by utilizing a neural network model obtained through pre-training based on the N groups of ultrasonic echo data, and is particularly used for carrying out data reconstruction on the N groups of ultrasonic echo data to obtain M groups of matrix data, wherein each group of matrix data comprises N groups of ultrasonic echo data, N is smaller than or equal to N, and each group of ultrasonic echo data comprises a bladder front wall distance value and a bladder back wall distance value; calculating to obtain M groups of front and rear wall difference matrixes by using the bladder front wall distance values and the bladder rear wall distance values in the M groups of matrix data, wherein each element in the front and rear wall difference matrixes represents the measured front and rear wall distance difference of the bladder; inputting M groups of front and rear wall difference matrixes into the neural network model to calculate and obtain the volume value of the bladder; inputting M groups of front and rear wall difference matrixes into the neural network model to calculate the volume value of the bladder, wherein the method comprises the following steps: inputting M groups of anterior and posterior wall difference matrixes into the neural network model, and outputting a bladder longitudinal incision profile; calculating the longitudinal contour area of the bladder by utilizing the bladder longitudinal contour; and calculating the volume value of the bladder through an ellipsoidal volume calculation formula based on the longitudinal contour area.
8. An electronic device, comprising:
a memory and a processor in communication with each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the bladder volume detection method of any of claims 1-6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing the computer to perform the bladder volume detection method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010827115.3A CN111938704B (en) | 2020-08-17 | 2020-08-17 | Bladder volume detection method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010827115.3A CN111938704B (en) | 2020-08-17 | 2020-08-17 | Bladder volume detection method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111938704A CN111938704A (en) | 2020-11-17 |
| CN111938704B true CN111938704B (en) | 2023-12-01 |
Family
ID=73343171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010827115.3A Active CN111938704B (en) | 2020-08-17 | 2020-08-17 | Bladder volume detection method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111938704B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0538346A (en) * | 1991-08-06 | 1993-02-19 | Akio Yamada | Urine incontinence preventing monitor device |
| JP2014023813A (en) * | 2012-07-30 | 2014-02-06 | Saga Univ | Ultrasonic sensor and organ measuring device |
| CN106821419A (en) * | 2016-12-30 | 2017-06-13 | 深圳开立生物医疗科技股份有限公司 | Calculate the method and system of Bladder Volume |
| CN107106122A (en) * | 2014-11-27 | 2017-08-29 | Umc乌得勒支控股有限公司 | Wearable ultrasonic unit for transmitting variable signal in human body or animal body |
| CN108024769A (en) * | 2015-07-27 | 2018-05-11 | 中央兰开夏大学 | Method and apparatus for estimating bladder condition |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IL158379A0 (en) * | 2003-10-13 | 2004-05-12 | Volurine Israel Ltd | Non invasive bladder distension monitoring apparatus to prevent enuresis, and method of operation therefor |
| JP6077184B2 (en) * | 2014-01-28 | 2017-02-08 | コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． | Device and method for monitoring bladder capacity of a subject |
-
2020
- 2020-08-17 CN CN202010827115.3A patent/CN111938704B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0538346A (en) * | 1991-08-06 | 1993-02-19 | Akio Yamada | Urine incontinence preventing monitor device |
| JP2014023813A (en) * | 2012-07-30 | 2014-02-06 | Saga Univ | Ultrasonic sensor and organ measuring device |
| CN107106122A (en) * | 2014-11-27 | 2017-08-29 | Umc乌得勒支控股有限公司 | Wearable ultrasonic unit for transmitting variable signal in human body or animal body |
| CN108024769A (en) * | 2015-07-27 | 2018-05-11 | 中央兰开夏大学 | Method and apparatus for estimating bladder condition |
| CN106821419A (en) * | 2016-12-30 | 2017-06-13 | 深圳开立生物医疗科技股份有限公司 | Calculate the method and system of Bladder Volume |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111938704A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7330207B2 (en) | adaptive ultrasound scanning | |
| CN110678933B (en) | Ultrasound clinical feature detection and associated devices, systems, and methods | |
| EP3040033A1 (en) | Diagnostic ultrasound apparatus and elasticity evaluation method | |
| CN101889216A (en) | Method and system for imaging vessels | |
| CN107072635A (en) | The quality metric for the multi-hop echocardiogram collection fed back for intermediate user | |
| CN110740689B (en) | Ultrasonic diagnostic apparatus and method of operating the same | |
| CN103635144A (en) | Method and apparatus for automated ultrasonic Doppler angle and flow velocity estimation | |
| CN105682551A (en) | Device and method for monitoring bladder volume of a subject | |
| JP7237147B2 (en) | Biometric measurement and quality assessment | |
| US11532084B2 (en) | Gating machine learning predictions on medical ultrasound images via risk and uncertainty quantification | |
| CN111820947B (en) | Ultrasonic heart reflux automatic capturing method and system and ultrasonic imaging equipment | |
| CN105997150B (en) | Adaptive timing in stress echocardiography guides | |
| JP7093093B2 (en) | Ultrasonic urine volume measuring device, learning model generation method, learning model | |
| CN111938704B (en) | Bladder volume detection method and device and electronic equipment | |
| CN114680929A (en) | Ultrasonic imaging method and system for measuring diaphragm | |
| WO2021209400A1 (en) | Systems and methods for non-invasive pressure measurements | |
| US8394023B2 (en) | Method and apparatus for automatically determining time to aortic valve closure | |
| CN115500867A (en) | Bone parameter measuring method and electronic equipment | |
| CN104367346A (en) | Echo displacement detecting method and imaging method based on sound radiation force | |
| CN110491513A (en) | A kind of arteria carotis detection system, information processing unit | |
| US20230397905A1 (en) | Ultrasound time series data processing apparatus and ultrasound time series data processing program | |
| TWI773472B (en) | Array measuring method and interpretation device for ultrasonic detection of middle ear effusion | |
| CN113616235B (en) | Ultrasonic detection method, device, system, equipment, storage medium and ultrasonic probe | |
| KR20230011855A (en) | Method and apparatus for extracting quantitative information in medical ultrasound | |
| US20210369232A1 (en) | Systems and methods for evaluating respiratory function using a smartphone |
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 |