CN115588509A - Multi-mode mammary gland health detection system - Google Patents
Multi-mode mammary gland health detection system Download PDFInfo
- Publication number
- CN115588509A CN115588509A CN202211281266.9A CN202211281266A CN115588509A CN 115588509 A CN115588509 A CN 115588509A CN 202211281266 A CN202211281266 A CN 202211281266A CN 115588509 A CN115588509 A CN 115588509A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- detection
- mammary gland
- module
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a multi-mode mammary gland health detection system, which belongs to the field of medical treatment and is used for solving the problems that the mammary gland health detection usually adopts a uniform detection standard and the detection accuracy is poor.
Description
Technical Field
The invention belongs to the field of medical treatment, relates to a breast health detection technology, and particularly relates to a multi-modal breast health detection system.
Background
The mammary gland is the accessory gland of the skin, which is the ductal vesicular gland. The mammary gland of a male gradually degenerates around one and a half years old, and the gland has ducts, but has no acinus and no lobular division. The female mammary gland is hyperplastic in puberty, and after the menstruation starts, the development of the mammary gland is nearly mature.
In the prior art, a uniform detection standard is generally adopted for breast health detection, detection strength is almost the same, detection strength of detection personnel is not set in a differentiation mode in combination with actual physical conditions, detection accuracy is not good enough, and therefore a multi-mode breast health detection system is provided.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a multi-modal mammary gland health detection system.
The technical problem to be solved by the invention is as follows:
how to set the breast detection strength of a detector based on actual factors so as to improve the accuracy of breast health detection.
The purpose of the invention can be realized by the following technical scheme:
a multi-modal mammary gland health detection system comprises a data acquisition module, a user terminal, a real-time monitoring module, a grade setting module, a detection comparison module, a model construction module, a big data module, a feature matching module and a server, wherein the data acquisition module is used for acquiring mammary gland real-time monitoring data of a detector and sending the mammary gland real-time monitoring data to the server, and the server sends the mammary gland real-time monitoring data to the real-time monitoring module;
the real-time monitoring data is used for monitoring the breast health condition of the detection personnel in real time, the obtained state deviation value of the detection personnel is fed back to the server, and the server sends the state deviation value of the detection personnel to the level setting module;
the level setting module is used for setting the detection level of the detection personnel in combination with the state deviation value, the detection level of the detection personnel is obtained and fed back to the server, and the server sets corresponding detection strength for the detection personnel according to the detection level and sends the detection strength to the detection comparison module;
the big data module is used for acquiring real-time monitoring data of different crowds; the model construction module is used for constructing mammary gland detection models of different crowds, the obtained mammary gland detection models are fed back to the server, and the server sends the mammary gland detection models to the detection comparison module;
the detection comparison module is used for comparing the health of the mammary gland of the detection personnel according to the detection times, generating a mammary gland abnormal signal and feeding the mammary gland abnormal signal back to the server or not performing any operation;
if the server receives the mammary gland abnormal signal, a mammary gland diagnosis signal is generated and sent to the user terminal, and the detection personnel at the user terminal sends the mammary gland diagnosis signal to the mammary gland detection point for detection after receiving the mammary gland diagnosis signal.
Furthermore, the data acquisition module is used for acquiring multi-modal real-time biological data of the patient and sending the multi-modal real-time biological data to the server, and the server sends the multi-modal real-time biological data to the feature matching module;
the characteristic matching module is used for identifying and matching the identity characteristics of detection personnel, and the working process is as follows:
step S1: acquiring multi-modal preset biological data and multi-modal real-time biological data of a detector, and comparing the multi-modal real-time biological data with the multi-modal preset biological data;
step S2: comparing the two groups of face information of the detected person;
and step S3: comparing the current external distance between the two canthi with a preset external distance between the two canthus, entering the next step if the external distances between the two canthus are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
and step S4: comparing the length width of the current head with the preset length width of the head, entering the next step if the length width of the head is the same, and otherwise, continuing the comparison until the matching failure signal is generated in failure;
step S5: comparing the current distance between the two ears with a preset distance between the two ears, entering the next step if the distances between the two ears are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S6: comparing the current mouth angle interval with a preset mouth angle interval, entering the next step if the mouth angle intervals are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current fingerprint information and preset fingerprint information, entering the next step if the fingerprint information is the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current iris information and preset iris information, if the iris information is the same, generating a matching success signal, otherwise, continuously comparing until a matching failure signal is generated in a failure mode;
the characteristic matching module feeds back a matching success signal or a matching failure signal to the server;
if the server receives the matching success signal, the user terminal logs in successfully;
and if the server receives the matching failure signal, the user terminal fails to log in.
Further, the multi-modal real-time biological data comprises fingerprint information, face information and iris information of the detected person;
the face information includes the extraocular distance, the head length width, the two-ear distance, and the mouth angle distance.
Further, the real-time monitoring data is real-time specification of the mammary gland, real-time number of the mammary gland and real-time pain times in unit time of the detection person.
Further, the working process of the real-time monitoring data is specifically as follows:
obtaining corresponding preset mammary gland monitoring data according to personal information of a detection person;
the preset mammary gland monitoring data comprise a mammary gland standard specification, a mammary gland standard number and an upper limit value of pain times in unit time;
acquiring real-time specifications of the mammary gland of a detector, and comparing the real-time specifications of the mammary gland with preset specifications of the mammary gland to obtain a mammary gland specification difference value of the detector; acquiring the real time number of the mammary gland of a detector, and comparing the real time number of the mammary gland with the standard number of the mammary gland to obtain a mammary gland number difference value of the detector; acquiring real-time pain times of a tester in unit time, and calculating the difference value between the real-time pain times and the upper limit value of the pain times to obtain the pain time difference value of the tester in unit time;
calculating to obtain a state deviation value of the detection personnel;
the mammary gland standard number is an interval range and comprises an mammary gland standard upper limit number and an mammary gland standard lower limit number, the real-time number of mammary glands is respectively calculated as a difference value with the mammary gland standard upper limit number and the mammary gland standard lower limit number, and then the difference value of the mammary gland number of the detection personnel can be obtained by adding the two groups and summing the sum to obtain an average value.
Further, the setting process of the level setting module is specifically as follows:
and comparing the state deviation value with a state deviation threshold value, and judging the detection level of the detection personnel to be a third detection level, a second detection level or a first detection level.
Further, the detection strength set by the server is specifically as follows:
if the detection level is the first detection level, setting N1 detection times for the detector;
if the detection level is the second detection level, setting N2 detection times for the detection personnel;
if the detection level is the third detection level, setting the detection times for the detector for N3 times; wherein N1, N2 and N3 are fixed numerical values and are normal numbers, and N3 is more than N2 and less than N1.
Further, the construction process of the model construction module is specifically as follows:
step S1: acquiring real-time monitoring data of different crowds to obtain real-time specifications of mammary glands, real-time number of mammary glands and real-time pain times in unit time of the different crowds;
step S2: sequentially traversing real-time specifications, real-time times of mammary glands and real-time pain times in unit time of different crowds to obtain real-time maximum specifications, real-time minimum specifications, real-time upper limit numbers, real-time lower limit numbers, real-time upper limit times of mammary glands and real-time lower limit times of mammary glands of different crowds;
and step S3: respectively removing the maximum value and the minimum value in real-time specification and real-time number of mammary glands, and adding a plurality of real-time specifications of mammary glands and taking an average value to obtain the optimal mammary gland specification of different people;
adding a plurality of real-time mammary gland number specifications, and taking an average value to obtain the optimal mammary gland number of different people;
the real-time pain lower limit times in a plurality of unit time are used as the optimal pain times in unit time of different crowds;
and step S4: the optimal breast size, the optimal number of breasts and the optimal number of pains per unit time constitute breast detection models for different populations.
Further, the alignment process of the detection and alignment module is specifically as follows:
step P1: substituting real-time breast monitoring data of a detector into a breast detection model according to the detection times;
step P2: comparing the real-time specification of the mammary gland during each detection with the optimal specification of the mammary gland, comparing the real-time number of the mammary gland during each detection with the optimal number of the mammary glands, and comparing the real-time pain frequency in unit time during each detection with the optimal pain frequency in unit time;
step P3: if the real-time specification of the mammary gland is within the error range of the optimal mammary gland specification, no operation is performed;
if the real-time specification of the mammary gland is not within the error range of the optimal mammary gland specification, entering the next step;
step P4: if the real time number of the mammary gland is within the error range of the optimal mammary gland number, no operation is carried out;
if the real number of the mammary glands is within the error range of the optimal number of the mammary glands, entering the next step;
step P5: if the real-time pain times in the unit time are within the error range of the optimal pain times in the unit time, no operation is performed;
and if the real-time pain times in the unit time are not within the error range of the optimal pain times in the unit time, generating a mammary gland abnormal signal.
Compared with the prior art, the invention has the beneficial effects that:
the invention firstly utilizes a characteristic matching module to identify and match the identity characteristics of a detector, generates a matching success signal or a matching failure signal, is convenient to verify the identity information of the detector, utilizes real-time monitoring data to monitor the health condition of the mammary gland of the detector after the verification is passed, obtains a state deviation value of the detector and sends the state deviation value to a level setting module, the level setting module sets the detection level of the detector by combining the state deviation value to obtain the detection level of the detector, a server sets corresponding detection strength for the detector according to the detection level and sends the detection strength to a detection comparison module, the detection comparison module compares the health of the mammary gland of the detector according to the detection times, substitutes the real-time monitoring data of the mammary gland of the detector into a mammary gland detection model according to the detection times to generate a mammary gland diagnosis signal or does not carry out any operation, and sets the detection strength of the mammary gland of the detector based on actual factors, thereby improving the accuracy of the mammary gland health detection.
Drawings
To facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is an overall system block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this embodiment, referring to fig. 1, a multimodal breast health detection system is provided, which includes a data acquisition module, a user terminal, a real-time monitoring module, a level setting module, a detection and comparison module, a model construction module, a big data module, a feature matching module, and a server;
the user terminal is used for registering a login system after a user inputs personal information and sending the personal information to the server for storage;
the personal information comprises the name, the gender and the age of a detected person, a mobile phone number for real-name authentication, multi-mode preset biological data and the like;
in one embodiment, the data acquisition module is used for acquiring multi-modal real-time biological data of a patient and sending the multi-modal real-time biological data to the server, and the server sends the multi-modal real-time biological data to the feature matching module;
it is further noted that the multi-modal real-time biological data includes fingerprint information, face information, iris information, etc. of the detected person; the face information may include the extraocular distance, the head length and width, the interaural distance, the mouth angle distance, etc.;
the characteristic matching module is used for identifying and matching the identity characteristics of detection personnel, and the working process is as follows:
step S1: acquiring multi-modal preset biological data and multi-modal real-time biological data of a detector, and comparing the multi-modal real-time biological data with the multi-modal preset biological data;
step S2: comparing the two groups of face information of the detected person;
and step S3: comparing the current external distance between the two canthi with a preset external distance between the two canthi, if the external distances between the two canthi are the same, entering the next step, otherwise, continuing to compare until a matching failure signal is generated in failure;
and step S4: comparing the length width of the current head with the preset length width of the head, entering the next step if the length width of the head is the same, and otherwise, continuing the comparison until the matching failure signal is generated in failure;
step S5: comparing the current distance between the two ears with a preset distance between the two ears, entering the next step if the distances between the two ears are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S6: comparing the current mouth angle interval with a preset mouth angle interval, entering the next step if the mouth angle intervals are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current fingerprint information and preset fingerprint information, entering the next step if the fingerprint information is the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current iris information and preset iris information, if the iris information is the same, generating a matching success signal, otherwise, continuously comparing until a matching failure signal is generated in a failure mode;
the characteristic matching module feeds back a matching success signal or a matching failure signal to the server;
if the server receives the matching success signal, the user terminal logs in successfully;
if the server receives the matching failure signal, the user terminal fails to log in;
in an embodiment, the data acquisition module is further configured to acquire real-time breast monitoring data of a detecting person and send the real-time breast monitoring data to the server, and the server sends the real-time breast monitoring data to the real-time monitoring module;
specifically, the real-time monitoring data includes real-time specification of the mammary gland, real-time number of the mammary gland, real-time pain times in unit time and the like of the detecting person;
in specific implementation, the data acquisition module is a smart phone or a tablet computer provided with a patient questionnaire program, can also be a computer capable of inputting patient medical record information, a palpation result and a tumor marker inspection result, and can also comprise infrared image acquisition equipment, ultrasonic image acquisition equipment, X-ray image acquisition equipment, thermal image acquisition equipment, resistance spectrum acquisition equipment, CT image equipment, nuclear magnetic image equipment and the like;
in this embodiment, the real-time monitoring data is used for monitoring the health condition of the breast of the detecting person in real time, and the working process specifically includes the following steps:
the method comprises the following steps: marking the detected person as u, u =1,2, … …, z, which is a positive integer; acquiring corresponding preset breast monitoring data according to personal information of a detector;
the preset mammary gland monitoring data comprise standard mammary gland specifications, standard mammary gland number, upper limit value of pain times in unit time and the like;
step two: acquiring real-time specifications of mammary glands of a detector, and comparing the real-time specifications of the mammary glands with preset specifications of the mammary glands to obtain a mammary gland specification difference value GCu of the detector;
step three: acquiring the real time number of the mammary gland of a detector, and comparing the real time number of the mammary gland with the standard number of the mammary gland to obtain a mammary gland number difference LCu of the detector;
the mammary gland standard number is an interval range and comprises an mammary gland standard upper limit number and a mammary gland standard lower limit number, the real-time number of mammary glands is respectively calculated as a difference value with the mammary gland standard upper limit number and the mammary gland standard lower limit number, and then the difference value of the mammary gland number of the detection personnel can be obtained by adding the two groups and summing the sum to obtain an average value;
step four: acquiring real-time pain times of a tester in unit time, and calculating a difference value between the real-time pain times and an upper limit value of the pain times to obtain a pain time difference value CCu of the tester in unit time;
step five: calculating to obtain a state deviation value ZPu of the inspector through a formula ZPu = GCu × a1+ LCu × a2+ CCu × a 3; in the formula, a1, a2 and a3 all fix the weight coefficient of the numerical value, and the values of a1, a2 and a3 are all larger than zero;
the real-time monitoring module feeds back a state deviation value ZPu of a detector to the server, and the server sends the state deviation value ZPu of the detector to the level setting module;
the level setting module is used for setting the detection level of a detector in combination with the state deviation value, and the setting process is as follows:
if ZPu is less than X1, the detection level of the detector is the third detection level;
if the X1 is not less than ZPu is less than X2, the detection level of the detection personnel is a second detection level;
if X2 is not more than ZPu, the detection level of the detector is the first detection level; wherein X1 and X2 are both state deviation threshold values with fixed numerical values, and X1 is less than X2;
the level setting module feeds back the detection level of the detection personnel to the server, and the server sets corresponding detection strength for the detection personnel according to the detection level and sends the detection strength to the detection comparison module, and specifically:
if the detection level is the first detection level, setting N1 detection times for the detector;
if the detection level is the second detection level, setting N2 detection times for the detection personnel;
if the detection level is the third detection level, setting the detection times for the detector for N3 times; wherein N1, N2 and N3 are fixed numerical value normal numbers, and N3 is more than N2 and less than N1;
the model building module is connected with a big data module, and the big data module is used for acquiring real-time monitoring data of different crowds; the model construction module is used for constructing mammary gland detection models of different crowds, and the construction process specifically comprises the following steps:
step S1: acquiring real-time monitoring data of different crowds to obtain real-time specifications of mammary glands, real-time number of mammary glands and real-time pain times in unit time of the different crowds;
step S2: sequentially traversing real-time specifications, real-time times of mammary glands and real-time pain times in unit time of different crowds to obtain real-time maximum specifications, real-time minimum specifications, real-time upper limit numbers, real-time lower limit numbers, real-time upper limit times of mammary glands and real-time lower limit times of mammary glands of different crowds;
and step S3: respectively removing the maximum value and the minimum value in real-time specification and real-time number of mammary glands, and adding a plurality of real-time specifications of mammary glands and taking an average value to obtain the optimal mammary gland specification of different people;
adding the specifications of the real-time numbers of the multiple mammary glands, and taking an average value to obtain the optimal number of the mammary glands of different people;
the real-time pain lower limit times in a plurality of unit time are used as the optimal pain times in unit time of different crowds;
and step S4: the breast detection models of different crowds are formed by the optimal breast specification, the optimal breast number and the optimal pain times in unit time;
the model construction module feeds back the breast detection model to the server, and the server sends the breast detection model to the detection comparison module;
the detection comparison module is used for comparing the breast health of the detection personnel according to the detection times, and the comparison process is concretely as follows;
step P1: substituting real-time breast monitoring data of a person to be detected into the breast detection model according to the detection times;
step P2: comparing the real-time specification of the mammary gland during each detection with the optimal specification of the mammary gland, comparing the real-time number of the mammary gland during each detection with the optimal number of the mammary glands, and comparing the real-time pain frequency in unit time during each detection with the optimal pain frequency in unit time;
and step P3: if the real-time specification of the mammary gland is within the error range of the optimal mammary gland specification, no operation is performed;
if the real-time specification of the mammary gland is not within the error range of the optimal mammary gland specification, entering the next step;
step P4: if the real time number of the mammary gland is within the error range of the optimal mammary gland number, no operation is carried out;
if the real number of the mammary glands is within the error range of the optimal number of the mammary glands, entering the next step;
step P5: if the real-time pain times in the unit time are within the error range of the optimal pain times in the unit time, no operation is performed;
if the real-time pain times in the unit time are not within the error range of the optimal pain times in the unit time, generating a mammary gland abnormal signal;
the detection and comparison module feeds back the mammary gland abnormal signal to a server or does not perform any operation;
if the server receives the mammary gland abnormal signal, a mammary gland diagnosis signal is generated and sent to the user terminal, and the detection personnel at the user terminal sends the mammary gland diagnosis signal to the mammary gland detection point for detection after receiving the mammary gland diagnosis signal.
In an embodiment, based on another concept of the same invention, a working method of a multi-modal breast health detection system is proposed, which specifically includes:
step S101, multi-modal real-time biological data of a patient are acquired through a data acquisition module and sent to a server, and the server sends the multi-modal real-time biological data to a feature matching module;
step S102, using a feature matching module to identify and match the identity features of the detection personnel, acquiring multi-mode preset biological data and multi-mode real-time biological data of the detection personnel, comparing the multi-mode real-time biological data with the multi-mode preset biological data, comparing two groups of face information of the detection personnel, comparing the current external space between the two canthus and the preset external space between the two canthus, if the external spaces between the two canthus are different, continuing to compare until failing to generate a matching failure signal, otherwise, comparing the current length width of the head with the preset length width of the head, if the length width of the head is different, continuing to compare until failing to generate a matching failure signal, otherwise, comparing the current distance between the two ears with the preset distance between the two ears, if the distances between the two ears are different, continuing to compare until failing to generate a matching failure signal, if the current mouth angle interval is not the same as the preset mouth angle interval, continuing to compare until a matching failure signal is failed to generate, otherwise, acquiring current fingerprint information and preset fingerprint information, if the fingerprint information is not the same, continuing to compare until a matching failure signal is failed to generate, otherwise, acquiring current iris information and preset iris information, if the iris information is the same, generating a matching success signal, otherwise, continuing to compare until a matching failure signal is failed to generate, if the matching success signal is received by the server, feeding back the matching success signal or the matching failure signal to the server, if the matching success signal is received by the server, the login of the user terminal is successful, and if the matching failure signal is received by the server, the login of the user terminal is failed;
step S103, the data acquisition module also acquires real-time breast monitoring data of a detector, and sends the real-time breast monitoring data to the server, and the server sends the real-time breast monitoring data to the real-time monitoring module;
step S104, real-time monitoring is carried out on the health condition of the mammary gland of a detector by using real-time monitoring data, the detector is marked as u, corresponding preset mammary gland monitoring data are obtained according to personal information of the detector, then real-time specifications of the mammary gland of the detector are obtained, the real-time specifications of the mammary gland are compared with the preset mammary gland specifications to obtain a mammary gland specification difference value GCu of the detector, real-time number of the mammary gland of the detector is obtained, the real-time pain times of the detector in unit time are obtained, the difference value between the real-time pain times and the upper limit value of the pain times is calculated to obtain a pain times difference value CCu of the detector in unit time, a state deviation value ZPu of the detector is obtained by calculating a formula ZPu = GCu × a1+ LCu × a2+ CCu × a3, the real-time monitoring module feeds back the state deviation value 3532 zxft Of the detector to a server, and the server sends the state deviation value 25 zxft 343425 to a setting level module;
step S105, a level setting module sets the detection level of the detection personnel according to the state deviation value, if ZPu is less than X1, the detection level of the detection personnel is a third detection level, if X1 is less than or equal to ZPu is less than X2, the detection level of the detection personnel is a second detection level, if X2 is less than or equal to ZPu, the detection level of the detection personnel is a first detection level, the level setting module feeds the detection level of the detection personnel back to a server, the server sets corresponding detection strength for the detection personnel according to the detection level and sends the detection strength to a detection comparison module, if the detection level is the first detection level, the detection times are set for the detection personnel for N1 times, if the detection level is the second detection level, the detection times are set for the detection personnel for N2 times, and if the detection level is the third detection level, the detection times are set for the detection personnel for N3 times;
step S106, the big data module acquires real-time monitoring data of different crowds, the model construction module is used for constructing mammary gland detection models of different crowds, acquiring the real-time monitoring data of different crowds, acquiring real-time specifications, real-time times of mammary glands and real-time pain times in unit time of different crowds, sequentially traversing the real-time specifications, real-time times of mammary glands and real-time pain times in unit time of different crowds, and acquiring real-time maximum specifications, real-time minimum specifications, real-time upper limit numbers, real-time lower limit numbers of mammary glands, real-time upper limit numbers of pain times in unit time and real-time lower limit numbers of pain times in unit time of different crowds, the method comprises the following steps of respectively removing the maximum value and the minimum value in real-time specifications of mammary glands and the real-time number of mammary glands, adding a plurality of real-time specifications of mammary glands and taking the average value to obtain the optimal specification of the mammary glands of different crowds, adding a plurality of real-time specifications of the mammary glands and taking the average value to obtain the optimal number of the mammary glands of the different crowds, taking the lower limit number of real-time pain in a plurality of unit time as the optimal number of pain in the unit time of the different crowds, forming a mammary gland detection model of the different crowds by the optimal specification of the mammary glands, the optimal number of the mammary glands and the optimal number of pain in the unit time, feeding the mammary gland detection model back to a server by a model building module, and sending the mammary gland detection model to a detection comparison module by the server;
step S107, the detection comparison module compares the breast health of the detection personnel according to the detection times, substitutes real-time breast monitoring data of the detection personnel into a breast detection model according to the detection times, compares the real-time breast specification of each detection with the optimal breast specification, compares the real-time breast number of each detection with the optimal breast number, compares the real-time breast pain number of each detection within unit time with the optimal breast pain number within unit time, if the real-time breast specification is within the error range of the optimal breast specification, does not perform any operation, if the real-time breast specification is not within the error range of the optimal breast specification, determines whether the real-time breast pain number is within the error range of the optimal breast number, if the real-time breast pain number is within the error range of the optimal breast number, does not perform any operation, if the real-time breast pain number within unit time is within the error range of the optimal breast pain number, determines whether the real-time breast pain number within unit time is within the error range of the optimal breast pain number within unit time, if the real-time breast pain number within the real-time breast signal is within the error range of the optimal breast pain number, does not perform any operation, and if the breast signal is received from the breast detection module to the operation server, and sends the breast signal to the detection server, if the breast detection server generates an abnormal detection signal, and sends the breast signal to the server.
The above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula of the latest real situation obtained by collecting a large amount of data and performing software simulation, the preset parameters in the formula are set by the technical personnel in the field according to the actual situation, the weight coefficient and the scale coefficient are specific numerical values obtained by quantizing each parameter, and the subsequent comparison is convenient.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. A multi-modal breast health detection system is characterized by comprising a data acquisition module, a user terminal, a real-time monitoring module, a grade setting module, a detection comparison module, a model construction module, a big data module, a feature matching module and a server, wherein the data acquisition module is used for acquiring breast real-time monitoring data of detection personnel and sending the data to the server, and the server sends the breast real-time monitoring data to the real-time monitoring module;
the real-time monitoring data is used for monitoring the breast health condition of the detection personnel in real time, the state deviation value of the detection personnel is obtained and fed back to the server, and the server sends the state deviation value of the detection personnel to the level setting module;
the level setting module is used for setting the detection level of the detection personnel in combination with the state deviation value, the detection level of the detection personnel is obtained and fed back to the server, and the server sets corresponding detection strength for the detection personnel according to the detection level and sends the detection strength to the detection comparison module;
the big data module is used for acquiring real-time monitoring data of different crowds; the model construction module is used for constructing mammary gland detection models of different crowds, the obtained mammary gland detection models are fed back to the server, and the server sends the mammary gland detection models to the detection comparison module;
the detection comparison module is used for comparing the health of the mammary gland of the detection personnel according to the detection times, generating a mammary gland abnormal signal and feeding the mammary gland abnormal signal back to the server or not performing any operation;
if the server receives the mammary gland abnormal signal, a mammary gland diagnosis signal is generated and sent to the user terminal, and the detection personnel at the user terminal sends the mammary gland diagnosis signal to the mammary gland detection point for detection after receiving the mammary gland diagnosis signal.
2. The multi-modal breast health detection system of claim 1, wherein the data collection module is configured to collect multi-modal real-time biological data of the patient and send the multi-modal real-time biological data to the server, and the server sends the multi-modal real-time biological data to the feature matching module;
the characteristic matching module is used for identifying and matching the identity characteristics of detection personnel, and the working process specifically comprises the following steps:
step S1: acquiring multi-modal preset biological data and multi-modal real-time biological data of a detector, and comparing the multi-modal real-time biological data with the multi-modal preset biological data;
step S2: comparing the two groups of face information of the detected person;
and step S3: comparing the current external distance between the two canthi with a preset external distance between the two canthus, entering the next step if the external distances between the two canthus are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
and step S4: comparing the length width of the current head with the preset length width of the head, entering the next step if the length width of the head is the same, and otherwise, continuing the comparison until the matching failure signal is generated in failure;
step S5: comparing the current distance between the two ears with a preset distance between the two ears, entering the next step if the distances between the two ears are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S6: comparing the current mouth angle interval with a preset mouth angle interval, entering the next step if the mouth angle intervals are the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current fingerprint information and preset fingerprint information, entering the next step if the fingerprint information is the same, and otherwise, continuing to compare until a matching failure signal is generated in failure;
step S7: acquiring current iris information and preset iris information, if the iris information is the same, generating a matching success signal, otherwise, continuously comparing until a matching failure signal is generated in a failure mode;
the characteristic matching module feeds back a matching success signal or a matching failure signal to the server;
if the server receives the matching success signal, the user terminal logs in successfully;
and if the server receives the matching failure signal, the user terminal fails to log in.
3. The system of claim 2, wherein the multi-modal breast health test system comprises fingerprint information, face information and iris information of the test person;
the face information includes the extraocular distance, the head length width, the two-ear distance, and the mouth angle distance.
4. The system of claim 1, wherein the real-time monitoring data is real-time breast size, real-time breast number and real-time pain rate per unit time of the examiner.
5. The multimodal breast health detection system according to claim 1, wherein the real-time monitoring data specifically comprises the following steps:
acquiring corresponding preset breast monitoring data according to personal information of a detector;
the preset mammary gland monitoring data comprise a mammary gland standard specification, a mammary gland standard number and an upper limit value of pain times in unit time;
acquiring real-time specifications of the mammary gland of a detector, and comparing the real-time specifications of the mammary gland with preset specifications of the mammary gland to obtain a mammary gland specification difference value of the detector; acquiring the real time number of the mammary gland of a detector, and comparing the real time number of the mammary gland with the standard number of the mammary gland to obtain a mammary gland number difference value of the detector; acquiring real-time pain times of a detection person in unit time, and calculating a difference value between the real-time pain times and an upper limit value of the pain times to obtain a pain time difference value of the detection person in unit time;
calculating to obtain a state deviation value of the detection personnel;
the mammary gland standard number is an interval range and comprises an upper mammary gland standard limit number and a lower mammary gland standard limit number, the real-time number of mammary glands is respectively calculated as a difference value with the upper mammary gland standard limit number and the lower mammary gland standard limit number, and then the two groups of mammary glands are added and summed to obtain an average value, so that the mammary gland number difference value of the detection personnel can be obtained.
6. The system of claim 1, wherein the setting process of the level setting module is as follows:
and comparing the state deviation value with a state deviation threshold value, and judging the detection level of the detection personnel to be a third detection level, a second detection level or a first detection level.
7. The system according to claim 1, wherein the detection strength set by the server is as follows:
if the detection level is the first detection level, setting N1 detection times for the detector;
if the detection level is the second detection level, setting N2 detection times for the detection personnel;
if the detection level is the third detection level, setting the detection times for the detector for N3 times; wherein N1, N2 and N3 are fixed numerical values and are normal numbers, and N3 is more than N2 and less than N1.
8. The system of claim 1, wherein the model building module is configured to perform the following steps:
step S1: acquiring real-time monitoring data of different crowds to obtain real-time specifications of mammary glands, real-time number of mammary glands and real-time pain times in unit time of the different crowds;
step S2: sequentially traversing real-time specifications, real-time times of mammary glands and real-time pain times in unit time of different crowds to obtain real-time maximum specifications, real-time minimum specifications, real-time upper limit numbers, real-time lower limit numbers, real-time upper limit times of mammary glands and real-time lower limit times of mammary glands of different crowds;
and step S3: respectively removing the maximum value and the minimum value in real-time specification and real-time number of mammary glands, and adding a plurality of real-time specifications of mammary glands and taking an average value to obtain the optimal mammary gland specification of different people;
adding the specifications of the real-time numbers of the multiple mammary glands, and taking an average value to obtain the optimal number of the mammary glands of different people;
the real-time pain lower limit times in a plurality of unit time are used as the optimal pain times in unit time of different crowds;
and step S4: the optimal mammary gland specification, the optimal number of mammary glands and the optimal pain times in unit time form mammary gland detection models of different people.
9. The system of claim 1, wherein the comparing process of the detecting and comparing module is as follows:
step P1: substituting real-time breast monitoring data of a detector into a breast detection model according to the detection times;
step P2: comparing the real-time specification of the mammary gland during each detection with the optimal specification of the mammary gland, comparing the real-time number of the mammary gland during each detection with the optimal number of the mammary glands, and comparing the real-time pain frequency in unit time during each detection with the optimal pain frequency in unit time;
step P3: if the real-time specification of the mammary gland is within the error range of the optimal mammary gland specification, no operation is performed;
if the real-time specification of the mammary gland is not within the error range of the optimal mammary gland specification, entering the next step;
step P4: if the real time number of the mammary gland is within the error range of the optimal mammary gland number, no operation is carried out;
if the real number of the mammary glands is within the error range of the optimal number of the mammary glands, entering the next step;
step P5: if the real-time pain times in the unit time are within the error range of the optimal pain times in the unit time, no operation is performed;
and if the real-time pain times in the unit time are not within the error range of the optimal pain times in the unit time, generating a mammary gland abnormal signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211281266.9A CN115588509B (en) | 2022-10-19 | 2022-10-19 | Multi-mode breast health detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211281266.9A CN115588509B (en) | 2022-10-19 | 2022-10-19 | Multi-mode breast health detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115588509A true CN115588509A (en) | 2023-01-10 |
| CN115588509B CN115588509B (en) | 2023-05-02 |
Family
ID=84779239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211281266.9A Active CN115588509B (en) | 2022-10-19 | 2022-10-19 | Multi-mode breast health detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115588509B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2473138A1 (en) * | 1998-11-25 | 2000-05-25 | Rubicor Medical Inc. | Breast stabilization devices and imaging and interventional methods using same |
| CN108720814A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health remote supervision system and method |
| CN109620147A (en) * | 2018-11-29 | 2019-04-16 | 深圳市衣信互联网科技有限公司 | A kind of monitoring mammary gland early warning system and its monitoring method based on NFC |
| CN112764515A (en) * | 2020-12-31 | 2021-05-07 | 深圳阜时科技有限公司 | Biological characteristic recognition device and electronic equipment |
| WO2021218340A1 (en) * | 2020-04-30 | 2021-11-04 | 中山大学孙逸仙纪念医院 | Breast lesion malignancy risk model for predicting dense breast, and method for constructing breast lesion malignancy risk model |
| CN114159099A (en) * | 2021-11-08 | 2022-03-11 | 中国医学科学院北京协和医院 | Mammary gland ultrasonic imaging method and equipment |
| CN115002397A (en) * | 2022-06-07 | 2022-09-02 | 上海杏丽林医疗科技有限公司 | Remote auditing and consultation system based on medical images |
-
2022
- 2022-10-19 CN CN202211281266.9A patent/CN115588509B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2473138A1 (en) * | 1998-11-25 | 2000-05-25 | Rubicor Medical Inc. | Breast stabilization devices and imaging and interventional methods using same |
| CN108720814A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health remote supervision system and method |
| CN109620147A (en) * | 2018-11-29 | 2019-04-16 | 深圳市衣信互联网科技有限公司 | A kind of monitoring mammary gland early warning system and its monitoring method based on NFC |
| WO2021218340A1 (en) * | 2020-04-30 | 2021-11-04 | 中山大学孙逸仙纪念医院 | Breast lesion malignancy risk model for predicting dense breast, and method for constructing breast lesion malignancy risk model |
| CN112764515A (en) * | 2020-12-31 | 2021-05-07 | 深圳阜时科技有限公司 | Biological characteristic recognition device and electronic equipment |
| CN114159099A (en) * | 2021-11-08 | 2022-03-11 | 中国医学科学院北京协和医院 | Mammary gland ultrasonic imaging method and equipment |
| CN115002397A (en) * | 2022-06-07 | 2022-09-02 | 上海杏丽林医疗科技有限公司 | Remote auditing and consultation system based on medical images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115588509B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104424385B (en) | A kind of evaluation method and device of medical image | |
| CN110600109B (en) | Diagnosis and monitoring comprehensive medical system with color image fusion and fusion method thereof | |
| US20110306894A1 (en) | Systems, methods and apparatus for acquiring and managing patient/subject data | |
| CN111643118B (en) | New coronary pneumonia risk prompting device and system based on ultrasonic imaging | |
| CN105943020B (en) | A kind of 6 lead misconnection detecting system of cardiac electric axis and method | |
| CN103886204B (en) | Data storage device and date storage method | |
| CN112435726B (en) | Health management system based on portable health monitoring equipment | |
| CN115050435A (en) | Clinical trial data management system and method based on big data | |
| CN106951676A (en) | A kind of medical clinical laboratory laboratory sample management system | |
| CN107456239A (en) | Bed conversion method, apparatus and Bed conversion system | |
| WO2021120737A1 (en) | St detection method and apparatus, computer device, and storage medium | |
| CN115588509A (en) | Multi-mode mammary gland health detection system | |
| CN113274025B (en) | Adjusting system and method based on pelvic floor muscle symmetry test | |
| CN105726016B (en) | Electrocardio output method and device | |
| CN111554394A (en) | Surgical operation control method and system based on block chain technology and readable storage medium | |
| CN113974636B (en) | Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method | |
| CN105380632B (en) | Bio-identification robot system with high safety performance | |
| CN113961902A (en) | Household skill level authentication method, equipment and medium | |
| CN109416940B (en) | System for determining user-centric therapy data | |
| CN221129865U (en) | Special blood flow dynamic detection system of physical examination branch of academic or vocational study | |
| CN111067506A (en) | VR game physiological information acquisition device and method | |
| CN117918951B (en) | Method for determining puncture time based on respiration monitoring and related products | |
| US20240055091A1 (en) | Method for calculating a degree of fatigue | |
| CN108108702A (en) | The testimony of a witness unifies information development system in a kind of examination management | |
| CN116242505A (en) | Medical system electronic body temperature measurement system based on Internet of things technology |
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 |