CN114468996A - Method for analyzing breast signs based on orderliness, multimodality and symmetry deficiency - Google Patents
Method for analyzing breast signs based on orderliness, multimodality and symmetry deficiency Download PDFInfo
- Publication number
- CN114468996A CN114468996A CN202111562362.6A CN202111562362A CN114468996A CN 114468996 A CN114468996 A CN 114468996A CN 202111562362 A CN202111562362 A CN 202111562362A CN 114468996 A CN114468996 A CN 114468996A
- Authority
- CN
- China
- Prior art keywords
- sign
- specific
- abnormal
- data
- breast
- 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
- 210000000481 breast Anatomy 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000007812 deficiency Effects 0.000 title claims description 6
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 230000008859 change Effects 0.000 claims description 136
- 230000002159 abnormal effect Effects 0.000 claims description 91
- 230000033764 rhythmic process Effects 0.000 claims description 61
- 238000012790 confirmation Methods 0.000 claims description 37
- 239000011159 matrix material Substances 0.000 claims description 36
- 210000005075 mammary gland Anatomy 0.000 claims description 29
- 238000013507 mapping Methods 0.000 claims description 24
- 238000013210 evaluation model Methods 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 16
- 230000008030 elimination Effects 0.000 claims description 14
- 238000003379 elimination reaction Methods 0.000 claims description 14
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000012351 Integrated analysis Methods 0.000 claims description 2
- 210000004293 human mammary gland Anatomy 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 4
- 206010006187 Breast cancer Diseases 0.000 abstract description 3
- 208000026310 Breast neoplasm Diseases 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 230000005856 abnormality Effects 0.000 description 19
- 238000004364 calculation method Methods 0.000 description 8
- 206010028980 Neoplasm Diseases 0.000 description 6
- 238000005065 mining Methods 0.000 description 6
- 201000011510 cancer Diseases 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000007717 exclusion Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000003325 tomography Methods 0.000 description 2
- 208000005623 Carcinogenesis Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000030270 breast disease Diseases 0.000 description 1
- 230000036952 cancer formation Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001020 rhythmical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/43—Detecting, measuring or recording for evaluating the reproductive systems
- A61B5/4306—Detecting, measuring or recording for evaluating the reproductive systems for evaluating the female reproductive systems, e.g. gynaecological evaluations
- A61B5/4312—Breast evaluation or disorder diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a method for analyzing breast signs based on orderliness, multimodality and symmetry defects, which collects various sign data including but not limited to the temperature, humidity and the like of breasts through sensors arranged on the breasts. Since breast cancer cells cause changes in their respective signs, these subtle changes are easily masked by noise generated by various human activities or different states, and it is difficult to perform accurate analysis using only a single sign data, such as temperature. By collecting various physical sign data, the invention correspondingly establishes various analysis modes, and can more accurately and effectively analyze different modes.
Description
Technical Field
The invention relates to a method for analyzing the physical signs of mammary gland, in particular to a method for analyzing the physical signs of mammary gland based on orderliness, multimodality, symmetry deficiency and the like.
Background
Breast diseases, especially breast cancer, have a high incidence rate in female malignancies. However, the cure rate of early-stage breast line cancer can be as high as 95%. Early detection, diagnosis and treatment can be realized through early breast line cancer screening so as to reduce the mortality rate of breast line cancer. The current common screening method comprises 1. the clinical breast line examination (CBE) CBE is simple, convenient and easy, has strong repeatability, but has low sensitivity and is greatly influenced by subjective factors; 2. the BUS (Breast ultrasound imaging) can well display the characteristics of breast line lumps, can identify the palpable lumps which cannot be seen on an X-ray, can also be used for women which are not suitable for mammogram and MAM examination (such as young women, pregnant women and the like), and is also suitable for dense breast lines. 3. The mammary line magnetic resonance imaging (Breast MRI) MR imaging technology has the characteristics of excellent soft tissue resolution, no radiation and the like, has unique advantages for mammary line examination, and particularly greatly improves the mammary line MR image quality and the diagnosis level along with the development and application of a special mammary line coil and a rapid imaging sequence; 4. the digital breast line tomosynthesis technology (DBT) is a high-grade application based on a flat panel detector technology, is a novel tomography technology developed by combining a digital image processing technology on the basis of the traditional tomography principle, quickly collects breast lines through a series of different angles, obtains small dose projection data under different projection angles, and retrospectively reconstructs an X-ray density image of any depth layer of the breast lines parallel to the plane of the detector.
However, the biggest defect of the above screening methods is that women have to go to a hospital for examination, and the examination cost is high. In addition to genetic testing, there is a risk of missed screening of dense breast in other imaging examination techniques. In recent years, further studies on the mammary gland cancer have revealed that the rhythm of the mammary gland cell sign is abnormal due to the presence of mammary gland cancer cells. By comparing the difference between the pattern of rhythmic changes in cancerous tissue and healthy tissue, the risk of carcinogenesis in the mammary gland cells can be monitored. However, there are technical barriers to how to continuously and accurately monitor changes in signs of milk line cells, including the fact that human body signs have a change cycle, changes in signs caused by different physiological states, adaptation between a sign measuring device and a human body, and other factors.
Disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, the present invention provides a method for analyzing breast signs based on orderliness, multimodality and symmetry deficiency, which analyzes and processes the measured sign data by combining various mathematical models, so as to analyze and obtain the time-varying law of the sign of the breast from a large amount of sign data with measurement noise.
In order to realize the purpose, the invention provides the following technical scheme:
a method for analyzing breast signs based on orderliness, multimodality and symmetry defects comprises the steps of arranging a plurality of sign data sensors at a breast part of an evaluation object, and continuously acquiring a plurality of sign data of the breast part in a specified time interval through the sign data sensors;
respectively carrying out primary analysis on the acquired sign data and endowing each sign numerical value of each kind of sign data with a corresponding weight value;
the following analysis steps are performed separately for each vital sign data:
s1-1, establishing a standard rhythm model according to the physical signs corresponding to the human mammary gland under normal conditions, and performing fitting operation on the physical sign data endowed with the weight value and a physical sign change equation corresponding to the standard rhythm model to obtain a specific physical sign change equation and/or a specific physical sign change curve of the mammary gland of the evaluation object;
s1-2, establishing an abnormal rhythm model according to the mammary gland signs under abnormal conditions, and searching whether the abnormal confirmation characteristics of the specified signs in the abnormal rhythm model exist in the specific sign change equation or the specific sign change curve of the mammary gland of the evaluation subject and/or the abnormal elimination characteristics of the specified signs in the abnormal rhythm model exist.
Preferably, the specific steps of finding abnormal confirmation features of whether the specified signs in the corresponding abnormal rhythm model exist in a plurality of specific sign change equations or specific sign change curves of the mammary gland of the evaluation subject are as follows:
selecting a physical sign, and searching abnormal confirmation characteristics of the specified physical sign in the abnormal rhythm model corresponding to the physical sign in a specific physical sign change equation or a specific physical sign change curve corresponding to the physical sign;
if the abnormal confirmation feature corresponding to the physical sign is found, searching whether the abnormal confirmation feature of the specified physical sign in the abnormal rhythm model corresponding to the other physical sign exists in a specific physical sign change equation or a specific physical sign change curve corresponding to the other physical sign in a specified time window corresponding to the abnormal confirmation feature;
repeating until the abnormal confirmation characteristics of all the signs are found.
Preferably, the characteristic sign change equation of the breast of the evaluation subject is subjected to fitting operation with a standard rhythm model to obtain corresponding parameter values of the equation; and establishing an evaluation model according to the change of the breast physical signs under the abnormal condition, inputting the parameter values into the evaluation model for operation, and outputting the result.
Preferably, the physical sign measuring devices are respectively and symmetrically placed on the surfaces of breasts at two sides of the human body; each sign measuring device is at least provided with two similar sign sensors, each sign sensor independently collects sign data of the sign sensor, and a specific sign change equation and/or a specific sign change curve corresponding to the sign sensor are established.
Preferably, the specific sign change equation or the specific sign change curve obtained from the feature data collected by the same sign sensor in the same designated time interval in different rhythm periods is compared, and the comparison value is input to the evaluation model as an input value for operation.
Preferably, the specific sign change equation or the specific sign change curve corresponding to different sign sensors of the breast on the same side are compared to obtain a corresponding contrast value at a certain time or an integral contrast value in a certain specified time interval, and the contrast values are input to the evaluation model as input values for operation.
Preferably, specific sign change equations or specific sign change curves corresponding to the sign sensors corresponding to the positions of the breasts on both sides are compared to obtain a contrast value corresponding to a certain moment or an integral contrast value of a certain specified time interval, and the contrast values are input to the evaluation model as input values for operation.
Preferably, before the specific physical sign change equation or the characteristic physical sign change curve is compared with the abnormal rhythm model, the intelligent ordered multi-modal dynamic mapping operation is performed on the specific physical sign change equation or the characteristic physical sign change curve, so that the specific physical sign change equation or the characteristic physical sign change curve is mapped into the abnormal rhythm model.
Preferably, before comparing the plurality of specific sign change equations or characteristic sign change curves, the intelligent ordered multi-modal dynamic mapping operation is performed on the specific sign change equations or characteristic sign change curves, so that the plurality of specific sign change equations or characteristic sign change curves are mapped with each other.
Preferably, the assignment method of the weight value is as follows: comparing the currently acquired sign data with historically acquired sign data, and calculating the change trend and the change rate of the current sign data relative to the historical sign data; assigning a higher weight value to the sign data with increased variation trend, and assigning a lower weight value to the sign data with reduced variation trend; and giving a higher weight value to the sign data with a smaller change rate, and giving a lower weight value to the sign data with a larger change rate.
Preferably, the method for finding the abnormal confirmation feature and/or abnormal elimination feature of the specified physical sign in the abnormal rhythm model in the specific physical sign change equation or the specific physical sign change curve is as follows:
collecting relevant physical sign data of a mammary gland under a normal condition and mammary gland physical sign data under an abnormal condition to respectively establish a standard rhythm model and a database of an abnormal rhythm model; establishing a corresponding data matrix for the ordered data of each sign acquired by the evaluation object, and establishing data windows with different lengths by a parameterized method; comparing the data window with a database of corresponding standard rhythm models and abnormal rhythm models, calculating a similarity value, and finding out abnormal confirmation features and/or abnormal elimination features;
and performing ordered multi-sign integrated analysis on the analysis results of different signs, distinguishing whether the related signs belong to dependent variables or independent variables, and calculating the time ordered intervals among the related signs for the dependent variables.
Preferably, the intelligent ordered multi-modal dynamic mapping operation is to perform mapping operation on each sign data acquired by the evaluation subject and corresponding abnormal confirmation features or abnormal elimination features in the standard rhythm model and the abnormal rhythm model, so that the change rate and the amplitude of the sign data are adapted to the corresponding abnormal confirmation features or abnormal elimination features.
Preferably, the intelligent ordered multi-modal dynamic mapping operation is to perform mapping operation on a specific sign change equation and/or a specific sign change curve to be compared, so that the change rate and the amplitude of the specific sign change equation and/or the specific sign change curve are adapted.
The invention has the beneficial effects that: the sensors disposed on the breast collect a variety of vital data including, but not limited to, breast temperature, humidity, etc. Since breast cancer cells cause changes in their respective signs, these subtle changes are easily masked by noise generated by various human activities or different states, and it is difficult to perform accurate analysis using only a single sign data, such as temperature. By collecting various physical sign data, the invention correspondingly establishes various analysis modes, and can more accurately and effectively analyze different modes.
Drawings
The invention is further described below with reference to the accompanying drawings:
FIG. 1 is a diagram showing the analysis of specific sign change curves to find out repeating abnormal features;
FIG. 2 is a diagram showing data block mining in an intelligent ordered multi-modal dynamic mapping operation;
FIG. 3 is a transformation matrix of an intelligent ordered multi-modal dynamic mapping operation method
And a presentation graph of the path plan;
FIG. 4 is a diagram showing a multi-modal analysis method;
fig. 5 is a diagram showing a comparison of homogeneous sign data of different breasts.
Detailed Description
The order mentioned in the invention means that various physical sign data of a human body, especially a mammary gland, can present certain periodicity along with time, and the appearance sequence of partial physical signs also has a sequential relation, and the periodic physical sign data comprises the physical signs of the human body in a normal state and the physical signs of the human body in an abnormal state. Through the analysis of the orderliness, whether the physical signs in the abnormal state exist can be found out.
The multi-mode is that different physical sign data of a human body are collected through different sensors, and multiple analysis modes are correspondingly established. Because each mode has unique orderliness, different modes can generate corresponding abnormal characteristics when an abnormal state occurs, the occurrence sequence of partial modes has a precedence relationship, and the accuracy of abnormal judgment can be effectively improved by jointly analyzing the abnormal characteristics of a plurality of modes.
The analytical method for the multiple modalities is as follows:
firstly, different physical sign data of human body are collected through different sensors, and a plurality of analysis modes are correspondingly established, namely, a specific physical sign change equation or a physical sign change curve is respectively established for different physical sign data,
then, one physical sign is selected, and abnormal confirmation characteristics of the specified physical sign in the abnormal rhythm model corresponding to the physical sign are searched in the specific physical sign change equation or the specific physical sign change curve corresponding to the physical sign. If the abnormal confirmation feature corresponding to the physical sign is found, the possibility of abnormality is indicated. But the judgment is carried out only by one mode, and the accuracy rate is relatively low.
Then, another physical sign needs to be analyzed and judged, and whether the abnormal confirmation feature of the specified physical sign in the abnormal rhythm model corresponding to the another physical sign exists in the specific physical sign change equation or the specific physical sign change curve of the another physical sign is searched within the specified time window corresponding to the abnormal confirmation feature of the previous physical sign. If the abnormal confirmation feature of the other physical sign cannot be found, the abnormal confirmation feature means that the probability of abnormality is reduced. Conversely, if a corresponding abnormality confirmation feature is also found in another sign, the probability of an abnormality increases. And so on until the abnormal confirmation features of all the signs are searched. That is, in different modalities, the more corresponding abnormality confirmation features are always found by different sign data, the higher the probability of evaluating the existence of abnormality in the mammary gland is; otherwise, the lower the probability. Through multi-mode analysis, the accuracy of judgment can be greatly improved.
For the mammary gland, current multimodalities can include the following human signs: the above modalities should also include physical sign data collected by the same type of sensors at different positions in the same period or different periods, physical sign data collected by different types of sensors at the same position in the same period or different periods, and the like.
The symmetry generally means that the body sign data of the human body are ordered in a normal state, i.e. a non-abnormal state, i.e. the characteristic data are symmetric in a corresponding period. For the mammary gland, the sign data collected from a pair of mammary glands in the same period is also symmetrical. In addition, the sign data collected from the same breast during the same time period, e.g., from 01:00 to 04:00 a.m., but at different time intervals, e.g., from three months to a year, are also symmetrical. However, in an abnormal state, if one mammary gland is abnormal, the above symmetrical sign data will be asymmetrical, resulting in a lack of symmetry. Mammary glands in different rhythm periods can be generated, and the basis for judging whether the abnormality occurs or not can be also obtained by analyzing the lack of symmetry.
For convenient and real-time continuous collection of the physical sign data of the mammary gland part, the corresponding physical sign sensor can be arranged in the bra, so that a user can wear the bra at any time and collect the data in real time. The collected data can be sent to a server and the like for processing and analysis in a wireless connection mode and the like. Considering factors such as wearing comfort, the sensor cannot be in close contact with the breast at all times, and for example, the movement or posture change of the user may cause the sensor to be separated from the surface of the breast, thereby causing errors or even errors in the acquired data. Therefore, the collected sign data are subjected to preliminary analysis, and each sign numerical value is endowed with a corresponding weight value.
It is considered that the normal human body sign data has limited change amplitude in one rhythm period and relatively small change rate in a short time interval. Therefore, the weight value of the collected physical sign data can be assigned according to the rule, the influence degree of the physical sign data on subsequent data processing is judged or determined according to the height of the weight value, generally speaking, the data with high weight value is relatively reliable or accurate data, and conversely, the data with errors or errors is low weight value. The assignment rule of the weight values is as follows: comparing the currently acquired physical sign data with the previously acquired physical sign data, and calculating the change trend and the change rate of the current physical sign data relative to the previously acquired physical sign data; endowing the sign data with increased variation trend with a higher weight value, and endowing the sign data with reduced variation trend with a lower weight value; and giving a higher weight value to the sign data with a smaller change rate, and giving a lower weight value to the sign data with a larger change rate.
Because various physical signs of the human body are ordered in the corresponding rhythm cycle, namely the physical signs in a certain rhythm cycle of the human body under normal conditions can be collected, a standard rhythm model of the physical signs is established, then the physical sign data to be analyzed which is sampled in real time and given with weight values is fitted with the standard rhythm model,
in the middle of
For fitting the function, it is possible to use, but not limited to, fourier transform, gaussian mixture model, wavelet transform, cosine fit, sine fit, etc.,
in the form of a time series of numbers,
the data series of the physical signs is a series of data,
in order to fit the relevant parameters to the model,
is an error value. And (3) fitting through a rhythm model to obtain a specific sign change equation and/or a specific sign change curve of the mammary gland of the evaluation subject. The specific sign change equation or specific characteristic change curve is used for subsequent analysis, and the equation or the curve is searchedWhether the characteristic of the anomaly is present.
Similarly, the signs of the body tissues that produce the abnormality show an order in the corresponding rhythm cycles, and for this reason, the abnormal rhythm model can also be established for the breast signs under abnormal conditions. And there will typically be some abnormal features in the abnormal rhythm model, as will be features for excluding abnormalities. And comparing the specific sign change equation or the specific characteristic change curve with the abnormal rhythm model and searching whether the abnormal confirmation characteristic exists in the specific sign change equation or the specific characteristic change curve. The abnormality exclusion feature is also found by finding an abnormality in a specific sign change equation or a specific characteristic change curve.
In view of the huge amount of various kinds of physical sign data obtained by continuous sampling, a large amount of data calculation is required in the above analysis and determination process. In order to improve the operation speed and the operation precision, the inventor also designs an evaluation model through a computer, and the evaluation model adopts an artificial neural network for operation. And performing fitting operation on the characteristic sign change equation of the mammary gland of the evaluation object and the standard rhythm model to obtain corresponding parameter values, abnormality confirmation characteristics, abnormality elimination characteristics and the like of the equation, wherein the corresponding parameter values, the abnormality confirmation characteristics, the abnormality elimination characteristics and the like are used as input of the evaluation model, and the operation result is output through the operation of the evaluation model.
The physical sign measuring devices are respectively and symmetrically placed on the surfaces of breasts at two sides of the human body; each sign measuring device is at least provided with two similar sign sensors, each sign sensor independently collects sign data of the sign sensor, and a specific sign change equation and/or a specific sign change curve corresponding to the sign sensor are/is established. The symmetry break description as described above includes various situations, such as comparison of similar physical sign data obtained from different positions of a breast, comparison of similar physical sign data of different breasts (as shown in fig. 5), and comparison of feature data of the same physical sign sensor in the same designated time interval in different rhythm cycles, so as to determine whether there is symmetry break. In a comparison manner of
In the middle of
In order to obtain a contrast value,
is as follows
The weight of each of the factors is determined,
，
a start time is specified for the comparison calculation,
an end time is specified for the comparison calculation,
in order to be a function of the comparison,
for the array of vital sign data, time-specific data may be assigned to both breasts or to the same breast. Therefore, specific sign change equations or specific sign change curves corresponding to different sign sensors of the breast on the same side need to be compared to obtain a corresponding contrast value at a certain moment or an integral contrast value in a certain specified time interval, and the contrast values are input to the evaluation model as input values for operation. Similarly, the specific sign change equation or the specific sign change curve corresponding to the sign sensors corresponding to the positions of the breasts on both sides need to be compared to obtain a contrast value corresponding to a certain time or an integral contrast value of a certain specified time interval, and the contrast values are input to the evaluation model as input values for calculation.
In addition, whether the same kind of physical sign data of the same breast in different rhythm cycles has symmetry defects or not should be determined, that is, specific physical sign change equations or specific physical sign change curves obtained by feature data collected by the same physical sign sensor in the same designated time interval in different rhythm cycles are compared, and the comparison value is input to the evaluation model as an input value for operation.
In order to quickly and accurately find whether the specific sign change equation or the specific sign change curve has the abnormality confirmation characteristic and the abnormality elimination characteristic, the invention also provides a corresponding comparison and search method, which can be implemented by but not limited to the following modes:
s2-1, establishing a sign data matrix for the sign data with the weighted values according to the time sequence T, wherein
；tnThe sign data are sampled at the moment, and n is the data number of the matrix and a positive integer;
s2-2, extracting m individual sign data in sequence from the ith position of the sign data matrix to form a data window with the length of m,
wherein i and m are positive integers, i is more than or equal to 1 and less than or equal to n-m +1, and m is more than or equal to n;
s2-3, the data of the data window and the sign data with the length of m corresponding to the beginning of the jth position in the sign data matrix
Calculating the similarity value, moving the data window from the jth position backwards and calculating to obtain a distance similarity matrix
Wherein d isi，jIs Ti，mAnd Tj，mThe calculated value of the similarity is smaller and more similar, wherein j is a positive integer, and j is more than or equal to 1 and less than or equal to n-m + 1;
s2-4, moving the data window from the first sign data of the sign data matrix to the (n-m + 1) th sign data, taking out the minimum value of each distance matrix, and obtaining the minimum distance matrix
Wherein
Is the distance similarity matrix, min: (
) Is composed of
Minimum value of (1). Obtaining repeated features in the sign data matrix through the minimum distance matrix; obtaining repeated features in the sign data matrix through the minimum distance matrix;
s2-5, comparing and/or confirming the repeated characteristics with the abnormity confirmation characteristics and/or the abnormity elimination characteristics.
S2-6, performing ordered multi-sign integration analysis on the analysis results of different signs, distinguishing whether the related signs belong to dependent variables or independent variables, and calculating the time ordered distance theta between the related signs for the dependent variables, namely the designated time window mentioned above.
The following detailed analysis of the above comparison and search method is made by specific examples:
the following is an example of the above-described systematic independent factor intelligent modal data analysis, as described in S2-1 and S2-2, and the following table is given as n =12, m =4, i =2, and the data window is T2，4The case (1);
and as described in S2-3, comparing the sign data T1, 4 with j =1 position and m =4 length with the data window T2, 4 to calculate a distance similarity matrix
The following table;
as described in S2-4, the minimum distance matrix is
The following table:
where figure 1 is a specific practical case of finding repetitive features within data according to the method described above.
The above repeat features are compared and/or validated against the abnormality confirmation feature and/or the abnormality exclusion feature as described in S2-5.
Then, as described in S2-6, based on the results of the different systematic independent factor intelligent modal data analysis, an ordered multi-factor intelligent integration analysis is performed to assign the factors as dependent variables or independent variables, and calculate the time ordered distance θ between the related factors for the dependent variables.
Considering that, the change rates of the same kind of physical sign data of different lateral breasts may be different, and the change rates of the same kind of physical sign data of different users are certainly different, which may cause a problem when comparing the standard rhythm model, the abnormal rhythm model, the specific physical sign change equation of a certain user or the specific characteristic change curve with each other. Therefore, before comparison, intelligent ordered multi-modal dynamic mapping operation needs to be performed on a specific sign change equation or a specific characteristic change curve, the algorithm aims to perform modal approximate comparison on large data of a large amount of collected human body sign data, and relates to data obtained by comparing and mining a standard rhythm model and an abnormal rhythm model with data to be subjected to modal comparison, the algorithm judges and finds whether a data set containing the abnormal rhythm model is contained in the data to be subjected to modal mining in an intelligent and effective mode and performs screening mining, the algorithm allows different speeds and wave amplitudes in the mapping comparison process but the same modes, such as fig. 3, the approximate modes are intelligently mined from the data in a dynamic mapping mode in an algorithm mode, and a related data block mining method can be obtained by calculation by using the following method, but is not limited to the following method, and the following method is used for performing detailed solution on the intelligent ordered multi-modal dynamic mapping operation method in a specific embodiment mode The assay can be performed, but is not limited to, in the following manner:
s3-1, after weight value assignment operation is carried out on the sign data number related to multiple modes, a specific sign change equation and/or a specific sign change curve are established, the equation/model/matrix to be subjected to intelligent ordered multi-mode dynamic mapping operation is converted into matrixes respectively, and a mapped matrix is formed
Wherein the length of the mapped matrix is q; the mapping matrix of one mode f corresponding to the relevant physical sign is
Wherein the length of the mapping matrix is p; wherein p and q are positive integers;
s3-2, constructing a p × q matrix B, wherein matrix elements in the matrix B
As elements in the mapped matrix
And elements of the mapping matrix
The contrast value obtained by contrast calculation is obtained; wherein k and l are positive integers
S3-3, mining the minimum distance path matrix in the matrix B according to the following rule
Wherein the u-th element in the minimum distance path matrix G is the x, y-th element in the matrix B, i.e.
And is
: wherein u, v, x, y are positive integers,
is the maximum of p, q
a. The starting point of the excavation path is
The end point of the excavation path is
；
b. If the current path point is
Then the next path point is
And two adjacent points must satisfy the following conditions
And
(ii) a Wherein the content of the first and second substances,
，
is a positive integer
c. The planning calculation of the path also satisfies the condition of selecting the highest approximation value/the lowest distance value in addition to the requirement of b. Where figure 2 illustrates the mechanism of path planning.
d. Forming the matrix elements corresponding to the minimum distance path into a mapped matrix and a mapping relation table between the mapped matrixes, repeating the steps b and c, and calculating the accumulated distance cost by the equation
The path and mode are obtained by calculation
As shown in fig. 2.
When the above mapping operation is applied to multiple modes, the following steps should be performed:
e. modality
The starting time of finding the minimum distance path in the matrix W corresponding to the specific sign change equation and/or the specific sign change curve is
Another modality based on ordering and multi-modality considerations
The modal factors are the following times
The period occurs and is an active modality, the other modality
The comparison method of (2) can be based on steps a, b, c, d, as shown in fig. 4, wherein the modality, i.e., the number of signs
，
，
。
f. Repeating the steps a, b, c, d and e until all the factor modes are calculated, and filling the related calculated values in sequence to form a characteristic number matrix.
Claims (13)
1. A method for analyzing breast signs based on orderliness, multimodality and symmetry deficiency is characterized in that: the method comprises the steps that a plurality of sign data sensors are arranged at a breast part of an evaluation object, and a plurality of sign data of the breast part in a specified time interval are continuously acquired through the sign data sensors;
respectively carrying out primary analysis on the acquired sign data and endowing each sign numerical value of each kind of sign data with a corresponding weight value;
the following analysis steps are performed separately for each vital sign data:
s1-1, establishing a standard rhythm model according to the physical signs corresponding to the human mammary gland under normal conditions, and performing fitting operation on the physical sign data endowed with the weight value and a physical sign change equation corresponding to the standard rhythm model to obtain a specific physical sign change equation and/or a specific physical sign change curve of the mammary gland of the evaluation object;
s1-2, establishing an abnormal rhythm model according to the mammary gland signs under abnormal conditions, and searching whether the abnormal confirmation characteristics of the specified signs in the abnormal rhythm model exist in the specific sign change equation or the specific sign change curve of the mammary gland of the evaluation subject and/or the abnormal elimination characteristics of the specified signs in the abnormal rhythm model exist.
2. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 1, characterized in that:
the specific steps of finding whether abnormal confirmation characteristics of specified signs exist in a plurality of specific sign change equations or specific sign change curves of the mammary gland of the evaluation subject in the corresponding abnormal rhythm model are as follows:
selecting a physical sign, and searching abnormal confirmation characteristics of the specified physical sign in the abnormal rhythm model corresponding to the physical sign in a specific physical sign change equation or a specific physical sign change curve corresponding to the physical sign;
if the abnormal confirmation feature corresponding to the physical sign is found, searching whether the abnormal confirmation feature of the specified physical sign in the abnormal rhythm model corresponding to the other physical sign exists in a specific physical sign change equation or a specific physical sign change curve corresponding to the other physical sign in a specified time window corresponding to the abnormal confirmation feature; repeating until the abnormal confirmation characteristics of all the signs are found.
3. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 1, characterized in that: fitting the characteristic sign change equation of the mammary gland of the evaluation object with a standard rhythm model to obtain corresponding parameter values of the equation; and establishing an evaluation model according to the change of the breast physical signs under the abnormal condition, inputting the parameter values into the evaluation model for operation, and outputting the result.
4. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 1, characterized in that: the physical sign measuring devices are respectively and symmetrically placed on the surfaces of breasts at two sides of a human body; each sign measuring device is at least provided with two similar sign sensors, each sign sensor independently collects sign data of the sign sensor, and a specific sign change equation and/or a specific sign change curve corresponding to the sign sensor are established.
5. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 4, wherein: and comparing a specific sign change equation or a specific sign change curve obtained by characteristic data collected by the same sign sensor in the same appointed time interval in different rhythm periods, and inputting the comparison value serving as an input value into an evaluation model for operation.
6. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 4, wherein: and comparing specific sign change equations or specific sign change curves corresponding to different sign sensors of the breast on the same side to obtain a corresponding contrast value at a certain moment or an integral contrast value in a certain specified time interval, and inputting the contrast value serving as an input value into the evaluation model for operation.
7. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 4, wherein: and comparing specific sign change equations or specific sign change curves corresponding to the sign sensors corresponding to the positions of the breasts at the two sides to obtain a corresponding contrast value at a certain moment or an integral contrast value in a certain specified time interval, and inputting the contrast values serving as input values into an evaluation model for operation.
8. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 1, characterized in that: before the specific sign change equation or the characteristic sign change curve is compared with the abnormal rhythm model, intelligent ordered multi-mode dynamic mapping operation is carried out on the specific sign change equation or the characteristic sign change curve, so that the specific sign change equation or the characteristic sign change curve is mapped into the abnormal rhythm model.
9. The method for breast sign analysis based on ordering, multimodal and symmetry breaking according to claim 5 or 6 or 7, wherein: before comparing a plurality of specific sign change equations or characteristic sign change curves, carrying out intelligent ordered multi-mode dynamic mapping operation on the specific sign change equations or the characteristic sign change curves to enable the plurality of specific sign change equations or the characteristic sign change curves to be mapped with each other.
10. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 1, characterized in that: the weight value assignment method comprises the following steps: comparing the currently acquired sign data with historically acquired sign data, and calculating the change trend and the change rate of the current sign data relative to the historical sign data; assigning a higher weight value to the sign data with increased variation trend, and assigning a lower weight value to the sign data with reduced variation trend; and giving a higher weight value to the sign data with a smaller change rate, and giving a lower weight value to the sign data with a larger change rate.
11. The method for breast sign analysis based on ordering, multimodal and symmetry breaking according to claim 1 or 2, characterized in that: the method for finding abnormal confirmation feature and/or abnormal elimination feature of specified sign in abnormal rhythm model by using specific sign change equation or specific sign change curve is as follows:
collecting related physical sign data of a mammary gland under a normal condition and mammary gland physical sign data under an abnormal condition to respectively establish a database of a standard rhythm model and a database of an abnormal rhythm model; establishing a corresponding data matrix for the ordered data of each sign acquired by the evaluation object, and establishing data windows with different lengths by a parameterized method; comparing the data window with a database of corresponding standard rhythm models and abnormal rhythm models, calculating a similarity value, and finding out abnormal confirmation features and/or abnormal elimination features;
and performing ordered multi-sign integrated analysis on the analysis results of different signs, distinguishing whether the related signs belong to dependent variables or independent variables, and calculating the time ordered intervals among the related signs for the dependent variables.
12. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 8, wherein: the intelligent ordered multi-modal dynamic mapping operation is to perform mapping operation on each sign data acquired by an evaluation object and corresponding abnormal confirmation features or abnormal elimination features in a standard rhythm model and an abnormal rhythm model, so that the change rate and the amplitude of the sign data are adapted to the corresponding abnormal confirmation features or abnormal elimination features.
13. The method for breast sign analysis based on ordering, multimodality and symmetry breaking according to claim 9, wherein: the intelligent ordered multi-modal dynamic mapping operation is to perform mapping operation on a specific sign change equation and/or a specific sign change curve to be compared, so that the change rate and the amplitude of the specific sign change equation and/or the specific sign change curve are adaptive.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562362.6A CN114468996B (en) | 2021-12-20 | 2021-12-20 | Method for analyzing breast signs based on order, multi-mode and symmetry deficiency |
| PCT/IB2022/062441 WO2023119103A1 (en) | 2021-12-20 | 2022-12-19 | Method for analyzing breast signs on basis of orderliness, multiple modalities and symmetry breaking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562362.6A CN114468996B (en) | 2021-12-20 | 2021-12-20 | Method for analyzing breast signs based on order, multi-mode and symmetry deficiency |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114468996A true CN114468996A (en) | 2022-05-13 |
| CN114468996B CN114468996B (en) | 2024-01-23 |
Family
ID=81494448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111562362.6A Active CN114468996B (en) | 2021-12-20 | 2021-12-20 | Method for analyzing breast signs based on order, multi-mode and symmetry deficiency |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114468996B (en) |
| WO (1) | WO2023119103A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023119103A1 (en) * | 2021-12-20 | 2023-06-29 | 香港生物节律研究院有限公司 | Method for analyzing breast signs on basis of orderliness, multiple modalities and symmetry breaking |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6179786B1 (en) * | 1998-10-02 | 2001-01-30 | Profemme Ltd. | System for thermometry-based breast cancer risk-assessment |
| JP2002333444A (en) * | 2001-02-23 | 2002-11-22 | Matsushita Electric Ind Co Ltd | Apparatus and method for gene diagnosis |
| WO2011133431A2 (en) * | 2010-04-16 | 2011-10-27 | New York University | Apparatus, systems, computer-accessible medium and methods for facilitating radio frequency hyperthermia and thermal contrast in a magnetic resonance imaging system |
| CN105686810A (en) * | 2015-07-31 | 2016-06-22 | 上海温尔信息科技有限公司 | A temperature measuring method and device |
| CN105740614A (en) * | 2016-01-28 | 2016-07-06 | 上海温尔信息科技有限公司 | Comparison assessment method and device for humiture field model based on cancer cell abnormality |
| CN105760701A (en) * | 2016-03-22 | 2016-07-13 | 上海温尔信息科技有限公司 | Method and device for capturing abnormal temperature metabolic heat of tumor cells |
| CN108720814A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health remote supervision system and method |
| CN108720812A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health apparatus for evaluating using mammary gland external temperature data |
| US20190290903A1 (en) * | 2018-03-23 | 2019-09-26 | The Board Of Regents Of The University Of Oklahoma | System and Method of Electric-Induced Acoustic Tomography for Electrotherapy Monitoring |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100312136A1 (en) * | 2007-06-22 | 2010-12-09 | Advanced Functional Systems, Llc | Systems and methods for thermographic-guided medical treatment |
| CN108777161A (en) * | 2018-06-19 | 2018-11-09 | 云士康（深圳）智能科技有限公司 | The method for monitoring breast data information using instantaneous distributed image |
| CN109008986A (en) * | 2018-08-21 | 2018-12-18 | 深圳市浓华生物电子科技有限公司 | A kind of chest detection method, electronic equipment and health monitor |
| CN110432866A (en) * | 2019-08-01 | 2019-11-12 | 福州智睿伊科技有限公司 | A kind of system and method based on temperature monitoring Breast health |
| CN114468996B (en) * | 2021-12-20 | 2024-01-23 | 香港生物节律研究院有限公司 | Method for analyzing breast signs based on order, multi-mode and symmetry deficiency |
-
2021
- 2021-12-20 CN CN202111562362.6A patent/CN114468996B/en active Active
-
2022
- 2022-12-19 WO PCT/IB2022/062441 patent/WO2023119103A1/en unknown
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6179786B1 (en) * | 1998-10-02 | 2001-01-30 | Profemme Ltd. | System for thermometry-based breast cancer risk-assessment |
| JP2002333444A (en) * | 2001-02-23 | 2002-11-22 | Matsushita Electric Ind Co Ltd | Apparatus and method for gene diagnosis |
| WO2011133431A2 (en) * | 2010-04-16 | 2011-10-27 | New York University | Apparatus, systems, computer-accessible medium and methods for facilitating radio frequency hyperthermia and thermal contrast in a magnetic resonance imaging system |
| CN105686810A (en) * | 2015-07-31 | 2016-06-22 | 上海温尔信息科技有限公司 | A temperature measuring method and device |
| CN105740614A (en) * | 2016-01-28 | 2016-07-06 | 上海温尔信息科技有限公司 | Comparison assessment method and device for humiture field model based on cancer cell abnormality |
| CN105760701A (en) * | 2016-03-22 | 2016-07-13 | 上海温尔信息科技有限公司 | Method and device for capturing abnormal temperature metabolic heat of tumor cells |
| US20190290903A1 (en) * | 2018-03-23 | 2019-09-26 | The Board Of Regents Of The University Of Oklahoma | System and Method of Electric-Induced Acoustic Tomography for Electrotherapy Monitoring |
| CN108720814A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health remote supervision system and method |
| CN108720812A (en) * | 2018-08-13 | 2018-11-02 | 脱浩东 | A kind of Breast health apparatus for evaluating using mammary gland external temperature data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023119103A1 (en) * | 2021-12-20 | 2023-06-29 | 香港生物节律研究院有限公司 | Method for analyzing breast signs on basis of orderliness, multiple modalities and symmetry breaking |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114468996B (en) | 2024-01-23 |
| WO2023119103A1 (en) | 2023-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Adegun et al. | Deep learning-based system for automatic melanoma detection | |
| CN107330949A (en) | A kind of artifact correction method and system | |
| US20080154154A1 (en) | Internet-based system and a method for automated analysis of tactile imaging data and detection of lesions | |
| WO2019184960A2 (en) | Electrocardio data pathological feature quantitative analysis method and apparatus | |
| US9811904B2 (en) | Method and system for determining a phenotype of a neoplasm in a human or animal body | |
| CN106600585A (en) | Skin condition quantitative evaluation method based on gray level co-occurrence matrix | |
| EP3207521A1 (en) | Image analysis method supporting illness development prediction for a neoplasm in a human or animal body | |
| CN107316334B (en) | Personalized precise magnetic resonance imaging method | |
| CN109745046B (en) | Electrical impedance imaging electrode and system suitable for motion state | |
| CN110575178B (en) | Diagnosis and monitoring integrated medical system for judging motion state and judging method thereof | |
| de Sá Gomes et al. | Scan time, reliability and accuracy of craniofacial measurements using a 3D light scanner | |
| Mohsen et al. | AI aided noise processing of spintronic based IoT sensor for magnetocardiography application | |
| Liu et al. | Detection of heterogeneity on multi-spectral transmission image based on multiple types of pseudo-color maps | |
| CN111887847A (en) | Visceral fat measuring method and device based on human body composition meter, computer equipment and storage medium | |
| WO2023119103A1 (en) | Method for analyzing breast signs on basis of orderliness, multiple modalities and symmetry breaking | |
| CN105232050B (en) | A kind of noninvasive detection device of human body thickness of the tongue coating | |
| JP7252512B2 (en) | ULTRASOUND DIAGNOSTIC APPARATUS, ULTRASOUND DIAGNOSTIC PROGRAM, AND ANALYSIS METHOD OF ULTRASOUND ECHO IMAGE | |
| CN111449638A (en) | Method for constructing three-dimensional pulse picture based on data acquired by sensor and application | |
| Singh et al. | Classification of first trimester ultrasound images using deep convolutional neural network | |
| CN106419884B (en) | A kind of rate calculation method and system based on wavelet analysis | |
| Chiverton et al. | Multiscale Shannon’s entropy modeling of orientation and distance in steel fiber micro-tomography data | |
| KR101843928B1 (en) | Method and apparatus for displaying an analysis result of medical measured data | |
| CN103142223B (en) | Heart magnetic signal processing method based on extreme value difference | |
| CN110507285A (en) | A kind of care device of dermatosis patient | |
| CN105740614A (en) | Comparison assessment method and device for humiture field model based on cancer cell abnormality |
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 |