A breast health data anomaly detection method and system

Abstract

The present application relates to the technical field of health monitoring, in particular to a breast health data anomaly detection method and system, comprising the following steps: extracting an abnormal attribute set based on temperature and conductivity characteristics, screening cross-zone anomalies by analyzing gradient and vector direction, evaluating deviation degree to calibrate anomaly level in combination with conductivity matrix and thermal field characteristics, matching response list and priority sequence, screening partition numbers that need to be adjusted, and outputting breast health repair adjustment partition number list. In the present application, by establishing a partition joint analysis system of temperature trajectory and conductivity response, synchronous analysis and trend capture of multi-source data are realized, and steady-state confirmation of abnormal linkage area is realized. By deviation trend evaluation, the abnormal level division ability is enhanced to cover the range comparison to promote the dynamic adjustment of the repair range, thereby improving the reliability of health state judgment and the accuracy of abnormal positioning, optimizing the sensitivity and consistency of risk assessment, reducing misjudgment and omission, and ensuring that the repair strategy has pertinence and coordination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring, in particular to a breast health data anomaly detection method and system. BACKGROUND

[0002] The technical field of health monitoring involves the continuous collection, analysis and evaluation of various physiological parameters and health data of the human body, aiming to realize real-time monitoring and trend judgment of individual health status through multi-dimensional data sensing. The core matters of this field include sensor data collection technology, physiological signal feature extraction and analysis, health index modeling and abnormal data determination mechanism. Health monitoring technology relies on the collaborative operation of wearable devices, mobile terminals and cloud data platforms to obtain multi-source physiological information such as heart rate, blood pressure, body temperature, blood oxygen and gait, and to realize individual health management, early warning and intervention support through data fusion and statistical analysis means. This field has important research significance in terms of data accuracy, detection sensitivity and optimization of abnormal recognition algorithms.

[0003] Among them, the traditional breast health data anomaly detection method refers to a means of collecting related physiological data on the surface or shallow layer of breast tissue, analyzing its change rule to identify potential health risks. This method is based on the detection of physical quantities such as temperature distribution, tissue conductivity characteristics or acoustic parameters, and uses thermal imaging instruments, ultrasonic probes or electrical impedance measurement devices to obtain data. Subsequently, by using experience threshold comparison, statistical feature extraction or pattern matching, the spatial distribution characteristics, time change trend and difference index of the collected data are analyzed to determine whether the data is abnormal. Traditional methods rely on fixed measurement points and manually set abnormal standards, and reflect the state difference of breast tissue through single parameter changes, lacking comprehensive analysis and dynamic evaluation ability of the correlation between multi-dimensional data.

[0004] Traditional breast health detection relies on single parameter collection and fixed measurement point mode, which cannot simultaneously depict the dynamic correlation of temperature distribution and conductivity characteristics, lacks linkage analysis means between spatial structure information and time sequence changes, leading to the inability to identify cross-regional abnormalities in a timely manner. The fixed threshold judgment method cannot adapt to the data drift caused by individual differences, resulting in significant fluctuations in abnormal determination results. The single feature comparison method cannot present the complex abnormal trend caused by deep tissue changes, the correlation between data cannot be effectively utilized, making the abnormal region boundary fuzzy and the trend inference insufficient. In the face of the demand for multi-source information fusion, there is a risk of recognition lag and misjudgment, which affects the stability and accuracy of breast health evaluation. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to provide a breast health data anomaly detection method and system.

[0006] In order to achieve the above object, the present application adopts the following technical scheme, a breast health data anomaly detection method, comprising the following steps:

[0007] S1: based on the breast tissue surface temperature distribution and the conductivity characteristic, the detection partition is divided, the temperature change trajectory and the conductivity response curve of the partition are extracted, the synchronous abnormal area of the temperature fluctuation interval and the conductivity response mutation point on the time axis is identified, the corresponding partition number and the spatial coordinates are extracted, and the breast partition abnormal attribute set is generated;

[0008] S2: according to the breast partition abnormal attribute set, the temperature gradient direction and the conductivity response vector of the partition are identified, the direction consistency of the two at the partition boundary is analyzed, the partition with connectivity and temperature gradient anomaly is screened out in combination with the connectivity of the partition boundary, and the cross-zone abnormal connectivity data group is formed;

[0009] S3: based on the cross-zone abnormal connectivity data group, the tissue conductivity distribution matrix and the local thermal field characteristics in the partition are extracted, the conductivity uniformity and the thermal field consistency are analyzed, the matching abnormal area is screened out, and the abnormal defect linkage area group is obtained;

[0010] S4: according to the abnormal defect linkage area group, the conductivity distribution trend of the corresponding partition is analyzed, the deviation degree from the original health state curve is evaluated, the abnormal grade of the partition is calibrated according to the deviation amplitude, and the breast health partition detection risk grade evaluation list is output.

[0011] As a further scheme of the present application, the breast partition abnormal attribute set includes temperature mutation partition number, conductivity response abnormal point, partition coordinate mark, time sequence mutation mark, the cross-zone abnormal connectivity data group includes temperature gradient abnormal partition mark, partition boundary connectivity unit, partition junction consistency block, the abnormal defect linkage area group includes conductivity abnormal continuous partition, thermal field irregular area, conductivity performance mutation coincidence area, linkage abnormal partition number, and the breast health partition detection risk grade evaluation list includes risk grade label, partition response deviation value, local conductivity abnormality index and health state deviation grade.

[0012] As a further scheme of the present application, the acquisition step of the breast partition abnormal attribute set is specifically:

[0013] S111: based on the breast tissue surface temperature distribution and the conductivity characteristic, the detection partition is divided, the temperature change trajectory and the conductivity response curve of the partition are extracted, the difference value calculation is carried out on the two kinds of data in the same partition, and the temperature and conductivity response difference degree trend value is obtained;

[0014] S112: According to the temperature and the difference degree of the conductive response trend value, the fluctuation interval in the temperature change curve and the mutation point of the conductive response track are identified, time superposition is carried out on the two types of values, the time interval in which the fluctuation exceeds the preset reference value and the mutation point is located in the set range is extracted, and a high-frequency abnormal interval time period set is generated;

[0015] S113: For the high-frequency abnormal interval time period set, the corresponding partition number and spatial coordinate information are matched, the partition position where the signal occurs is extracted, and a breast partition abnormal attribute set is generated.

[0016] As a further scheme of the present application, the acquisition step of the cross-zone abnormal connectivity data group is specifically:

[0017] S211: The temperature gradient direction and the conductive response vector of the partition in the breast partition abnormal attribute set are identified, the projection track of the two at the partition boundary is extracted, the distribution number and aggregation degree of the boundary point in the partition are identified, and a partition boundary consistency atlas is obtained;

[0018] S212: According to the partition boundary consistency atlas, the boundary region with an aggregation degree higher than the average level is screened, the spatial boundary of the overall structure of the breast is compared, the continuous and belonging to the same partition in the boundary set is identified, and the temperature gradient abnormal division in the breast partition is obtained;

[0019] S213: Based on the temperature gradient abnormal division in the breast partition, the partition boundary consistency, the temperature gradient dispersion, the conductivity uniformity and the conductive response delay are integrated and analyzed, the response block in the partition is matched according to the partition, and the cross-zone abnormal connectivity data group is formed.

[0020] As a further scheme of the present application, the acquisition step of the abnormal defect linkage region group is specifically:

[0021] S311: Based on the cross-zone abnormal connectivity data group, the conductivity distribution matrix and the local thermal field characteristics of the partition in the partition are extracted, the data in the partition are time stamped, the conductivity fluctuation value and the thermal field consistency offset are identified, and a breast local defect response feature set is obtained;

[0022] S312: According to the breast local defect response feature set, the conductivity uniformity and the thermal field consistency in the partition are jointly analyzed, and the formula is used:

[0023] ;

[0024] The conductivity thermal field coupling characteristic value is calculated, the partition unit of the conductivity thermal field coupling degree in the partition is screened, and a conductivity thermal field cooperative response spatial distribution map is established;

[0025] Among them, representing the thermal field coupling characteristic value of the conductivity, representing the conductivity value of the i-th unit, representing the temperature value of the i-th unit, representing the spatial coordinate change amount of the i-th unit in the x-axis direction, representing the spatial coordinate change amount of the i-th unit in the y-axis direction, representing the thermal diffusion coefficient of the material per unit volume, representing the thermal coefficient of the conductivity per unit volume;

[0026] S313: calling the conductivity thermal field cooperative response spatial distribution map, clustering the partitions exceeding the cooperative identification benchmark in the coupling characteristic value partition, marking the partition code and coordinates corresponding to the continuous abnormal area, and obtaining the abnormal defect linkage area group.

[0027] As a further scheme of the present application, the obtaining step of the breast health partition detection risk level evaluation list is specifically:

[0028] S411: According to the abnormal defect linkage area group, extract the partition conductivity performance distribution curve under the specified number, and perform time unified processing to identify the unit time conductivity performance change amount, and obtain the partition conductivity performance abnormal change rate set;

[0029] S412: According to the partition conductivity performance abnormal change rate set, identify the conductivity performance distribution curve of the original health state stage in the original data or the reference data, compare the current conductivity performance change sequence with the reference curve, identify the partition conductivity performance deviation level, extract and mark the partition whose deviation level exceeds the upper limit of the warning, and obtain the deviation sudden increase partition set;

[0030] S413: According to the deviation sudden increase partition set, bind the deviation level value of each partition with the position number in the breast structure spatial map, and use the formula:

[0031] ;

[0032] Calculate the health risk index of the partition, sort according to the risk level, and output the breast health partition detection risk level evaluation list;

[0033] wherein, representing the health risk index of the partition, representing the deviation level value, representing the mean value of the deviation level value of all partitions, representing the standard deviation of the deviation level value of all partitions, representing the spatial distance of the i-th partition position in the breast structure spatial map, representing the spatial distance of the i-th partition position in the breast structure spatial map, representing the spatial distance of the i-th partition position in the breast structure spatial map, a risk weight coefficient of a partition position, representing the total number of involved partition positions.

[0034] As a further scheme of the present application, the method further comprises a step S5 of:

[0035] S5: calling the breast health partition detection risk level evaluation list, identifying the corresponding number of the partition in the breast function map, calling the repair response unit list, comparing the response level and the breast protection priority sequence, screening the partition number that needs to adjust the response coverage, and outputting the breast health repair adjustment partition number list;

[0036] The breast protection priority sequence refers to the order according to the breast function criticality and protection demand.

[0037] The breast health repair adjustment partition number list includes adjustment target partition number, response level adjustment parameter, protection priority comparison item, and linkage response trigger type.

[0038] As a further scheme of the present application, the breast health repair adjustment partition number list is obtained by:

[0039] S511: calling the breast health partition detection risk level evaluation list, extracting the number of the partition in the breast function map, mapping the partition risk level value and the region coordinate boundary, identifying the partition information corresponding to the breast protection level, and generating a breast partition risk distribution map;

[0040] S512: based on the breast partition risk distribution map, extracting the repair response unit number and the response level, matching the partition risk level and the repair response level, identifying the unit number with insufficient response coverage, and obtaining a breast partition response risk disconnection list;

[0041] S513: according to the breast partition response risk disconnection list, according to the level number in the breast protection priority sequence, extracting the key partition number that needs to improve the response coverage, outputting the adjustment control parameter linked with the original repair unit in order, and outputting the breast health repair adjustment partition number list.

[0042] The breast health data anomaly detection system is used to execute the above-mentioned breast health data anomaly detection method, and the system comprises:

[0043] The temperature monitoring module divides the detection partition based on the breast tissue surface temperature distribution and the conductive characteristics, compares the temperature fluctuation range and the conductive response mutation point in the same time period, screens the synchronous abnormal area of the two, extracts the partition number and the spatial coordinates, summarizes the abnormal time period and the partition number, and generates a breast partition abnormal attribute set;

[0044] The partition positioning module identifies the consistency of the temperature gradient direction and the conductive response vector, labels the partition boundary number, matches the overall breast structure diagram, extracts the partition number range of the temperature gradient abnormal area, and establishes the cross-zone abnormal connectivity data group based on the breast partition abnormal attribute set.

[0045] The defect linkage module retrieves the continuity data sequence of the conductivity distribution matrix and the local thermal field characteristics in the region, judges the conductivity abnormal boundary connectivity and the thermal field consistency, marks the partition number that meets the linkage threshold of both, and outputs the abnormal defect linkage area group based on the cross-zone abnormal connectivity data group.

[0046] The conductive early warning module analyzes the deviation trend of the corresponding partition conductivity performance distribution trend and the original health state curve, extracts the partition number of the deviation trend, completes the grade identification according to the risk grading standard, and generates a breast health partition detection risk grade evaluation list.

[0047] The repair optimization module finds the corresponding position number of the risk grade partition in the breast function diagram based on the breast health partition detection risk grade evaluation list, retrieves the current repair response unit configuration list, compares the breast protection priority with the current response level matching situation, selects the partition that needs to be updated, and outputs the breast health repair adjustment partition number list.

[0048] Compared with the prior art, the advantages and positive effects of the present application are:

[0049] In the present application, the synchronous analysis and trend capture of multi-source data are realized by establishing a partition joint analysis system of temperature trajectory and conductive response, the identification ability of abnormal areas is strengthened from the dual angles of time fluctuation and spatial correlation, the precision of cross-zone abnormal association judgment is improved through the connectivity screening mechanism and gradient direction consistency analysis, the multi-dimensional steady-state confirmation of abnormal linkage areas is realized under the matching filtering of the conductivity matrix and the local thermal field characteristics, the quantitative ability and risk presentation ability of abnormal grade division are enhanced through the deviation trend evaluation method, and the dynamic adjustment of the key area repair range is promoted through the comparison and screening of the strategy coverage range, so that the comprehensiveness and continuity of abnormal identification are realized, the reliability and stability of the partition-level health state judgment are improved, the accuracy and trend expression ability of abnormal positioning are strengthened, the sensitivity and consistency of risk assessment are optimized, the misjudgment and omission are reduced, the health repair strategy has pertinence and coordination, and the effective implementation of breast health management is promoted. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 The workflow schematic diagram of the present application is shown in the figure;

[0051] Figure 2 The acquisition flowchart of the breast partition abnormal attribute set in the present application is shown in the figure;

[0052] Figure 3 Flowchart for acquiring cross-zone abnormal connectivity data group in the present application;

[0053] Figure 4 Flowchart for acquiring abnormal defect linkage area group in the present application;

[0054] Figure 5 Flowchart for acquiring breast health partition detection risk level evaluation list in the present application;

[0055] Figure 6 Flowchart for acquiring breast health repair adjustment partition number list in the present application. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0057] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0058] Embodiment 1: Please refer to Figure 1 The present application provides a technical solution, a breast health data anomaly detection method, comprising the following steps:

[0059] S1: Based on the temperature distribution and conductivity characteristics of the breast tissue surface, the detection partition is divided, the temperature change trajectory and the conductivity response curve of the partition are extracted, the synchronous abnormal area of the temperature fluctuation interval and the conductivity response mutation point on the time axis is identified, the corresponding partition number and spatial coordinates are extracted, and a breast partition abnormal attribute set is generated;

[0060] S2: According to the breast partition abnormal attribute set, the temperature gradient direction and the conductivity response vector of the partition are identified, the consistency of the two at the partition boundary is analyzed, the partitions with connectivity and temperature gradient anomaly are screened out in combination with the partition boundary connectivity, and a cross-zone abnormal connectivity data group is formed;

[0061] S3: Based on the cross-zone abnormal connectivity data set, the conductivity distribution matrix and the local thermal field characteristics within the partition are extracted, the uniformity of the conductivity and the consistency of the thermal field are analyzed, the matching abnormal area is screened, and the abnormal defect linkage area group is obtained;

[0062] S4: According to the abnormal defect linkage area group, the conductivity distribution trend of the partition is analyzed, the deviation degree from the original health state curve is evaluated, the abnormal grade of the partition is calibrated according to the deviation amplitude, and the breast health partition detection risk level evaluation list is output;

[0063] S5: Call the breast health partition detection risk level evaluation list, identify the corresponding number of the partition in the breast function map, call the repair response unit list, compare the response level and the breast protection priority sequence, screen the partition number that needs to adjust the response coverage range, and output the breast health repair adjustment partition number list;

[0064] The breast protection priority sequence refers to the sequence according to the breast function criticality and protection demand.

[0065] The breast partition abnormal attribute set includes temperature mutation partition number, conductivity response abnormal point, partition coordinate marker, time sequence mutation identifier, cross-zone abnormal connectivity data set includes temperature gradient abnormal partition identifier, partition boundary connectivity unit, partition boundary consistency block, abnormal defect linkage area group includes conductivity abnormal continuous partition, thermal field irregular area, conductivity performance mutation overlap area, linkage abnormal partition number, breast health partition detection risk level evaluation list includes risk level label, partition response deviation value, local conductivity abnormal index, health state deviation grade, breast health repair adjustment partition number list includes adjustment target partition number, response level adjustment parameter, protection priority comparison item, linkage response trigger type.

[0066] Please refer to Figure 2 The acquisition steps of the breast partition abnormal attribute set are as follows:

[0067] S111: Based on the breast tissue surface temperature distribution and conductivity characteristics, the detection partition is divided, the temperature change trajectory and the conductivity response curve of the partition are extracted, the difference value calculation is performed on the two types of data in the same partition, and the temperature and conductivity response difference trend value is obtained;

[0068] Based on the breast tissue surface temperature distribution and the conductive characteristics of the detection partition, the high-precision infrared thermal imager scans to obtain the breast surface temperature distribution data, the accuracy is 0.1 Celsius, the matrix specification is 256x256, and the bioimpedance analyzer obtains the breast conductive characteristic data, the accuracy is 0.01 S / m, and the matrix specification is 256x256. The temperature distribution of a certain area is 36.5 degrees Celsius to 37.8 degrees Celsius, the conductivity distribution is 0.5 S / m to 0.7 S / m, the preset physiological partition standard is divided into 8 detection partitions, for example, the left breast upper outer partition contains 64x64 pixel points, the temperature and conductivity data in the partition are averaged, the temperature change trajectory and the conductivity response curve of the partition are extracted, the average temperature value and the average conductivity value are recorded in the continuous monitoring period (every 10 minutes), and the time sequence is formed. For example, the temperature sequence data and the conductivity sequence data of a certain section of partition A, the difference value calculation is performed on the two types of data in the same partition, the difference between the temperature value at each monitoring time point and the temperature value at the previous time point, and the difference between the conductivity value and the conductivity value at the previous time point. For example, the temperature change of partition A is 0.1 Celsius, and the conductivity change is 0.02 S / m. The temperature and conductivity response difference trend value is obtained, and the weighted or Euclidean distance of the temperature change and the conductivity change is calculated.

[0069] S112: According to the temperature and conductivity response difference trend value, the fluctuation interval in the temperature change curve and the mutation point of the conductivity response trajectory are identified, the time overlap of the two types of values is performed, the time interval in which the fluctuation exceeds the preset reference value and the mutation point is located in the set range is extracted, and the high-frequency abnormal interval time period set is generated;

[0070] According to the temperature and conductivity response difference trend value, the fluctuation interval is identified by calculating the local standard deviation of the temperature change sequence. If the local standard deviation (3 time points) exceeds the temperature fluctuation threshold of 0.05 degrees Celsius, there is a fluctuation. The mutation point is identified by calculating the second derivative of the conductivity change sequence. If the second derivative or CUSUM value exceeds the conductivity mutation threshold of 0.03 S / m, there is a mutation. For example, in the difference trend value sequence of a certain section of partition A, between the 6th and 7th time points, the local standard deviation of temperature change increases from 0.03 degrees Celsius to 0.07 degrees Celsius, and the second derivative of conductivity change changes from 0.01 S / m to 0.04 S / m. Temperature fluctuations and conductivity mutations are identified. The two types of values are time overlapped, and the temperature fluctuation interval and conductivity mutation point are aligned on the time axis. For example, the temperature fluctuation interval lasts from time point 5 to 8, and the conductivity mutation point appears at time points 6 and 7. The overlapping time period is time points 6 and 7. Extract the time interval where the fluctuation exceeds the preset baseline value and the mutation point is within the set range. The preset baseline value is defined as the average difference trend value of the partition health state plus two standard deviations. For example, the average difference trend value of partition A in the healthy state is 0.05, the standard deviation is 0.01, the baseline value is 0.07, the set mutation amplitude threshold is 0.03 S / m, the difference trend value at time point 6 is 0.15, which exceeds the baseline value 0.07, and there is a conductivity mutation. Time point 6 is extracted, a high-frequency abnormal interval time period set is generated, and time intervals that meet the conditions are collected.

[0071] S113: For the high-frequency abnormal interval time period set, match the corresponding partition number and spatial coordinate information, extract the partition position where the signal occurs, and generate a breast partition abnormal attribute set;

[0072] For the high-frequency abnormal interval time period set, take out the abnormal interval, for example, "time point 6-time point 8" is the abnormal interval, match the partition number and spatial coordinate information, for each abnormal time interval, find the abnormal partition number (P01) and its spatial coordinate range (pixel points (10, 10) to (74, 74)), match the partition division and spatial mapping based on the pre-defined partition. For example, P01 is identified as high-frequency abnormal during "time point 6-time point 8", partition number P01, spatial coordinate range ((10, 10), (74, 74)), extract the partition position where the signal occurs, extract the matched partition number and its spatial coordinate information and store. For example, store P01 and coordinate range ((10, 10), (74, 74)), generate a breast partition abnormal attribute set, the set is composed of records, each record contains partition number, abnormal time period, and partition spatial coordinate information.

[0073] Please refer to Figure 3 The acquisition steps of the cross-zone abnormal connectivity data group are as follows:

[0074] S211: Identify the temperature gradient direction and the conductive response vector in the partition of the breast partition abnormal attribute set, extract the projection trajectory of the two at the partition boundary, identify the distribution number and aggregation degree of the intersection point in the partition, and obtain the partition boundary consistency atlas;

[0075] Identify the breast partition abnormal attribute set, obtain the number and spatial coordinate information of each abnormal partition, for example, the spatial coordinate range of partition P01 is ((10, 10), (74, 74)), retrieve the original temperature distribution data and conductive characteristic data of the partition and its adjacent partitions, identify the temperature gradient direction, and calculate the temperature change rate vector within the partition and between adjacent partitions. For example, at the boundary between P01 and P02, point (x1, y1) has a temperature of 37.0 degrees Celsius, point (x1+1, y1) has a temperature of 37.1 degrees Celsius, the temperature gradient is 0.1 degrees Celsius / mm, the conductive response vector is identified, the conductivity change rate vector within the partition and between adjacent partitions is calculated, for example, point (x1, y1) has a conductivity of 0.60 S / m, point (x1+1, y1) has a conductivity of 0.61 S / m, the conductive response is 0.01 S / m / mm, and the projection trajectory of the two at the partition boundary is extracted. At each intersection point, the temperature gradient vector and the conductive response vector are projected onto the normal and tangent directions of the intersection line to obtain a set of components that constitute the projection trajectory. For example, intersection point A, temperature gradient vector GT, conductive response vector GC, projection trajectory includes the components of GT in the normal and tangent directions and the components of GC in the normal and tangent directions, identify the distribution number and aggregation degree of the intersection point in the partition, count the number of intersection points on the intersection line whose projection trajectory similarity reaches the threshold (angle less than 10 degrees and modulus ratio 0.8 to 1.2), and evaluate the spatial aggregation degree. For example, 80 out of 100 sampling points on the P01 and P02 intersection line have a similarity that meets the threshold and are continuously distributed, the aggregation degree is high, the partition boundary consistency atlas is obtained, and the atlas is represented in matrix form, with elements representing the consistency score of a pair of adjacent partition boundaries. The score is calculated based on the distribution number and aggregation degree of the intersection points.

[0076] S212: According to the partition boundary consistency atlas, filter the boundary regions with aggregation degree higher than the average level, compare the spatial boundary of the whole breast structure atlas, identify the continuous and belonging to the same partition of the intersection set area, and obtain the temperature gradient abnormal area in the breast partition;

[0077] According to the consistency map of the partition boundary, the boundary consistency score of each adjacent partition pair is obtained, for example, P01 and P02 score 0.85, P02 and P03 score 0.70, the boundary area with aggregation degree higher than the average level is screened, and the average value of the consistency scores of all adjacent partitions is calculated. For example, the average value is 0.75, the area with a score higher than 0.75 is screened, such as the boundary area of P01 and P02 (0.85 is higher than 0.75), and the spatial boundary of the overall breast structure is compared, and the high-aggregation-degree boundary area screened is superimposed on the breast anatomical structure map to check the continuity and align with the structure boundary. For example, the high-aggregation-degree boundary area of P01 and P02 is consistent with the direction of a main duct of the breast, and matches the breast structure boundary, the continuous area with continuity and belonging to the same partition is identified, the high-aggregation-degree boundary area that matches the structure boundary is tracked, and the continuous area that functions as a whole is determined, all the boundary points in the area belong to the same functional partition, for example, the three partitions P01, P02 and P03 have a consistency score higher than the average level, forming a continuous area, which is determined as a certain lobe of the breast, and is identified as a boundary concentrated area, and the temperature gradient abnormal area in the breast partition is obtained. The temperature gradient and the conductive response in the area show consistency and match the physiological structure, and are marked as the temperature gradient abnormal area in the breast partition.

[0078] S213: Based on the temperature gradient abnormal area in the breast partition, the partition boundary consistency, temperature gradient dispersion, conductivity balance and conductive response delay are integrated and analyzed, the response blocks in the partition are matched according to the partition, and a cross-zone abnormal connectivity data set is formed;

[0079] Based on the temperature gradient abnormal area in the breast partition, the temperature gradient abnormal area information is obtained, for example, the "lobe A abnormal area" covers the P01, P02 and P03 partitions, and the partition boundary consistency, temperature gradient dispersion, conductivity balance and conductive response delay are integrated and analyzed;

[0080] Partition boundary consistency: Extract the boundary consistency score between each two partitions, calculate the average value, for example, P01-P02 is 0.85, P02-P03 is 0.70, and P01-P03 is 0.65, and the average value is 0.73;

[0081] Temperature gradient dispersion: Calculate the standard deviation of the modulus and direction of all temperature gradient vectors in the partition, for example, the standard deviation of the modulus of the temperature gradient in the P01 partition is 0.02 degrees Celsius / mm, and the standard deviation of the direction is 5 degrees;

[0082] Conductivity balance: Calculate the coefficient of variation of all conductivity values in the partition, for example, the conductivity variation coefficient of P01 partition is 0.05;

[0083] Conductive response delay: record the time difference between temperature change and conductive response, calculate the average and standard deviation, for example, the average conductive response delay of P01 partition is 5 seconds;

[0084] The four indicators are normalized (0 to 1 range) and weighted summed to obtain the integrated abnormal score of the abnormal zone. Weight: boundary consistency 0.3, temperature gradient dispersion 0.25, conductivity uniformity 0.25, conductive response delay 0.2. The integrated abnormal score of "adenoid leaf A abnormal zone" is 0.8845. According to the response block in the partition, the partition matching is carried out. The integrated abnormal score is compared with the preset "abnormal response threshold" (0.8). If the score exceeds the threshold, the zone is a strong response block. It is accurately matched with the breast partition number. For example, 0.8845 is higher than 0.8. "Adenoid leaf A abnormal zone" is confirmed as a response block. It is bound with P01, P02, P03 partition number to form a cross-zone abnormal connectivity data group, which includes strong response block abnormal zone, covers breast partition number and connectivity relationship.

[0085] Please refer to Figure 4 The acquisition steps of the abnormal defect linkage area group are as follows:

[0086] S311: Based on the cross-zone abnormal connectivity data group, the conductivity distribution matrix and local thermal field characteristics of the partition number partition are extracted. The data in the partition is time stamped and aligned. The conductivity fluctuation value and thermal field consistency offset are identified. The local defect response feature set of the breast is obtained.

[0087] Based on the cross-zone abnormal connectivity data set, the abnormal zone corresponding to the connectivity ID and the partition number contained therein are extracted. For example, C01 contains P01, P02, P03, the conductivity distribution matrix and the local thermal field characteristics of the partition number partition are extracted, and for each partition (P01, P02, P03), the conductivity distribution matrix and the local temperature distribution data in the abnormal time period are called, and the local thermal field characteristics include the average temperature, the temperature standard deviation, and the maximum value of the local temperature gradient. For example, the conductivity distribution matrix of P01 is a 64×64 numerical matrix, and the local thermal field characteristics include the average temperature of 37.5 degrees Celsius and the temperature standard deviation of 0.3 degrees Celsius. The data in the partition are time stamped to ensure that the conductivity data and the temperature data are collected at the same time point or time period. For example, the conductivity data is collected at 10:00, 10:10, and 10:20, and the temperature data is sampled at the same time point. The conductivity fluctuation value and the thermal field consistency offset are identified, and the conductivity fluctuation value is obtained by calculating the conductivity standard deviation or the difference between the maximum and minimum values of the conductivity matrix in the abnormal time period. For example, the conductivity standard deviation of P01 partition is 0.08 S / m, and the thermal field consistency offset is obtained by comparing the local thermal field characteristics in the partition with the average temperature difference under healthy state. For example, the current average temperature of P01 partition is 37.5 degrees Celsius, and the average temperature under healthy state is 37.0 degrees Celsius, and the offset is 0.5 degrees Celsius. The local defect response feature set of the breast is obtained, and the feature set includes the conductivity fluctuation value and the thermal field consistency offset in the abnormal time period of each abnormal partition.

[0088] S312: According to the breast local defect response feature set, the conductivity uniformity and the thermal field consistency in the partition are jointly analyzed, and the formula is used:

[0089] ;

[0090] The conductivity thermal field coupling characteristic value is calculated, the partition unit of the conductivity thermal field coupling degree in the partition is screened, and the conductivity thermal field cooperative response space distribution map is established.

[0091] wherein, represents the conductivity thermal field coupling characteristic value, represents the conductivity value of the i-th unit, represents the temperature value of the i-th unit, represents the spatial coordinate change of the i-th unit in the x-axis direction, represents the spatial coordinate change of the i-th unit in the y-axis direction, represents the thermal diffusion coefficient of unit volume of material, represents the thermal coefficient of unit volume of electrical conductivity;

[0092] Based on the local defect response feature set of the breast, the conductivity fluctuation value and thermal field consistency offset of each partition are obtained. For example, the conductivity fluctuation value of partition P01 is 0.08 S / m, and the thermal field consistency offset is 0.5℃. A joint analysis of conductivity uniformity and thermal field consistency within the partition is performed. This analysis is a comprehensive evaluation of conductivity fluctuation value and thermal field consistency offset, rather than simply looking at a single value. For example, a high conductivity fluctuation value but a low thermal field consistency offset indicates different types of tissue abnormalities, while both indicate more severe defects. A formula is used to... Calculate the thermal field coupling eigenvalues ​​of conductivity, where, Represents the characteristic value of electrical conductivity coupled with thermal field. Representing the The conductivity value of each unit, for example, for partition P01, can be taken as its average conductivity value of 0.65 S / m during the abnormal time period, or as the maximum conductivity value within that partition. Here, the average conductivity value is taken, which is obtained by averaging the conductivity data of all monitoring points in partition P01 during the abnormal time period. Representing the The temperature value of each unit, for example, for partition P01, is taken as its average temperature value of 37.5℃ during the abnormal time period. This is obtained by averaging the temperature data of all monitoring points in partition P01 during the abnormal time period. Representing the The spatial coordinate change of a unit along the x-axis. For example, for partition P01, its span along the x-axis. If the pixel range of partition P01 is (10, 10) to (74, 74), and each pixel represents 1 mm, then... , Show the first The change in spatial coordinates of each unit along the y-axis, similarly, , The thermal diffusivity of a material per unit volume represents its ability to transfer heat. Its value can be obtained through experimental measurements of breast tissue or by consulting databases of the thermophysical properties of biological tissues. For healthy breast tissue... The typical value is For abnormal tissues, this value changes; here it is set to [value]. , The thermal coefficient represents the electrical conductivity per unit volume. This coefficient characterizes the sensitivity of electrical conductivity to temperature changes. Its value can be calculated by measuring the conductivity of breast tissue samples at different temperatures and then using methods such as linear fitting. For breast tissue, The typical value is This is set to ;

[0093] Operational logic and purpose of the formula: the formula aims to quantify the degree of coupling between the electrical conductivity and the thermal field in a local region of breast tissue, i.e. when temperature and electrical conductivity change in a particular region, the molecular term represents the product of electrical conductivity and temperature, reflecting the strength of the thermoelectric effect; the in the denominator represents the spatial scale of the unit, used to normalize the coupling strength to eliminate the influence of unit size and ensure comparability between different sizes of sub-regions; the on the far right is a normalization factor, where and are material intrinsic properties, used to convert the coupling eigenvalue into a dimensionless or uniformly dimensioned index, making comparisons between different tissue types physically meaningful;

[0094] The benefit of this formula is that by introducing spatial scale normalization and material intrinsic property correction, the calculated coupling eigenvalue more accurately reflects the inherent physical properties of local defects, rather than being affected by sub-region size or general thermoelectric properties of the tissue, thereby improving the accuracy of anomaly detection;

[0095] Now, substitute the numerical values of P01 sub-region for calculation: , , , , , ;

[0096] ;

[0097] Screen the sub-region units of the electrical conductivity-thermal field coupling degree in the sub-region, compare the calculated value with the preset coupling eigenvalue threshold , for example, by analyzing a large number of healthy and diseased breast tissue samples, set to , if the value of the sub-region is higher than , it is considered that the sub-region has a higher electrical conductivity-thermal field coupling degree, for example, is higher than , so P01 is screened out, and an electrical conductivity-thermal field synergistic response spatial distribution map is established, all screened high coupling degree sub-region units are visualized according to their actual positions in the breast structure map, forming a spatial distribution map in which each high coupling degree sub-region is marked.

[0098] S313: Call the electrical conductivity-thermal field synergistic response spatial distribution map, cluster the sub-regions that exceed the synergistic identification benchmark in the coupling eigenvalue sub-regions, mark the sub-region codes and coordinates corresponding to the continuous abnormal regions, and obtain the abnormal defect linkage region group;

[0099] The conductivity thermal field synergistic response spatial distribution map is called to obtain all the screened high coupling degree partition units and their coupling characteristic values, for example, the coupling characteristic value of P01 partition is 1.5869 multiplied by 10 to the power of 11, the partitions in the coupling characteristic value partition that exceed the synergistic identification benchmark are clustered, the synergistic identification benchmark is 1.2 multiplied by 10 to the power of 11, any partition with a coupling characteristic value higher than this benchmark is a partition exceeding the benchmark, the P01 coupling characteristic value 1.5869 multiplied by 10 to the power of 11 is higher than the benchmark 1.2 multiplied by 10 to the power of 11, P01 is identified as exceeding the benchmark, and the partitions adjacent to the partitions exceeding the benchmark are clustered in space as a continuous abnormal area. For example, P01, P02, and P03 are adjacent and have coupling characteristic values exceeding the benchmark, and are clustered as a continuous abnormal area, and the partition codes and coordinates corresponding to the continuous abnormal area are marked, and each cluster forms a continuous abnormal area and is assigned a unique identifier (A01), and all partition codes (P01, P02, P03) and their overall spatial coordinate ranges on the breast structure map are recorded. For example, the A01 area covers pixel points (10, 10) to (138, 74), and an abnormal defect linkage area group is obtained, which includes all identified continuous abnormal areas and their associated partition codes and spatial coordinate information.

[0100] Please refer to Figure 5 The acquisition steps of the breast health partition detection risk level evaluation list are as follows:

[0101] S411: According to the abnormal defect linkage area group, the partition conductivity performance distribution curve under the specified number is extracted, and time unified processing is performed to identify the unit time conductivity performance change amount, and a partition conductivity performance abnormal change rate set is obtained;

[0102] According to the abnormal defect linkage area group, extract each abnormal area (A01) and the subarea number (P01, P02, P03) contained therein, extract the conductivity distribution curve of the subarea under the specified number, extract the conductivity time series data of each subarea (P01) during the entire monitoring period, and construct the conductivity distribution curve. For example, the P01 conductivity curve is a continuous conductivity value E1, E2,..., Ek corresponding to the time point t1, t2,..., tk. Perform time uniform processing, synchronize the conductivity distribution curves of different subareas, and synchronize all curve data points to the same time stamp. For example, all curves are interpolated to one data point every 5 minutes, the conductivity performance change amount per unit time is identified, and the conductivity performance change amount between adjacent time points on the conductivity distribution curve is calculated for each subarea. Divide by the corresponding time interval to obtain the conductivity performance change rate per unit time. For example, the P01 subarea has a conductivity of 0.60 S / m at time t1 and a conductivity of 0.62 S / m at time t2 (t2-t1=10 minutes). The conductivity performance change amount per unit time is 0.002 S / (m·min). Obtain the subarea conductivity performance abnormal change rate set, and the unit time conductivity performance change amount set of all abnormal subareas at all monitoring time points.

[0103] S412: According to the subarea conductivity performance abnormal change rate set, identify the conductivity performance distribution curve of the original health state stage in the original data or the reference data, compare the current conductivity performance change sequence with the reference curve, identify the subarea conductivity performance deviation level, extract and mark the subarea whose deviation level exceeds the upper warning limit, and obtain the deviation surge subarea set;

[0104] Based on the set of abnormal conductivity change rates for each partition, the conductivity change rate at each time point is obtained for each abnormal partition. For example, the conductivity change rate sequence for a certain segment of partition P01 can be obtained by analyzing conductivity data from a patient's healthy period, or by constructing a reference curve using a statistical model of healthy individuals. For instance, the average conductivity change rate distribution curve for partition P01 in a healthy state fluctuates between (-0.0005, 0.0005) S / (m·min). The current conductivity change sequence is compared with the reference curve. For each partition, the current conductivity change rate sequence is compared with the healthy reference curve. For example, the DTW distance between the current sequence and the healthy reference curve for partition P01 is calculated to identify the deviation level of the partition's conductivity. Based on the comparison results, the degree of deviation is classified into different levels. For example, there are 5 deviation levels: level 1 to level 5, with the level classification based on a quantified difference threshold. For example, a DTW distance of 0-0.5 is considered level 1, and a distance greater than 2.0 is considered level 5. Partition P01 has a DTW distance of 1.7, which is level 4. Partitions whose deviation level exceeds the upper limit of the warning are extracted and marked. The upper limit of the warning is the deviation level threshold of level 3. Any partition with a deviation level higher than level 3 is extracted and marked as a "deviation surge partition". For example, P01 has a deviation level of 4, which is higher than level 3. P01 is marked as a deviation surge partition. The deviation surge partition set is obtained, which contains the partition numbers marked as deviation levels exceeding the upper limit of the warning.

[0105] S413: Based on the deviation abrupt increase partition set, the deviation level value of each partition is bound to the position number in the breast structure spatial map, using the formula:

[0106] Calculate the health risk index of each zone, sort them by risk level, and output a list of breast health zone detection risk level assessments.

[0107] in, The health risk index represents the region. This represents a deviation from the grade value. This represents the mean deviation of all partitions from their rank values. This represents the standard deviation of all partitions from their respective rank values. The first one in the spatial diagram representing the breast structure Spatial distance between partition locations Representing the Risk weight coefficient for each partition location This represents the total number of partition locations involved;

[0108] Based on the set of deviation abrupt increases, obtain the deviation level value for each partition (e.g., P01, P04, P07). For example, the deviation level value for P01 is 4, the deviation level value for P04 is 3.5, and the deviation level value for P07 is 4.2 (the level values ​​can be refined here for ease of calculation). Bind the deviation level value of each partition to its position number in the breast structure spatial map, and associate the level value of each deviation abrupt increase partition with its specific location in the breast structure spatial map (represented by the partition number and spatial coordinates). For example, the deviation level value of P01 is 4, which is bound to the position of partition P01 in the map, using the formula: Calculate the health risk index for each region. The health risk index represents the region. This represents a deviation from the grade value, for example, P01. , This represents the mean deviation of all partitions from their rank values. For example, in the partition set {P01, P04, P07} with a sudden increase in deviation, the deviation rank values ​​are respectively... ,but , This represents the standard deviation of all partitions from the grade value, calculated based on the aforementioned deviation from the grade value. ;

[0109] The first one in the spatial diagram representing the breast structure The spatial distance of a partition location, where spatial distance refers to the distance from the partition of the deviation to its nearest known high-risk area (e.g., tumor location in historical cases or densely populated areas of the breast), or, if no known high-risk area, the distance to the center point of the breast, here defined as the distance to the nearest densely populated area of ​​the breast, is measured in millimeters. For example, the distance from partition P01 to the nearest densely populated area of ​​the breast is... Partition P04 is Partition P07 is , Representing the The risk weight coefficient for each quadrant location reflects the importance or susceptibility of that location within the breast structure. For example, specific quadrants of the breast (such as the upper outer quadrant) have a higher risk due to abundant glandular tissue. This weight can be set based on anatomical knowledge; for instance, the weight of the upper outer quadrant... Upper inner quadrant Here, it is assumed that P01, P04, and P07 are all located in the upper outer quadrant, then the risk weight coefficient... , This represents the total number of partition locations involved, which in this case is the number of partitions that deviate from the burst partition set. ;

[0110] The formula's operational logic and purpose: This formula aims to comprehensively assess the health risks of a region, considering not only the degree of abnormality in its conductivity deviation level but also its spatial location risk within the breast structure. The left side of the formula... This involves Z-score standardization of the deviation level values ​​to measure the degree of "abnormality" of the current partition's deviation relative to the average level of all partitions with deviations. This avoids the absoluteness of direct comparison with the original deviation level values ​​and better reflects relative risk. (The right side...) This introduces spatial risk factors, among which This represents the product of each deviation partition and its spatial location risk, which is then summed and squared. This aims to reflect the potential spatial risk impact of all deviation partitions as a whole. The square root operation can mitigate the excessive impact of extreme distances or weights on the overall risk.

[0111] The advantage of this formula is that it combines the degree of physiological abnormality (deviation grade) with the inherent risk of spatial location, providing a more comprehensive and quantitative health risk assessment indicator, making the assessment results more biologically meaningful and clinically valuable.

[0112] Now, calculate the health risk index for partition P01: , , , , ;

[0113] For the summation term on the right, we need to calculate all deviations from the sudden increase partition. sum: ;

[0114] ;

[0115] ;

[0116] Similarly, the health risk indices for P04 and P07 can be calculated:

[0117] ;

[0118] ;

[0119] Sort by risk level, based on the calculated health risk index The values ​​are sorted in descending order for all partitions that deviate from the sudden increase, for example, P04 ( P07 P01 The sorting results, together with the partition number, deviation level value and spatial coordinates, constitute the breast health partition detection risk level assessment list, as shown in Table 1.

[0120] Table 1: List of Risk Level Assessments for Breast Health Zoning Detection

[0121]

[0122] The results indicate that the P07 partition has the highest health risk, which further suggests that its tissue abnormalities are more severe or that its location carries a higher clinical risk. The deviation grade value of P04 is 3.5. Although its health risk index R value is high, the results show that its health risk is not as high as that of P07. This list directly constitutes the results of this step.

[0123] Please see Figure 6 The specific steps to obtain the list of breast health repair and adjustment zone numbers are as follows:

[0124] S511: Call the list of risk level assessment for breast health zoning detection, extract the number of the zoning in the breast function map, map the risk level value of the zoning to the regional coordinate boundary, identify the zoning information corresponding to the breast protection level, and generate a breast zoning risk distribution map.

[0125] The system retrieves the breast health zoning risk level assessment list and extracts the zoning number, health risk index (R) value, and deviation level value for each zoning zone. For example, zone P04 has an R value of 11.546 and a deviation level value of 3.5. The breast zoning number is mapped to the breast function map to determine the zone's functional affiliation. For instance, zone P04 belongs to a specific lobe of the breast. The zone's risk level value is mapped to the region's coordinate boundaries, and the health risk index (R) value for each zone is associated with its coordinate boundaries on the breast structure spatial map. For example, the coordinate range of zone P04 is ((xa, ya), (xb, yb)), and the risk index of 11.546 is associated with this region. The system identifies the zoning information corresponding to the breast protection level. Based on clinical guidelines or pre-defined strategies, the breast region is divided into different protection levels (Level 1: High Risk, Level 2: Medium Risk, Level 3: Low Risk), and the zoning information corresponding to each risk level is identified. For example, a level 1 protected area is defined as R greater than or equal to 10, a level 2 protected area is defined as 5 less than or equal to R less than 10, and a level 3 protected area is defined as R less than 5. P04 (R=11.546) is a level 1 protected area, P07 (R=8.641) is a level 2 protected area, and P01 (R=2.885) is a level 3 protected area. A risk distribution map of the breast region is generated. The map visualizes the protection level of each region of the breast. Different protection level regions are marked on the breast structure map with different colors or markers.

[0126] S512: Based on the risk distribution map of breast regions, extract the repair response unit number and response level, match the regional risk level with the repair response level, identify the unit number with insufficient response coverage, and obtain the breast region response risk disconnect list.

[0127] Based on the risk distribution map of breast cancer zones, the protection level information and map markers for each zone are obtained. For example, P04 is a Level 1 protected area (highlighted in red), P07 is a Level 2 protected area (yellow), and P01 is a Level 3 protected area (green). Repair response units represent intervention measures, and each unit has a response level, indicating the applicable risk level and treatment intensity. For example, physical therapy (unit F01) has a response level of "mild (applicable to Level 3 protected area)", drug therapy (unit F02) has a response level of "moderate (applicable to Level 2 protected area)", and surgical treatment (unit F03) has a response level of "severe (applicable to Level 1 protected area)". Zone risk levels are matched with repair response levels, and the protection level of each zone is matched with the response level of its corresponding repair response unit. For example, P04 (Level 1 protected area) matches F03 (severe), P07 (Level 2 protected area) matches F02 (moderate), and P01 (Level 3 protected area) matches F01 (mild). Unit numbers with insufficient response coverage are identified, and it is checked whether each zone has obtained repair response coverage. For example, in a Level 1 protected area, P04 is currently only matched with F02 (moderate) instead of F03 (severe), indicating insufficient response coverage. This unit number (F02) and its service area (P04) are identified, resulting in a list of mammary gland zoning response risk gaps. The list includes zoning numbers with insufficient response coverage and information on currently matched (or unmatched) remediation response units.

[0128] S513: Based on the list of risk disconnection in breast region response and the level number in the breast protection priority sequence, extract the key region numbers that need to improve the response coverage, output the adjustment control parameters linked with the original repair unit in sequence, and output the list of breast health repair adjustment region numbers.

[0129] Based on the breast cancer regional response risk discontinuity list, obtain the regional numbers with insufficient response coverage and their current and expected response units. For example, in region P04, the current response unit is F02 (moderate) and the expected response unit is F03 (severe). Extract the key regional numbers that need to improve response coverage. The breast cancer protection priority sequence guides the intervention priority. From the discontinuity list, extract the key regions that need immediate improvement in response coverage according to the priority sequence. For example, P04 (Level 1 protected area) has a high priority and is identified as a key zone requiring an increased response coverage. Adjustment control parameters linked to the original repair units are output sequentially. For each key zone, based on the expected repair response level, adjustment parameters for the existing repair units are determined. These adjustment parameters include increasing treatment intensity, adjusting drug dosage, increasing treatment frequency, or introducing advanced treatment methods. For instance, if zone P04 is currently at F02 (moderate) and expected to reach F03 (severe), the adjustment control parameters would include: "Increase F02 treatment intensity to 80%, increase F03 intervention frequency to twice per week." These parameters are output in conjunction with the original repair units, generating a list of breast health repair adjustment zone numbers. This list contains all key zone numbers requiring adjustment and their detailed adjustment control parameters.

[0130] The breast health data anomaly detection system is used to perform the above-mentioned breast health data anomaly detection method. The system includes:

[0131] The temperature monitoring module divides the detection zones based on the surface temperature distribution and conductivity characteristics of breast tissue. It compares the temperature fluctuation range and conductivity response abrupt change points within the same time period, filters out synchronous abnormal areas, extracts the zone number and spatial coordinates, summarizes the abnormal time period and zone number, and generates a set of abnormal attributes of breast zones.

[0132] The partition localization module identifies the consistency between the temperature gradient direction and the conductivity response vector based on the abnormal attribute set of the breast partition, marks the partition boundary number, matches the overall breast structure map, extracts the partition number range of the abnormal temperature gradient region, and establishes a cross-regional abnormal connectivity data group.

[0133] The defect linkage module is based on the cross-regional abnormal connectivity data group. It retrieves the conductivity distribution matrix and the local thermal field characteristics in the continuous data sequence of the region, judges the consistency between the conductivity abnormal boundary connectivity and the thermal field, marks the partition number that meets the linkage threshold of the two, and outputs the abnormal defect linkage region group.

[0134] The conductivity early warning module analyzes the distribution trend of conductivity performance of the corresponding partition and the degree of deviation from the original health status curve based on the partition number of the abnormal defect linkage area group, extracts the partition number of the deviation trend, completes the level identification according to the risk classification standard, and generates a list of breast health partition detection risk level assessment.

[0135] The repair and optimization module is based on the risk level assessment list of breast health zones. It finds the corresponding position number of the risk level zone in the breast function map, retrieves the current repair response unit configuration list, compares the matching of breast protection priority with the current response level, filters the zones that need to be updated, and outputs a list of breast health repair adjustment zone numbers.

[0136] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A breast health data anomaly detection method, characterized by, The method comprises the following steps: S1: based on the surface temperature distribution and the electrical conductivity of the breast tissue, the detection sub-area is divided, the temperature change trajectory and the electrical conductivity response curve of the sub-area are extracted, the synchronous abnormal area of the temperature fluctuation interval and the electrical conductivity response mutation point on the time axis is identified, the corresponding sub-area number and spatial coordinates are extracted, and a breast sub-area abnormal attribute set is generated; The acquisition step of the breast sub-area abnormal attribute set is specifically: S111: based on the surface temperature distribution and the electrical conductivity of the breast tissue, the detection sub-area is divided, the temperature change trajectory and the electrical conductivity response curve of the sub-area are extracted, the difference value calculation is performed on the two types of data in the same sub-area, and the temperature and electrical conductivity response difference trend value is obtained; S112: according to the temperature and electrical conductivity response difference trend value, the fluctuation interval in the temperature change curve and the mutation point of the electrical conductivity response trajectory are identified, the two types of values are time superimposed, the time interval in which the fluctuation exceeds the preset reference value and the mutation point is located in the set range is extracted, and a high-frequency abnormal interval time period set is generated; S113: for the high-frequency abnormal interval time period set, the corresponding sub-area number and spatial coordinate information are matched, the sub-area position where the signal occurs is extracted, and a breast sub-area abnormal attribute set is generated; S2: according to the breast sub-area abnormal attribute set, the temperature gradient direction and the electrical conductivity response vector of the sub-area are identified, the direction consistency of the two at the sub-area boundary is analyzed, the sub-area with connectivity and temperature gradient anomaly is screened out in combination with the sub-area boundary connectivity, and a cross-area abnormal connectivity data group is formed; The acquisition step of the cross-area abnormal connectivity data group is specifically: S211: the temperature gradient direction and the electrical conductivity response vector of the sub-area in the breast sub-area abnormal attribute set are identified, the projection trajectory of the two at the sub-area boundary is extracted, the distribution number and aggregation degree of the boundary points in the sub-area are identified, and a sub-area boundary consistency atlas is obtained; S212: according to the sub-area boundary consistency atlas, the boundary area with an aggregation degree higher than the average level is screened out, the spatial boundary of the overall structure diagram of the breast is compared, the continuous and sub-area boundary concentrated area is identified, and a temperature gradient abnormal area in the breast sub-area is obtained; S213: based on the temperature gradient abnormal area in the breast sub-area, the sub-area boundary consistency, the temperature gradient dispersion degree, the electrical conductivity uniformity and the electrical conductivity response delay are integrated and analyzed, the response blocks in the sub-area are matched, and a cross-area abnormal connectivity data group is formed; S3: based on the cross-area abnormal connectivity data group, the electrical conductivity distribution matrix and the local thermal field characteristics of the sub-area are extracted, the electrical conductivity uniformity and the thermal field consistency are analyzed, the matching abnormal area is screened out, and an abnormal defect linkage area group is obtained; The acquisition step of the abnormal defect linkage area group is specifically: S311: based on the cross-area abnormal connectivity data group, the electrical conductivity distribution matrix and the local thermal field characteristics of the numbered sub-area in the sub-area are extracted, the time stamp of the data in the sub-area is aligned, the electrical conductivity fluctuation value and the thermal field consistency offset are identified, and a breast local defect response feature set is obtained; S312: according to the breast local defect response feature set, the electrical conductivity uniformity and the thermal field consistency in the sub-area are jointly analyzed, and the formula: ； The conductivity thermal field coupling characteristic value is calculated, the partition unit of the conductivity thermal field coupling degree in the partition is screened, and a conductivity thermal field cooperative response spatial distribution map is established; wherein, represents the thermal field coupling characteristic value of the electrical conductivity, represents the electrical conductivity value of the i-th cell, represents the temperature value of the i-th cell, represents the spatial coordinate variation of the i-th cell in the x-axis direction, represents the spatial coordinate variation of the i-th cell in the y-axis direction, represents the thermal diffusion coefficient of the material per unit volume, represents the thermal coefficient of the electrical conductivity per unit volume; S313: calling the conductivity thermal field cooperative response spatial distribution map, clustering the partition exceeding the cooperative identification benchmark in the coupling characteristic value partition, marking the partition code and coordinates corresponding to the continuous abnormal area, and obtaining an abnormal defect linkage area group; S4: According to the abnormal defect linkage area group, the distribution trend of the conductivity performance corresponding to the partition is analyzed, the deviation degree from the original health state curve is evaluated, the abnormal level of the partition is calibrated according to the deviation amplitude, and a breast health partition detection risk level evaluation list is output.

2. The breast health data anomaly detection method of claim 1, wherein, The breast partition abnormal attribute set includes temperature mutation partition number, conductivity response abnormal point, partition coordinate mark and time sequence mutation mark. The cross-zone abnormal connectivity data group includes temperature gradient abnormal partition identification, partition boundary connectivity unit and partition boundary consistency block. The abnormal defect linkage area group includes conductivity abnormal continuous partition, thermal field irregular area, conductivity performance mutation overlap area and linkage abnormal partition number. The breast health partition detection risk level evaluation list includes risk level label, partition response deviation value, local conductivity abnormality index and health state deviation level.

3. The breast health data anomaly detection method of claim 1, wherein, The acquisition step of the breast health partition detection risk level evaluation list is specifically: S411: According to the abnormal defect linkage area group, the partition conductivity performance distribution curve under the specified number is extracted, and time unified processing is performed, the conductivity performance change amount per unit time is identified, and a partition conductivity performance abnormal change rate set is obtained; S412: According to the partition conductivity performance abnormal change rate set, the conductivity performance distribution curve of the original health state stage in the original data or the reference data is identified, the current conductivity performance change sequence is compared with the reference curve, the partition conductivity performance deviation level is identified, the partition whose deviation level exceeds the upper limit of the warning boundary is extracted and marked, and a deviation sudden increase partition set is obtained; S413: According to the deviation sudden increase partition set, the deviation level value of each partition is bound with the position number in the breast structure spatial map, and the formula is used: ； The health risk index of the partition is calculated, the risk level is sorted, and the breast health partition detection risk level evaluation list is output; wherein, a health risk index representative of a partition, a deviation level representative of a partition, a mean value representative of deviation levels of all partitions, a standard deviation representative of deviation levels of all partitions, a spatial distance representative of a position of a partition in a breast structure space map, a risk weight coefficient representative of a position of a partition, a total number representative of positions of involved partitions.

4. The breast health data anomaly detection method of claim 1, wherein, The method further includes the S5 step: S5: Calling the breast health partition detection risk level evaluation list, identifying the corresponding number of the partition in the breast function map, calling the repair response unit list, comparing the response level with the breast protection priority sequence, screening the partition number which needs to adjust the response coverage range, and outputting a breast health repair adjustment partition number list; The breast protection priority sequence refers to the sequence according to the breast function criticality and protection demand; The breast health repair adjustment partition number list includes adjustment target partition number, response level adjustment parameter, protection priority comparison item and linkage response trigger type.

5. The breast health data anomaly detection method of claim 4, wherein, The acquisition step of the breast health repair adjustment partition number list is specifically: S511: Call the breast health partition detection risk level evaluation list, extract the number of partitions in the breast function map, map the partition risk level value to the region coordinate boundary, identify the partition information corresponding to the breast protection level, and generate a breast partition risk distribution map; S512: Based on the breast partition risk distribution map, extract the repair response unit number and response level, match the partition risk level and repair response level, identify the unit number with insufficient response coverage, and obtain a breast partition response risk disconnection list; S513: According to the breast partition response risk disconnection list, according to the level number in the breast protection priority sequence, extract the key partition number that needs to improve the response coverage range, output the adjustment control parameter linked with the original repair unit in order, and output the breast health repair adjustment partition number list.

6. A breast health data anomaly detection system characterized by, The system is used to realize the breast health data anomaly detection method of any one of claims 1-5, and the system comprises: The temperature monitoring module divides the detection partition based on the breast tissue surface temperature distribution and the conductivity characteristics, compares the temperature fluctuation interval and the conductivity response mutation point in the same time period, screens the synchronous abnormal area of the two, extracts the partition number and spatial coordinates, and outputs the breast partition abnormal attribute set. The partition positioning module identifies the consistency of the temperature gradient direction and the conductivity response vector based on the breast partition abnormal attribute set, calibrates the partition boundary number, matches the overall structure of the breast, extracts the partition number range of the temperature gradient abnormal area, and establishes the cross-zone abnormal connectivity data group. The defect linkage module retrieves the conductivity distribution matrix and the continuous data sequence of local thermal field characteristics in the region based on the cross-zone abnormal connectivity data group, judges the conductivity abnormal boundary connectivity and thermal field consistency, marks the partition number that meets the linkage threshold of the two, and outputs the abnormal defect linkage area group. The conductivity warning module analyzes the conductivity performance distribution trend and the original health state curve deviation degree of the corresponding partition based on the partition number of the abnormal defect linkage area group, extracts the partition number of the deviation trend, completes the level identification according to the risk grading standard, and generates a breast health partition detection risk level evaluation list. The repair optimization module finds the corresponding position number of the risk level partition in the breast function map based on the breast health partition detection risk level evaluation list, retrieves the current repair response unit configuration list, compares the breast protection priority with the current response level matching situation, screens the partition that needs to be updated, and outputs the breast health repair adjustment partition number list.

Images