A method and system for risk management of breast interventional ultrasound procedures

Abstract

The present application relates to the technical field of healthcare informatics, and in particular to a risk management method and system for breast interventional ultrasound surgery, which comprises: determining whether there is an initial risk of tissue elasticity by using intraoperative synchronous ultrasound images and elastography; determining whether there is an initial risk of energy deposition by using the average temperature change rate of the energy action area of the intraoperative ultrasound images and the gray scale gradient value of the anatomical boundary; determining whether there is an initial risk of physiological compensation by using the correlation between the heart rate variability signal before surgery and the breast microvascular blood flow signal; determining similar cases in the historical surgery case database by using the initial risk type and the high-risk area calibration result; and determining the real-time risk probability of risk escalation in the current surgery process by using the similar cases and performing risk warning. Through the technical scheme of the present application, the hysteresis problem of traditional single threshold early warning is solved, precise risk intervention opportunity judgment is provided for doctors, and the risk of intraoperative complications is reduced.

Description

Technical Field

[0001] This invention relates to the field of healthcare informatics technology, specifically to a risk management method and system for breast interventional ultrasound surgery. Background Technology

[0002] Interventional ultrasound-guided breast surgery is a minimally invasive technique that uses real-time ultrasound imaging for precise diagnosis and treatment of tumors. This technique utilizes a high-frequency ultrasound probe to locate lesions, and combines it with instruments such as puncture needles or ablation electrodes to perform tissue sampling or tumor ablation under real-time image monitoring. During the procedure, doctors can dynamically observe the instrument's movement trajectory, the range of energy application, and local tissue reactions through ultrasound images. Its advantages include visualized operation, minimal trauma, and precise targeting of millimeter-level lesions, providing crucial intraoperative decision support for clinicians.

[0003] The current risk management of interventional ultrasound surgery for breast cancer is inadequate, mainly due to insufficient ability to integrate multidimensional real-time data and dynamically assess risks. It is unable to identify early malignant events and has not constructed a dynamic closed-loop feedback mechanism of tissue elastic deformation-energy deposition-physiological compensation. This results in risk warning relying on a lagging single indicator, making it impossible to accurately assess the evolution path of sudden risks during surgery, ultimately leading to delayed risk decision-making and blind spots in intraoperative safety control. Summary of the Invention

[0004] To address the shortcomings of existing breast interventional ultrasound surgery in risk management, the difficulty in accurately assessing the evolution path of sudden intraoperative risks, and the resulting delays in risk decision-making and blind spots in intraoperative safety control, this invention aims to provide a risk management method and system for breast interventional ultrasound surgery. The specific technical solution adopted is as follows:

[0005] This invention provides a risk management method for interventional ultrasound surgery of the breast, the method comprising:

[0006] By using the grayscale distribution histograms and elastic signal distribution histograms corresponding to the ultrasound images and elastography images simultaneously during surgery, respectively, the existence of initial risk to tissue elasticity can be determined.

[0007] By using the average temperature change rate of the energy action zone of the ablation device and the gray-scale gradient value of the anatomical boundary in the intraoperative ultrasound imaging, the presence of initial risk of energy deposition can be determined.

[0008] By utilizing the correlation between preoperative heart rate variability signals and breast microvascular blood flow signals in the surgical area, it can be determined whether there is an initial risk of physiological compensation.

[0009] By utilizing the overlap between the location of the initial risk type and the high-risk area identification results, similar cases in the historical surgical case database can be identified in combination with the initial risk type.

[0010] By using similar cases, the initial risk probability of escalation in the current surgical procedure is determined and the real-time risk probability is obtained. Risk alerts are then issued based on the real-time risk probability.

[0011] Furthermore, the determination of the existence of initial tissue elasticity risk using the grayscale distribution histograms and elasticity signal distribution histograms corresponding to the ultrasound images and elastography simultaneously during surgery includes:

[0012] Clustering was performed on the gray-level distribution histogram of ultrasound images and the elastic signal distribution histogram of elastography to obtain each gray-level interval and each elastic signal interval.

[0013] By traversing all combinations of grayscale intervals and elastic signal intervals, the grayscale signal entropy, elastic signal entropy, and joint entropy are obtained by using the respective distribution probabilities of the grayscale values ​​in the grayscale intervals and the elastic signals in the elastic signal intervals in the combinations.

[0014] The mutual information entropy of the combination is determined by using the gray signal entropy, elastic signal entropy and joint entropy, and the Young's modulus distribution matrix is ​​constructed by using the combination corresponding to the largest mutual information entropy;

[0015] The abnormal coefficients of the elastic gradient abnormal region are determined based on the Young's modulus distribution matrix, and the abnormal coefficients are used to determine whether there is an initial risk of tissue elasticity during the current surgical procedure.

[0016] Furthermore, the step of determining the anomalous coefficients of the elastic gradient anomalous region based on the Young's modulus distribution matrix, and using these anomalous coefficients to determine whether there is an initial risk to tissue elasticity during the current surgical procedure, includes:

[0017] The elastic gradient of a pixel is obtained by calculating the difference in Young's modulus between adjacent pixels based on the Young's modulus distribution matrix.

[0018] Pixels with elastic gradients greater than a preset multiple of the standard deviation of the elastic gradient of similar tissues before surgery are identified as abnormal elastic gradient pixels.

[0019] Continuous abnormal elastic gradient pixels are aggregated into an abnormal elastic gradient region. The abnormal coefficient is obtained by using the first area ratio of the abnormal elastic gradient region relative to the lesion edge region and the second area ratio of the normal tissue region.

[0020] If the anomaly coefficient is less than 1, it is determined that there is an initial risk of tissue elasticity during the current surgical procedure; otherwise, it is determined that there is no initial risk of tissue elasticity during the current surgical procedure.

[0021] Furthermore, the determination of the existence of initial risk of energy deposition by utilizing the average temperature change rate of the energy action zone of the ablation device in intraoperative ultrasound imaging and the grayscale gradient value of the anatomical boundary therein includes:

[0022] The average temperature change rate of the energy-affected area was determined by using the temperature change rate of each pixel in the energy-affected area of ​​the ablation instrument in the ultrasound image during surgery.

[0023] As the average temperature change rate of the energy-affected region continues to increase, the grayscale gradient values ​​of the boundary pixels of the anatomical boundary of the energy-affected region in the horizontal and vertical directions are obtained.

[0024] By using the average temperature change rate and their respective grayscale gradient values, it is determined whether there is an initial risk of energy deposition during the current surgical procedure.

[0025] Furthermore, the method of determining whether there is an initial risk of energy deposition during the current surgical procedure using the average temperature change rate and their respective grayscale gradient values ​​includes:

[0026] The edge intensity of the boundary pixels is obtained by using their respective grayscale gradient values, and the sharpness score of the energy zone is obtained by using the edge intensity of all boundary pixels.

[0027] If the average temperature change rate of the energy-affected area continues to increase and the clarity score shows a decrease for the first time, it is determined that there is an initial risk of energy deposition during the current surgical procedure.

[0028] Furthermore, the method of using the correlation between preoperative heart rate variability signals and breast microvascular blood flow signals in the surgical area to determine whether there is an initial risk of physiological compensation includes:

[0029] The Pearson correlation coefficient between the high-frequency components of the preoperative heart rate variability signal extracted by high-pass filtering and the microvascular blood flow signal in the surgical area of ​​the breast was determined, and the correlation change curve was obtained by using the Pearson correlation coefficient in multiple preset analysis periods.

[0030] If the correlation curve tilts negatively continuously within a preset number of analysis periods and the peak of blood flow rhythm appears continuously with a delay, it is determined that there is an initial risk of physiological compensation during the current surgical procedure.

[0031] Furthermore, the method of utilizing the overlap between the location of the initial risk type and the high-risk area identification results, combined with the initial risk type, to determine similar cases in the historical surgical case database includes:

[0032] The three-dimensional anatomical model of the breast reconstructed from the preoperative CT scan was retrieved, and high-risk condition areas were marked based on the anatomical structural characteristics to obtain the high-risk area labeling results;

[0033] The spatial overlap algorithm is used to determine the degree of overlap between the location of the initial risk type and the high-risk area calibration results, thereby determining the risk occurrence time of the initial risk type.

[0034] By utilizing the initial risk type, overlap, and time of risk occurrence, similar cases in the historical surgical case database are identified.

[0035] Furthermore, the step of determining the initial risk probability of escalation of the current surgical procedure risk using similar cases and obtaining the real-time risk probability, and then issuing a risk alert based on the real-time risk probability, includes:

[0036] The proportion of similar cases that escalate from the initial risk type to an explicit accident is determined as the initial risk probability and corresponding initial risk status of the current surgical procedure risk escalation;

[0037] Identify multiple surgical factors between the occurrence of the initial risk type and the appearance of the accident, and compare the actual values ​​of the surgical factors with the corresponding standard reference values ​​to determine the risk scenario in which they occur;

[0038] Determine the proportion of similar cases that transform from the initial risk state to other initial risk states under the target risk scenario, and use the proportion of similar cases as the element value of the transition matrix under the target risk scenario;

[0039] The real-time risk probability is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and risk alarms are generated based on the real-time risk probability.

[0040] Furthermore, the step of obtaining the real-time risk probability using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and then issuing a risk alarm based on the real-time risk probability, includes:

[0041] The transition probability of the target initial risk state transforming into other initial risk states is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario;

[0042] The initial risk probability is updated and the real-time risk probability is obtained by using all the corresponding transition probabilities in the transition matrix under the target risk scenario. The preset safety threshold is compared with the real-time risk probability to generate a risk alarm.

[0043] The present invention also provides a risk management system for breast interventional ultrasound surgery, the system being used to implement the risk management method for breast interventional ultrasound surgery as described in any of the preceding claims; the system comprising:

[0044] The risk analysis module is used to determine whether there is an initial risk of tissue elasticity using the gray-level distribution histogram and elastic signal distribution histogram corresponding to the ultrasound images and elastography images during surgery, respectively; to determine whether there is an initial risk of energy deposition using the average temperature change rate of the energy action zone of the ablation device in the ultrasound images during surgery and the gray-level gradient value of the anatomical boundary therein; and to determine whether there is an initial risk of physiological compensation using the correlation between the preoperative heart rate variability signal and the blood flow signal of the breast microvessels in the surgical area.

[0045] The risk alarm module is used to determine similar cases in the historical surgical case database by combining the overlap between the location of the initial risk type and the high-risk area calibration results with the initial risk type; it uses similar cases to determine the initial risk probability of the current surgical procedure risk escalation and obtains the real-time risk probability, and then performs risk alarms based on the real-time risk probability.

[0046] The present invention has the following beneficial effects:

[0047] This invention combines ultrasound image grayscale mapping with elastography mutual information entropy analysis to construct an intraoperative stable Young's modulus estimation model, effectively identifying abnormal diffusion of tissue elastic gradients and overcoming the bottleneck of inaccuracy in traditional elastography due to operational interference. It simultaneously integrates dynamic data on tissue deformation, energy deposition, and physiological compensation to achieve cross-validation of early risks such as carbonization precursors and microvascular injury. Furthermore, based on a state transition matrix, it fuses surgical operation parameters, anatomical condition superposition, and historical case evolution patterns in real time, predicting risk escalation paths through multi-scenario probability iteration. This solves the lag problem of traditional single-threshold early warning, providing doctors with precise judgment of risk intervention timing and reducing the risk of intraoperative complications. Attached Figure Description

[0048] Figure 1 A flowchart illustrating the steps of a risk management method for breast interventional ultrasound surgery according to an embodiment of the present invention;

[0049] Figure 2 This is a detailed flowchart of step S1 in a risk management method for breast interventional ultrasound surgery provided in an embodiment of the present invention;

[0050] Figure 3 This is a detailed flowchart of step S2 in a risk management method for breast interventional ultrasound surgery provided in an embodiment of the present invention;

[0051] Figure 4 This is a detailed flowchart of step S3 in a risk management method for breast interventional ultrasound surgery provided in an embodiment of the present invention;

[0052] Figure 5 This is a detailed flowchart of step S4 in a risk management method for breast interventional ultrasound surgery provided in an embodiment of the present invention;

[0053] Figure 6 This is a detailed flowchart of step S5 in a risk management method for breast interventional ultrasound surgery provided in an embodiment of the present invention;

[0054] Figure 7 This is a schematic diagram of the hardware operating environment of the risk management device for breast interventional ultrasound surgery involved in the embodiments of the present invention;

[0055] Figure 8 This is a schematic diagram of the framework structure of the risk management system for breast interventional ultrasound surgery involved in the embodiments of the present invention. Detailed Implementation

[0056] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a risk management method for breast interventional ultrasound surgery proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0058] The specific scheme of the risk management method for breast interventional ultrasound surgery provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Example 1:

[0060] For a risk management method for breast interventional ultrasound surgery provided by this invention, please refer to [link / reference needed]. Figure 1 The diagram illustrates a flowchart of a risk management method for breast interventional ultrasound surgery according to an embodiment of the present invention.

[0061] The risk management methods for the aforementioned breast interventional ultrasound surgery include:

[0062] Step S1: Using the grayscale distribution histogram and elastic signal distribution histogram corresponding to the ultrasound images and elastography images synchronized during surgery, respectively, determine whether there is an initial risk of tissue elasticity.

[0063] In this embodiment, the complete historical data of 500 or more breast interventional ultrasound surgeries can be screened first. At the same time, two types of invalid cases can be excluded: one type is cases with no risk events recorded throughout the process, and the other type is cases with more than 30% missing key monitoring items (such as instrument coordinates, energy parameters, and ultrasound imaging data). Finally, valid cases containing risk-related information are retained as the data basis for the following embodiments.

[0064] Specifically, please refer to Figure 2 Step S1 includes:

[0065] Step S11: Cluster the gray-level distribution histogram of ultrasound image and the elastic signal distribution histogram of elastography to obtain each gray-level interval and each elastic signal interval.

[0066] Step S12: Traverse all combinations of grayscale intervals and elastic signal intervals, and obtain the grayscale signal entropy, elastic signal entropy, and joint entropy by using the distribution probability of the grayscale value of the grayscale interval and the elastic signal of the elastic signal interval in the combination respectively.

[0067] Step S13: Determine the mutual information entropy of the combination using the gray signal entropy, elastic signal entropy, and joint entropy, and construct the Young's modulus distribution matrix using the combination corresponding to the largest mutual information entropy;

[0068] Step S14: Determine the abnormal coefficients of the abnormal elastic gradient region based on the Young's modulus distribution matrix, and use the abnormal coefficients to determine whether there is an initial risk of tissue elasticity during the current surgical procedure.

[0069] More specifically, step S14 includes:

[0070] The elastic gradient of a pixel is obtained by calculating the difference in Young's modulus between adjacent pixels based on the Young's modulus distribution matrix.

[0071] Pixels with elastic gradients greater than a preset multiple of the standard deviation of the elastic gradient of similar tissues before surgery are identified as abnormal elastic gradient pixels.

[0072] Continuous abnormal elastic gradient pixels are aggregated into an abnormal elastic gradient region. The abnormal coefficient is obtained by using the first area ratio of the abnormal elastic gradient region relative to the lesion edge region and the second area ratio of the normal tissue region.

[0073] If the anomaly coefficient is less than 1, it is determined that there is an initial risk of tissue elasticity during the current surgical procedure; otherwise, it is determined that there is no initial risk of tissue elasticity during the current surgical procedure.

[0074] In this embodiment, ultrasound elastography data (i.e., elastography) of the breast surgical area under static scanning is obtained from the data of each case. The anatomical boundaries of fat, breast glands, lesions and surrounding normal tissues are captured by edge segmentation to obtain the number of tissue regions m.

[0075] Before surgery, the Young's modulus of each tissue was maintained at the baseline level, with no abnormal elastic gradient areas, and the risk was in a latent state. Therefore, more than 5 typical sampling points were selected for each type of tissue (avoiding blood vessels and calcification points). After repeated measurements, the maximum and minimum values ​​were removed, and the average Young's modulus value of each type of tissue was calculated to obtain the baseline Young's modulus of different tissue types.

[0076] Then, when the puncture or ablation procedure is initiated, the instrument will apply pressure or energy to the tissue. The Young's modulus of the local tissue will deviate from the baseline. If sporadic abnormal pixels appear, it means that the risk may be starting to emerge.

[0077] However, once the surgical procedure begins, it disrupts the stable tissue environment of ultrasound elastography, significantly reducing the readability of ultrasound elastography information and resulting in a large number of false abnormalities. Ultrasound images, on the other hand, have better stability. In this embodiment, ultrasound images and ultrasound elastography are used simultaneously to map the stable gray values ​​of ultrasound images into elastic signal estimates, enabling the stable detection of tissue elasticity abnormalities during surgery.

[0078] Acquire simultaneous ultrasound and elastography data after the start of surgery, and perform probe offset calibration on both to avoid unnecessary error problems;

[0079] Next, the gray-level distribution histogram of the ultrasound image is obtained; the elastic signal (Young's modulus) distribution histogram of the elastography is obtained; and according to the number of tissue regions in the breast surgery area, all gray levels of the gray-level distribution histogram are clustered by k-means to obtain m gray-level intervals. At the same time, the elastic signal distribution histogram is also divided into m elastic signal intervals using k-means clustering.

[0080] By traversing all combinations of grayscale intervals and elastic signal intervals, we can obtain any grayscale interval corresponding to any elastic signal interval.

[0081] Next, the probability distribution of all gray values ​​in each gray range of the ultrasound image is statistically analyzed, and then the information entropy (gray signal entropy) in that gray range is calculated; similarly, for the probability distribution of all elastic signals in each elastic signal range in real-time elastic imaging, the information entropy (elastic signal entropy) in that elastic signal range is obtained.

[0082] Next, for all combinations of "grayscale interval - elastic signal interval", the joint probability of all grayscale values ​​in the grayscale interval and all elastic signal values ​​(Young's modulus) in the elastic signal interval is calculated. Then, the joint (information) entropy of each combination of "grayscale interval - elastic signal interval" is calculated. This entropy value reflects the uncertainty of the co-occurrence of the grayscale interval and the elastic signal interval.

[0083] Then, the mutual information entropy of each "grayscale interval - elastic signal interval" combination is calculated as: joint entropy - (grayscale signal entropy + elastic signal entropy), which is used to characterize the correlation between the above grayscale values ​​and the elastic signal.

[0084] Each combination of grayscale interval and elastic signal interval can output a mutual information entropy. With the grayscale interval fixed and the elastic signal as the variable, the combination with the maximum mutual information entropy among all combinations of grayscale intervals is selected as the target elastic signal interval corresponding to that grayscale interval.

[0085] All combinations of grayscale intervals and target elastic signal intervals can construct a Young's modulus distribution matrix;

[0086] The purpose of constructing this matrix is ​​to convert the gray values ​​in stable ultrasound images into Young's modulus, which can reflect tissue elasticity, in order to avoid the problem of unreliable elastic imaging information during surgery.

[0087] Based on the real-time Young's modulus distribution matrix, the difference in Young's modulus between adjacent pixels, i.e., the elastic gradient, is calculated. Pixels whose difference exceeds twice the elastic standard deviation of similar tissues before surgery (such as the edge area of ​​the lesion) (preset multiple, which can be adjusted) are called abnormal elastic gradient pixels (abnormal pixels for short).

[0088] During the surgical procedure, abnormal pixels spread through elastic gradients to form continuous abnormal regions. Using a region growing algorithm (existing technology), spatially continuous abnormal pixels are aggregated into complete elastic gradient abnormal regions (referred to as "abnormal regions"). At the same time, the tissue type to which the abnormal regions belong is marked by comparing with the preoperative anatomical boundaries, such as abnormal lesion edge regions, abnormal fat-gland junction regions, etc.

[0089] Calculate the first area ratio S1 of the abnormal region in the lesion edge region in consecutive frames, and the second area ratio S2 of the abnormal region in the normal tissue region in consecutive frames.

[0090] Anomaly coefficient = S1 / S2, which is the ratio of the first area proportion to the second area proportion.

[0091] If the abnormality coefficient is greater than or equal to 1, it means that the abnormal area accounts for a higher proportion of the area at the edge of the lesion and a lower proportion in the normal tissue area. It is determined that there is no initial risk of tissue elasticity during the current operation, but it suggests that the risk is more likely to come from lesion infiltration.

[0092] If the anomaly coefficient is less than 1, it means that the proportion of abnormal areas in normal tissue areas is relatively high, which indicates an initial risk to tissue elasticity and suggests that the risk is more likely to originate from tissue damage caused by the operation.

[0093] Step S2: Using the average temperature change rate of the energy action zone of the ablation device in the intraoperative ultrasound image and the grayscale gradient value of the anatomical boundary therein, determine whether there is an initial risk of energy deposition.

[0094] Specifically, please refer to Figure 3 Step S2 includes:

[0095] Step S21: Determine the average temperature change rate of the energy-acting area by using the temperature change rate of each pixel in the energy-acting area of ​​the ablation instrument in the ultrasound image during surgery.

[0096] Step S22: As the average temperature change rate of the energy-affected area continues to increase, obtain the grayscale gradient values ​​of the boundary pixels of the anatomical boundary of the energy-affected area in the horizontal and vertical directions.

[0097] Step S23: Using the average temperature change rate and their respective grayscale gradient values, determine whether there is an initial risk of energy deposition during the current surgical procedure.

[0098] More specifically, step S23 includes:

[0099] The edge intensity of the boundary pixels is obtained by using their respective grayscale gradient values, and the sharpness score of the energy zone is obtained by using the edge intensity of all boundary pixels.

[0100] If the average temperature change rate of the energy-affected area continues to increase and the clarity score shows a decrease for the first time, it is determined that there is an initial risk of energy deposition during the current surgical procedure.

[0101] In this embodiment, the position of the electrode tip of the ablation device is identified by ultrasound imaging. A circular energy action area is set with the tip as the center according to the natural energy diffusion range of the ablation device. Then, the energy action area is marked on the ultrasound image by an image overlay algorithm (existing technology). The anatomical structure of the energy action area, including glandular ducts, microvessels, etc., is recorded simultaneously and is called the sensitive structure.

[0102] Next, adjust the acquisition frequency of the ultrasonic thermal imaging module to align it with the energy output timing of the ablation device, ensuring that a thermal imaging image is acquired every 0.5 seconds, synchronized with the energy output status;

[0103] The rate of temperature change in the energy-affected area is calculated by taking the temperature difference of the same pixel in two consecutive frames of the synchronized thermal imaging image and dividing it by the time interval between the two frames to obtain the rate of temperature change of that pixel. Finally, the average rate of temperature change of the entire energy-affected area is calculated by the regional averaging algorithm.

[0104] When the temperature change rate of the energy-affected area increases further, the gray value rises sharply and the clarity decreases significantly, this may indicate a precursor to carbonization. The formation of carbonized tissue can lead to blind spots in ultrasound imaging and increase the risk of needle tract adhesion, thus escalating the risk.

[0105] Therefore, for areas where the rate of temperature change continues to increase, the grayscale value and clarity of ultrasound images should be monitored simultaneously.

[0106] The Canny edge detection algorithm is used to extract pixels of anatomical boundaries (such as lesion edges and blood vessel contours) in images. The gray-level gradient values ​​of each boundary pixel in the horizontal and vertical directions are calculated, and the square root of the sum of the two is taken as the edge intensity of that point. Then, the arithmetic mean of the edge intensity of all boundary pixels is taken to obtain the sharpness score. The higher the value, the clearer the boundary.

[0107] If the clarity score is lower than before the temperature rise, carbonization precursors can be further confirmed. That is, when the clarity score first drops, it can be determined that there is an initial risk of energy deposition during the current surgery.

[0108] Furthermore, when the carbonized area overlaps with microvessels, thermal damage may trigger the risk of microvessel rupture. At the same time, the imaging blind spot may prevent doctors from accurately controlling the instrument, further aggravating the risk of energy deposition and tissue damage.

[0109] The carbonization precursor identification results are compared with the anatomical structure annotation results of the energy action zone to determine whether the carbonization region contains sensitive structures such as microvessels and glandular ducts.

[0110] If the above-mentioned sensitive structures are included, the overlap area between the carbonized region and the sensitive structure is further calculated: first, the outlines of the carbonized region and the sensitive structure (microvessels, glandular ducts) are binarized, the total number of pixels in the overlap area is counted, and then the number of pixels is converted into the actual anatomical overlap area according to the pixel-actual size conversion ratio inherent in ultrasound images.

[0111] If the rate of temperature change continues to increase (the slope of temperature change in consecutive frames is positive) and the overlapping area expands (the slope of overlapping area change in consecutive frames is positive), it indicates an increased risk of damage.

[0112] Step S3: Utilize the correlation between preoperative heart rate variability signals and breast microvascular blood flow signals in the surgical area to determine whether there is an initial risk of physiological compensation.

[0113] Specifically, please refer to Figure 4 Step S3 includes:

[0114] Step S31: Determine the Pearson correlation coefficient between the high-frequency component of the preoperative heart rate variability signal extracted by high-pass filtering and the microvascular blood flow signal of the breast in the surgical area, and obtain the correlation change curve using the Pearson correlation coefficient in multiple preset analysis periods.

[0115] Step S32: If the correlation change curve tilts negatively continuously within a preset number of analysis cycles and the peak of blood flow rhythm appears continuously with a delay, it is determined that there is an initial risk of physiological compensation during the current surgical procedure.

[0116] In this embodiment, heart rate variability (HRV) signals and microvascular blood flow signals in the surgical area of ​​the breast were collected from the patient in a stable state 10 minutes before surgery. The high-frequency components of HRV (high-pass filtered extraction, generally between 0.15 Hz and 0.40 Hz) were calculated through a sliding window of 1 minute to reflect vagal nerve activity. The Pearson correlation coefficient between the high-frequency components of HRV and the microvascular blood flow pulsation cycle within the same sliding window was calculated as the correlation (degree) between the two. The above calculation was repeated 5 times and the stable value was taken as the basic correlation benchmark for physiological compensation.

[0117] The correlation calculation is repeated three times (minutes 1, 3, and 5) within each 5-minute analysis cycle, resulting in correlation values ​​for three cycles (multiple preset analysis cycles, which can be adjusted). A correlation change curve is generated through linear fitting. The slope of the curve is observed. If the slope changes from positive to negative, it means that the correlation has changed from stable to decreasing. If the slope remains negative for two consecutive cycles (preset number, which can be adjusted) and the absolute value continues to increase, it indicates that the neural-blood flow compensation synergy is beginning to be unbalanced.

[0118] For cycles with decreased correlation, the time-domain curves of microvascular blood flow velocity within the corresponding cycles are extracted. The fluctuation rhythm of blood flow velocity is identified by the peak detection algorithm. During normal compensation, the rhythm should be consistent with the HRV fluctuation. If the peak of the blood flow rhythm is delayed compared with the HRV fluctuation and occurs 5 times in a row, it further verifies the synchronicity disruption of the neuro-blood flow compensation regulation.

[0119] In summary, if the correlation curve shows a negative slope for two consecutive cycles and the blood flow rhythm peak is delayed for five consecutive cycles, it is considered a preliminary risk event of physiological compensation abnormality, i.e., the initial risk of physiological compensation.

[0120] Step S4: Utilize the overlap between the location of the initial risk type and the high-risk area identification results, and combine the initial risk type to determine similar cases in the historical surgical case database;

[0121] Based on the monitoring results of the three initial risk types (initial risk of tissue elasticity, initial risk of energy deposition, and initial risk of physiological compensation), the intraoperative initial risks in all cases were identified and summarized as follows:

[0122] a. If an abnormal elasticity region spreads across the organizational boundary during organizational elasticity monitoring, i.e., the abnormality coefficient is less than 1, it is determined to be an initial risk to organizational elasticity.

[0123] b. If the temperature change rate continues to rise and the clarity decreases for the first time in the energy deposition monitoring, it indicates the presence of carbonization precursors and is judged as the initial risk of energy deposition.

[0124] c. If the correlation curve shows a negative tilt for two consecutive cycles and the peak blood flow rhythm is delayed for five consecutive times in the physiological compensation monitoring, it is determined to be the initial risk of physiological compensation.

[0125] For each type of initial risk event, its occurrence time, anatomical location, and associated operation type are recorded to form an initial risk file, which provides starting data for subsequent risk accumulation analysis.

[0126] Specifically, please refer to Figure 5 Step S4 includes:

[0127] Step S41: Retrieve the three-dimensional anatomical model of the breast reconstructed by CT before surgery, and mark the high-risk condition area based on the anatomical structural characteristics to obtain the high-risk area labeling result;

[0128] Step S42: Use the spatial overlap algorithm to determine the overlap between the location of the initial risk type and the high-risk area calibration result, and determine the risk occurrence time of the initial risk type;

[0129] Step S43: Using the initial risk type, overlap, and risk occurrence time, identify similar cases in the historical surgical case database.

[0130] In this embodiment, the three-dimensional anatomical model of the breast reconstructed by preoperative CT (Computed Tomography) is retrieved, and high-risk condition areas are marked based on anatomical structural characteristics to obtain high-risk area labeling results. For example, the lung tissue adjacent area is defined based on the natural adjacency relationship between the lower border of the breast and the lung tissue, the large blood vessel dense area is defined based on the blood vessel distribution marked by preoperative ultrasound, and the nerve course area is defined based on the matching of anatomical atlas and preoperative images, etc., to provide spatial basis for subsequent judgment on whether the initial risk is superimposed with high-risk conditions.

[0131] Based on the location of risks a and b in the initial risk file and the high-risk area marking results, the overlap degree is calculated using the spatial overlap degree algorithm (existing technology): First, the initial risk occurrence area and the high-risk area are transformed into polygons in the same coordinate system, and then the ratio of the area of ​​the overlapping area to the area of ​​the initial risk area is calculated. This ratio is the overlap degree.

[0132] The higher the degree of overlap, the greater the intensity of accumulated risk;

[0133] For example, when the initial risk area of ​​needle tract deviation has a high degree of overlap with the adjacent area of ​​lung tissue (assuming 40%), it indicates that the initial risk has partially superimposed high-risk conditions, and the risk is relatively high.

[0134] Based on the identified risk type, if it is identified as 'a', the superposition degree of risk 'a' is obtained; if it is identified as 'b', the superposition degree of risk 'b' is obtained; at the same time, the occurrence time of risks 'a' and 'b' after the start of surgery is obtained.

[0135] If it is c, then only the time when risk c occurs after the start of surgery is obtained;

[0136] Different surgical cases can yield different initial risk events;

[0137] Dynamically predict the probability of risk escalation and issue risk warnings:

[0138] During the current surgery, if any of the above-mentioned risk events are triggered, the database of similar historical surgical cases is retrieved, and similar cases with similar "initial risk type, superposition degree, and risk occurrence time" are selected (the corresponding text can be converted into vectors to calculate the similarity of the directional quantities, such as cosine similarity, existing technology). The proportion of cases in which the initial risk escalates into overt accidents (bleeding, pneumothorax, tissue necrosis) is statistically analyzed.

[0139] Step S5: Use similar cases to determine the initial risk probability of the current surgical procedure risk escalation and obtain the real-time risk probability, and issue a risk alarm based on the real-time risk probability.

[0140] Specifically, please refer to Figure 6 Step S5 includes:

[0141] Step S51: Determine the proportion of similar cases that escalate from the initial risk type to an overt accident as the initial risk probability and the corresponding initial risk state of the current surgical procedure risk escalation;

[0142] Step S52: Identify multiple surgical factors between the occurrence of the initial risk type and the appearance of the accident, and compare the actual values ​​of the surgical factors with the corresponding standard reference values ​​to determine the risk scenario in which they occur;

[0143] Step S53: Determine the proportion of similar cases that have transformed from the target initial risk state to other initial risk states under the target risk scenario, and use the proportion of similar cases as the element value of the transition matrix under the target risk scenario;

[0144] Step S54: Obtain the real-time risk probability using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and issue a risk alarm based on the real-time risk probability.

[0145] More specifically, step S54 includes:

[0146] The transition probability of the target initial risk state transforming into other initial risk states is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario;

[0147] The initial risk probability is updated and the real-time risk probability is obtained by using all the corresponding transition probabilities in the transition matrix under the target risk scenario. The preset safety threshold is compared with the real-time risk probability to generate a risk alarm.

[0148] Based on the above embodiments, after statistically analyzing the proportion of initial risks escalating into overt accidents (bleeding, pneumothorax, tissue necrosis) in the cases, this proportion is used as the initial risk probability of risk escalation in the current surgical procedure.

[0149] Then, based on these cases, we organize multiple surgical factors (the more the better) between the occurrence of initial intraoperative risks and the emergence of manifest accidents, such as surgical procedures, surgical instrument parameters, and patient physiological data, and perform state transitions on the initial probabilities:

[0150] First, define 5 levels (initial) of risk status. Divide the initial risk probability range of 0-100% into risk levels in 20% increments: S0 Basic Risk (0-20%); S1 Low Risk Escalation (20%-40%); S2 Medium Risk Escalation (40%-60%); S3 High Risk Escalation (60%-80%); S4 Obvious Accident (80%-100%).

[0151] Based on the initial risk probability of the current surgical procedure, determine its initial risk level, denoted as . ;

[0152] Based on the degree of abnormality of the factors (i.e., the degree of difference between the actual value of the surgical factors and the standard reference value of each factor), three risk scenarios are divided: normal, slightly abnormal, and significantly abnormal; different degrees of abnormality of factors will directly change the transformation pattern of risk status;

[0153] Then, the risk status was statistically analyzed for each type of risk scenario (normal, mildly abnormal, significantly abnormal). (As the initial risk state of the target) transformed into The percentage of similar cases (as other initial risk states) is used as the element at the corresponding position in the (state) transition matrix. The values ​​form a transfer matrix specific to three risk scenarios;

[0154] The matrix has horizontal and vertical axes S0, S1, S2, S3, and S4; the elements in the matrix both exist... (The element in the i-th row and j-th column) also exists (The element in the j-th row and j-th column) can be represented in one of the following ways: that is, there is both risk escalation and risk downgrade.

[0155] Then, starting from the initial risk probability, factor data is collected in real time every cycle (10s) and matched with the corresponding abnormal scenario, and the transition matrix of the scenario is called.

[0156] The initial risk may change from the original risk state to any other risk state;

[0157] Multiply the initial risk probability by the transition probability of each row in the transition matrix. That is, the transition probability of the initial risk transforming into any other risk state. By summing all the transition probabilities and updating the initial risk probability, the real-time risk probability is obtained.

[0158] Then, in the next cycle (10s), the state transition matrix is ​​updated based on the real-time collected factor data. At the same time, the updated state transition matrix and risk probability are used to continue iteratively updating, and this process is repeated continuously to achieve real-time prediction of surgical risk.

[0159] When the predicted real-time risk probability exceeds the preset safety threshold, such as exceeding 50% (medium-risk sustained stage, the specific value can be adjusted), a risk alarm will be triggered.

[0160] This invention combines ultrasound image grayscale mapping with elastography mutual information entropy analysis to construct an intraoperative stable Young's modulus estimation model, effectively identifying abnormal diffusion of tissue elastic gradients and overcoming the bottleneck of inaccuracy in traditional elastography due to operational interference. It simultaneously integrates dynamic data on tissue deformation, energy deposition, and physiological compensation to achieve cross-validation of early risks such as carbonization precursors and microvascular injury. Furthermore, based on a state transition matrix, it fuses surgical operation parameters, anatomical condition superposition, and historical case evolution patterns in real time, predicting risk escalation paths through multi-scenario probability iteration. This solves the lag problem of traditional single-threshold early warning, providing doctors with precise judgment of risk intervention timing and reducing the risk of intraoperative complications.

[0161] Example 2:

[0162] This invention also proposes a risk management device for breast interventional ultrasound surgery. The device can be a computer, server, or other data analysis and computing equipment, or a combination of multiple devices.

[0163] like Figure 7 As shown, Figure 7 This is a schematic diagram of the hardware operating environment of the risk management device for breast interventional ultrasound surgery involved in the embodiments of the present invention.

[0164] like Figure 7As shown, the risk management device for breast interventional ultrasound surgery may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display or an input unit such as a control panel; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, may include the risk management program for breast interventional ultrasound surgery.

[0165] Those skilled in the art will understand that Figure 7 The hardware structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0166] Continue to refer to Figure 7 , Figure 7 The memory 1005, which is a computer-readable storage medium, may include an operating system, a user interface module, a network communication module, and a risk management program for breast interventional ultrasound surgery.

[0167] exist Figure 7 In this embodiment, the network communication module is mainly used to connect to the server and can communicate with the server for data; while the processor 1001 can call the risk management program for breast interventional ultrasound surgery stored in the memory 1005 and execute the steps in the above embodiments.

[0168] Based on the hardware structure of the risk management device for breast interventional ultrasound surgery described above, various embodiments of the risk management method for breast interventional ultrasound surgery of the present invention are implemented.

[0169] In addition, the present invention also provides a risk management system for breast interventional ultrasound surgery, please refer to... Figure 8 The risk management system for the breast interventional ultrasound surgery includes:

[0170] The risk analysis module A10 is used to determine whether there is an initial risk of tissue elasticity by using the gray-level distribution histogram and elastic signal distribution histogram corresponding to the ultrasound images and elastography images during surgery, respectively; to determine whether there is an initial risk of energy deposition by using the average temperature change rate of the energy action zone of the ablation device in the ultrasound images during surgery and the gray-level gradient value of the anatomical boundary therein; and to determine whether there is an initial risk of physiological compensation by using the correlation between the preoperative heart rate variability signal and the breast microvascular blood flow signal in the surgical area.

[0171] The risk alarm module A20 is used to determine similar cases in the historical surgical case database by combining the overlap between the location of the initial risk type and the high-risk area calibration results with the initial risk type; it uses similar cases to determine the initial risk probability of the current surgical procedure risk escalation and obtains the real-time risk probability, and performs risk alarms based on the real-time risk probability.

[0172] Furthermore, the risk analysis module A10 is also used for:

[0173] Clustering was performed on the gray-level distribution histogram of ultrasound images and the elastic signal distribution histogram of elastography to obtain each gray-level interval and each elastic signal interval.

[0174] By traversing all combinations of grayscale intervals and elastic signal intervals, the grayscale signal entropy, elastic signal entropy, and joint entropy are obtained by using the respective distribution probabilities of the grayscale values ​​in the grayscale intervals and the elastic signals in the elastic signal intervals in the combinations.

[0175] The mutual information entropy of the combination is determined by using the gray signal entropy, elastic signal entropy and joint entropy, and the Young's modulus distribution matrix is ​​constructed by using the combination corresponding to the largest mutual information entropy;

[0176] The abnormal coefficients of the elastic gradient abnormal region are determined based on the Young's modulus distribution matrix, and the abnormal coefficients are used to determine whether there is an initial risk of tissue elasticity during the current surgical procedure.

[0177] Furthermore, the risk analysis module A10 is also used for:

[0178] The elastic gradient of a pixel is obtained by calculating the difference in Young's modulus between adjacent pixels based on the Young's modulus distribution matrix.

[0179] Pixels with elastic gradients greater than a preset multiple of the standard deviation of the elastic gradient of similar tissues before surgery are identified as abnormal elastic gradient pixels.

[0180] Continuous abnormal elastic gradient pixels are aggregated into an abnormal elastic gradient region. The abnormal coefficient is obtained by using the first area ratio of the abnormal elastic gradient region relative to the lesion edge region and the second area ratio of the normal tissue region.

[0181] If the anomaly coefficient is less than 1, it is determined that there is an initial risk of tissue elasticity during the current surgical procedure; otherwise, it is determined that there is no initial risk of tissue elasticity during the current surgical procedure.

[0182] Furthermore, the risk analysis module A10 is also used for:

[0183] The average temperature change rate of the energy-affected area was determined by using the temperature change rate of each pixel in the energy-affected area of ​​the ablation instrument in the ultrasound image during surgery.

[0184] As the average temperature change rate of the energy-affected region continues to increase, the grayscale gradient values ​​of the boundary pixels of the anatomical boundary of the energy-affected region in the horizontal and vertical directions are obtained.

[0185] By using the average temperature change rate and their respective grayscale gradient values, it is determined whether there is an initial risk of energy deposition during the current surgical procedure.

[0186] Furthermore, the risk analysis module A10 is also used for:

[0187] The edge intensity of the boundary pixels is obtained by using their respective grayscale gradient values, and the sharpness score of the energy zone is obtained by using the edge intensity of all boundary pixels.

[0188] If the average temperature change rate of the energy-affected area continues to increase and the clarity score shows a decrease for the first time, it is determined that there is an initial risk of energy deposition during the current surgical procedure.

[0189] Furthermore, the risk analysis module A10 is also used for:

[0190] The Pearson correlation coefficient between the high-frequency components of the preoperative heart rate variability signal extracted by high-pass filtering and the microvascular blood flow signal in the surgical area of ​​the breast was determined, and the correlation change curve was obtained by using the Pearson correlation coefficient in multiple preset analysis periods.

[0191] If the correlation curve tilts negatively continuously within a preset number of analysis periods and the peak of blood flow rhythm appears continuously with a delay, it is determined that there is an initial risk of physiological compensation during the current surgical procedure.

[0192] Furthermore, the risk alarm module A20 is also used for:

[0193] The three-dimensional anatomical model of the breast reconstructed from the preoperative CT scan was retrieved, and high-risk condition areas were marked based on the anatomical structural characteristics to obtain the high-risk area labeling results;

[0194] The spatial overlap algorithm is used to determine the degree of overlap between the location of the initial risk type and the high-risk area calibration results, thereby determining the risk occurrence time of the initial risk type.

[0195] By utilizing the initial risk type, overlap, and time of risk occurrence, similar cases in the historical surgical case database are identified.

[0196] Furthermore, the risk alarm module A20 is also used for:

[0197] The proportion of similar cases that escalate from the initial risk type to an explicit accident is determined as the initial risk probability and corresponding initial risk status of the current surgical procedure risk escalation;

[0198] Identify multiple surgical factors between the occurrence of the initial risk type and the appearance of the accident, and compare the actual values ​​of the surgical factors with the corresponding standard reference values ​​to determine the risk scenario in which they occur;

[0199] Determine the proportion of similar cases that transform from the initial risk state to other initial risk states under the target risk scenario, and use the proportion of similar cases as the element value of the transition matrix under the target risk scenario;

[0200] The real-time risk probability is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and risk alarms are generated based on the real-time risk probability.

[0201] Furthermore, the risk alarm module A20 is also used for:

[0202] The transition probability of the target initial risk state transforming into other initial risk states is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario;

[0203] The initial risk probability is updated and the real-time risk probability is obtained by using all the corresponding transition probabilities in the transition matrix under the target risk scenario. The preset safety threshold is compared with the real-time risk probability to generate a risk alarm.

[0204] The specific implementation of the risk management system for breast interventional ultrasound surgery of the present invention is basically the same as the various embodiments of the risk management method for breast interventional ultrasound surgery described above, and will not be repeated here.

[0205] Furthermore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium of the present invention stores a risk management program for breast interventional ultrasound surgery, wherein, when executed by a processor, the risk management program for breast interventional ultrasound surgery implements the steps of the risk management method for breast interventional ultrasound surgery as described above.

[0206] The method for implementing the risk management procedure of breast interventional ultrasound surgery can be referred to in various embodiments of the risk management method of breast interventional ultrasound surgery of the present invention, and will not be repeated here.

[0207] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0208] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0209] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A risk management method for breast interventional ultrasound surgery, characterized in that, The method includes: By using the grayscale distribution histograms and elastic signal distribution histograms corresponding to the ultrasound images and elastography images simultaneously during surgery, respectively, the existence of initial risk to tissue elasticity can be determined. By using the average temperature change rate of the energy action zone of the ablation device and the gray-scale gradient value of the anatomical boundary in the intraoperative ultrasound imaging, the presence of initial risk of energy deposition can be determined. By utilizing the correlation between preoperative heart rate variability signals and breast microvascular blood flow signals in the surgical area, it can be determined whether there is an initial risk of physiological compensation. By utilizing the overlap between the location of the initial risk type and the high-risk area identification results, similar cases in the historical surgical case database can be identified in combination with the initial risk type. By using similar cases, the initial risk probability of escalation in the current surgical procedure is determined and the real-time risk probability is obtained. Risk alerts are then issued based on the real-time risk probability.

2. The risk management method for breast interventional ultrasound surgery according to claim 1, characterized in that, The method of using the grayscale distribution histograms and elastic signal distribution histograms corresponding to synchronous ultrasound images and elastography during surgery, respectively, to determine whether there is an initial risk of tissue elasticity loss includes: Clustering was performed on the gray-level distribution histogram of ultrasound images and the elastic signal distribution histogram of elastography to obtain each gray-level interval and each elastic signal interval. By traversing all combinations of grayscale intervals and elastic signal intervals, the grayscale signal entropy, elastic signal entropy, and joint entropy are obtained by using the respective distribution probabilities of the grayscale values ​​in the grayscale intervals and the elastic signals in the elastic signal intervals in the combinations. The mutual information entropy of the combination is determined by using the gray signal entropy, elastic signal entropy and joint entropy, and the Young's modulus distribution matrix is ​​constructed by using the combination corresponding to the largest mutual information entropy; The abnormal coefficients of the elastic gradient abnormal region are determined based on the Young's modulus distribution matrix, and the abnormal coefficients are used to determine whether there is an initial risk of tissue elasticity during the current surgical procedure.

3. The risk management method for breast interventional ultrasound surgery according to claim 2, characterized in that, The method of determining the abnormal coefficients of the elastic gradient abnormality region based on the Young's modulus distribution matrix, and using the abnormal coefficients to determine whether there is an initial risk of tissue elasticity during the current surgical procedure, includes: The elastic gradient of a pixel is obtained by calculating the difference in Young's modulus between adjacent pixels based on the Young's modulus distribution matrix. Pixels with elastic gradients greater than a preset multiple of the standard deviation of the elastic gradient of similar tissues before surgery are identified as abnormal elastic gradient pixels. Continuous abnormal elastic gradient pixels are aggregated into an abnormal elastic gradient region. The abnormal coefficient is obtained by using the first area ratio of the abnormal elastic gradient region relative to the lesion edge region and the second area ratio of the normal tissue region. If the anomaly coefficient is less than 1, it is determined that there is an initial risk of tissue elasticity during the current surgical procedure; otherwise, it is determined that there is no initial risk of tissue elasticity during the current surgical procedure.

4. The risk management method for breast interventional ultrasound surgery according to claim 1, characterized in that, The method of determining the existence of initial risk of energy deposition by utilizing the average temperature change rate of the energy-acting area of ​​the ablation device in intraoperative ultrasound imaging and the grayscale gradient value of the anatomical boundary therein includes: The average temperature change rate of the energy-affected area was determined by using the temperature change rate of each pixel in the energy-affected area of ​​the ablation instrument in the ultrasound image during surgery. As the average temperature change rate of the energy-affected region continues to increase, the grayscale gradient values ​​of the boundary pixels of the anatomical boundary of the energy-affected region in the horizontal and vertical directions are obtained. By using the average temperature change rate and their respective grayscale gradient values, it is determined whether there is an initial risk of energy deposition during the current surgical procedure.

5. The risk management method for breast interventional ultrasound surgery according to claim 4, characterized in that, The method of determining whether there is an initial risk of energy deposition during the current surgical procedure by using the average temperature change rate and their respective grayscale gradient values ​​includes: The edge intensity of the boundary pixels is obtained by using their respective grayscale gradient values, and the sharpness score of the energy zone is obtained by using the edge intensity of all boundary pixels. If the average temperature change rate of the energy-affected area continues to increase and the clarity score shows a decrease for the first time, it is determined that there is an initial risk of energy deposition during the current surgical procedure.

6. The risk management method for breast interventional ultrasound surgery according to claim 1, characterized in that, The method of using the correlation between preoperative heart rate variability signals and breast microvascular blood flow signals in the surgical area to determine whether there is an initial risk of physiological compensation includes: The Pearson correlation coefficient between the high-frequency components of the preoperative heart rate variability signal extracted by high-pass filtering and the microvascular blood flow signal in the surgical area of ​​the breast was determined, and the correlation change curve was obtained by using the Pearson correlation coefficient in multiple preset analysis periods. If the correlation curve tilts negatively continuously within a preset number of analysis periods and the peak of blood flow rhythm appears continuously with a delay, it is determined that there is an initial risk of physiological compensation during the current surgical procedure.

7. The risk management method for breast interventional ultrasound surgery according to claim 1, characterized in that, The method of utilizing the overlap between the location of the initial risk type and the high-risk area identification results, combined with the initial risk type, to determine similar cases in the historical surgical case database includes: The three-dimensional anatomical model of the breast reconstructed from the preoperative CT scan was retrieved, and high-risk condition areas were marked based on the anatomical structural characteristics to obtain the high-risk area labeling results; The spatial overlap algorithm is used to determine the degree of overlap between the location of the initial risk type and the high-risk area calibration results, thereby determining the risk occurrence time of the initial risk type. By utilizing the initial risk type, overlap, and time of risk occurrence, similar cases in the historical surgical case database are identified.

8. The risk management method for breast interventional ultrasound surgery according to claim 1, characterized in that, The process of determining the initial risk probability of escalation in the current surgical procedure using similar cases and obtaining the real-time risk probability, and then issuing a risk alert based on the real-time risk probability, includes: The proportion of similar cases that escalate from the initial risk type to an explicit accident is determined as the initial risk probability and corresponding initial risk status of the current surgical procedure risk escalation; Identify multiple surgical factors between the occurrence of the initial risk type and the appearance of the accident, and compare the actual values ​​of the surgical factors with the corresponding standard reference values ​​to determine the risk scenario in which they occur; Determine the proportion of similar cases that transform from the initial risk state to other initial risk states under the target risk scenario, and use the proportion of similar cases as the element value of the transition matrix under the target risk scenario; The real-time risk probability is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and risk alarms are generated based on the real-time risk probability.

9. The risk management method for breast interventional ultrasound surgery according to claim 8, characterized in that, The process of obtaining the real-time risk probability using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario, and then issuing a risk alarm based on the real-time risk probability, includes: The transition probability of the target initial risk state transforming into other initial risk states is obtained by using the initial risk probability and the element values ​​of the transition matrix under the target risk scenario; The initial risk probability is updated and the real-time risk probability is obtained by using all the corresponding transition probabilities in the transition matrix under the target risk scenario. The preset safety threshold is compared with the real-time risk probability to generate a risk alarm.

10. A risk management system for interventional ultrasound surgery of the breast, characterized in that, The system is used to implement the risk management method for breast interventional ultrasound surgery as described in any one of claims 1 to 9; the system includes: The risk analysis module is used to determine whether there is an initial risk of tissue elasticity using the gray-level distribution histogram and elastic signal distribution histogram corresponding to the ultrasound images and elastography images during surgery, respectively; to determine whether there is an initial risk of energy deposition using the average temperature change rate of the energy action zone of the ablation device in the ultrasound images during surgery and the gray-level gradient value of the anatomical boundary therein; and to determine whether there is an initial risk of physiological compensation using the correlation between the preoperative heart rate variability signal and the blood flow signal of the breast microvessels in the surgical area. The risk alarm module is used to determine similar cases in the historical surgical case database by combining the overlap between the location of the initial risk type and the high-risk area calibration results with the initial risk type; it uses similar cases to determine the initial risk probability of the current surgical procedure risk escalation and obtains the real-time risk probability, and then performs risk alarms based on the real-time risk probability.

Images