Intelligent identification method and system for breast rotary cutting tissue characteristics

Abstract

The invention discloses an intelligent identification method and system for breast rotary cutting tissue characteristics, the system collects tissue characteristic data in real time in the rotary cutting process, an innovative signal processing and pattern recognition algorithm is adopted for analysis, and the type and characteristics of cut tissue can be identified with high precision. The method comprises the steps of real-time data acquisition, signal preprocessing, feature parameter extraction, intelligent classification and recognition and the like, and the recognition accuracy is improved through parameter self-adaptive adjustment and optimization. The system is composed of a sensing module, a data processing module, a mode recognition module and an output interaction module, can be compatible with various rotary cutting devices and supports various data formats through a standardized interface. The system can output tissue category information in real time according to an identification result, and automatically adjust working parameters of the rotary cutting equipment when necessary, so as to ensure that the cutting effect is stable and reliable under different tissue conditions. According to the method, real-time intelligent identification of tissue characteristics in the breast rotary cutting biopsy operation is realized, and the accuracy and efficiency are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical devices and signal processing technology, in particular to a breast vacuum-assisted core needle biopsy tissue property intelligent identification method and system. BACKGROUND

[0002] Vacuum-assisted core needle biopsy has been widely used in minimally invasive diagnosis and resection of suspicious lesions in the breast. However, the existing core needle biopsy system mainly relies on intraoperative image guidance and the experience of the operator, and lacks accurate technical means for real-time judgment of tissue properties. For example, in the prior art, the physician usually judges whether the target lesion tissue is removed according to the appearance of the extracted tissue or the postoperative image. Some systems provide real-time imaging verification function or set "dense tissue mode" and other presets to manually cope with different tissue densities. However, these methods either verify after tissue sampling and cannot provide immediate feedback on the tissue properties during the cutting process, or require manual judgment and mode switching, making it difficult to accurately identify different types of tissue in a timely and accurate manner. As a result, the problem of inaccurate identification of tissue properties in breast core needle biopsy is still prominent: the ability to intelligently judge whether the cut tissue is lesion tissue or its density is not available during the operation, which may lead to insufficient resection or normal tissue mis-cut, affecting the efficiency and accuracy of diagnosis and treatment.

[0003] Therefore, there is an urgent need for a technical solution that can identify the properties of the tissue in real time and accurately during the breast core needle biopsy process to address the shortcomings of the prior art in terms of the inability to intelligently identify tissue types and properties. SUMMARY

[0004] Technical purpose: In view of the defect of inaccurate identification of tissue properties in breast core needle biopsy in the prior art, the present application discloses a breast core needle biopsy tissue property intelligent identification method and system, which can collect and analyze tissue property data in real time during the core needle biopsy process, intelligently and accurately identify the properties of the cut tissue, and significantly improve the accuracy and efficiency of the core needle biopsy.

[0005] Technical solution: In order to achieve the above technical purpose, the present application adopts the following technical solution:

[0006] A breast core needle biopsy tissue property intelligent identification method, specifically comprising the following steps:

[0007] During the breast core needle biopsy procedure, the signal data representing the properties of the tissue are acquired in real time by a sensing module, and the signal data at least includes the motor current signal and the vacuum negative pressure signal of the core needle biopsy device during operation;

[0008] The collected signal data is filtered, denoised and calibrated to obtain effective signals reflecting the state of tissue cutting;

[0009] a plurality of characteristic parameters representing the tissue properties are extracted from the processed effective signals, including the motor load characteristics and the negative pressure variation characteristics during the cutting process;

[0010] the extracted characteristic parameters are input into a pre-trained pattern recognition model, and a pattern recognition algorithm is used to classify and identify the characteristics of the current resected tissue, to obtain a tissue characteristic identification result;

[0011] output information is generated according to the identification result, and the output information is provided to the surgical operator or the device control unit to indicate the tissue characteristics or to adjust the working parameters of the rotary cutting device accordingly.

[0012] Preferably, the sensing module includes a plurality of sensors for acquiring different types of signal data, including at least one selected from the following signals: motor drive current signal, rotary cutting needle head vibration signal, vacuum suction pressure signal, acoustic signal, optical spectrum signal and bioelectric impedance signal.

[0013] Preferably, adaptive filtering or wavelet transform is used to denoise the signal data, and baseline calibration is performed on the motor current signal to eliminate the influence of device static bias on feature extraction.

[0014] Preferably, the integral value of the motor current signal during a single rotary cutting sampling process is calculated to obtain the tissue hardness characteristic parameter, the drop amplitude and recovery time of the vacuum negative pressure signal during the sampling process are calculated to obtain the tissue density and patency characteristic parameters, and the main frequency of the vibration or sound signal is extracted to assist in identifying the tissue type.

[0015] Preferably, the pattern recognition model is constructed using a machine learning classification algorithm, including a support vector machine classifier or an artificial neural network model, and the model is trained in advance using known categories of breast tissue data, and the feature threshold is adaptively adjusted during operation to improve the recognition accuracy.

[0016] Preferably, when the identification result indicates that the current tissue is dense tissue, a control signal is automatically sent to the rotary cutting device to increase the vacuum negative pressure or reduce the cutting speed of the needle head, so as to optimize the cutting and suction of dense tissue; when the identification result indicates that the target lesion tissue has been removed, a prompt signal is generated to remind to stop sampling.

[0017] A breast rotary cutting tissue characteristic intelligent identification system for implementing a breast rotary cutting tissue characteristic intelligent identification method as described above, comprising:

[0018] A sensing module is arranged on the breast core needle biopsy device to collect various signal data in real time during the operation, and the sensing module comprises a current sensor, a pressure sensor, and a vibration sensor, an acoustic sensor, an optical sensor, or a bioimpedance sensor to obtain electrical signals, mechanical signals, and optical / electrical characteristic signals related to tissue cutting;

[0019] A data processing module is connected with the sensing module to receive and process the signal data and extract characteristic parameters representing tissue characteristics.

[0020] A pattern recognition module is embedded in the data processing module to perform pattern recognition algorithms to classify and analyze the characteristic parameters and generate tissue characteristic recognition results.

[0021] An output interaction module is connected with the data processing module to provide information output and user prompts according to the tissue characteristic recognition results, or use the recognition results to control the working parameter adjustment of the breast core needle biopsy device.

[0022] Preferably, the data processing module comprises a signal conditioning unit and a feature extraction unit, the signal conditioning unit filters, amplifies, and digitizes the original signals from each sensor, and the feature extraction unit calculates multiple characteristic parameters such as the integral value of the motor current, the rate of change of the vacuum pressure, and the frequency spectrum characteristics of the vibration signal.

[0023] Preferably, the pattern recognition module uses a trained artificial intelligence algorithm to perform real-time classification and judgment on the characteristic parameters, wherein the artificial intelligence algorithm is a convolutional neural network or a support vector machine model, which can calculate the input feature vector according to the pre-stored model parameters and output a result signal indicating the tissue category.

[0024] Preferably, the output interaction module comprises a human-machine interface and a control interface, the human-machine interface is used to display real-time tissue characteristic category information and related indicators to the user, and the control interface is used to send control instructions to the breast core needle biopsy device to automatically adjust the vacuum negative pressure intensity or the speed of the core needle when detecting a predetermined type of tissue.

[0025] Beneficial effects: The breast core needle tissue characteristic intelligent recognition method and system provided by the present application has the following beneficial effects:

[0026] 1、The present application collects multi-source data including motor current signal, vacuum negative pressure signal, vibration, acoustic, optical or bioimpedance signal, etc. in real time during the breast core needle biopsy process, and through signal processing steps such as filtering and noise reduction, baseline calibration, extracts multiple quantitative characteristic parameters reflecting tissue characteristics, and inputs these characteristics into a pre-trained and self-adaptive adjustable pattern recognition model for classification analysis, and outputs the tissue characteristic identification result in real time, and automatically adjusts the working parameters through the output interaction module if necessary. The present application can more comprehensively reflect the hardness, patency and vibration spectrum characteristics of the tissue through multi-source signal fusion and multi-dimensional feature extraction, so as to improve the discrimination degree of different tissue types and reduce the misjudgment and omission caused by artificial experience judgment.

[0027] 2、The signal processing and pattern recognition are completed within milliseconds, the identification result can be output in real time during the tissue cutting process, and the working parameters such as rotation speed and vacuum negative pressure are dynamically adjusted according to the result, so as to realize the adaptive optimization of the operation process; the modular architecture and standardized data interface design enable the system to adapt to different types of breast core needle biopsy devices, and new sensing modules and feature dimensions can be expanded as needed, improving the applicability under various clinical conditions; the identification result drives the equipment to increase the torque and negative pressure when cutting dense tissue, and to improve the efficiency and reduce the negative pressure when cutting soft tissue, thereby reducing the risk of surgical trauma and avoiding unnecessary normal tissue removal. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description.

[0029] Figure 1 The method flowchart of the present application;

[0030] Figure 2 The system block diagram of the present application;

[0031] Figure 3 The motor current change curve diagram of the present application;

[0032] Figure 4 The vacuum pressure recovery curve diagram of the present application. DETAILED DESCRIPTION

[0033] The present application will be more clearly and completely described below by means of a preferred embodiment and in combination with the drawings, but the present application is not limited in the scope of the described embodiments.

[0034] As shown in the drawings, Figure 1 A breast core needle biopsy tissue characteristic intelligent identification method, specifically comprising the following steps:

[0035] S1, during the breast core needle biopsy procedure, real-time acquisition of signal data representing tissue characteristics through a sensing module.

[0036] The signal data includes various signals at the core needle handle or needle, such as current and torque signals of the core needle motor, vacuum negative pressure signal, knife head vibration signal, and optional acoustic signal or optical spectrum signal, etc. The above signals are acquired through the sensing module connected to the core needle device, ensuring real-time capture of tissue characteristic information during tissue cutting.

[0037] S2, filtering, denoising and calibration of the collected signal data to obtain effective signals reflecting the state of tissue cutting.

[0038] Preferably, digital signal processing algorithms are used for signal denoising and baseline calibration, such as using a band-pass filter to filter out environmental low-frequency drift and high-frequency noise, or using wavelet transform to separate useful signal components. Through parameter self-adaptive adjustment, the cutoff frequency and gain of the filter are optimized to adapt to different types of core needle devices and individual differences of patients, ensuring that the processed data is accurate and reliable.

[0039] S3, extracting a plurality of characteristic parameters representing tissue properties from the processed effective signals, including motor load characteristics and negative pressure change characteristics during cutting.

[0040] Specifically, including but not limited to: extracting cutting resistance characteristics from motor current signals, extracting tissue suction difficulty characteristics from vacuum pressure signals, extracting frequency spectrum characteristics from vibration or acoustic signals, and extracting tissue composition characteristics from optical or electrical signals, etc. For example, the integral of the motor current during each core needle biopsy process is calculated to represent the tissue density hardness index:

[0041]

[0042] wherein I(t) is the instantaneous current of the core needle motor during cutting, I0 is the baseline current when idling without load, and T is the time length of a single core needle biopsy process. The hardness index H reflects the energy consumed by the knife head to cut the tissue, and the larger the value, the more dense and hard the tissue. For example, frequency spectrum analysis is performed on the sensed vibration or acoustic signal to determine its main frequency f p , such as:

[0043]

[0044] wherein X(f) is the amplitude spectrum of the signal at frequency f. Different types of tissue may correspond to different characteristic frequency distributions: for example, dense fibrous tissue may produce a higher main frequency peak, while fatty tissue has a lower main frequency. The above characteristic parameters constitute a feature vector.

[0045] S4, input the extracted feature parameters into a pre-trained pattern recognition model, and use a pattern recognition algorithm to classify and recognize the characteristics of the current resected tissue to obtain a tissue characteristic recognition result.

[0046] The intelligent recognition model is preferably constructed using a machine learning or deep learning algorithm. For example, real-time features are compared and classified with normal breast tissue and tumor tissue features in a training library using a support vector machine (SVM) or neural network classifier. The pattern recognition module improves the accuracy of recognition through prior parameter training and real-time adaptive optimization. The parameters of the model can be obtained by training a large amount of ex vivo tissue experimental data, and corrected according to the specific device characteristics or patient conditions during system deployment. Through such parameter optimization, the pattern recognition module can achieve high-precision recognition of tissue characteristics. For example, when the hardness index H is higher than a threshold value and the vibration signal main frequency f p significantly increases, the model determines that the current cut tissue is likely to be fibrous dense suspicious lesion tissue; otherwise, it is determined to be normal gland or fat tissue. The entire recognition process is completed within milliseconds, realizing real-time intelligent discrimination of tissue characteristics.

[0047] S5, generating output information according to the recognition result, and providing the output information to the surgical operator or the device control unit to indicate the tissue characteristics or adjust the working parameters of the rotary cutting device accordingly.

[0048] The output form can be real-time display of the tissue type determination result (such as prompting "current tissue: benign fibrous tissue" or "suspected tumor tissue") on the device touch screen interface for the surgeon to refer to. Further, the system can also automatically adjust the working parameters of the rotary cutting device according to the recognition result, thereby optimizing the surgical procedure. For example, when the current tissue is recognized as dense tissue, the system can automatically increase the vacuum negative pressure or slow down the rotary cutting speed to ensure that the dense tissue is smoothly sucked into the knife slot and completely cut; when the target lesion tissue is recognized as being almost completely removed and the slices are mostly normal tissue, the system can remind the surgeon to end the sampling to avoid excessive removal of normal tissue. Through this closed-loop feedback mechanism, intelligent control is integrated to further improve the safety and efficiency of the surgery.

[0049] A breast rotary cutting tissue characteristic intelligent recognition system for implementing a breast rotary cutting tissue characteristic intelligent recognition method as described above, comprising:

[0050] A sensing module for mounting on a breast rotary cutting biopsy device to collect various signal data in real time during the surgical procedure.

[0051] The sensing module contains one or more sensors for detecting signals generated by the interaction between the rotating needle and the tissue. For example, current and voltage sensors are included to monitor the motor drive signals, pressure sensors to monitor the vacuum negative pressure changes, accelerometers / acoustic sensors to detect the tool head vibration or cutting audio signals, optical sensors (such as fiber optic spectroscopy probes or lasers with photoacoustic transducers) to detect the optical / photoacoustic characteristics of the tissue, bioimpedance electrodes to measure the electrical properties of the tissue, etc. The sensing module can be equipped with a combination of at least one of the above types of sensors as needed to comprehensively obtain information on the characteristics of the tissue. The sensing module is structurally connected to the rotating biopsy device through a standardized interface, which can be adapted to different models of rotating needles and equipment, ensuring the accuracy and real-time nature of data acquisition.

[0052] The data processing module is connected to the sensing module and is used to receive and process signal data and extract characteristic parameters representing the characteristics of the tissue.

[0053] The module includes sub-modules such as a signal conditioning unit and a feature extraction unit. The signal conditioning unit filters, amplifies, and digitizes signals from different sources, using programmable parameters to adapt to different signal amplitude and frequency ranges of different equipment. The feature extraction unit performs various feature calculations in the above method steps, such as calculating the hardness index H, the spectral dominant frequency f p , signal energy ratio, etc., and constructs the results into a feature vector to provide to the recognition module. The data processing module uses a high-speed digital signal processor or an embedded AI chip to realize parallel processing and real-time calculation of multi-channel data.

[0054] The pattern recognition module is embedded in the data processing module and is used to execute pattern recognition algorithms to perform classification analysis on the characteristic parameters, generating a tissue characteristic recognition result.

[0055] This module can be implemented using software algorithms (such as machine learning models deployed in the data processing module) or by hardware circuits for dedicated AI acceleration. The pattern recognition module has a built-in trained tissue characteristic classification model (such as a model based on neural networks or support vector machines). During operation, the module can also adaptively adjust certain parameters based on the actual collected data (for example, fine-tune the discrimination threshold based on the tissue characteristics obtained from the first few cuts) to improve recognition accuracy and robustness. The output of this module is the characteristic determination result for the currently collected tissue.

[0056] The output interaction module is connected to the data processing module and is used to provide information output and user prompts based on the tissue characteristic recognition result, or to use the recognition result to control the adjustment of the working parameters of the breast rotating biopsy device.

[0057] The output interaction module includes a human-computer interaction interface (such as a touch display screen, an audible and visual alarm device, etc.), which feeds back the recognition information to the surgical operator in real time. For example, when a suspected tumor tissue is detected, a high-light warning is displayed on the interface, and relevant quantitative indicators (such as a hardness index value) can be displayed; when the tissue is normal, the system generally prompts that the sampling is normal. If the system is configured with an automatic control function, the output interaction module also transmits the recognition result to the control unit of the rotary cutting device to realize dynamic adjustment of parameters, such as automatically controlling the power of the vacuum pump or the speed of the motor, so as to cope with different tissue conditions with optimal parameters. The output interaction module communicates with other systems in the hospital through a standardized data interface (such as a UART, a CAN bus or an Ethernet, etc.), and the data interface follows a unified protocol, which can support output and recording of the recognition result and surgical data in multiple formats, facilitating postoperative analysis and cross-device compatibility.

[0058] The system of the present application preferably adopts a modular design, and the modules are interconnected through standard interfaces. For example, the sensing module and the data processing module are connected through a high-speed data interface (USB3.0, SPI, etc.), the pattern recognition module is integrated as a software unit in the processor, and the output interaction module is connected to the processing unit through a communication interface. This modular design effectively solves the system integration barrier, so that the system can be flexibly deployed or upgraded. When a new rotary cutting device needs to be adapted or a new sensor needs to be added, only the corresponding module needs to be replaced or the interface protocol needs to be modified, without affecting the functions of other modules. At the same time, the system is equipped with necessary power management, a case and a fixing bracket and other auxiliary units to ensure reliable operation in a surgical environment.

[0059] Embodiment 1

[0060] As shown in Figure 2 The breast rotary cutting tissue property intelligent identification system of the present embodiment includes a sensing module, a data processing module, a pattern recognition module and an output interaction module connected with a breast rotary cutting biopsy device. The parts of the system are connected into a whole through wired or wireless means, wherein the sensing module is installed on the breast rotary cutting biopsy device for real-time acquisition of various signal data during the operation; the data processing module is connected with the sensing module for analysis and processing of the acquired data; the pattern recognition module is embedded in the processor of the data processing module for intelligent judgment of the extracted features; and the output interaction module communicates with the data processing module for providing the recognition result to the surgical doctor or the feedback control device.

[0061] Before the minimally invasive breast biopsy begins, all sensors in the sensing module are calibrated to their initial state. For example, the cutting needle is allowed to idle to determine the reference motor current I0 and reference noise level, and the vacuum pressure sensor reading is calibrated at zero point. This ensures the accuracy and reliability of subsequent measurements and reduces the impact of individual equipment differences on the recognition algorithm. Subsequently, during the biopsy procedure, all sensors in the sensing module synchronously begin data acquisition. The current sensor continuously monitors changes in the driving current of the cutting motor, the pressure sensor measures the real-time pressure value of the negative pressure suction, the accelerometer / microphone sensor is attached to the cutting needle handle to capture the blade vibration and cutting sound, and the optical / electrical sensor (if configured) performs rapid spectral or impedance measurements on the extracted tissue at the end of each cutting cycle. All sensor data is sent to the data processing module via a high-speed digital interface.

[0062] like Figure 3 As shown, the curve illustrates the typical variation of the instantaneous current I(t) of the rotary cutting motor during the breast rotary cutting process. The vertical axis represents the current I, and the horizontal axis represents time t; the horizontal dashed line represents the reference current I0 when idling without load. The curve includes rising, slight overshoot, and rippled steady-state segments, reflecting the characteristics of blade engagement and tissue load changes. This curve is used to calculate the tissue hardness characteristic parameter H.

[0063] The data processing module performs real-time preprocessing on data streams from different sources according to their respective characteristics. For example, it applies Fast Fourier Transform (FFT) to the motor current signal to obtain its spectrum and observe for abnormal peaks; or it calculates the current mean and variance using a sliding window to estimate the trend changes in the cutting load. For vacuum negative pressure signals, the data processing module calculates their drop amplitude and recovery time to assess the ease and patency of tissue suction. If the negative pressure fails to recover for an extended period (potentially indicating tissue blockage or incomplete cutting), the system can record this anomaly for the identification module's reference. For vibration and sound signals, time-frequency analysis methods such as wavelet transform are preferred to extract features such as energy proportion and instantaneous frequency changes in specific frequency bands, thereby capturing the differences in vibration modes when cutting different tissue materials. A series of original characteristic parameters are calculated, such as the hardness index H and the dominant frequency f. p Vacuum pressure recovery time constant Vibration signal energy ratio E, etc.

[0064] In a rotary cutting and suction cutting event, the vacuum pressure signal first drops to a local minimum. It then rose back to steady-state pressure. The sampling frequency is The time to the local minimum is denoted as To suppress noise interference, the pressure signal is first filtered and subjected to moving average processing, and then a linearized sequence is constructed within the recovery segment.

[0065]

[0066] in This represents the logarithmic transformation value of the vacuum pressure decay curve. It is a time-sampled sequence. The vacuum pressure at the time of sampling. This is the sampling point number corresponding to the minimum vacuum pressure. To prevent logarithmic operations from diverging to extremely small positive numbers, robust linear regression is used to obtain the slope. The first estimate was obtained. Simultaneously calculate the calibration value of "63.2% arrival time". ,in To restore stress The earliest moment, This is the difference between the steady-state pressure and the minimum vacuum pressure. The final weighted fusion result is taken.

[0067]

[0068] in It adaptively adjusts according to the fitting residuals and fluctuations. , , The unit is kPa. The unit is seconds; the larger the value, the denser the organization and the less unobstructed the channels.

[0069] like Figure 4 The figure shows the vacuum pressure recovery process during a single rotary cutting and suction cutting event. The curve at t min The minimum value p is reached at point min It then tends towards a steady state p ss When the pressure first reaches p ss The time when −0.368Δp is denoted as t. 63 ,definition .

[0070] Within a single rotary cutting and suction cutting event window W, the acceleration signal at the tool holder is acquired. Or microphone wind sound pressure signal The sampling frequency is The amplitude spectrum of the signal at time slice k is obtained by calculating the short-time Fourier transform. In the available frequency domain Within, calculate the average power spectrum of the event. Where K is the number of time window slices, adaptively finding the low-frequency main peak. With high frequency main peak Construct low-frequency bands respectively and high frequency band .calculate

[0071]

[0072] Again

[0073]

[0074] wherein is the low frequency band energy sum, is the high frequency band energy sum, is the frequency resolution, is a very small positive number to prevent the denominator from being zero, is a dimensionless quantity, and a high value of the high frequency energy fraction usually corresponds to a fibrotic or hard lesion.

[0075] After the feature extraction, the pattern recognition module performs fusion analysis on these features. The pattern recognition model in this embodiment is a trained three-layer artificial neural network classifier, whose input is the extracted feature vector (H, f p , τ, E,...) described above, and whose output is the classification result, including categories such as "normal tissue", "fibrotic tissue", or "suspected tumor tissue". In order to ensure the adaptability of the model to different patients and devices, the system pre-introduces several adjustable parameters in the model. For example, the final classification threshold of the neural network can be fine-tuned according to the samples obtained in the first few rotations during the operation - if the first few tissues in the operation are confirmed to be benign by rapid pathology, the model can appropriately increase the feature weight threshold required for determining malignancy, reducing the false positive rate; vice versa. The pattern recognition module internally performs the following recognition logic: first, the input features are standardized (subtract the mean, divide by the standard deviation, etc.), then the non-linear combination is calculated through the hidden layer of the network, and finally the confidence of each category is obtained in the output layer. If the confidence of a certain category (such as "suspected tumor") exceeds the preset threshold, the system determines that the current cut tissue belongs to this category. The entire judgment process takes very little time (typically less than 100 milliseconds), which can be considered as real-time completion relative to the mechanical movement of the rotating cutting device.

[0076] Once the pattern recognition module obtains the determination result, the data processing module immediately sends the result to the output interaction module. The output interaction module will pop up a prompt message on the display screen interface of the surgical device, such as "tissue recognition result: suspected tumor tissue, please pay attention to the cutting edge", and cooperate with the buzzer to issue a prompt sound to attract the attention of the operator. At the same time, the system records and stores the result, and marks the corresponding sampling number for postoperative pathological comparison and reference. If the recognition result shows that the current tissue is normal tissue and no abnormalities have been detected for several consecutive times, the system interface can prompt "the target lesion may have been completely removed", assisting the operator to decide whether to end the operation.

[0077] In this embodiment, the system also uses the recognition result to automatically adjust the surgical parameters. When the pattern recognition determines that the tissue density is high (for example, the two consecutive samples are both determined as dense fibrous tissue), the output module instructs the breast core needle biopsy device to enter a preset "dense tissue mode" through the control interface. In this mode, the vacuum control system automatically increases the negative pressure suction strength and prolongs the suction time to ensure that the tough tissue fragments are smoothly sucked out of the knife groove; at the same time, the motor control reduces the rotation speed to provide greater torque to avoid needle jamming. Conversely, when the detected tissue is soft (fat tissue) or normal, the system can restore or switch to the "normal tissue mode", that is, reduce the negative pressure and increase the cutting speed to improve the sampling efficiency and reduce the damage to the surrounding normal tissue. The whole process is automatically completed by the system without human intervention, realizing truly intelligent assistance and adaptive control.

[0078] Embodiment 2

[0079] The system of the present application has high modularity and scalability. This embodiment introduces an improved scheme integrating photoacoustic sensing technology for identifying the pathological characteristics of the tissue.

[0080] On the basis of the standard configuration, the sensing module adds a photoacoustic sensing sub-module: including a pulsed laser diode and a high-sensitivity piezoelectric ultrasonic sensor. The photoacoustic sensing sub-module works in the gap after each rotation and sampling, and a short pulse of laser (for example, wavelength 808 nm, pulse width 25 ns) is emitted by the laser diode to the tissue in the rotation knife groove. The laser energy is absorbed by the tissue and produces instantaneous thermal-elastic expansion, thereby exciting ultrabroadband ultrasonic signals (i.e. photoacoustic signals). After the piezoelectric sensor collects the photoacoustic signals, the data processing module performs frequency domain analysis on them and calculates the power spectrum of the photoacoustic signals. Studies have shown that the photoacoustic spectra of different breast tissues differ significantly: for example, fibrocystic breast tissue produces a main spectral peak at about 1.60 MHz, while normal breast tissue has a peak frequency of about 0.26 MHz. The present application uses these cross-disciplinary findings to incorporate photoacoustic spectral features (such as the main peak frequency, average frequency, and photoacoustic energy) into the feature extraction and pattern recognition process. When the photoacoustic sensing sub-module detects that the main frequency is much higher than the normal value and the photoacoustic energy is large, the pattern recognition module takes this as an auxiliary criterion for malignant or dense lesion tissue, thereby further improving the accuracy of recognition. The addition of the photoacoustic sensing sub-module fully demonstrates the compatibility and scalability of the system: by introducing advanced technologies from the fields of acoustics and optical imaging, the system can obtain information about the molecular composition and density of the tissue that cannot be provided by traditional motor and pressure signals, and achieve a clever integration of different technologies in the context of the present application.

[0081] It is noted that in the application of the above photoacoustic technology, in order to ensure safety, the laser output power and irradiation time are strictly controlled within the medical safety standard, and the laser is triggered only when there is no residual uncut tissue in the slot or direct irradiation to the patient. This design ensures that additional tissue information is obtained without increasing the risk to the patient.

[0082] Example 3

[0083] This embodiment provides a test of the system of the present application under simulated extreme tissue conditions to demonstrate the stability and reliability of the system. The test is divided into two extreme scenarios: (1) extreme hardness: using a material with physical properties close to highly fibrotic lesions (such as high-strength rubber blocks) as a prosthetic tissue for rotation cutting; (2) extreme softness: using a soft material with properties close to pure fat tissue (such as low-density sponge) as a prosthetic tissue. The system of the present application is connected to a commercial breast rotation biopsy device, and continuous rotation sampling is performed on the two extreme prostheses, each for 50 cycles. The results show that for high-hardness prostheses, the system sensing module successfully records a significantly increased motor load signal and a delayed negative pressure recovery time, and the pattern recognition module accurately determines it as "high-density tissue" and automatically triggers the dense mode to increase the negative pressure suction; for extremely soft prostheses, the system signal characteristics show that the motor load is very low and the vacuum pressure recovers quickly, and the recognition module determines it as "soft tissue", and the system can be successfully cut under normal working mode without special adjustment. During the entire test process, the system recognition accuracy is more than 98%, without error classification or system instability, which proves that the algorithm still maintains high robustness and stability under extreme conditions. At the same time, the system hardware runs smoothly, and the module interfaces cooperate well, without data loss or delay phenomenon. It can be seen that the system of the present application has been strictly tested, and can ensure that in actual surgery, even if it encounters abnormal difficulties or special tissue conditions, it can still provide reliable tissue characteristic recognition results, and will not affect the surgical judgment due to individual extreme cases.

[0084] Those skilled in the art can make various modifications, combinations or replacements to the specific technical features in the embodiments without departing from the concept of the present application, which shall fall within the protection scope of the present application. For example, the specific implementation of the pattern recognition algorithm can use a convolutional neural network instead of the fully connected network in the embodiments herein to utilize the local features of the time series signal; again, the output module of the system can be connected to the information system of the hospital to record the real-time recognition result in the patient file. These improvements do not affect the implementation of the function of the present application. In summary, the present application provides a new technical tool for breast rotation cutting surgery with unique multi-sensor fusion and intelligent algorithm. The core idea and advantage of the present application is real-time, intelligent and high-precision identification of tissue characteristics, which significantly distinguishes the present application from the prior art and improves the clinical effect. The combination and additional changes between the embodiments shall be considered as the protection scope of the present application without departing from the principle of the present application.

Claims

1. A method for intelligent identification of breast excised tissue characteristics, characterized in that, Specifically, the following steps are included: During the breast biopsy procedure, signal data characterizing tissue properties are acquired in real time through a sensing module. The signal data includes at least the motor current signal and vacuum negative pressure signal when the biopsy device is running. The acquired signal data is filtered, denoised, and calibrated to obtain an effective signal reflecting the tissue cutting status; Multiple characteristic parameters that can characterize tissue properties are extracted from the processed effective signal, including motor load characteristics and negative pressure change characteristics during the cutting process; The extracted feature parameters are input into a pre-trained pattern recognition model, and the pattern recognition algorithm is used to classify and identify the characteristics of the currently excised tissue to obtain the tissue characteristic identification results. Output information is generated based on the identification results and provided to the surgical operator or equipment control unit to indicate tissue characteristics or adjust the operating parameters of the rotary cutting device accordingly.

2. The intelligent identification method for breast excision tissue characteristics according to claim 1, characterized in that, The sensing module includes a variety of sensors for acquiring different types of signal data. The signal data includes at least one of the following signals: motor drive current signal, rotary cutting needle head vibration signal, vacuum suction pressure signal, acoustic signal, optical spectrum signal, and bioelectric impedance signal.

3. The intelligent identification method for breast excision tissue characteristics according to claim 1, characterized in that, Adaptive filtering or wavelet transform is used to denoise the signal data, and baseline calibration is performed on the motor current signal to eliminate the influence of equipment static bias on feature extraction.

4. The intelligent identification method for breast excision tissue characteristics according to claim 1, characterized in that, The integral value of the motor current signal during a single rotary cutting sampling process is calculated to obtain tissue hardness characteristic parameters. The decrease amplitude and recovery time of the vacuum negative pressure signal during the sampling process are calculated to obtain tissue density and patency characteristic parameters. The dominant frequency of the vibration or sound signal is extracted to help identify the tissue type.

5. The intelligent identification method for breast excision tissue characteristics according to claim 1, characterized in that, The pattern recognition model is constructed using machine learning classification algorithms, including support vector machine classifiers or artificial neural network models. The model is trained in advance using breast tissue data of known categories, and the feature thresholds are adaptively adjusted during operation to improve recognition accuracy.

6. The intelligent identification method for breast excision tissue characteristics according to claim 1, characterized in that, When the identification result indicates that the current tissue is a dense tissue, a control signal is automatically sent to the rotary cutting device to increase the vacuum negative pressure or reduce the cutting speed of the cutter head, thereby optimizing the cutting and suction of dense tissue; When the identification results indicate that the target lesion tissue has been removed, a prompt signal is generated to remind the user to stop sampling.

7. A smart identification system for the characteristics of breast excised tissue, characterized in that, A method for intelligent identification of breast excised tissue characteristics as described in any one of claims 1-7 includes: The sensing module is used to collect various signal data in real time during the surgical process when installed on the breast biopsy device. The sensing module includes a current sensor, a pressure sensor, as well as a vibration sensor, an acoustic sensor, an optical sensor or a bioimpedance sensor to obtain electrical signals, mechanical signals and optical / electrical characteristic signals related to tissue cutting. The data processing module, connected to the sensing module, is used to receive and process signal data and extract characteristic parameters that characterize tissue properties. The pattern recognition module, embedded in the data processing module, is used to execute pattern recognition algorithms to classify and analyze feature parameters and generate tissue characteristic identification results. The output interaction module, connected to the data processing module, is used to provide information output and user prompts based on the identification results of tissue characteristics, or to use the identification results to control the adjustment of the working parameters of the breast biopsy device.

8. The intelligent identification system for breast excision tissue characteristics according to claim 7, characterized in that, The data processing module includes a signal conditioning unit and a feature extraction unit. The signal conditioning unit filters, amplifies, and performs analog-to-digital conversion on the raw signals from each sensor. The feature extraction unit calculates multiple feature parameters, including the integral value of the motor current, the rate of change of the vacuum pressure, and the spectral characteristics of the vibration signal.

9. The intelligent identification system for breast excision tissue characteristics according to claim 7, characterized in that, The pattern recognition module uses a trained artificial intelligence algorithm to classify and judge the feature parameters in real time. The artificial intelligence algorithm is a convolutional neural network or support vector machine model, which can calculate the input feature vector based on the pre-stored model parameters and output a result signal indicating the tissue category.

10. The intelligent identification system for breast excision tissue characteristics according to claim 7, characterized in that, The output interaction module includes a human-machine interface and a control interface. The human-machine interface is used to display real-time tissue characteristic category information and related indicators to the user. The control interface is used to send control commands to the breast biopsy device when a predetermined type of tissue is detected, so as to automatically adjust the vacuum negative pressure intensity or the speed of the biopsy blade.

Images