Intelligent tissue damage identification method and system based on neurosurgery

Abstract

The invention discloses an intelligent tissue damage identification method and system based on neurosurgery, and relates to the field of medical science and technology, and the method comprises the steps: carrying out the ultrasonic monitoring of a target nervous tissue, collecting an ultrasonic scattering echo signal, and carrying out the preprocessing of the collected signal, so as to obtain a preprocessed ultrasonic scattering echo signal; fourier transform is carried out on the preprocessed ultrasonic scattering echo signal to obtain the time frequency of Fourier transform; performing energy analysis on the Fourier transform time frequency to obtain a time frequency energy analysis result; and according to the time-frequency energy analysis result, positioning a nerve tissue injury area to obtain an echo signal of the injury area, and according to the time-frequency energy analysis result, positioning the nerve tissue injury area to obtain an echo signal of the injury area. According to the invention, through feature extraction and classification, the accuracy and reliability of nervous tissue damage identification are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a method and system for intelligently identifying tissue damage under neurosurgery. Background Art

[0002] Clinical observation mainly relies on the patient's self-reported symptoms and the doctor's physical examination. However, the symptoms of different patients may vary due to individual differences, and some initial symptoms of nerve damage may not be obvious, which increases the difficulty of diagnosis.

[0003] Due to the limitations of traditional diagnostic methods, the field of neurosurgery faces a certain risk of misdiagnosis when diagnosing nerve tissue damage. Especially when faced with minor injuries, the recognition ability of these traditional methods is even more stretched. Minor injuries may only manifest as slight abnormalities in nerve tissue, and these abnormalities are often difficult to accurately capture and identify under traditional diagnostic methods. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for intelligent identification of tissue damage based on neurosurgery, which improves the accuracy and reliability of neural tissue damage identification through feature extraction and classification.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows: In a first aspect, a method for intelligently identifying tissue damage under neurosurgery comprises: Performing ultrasonic monitoring on the target nerve tissue, collecting ultrasonic scattering echo signals, and preprocessing the collected signals to obtain preprocessed ultrasonic scattering echo signals; Performing Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain the time-frequency of Fourier transform; Perform energy analysis on the time-frequency of Fourier transform to obtain the time-frequency energy analysis result; According to the time-frequency energy analysis results, the damaged area of ​​nerve tissue is located to obtain the echo signal of the damaged area; Extracting features of echo signals in the damaged area to obtain characteristic parameters; According to the characteristic parameters, the ultrasonic scattering echo signal is classified to obtain the classification result; According to the classification result, the damage state of the neural tissue is identified to obtain an identification result.

[0006] Further, the target nerve tissue is ultrasonically monitored, and ultrasonic scattering echo signals are collected, and the collected signals are preprocessed to obtain preprocessed ultrasonic scattering echo signals, including: The high-frequency ultrasonic probe performs ultrasonic monitoring on the target nerve tissue to obtain ultrasonic scattering echo signals; Amplifying the ultrasonic scattered echo signal, and filtering the amplified signal through calculation to obtain a filtered signal; The filtered signal is time-calibrated to obtain a pre-processed ultrasonic scattering echo signal.

[0007] Further, the preprocessed ultrasonic scattering echo signal is subjected to Fourier transform to obtain a Fourier transform time-frequency, including: dividing the preprocessed ultrasonic scattering echo signal into a series of overlapping frames and determining the length of the frames; According to the length of the frame, the Hamming window function is calculated for each frame signal; According to the Hamming window function, the transformation result is obtained by calculation; The transformation results are summed up to obtain the time-frequency of the Fourier transform.

[0008] Furthermore, energy analysis is performed on the time-frequency of the Fourier transform to obtain a time-frequency energy analysis result, including: According to the time-frequency of Fourier transform, the energy spectrum of the signal is obtained by calculating the square of the amplitude of each frequency component; The frequency components in the ultrasonic scattering echo signal are identified by analyzing the energy spectrum to obtain the time-frequency energy analysis results.

[0009] Further, according to the time-frequency energy analysis result, the nerve tissue damage area is located to obtain the echo signal of the damage area, including: Perform edge detection on the time-frequency energy analysis results to identify the characteristics of the damaged area, including shape, size, and location; According to the characteristics of the damaged area, locate the corresponding damaged area; According to the damaged area, the echo signal of the damaged area is extracted from the ultrasonic scattered echo signal.

[0010] Furthermore, feature extraction is performed on the echo signal of the damaged area to obtain feature parameters, including: Divide the echo signals of the damaged area into different granularity levels; For each granularity level, the entropy of the signal is calculated to obtain the characteristic parameter of signal complexity, where L is the granularity level, is the number of signal values ​​at the granularity level, is the probability of the signal value appearing, i is the signal value; For each granularity level, the characteristic parameter of the DC component of the signal is obtained by calculating the average value of the signal; For each granularity level, the variance of the signal is calculated to obtain the characteristic parameter of the signal fluctuation degree; For each granularity level, the energy characteristic parameter of the signal is obtained by calculating the sum of the squares of the signal.

[0011] Furthermore, the ultrasonic scattered echo signal is classified according to the characteristic parameters to obtain a classification result, including: According to the characteristic parameters of complexity, the characteristic parameters of DC components, the characteristic parameters of fluctuation degree and the characteristic parameters of energy, the initial cluster center and the number of clusters are set; According to the initial cluster center and the number of clusters, the membership degree of each cluster center is calculated; According to the membership degree of each cluster center, the cluster center is updated; Through iterative calculation of membership degree and cluster center, cluster analysis is performed on the extracted feature parameters to obtain the classification results.

[0012] The second aspect is the intelligent identification system of tissue damage based on neurosurgery, including: An acquisition module is used to perform ultrasonic monitoring on the target nerve tissue, collect ultrasonic scattering echo signals, and preprocess the collected signals to obtain preprocessed ultrasonic scattering echo signals; A transform module, used for performing Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain a Fourier transform time-frequency; An energy analysis module is used to perform energy analysis on the time-frequency of Fourier transform to obtain a time-frequency energy analysis result; based on the time-frequency energy analysis result, the nerve tissue damage area is located to obtain an echo signal of the damage area; An extraction module is used to extract features of echo signals in the damaged area to obtain feature parameters; A classification module is used to classify the ultrasonic scattering echo signal according to the characteristic parameters to obtain a classification result; The recognition module is used to recognize the damage state of the nerve tissue according to the classification result to obtain the recognition result.

[0013] According to a third aspect, a computing device includes: one or more processors; The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0014] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0015] The above solution of the present invention includes at least the following beneficial effects: The present invention uses high-precision ultrasonic monitoring technology to accurately capture subtle changes in nerve tissue, thereby significantly improving the accuracy of diagnosis; utilizes Fourier transform, time-frequency energy analysis and feature extraction technology to perform detailed analysis of ultrasonic scattering echo signals, and can accurately identify nerve tissue damage in its early stages; and optimizes the coarse-grained algorithm and the GK fuzzy clustering algorithm to achieve intelligent feature extraction and classification of ultrasonic scattering echo signals, thereby improving the efficiency and accuracy of data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a method for intelligently identifying tissue damage under neurosurgery provided by an embodiment of the present invention.

[0017] Figure 2 It is a schematic diagram of an intelligent identification system for tissue damage based on neurosurgery provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in a form and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0019] like Figure 1 As shown, an embodiment of the present invention proposes an intelligent identification method for tissue damage based on neurosurgery, and the method comprises the following steps: Step 11, performing ultrasonic monitoring on the target nerve tissue, collecting ultrasonic scattering echo signals, and preprocessing the collected signals to obtain preprocessed ultrasonic scattering echo signals; Step 12, performing Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain a Fourier transform time-frequency; Step 13, performing energy analysis on the Fourier transformed time-frequency to obtain a time-frequency energy analysis result; Step 14, locating the nerve tissue damage area according to the time-frequency energy analysis result to obtain the echo signal of the damage area; Step 15, extracting features of the echo signal of the damaged area to obtain feature parameters; Step 16, classifying the ultrasonic scattering echo signal according to the characteristic parameter to obtain a classification result; Step 17, identifying the damage state of the nerve tissue according to the classification result to obtain an identification result.

[0020] In an embodiment of the present invention, non-invasive, real-time and continuous monitoring of target nerve tissue is achieved through ultrasonic monitoring technology, avoiding the need for destructive operations such as tissue slicing in traditional methods; the collected ultrasonic scattering echo signal is preprocessed to effectively remove noise interference factors and improve the signal-to-noise ratio and accuracy of the signal; the preprocessed ultrasonic scattering echo signal is converted from the time domain to the frequency domain through Fourier transform to obtain the time-frequency characteristics of the signal; energy analysis is performed on the time and frequency after Fourier transform to obtain the time-frequency energy analysis result; based on the time-frequency energy analysis result, the nerve tissue damage area is successfully located and the echo signal of the damage area is obtained; feature extraction is performed on the echo signal of the damage area to obtain feature parameters that can reflect the damage state of the nerve tissue; based on the feature parameters, a suitable classifier is used to classify the ultrasonic scattering echo signal to obtain a classification result that can accurately reflect the damage state of the nerve tissue.

[0021] In a preferred embodiment of the present invention, the above step 11 may include: The high-frequency ultrasonic probe performs ultrasonic monitoring on the target nerve tissue to obtain ultrasonic scattering echo signals; The ultrasonic scattered echo signal is amplified and the amplified signal is transmitted through Filtering is performed to obtain a filtered signal, wherein, is the filtered signal, is the original signal, is the number of points in the domain, At every point in time, is the index; The filtered signal is time-calibrated to obtain a pre-processed ultrasonic scattering echo signal.

[0022] In an embodiment of the present invention, ultrasonic monitoring of the target nerve tissue is performed using a high-frequency ultrasonic probe, thereby achieving high-resolution imaging of the nerve tissue, amplifying the ultrasonic scattering echo signal, and enhancing the signal strength; through filtering processing, noise and interference factors in the ultrasonic scattering echo signal are effectively removed, and the filtered signal is time-calibrated to eliminate the time deviation of the signal during the acquisition process, thereby ensuring the accuracy and consistency of the signal.

[0023] In a preferred embodiment of the present invention, the above step 12 may include: dividing the preprocessed ultrasonic scattering echo signal into a series of overlapping frames and determining the length of the frames; According to the length of the frame, each frame signal is The Hamming window function is calculated, where is the window length; is the index of the current sampling point, ranging from 0 to ; According to the Hamming window function, Calculate to get the transformation result, where is a discrete time series, w[n] is the window function, m is the frame index, R is the sample interval between two adjacent frames, and n is the index of the current sampling point. is the angular frequency, is a complex exponential function, n is the time index, is an imaginary unit, is at a given window index and angular frequency The signal spectrum value under ; The transformation results are summed up to obtain the time-frequency of the Fourier transform.

[0024] In an embodiment of the present invention, the preprocessed ultrasonic scattering echo signal is divided into a series of overlapping frames, and the length of the frame is determined, so as to capture local features in the signal and improve the accuracy of feature extraction. A Hamming window function is obtained by calculation for each frame of the signal. The Hamming window function can effectively reduce the mutation of the signal at the edge of the frame, reduce spectrum leakage, and improve the accuracy of Fourier transform. According to the Hamming window function, a transformation result is obtained by calculation. The transformation result can reflect the energy distribution of the signal at different frequencies and times. The transformation results are summarized to obtain the time-frequency of Fourier transform, so as to understand the frequency and time characteristics of the signal, realize high-resolution imaging and precise monitoring of neural tissue, and improve the accuracy and reliability of identifying the damage state of neural tissue.

[0025] In a specific embodiment of the present invention, the frame length is determined according to the frequency content of the signal and the fineness of the analysis. In order to make the signal processing smoother and capture the dynamic changes in the signal, overlapping frames are usually used, which means that when the signal is segmented, there will be a certain number of shared samples between two adjacent frames. For example, if the frame shift (i.e., the sample interval R between two adjacent frames) is less than the frame length, there will be overlap between the frames. For each frame of signal, a window function needs to be applied to reduce spectral leakage. The Hamming window is a commonly used window function. According to the formula, the signal samples of each frame are multiplied by the corresponding Hamming window coefficients to obtain the windowed signal frame.

[0026] According to the length of the frame, the range and resolution of the angular frequency and the frame index m are set, where m represents the frame currently being processed. For each frame of the windowed signal, the short-time Fourier transform (STFT) formula is used to calculate its spectrum. For each frame of signal and each angular frequency value, the above STFT calculation is performed to obtain the spectrum value of the frame at the frequency. The STFT results of each frame are stored, usually as a complex matrix, in which rows represent different frames and columns represent different frequency components.

[0027] In a preferred embodiment of the present invention, the above step 13 may include: According to the time-frequency of Fourier transform, the energy spectrum of the signal is obtained by calculating the square of the amplitude of each frequency component; The frequency components in the ultrasonic scattering echo signal are identified by analyzing the energy spectrum to obtain the time-frequency energy analysis results.

[0028] In an embodiment of the present invention, based on the time-frequency of Fourier transform, the energy spectrum of the signal is obtained by calculating the square of the amplitude of each frequency component, and the frequency components in the ultrasonic scattering echo signal are identified by analyzing the energy spectrum to obtain the time-frequency energy analysis result; the neural tissue is monitored and analyzed non-invasively, avoiding the need for destructive operations such as tissue slicing in traditional methods, thereby reducing the risk of damage to the neural tissue.

[0029] In a specific embodiment of the present invention, according to the time-frequency representation of Fourier transform, the time-frequency representation is usually a complex matrix, in which rows represent time and columns represent frequency. For each complex value of the time-frequency point in the Fourier transform result, the square of its amplitude is calculated. The calculation formula of the square of the amplitude is: ,in is the amplitude of the complex value at the time-frequency point, is the time index, is the frequency index, Represents the energy spectrum value at the frame index and frequency. The squared amplitude values ​​of all time-frequency points are summed up to form a new matrix, which is the energy spectrum of the signal. The rows of the energy spectrum still represent time, and the columns still represent frequency, but the value of each element is now the energy of the corresponding time-frequency point; Draw a heat map or three-dimensional surface diagram of the energy spectrum to visually observe how the energy in the signal is distributed at different times and frequencies. By observing the energy spectrum, identify the main frequency components in the signal. The main frequency components usually correspond to high-energy areas in the energy spectrum, which appear as areas with higher brightness or darker colors. Analyze the changes in signal energy at different times and frequencies, quantify the energy spectrum, and calculate certain statistical characteristics of the energy spectrum.

[0030] In a preferred embodiment of the present invention, the above step 14 may include: Perform edge detection on the time-frequency energy analysis results to identify the characteristics of the damaged area, including shape, size, and location; According to the characteristics of the damaged area, locate the corresponding damaged area; According to the damaged area, an echo signal of the damaged area is extracted from the ultrasonic scattered echo signal; In the embodiment of the present invention, the edge detection technology can accurately outline the contour of the damaged area, thereby accurately identifying the shape, size and position of the damaged area; according to the damaged area characteristics identified by edge detection, the corresponding damaged area can be accurately located; by accurately locating the damaged area, the echo signal of the damaged area can be accurately extracted from a large number of ultrasonic scattered echo signals; accurate damage area identification and positioning provide assistance for diagnosis and treatment; edge detection and damage area positioning reduce the time of manual analysis and positioning, and improve the efficiency of medical services. At the same time, it also reduces the risk of misjudgment caused by human factors.

[0031] In a specific embodiment of the present invention, a feature point matching technique is used according to the time-frequency energy analysis result to locate the damaged area on the time-frequency energy distribution diagram, and the position of the damaged area in the time-frequency domain is converted into the time or space coordinates in the original ultrasonic signal; based on the located damaged area coordinates, the signal of the corresponding time period or space segment is intercepted in the original ultrasonic scattering echo signal, and the intercepted signal is enhanced and processed.

[0032] In a preferred embodiment of the present invention, the above step 15 may include: Divide the echo signals of the damaged area into different granularity levels; For each granularity level, Calculate the entropy of the signal to obtain the characteristic parameter of the signal complexity, L is the granularity level, is the number of signal values ​​at the granularity level, is the probability of the signal value occurring, is the signal value; For each granularity level, Calculate the average value of the signal to obtain the characteristic parameter of the DC component of the signal, where: is the signal length at granularity level L, It's time. is the signal value at the granularity level and time, is the mean; For each granularity level, Calculate the variance of the signal to obtain the characteristic parameter of the signal's fluctuation degree, where: is the mean of the signal at the granularity level; For each granularity level, Calculate the sum of the squares of the signal to obtain the energy characteristic parameters of the signal, where: is the energy of the signal.

[0033] In the embodiment of the present invention, the echo signal of the damaged area is divided into different granularity levels, and the multi-scale analysis of the signal is realized. By calculating the entropy, mean value, variance and energy of each granularity level, a variety of characteristic parameters are obtained. These characteristic parameters describe the characteristics of the signal from multiple aspects such as signal complexity, DC component, fluctuation degree and energy. The extraction of multiple characteristic parameters provides more information for the classifier, which helps to improve the classification performance and accuracy of the classifier.

[0034] In a specific embodiment of the present invention, the echo signal of the damaged area is segmented according to the defined granularity level. For example, if we define the granularity level as 1 millisecond, the signal of every 1 millisecond will be regarded as a separate segment. For the signal segment at each granularity level, the probability of each value appearing in the signal is determined by counting the number of times each value appears in the signal segment and then dividing it by the length of the signal segment. The entropy of the signal segment at each granularity level is calculated using the entropy formula. Entropy is a measure of signal complexity and can reflect the amount of information in the signal. For the signal segment at each granularity level, the values ​​of all signals in the segment are accumulated, and the accumulated signal values ​​are divided by the length of the signal segment to obtain the average value of the signal segment at the granularity level. The average value reflects the DC component of the signal. For the signal segment at each granularity level, the difference between each signal value and the mean is calculated, each difference is squared, and all squared values ​​are accumulated. The accumulated squared difference is divided by the length of the signal segment to obtain the variance of the signal segment at the granularity level. The variance reflects the degree of fluctuation of the signal. For the signal segment at each granularity level, all squared signal values ​​are accumulated, and the accumulated square value is the energy of the signal segment at this granularity level, and the energy reflects the strength of the signal.

[0035] In a preferred embodiment of the present invention, the above step 16 may include: According to the characteristic parameters of complexity, the characteristic parameters of DC components, the characteristic parameters of fluctuation degree and the characteristic parameters of energy, the initial cluster center and the number of clusters are set; According to the initial cluster center and the number of clusters, Calculate the membership degree of each cluster center, where is the membership degree of the cluster center, x j is a data point, is the distance from the data point to the cluster center, is the index, c is the number of clusters, is the distance between data point j and another cluster center k, is the fuzziness coefficient; According to the membership degree of each cluster center, Update cluster centers, is the updated center of the ith cluster, is the membership degree of the cluster center, xj is a data point, is the total number of data points, is a fuzzy parameter; Through iterative calculation of membership degree and cluster center, cluster analysis is performed on the extracted feature parameters to obtain the classification results.

[0036] In an embodiment of the present invention, through cluster analysis, the extracted characteristic parameters can be accurately divided into different categories, thereby realizing accurate identification of the state of nerve tissue damage. The method can adaptively determine the optimal number of clusters and cluster centers by iteratively calculating membership and cluster centers, without specifying the number of clusters in advance, so that the clustering results are more in line with the actual distribution of the data. In the clustering process, the characteristic parameters of complexity, the characteristic parameters of DC components, the characteristic parameters of fluctuation degree and the energy characteristic parameters are comprehensively considered, and the extracted characteristic information is fully utilized to improve the accuracy and reliability of classification.

[0037] In a specific embodiment of the present invention, an appropriate number of clusters c is set according to the distribution of characteristic parameters of complexity, characteristic parameters of DC components, characteristic parameters of fluctuation degree and characteristic parameters of energy, and c points are randomly selected in the characteristic space as initial cluster centers. These points are as dispersed as possible to cover the entire data space. For each data point, its distance to each cluster center is calculated, and the membership of each data point to each cluster center is calculated by a formula, and the membership indicates the degree to which the data point belongs to a certain cluster. Based on the membership and the position of the data point, a new cluster center is calculated using a weighted average method, and the contribution of each data point to the cluster center is proportional to its membership, ensuring that the sum of the membership of each data point to all clusters is 1.

[0038] The process of calculating membership and updating cluster centers is repeated until the maximum number of iterations is reached. After the iteration, the cluster center obtained is the final cluster center. According to the final membership matrix, the data points are assigned to the cluster with the highest membership to obtain the data points and cluster centers of each cluster.

[0039] In a preferred embodiment of the present invention, the above step 17 may include: Obtain the neural damage status corresponding to different cluster centers; Compare the nerve injury states corresponding to different cluster centers with the cluster centers corresponding to the echo signal characteristics of each injury area to identify the nerve injury state, including but not limited to: normal, slight injury, moderate injury, severe injury; An identification result is obtained based on the identified nerve damage status.

[0040] In an embodiment of the present invention, by comparing the cluster center corresponding to the echo signal characteristics of each damaged area with the nerve damage status corresponding to different cluster centers, the damage status of the nerve tissue can be accurately identified, including normal, slight damage, moderate damage, and severe damage. It takes into account a variety of damage status of the nerve tissue and provides a more comprehensive damage assessment. The degree and type of damage to the nerve tissue can be judged based on the identification results, and a more accurate treatment plan can be formulated to improve the treatment effect.

[0041] In a specific embodiment of the present invention, the nerve injury states corresponding to different cluster centers are mapped based on medical knowledge. For example, a certain cluster center may mainly correspond to the data point of "mild injury". The correspondence between such cluster centers and nerve injury states is formed into a mapping table or database. For a new damaged area, the features of its ultrasonic scattering echo signal are first extracted, including complexity feature parameters, feature parameters of DC components, fluctuation degree feature parameters, and energy feature parameters. These features are clustered and analyzed to determine the cluster center corresponding to the features of the damaged area. Based on the comparison results, the nerve injury state of the damaged area is determined, such as "normal", "mild injury", "moderate injury" or "severe injury".

[0042] like Figure 2 As shown, the embodiment of the present invention also provides a tissue damage intelligent identification system 20 based on neurosurgery, including: An acquisition module 21 is used to perform ultrasonic monitoring on the target nerve tissue, collect ultrasonic scattered echo signals, and preprocess the collected signals to obtain preprocessed ultrasonic scattered echo signals; A transform module 22, used for performing Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain a Fourier transform time-frequency; The energy analysis module 23 is used to perform energy analysis on the time-frequency of the Fourier transform to obtain a time-frequency energy analysis result; and locate the nerve tissue damage area according to the time-frequency energy analysis result to obtain an echo signal of the damage area; An extraction module 24 is used to extract features of the echo signal of the damaged area to obtain feature parameters; The classification module 25 is used to classify the ultrasonic scattered echo signal according to the characteristic parameters to obtain a classification result; The identification module 26 is used to identify the damage state of the nerve tissue according to the classification result to obtain an identification result.

[0043] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0044] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0045] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0046] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent identification method for tissue damage based on neurosurgery, characterized in that: The method comprises: Performing ultrasonic monitoring on the target nerve tissue, collecting ultrasonic scattering echo signals, and preprocessing the collected signals to obtain preprocessed ultrasonic scattering echo signals; Performing Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain the time-frequency of Fourier transform; Perform energy analysis on the time-frequency of Fourier transform to obtain the time-frequency energy analysis result; According to the time-frequency energy analysis results, the damaged area of ​​nerve tissue is located to obtain the echo signal of the damaged area; Extracting features of echo signals in the damaged area to obtain characteristic parameters; Classifying the ultrasonic scattering echo signal according to the characteristic parameters to obtain a classification result; According to the classification result, the damage state of the neural tissue is identified to obtain an identification result.

2. The method for intelligent identification of tissue damage based on neurosurgery according to claim 1 is characterized in that: Performing ultrasonic monitoring on the target nerve tissue, collecting ultrasonic scattering echo signals, and preprocessing the collected signals to obtain preprocessed ultrasonic scattering echo signals, including: The high-frequency ultrasonic probe performs ultrasonic monitoring on the target nerve tissue to obtain ultrasonic scattering echo signals; Amplifying the ultrasonic scattered echo signal, and filtering the amplified signal through calculation to obtain a filtered signal; The filtered signal is time-calibrated to obtain a pre-processed ultrasonic scattering echo signal.

3. The method for intelligent identification of tissue damage based on neurosurgery according to claim 2 is characterized in that: Perform Fourier transform on the preprocessed ultrasonic scattering echo signal to obtain the time-frequency of Fourier transform, including: dividing the preprocessed ultrasonic scattering echo signal into a series of overlapping frames and determining the length of the frames; According to the length of the frame, the Hamming window function is calculated for each frame signal; According to the Hamming window function, the transformation result is obtained by calculation; The transformation results are summed up to obtain the time-frequency of the Fourier transform.

4. The method for intelligent identification of tissue damage based on neurosurgery according to claim 3 is characterized in that: Perform energy analysis on the time-frequency of Fourier transform to obtain time-frequency energy analysis results, including: According to the time-frequency of Fourier transform, the energy spectrum of the signal is obtained by calculating the square of the amplitude of each frequency component; The frequency components in the ultrasonic scattering echo signal are identified by analyzing the energy spectrum to obtain the time-frequency energy analysis results.

5. The method for intelligent identification of tissue damage based on neurosurgery according to claim 4 is characterized in that: According to the time-frequency energy analysis results, the nerve tissue damage area is located to obtain the echo signal of the damaged area, including: Perform edge detection on the time-frequency energy analysis results to identify the characteristics of the damaged area, including shape, size, and location; According to the characteristics of the damaged area, locate the corresponding damaged area; According to the damaged area, the echo signal of the damaged area is extracted from the ultrasonic scattered echo signal.

6. The method for intelligent identification of tissue damage based on neurosurgery according to claim 5 is characterized in that: The echo signal of the damaged area is extracted to obtain characteristic parameters, including: Divide the echo signals of the damaged area into different granularity levels; For each granularity level, the entropy of the signal is calculated to obtain the characteristic parameter of signal complexity, where L is the granularity level, is the number of signal values ​​at the granularity level, is the probability of the signal value appearing, i is the signal value; For each granularity level, the characteristic parameter of the DC component of the signal is obtained by calculating the average value of the signal; For each granularity level, the variance of the signal is calculated to obtain the characteristic parameter of the signal fluctuation degree; For each granularity level, the energy characteristic parameter of the signal is obtained by calculating the sum of the squares of the signal.

7. The method for intelligent identification of tissue damage based on neurosurgery according to claim 6 is characterized in that: According to the characteristic parameters, the ultrasonic scattering echo signal is classified to obtain the classification results, including: According to the characteristic parameters of complexity, the characteristic parameters of DC components, the characteristic parameters of fluctuation degree and the characteristic parameters of energy, the initial cluster center and the number of clusters are set; According to the initial cluster center and the number of clusters, the membership degree of each cluster center is calculated; According to the membership degree of each cluster center, the cluster center is updated; Through iterative calculation of membership degree and cluster center, cluster analysis is performed on the extracted feature parameters to obtain the classification results.

8. Based on the intelligent identification system of tissue damage under neurosurgery, it is characterized by: include: An acquisition module is used to perform ultrasonic monitoring on the target nerve tissue, collect ultrasonic scattering echo signals, and preprocess the collected signals to obtain preprocessed ultrasonic scattering echo signals; A transformation module, used for performing Fourier transformation on the preprocessed ultrasonic scattering echo signal to obtain a Fourier transformed time-frequency; An energy analysis module is used to perform energy analysis on the time-frequency of Fourier transform to obtain a time-frequency energy analysis result; According to the time-frequency energy analysis results, the damaged area of ​​nerve tissue is located to obtain the echo signal of the damaged area; An extraction module is used to extract features of echo signals in the damaged area to obtain feature parameters; A classification module is used to classify the ultrasonic scattering echo signal according to the characteristic parameters to obtain a classification result; The recognition module is used to recognize the damage state of the nerve tissue according to the classification result to obtain the recognition result.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images