Intelligent medical auxiliary platform and method based on ultrasonic radio frequency echo signal and application

Abstract

The invention discloses an intelligent medical auxiliary platform and method based on ultrasonic radio frequency echo signals and application. The intelligent medical auxiliary platform comprises an ultrasonic radio frequency echo signal extraction module, an interest region characteristic signal processing module and an MSS estimation module. The ultrasonic radio frequency echo signal extraction module is used for obtaining an ultrasonic radio frequency echo signal of the biological tissue through ultrasonic equipment; the region-of-interest characteristic signal processing module is used for performing time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain a tissue region-of-interest radio frequency echo signal and a tissue region-of-interest fundamental wave and harmonic signal frequency spectrum; the MSS estimation module is used for estimating an ISS (adjacent scattering element spacing) and an MSS (average scattering element spacing) through an LOMGA (LOMGA) method for positioning the optimally matched Gabor atom position from the ultrasonic radio frequency echo signal of the region of interest; according to the method, the estimation performance of the MSS is improved through the method for positioning the optimal matching Gabor atom position based on the base harmonic of the ultrasonic radio frequency echo signal.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic technology, and more specifically to an intelligent medical assistance platform, method and application based on ultrasonic radio frequency echo signals. Background Art

[0002] At present, clinical disease diagnosis and tissue characterization are mainly based on ultrasound, magnetic resonance imaging, tissue tomography CT and other methods. Since CT may cause certain damage to human tissues and MRI has poor real-time performance, is expensive and requires magnetic resonance imaging compatible equipment, it is not convenient to promote their use. Ultrasound has been widely used in clinical disease diagnosis and tissue characterization due to its low cost, real-time performance, non-invasiveness and portability.

[0003] However, existing ultrasound equipment and related platforms have the following problems: (1) Ultrasound equipment does not expose the underlying ultrasound radio frequency echo signal that carries tissue microstructure information; (2) The ultrasound operation platform and its interface mainly process ultrasound images of tissues, and their tasks are to display images, extract regions of interest, detect the size of regions of interest, etc., but do not perform real-time quantitative analysis and estimation of tissue regions of interest; (3) Existing ultrasound platforms are seriously out of touch with cutting-edge technologies and methods, and do not conduct ultrasound tissue quantitative analysis and research based on clinical ultrasound big data, nor do they have relevant intelligent platforms to assist doctors in disease diagnosis and tissue characterization.

[0004] In addition, the Mean Scatterer Spacing (MSS) of regular scatterers is an important parameter for describing the microstructural characteristics and ultrasonic scattering characteristics of biological tissues. When affected by factors such as lesions or temperature, the spatial distribution characteristics of tissues will change, which will correspondingly cause changes in the MSS of the tissues. Therefore, quantitatively analyzing the ultrasonic radio frequency echo signals of tissues and estimating the MSS therefrom can effectively reveal the correlation between tissue microstructural changes and diseases and temperature, which is of great significance for assisting clinical disease diagnosis and ultrasonic tissue characterization.

[0005] At present, there are two main methods for estimating MSS using ultrasonic RF echo signals: frequency domain (power spectrum, inverse spectrum, spectral autocorrelation, quadratic transform and singular spectrum analysis, etc.) and time domain (based on ensemble empirical mode decomposition (EEMD) and wavelet transform (WT). Among them, the traditional method based on frequency domain mainly uses the redundant information of the spectral peak of harmonic frequency or the amplitude and phase of the power spectrum to estimate MSS. However, this type of method has the following shortcomings: (1) It is easily interfered by noise and diffuse scattering signals; (2) It is necessary to assume that the tissue structure is quasi-regularly distributed; (3) It is greatly affected by signal length and has low time-frequency resolution; (4) It can only estimate the MSS result, and cannot obtain the spatial distribution information of the scattering elements. The above factors lead to poor accuracy and stability of MSS estimation based on frequency domain methods; while the method based on time domain adopts the idea of ​​decomposition and extracts the MSS from the ultrasonic RF echo signal of the tissue. First, the regular scattering component and diffuse scattering component of the signal are separated, and then the peak value of the decomposition component related to the position of the regular scattering element of the tissue is extracted to estimate the MSS and the ISS between adjacent scattering elements. This type of method is less affected by noise and diffuse scattering components, and can obtain the spatial distribution information of the regular scattering elements of the tissue. However, since the selection of decomposition components related to the regular scattering structure of a specific tissue lacks a theoretical basis and its peak point cannot accurately reflect the position of the regular scattering element, this type of method has limitations in objectively and accurately estimating the MSS and ISS. In addition, the existing SS estimation methods are all based on the fundamental component of the ultrasonic RF echo signal, and do not take into account the tissue nonlinearity and the differences between the microstructure, scattering element concentration and harmonic signal energy at different temperatures and different types of normal and diseased tissues, which also affects the estimation precision and accuracy of the MSS.

[0006] Therefore, how to develop an intelligent medical assistance platform to realize ultrasonic RF echo signal extraction and quantitatively analyze and estimate tissue ultrasonic echo signals to improve the estimation performance of MSS, so as to assist doctors in disease diagnosis and tissue characterization, is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0007] In view of this, the present invention provides an intelligent medical assistance platform, method and application based on ultrasonic radio frequency echo signals to solve some of the technical problems mentioned in the background technology.

[0008] In order to achieve the above object, the present invention adopts the following technical solution:

[0009] An intelligent medical assistance platform based on ultrasonic radio frequency echo signals, comprising an ultrasonic radio frequency echo signal extraction module, an interest area characteristic signal processing module and an MSS estimation module;

[0010] An ultrasonic radio frequency echo signal extraction module is used to obtain an ultrasonic radio frequency echo signal of a biological tissue through an ultrasonic device;

[0011] The region of interest characteristic signal processing module is used to perform time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain the radio frequency echo signal of the tissue region of interest and the spectrum of the fundamental wave and harmonic wave signal of the tissue region of interest;

[0012] The MSS estimation module is used to estimate the inter-scattering element spacing ISS and the average scattering element spacing MSS by using the Gabor atom position LOMGA method based on the best matching of the radio frequency echo signal positioning in the area of ​​interest.

[0013] Preferably, the ultrasonic device transmits ultrasonic waves to biological tissues through an ultrasonic transducer as a sound source, and then uses a receiving transducer to receive echo signals from the biological tissues.

[0014] Preferably, the intelligent medical assistance platform based on ultrasonic radio frequency echo signals also includes a B-ultrasound image generation module, which is used to generate a B-ultrasound image by performing envelope extraction, logarithmic compression and interpolation on the ultrasonic radio frequency echo signals.

[0015] Preferably, the interest region characteristic signal processing module includes a time domain analysis unit, a frequency domain analysis unit and a filtering unit;

[0016] A time domain analysis unit, used for extracting a tissue region of interest and obtaining size data of the tissue region of interest by performing a time domain sampling theorem on the ultrasonic radio frequency echo signal;

[0017] A frequency domain analysis unit, used for obtaining a radio frequency echo signal of the tissue region of interest by Fourier transforming the extracted signal data of the tissue region of interest;

[0018] The filtering module is used to separate and filter the radio frequency echo signal of the tissue interest region through a Butterworth filter to obtain the fundamental wave and harmonics of the tissue interest region.

[0019] Preferably, the intelligent medical assistance platform based on ultrasonic radio frequency echo signals also includes a wavelet transform analysis module, which is used to analyze and extract transient characteristic changes in the radio frequency echo spectrum signal of the area of ​​interest through a multi-resolution time-frequency analysis method to estimate the mean scattering element spacing MSS.

[0020] Preferably, the specific contents of the MSS estimation module are:

[0021] Generate redundant Gabor atom sets and use MP algorithm to identify Gabor atoms matching the local components of the signal from the ultrasonic radio frequency echo signal;

[0022] According to the change of the second-order difference SOD of the energy ratio RSRR of the reconstructed signal and the residual signal in the matching process, the Gabor atoms matching the regular scattering components are automatically obtained and the regular scattering components are reconstructed;

[0023] Based on the reconstructed regular scattering components, the position information of the matching atoms is used to calculate the adjacent spacing of the matching atoms to estimate the adjacent scattering element spacing ISS. The average result of ISS is the mean scattering element spacing MSS.

[0024] Preferably, the average scattering element spacing MSS estimation is based on the best matching Gabor atoms, specifically, the maximum negative peak of the SOD curve of RSRR is used to determine the M′ (M′≤M) Gabor atoms that are most strongly correlated with the regular scattering components of the tissue, and the position information of the matching atoms is used to calculate the distance between adjacent atoms to obtain the ISS and its MSS.

[0025] Preferably, the spacing ISS between adjacent scattering elements is:

[0026] ISS k =(u k+1 -u k ),k=1,2,...,M′-1

[0027] The mean scattering element spacing MSS is:

[0028]

[0029] Where, M′ (M′≤M) is the number of Gabor atoms with the strongest correlation with the regular scattering component of the tissue, determined by using the maximum negative peak of the SOD curve of RSRR, and u k+1 、u k Adjacent matching atoms location information.

[0030] A smart medical assistance method based on ultrasonic radio frequency echo signals, based on the smart medical assistance platform based on ultrasonic radio frequency echo signals, comprises the following steps:

[0031] Obtaining ultrasonic radio frequency echo signals of biological tissues through ultrasonic equipment;

[0032] Performing time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain the radio frequency echo signal of the tissue interest area and the spectrum of the fundamental wave and harmonic wave signal of the tissue interest area;

[0033] The inter-scatterer spacing (ISS) and the average scatterer spacing (MSS) are estimated by using the LOMGA method based on the best matching Gabor atom position positioning of the RF echo signal in the region of interest.

[0034] An application of an intelligent medical assistance platform based on ultrasonic radio frequency echo signals, using the intelligent medical assistance platform based on ultrasonic radio frequency echo signals to assist in evaluating changes in tissue microwave ablation thermal damage areas and to assist in distinguishing benign and malignant breast tumor tissues.

[0035] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses an intelligent medical auxiliary platform, method and application based on ultrasonic radio frequency echo signals, which not only realizes ultrasonic radio frequency echo signal extraction, B-ultrasound image generation and region of interest extraction, but also realizes ultrasonic tissue quantitative index analysis and estimation for the fundamental wave and harmonic signal of the ultrasonic echo signal of the tissue interest region; the present invention improves the estimation performance of MSS by locating the best matching Gabor atom position based on the fundamental harmonic of the ultrasonic radio frequency echo signal; further, the estimated MSS can be used to more accurately reflect the change of MSS of the tissue microwave ablation thermal damage area with temperature and the correlation between different breast pathological tissues and their MSS, which is of great significance to improving the auxiliary clinical disease diagnosis and ultrasonic tissue characterization performance based on MSS. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of an intelligent medical assistance platform based on ultrasonic radio frequency echo signals provided by the present invention;

[0038] Figure 2 A schematic diagram of the ultrasonic transducer transmitting the sound field provided by the present invention;

[0039] Figure 3 A schematic diagram of the MSS estimation algorithm based on LOMGA provided by the present invention;

[0040] Figure 4 A schematic diagram of the workflow of an intelligent medical assistance platform based on ultrasonic radio frequency echo signals provided by the present invention;

[0041] Figure 5 B-ultrasound images of the fundamental wave and second harmonic of a pig liver tissue sample after microwave ablation provided by the present invention;

[0042] Figure 6 A schematic diagram of the linear fitting results of the MSD, coefficient of variation CV and MSS mean value of the MSS estimated from 200 groups of fundamental harmonic signals at 21 time points of a tissue sample provided by the present invention;

[0043] Figure 7 The scatter plot of MSS of 200 groups of fundamental waves and second harmonics at six ablation time points based on 10 cases of pig liver tissue provided by the present invention;

[0044] Figure 8 The ROC curve diagram of MSS of fundamental wave and second harmonic of 10 pig liver tissues at five adjacent time points provided by the present invention;

[0045] Fig. 9 The B-ultrasound image of the lesion ROI of benign and malignant breast tumors scanned by transverse ultrasound provided by the present invention;

[0046] Fig.10 A scatter plot of the MSS estimated from the benign and malignant tumor ROIs of grade 3 and grade 5 determined based on the BI-RADS standard based on the LOMGA and WT methods provided by the present invention;

[0047] Fig.11 The present invention provides a ROC curve diagram obtained from the radio frequency echo signal MSS of benign and malignant tumor ROIs marked as 0 and 1 and grade 3 and 5 determined by the BI-RADS standard based on the LOMGA and WT methods respectively. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Embodiment 1

[0050] The embodiment of the present invention discloses a smart medical assistance platform based on ultrasonic radio frequency echo signals, such as Figure 1 , including an ultrasonic radio frequency echo signal extraction module, an interest area characteristic signal processing module and an MSS estimation module;

[0051] An ultrasonic radio frequency echo signal extraction module is used to obtain an ultrasonic radio frequency echo signal of a biological tissue through an ultrasonic device;

[0052] The region of interest characteristic signal processing module is used to perform time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain the radio frequency echo signal of the tissue region of interest and the spectrum of the fundamental wave and harmonic wave signal of the tissue region of interest;

[0053] The MSS estimation module is used to estimate the inter-scattering element spacing ISS and the average scattering element spacing MSS by using the Gabor atom position LOMGA method based on the best matching of the radio frequency echo signal positioning in the area of ​​interest.

[0054] In order to further implement the above technical solution, the ultrasonic device transmits ultrasonic waves to biological tissues through an ultrasonic transducer as a sound source, and then uses a receiving transducer to receive echo signals of the biological tissues, such as Figure 2 .

[0055] Ultrasonic equipment is used to obtain the structural information of biological tissue by detecting the echo signals of scatterers (scattering points) in each resolution unit in the tissue. Specifically, the random distribution characteristics of scatterers and their backscattered signals in the biological medium are utilized. According to certain statistical characteristics of the echo signals, the distribution state of scatterers in biological tissue can be analyzed to further obtain the physiological and pathological information of tissues and organs.

[0056] In order to further implement the above technical solution, an intelligent medical assistance platform based on ultrasonic radio frequency echo signals also includes a B-ultrasound image generation module, which is used to generate B-ultrasound images by envelope extraction, logarithmic compression and interpolation of ultrasonic radio frequency echo signals.

[0057] In order to further implement the above technical solution, the interest area characteristic signal processing module includes a time domain analysis unit, a frequency domain analysis unit and a filtering unit;

[0058] A time domain analysis unit, used for extracting a tissue region of interest and obtaining size data of the tissue region of interest by performing a time domain sampling theorem on the ultrasonic radio frequency echo signal;

[0059] A frequency domain analysis unit, used for obtaining a radio frequency echo signal of the tissue region of interest by Fourier transforming the extracted signal data of the tissue region of interest;

[0060] A filtering module is used to separate and filter the radio frequency echo signal of the tissue interest region through a Butterworth filter to obtain the fundamental wave and harmonics of the tissue interest region;

[0061] In this embodiment, a Butterworth bandpass filter with a passband frequency range of 3MHz-7MHz and 8MHz-12MHz, an attenuation of -3dB, and an 8th order is used to separate the original ultrasonic radio frequency echo signal to obtain fundamental wave and harmonic wave signals respectively.

[0062] The specific content of the time domain sampling theorem is: sampling is the conversion of a continuous-time signal into a discrete-time signal or sequence. If the signal is band-limited and the sampling frequency is higher than twice the highest frequency of the signal, then the original continuous signal can be completely reconstructed from the sampled samples.

[0063] In order to further implement the above technical solution, an intelligent medical assistance platform based on ultrasonic radio frequency echo signals also includes a wavelet transform analysis module, which is used to analyze and extract transient characteristic changes in the radio frequency echo spectrum signal of the area of ​​interest through a multi-resolution time-frequency analysis method to estimate the average scattering element spacing MSS.

[0064] The multi-resolution time-frequency analysis method of the wavelet transform analysis module is specifically characterized by having higher frequency resolution and lower time resolution in the low-frequency part, and higher time resolution and lower frequency resolution in the high-frequency part, to extract transient feature changes in the signal.

[0065] In order to further implement the above technical solution, Figure 3 , the specific contents of the MSS estimation module are:

[0066] Generate redundant Gabor atom sets and use MP algorithm to identify Gabor atoms matching the local components of the signal from the ultrasonic radio frequency echo signal;

[0067] According to the change of the second-order difference SOD of the energy ratio RSRR of the reconstructed signal and the residual signal in the matching process, the Gabor atoms matching the regular scattering components are automatically obtained and the regular scattering components are reconstructed;

[0068] Based on the reconstructed regular scattering components, the position information of the matching atoms is used to calculate the adjacent spacing of the matching atoms to estimate the adjacent scattering element spacing ISS. The average result of ISS is the mean scattering element spacing MSS.

[0069] In order to further implement the above technical solution, an intelligent medical assistance platform based on ultrasonic radio frequency echo signals is proposed. The average scattering element spacing MSS estimation is based on the best matching Gabor atoms. Specifically, the maximum negative peak of the SOD curve of RSRR is used to determine the M′ (M′≤M) Gabor atoms with the strongest correlation with the regular scattering components of the tissue. The position information of the matching atoms is used to calculate the distance between adjacent atoms to obtain the ISS and its MSS.

[0070] In order to further implement the above technical solution, the spacing ISS between adjacent scattering elements is:

[0071] ISS k =(u k+1 -u k ),k=1,2,...,M′-1

[0072] The mean scatterer spacing MSS is:

[0073]

[0074] Where, M′ (M′≤M) is the number of Gabor atoms with the strongest correlation with the regular scattering component of the tissue, determined by using the maximum negative peak of the SOD curve of RSRR, and u k+1 、u k Adjacent matching atoms location information.

[0075] Embodiment 2

[0076] A smart medical assistance method based on ultrasonic radio frequency echo signals, based on a smart medical assistance platform based on ultrasonic radio frequency echo signals, such as Figure 4 , including the following steps:

[0077] Obtaining ultrasonic radio frequency echo signals of biological tissues through ultrasonic equipment;

[0078] Performing time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain the radio frequency echo signal of the tissue interest area and the spectrum of the fundamental wave and harmonic wave signal of the tissue interest area;

[0079] The inter-scatterer spacing (ISS) and the average scatterer spacing (MSS) are estimated by the LOMGA method based on the best matching Gabor atom position positioning of the RF echo signal in the region of interest.

[0080] An application of an intelligent medical assistance platform based on ultrasonic radio frequency echo signals, using an intelligent medical assistance platform based on ultrasonic radio frequency echo signals to assist in evaluating changes in tissue microwave ablation thermal damage areas and to assist in distinguishing benign and malignant breast tumor tissues.

[0081] Embodiment 3

[0082] This embodiment uses a smart medical assistance platform based on ultrasonic radio frequency echo signals to assist in the assessment of microwave ablation thermal damage area. The specific contents are as follows:

[0083] (1) At room temperature (17°C), ultrasound system was used to collect ultrasound radiofrequency echo signals of normal (unablated) liver tissue samples. Then, microwave ablation was performed on the tissue samples. Ultrasound radiofrequency echo signals of the coagulated liver tissue after ablation were collected and saved at 15-second intervals. The collection time lasted for 300 seconds in total. After ablation, the tissue was cut along the ultrasound scanning plane for histological observation.

[0084] (2) The ultrasonic radio frequency echo signals collected at 21 time points are loaded offline, and the envelope of the signal is extracted using Hilbert transform. Then, the B-ultrasound image is obtained through downsampling, logarithmic compression and lateral interpolation.

[0085] (3) A region of interest (ROI) with a size of 15 mm × 12 mm, including the tissue thermal damage area, was selected from the B-ultrasound image. Four lines of signal (each line signal length was 512 sampling points) were randomly selected and spliced ​​to form the signal to be processed. The signal was separated using an 8th-order Butterworth bandpass filter with a passband frequency range of 8 MHz to 12 MHz and an attenuation of -3 dB to obtain the SHRS, as shown in Figure 2. Figure 5 .

[0086] (4) Quantitative analysis of the performance of SHRS-based MSS in evaluating the thermal damage area of ​​tissue microwave ablation: For 10 cases of pig liver tissue, 200 groups of FRS and SHRS were randomly selected to estimate MSS at 21 different ablation time points, and the mean, standard deviation and coefficient of variation of MSS were calculated; then, a linear fit was performed on the MSS mean to obtain the slope and determination coefficient of the change of the MSS mean with the ablation time, and the results of the fundamental harmonics were compared, such as Figure 6 (a) is the MSD of the MSS estimated by the fundamental harmonic signal, (b) is the coefficient of variation CV, and (c) is the result of linear fitting of the MSS mean;

[0087] (5) Draw a scatter plot and ROC curve based on the MSS mean of the fundamental and harmonic signals, and further quantitatively analyze the evaluation performance of the MSS of the fundamental and harmonic waves on the thermal damage area of ​​microwave ablation, such as Figure 7 (a) is the scatter plot of the MSS of the fundamental wave, and (b) is the scatter plot of the MSS of the second harmonic. Figure 8 (a) is the ROC curve of the MSS of the fundamental wave, and (b) is the ROC curve of the MSS of the second harmonic.

[0088] Embodiment 4

[0089] This embodiment uses an intelligent medical assistance platform based on ultrasonic radio frequency echo signals to assist in the experiment of distinguishing benign and malignant breast tumor tissues. The specific contents are as follows:

[0090] (1) collecting and acquiring the ultrasonic radio frequency echo signals and B-ultrasound images of two vertical ultrasonic scans (transverse and longitudinal) of the ultrasonic scanner;

[0091] (2) Describe the acquisition of ultrasound radiofrequency echo signals and B-ultrasound images of two breast tissue benign and malignant tumor ROIs based on BI-RADS classification and tissue biopsy, such as Fig. 9 (a) is an ultrasound image of a benign breast tumor, (b) is an ultrasound image of a benign breast tumor lesion ROI, (c) is an ultrasound image of a malignant breast tumor, and (d) is an ultrasound image of a malignant breast tumor lesion ROI;

[0092] (3) The proposed LOMGA and the traditional WT method are used to estimate the MSS and its mean and standard deviation from the acquired ultrasonic RF echo signals respectively;

[0093] (4) Quantitative analysis and evaluation of the performance of MSS estimation results in distinguishing benign and malignant breast tumors: Draw scatter plots of the MSS of two different benign and malignant breast tumors estimated based on the LOMGA and WT methods, such as Fig.10(a) is a scatter plot of MSS estimated from benign and malignant tumor ROIs of levels 3 and 5 determined based on the BI-RADS standard based on the LOMGA method, and (b) is a scatter plot of MSS estimated from benign and malignant tumor ROIs of levels 3 and 5 determined based on the BI-RADS standard based on the WT method. The MSS results were processed by ANOVA and the p value was calculated. The ROC curve was drawn and the AUC was calculated, as shown in Fig.11 (a) is the ROC curve obtained from the MSS of the RF echo signals of the benign and malignant tumor ROIs of levels 3 and 5 marked as 0 and 1 based on the LOMGA and WT methods, respectively; (b) is the ROC curve obtained from the MSS of the RF echo signals of the benign and malignant tumor ROIs of levels 3 and 5 determined by the BI-RADS standard.

[0094] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0095] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent medical assistance platform based on ultrasonic radio frequency echo signals, characterized in that: It includes an ultrasonic radio frequency echo signal extraction module, an area of ​​interest feature signal processing module and an MSS estimation module; An ultrasonic radio frequency echo signal extraction module is used to obtain an ultrasonic radio frequency echo signal of a biological tissue through an ultrasonic device; The region of interest characteristic signal processing module is used to perform time domain analysis processing, frequency domain analysis processing and filtering processing on the ultrasonic radio frequency echo signal to obtain the tissue region of interest radio frequency echo signal and the tissue region of interest radio frequency echo spectrum; The MSS estimation module is used to estimate the inter-scattering element spacing ISS and the average scattering element spacing MSS by using the LOMGA method based on the RF echo signal of the region of interest to locate the best matching Gabor atom position.

2. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 1, characterized in that: Ultrasonic equipment transmits ultrasonic waves to biological tissues through an ultrasonic transducer as a sound source, and then uses a receiving transducer to receive the echo signal of the biological tissue.

3. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 1, characterized in that: It also includes a B-ultrasound image generation module, which is used to generate a B-ultrasound image by performing envelope extraction, logarithmic compression and interpolation on the ultrasonic radio frequency echo signal.

4. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 1, characterized in that: The interest area characteristic signal processing module includes a time domain analysis unit, a frequency domain analysis unit and a filtering unit; A time domain analysis unit, used for extracting a tissue region of interest and obtaining size data of the tissue region of interest by performing a time domain sampling theorem on the ultrasonic radio frequency echo signal; A frequency domain analysis unit, used for obtaining a radio frequency echo signal of the tissue region of interest by Fourier transforming the extracted signal data of the tissue region of interest; The filtering module is used to separate and filter the radio frequency echo signal of the tissue interest region through a Butterworth filter to obtain the fundamental wave and harmonics of the tissue interest region.

5. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 1, characterized in that: It also includes a wavelet transform analysis module for analyzing and extracting transient characteristic changes in the radio frequency echo spectrum signal of the area of ​​interest through a multi-resolution time-frequency analysis method to estimate the average scattering element spacing MSS.

6. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 1, characterized in that: The specific contents of the MSS estimation module are: Generate redundant Gabor atom sets and use MP algorithm to identify Gabor atoms matching the local components of the signal from the ultrasonic radio frequency echo signal; According to the change of the second-order difference SOD of the energy ratio RSRR of the reconstructed signal and the residual signal in the matching process, the Gabor atoms matching the regular scattering components are automatically obtained and the regular scattering components are reconstructed; Based on the reconstructed regular scattering components, the position information of the matching atoms is used to calculate the adjacent spacing of the matching atoms to estimate the adjacent scattering element spacing ISS. The average result of ISS is the mean scattering element spacing MSS.

7. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 6, characterized in that: The average scattering element spacing MSS estimation is based on the best matching Gabor atoms. Specifically, the maximum negative peak of the SOD curve of RSRR is used to determine the M' (M'≤M) Gabor atoms with the strongest correlation with the tissue regular scattering component. The position information of the matching atoms is used to calculate the distance between adjacent atoms to obtain the ISS and its MSS.

8. The intelligent medical assistance platform based on ultrasonic radio frequency echo signal according to claim 6, characterized in that: The distance between adjacent scattering elements ISS is: ISS k =(v k+1 -u k ),k=1,2,..,M'-1 The mean scatterer spacing MSS is: Where, M′ (M′≤M) is the number of Gabor atoms with the strongest correlation with the regular scattering component of the tissue, determined by using the maximum negative peak of the SOD curve of RSRR, and u k+1 、u k Adjacent matching atoms location information.

9. An intelligent medical assistance method based on ultrasonic radio frequency echo signal, characterized in that: A smart medical assistance platform based on ultrasonic radio frequency echo signals according to any one of claims 1 to 8, comprising the following steps: Obtaining ultrasonic radio frequency echo signals of biological tissues through ultrasonic equipment; Performing time domain analysis, frequency domain analysis and filtering processing on the ultrasonic radio frequency echo signal to obtain the radio frequency echo signal of the tissue interest area and the spectrum of the fundamental wave and harmonic wave signal of the tissue interest area; The inter-scatterer spacing (ISS) and the average scatterer spacing (MSS) are estimated by the LOMGA method based on the best matching Gabor atom position positioning of the RF echo signal in the region of interest.

10. An application of an intelligent medical assistance platform based on ultrasonic radio frequency echo signals, characterized in that: An intelligent medical assistance platform based on ultrasonic radio frequency echo signals as described in any one of claims 1 to 8 is used to assist in evaluating changes in tissue microwave ablation thermal damage areas and to assist in distinguishing benign and malignant breast tumor tissues.

Images