A prostate detection system, method, device and medium based on ultrasonic signals

Abstract

The present application discloses a prostate detection system, method, device and medium based on ultrasonic signals, which relates to the field of ultrasonic examination technology, and includes: a preset strain ultrasonic probe, which is used to apply pressure to the prostate gland to be examined in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through a data acquisition module; a processor, which is used to perform strain analysis on the prostate gland image to obtain the strain distribution results of the prostate gland to be examined under different pressure states, and obtain the hardness quantitative parameters and corresponding hardness distribution cloud map of the prostate gland to be examined according to the strain distribution results and pressure data; a memory, which is used to store the hardness quantitative parameters and hardness distribution cloud map sent by the processor; and an output device, which is used to output and display the hardness quantitative parameters and hardness distribution cloud map in the memory. It is non-invasive, accurate and efficient in prostate examination.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic examination, and in particular to a prostate detection system, method, device and medium based on ultrasonic signals. Background Art

[0002] At present, prostate examination is usually divided into non-invasive examination and invasive examination. Among them, the digital rectal examination is more common in non-invasive examination. The digital rectal examination requires the doctor to insert his finger into the patient's rectum and touch the prostate to check its size, shape, texture, etc. The digital examination is highly dependent on the experience of the operating doctor and is highly subjective. The examination results of different doctors may vary and lack objective quantitative standards. It can only provide a preliminary evaluation, and it may be difficult to accurately detect early or smaller lesions. For patients, it may bring some discomfort and psychological pressure. Invasive examinations are generally carried out in the form of prostate biopsy and PSA (Prostate Specific Antigen) screening, and the above invasive examinations generally cause pain and bleeding in patients. The TRUS (Transrectal ultrasound) examination method in non-invasive examinations is mainly used to guide prostate biopsy and display prostate nodules, and has poor specificity for the diagnosis of prostate cancer. It is difficult to accurately distinguish between benign and malignant lesions, and misdiagnosis or missed diagnosis may occur. Image quality is affected by many factors, such as intestinal gas and patient body shape. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a prostate detection system, method, device and medium based on ultrasonic signals, which can realize non-invasive and quantitative prostate examination. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a prostate detection system based on ultrasonic signals, comprising: a preset strain ultrasonic probe, a data acquisition module, a processor, a memory and an output device, wherein:

[0005] The preset strain ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through the data acquisition module;

[0006] The processor is used to perform strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtain the hardness quantitative parameters of the prostate gland to be inspected and the corresponding hardness distribution cloud map according to the strain distribution results and the pressure data;

[0007] The memory is used to store the hardness quantitative parameter and the hardness distribution cloud map sent by the processor;

[0008] The output device is used to output and display the hardness quantitative parameters and the hardness distribution cloud map in the memory.

[0009] Optionally, the preset strain ultrasonic probe includes:

[0010] An ultrasonic probe, a silicone coupling sleeve covering an ultrasonic emitting portion of the ultrasonic probe, and a preset pressure sensor fixedly attached to an outer surface of the silicone coupling sleeve.

[0011] Optionally, the preset strain ultrasonic probe includes:

[0012] The ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and continuously emit ultrasonic signals under different pressure states, and obtain prostate gland images under different pressure states according to the reflected ultrasonic signals, and synchronize the prostate gland images to the data acquisition module;

[0013] The preset pressure sensor is used to measure in real time the pressure data applied by the ultrasonic probe to the prostate gland to be inspected during operation, and synchronize the pressure data to the data acquisition module.

[0014] Optionally, the prostate detection system based on ultrasonic signals further includes an image processing module, wherein the image processing module includes:

[0015] An image segmentation unit, used for performing image segmentation processing on each of the prostate gland images in the data acquisition module to obtain a prostate portion image in the image, and performing smoothing processing on the prostate portion image to obtain each target prostate image;

[0016] The image deformation submodule is used to perform binarization processing on each of the target prostate images under different pressure states to obtain each target mask image; and perform displacement field analysis on each of the target mask images using a preset configuration algorithm to obtain target deformation image information relative to a reference image under different pressure states.

[0017] Optionally, the image deformation submodule includes:

[0018] An image binarization unit, used for setting the pixel value of the first area where the prostate tissue is located in each of the target prostate images under different pressure states to 1, and setting the pixel value of the second area where the non-prostate tissue is located to 0, so as to obtain each target mask image;

[0019] The image registration unit is used to use the target mask image corresponding to the minimum pressure as a reference image, and use other target mask images except the reference image as images to be registered; and perform registration processing on the images to be registered and the reference image to output target deformation image information under different pressure states.

[0020] Optionally, the processor includes:

[0021] A first processor unit is used to perform strain analysis on the prostate gland to be inspected under different pressure states based on the target deformation image information to obtain corresponding strain distribution results;

[0022] The second processor unit is used to perform fitting calculation on each pressure-strain single-point data to obtain the quantitative hardness parameter of the prostate gland to be inspected; wherein the pressure-strain single-point data is a data point constructed according to the strain distribution result and the corresponding pressure data.

[0023] Optionally, the processor includes:

[0024] The third processor unit is used to generate a hardness distribution cloud map of the prostate gland to be inspected according to the hardness quantitative parameters, strain distribution results and a preset visualization algorithm; wherein the hardness distribution cloud map represents the hardness distribution of different positions of the prostate gland to be inspected with different colors and / or gray levels.

[0025] In a second aspect, the present application discloses a prostate detection method based on ultrasonic signals, comprising:

[0026] Apply pressure to the prostate gland to be examined and emit ultrasonic signals in the order of applying pressure from low pressure to high pressure, so as to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through a data acquisition module;

[0027] Performing strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtaining hardness quantitative parameters and corresponding hardness distribution cloud diagrams of the prostate gland to be inspected according to the strain distribution results and the pressure data;

[0028] storing the hardness quantitative parameter and the hardness distribution cloud map;

[0029] The hardness quantitative parameter and the hardness distribution cloud map are output and displayed.

[0030] In a third aspect, the present application discloses an electronic device, including:

[0031] Memory, used to store computer programs;

[0032] A processor is used to execute the computer program to implement the steps of the aforementioned prostate detection method based on ultrasound signals.

[0033] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed prostate detection method based on ultrasound signals are implemented.

[0034] It can be seen that the present application discloses a prostate detection system based on ultrasonic signals, including: a preset strain ultrasonic probe, a data acquisition module, a processor, a memory and an output device, wherein the preset strain ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through the data acquisition module; the processor is used to perform strain analysis on the prostate gland image to obtain the strain distribution results of the prostate gland to be inspected under different pressure states, and obtain the hardness quantitative parameters and corresponding hardness distribution cloud map of the prostate gland to be inspected according to the strain distribution results and the pressure data; the memory is used to store the hardness quantitative parameters and the hardness distribution cloud map sent by the processor; the output device is used to output and display the hardness quantitative parameters and the hardness distribution cloud map in the memory. It can be seen that the inspection system of the present invention can quantitatively measure the hardness of the prostate, overcome the shortcomings of the doctor's finger inspection relying on subjective experience and judgment and the shortcomings of strain elastic ultrasound semi-quantitative, and can provide objective and accurate hardness values, providing a more reliable basis for doctors to diagnose prostate diseases. Moreover, the penetration depth of the examination is sufficient to examine the complete gland. Compared with the excitable shear wave technology, the present invention can fully cover the prostate tissue, avoid missing the lesion due to the limited signal penetration depth, and ensure effective detection of the entire prostate. The present invention is a non-invasive examination, which does not cause trauma to the patient's body, reducing the patient's pain and the risk of complications. Compared with invasive examinations such as prostate biopsy, patients are more likely to accept it. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 This is a schematic diagram of the structure of a prostate detection system based on ultrasonic signals disclosed in this application;

[0037] Figure 2 This is a schematic diagram of the structure of a preset strain ultrasonic probe disclosed in this application;

[0038] Figure 3 This is a flow chart of a prostate detection method based on ultrasonic signals disclosed in this application;

[0039] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 making creative work are within the scope of protection of the present invention.

[0041] At present, prostate examination is usually divided into non-invasive examination and invasive examination. Among them, the digital rectal examination is more common in non-invasive examination. The digital rectal examination requires the doctor to insert his finger into the patient's rectum and touch the prostate to check its size, shape, texture, etc. The digital examination is highly dependent on the experience of the operating doctor and is highly subjective. The examination results of different doctors may vary and lack objective quantitative standards. It can only provide a preliminary evaluation, and it may be difficult to accurately detect early or smaller lesions. For patients, it may bring some discomfort and psychological pressure. Invasive examinations are generally carried out in the form of prostate biopsy and PSA screening, and the above-mentioned invasive examinations generally cause pain and bleeding in patients. The transrectal ultrasound TRUS examination method in non-invasive examinations is mainly used to guide prostate biopsy and display prostate nodules, and has poor specificity for the diagnosis of prostate cancer. It is difficult to accurately distinguish between benign and malignant lesions, and misdiagnosis or missed diagnosis may occur. Image quality is affected by many factors, such as intestinal gas and patient body shape.

[0042] To this end, the present invention provides a prostate detection solution based on ultrasonic signals, which can realize non-invasive and quantitative prostate examination.

[0043] Reference Figure 1 As shown, the embodiment of the present invention discloses a prostate detection system based on ultrasonic signals, including: a preset strain ultrasonic probe 11, a data acquisition module 12, a processor 13, a memory 14 and an output device 15, wherein:

[0044] The preset strain ultrasonic probe 11 is used to apply pressure to the prostate gland to be examined in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through the data acquisition module 12;

[0045] The processor 13 is used to perform strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtain hardness quantitative parameters and corresponding hardness distribution cloud diagrams of the prostate gland to be inspected according to the strain distribution results and the pressure data;

[0046] The memory 14 is used to store the hardness quantitative parameters and the hardness distribution cloud map sent by the processor;

[0047] The output device 15 is used to output and display the hardness quantitative parameters and the hardness distribution cloud map in the memory.

[0048] In this embodiment, the aiming angle and multi-level pressure levels of the collection are pre-set according to the experience of clinical imaging doctors and clinical data; after the preset strain ultrasonic probe 11 is inserted into the rectum, different pressures are applied to the prostate gland by the ultrasonic probe. It should be noted that, in order to facilitate measurement and also considering the patient's examination psychology, pressure is continuously applied to the prostate gland in the order of low pressure to high pressure, and ultrasonic signals are emitted according to the set aiming angle while applying pressure, so that the data acquisition module 12 can collect ultrasonic images under different pressure levels, that is, prostate gland images under different pressure states. It should be noted that while collecting ultrasonic images, the data acquisition module 12 synchronously collects and records the corresponding pressure levels, that is, pressure data. It should be noted that when the data acquisition module 12 synchronously records and saves the signals collected by the pressure sensor and the ultrasonic probe, it is necessary to record the synchronous signals under no less than two pressure states, which at least include data of the two states of maximum loading pressure and minimum loading pressure.

[0049] In this embodiment, the pressure data and prostate gland image collected by the data acquisition module 12 are transmitted to the processor 13 so that the processor 13 performs strain analysis on the acquired prostate gland image. In this process, the processor 13 will evaluate the changes of the prostate gland to be inspected under different pressure states, and obtain the strain distribution results of the prostate gland to be inspected under various pressure states through strain calculation and analysis. When collecting pressure signals and prostate ultrasound images, pressure is applied step by step to the preset pressures at each level, and ultrasound images under different pressure levels are collected synchronously. This process allows the system to obtain more comprehensive prostate tissue information under different pressure conditions. By analyzing and processing images under multiple pressure states, the entire prostate gland can be better covered to ensure that no area is missed, reflecting the ability to inspect the complete gland. It should be noted that this strain distribution result can clearly reflect the local deformation degree and direction of the prostate gland to be inspected under different stress conditions. Then, the processor 13 will use the strain distribution results and the pressure data collected synchronously. Through specific algorithms and models, these data are comprehensively processed and calculated to obtain the hardness quantitative parameters of the prostate gland to be inspected. This hardness quantitative parameter is a value that can accurately reflect the hardness characteristics of the prostate gland, and fully considers the nonlinear characteristics of biological tissues, making the assessment of the gland hardness more scientific and accurate. At the same time, the processor 13 will further generate a corresponding hardness distribution cloud map based on the above data. This hardness distribution cloud map shows the hardness distribution of different positions of the prostate gland to be inspected in an intuitive way. Through visualization methods such as different colors or gray levels, the hardness change trend and distribution characteristics of the gland can be clearly understood at a glance. It provides an extremely important reference for the screening, diagnosis and treatment of prostate diseases.

[0050] In this embodiment, the memory 14 is used to store the hardness quantitative parameters and hardness distribution cloud map sent by the processor 13 after processing. Further, when it comes to the output display of the hardness quantitative parameters, the output device 15 will present this important value reflecting the hardness characteristics of the prostate gland in a clear and easy-to-read manner. The data device 15 can be displayed through a digital display screen, a printed report or on a specific software interface to ensure that doctors and related personnel can accurately and quickly obtain this key parameter so as to have an intuitive quantitative understanding of the hardness of the prostate gland. As for the output display of the hardness distribution cloud map, the output device 15 will give full play to its visual advantages. It will vividly display the hardness distribution of different positions of the prostate gland in a high-resolution image display mode. Through rich color levels, clear graphic contours and detailed annotation information, the observer can understand the hardness change trend of each part of the gland as if he were there. Whether at the scene of medical diagnosis or in the environment of research and analysis, the output device can provide doctors, researchers and patients with an intuitive and comprehensive visual reference, which helps the accurate diagnosis and effective treatment of prostate diseases.

[0051] The preset strain ultrasonic probe 11 comprises:

[0052] An ultrasonic probe 111, a silicone coupling sleeve 112 covering an ultrasonic emitting portion of the ultrasonic probe, and a preset pressure sensor 113 fixedly attached to the outer surface of the silicone coupling sleeve.

[0053] The ultrasonic probe 111 is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and continuously emit ultrasonic signals under different pressure states, and obtain prostate gland images under different pressure states according to the reflected ultrasonic signals, and synchronize the prostate gland images to the data acquisition module 12;

[0054] The preset pressure sensor 113 is used to measure in real time the pressure data applied by the ultrasonic probe 111 to the prostate gland to be inspected during operation, and synchronize the pressure data to the data acquisition module 12 .

[0055] It is understandable that if Figure 2As shown, the preset strain ultrasonic probe 11 includes an ultrasonic probe 111, a silicone coupling sleeve 112 and a preset pressure sensor 113, wherein the preset pressure sensor 113 is a flexible film pressure sensor, which is attached to the outer surface of the silicone coupling sleeve and covers the ultrasonic emitting part of the ultrasonic probe. Therefore, when the preset strain ultrasonic probe 11 is working, it can ensure that ultrasonic waves can be effectively transmitted into and out of the prostate tissue, and the silicone coupling sleeve 112 can reduce the air gap between the ultrasonic probe 111 and the human tissue, improve the transmission efficiency of ultrasonic waves, and thus help to achieve sufficient penetration depth to inspect the complete prostate gland to be inspected.

[0056] The prostate detection system based on ultrasonic signals further includes an image processing module 16, wherein the image processing module 16 includes:

[0057] The image segmentation unit 161 is used to perform image segmentation processing on each of the prostate gland images in the data acquisition module 12 to obtain a prostate portion image in the image, and to perform smoothing processing on the prostate portion image to obtain each target prostate image;

[0058] The image deformation submodule 162 is used to perform binarization processing on each of the target prostate images under different pressure states to obtain each target mask image; and perform displacement field analysis on each of the target mask images using a preset configuration algorithm to obtain target deformation image information relative to the reference image under different pressure states.

[0059] It is understandable that the image processing module 16 can perform image segmentation on each prostate gland image in the data acquisition module 12. In this process, the image segmentation unit 161 can accurately identify the prostate part in the prostate gland image through image analysis technology. Specifically, by comprehensively analyzing the grayscale features, texture features and edge information of the prostate gland image, the prostate tissue is distinguished from other surrounding tissues, thereby obtaining a clear and definite prostate part image in the image. In order to further improve the quality of the image and the accuracy of subsequent processing, the image segmentation unit 161 will perform image smoothing processing on the obtained prostate part image. Specifically, by adopting methods such as mean filtering, Gaussian filtering or median filtering, the noise in the image is reduced, so that the surface of the prostate part image is smoother and continuous. After this processing process, each target prostate image is finally obtained, and these images provide a more reliable basis for subsequent analysis and diagnosis. Further, the image deformation submodule 162 first performs binarization processing on each target prostate image under different pressure states. In this process, the image deformation submodule 162 divides the pixels in the target prostate image into two categories, thereby obtaining each target mask image. These mask images can clearly highlight the scope of the prostate tissue and provide a clear focus area for the subsequent displacement field analysis. Finally, the image deformation submodule 162 will use a preset configuration algorithm to perform an in-depth displacement field analysis on each target mask image. This preset configuration algorithm may include a differential homeomorphism demons registration algorithm, an iterative closest point ICP and other non-rigid registration algorithms. Through these algorithms, the image deformation submodule 162 can accurately calculate the deformation of the target mask image under different pressure states relative to the reference image. Finally, the target deformation image information relative to the reference image under different pressure states is obtained, which provides a key basis for the subsequent strain analysis and hardness calculation.

[0060] Specifically, the image deformation submodule 162 includes:

[0061] An image binarization unit 1621 is used to set the pixel value of the first area where the prostate tissue is located in each of the target prostate images under different pressure states to 1, and set the pixel value of the second area where the non-prostate tissue is located to 0, so as to obtain each target mask image;

[0062] The image registration unit 1622 is used to use the target mask image corresponding to the minimum pressure as a reference image, and use other target mask images except the reference image as images to be registered; and perform registration processing on the images to be registered and the reference image to output target deformation image information under different pressure states.

[0063] It can be understood that the image binarization unit 1621 undertakes the task of key processing of the target prostate image. It will carefully analyze each target prostate image under different pressure states. For the first area where the prostate tissue in the image is located, the image binarization unit 1621 will set its pixel value to 1. This operation can clearly identify the range of the prostate tissue, so that subsequent processing can focus more on the prostate area. For the second area where the non-prostate tissue is located, the image binarization unit 1621 will set its pixel value to 0. Through such processing, each target mask image is obtained. These mask images are presented in a concise and clear binary form, clearly dividing the prostate tissue and non-prostate tissue, providing clear boundaries and target areas for subsequent analysis. The image registration unit 1622 plays a vital role in the entire processing flow. First, it will determine the target mask image corresponding to the minimum pressure from a large number of target mask images, and use it as a reference image. Specifically, the prostate gland image at the minimum pressure level (under the premise of ensuring the quality of the ultrasound image, the ultrasound probe is close to the rectal wall with the minimum force) is used as a reference image. This reference image plays a benchmark role in the subsequent registration process. At the same time, the image registration unit 1622 uses other target mask images except the reference image as images to be registered. Next, the image registration unit 1622 will perform fine registration processing on these images to be registered and the reference image. Specifically, determine the reference image and the image to be registered. Usually, the reference image is an image that is relatively stable or has a standard state obtained under specific conditions (the present invention uses the prostate gland image under the minimum pressure level as the reference image), and the image to be registered is an image that needs to be aligned with the reference image. The force field is calculated based on the grayscale difference between the reference image and the image to be registered. The direction of the force points to the direction that reduces the difference between the two images. This force field reflects the deformation trend of each pixel in the image. The deformation field of the image is updated according to the force field, so that the image to be registered gradually approaches the reference image. The deformation field describes the displacement vector of each pixel in the image. By continuously adjusting the deformation field, the deformation and alignment of the image can be achieved. Repeat the above steps for multiple iterations until the convergence condition is reached, that is, the difference between the two images is small enough. The convergence condition can be set according to the specific application, for example, the similarity between the images reaches a certain threshold or the number of iterations reaches a preset value. In this process, it will continuously adjust the deformation parameters of the image to be registered. By using a registration algorithm, such as a differential homeomorphism demons registration algorithm or an iterative closest point ICP and other non-rigid registration algorithms, the image registration unit 1622 can accurately calculate the difference between the image to be registered and the reference image, and adjust the deformation parameters according to these differences. Its purpose is to control the image to be registered to gradually approach the reference image so that the difference between the two gradually decreases.Through continuous iteration and optimization of this process, the target deformation image information under different pressure states, that is, the displacement field information, is finally output. These deformation image information reflects the changes of prostate tissue under different pressure states relative to the reference state, providing data support for subsequent strain analysis and hardness calculation.

[0064] The processor 13 includes:

[0065] The first processor unit 131 is used to perform strain analysis on the prostate gland to be inspected under different pressure states based on the target deformation image information to obtain corresponding strain distribution results;

[0066] The second processor unit 132 is used to perform fitting calculation on each pressure-strain single point data to obtain the hardness quantitative parameter of the prostate gland to be inspected; wherein the pressure-strain single point data is a data point constructed according to the strain distribution result and the corresponding pressure data;

[0067] The third processor unit 133 is used to generate a hardness distribution cloud map of the prostate gland to be inspected according to the hardness quantitative parameters, strain distribution results and a preset visualization algorithm; wherein the hardness distribution cloud map represents the hardness distribution of different positions of the prostate gland to be inspected with different colors and / or gray levels.

[0068] It is understandable that the processor 13 includes multiple processor units, among which the first processor unit 131 performs an in-depth and detailed strain analysis on the prostate gland to be inspected under different pressure states based on the target deformation image information. In this process, the first processor unit 131 calculates the deformation degree and direction of the prostate gland under different pressure states, and then through the interpretation of the target deformation image information, it can determine the displacement change of each pixel point, and calculate the corresponding strain value based on these displacement changes. Finally, the corresponding strain distribution result is obtained, which clearly reflects the strain of the prostate gland in various parts and provides important basic data for subsequent hardness analysis. The second processor unit 132 is responsible for fitting and calculating each pressure-strain single-point data. The pressure-strain single-point data is a data point constructed based on the strain distribution result and the corresponding pressure data. These data points reflect the relationship between the strain of the prostate gland under different pressures and the pressure it is subjected to. The second processor unit 132 will use a specific fitting algorithm, such as the least squares method, to fit these single-point data to obtain the hardness quantitative parameters of the prostate gland to be inspected. Specifically, considering the nonlinear characteristics of biological tissues, the fitting formula is as follows:

[0069] ;Formula (1)

[0070] in, Represents pressure data, Represents strain, , , represents the fitting coefficient.

[0071] The above fitting formula is used to describe the relationship between pressure and strain of prostate tissue under stress. The nonlinear characteristics of biological tissue are taken into account, that is, the relationship between pressure and strain is not a simple linear relationship. Through the above formula, the corresponding pressure value can be calculated according to the measured strain value, or conversely, the strain can be estimated according to the pressure value. The consideration of this nonlinear relationship makes the assessment of prostate tissue hardness more accurate, because biological tissues often exhibit complex nonlinear behavior under different stress conditions. The values ​​of coefficients and exponents may need to be determined by fitting experimental data to better adapt to the prostate tissue characteristics of different individuals.

[0072] According to the fitting result of the above formula (1), a pressure-strain data curve is obtained, and N points of the data curve are uniformly sampled to calculate the hardness quantitative parameters according to formula (2) through the processor 13, as shown below:

[0073] ;Formula (2)

[0074] in, represents the quantitative parameter of hardness, Indicates sampling points, and N represents the total number of sampling points.

[0075] This hardness quantitative parameter fully considers the nonlinear characteristics of biological tissues and can accurately reflect the comprehensive hardness distribution of the prostate gland. It provides a quantitative indicator for doctors to evaluate the health of the prostate, which helps to diagnose prostate diseases more accurately. The task of the third processor unit 133 is to generate a hardness distribution cloud map of the prostate gland to be inspected through a preset visualization algorithm based on the hardness quantitative parameter and the strain distribution result. In the process of generating the cloud map, the third processor unit 133 will fully consider the hardness difference at different positions and characterize the hardness distribution of different positions of the prostate gland to be inspected with different colors and / or gray levels. For example, harder areas may be represented by darker colors or higher gray levels, while softer areas are represented by lighter colors or lower gray levels. The hardness distribution cloud map generated in this way is intuitive and vivid, which allows doctors to understand the hardness change trend and distribution characteristics of the prostate gland at a glance, and provides strong visualization support for the diagnosis and treatment of prostate diseases.

[0076] In this way, the processor 13 comprehensively analyzes and processes the collected pressure data, ultrasonic images, and displacement field information obtained through registration, and finally generates quantitative parameters reflecting the hardness characteristics of the prostate gland and an intuitive hardness distribution cloud map. These results provide doctors with comprehensive and accurate information, which helps them to more accurately judge the health status of the prostate, timely discover potential disease risks, and develop more effective treatment plans. At the same time, the efficiency and accuracy of the processor also make the entire detection system more reliable and practical, providing strong technical support for the screening and diagnosis of prostate diseases.

[0077] It can be seen that the present application discloses a prostate detection system based on ultrasonic signals, including: a preset strain ultrasonic probe, a data acquisition module, a processor, a memory and an output device, wherein the preset strain ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through the data acquisition module; the processor is used to perform strain analysis on the prostate gland image to obtain the strain distribution results of the prostate gland to be inspected under different pressure states, and obtain the hardness quantitative parameters and corresponding hardness distribution cloud map of the prostate gland to be inspected according to the strain distribution results and the pressure data; the memory is used to store the hardness quantitative parameters and the hardness distribution cloud map sent by the processor; the output device is used to output and display the hardness quantitative parameters and the hardness distribution cloud map in the memory. It can be seen that the inspection system of the present invention can quantitatively measure the hardness of the prostate, overcome the shortcomings of the doctor's finger inspection relying on subjective experience and judgment and the shortcomings of strain elastic ultrasound semi-quantitative, and can provide objective and accurate hardness values, providing a more reliable basis for doctors to diagnose prostate diseases. Moreover, the penetration depth of the examination is sufficient to examine the complete gland. Compared with the excitable shear wave technology, the present invention can fully cover the prostate tissue, avoid missing the lesion due to the limited signal penetration depth, and ensure effective detection of the entire prostate. The present invention is a non-invasive examination, which does not cause trauma to the patient's body, reducing the patient's pain and the risk of complications. Compared with invasive examinations such as prostate biopsy, patients are more likely to accept it.

[0078] Reference Figure 3 As shown, the present invention also discloses a prostate detection method based on ultrasonic signals, comprising:

[0079] Step S11: applying pressure to the prostate gland to be inspected and emitting ultrasonic signals in a pressure sequence from low pressure to high pressure to obtain prostate gland images under different pressure states, and synchronously recording corresponding pressure data through a data acquisition module;

[0080] Step S12: performing strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtaining hardness quantitative parameters and corresponding hardness distribution cloud diagrams of the prostate gland to be inspected according to the strain distribution results and the pressure data;

[0081] Step S13: storing the hardness quantitative parameter and the hardness distribution cloud map;

[0082] Step S14: outputting and displaying the hardness quantitative parameter and the hardness distribution cloud map.

[0083] For more detailed implementation processes of steps S11, S12, S13, and S14, please refer to the aforementioned disclosed embodiments, which will not be described again here.

[0084] It can be seen that the present application discloses applying pressure to the prostate gland to be inspected in the order of applying pressure from low pressure to high pressure and emitting ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data; strain analysis is performed on the prostate gland image to obtain the strain distribution results of the prostate gland to be inspected under different pressure states, and the hardness quantitative parameters and the corresponding hardness distribution cloud map of the prostate gland to be inspected are obtained according to the strain distribution results and the pressure data; the hardness quantitative parameters and the hardness distribution cloud map are stored; the hardness quantitative parameters and the hardness distribution cloud map are output and displayed. It can be seen that the present invention quantitatively measures the hardness of the prostate, overcomes the shortcomings of the doctor's finger examination relying on subjective experience judgment and the shortcomings of strain elastic ultrasound semi-quantitative, can provide objective and accurate hardness values, and provide doctors with a more reliable basis for diagnosing prostate diseases. Moreover, the penetration depth of the inspection is sufficient to inspect the complete gland. Compared with the excitable shear wave technology, the present invention can fully cover the prostate tissue, avoid missing the lesion due to the limited signal penetration depth, and ensure effective detection of the entire prostate. The present invention is a non-invasive examination, which is non-invasive to the patient's body, reducing the patient's pain and the risk of complications. Compared with invasive examinations such as prostate biopsy, patients are more likely to accept it.

[0085] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0086] Figure 4The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the prostate detection method based on ultrasound signals disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0087] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0088] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0089] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0090] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the prostate detection method based on ultrasonic signals performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the electronic device, the data 223 can also include data collected by its own input and output interface 25.

[0091] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed prostate detection method based on ultrasonic signals is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, and no further description will be given here.

[0092] 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.

[0093] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly with hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory RAM (Random Access Memory), memory, read-only memory ROM (Read Only Memory), electrically programmable EPROM (Electrically Programmable Read Only Memory), electrically erasable programmable EEPROM (ElectricErasable Programmable Read Only Memory), register, hard disk, removable disk, CD-ROM (CompactDisc-Read Only Memory), or any other form of storage medium known in the technical field.

[0094] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0095] The scheme provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A prostate detection system based on ultrasonic signals, characterized in that: include: Preset strain ultrasonic probe, data acquisition module, processor, memory, image processing module and output device, wherein: The preset strain ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and emit ultrasonic signals to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through the data acquisition module; The processor is used to perform strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtain the hardness quantitative parameters of the prostate gland to be inspected and the corresponding hardness distribution cloud map according to the strain distribution results and the pressure data; The memory is used to store the hardness quantitative parameter and the hardness distribution cloud map sent by the processor; The output device is used to output and display the hardness quantitative parameters and the hardness distribution cloud map in the memory; Wherein, the image processing module includes: An image segmentation unit, used for performing image segmentation processing on each of the prostate gland images in the data acquisition module to obtain a prostate portion image in the image, and performing smoothing processing on the prostate portion image to obtain each target prostate image; An image deformation submodule is used to perform binarization processing on each of the target prostate images under different pressure states to obtain each target mask image; and perform displacement field analysis on each of the target mask images using a preset configuration algorithm to obtain target deformation image information relative to a reference image under different pressure states; The image deformation submodule comprises: An image binarization unit, used for setting the pixel value of the first area where the prostate tissue is located in each of the target prostate images under different pressure states to 1, and setting the pixel value of the second area where the non-prostate tissue is located to 0, so as to obtain each target mask image; An image registration unit, used to use the target mask image corresponding to the minimum pressure as a reference image, and use other target mask images except the reference image as images to be registered; perform registration processing on the images to be registered and the reference image to output target deformation image information under different pressure states; The processor comprises: A first processor unit is used to perform strain analysis on the prostate gland to be inspected under different pressure states based on the target deformation image information to obtain corresponding strain distribution results; The second processor unit is used to perform fitting calculation on each pressure-strain single-point data to obtain the hardness quantitative parameter of the prostate gland to be inspected; wherein the pressure-strain single-point data is a data point constructed according to the strain distribution result and the corresponding pressure data; The second processor unit is specifically configured to: Fitting calculation is performed on each single-point pressure-strain data to obtain the pressure-strain data curve; wherein, Represents pressure data, Represents strain, , , represents the fitting coefficient; The second processor unit is specifically configured to Calculate the quantitative parameters of hardness; represents the quantitative parameter of hardness, Indicates sampling points, N Represents the total number of sampling points on the pressure-strain data curve.

2. The prostate detection system based on ultrasonic signals according to claim 1, characterized in that: The preset strain ultrasonic probe comprises: An ultrasonic probe, a silicone coupling sleeve covering an ultrasonic emitting portion of the ultrasonic probe, and a preset pressure sensor fixedly attached to an outer surface of the silicone coupling sleeve.

3. The prostate detection system based on ultrasonic signals according to claim 2, characterized in that: The preset strain ultrasonic probe comprises: The ultrasonic probe is used to apply pressure to the prostate gland to be inspected in a pressure sequence from low pressure to high pressure and continuously emit ultrasonic signals under different pressure states, and obtain prostate gland images under different pressure states according to the reflected ultrasonic signals, and synchronize the prostate gland images to the data acquisition module; The preset pressure sensor is used to measure in real time the pressure data applied by the ultrasonic probe to the prostate gland to be inspected during operation, and synchronize the pressure data to the data acquisition module.

4. The prostate detection system based on ultrasonic signals according to claim 1, characterized in that: The processor comprises: The third processor unit is used to generate a hardness distribution cloud map of the prostate gland to be inspected according to the hardness quantitative parameters, strain distribution results and a preset visualization algorithm; wherein the hardness distribution cloud map represents the hardness distribution of different positions of the prostate gland to be inspected with different colors and / or gray levels.

5. A prostate detection method based on ultrasonic signals, characterized in that: include: Apply pressure to the prostate gland to be examined and emit ultrasonic signals in the order of applying pressure from low pressure to high pressure, so as to obtain prostate gland images under different pressure states, and synchronously record corresponding pressure data through a data acquisition module; Performing strain analysis on the prostate gland image to obtain strain distribution results of the prostate gland to be inspected under different pressure states, and obtaining hardness quantitative parameters and corresponding hardness distribution cloud diagrams of the prostate gland to be inspected according to the strain distribution results and the pressure data; storing the hardness quantitative parameter and the hardness distribution cloud map; Outputting and displaying the hardness quantitative parameter and the hardness distribution cloud map; The prostate detection method further includes: performing image segmentation processing on each of the prostate gland images in the data acquisition module to obtain a prostate partial image in the image, and performing smoothing processing on the prostate partial image to obtain each target prostate image; performing binarization processing on each of the target prostate images under different pressure states to obtain each target mask image; performing displacement field analysis on each of the target mask images using a preset configuration algorithm to obtain target deformation image information relative to a reference image under different pressure states; The binarization processing is performed on each of the target prostate images under different pressure states to obtain each target mask image; and the displacement field analysis is performed on each of the target mask images using a preset configuration algorithm to obtain target deformation image information relative to a reference image under different pressure states, including: The pixel value of the first area where the prostate tissue is located in each of the target prostate images under different pressure states is set to 1, and the pixel value of the second area where the non-prostate tissue is located is set to 0, so as to obtain each target mask image; the target mask image corresponding to the minimum pressure is used as a reference image, and other target mask images except the reference image are used as images to be registered; the images to be registered are registered with the reference image to output target deformation image information under different pressure states; The strain analysis of the prostate gland image is performed to obtain the strain distribution results of the prostate gland to be inspected under different pressure states, including: Based on the target deformation image information, strain analysis is performed on the prostate gland to be inspected under different pressure states to obtain corresponding strain distribution results; fitting calculation is performed on each pressure-strain single point data to obtain the hardness quantitative parameter of the prostate gland to be inspected; wherein the pressure-strain single point data is a data point constructed according to the strain distribution result and the corresponding pressure data; The fitting calculation of each pressure-strain single point data to obtain the hardness quantitative parameter of the prostate gland to be inspected includes: pass Fitting calculation is performed on each single-point pressure-strain data to obtain the pressure-strain data curve; wherein, Represents pressure data, Represents strain, , , represents the fitting coefficient; according to Calculate the quantitative parameters of hardness; represents the quantitative parameter of hardness, Indicates sampling points, N Indicates the total number of sampling points.

6. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the prostate detection method based on ultrasound signals as described in claim 5.

7. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the prostate detection method based on ultrasound signals as claimed in claim 5 are implemented.

Images