Medical ultrasonic image analysis system and method

Abstract

The invention discloses a medical ultrasonic image analysis system and method, and relates to the technical field of medical image processing, and the system comprises an ultrasonic image collection module, an image feature extraction module, a Bayesian network diagnosis model construction module, a probabilistic reasoning calculation module and a diagnosis result output module. According to the medical ultrasonic image analysis system, the Bayesian network diagnosis model is constructed, various features in the image and personal information and medical history of a patient can be comprehensively considered, comprehensive and accurate diagnosis of diseases is achieved, the accuracy and reliability of diagnosis are improved, and the diagnosis efficiency is improved. Meanwhile, the influence of subjective judgment of a doctor on the diagnosis result is greatly reduced, the risk of misdiagnosis and missed diagnosis is reduced, meanwhile, due to the fact that the Bayesian network has the high reasoning ability and self-learning ability, the system can continuously optimize and perfect the diagnosis model along with accumulation of clinical data, and the diagnosis precision and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a medical ultrasonic image analysis system and method. Background Art

[0002] As one of the important means of modern medical diagnosis, medical ultrasound imaging technology is widely used in clinical practice due to its non-invasive, real-time and low-cost characteristics. In the field of medical image analysis, especially when diagnosing ultrasound images, doctors often need to comprehensively judge the type and severity of the disease based on multiple features in the image as well as the patient's personal information and medical history. Therefore, it is particularly important to develop a system that can automatically and intelligently analyze medical ultrasound images and accurately diagnose diseases.

[0003] However, some current medical ultrasound image analysis systems that use machine learning and artificial intelligence technologies have limitations when processing complex and changeable ultrasound images. They only rely on a single image feature for diagnosis, ignoring the correlation and complementarity between different features, resulting in insufficient accuracy and reliability of diagnostic results. In addition, they fail to fully consider the impact of patient information when constructing diagnostic models, causing diagnostic results to deviate from actual conditions and failing to provide doctors with comprehensive diagnostic reference information, increasing the difficulty and risk of diagnostic decisions.

[0004] In summary, the existing technology has limitations in the automated analysis and uncertainty quantification of ultrasound images. Therefore, a more comprehensive and accurate ultrasound image analysis solution is developed by introducing a diagnostic model based on a Bayesian network to meet the development trend of modern medicine. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a medical ultrasound image analysis system and method. It can effectively integrate ultrasound image features and patient information by constructing a diagnostic model based on a Bayesian network, provide a more accurate probability of disease occurrence, and use confidence intervals and entropy values ​​to evaluate the reliability of the results, thereby providing doctors with more comprehensive diagnostic reference information. This ability to quantify uncertainty enables doctors to better assess risks during the diagnosis process and make more reasonable treatment decisions.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, a medical ultrasound image analysis system, the system comprises: an ultrasound image acquisition module, an image feature extraction module, a Bayesian network diagnosis model construction module, a probability reasoning calculation module and a diagnosis result output module; The ultrasonic image acquisition module is connected to the medical ultrasonic imaging device and is used to acquire medical ultrasonic images and pre-process the images to optimize the influence of interference factors on diagnosis; The image feature extraction module extracts multiple features from the collected ultrasound image and uses the extracted features as input information of the Bayesian network diagnosis model. The features include edge gradient features, regional contrast features, and spectrum features, wherein: The edge gradient feature extraction process is as follows: Medium pixel Gray value at , use the Sobel operator to calculate the horizontal gradient and vertical gradient , that is, the horizontal gradient operator is , the vertical gradient operator is ,but , edge gradient amplitude , for the entire image, the total number of image pixels is , then the edge gradient eigenvalue , where M and N are the number of rows and columns of the image, and this value is used to describe the overall degree of change of the tissue boundary in the image and input the information into the Bayesian network diagnosis model; The extraction process of the regional contrast feature is as follows: the image is divided into non-overlapping sub-regions ,in , , set sub-area The average gray value is The average gray value of the entire image is , then the sub-region Contrast value with the entire image , regional contrast feature ,in For sub-region The weight of , which is used to reflect the grayscale differences between different regions and input into the Bayesian network diagnosis model; The process of extracting the spectrum features is: performing a two-dimensional discrete Fourier transform 2D-DFT on the ultrasound image, that is, ,in and are the number of rows and columns of the image, respectively. , , the spectral characteristics include the peak frequency , that is, the spectrum amplitude The frequency coordinate corresponding to the maximum, and the bandwidth , the corresponding spectrum energy function is , calculate the total energy , starting from low frequency to accumulate energy, when the accumulated energy reaches The frequency range corresponding to the time is the bandwidth The spectrum feature is used to analyze the relationship between the frequency characteristics of the ultrasonic reflection signal and the tissue characteristics and is used as the model input. The spectrum feature value is ; The Bayesian network diagnostic model construction module is used to construct a Bayesian network diagnostic model, determine the probability relationship between the nodes of the network, set the extracted image features and patient information as network nodes, and determine the conditional probability distribution between the nodes according to the clinical data to obtain the disease nodes, thereby constructing a complete Bayesian network structure. At the same time, uncertainty quantification indicators, namely confidence intervals and entropy values, are introduced into the model to quantify the degree of uncertainty of the probability results. The specific construction process of the Bayesian network diagnostic model is as follows: Determine the node type: According to the edge gradient feature value obtained by the image feature extraction module , Regional contrast features The spectral characteristic value is , and the patient's age and gender Information is used as image feature nodes and patient information nodes respectively, and the basic node set in the Bayesian network is obtained as follows: , where the image feature nodes include edge gradient feature nodes , Regional Contrast Feature Node , Spectrum Feature Node , patient information nodes include age nodes , Gender Node ; Determine the probability relationship between nodes: Collect clinical case data, including the patient's ultrasound image data, the corresponding image feature calculation results, the patient's age, gender information, and the final confirmed disease type, and determine the probability distribution between nodes through conditional probability distribution, that is, for disease nodes and the base node set , calculate the conditional probability distribution , that is, considering the disease and a combination of a set of feature values ​​and patient information values , count the co-occurrence of diseases in the dataset The number of times this feature is combined , and the number of times this feature combination appears alone , then the conditional probability , through this conditional probability method, the basic node set All image feature nodes and patient information nodes in are associated with disease nodes; Constructing a Bayesian network structure: Based on the determined probabilistic relationship between nodes, a Bayesian network structure is constructed. Each node in the network represents a random variable, and the directed edges between nodes represent the dependency relationship between variables. Introducing uncertainty quantification indicators: Introducing uncertainty quantification indicators into the Bayesian network diagnosis model, including confidence intervals and entropy values, to quantify the degree of uncertainty of probability results; The probability reasoning calculation module inputs the feature data obtained by the image feature extraction module into the Bayesian network diagnosis model, calculates the probability of disease occurrence through the Bayesian network structure, and updates the value of the uncertainty quantification index in real time during the calculation process. With the input of new data and the progress of probability reasoning, the confidence interval and entropy value indicators are dynamically adjusted; The diagnosis result output module presents the disease occurrence probability obtained by the probability reasoning calculation module to the doctor in the form of a probability numerical list, and provides corresponding diagnosis suggestions to assist the doctor in making the final diagnosis decision.

[0007] Furthermore, in the process of constructing the Bayesian network diagnosis model, the Bayesian network diagnosis model construction module compares the edge gradient feature nodes of the image feature nodes with the disease nodes. The association determination process is as follows: extract edge gradient features from clinical ultrasound image samples to obtain the edge gradient feature value set of each sample image ,in For the edge gradient feature values ​​of sample images, for each disease type , statistics the distribution of edge gradient eigenvalues ​​in sample images where the disease exists, that is, the disease The corresponding edge gradient eigenvalue subset is , calculate disease With edge gradient feature node The conditional probability distribution of for: ,in, Indicates disease And the edge gradient eigenvalue is The number of samples, Indicates that the edge gradient feature value is The total number of samples.

[0008] Furthermore, in the process of constructing the Bayesian network diagnosis model, the Bayesian network diagnosis model construction module calculates the regional contrast feature nodes of the image feature nodes. Disease Node The association determination process is as follows: Calculate the regional contrast feature value for clinical ultrasound image samples , and obtain the regional contrast feature value set , for diseases , determine the corresponding regional contrast feature value subset as , calculate disease With the regional contrast feature node The conditional probability distribution of for: ,in, Indicates disease And the regional contrast feature value is The number of samples, Indicates that the regional contrast feature value is The total number of samples.

[0009] Furthermore, in the process of constructing the Bayesian network diagnosis model, the Bayesian network diagnosis model construction module generates a spectrum feature node for the image feature node. Disease Node The association determination process is as follows: obtain the spectrum feature value from the spectrum analysis of clinical ultrasound image samples , including the peak frequency and bandwidth , forming a set of spectral eigenvalues , for diseases , determine the corresponding subset of spectral eigenvalues , calculate disease With the Spectrum Feature Node The conditional probability distribution of for: , where the count function is used to count the number of samples that combine disease and spectrum feature values.

[0010] Furthermore, the Bayesian network diagnosis model construction module, in the process of constructing the Bayesian network diagnosis model, for the age node of the patient information node Disease Node The association determination process is as follows: collect patient age information and disease diagnosis results in clinical case data, divide age into different intervals, and count each disease in each age interval. The number of cases And the total number of samples in each age range , calculate disease With age node The conditional probability distribution of for: ,in, Indicates the age range interval.

[0011] Furthermore, the Bayesian network diagnosis model construction module, in the process of constructing the Bayesian network diagnosis model, for the gender node of the patient information node Disease Node The association determination process is as follows: Count the number of male and female patients with each disease in the clinical case data The number of cases and , and the total sample size of male and female patients and , calculate disease With gender node The conditional probability distribution of for: .

[0012] Furthermore, the Bayesian network diagnostic model construction module introduces quantitative indicators of uncertainty confidence interval and entropy value in the process of constructing the Bayesian network diagnostic model, wherein: For confidence interval: for the probability of disease occurrence , calculate the sample mean and the sample standard deviation , using the unbiased estimation formula in the normal approximation method ,in It is The estimated probability of disease occurrence for samples is is the sample size, at a confidence level of Next, we can get the quantile by looking up the standard normal distribution table. , then the confidence interval is , the confidence interval can intuitively show the range of the estimated probability of disease occurrence; For entropy value: according to the probability distribution of disease occurrence , For disease The probability of occurrence, the calculated entropy value is: ,in, is the total number of disease types. A large entropy value indicates a dispersed probability distribution with high uncertainty. A small entropy value indicates that the probability is concentrated on one disease type with low uncertainty. The entropy value is used to quantify the degree of uncertainty in the probability of disease occurrence, providing doctors with more comprehensive diagnostic reference information and helping them evaluate the credibility of the diagnostic results.

[0013] Furthermore, the probability reasoning calculation module adopts the Bayesian reasoning formula , dynamically adjust the confidence interval and entropy value indicators, where is the disease node, is the set of evidence nodes, i.e., image feature and patient information nodes, For the disease Evidence under the conditions of occurrence The probability of occurrence, For disease The prior probability of For the evidence Lower Disease The posterior probability of the iterative calculation process is updated according to the structure and conditional probability distribution of the Bayesian network after each new data input. and Parameters, recalculate the posterior probability , and update the confidence interval and entropy value at the same time. That is, when new image feature data and patient information are added, the new conditional probability distribution is calculated according to the new evidence combination, and then the estimated value of the disease probability and its confidence interval and entropy value are updated, and a new evidence node is set. Add, calculate ,renew for Recalculate , for confidence interval updates, recalculate based on new sample data and , and then get a new confidence interval, and the entropy value is updated by the new posterior probability Form a new probability distribution , recalculate .

[0014] On the other hand, a medical ultrasound image analysis method, the specific steps of the method are: S1. Start the ultrasound image acquisition module, establish a connection with the ultrasound imaging device, receive and store the acquired ultrasound image data in real time, and record the acquisition time and metadata of the patient information; S2, transmitting the collected ultrasound image to the image feature extraction module, performing edge gradient feature, regional contrast feature, and spectrum feature extraction on the image, storing the processed feature data in the feature database, and establishing an associated index with the patient information; S3. Construct a Bayesian network diagnostic model, determine the node type and number of the Bayesian network, collect clinical case data, calculate the conditional probability distribution between nodes based on the clinical data, and integrate the calculation model of uncertainty quantification indicators into the model so that the model can simultaneously output uncertainty quantification results while calculating the probability of disease occurrence; S4, reading the image feature data and basic information of the current patient from the feature database, inputting the data into the constructed Bayesian network diagnosis model, starting the probability reasoning calculation process, performing iterative calculation, and outputting the disease occurrence probability result and the corresponding uncertainty quantification value; S5. The calculated probability of occurrence of various diseases and their uncertainty quantitative information are transmitted to the diagnosis result output module to generate a visual diagnosis result report.

[0015] Compared with the prior art, the medical ultrasound image analysis system and method have the following beneficial effects: 1. The medical ultrasound image analysis system of the present invention can comprehensively consider multiple features in the image as well as the patient's personal information and medical history by constructing a Bayesian network diagnostic model, thereby achieving a comprehensive and accurate diagnosis of the disease. It not only improves the accuracy and reliability of the diagnosis, but also greatly reduces the impact of the doctor's subjective judgment on the diagnosis results, and reduces the risk of misdiagnosis and missed diagnosis. At the same time, since the Bayesian network has powerful reasoning and self-learning capabilities, the system can continuously optimize and improve the diagnostic model as clinical data accumulates, thereby improving the accuracy and efficiency of the diagnosis.

[0016] 2. The present invention also introduces uncertainty quantification indicators to provide doctors with more comprehensive diagnostic reference information. By calculating the uncertainty quantification indicators of confidence intervals and entropy values, the present invention can quantify the degree of uncertainty in the diagnostic results, help doctors more accurately assess the severity of the disease and possible development trends, enhance the objectivity and scientific nature of the diagnostic results, and provide strong support for doctors to formulate personalized treatment plans.

[0017] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is an operation flow chart of a medical ultrasound image analysis system; Figure 2 This is a node association process diagram of an image feature extraction module in a medical ultrasound image analysis system. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0021] Embodiment 1 This embodiment demonstrates the application of the medical ultrasound image analysis system of the present invention in the diagnosis of cardiovascular diseases. Through ultrasound image acquisition, feature extraction, Bayesian network diagnosis model construction and analysis, it finally outputs diagnosis results and suggestions, providing strong support for the accurate diagnosis of cardiovascular diseases.

[0022] In the specific implementation, first, the ultrasound image acquisition module is connected to the cardiovascular ultrasound imaging device to acquire the ultrasound image of the patient's heart. During the acquisition process, the probe frequency, scanning depth and gain parameters are adjusted according to the patient's body position and heart condition to obtain clear ultrasound image data. The acquired image is preprocessed to remove noise interference, enhance the image contrast and clarity, optimize the image quality, and transmit the image to the image feature extraction module.

[0023] Then, the image feature extraction module extracts edge gradient features from the ultrasound image. The Sobel operator is applied to the ultrasound image to calculate the edge gradient amplitude of each pixel. Then, the edge gradient amplitude of the entire image is statistically analyzed, that is, the mean and variance statistics are calculated as the value of this node. This node is designed to capture the severity of changes in tissue boundaries and overall characteristics in the image, because diseased tissues often differ from normal tissues in boundary morphology, with more blurred, irregular edges or higher gradient changes. Therefore, for images, Pixels in , use the Sobel operator to calculate the horizontal gradient (in is the horizontal gradient operator, Pixel Gray value at ) and vertical gradient is the vertical gradient operator), and calculates the edge gradient amplitude , for the entire image (assuming the total number of pixels is , the number of image rows is , the number of columns is ), edge gradient eigenvalue This value is used to describe the overall degree of change of the cardiac tissue boundary and is input into the Bayesian network diagnostic model. Then, regional contrast feature extraction is performed: the image is divided into multiple sub-regions, and the grayscale contrast between each sub-region and the entire image is calculated respectively. The feature value is obtained by summing up the weights assigned according to the importance of the sub-regions. This node reflects the difference in grayscale levels between different regions in the image. The lesion area may show a different contrast from the surrounding normal tissue due to changes in tissue density and structure, which helps to locate and identify the lesion site and its range. The specific process is: the cardiac ultrasound image is divided into non-overlapping sub-regions , , calculate the sub-region The average gray value and the average gray value of the entire image , sub-area Contrast value with the entire image , regional contrast feature For sub-region The feature reflects the grayscale difference between different areas of the heart and is used to input into the Bayesian network diagnostic model; then the spectrum feature extraction is performed: the ultrasound image is subjected to a two-dimensional discrete Fourier transform to obtain the spectrum information, and the key parameters of the spectrum peak frequency and bandwidth are determined as the node information. Different tissues and lesions have different spectral characteristics in the ultrasound reflection signal. Normal tissue has a relatively stable and specific range of spectral characteristics, while the diseased tissue causes the spectrum peak to shift and the bandwidth to change. The specific process of spectrum feature extraction is: a two-dimensional discrete Fourier transform (2D-DFT) is performed on the cardiac ultrasound image, that is, , determine the spectrum peak frequency (i.e., spectrum amplitude The frequency coordinate corresponding to the maximum) and bandwidth , first calculate the spectrum energy function , total energy , starting from low frequency to accumulate energy, when the accumulated energy reaches The frequency range corresponding to the time is the bandwidth , spectral eigenvalue It is used to analyze the relationship between the frequency characteristics of ultrasonic reflection signals and the characteristics of cardiac tissue, and input them into the Bayesian network diagnosis model.

[0024] Subsequently, the Bayesian network diagnosis model construction module is used to construct the Bayesian network diagnosis model. The construction process is as follows: Determine the node type: According to the extracted edge gradient feature value , Regional contrast features , spectral eigenvalue and the patient's age and gender Information, determine the nodes in the Bayesian network, image feature nodes include edge gradient feature nodes , Regional Contrast Feature Node , Spectrum Feature Node , patient information nodes include age nodes , Gender Node , the basic node set is ; Determine the probability relationship between nodes: collect a large amount of clinical cardiovascular disease case data, including the patient's ultrasound image data, the corresponding image feature calculation results, age, gender information and the final confirmed disease type, for the disease node and the base node set , calculate the conditional probability distribution , for example, for diseases and a combination of a set of feature values ​​and patient information values , conditional probability (in Indicates that diseases occur simultaneously in the dataset and eigenvalue combinations The number of Represents the eigenvalue combination The number of occurrences), the specific association between each node and the disease node is determined as follows: the edge gradient feature node is associated with the disease node, the edge gradient feature extraction is performed on the clinical cardiovascular ultrasound image samples, and the edge gradient feature value set is obtained. , for diseases , count the corresponding edge gradient eigenvalue subset ,disease With edge gradient feature node The conditional probability distribution of ; Regional contrast feature nodes are associated with disease nodes to calculate regional contrast feature values ​​of clinical ultrasound image samples , and obtain the regional contrast feature value set , for diseases , determine the corresponding regional contrast feature value subset ,disease With the regional contrast feature node The conditional probability distribution of ; Regional contrast feature nodes are associated with disease nodes to calculate regional contrast feature values ​​of clinical ultrasound image samples , and obtain the regional contrast feature value set , for diseases , determine the corresponding regional contrast feature value subset ,disease With the regional contrast feature node The conditional probability distribution of ; Spectral feature nodes are associated with disease nodes, and spectral feature values ​​are obtained from spectral analysis of clinical ultrasound image samples , for diseases , determine the corresponding subset of spectral eigenvalues ,disease With the Spectrum Feature Node The conditional probability distribution of ; The age node is associated with the disease node, collecting the patient age information and disease diagnosis results in the clinical case data, and dividing the age into different intervals , statistics of each disease in each age range The number of cases And the total number of samples in each age range ,disease With age node The conditional probability distribution of ; Gender nodes are associated with disease nodes, and the number of male and female patients with each disease in clinical case data is counted The number of cases and , and the total sample size of male and female patients and ,disease With gender node The probability of occurrence of the conditional probability distribution ; Construct a Bayesian network structure: Construct a Bayesian network structure based on the determined probabilistic relationship between nodes. Each node in the network represents a random variable, and the directed edges between nodes represent the dependency relationship between variables; Introduce uncertainty quantification indicators: Introduce confidence intervals and entropy values ​​in the Bayesian network diagnostic model. For confidence intervals, calculate the sample mean for the probability of disease occurrence and the sample standard deviation ( It is The estimated probability of disease occurrence for samples is is the sample size), at a confidence level of Next, we can get the quantile by looking up the standard normal distribution table. , the confidence interval is , for entropy values, according to the probability distribution of disease occurrence ( For disease The probability of occurrence), entropy value .

[0025] Next, the probability reasoning calculation module uses the feature data (edge ​​gradient feature value) obtained by the image feature extraction module , Regional contrast features , spectral eigenvalue ) and patient information (age, sex) are input into the Bayesian network diagnosis model, and the Bayesian inference formula is used. (in is the disease node, is the set of evidence nodes, For the disease Evidence under the conditions of occurrence The probability of occurrence, For disease The prior probability of For the evidence Lower Disease After each new data input, the posterior probability of the Bayesian network is updated according to the structure and conditional probability distribution of the Bayesian network. and Parameters, recalculate the posterior probability , and update the confidence interval and entropy value at the same time, for example, the new evidence node When adding, calculate ,renew for , and then recalculate , for confidence interval updates, recalculate based on new sample data and , and then get a new confidence interval; the entropy value is updated by the new posterior probability Form a new probability distribution , recalculate .

[0026] Finally, the diagnosis result output module presents the probability of occurrence of various diseases and the corresponding uncertainty quantification information obtained by the probability reasoning calculation module to the doctor in an intuitive and clear manner, and intelligently generates detailed diagnostic suggestions based on the disease probability and uncertainty quantification information. For diseases with high probability and low uncertainty, doctors are advised to conduct further targeted examinations or formulate treatment plans; for situations with low probability but high uncertainty, doctors are prompted to conduct re-examinations or make comprehensive judgments in combination with other diagnostic methods; for complex situations with similar probabilities of multiple diseases and large uncertainties, multi-dimensional analysis ideas and recommendations for further examination directions are provided to assist doctors in making scientific and reasonable final diagnostic decisions.

[0027] In summary, this embodiment elaborates on the application process of the present invention in the diagnosis of cardiovascular diseases. Through the links of image acquisition, feature extraction, Bayesian network model construction and analysis, and output of diagnostic results, the effectiveness and accuracy of the system are fully demonstrated. The system can comprehensively consider a variety of image features and patient information, accurately calculate the probability of disease occurrence, and provide doctors with a more comprehensive diagnostic basis through uncertainty quantification indicators, effectively assisting doctors to make scientific and reasonable diagnostic decisions, and improving the diagnostic level and medical quality of cardiovascular diseases.

[0028] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A medical ultrasonic image analysis system, characterized in that: The system consists of: ultrasound image acquisition module, image feature extraction module, Bayesian network diagnosis model construction module, probability reasoning calculation module and diagnosis result output module; The ultrasonic image acquisition module is connected to the medical ultrasonic imaging device and is used to acquire medical ultrasonic images and pre-process the images to optimize the influence of interference factors on diagnosis; The image feature extraction module extracts multiple features from the collected ultrasound image and uses the extracted features as input information of the Bayesian network diagnosis model. The features include edge gradient features, regional contrast features, and spectrum features, wherein: The edge gradient feature extraction process is as follows: Medium pixel Gray value at , use the Sobel operator to calculate the horizontal gradient and vertical gradient , that is, the horizontal gradient operator is , the vertical gradient operator is ,but , edge gradient amplitude , for the entire image, the total number of image pixels is , then the edge gradient eigenvalue , where M and N are the number of rows and columns of the image, and this value is used to describe the overall degree of change of the tissue boundary in the image and input the information into the Bayesian network diagnosis model; The extraction process of the regional contrast feature is as follows: the image is divided into non-overlapping sub-regions ,in , , set sub-area The average gray value is The average gray value of the entire image is , then the sub-region Contrast value with the entire image , regional contrast feature ,in For sub-region The weight of , which is used to reflect the grayscale differences between different regions and input into the Bayesian network diagnosis model; The process of extracting the spectrum features is as follows: performing a two-dimensional discrete Fourier transform 2D-DFT on the ultrasound image, that is, ,in and are the number of rows and columns of the image, respectively. , , the spectral characteristics include the peak frequency , that is, the spectrum amplitude The frequency coordinate corresponding to the maximum, and the bandwidth , the corresponding spectrum energy function is , calculate the total energy , starting from low frequency to accumulate energy, when the accumulated energy reaches The frequency range corresponding to the time is the bandwidth The spectrum feature is used to analyze the relationship between the frequency characteristics of the ultrasonic reflection signal and the tissue characteristics and is used as the model input. The spectrum feature value is ; The Bayesian network diagnostic model construction module is used to construct a Bayesian network diagnostic model, determine the probability relationship between the nodes of the network, set the extracted image features and patient information as network nodes, and determine the conditional probability distribution between the nodes according to the clinical data to obtain the disease nodes, thereby constructing a complete Bayesian network structure. At the same time, uncertainty quantification indicators, namely confidence intervals and entropy values, are introduced into the model to quantify the degree of uncertainty of the probability results. The specific construction process of the Bayesian network diagnostic model is as follows: Determine the node type: According to the edge gradient feature value obtained by the image feature extraction module , Regional contrast features The spectral characteristic value is , and the patient's age and gender Information is used as image feature nodes and patient information nodes respectively, and the basic node set in the Bayesian network is obtained as follows: , where the image feature nodes include edge gradient feature nodes , Regional Contrast Feature Node , Spectrum Feature Node , patient information nodes include age nodes , Gender Node ; Determine the probability relationship between nodes: Collect clinical case data, including the patient's ultrasound image data, the corresponding image feature calculation results, the patient's age, gender information, and the final confirmed disease type, and determine the probability distribution between nodes through conditional probability distribution, that is, for disease nodes and the base node set , calculate the conditional probability distribution , that is, considering the disease and a combination of a set of feature values ​​and patient information values , count the co-occurrence of diseases in the dataset The number of times this feature is combined , and the number of times this feature combination appears alone , then the conditional probability , through this conditional probability method, the basic node set All image feature nodes and patient information nodes in are associated with disease nodes; Constructing a Bayesian network structure: Based on the determined probabilistic relationship between nodes, a Bayesian network structure is constructed. Each node in the network represents a random variable, and the directed edges between nodes represent the dependency relationship between variables. Introducing uncertainty quantification indicators: Introducing uncertainty quantification indicators into the Bayesian network diagnosis model, including confidence intervals and entropy values, to quantify the degree of uncertainty of probability results; The probability reasoning calculation module inputs the feature data obtained by the image feature extraction module into the Bayesian network diagnosis model, calculates the probability of disease occurrence through the Bayesian network structure, and updates the value of the uncertainty quantification index in real time during the calculation process. With the input of new data and the progress of probability reasoning, the confidence interval and entropy value indicators are dynamically adjusted; The diagnosis result output module presents the disease occurrence probability obtained by the probability reasoning calculation module to the doctor in the form of a probability numerical list, and provides corresponding diagnosis suggestions to assist the doctor in making the final diagnosis decision.

2. A medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnosis model building module is used to build the Bayesian network diagnosis model. The association determination process is as follows: extract edge gradient features from clinical ultrasound image samples to obtain the edge gradient feature value set of each sample image ,in For the edge gradient feature values ​​of sample images, for each disease type , statistics the distribution of edge gradient eigenvalues ​​in sample images where the disease exists, that is, the disease The corresponding edge gradient eigenvalue subset is , calculate disease With edge gradient feature node The conditional probability distribution of for: ,in, Indicates disease And the edge gradient eigenvalue is The number of samples, Indicates that the edge gradient feature value is The total number of samples.

3. A medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnostic model building module is used to build the Bayesian network diagnostic model. Disease Node The association determination process is as follows: Calculate the regional contrast feature value for clinical ultrasound image samples , and obtain the regional contrast feature value set , for diseases , determine the corresponding regional contrast feature value subset as , calculate disease With the regional contrast feature node The conditional probability distribution of for: ,in, Indicates disease And the regional contrast feature value is The number of samples, Indicates that the regional contrast feature value is The total number of samples.

4. The medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnosis model building module, in the process of building the Bayesian network diagnosis model, for the spectrum feature nodes of the image feature nodes Disease Node The association determination process is as follows: obtain the spectrum feature value from the spectrum analysis of clinical ultrasound image samples , including the peak frequency and bandwidth , forming a set of spectral eigenvalues , for diseases , determine the corresponding subset of spectral eigenvalues , calculate disease With the Spectrum Feature Node The conditional probability distribution of for: , where the count function is used to count the number of samples that combine disease and spectrum feature values.

5. The medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnosis model building module, in the process of building the Bayesian network diagnosis model, for the age node of the patient information node Disease Node The association determination process is as follows: collect patient age information and disease diagnosis results in clinical case data, divide age into different intervals, and count each disease in each age interval. The number of cases And the total number of samples in each age range , calculate disease With age node The conditional probability distribution of for: ,in, Indicates the age range interval.

6. The medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnosis model building module, in the process of building the Bayesian network diagnosis model, for the gender node of the patient information node Disease Node The association determination process is as follows: Count the number of male and female patients with each disease in the clinical case data The number of cases and , and the total sample size of male and female patients and , calculate disease With gender node The conditional probability distribution of for: 。 7. The medical ultrasonic image analysis system according to claim 1, characterized in that: The Bayesian network diagnostic model construction module introduces quantitative indicators of uncertainty confidence interval and entropy value in the process of constructing the Bayesian network diagnostic model, where: For confidence interval: for the probability of disease occurrence , calculate the sample mean and the sample standard deviation , using the unbiased estimation formula in the normal approximation method ,in It is The estimated probability of disease occurrence for samples is is the sample size, at a confidence level of Next, we can get the quantile by looking up the standard normal distribution table. , then the confidence interval is , the confidence interval can intuitively show the range of the estimated probability of disease occurrence; For entropy value: according to the probability distribution of disease occurrence , For disease The probability of occurrence, the calculated entropy value is: ,in, is the total number of disease types. A large entropy value indicates a dispersed probability distribution with high uncertainty. A small entropy value indicates that the probability is concentrated on one disease type with low uncertainty. The entropy value is used to quantify the degree of uncertainty in the probability of disease occurrence, providing doctors with more comprehensive diagnostic reference information and helping them evaluate the credibility of the diagnostic results.

8. The medical ultrasonic image analysis system according to claim 1, characterized in that: The probability reasoning calculation module adopts the Bayesian reasoning formula , dynamically adjust the confidence interval and entropy value indicators, where is the disease node, is the set of evidence nodes, i.e., image feature and patient information nodes, For the disease Evidence under the conditions of occurrence The probability of occurrence, For disease The prior probability of For the evidence Lower Disease The posterior probability of the iterative calculation process is updated according to the structure and conditional probability distribution of the Bayesian network after each new data input. and Parameters, recalculate the posterior probability , and update the confidence interval and entropy value at the same time. That is, when new image feature data and patient information are added, the new conditional probability distribution is calculated according to the new evidence combination, and then the estimated value of the disease probability and its confidence interval and entropy value are updated, and a new evidence node is set. Add, calculate ,renew for Recalculate , for confidence interval updates, recalculate based on new sample data and , and then get a new confidence interval, and the entropy value is updated by the new posterior probability Forming a new probability distribution , recalculate .

9. A medical ultrasonic image analysis method, applicable to a medical ultrasonic image analysis system according to any one of claims 1 to 8, characterized in that: The specific steps of this method are: S1. Start the ultrasound image acquisition module, establish a connection with the ultrasound imaging device, receive and store the acquired ultrasound image data in real time, and record the acquisition time and metadata of the patient information; S2, transmitting the collected ultrasound image to the image feature extraction module, performing edge gradient feature, regional contrast feature, and spectrum feature extraction on the image, storing the processed feature data in the feature database, and establishing an associated index with the patient information; S3. Construct a Bayesian network diagnostic model, determine the node type and number of the Bayesian network, collect clinical case data, calculate the conditional probability distribution between nodes based on the clinical data, and integrate the calculation model of uncertainty quantification indicators into the model so that the model can simultaneously output uncertainty quantification results while calculating the probability of disease occurrence; S4, reading the image feature data and basic information of the current patient from the feature database, inputting the data into the constructed Bayesian network diagnosis model, starting the probability reasoning calculation process, performing iterative calculation, and outputting the disease occurrence probability result and the corresponding uncertainty quantification value; S5. The calculated probability of occurrence of various diseases and their uncertainty quantitative information are transmitted to the diagnosis result output module to generate a visual diagnosis result report.

Images