Image diagnosis auxiliary decision-making system based on medical knowledge graph

Abstract

The invention discloses an image diagnosis auxiliary decision-making system based on a medical knowledge graph, which relates to the technical field of medical auxiliary diagnosis and comprises an image data set establishment module, an image data set analysis module, a 24-dimensional boundary box acquisition module, a fuzzy processing module and a fracture type judgment module. 24-dimensional vector forms of different fracture types are analyzed, a 24-dimensional boundary box corresponding to each fracture type is obtained, a clear boundary interval is provided, fuzzy processing is carried out on the boundary interval of the 24-dimensional boundary box, similarity and variability possibly existing between different fracture types are considered, and therefore the fracture types of different fracture types can be obtained. According to the method, the flexibility and fault tolerance of the to-be-detected image during fracture type judgment are improved, a complex or indefinite diagnosis image can be reasonably judged, a wider reference range is provided for judgment of the fracture type, the misjudgment risk caused by the fact that the feature value is close to the boundary is reduced, and the diagnosis accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the field of medical auxiliary diagnosis technology, and specifically is an image diagnosis auxiliary decision-making system based on medical knowledge graph. Background Art

[0002] In recent years, with the continuous advancement of medical imaging technology, medical knowledge graphs, as an emerging medical information technology, have provided more systematic and knowledge-based support for imaging diagnosis. Medical knowledge graphs can structure a large amount of medical data, medical knowledge, and clinical experience, allowing machine learning and deep learning algorithms to better mine valuable information from them, thereby providing more accurate decisions for imaging diagnosis systems.

[0003] Patent publication number CN110911009A discloses a clinical diagnosis decision support system and a method for accumulating medical knowledge graphs. The clinical diagnosis decision support system includes: a vital sign acquisition module, a medical image acquisition module, a central control module, a diagnosis and analysis module, a treatment plan recommendation module, a medical knowledge retrieval module, a graph creation module, a data storage module, and a display module. The present invention uses the historical data of various diseases to train the model through the diagnosis and analysis module, so that only one model can be used to pre-diagnose multiple diseases. It is very suitable for clinical diagnosis management and maintenance, and the diagnosis and analysis results are accurate. At the same time, a medical knowledge graph is created through the graph creation module, and medical data is managed through the medical knowledge graph. Therefore, when using medical data, medical data can be extracted through the medical knowledge graph, which can improve the convenience of using medical data to a certain extent. However, at present, most applications of medical knowledge graphs are mainly concentrated on the processing and analysis of text information, and the in-depth analysis and diagnostic support for medical images are relatively weak. In some special cases, especially in the classification of fracture types, they only rely on the doctor's experience and visual judgment and simple feature matching or rough pattern recognition, which leads to the shortcomings of diagnostic results being easily affected by human factors and low diagnostic efficiency. At the same time, due to the inability to deeply explore the texture features and subtle differences in the image, it is impossible to accurately judge different types of fractures and unable to assist doctors in making decisions in real time. Based on this, an image diagnosis decision support system based on medical knowledge graphs is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an image diagnosis decision-making support system based on a medical knowledge graph, which solves the technical problem that it is impossible to deeply explore the texture features and slight differences in the image, resulting in the inability to accurately judge different types of fractures and the inability to assist doctors in making decisions in real time.

[0005] The imaging diagnosis decision-making support system based on medical knowledge graph includes: An image data set building module, which builds an image data set through multiple distal radius fracture images; The image data set analysis module extracts and analyzes the texture information corresponding to each pixel point in each preprocessed distal fracture image to obtain the 24-dimensional vector form of each distal radius fracture image; The 24-dimensional bounding box acquisition module analyzes the values ​​of each dimension in the 24-dimensional vector form corresponding to each distal radius fracture image under different fracture types, and obtains the 24-dimensional bounding boxes of different fracture types and the boundary intervals of each dimension of the 24-dimensional bounding boxes of different fracture types; A fuzzy processing module performs fuzzy processing on the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types to obtain the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types; The fracture type judgment module compares and analyzes the numerical values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected with the boundary intervals and fuzzy intervals of each dimension of the 24-dimensional bounding box of different fracture types to determine the fracture type corresponding to the diagnostic image to be detected.

[0006] As a further solution of the present invention, the specific method of obtaining the 24-dimensional vector form of each distal radius fracture image is: Firstly, the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions are obtained by a feature value extraction unit according to the texture information of each distal radius fracture image at different scales and directions. Then, the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions are analyzed by a feature value analysis unit. According to the analysis results, the calculated values ​​corresponding to each distal radius fracture image at different scales and directions are obtained. Then, the mean and variance of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions are normalized by a normalization processing unit to obtain the calibration values ​​of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions. Finally, the calculated values ​​of each distal radius fracture image are vectorized by a 24-dimensional vector morphology acquisition unit to obtain the 24-dimensional vector morphology of each distal radius fracture image. Here, the number of directions is selected as 4, namely 0°, 45°, 90°, and 135°, and the different scales are 1, 2, and 3, respectively.

[0007] The specific method for obtaining the calculated values ​​corresponding to each distal radius fracture image at different scales and directions is as follows: A fixed scale and direction is selected from different scales and directions as the target scale direction, and the texture feature values ​​corresponding to each pixel point in each distal radius fracture image in the target scale direction are obtained, and the mean and variance of the texture feature values ​​in each distal radius fracture image are used as the corresponding calculation values ​​of each distal radius fracture image in the target scale direction; The same analysis method was used to obtain the calculated values ​​Tnij (Anij, Bnij) corresponding to each distal radius fracture image at different scales and directions, where Anij is the mean value of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, Bnij refers to the variance of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, n refers to different distal radius fracture images, i refers to different direction numbers, i=1, 2, 3 and 4, and j refers to different scales, j=1, 2 and 3.

[0008] The specific method for obtaining the calibration values ​​of each distal radius fracture image corresponding to the calculated values ​​at different scales and directions is as follows: By formula: XAnij=(Anij-Anij min ) / (Anij max -Anij min );XBnij=(Bnij-Bnij min ) / (Bnij max -Bnij min ), calculate the calibration value XTNij (XAnij, XBnij) of the calculated value corresponding to each distal radius fracture image at different scales and directions, where Anij max and Anij min are the maximum and minimum values ​​in Anij, Bnij max and Bnij min are the maximum and minimum values ​​in Bnij respectively.

[0009] The specific method of obtaining the 24-dimensional vector form of each distal radius fracture image is as follows: According to the calibration values ​​XTNij (XAnij, XBnij) of the calculated values ​​corresponding to each distal radius fracture image in different scales and directions, the calculated values ​​of each distal radius fracture image are vectorized to obtain the 24-dimensional vector morphology Ln (XAn11, XBn11, XAn12, XBn12, XAn12, XBn12, …, XAn43, XBn43) of each distal radius fracture image. Each vector morphology contains 24 dimensional values.

[0010] As a further solution of the present invention, a specific method for obtaining 24-dimensional bounding boxes of different fracture types and boundary intervals of each dimension of the 24-dimensional bounding boxes of different fracture types is as follows: The fracture types include A, B and C fracture types. First, the vector morphology of multiple distal radius fracture images corresponding to the A fracture type is obtained as Le, where e refers to different distal radius fracture images of the A fracture type. The average of the maximum and minimum values ​​of each dimension in the vector morphology Le of the A fracture type is obtained and marked as the benchmark value of each dimension. The benchmark value of each dimension is added to the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value as the upper limit value corresponding to each dimension of the A fracture type. Then, the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value is subtracted from the benchmark value of each dimension to obtain the value of the A fracture type. The lower boundary values ​​corresponding to each dimension of the fracture type are respectively determined, and the boundary intervals QAr[WBr,WAr] ​​corresponding to each dimension of the A fracture type are established through the upper boundary values ​​WAr and the lower boundary values ​​WBr corresponding to each dimension of the A fracture type. According to the boundary intervals Qr corresponding to each dimension of the A fracture type, the 24-dimensional bounding box HA corresponding to the A fracture type is obtained, where r refers to different dimensions, r=1, 2, ..., 24. The same analysis method is used to analyze the vector morphology of multiple distal radius fracture images corresponding to B and C fracture types, and the 24-dimensional bounding boxes HB and HC corresponding to B and C fracture types are obtained, respectively.

[0011] As a further solution of the present invention, the specific method of obtaining the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types is: The standard deviation Zr corresponding to each dimension value in each 24-dimensional vector morphology of type A fracture is obtained, and the ratio between the standard deviation Zr of each dimension and the benchmark value is used as the buffer coefficient Cr of each dimension. The product of the buffer coefficient Cr of each dimension and the standard deviation Zr is used as the buffer value Fr of the boundary interval of each dimension. The sum of the upper boundary value KAr corresponding to the boundary interval of each dimension of type A fracture and the buffer value Fr is used as the buffer upper limit value VAr corresponding to the boundary interval of each dimension of type A fracture. The absolute value of the difference between the lower boundary value KBr corresponding to the boundary interval of each dimension of type A fracture and the buffer value Fr is used as the buffer lower limit value VBr corresponding to the boundary interval of each dimension of type A fracture, and then the fuzzy interval MHr[VBr,VAr] corresponding to the boundary interval of each dimension of type A fracture is obtained. ], the same analysis method is used to perform fuzzy processing on the boundary intervals of each dimension of the 24-dimensional bounding box of type B and type C fractures, and the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of type B and type C fractures are obtained; when judging the values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected, first determine whether its dimension value is located in the boundary interval of each dimension of the 24-dimensional bounding box of different fracture types. If it is, it is determined that the corresponding dimension value belongs to the boundary interval of the corresponding fracture type, and the number of boundary interval matches of the corresponding fracture type is increased by 1. If it is not located, it is determined whether it is located in the fuzzy interval of each dimension of the 24-dimensional bounding box of each fracture type. If it is, it is determined that the corresponding dimension value belongs to the fuzzy interval of the corresponding fracture type, and the number of fuzzy interval matches of the corresponding fracture type is increased by 1. Otherwise, no processing is performed.

[0012] As a further solution of the present invention: the specific method of determining the fracture type corresponding to the diagnostic image to be detected is: The sum of the products of the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types and the preset coefficients β1 and β2 are obtained, and the sum of the products of the values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected and the fuzzy interval are obtained, and the sum of the products of the preset coefficients β1 and β2 are obtained, and the sum of the products is used as the selection coefficients corresponding to the 24-dimensional bounding box of different fracture types of the diagnostic image to be detected, and the fracture type corresponding to the maximum selection coefficient is used as the fracture type of the diagnostic image to be detected, where 1=β1+β2, satisfying 1>β1>0.5>β2>0.

[0013] When the selection coefficients of multiple fracture types are the same and the largest, the number of values ​​of each dimension in the 24-dimensional vector form of the diagnostic image to be detected that are respectively located in the boundary interval of the 24-dimensional boundary box with the same selection coefficient is obtained, and the fracture type with the largest number is taken as the fracture type corresponding to the diagnostic image to be detected. If the number is still the same, the fracture types corresponding to the same number are output at the same time; When the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is 0, the manual review procedure is triggered.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention obtains a 24-dimensional bounding box corresponding to each fracture type by analyzing the 24-dimensional vector morphology of different fracture types, provides a clear boundary interval, provides standardized and structured data support for fracture type classification, improves the reliability of classification judgment, and further improves the diagnostic accuracy of the system by setting a clear boundary interval, ensuring the efficiency and accuracy of the diagnostic process; (2) The present invention, by fuzzy processing the boundary interval of the 24-dimensional bounding box, takes into account the possible similarities and variability between different fracture types, improves the flexibility and fault tolerance in judging the fracture type of the image to be detected, can make reasonable judgments on complex or unclear diagnostic images, provides a wider reference range for the judgment of fracture types, reduces the risk of misjudgment caused by characteristic values ​​close to the boundaries, and improves the accuracy of diagnosis; (3) The present invention can automatically and accurately determine the fracture type corresponding to the image to be detected by analyzing the 24-dimensional vector morphology of the image to be detected in real time and comparing it with the preset 24-dimensional bounding box and fuzzy interval, thereby improving the intelligence and automation level of fracture type classification and improving the diagnosis speed and accuracy; (4) The present invention, when the selection coefficients of multiple fracture types are the same, determines the fracture type by further comparing the number of dimensions within the boundary interval, which can effectively deal with diagnostic difficulties in complex situations. This multi-level judgment logic enables the system to make more reasonable decisions when faced with complex situations. At the same time, when the feature value of the image to be detected cannot match the boundary interval or fuzzy interval of any fracture type, it can trigger a manual review procedure to ensure the ultimate accuracy and reliability of the diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the system framework structure of the present invention; Figure 2 It is a flow chart of judging the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are respectively located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types in the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1-Figure 2 ,This application provides an image diagnosis decision-making support system based on medical knowledge graph, including; An image data set building module is used to acquire multiple distal radius fracture images and build an image data set; It should be noted that the distal radius fracture images can be obtained from the hospital database, and some distal radius fracture images and related case information accumulated in previous studies are extracted. At the same time, when obtaining the distal radius fracture images, the basic information of the patient, that is, the patient's name, ID number and other information are desensitized in advance to protect the patient's privacy. The above are all existing and mature technologies, so they will not be elaborated here. It should be noted that each fracture image was annotated with fracture type by an experienced orthopedic surgeon; According to the internationally accepted AO classification standard, fracture types are divided into three types: A, B and C: Category A: Lateral fracture, i.e. the bone breaks outside the joint.

[0018] Category B: Simple, minor or small medial-articular fracture, i.e. a small part of the bone is broken within the joint.

[0019] Category C: Complex medial articular fractures, such as multiple broken fragments of the bone within the joint; The internationally accepted AO classification standard is an existing internationally accepted classification standard and is the current default classification standard. This classification is used by default in this embodiment, so no further details will be given here. This module can quickly build a high-quality and complete imaging data set by extracting distal radius fracture images from hospital databases or previous studies, protect patient privacy through desensitization processing, and ensure compliance with data protection regulations. This module provides accurate and comprehensive input for subsequent data analysis, reduces the error rate in the data collection process, and lays a solid foundation for the accuracy and stability of the system.

[0020] The image data set analysis module is used to extract and analyze the texture information corresponding to each pixel point in each distal bone fracture image after preprocessing each distal bone fracture image in the image data set, and obtain the 24-dimensional vector form of each distal radius fracture image according to the analysis results. The specific method is as follows: Before analyzing the image data set, each distal radius fracture image in the image data set needs to be preprocessed to improve the image quality. The preprocessing includes image enhancement, noise removal and other processing methods, which are all existing and mature technologies and are therefore not described in detail here.

[0021] The feature value extraction unit extracts the texture information of each distal radius fracture image at different scales and directions by setting different Gabor filters, thereby obtaining the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions; It should be noted that: here, the number of directions is selected as 4, such as 0°, 45°, 90°, and 135°, and the number of scales is selected as 3, and the different scales are 1, 2, and 3 respectively; A feature value analysis unit is used to analyze the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions, and obtain the calculated values ​​corresponding to each distal radius fracture image at different scales and directions according to the analysis results; It should be noted that the texture feature value of each pixel is obtained by convolving the Gabor filter with the corresponding area in the image. The texture feature value of each pixel is calculated by the filter response. Specifically, in order to extract texture features, the Gabor filter will slide across the entire image with a certain size (usually a small window). This process is called convolution. During the convolution process, the filter will cover 1 pixel of the image each time, that is, the window size, and calculate the response of the pixel area. Finally, the calculation result is stored in the corresponding pixel position. The way in which the Gabor filter obtains texture feature values ​​is an existing and mature technology, so no further explanation is given here. Select a fixed scale and direction from different scales and directions as the target scale and direction; Obtain the texture feature values ​​corresponding to each pixel point in each distal radius fracture image in the target scale direction, and use the mean and variance of the texture feature values ​​in each distal radius fracture image as the corresponding calculated values ​​of each distal radius fracture image in the target scale direction; It should be noted that the calculation methods for obtaining the mean and variance are existing and mature calculation methods, so no further explanation is given here; The mean reflects the overall intensity or brightness of the texture, and the variance reflects the complexity or roughness of the texture; By using the same analysis method, the calculated values ​​Tnij (Anij, Bnij) corresponding to each distal radius fracture image at different scales and directions can be obtained, where Anij is the mean value of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, Bnij refers to the variance of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, n refers to different distal radius fracture images, and n is a positive integer, i refers to different direction numbers, i=1, 2, 3 and 4, j refers to different scales, j=1, 2 and 3; The normalization processing unit performs normalization processing on the mean Anij and variance Bnij of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions, so as to obtain the calibration values ​​of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions; The specific method is: through the formula: XAnij= (Anij-Anij min ) / (Anij max -Anij min );XBnij=(Bnij-Bnij min ) / (Bnij max -Bnij min ), calculate and obtain the calibration values ​​XTnij (XAnij, XBnij) of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions; Among them Anij max and Anij min are the maximum and minimum values ​​in Anij, Bnij max and Bnij min are the maximum and minimum values ​​in Bnij respectively; Normalize the values ​​and scale the calculated values ​​to the range of [0,1] to facilitate the subsequent analysis of the calculated values; A 24-dimensional vector morphology acquisition unit performs vectorization processing on the calculated values ​​of each distal radius fracture image to obtain the 24-dimensional vector morphology of each distal radius fracture image; According to the calibration values ​​XTNij (XAnij, XBnij) of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions, the calculated values ​​of each distal radius fracture image are vectorized to obtain the 24-dimensional vector form Ln (XAn11, XBn11, XAn12, XBn12, XAn12, XBn12, …, XAn43, XBn43) of each distal radius fracture image. Each vector form contains 24 dimensional values, that is, 24=4×3×2, so the vector form of the distal radius fracture image is a 24-dimensional vector form; By preprocessing, extracting and analyzing the texture features of distal radius fracture images, the key information in the images can be effectively extracted and converted into a quantifiable 24-dimensional vector form. This not only improves the data processing efficiency, but also provides accurate feature input for subsequent classification analysis, which can better capture the subtle differences between fracture types and significantly improve the accuracy of imaging diagnosis.

[0022] The 24-dimensional bounding box acquisition module analyzes the values ​​of each dimension in the 24-dimensional vector form corresponding to each distal radius fracture image under different fracture types, and obtains the 24-dimensional bounding boxes corresponding to different fracture types according to the analysis results. The specific method is as follows: The vector forms of multiple distal radius fracture images corresponding to the type A fracture are obtained, which are marked as Le, wherein e refers to different distal radius fracture images of the type A fracture; Obtain the mean of the maximum and minimum values ​​of each dimension in each 24-dimensional vector morphology of Class A fracture type and mark it as the reference value of each dimension, and add the reference value of each dimension to the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value as the upper limit value corresponding to each dimension of Class A fracture type, and then subtract the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value from the reference value of each dimension as the lower limit value corresponding to each dimension of Class A fracture type; For example, the maximum and minimum values ​​of each dimension in each 24-dimensional vector form of type A fracture are marked as KAr and KBr, respectively, where r refers to different dimensions, r=1, 2, ..., 24, and the upper limit value WAr and the lower limit value WBr corresponding to each dimension of type A fracture are calculated by WAr=(KAr+KBr) / 2+|KAr-KBr| and WBr=(KAr+KBr) / 2-|KAr-KBr|; Through the upper bound value WAr and lower bound value WBr corresponding to each dimension of Class A fracture type, the boundary interval QAr[WBr,WAr] ​​corresponding to each dimension of Class A fracture type is established. According to the boundary interval Qr corresponding to each dimension of Class A fracture type, the 24-dimensional bounding box HA corresponding to Class A fracture type is obtained. This bounding box contains all feature value ranges of Class A fracture images in 24-dimensional space. The same analysis method was used to analyze the vector morphology of multiple distal radius fracture images corresponding to the B and C fracture types, and the 24-dimensional bounding boxes HB and HC corresponding to the B and C fracture types were obtained respectively; This module analyzes the 24-dimensional vector morphology of different fracture types and obtains the 24-dimensional bounding box corresponding to each fracture type, providing a clear boundary interval, and providing standardized and structured data support for the system's fracture type classification, effectively avoiding ambiguity and errors, and improving the reliability of classification judgments. By setting clear boundary intervals, the system's diagnostic accuracy is further improved, ensuring the efficiency and accuracy of the diagnostic process.

[0023] The fuzzy processing module performs fuzzy processing on the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types to obtain the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types. The specific method is as follows: Obtain the standard deviation Zr corresponding to each dimension value in the vector morphology Le of the type A fracture, where r refers to different dimensions, r=1, 2, ..., 24; The ratio between the standard deviation Zr of each dimension and the reference value is used as the buffer coefficient Cr of each dimension to expand the boundary interval, and the product between the buffer coefficient Cr of each dimension and the standard deviation Zr is used as the buffer value Fr of the boundary interval of each dimension; The sum of the upper boundary value KAr and the buffer value Fr corresponding to each dimension boundary interval of the type A fracture is taken as the buffer upper limit value VAr corresponding to each dimension boundary interval of the type A fracture, and the absolute value of the difference between the lower boundary value KBr corresponding to each dimension boundary interval of the type A fracture and the buffer value Fr is taken as the buffer lower limit value VBr corresponding to each dimension boundary interval of the type A fracture, and then the fuzzy interval MHr[VBr,VAr] corresponding to each dimension boundary interval of the type A fracture is obtained, which provides a basis for fuzzy judgment of fracture type. The same analysis method is used to perform fuzzy processing on the boundary intervals of each dimension of the 24-dimensional bounding box of type B and type C fractures, and the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of type B and type C fractures are obtained; By fuzzifying the boundary interval of the 24-dimensional bounding box, the system is allowed to be more flexible and fault-tolerant when processing image data, taking into account the similarities and variability that may exist between different fracture types. By introducing fuzzy intervals, the system can make reasonable judgments on complex or ambiguous diagnostic images, avoiding the rigid rule restrictions of traditional models, and improving the adaptability and robustness of the system when facing complex cases. At the same time, by expanding the boundary interval, a wider reference range is provided for the judgment of fracture types, reducing the risk of misjudgment caused by eigenvalues ​​close to the boundaries. The existence of fuzzy intervals enables the system to more comprehensively consider the distribution of eigenvalues, thereby improving the accuracy of diagnosis.

[0024] The fracture type judgment module obtains the real-time 24-dimensional vector form of the diagnostic image to be detected, compares and analyzes the values ​​of each dimension in the real-time vector form with the boundary intervals and fuzzy intervals of each dimension of the 24-dimensional bounding box of different fracture types, and judges the fracture type corresponding to the diagnostic image to be detected according to the analysis results. The specific method is as follows: The number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is obtained, and they are marked as AS1, AS2, BS1, BS2, CS1 and CS2 respectively; AS1, BS1 and CS1 refer to the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are respectively located within the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types; AS2, BS2 and CS2 refer to the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are respectively located within the fuzzy intervals of each dimension of the 24-dimensional bounding box of different fracture types; It should be noted that when judging the values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected, first determine whether the value of the dimension is located in the boundary interval of each dimension of the 24-dimensional bounding box of different fracture types. If it is, it is determined that the corresponding dimension value belongs to the boundary interval of the corresponding fracture type, and the number of boundary interval matches of the corresponding fracture type is increased by 1. For the dimension values ​​that are not located in the boundary interval of each dimension of the 24-dimensional bounding box of each fracture type, it is determined whether it is located in the fuzzy interval of each dimension of the 24-dimensional bounding box of each fracture type. If it is, it is determined that the corresponding dimension value belongs to the fuzzy interval of the corresponding fracture type, and the number of fuzzy interval matches of the corresponding fracture type is increased by 1. Otherwise, no processing is performed, and the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is obtained; Obtain the sum of the products of the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types and the preset coefficients β1 and β2, and use them as the selection coefficients corresponding to the 24-dimensional bounding box of different fracture types of the diagnostic image to be detected, and use the fracture type corresponding to the maximum selection coefficient as the fracture type of the diagnostic image to be detected. The specific values ​​of the preset coefficients β1 and β2 are formulated by relevant personnel according to actual needs. Here, 1=β1+β2, satisfying 1>β1>0.5>β2>0; The selection coefficients XZA, XZB and XZC corresponding to the diagnostic image to be detected in the 24-dimensional bounding box of different fracture types are calculated by the formulas: XZA=AS1×β1+AS2×β2, XZB=BS1×β1+BS2×β2 and XZC=CS1×β1+CS2×β2; By analyzing the 24-dimensional vector morphology of the image to be detected in real time and comparing it with the preset 24-dimensional bounding box and fuzzy interval, it can automatically and accurately determine the fracture type corresponding to the image to be detected. It integrates a comprehensive knowledge graph and multi-dimensional analysis, greatly improving the intelligence and automation level of fracture type classification, reducing manual intervention, and improving the speed and accuracy of diagnosis. The module can also ensure the most appropriate diagnosis in multiple selections by further comparing the number of dimension values ​​when the selection coefficients are the same. It can greatly improve the accuracy and efficiency of image analysis, reduce errors in manual operations, and improve the fault tolerance of the system through fuzzy processing. In the classification of fracture types, the system can accurately classify according to the 24-dimensional vector morphology and bounding box.

[0025] Embodiment 2: As the embodiment 2 of the present invention, when the present application is specifically implemented, compared with embodiment 1, the difference between the technical solution of this embodiment and embodiment 1 is that in this embodiment, the selection coefficient of more than one fracture type is the largest and the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are respectively located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is 0. When the selection coefficient of more than one fracture type is the largest, the number of values ​​of each dimension in the 24-dimensional vector form of the diagnostic image to be detected that are respectively located in the boundary interval of the 24-dimensional bounding box with the same selection coefficient is obtained, and the fracture type with the largest number is taken as the fracture type corresponding to the diagnostic image to be detected. If the number is still the same, the fracture types corresponding to the 24-dimensional bounding boxes with the same number are output simultaneously; When the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is 0, the manual review procedure is triggered.

[0026] When the selection coefficients of multiple fracture types are the same, the fracture type is determined by further comparing the number of dimensions within the boundary interval, which can effectively deal with diagnostic difficulties in complex situations. This multi-level judgment logic enables the system to make more reasonable decisions when faced with complex situations, improving the robustness and reliability of the system. When the feature value of the image to be detected cannot match the boundary interval or fuzzy interval of any fracture type, it can trigger a manual review procedure to ensure the final accuracy of the diagnosis. By introducing manual intervention when necessary, the reliability of the diagnostic results is ensured.

[0027] When multiple selection coefficients are the same, the quantity priority principle is adopted to further improve diagnostic accuracy. In addition, the system is automated and real-time, which greatly reduces waiting time and the need for manual intervention, providing reliable decision support for clinicians.

[0028] Embodiment 3: As the embodiment 3 of the present invention, when the present application is implemented specifically, compared with the embodiments 1 and 2, the technical solution of this embodiment is to combine the solutions of the above-mentioned embodiments 1 and 2 for implementation.

[0029] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The image diagnosis decision-making support system based on medical knowledge graph is characterized by: include: An image data set building module, which builds an image data set through multiple distal radius fracture images; The image data set analysis module extracts and analyzes the texture information corresponding to each pixel point in each preprocessed distal radius fracture image to obtain the 24-dimensional vector form of each distal radius fracture image; The 24-dimensional bounding box acquisition module analyzes the values ​​of each dimension in the 24-dimensional vector morphology of each distal radius fracture image under different fracture types, and obtains the 24-dimensional bounding boxes of different fracture types and the boundary intervals of each dimension of the 24-dimensional bounding boxes of different fracture types; A fuzzy processing module performs fuzzy processing on the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types to obtain the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types; The fracture type judgment module compares and analyzes the numerical values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected with the boundary intervals and fuzzy intervals of each dimension of the 24-dimensional bounding box of different fracture types to determine the fracture type corresponding to the diagnostic image to be detected.

2. The image diagnosis decision support system based on medical knowledge graph according to claim 1 is characterized in that: The specific method of obtaining the 24-dimensional vector form of each distal radius fracture image is as follows: Firstly, the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions are obtained by a feature value extraction unit according to the texture information of each distal radius fracture image at different scales and directions. Then, the texture feature values ​​corresponding to each pixel point in each distal radius fracture image at different scales and directions are analyzed by a feature value analysis unit. According to the analysis results, the calculated values ​​corresponding to each distal radius fracture image at different scales and directions are obtained. Then, the mean and variance of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions are normalized by a normalization processing unit to obtain the calibration values ​​of the calculated values ​​corresponding to each distal radius fracture image at different scales and directions. Finally, the calculated values ​​of each distal radius fracture image are vectorized by a 24-dimensional vector morphology acquisition unit to obtain the 24-dimensional vector morphology of each distal radius fracture image. Here, the number of directions is selected as 4, namely 0°, 45°, 90°, and 135°, and the different scales are 1, 2, and 3, respectively.

3. The image diagnosis decision support system based on medical knowledge graph according to claim 2 is characterized in that: The specific method for obtaining the calculated values ​​corresponding to each distal radius fracture image at different scales and directions is as follows: A fixed scale and direction is selected from different scales and directions as the target scale direction, and the texture feature values ​​corresponding to each pixel point in each distal radius fracture image in the target scale direction are obtained, and the mean and variance of the texture feature values ​​in each distal radius fracture image are used as the corresponding calculation values ​​of each distal radius fracture image in the target scale direction; The same analysis method was used to obtain the calculated values ​​Tnij (Anij, Bnij) corresponding to each distal radius fracture image at different scales and directions, where Anij is the mean value of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, Bnij refers to the variance of the texture feature values ​​corresponding to each distal radius fracture image at different scales and directions, n refers to different distal radius fracture images, i refers to different direction numbers, i=1, 2, 3 and 4, and j refers to different scales, j=1, 2 and 3.

4. The image diagnosis decision support system based on medical knowledge graph according to claim 3 is characterized in that: The specific method for obtaining the calibration values ​​of each distal radius fracture image corresponding to the calculated values ​​at different scales and directions is as follows: By formula: XAnij=(Anij-Anij min ) / (Anij max -Anij min );XBnij=(Bnij-Bnij min ) / (Bnij max -Bnij min ), calculate the calibration value XTNij (XAnij, XBnij) of the calculated value corresponding to each distal radius fracture image at different scales and directions, where Anij max and Anij min are the maximum and minimum values ​​in Anij, Bnij max and Bnij min are the maximum and minimum values ​​in Bnij respectively.

5. The image diagnosis decision support system based on medical knowledge graph according to claim 4 is characterized in that: The specific method of obtaining the 24-dimensional vector form of each distal radius fracture image is as follows: According to the calibration values ​​XTNij (XAnij, XBnij) of the calculated values ​​corresponding to each distal radius fracture image in different scales and directions, the calculated values ​​of each distal radius fracture image are vectorized to obtain the 24-dimensional vector morphology Ln (XAn11, XBn11, XAn12, XBn12, XAn12, XBn12, …, XAn43, XBn43) of each distal radius fracture image. Each vector morphology contains 24 dimensional values.

6. The image diagnosis decision support system based on medical knowledge graph according to claim 5 is characterized in that: The specific method of obtaining the 24-dimensional bounding boxes of different fracture types and the boundary intervals of each dimension of the 24-dimensional bounding boxes of different fracture types is: The fracture types include A, B and C fracture types. First, the vector morphology of multiple distal radius fracture images corresponding to the A fracture type is obtained as Le, where e refers to different distal radius fracture images of the A fracture type. The average of the maximum and minimum values ​​of each dimension in the vector morphology Le of the A fracture type is obtained and marked as the benchmark value of each dimension. The benchmark value of each dimension is added to the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value as the upper limit value corresponding to each dimension of the A fracture type. Then, the absolute value of the difference between the maximum and minimum values ​​in the corresponding dimension value is subtracted from the benchmark value of each dimension to obtain the value. The lower boundary values ​​corresponding to each dimension of Class A fracture type are respectively established through the upper boundary values ​​WAr and the lower boundary values ​​WBr corresponding to each dimension of Class A fracture type, and the boundary intervals QAr[WBr,WAr] ​​corresponding to each dimension of Class A fracture type are established. According to the boundary intervals Qr corresponding to each dimension of Class A fracture type, the 24-dimensional bounding box HA corresponding to Class A fracture type is obtained, where r refers to different dimensions, r=1, 2, ..., 24. The same analysis method is used to analyze the vector morphology of multiple distal radius fracture images corresponding to Class B and Class C fracture types, and the 24-dimensional bounding boxes corresponding to Class B and Class C fracture types are obtained.

7. The image diagnosis decision support system based on medical knowledge graph according to claim 6 is characterized in that: The specific method of obtaining the fuzzy intervals corresponding to the boundary intervals of each dimension of the 24-dimensional bounding box of different fracture types is: The standard deviation Zr corresponding to the values ​​of each dimension in the 24-dimensional vector morphology of type A fracture is obtained, and the ratio of the standard deviation Zr of each dimension to the benchmark value is used as the buffer coefficient Cr of each dimension. The product of the buffer coefficient Cr and the standard deviation Zr of each dimension is used as the buffer value Fr of the boundary interval of each dimension. The sum of the upper boundary value KAr corresponding to the boundary interval of each dimension of type A fracture and the buffer value Fr is used as the buffer upper limit value VAr corresponding to the boundary interval of each dimension of type A fracture. The absolute value of the difference between the lower boundary value KBr corresponding to the boundary interval of each dimension of type A fracture and the buffer value Fr is used as the buffer lower limit value VBr corresponding to the boundary interval of each dimension of type A fracture. Then, the fuzzy interval MHr[VBr,VAr] corresponding to the boundary interval of each dimension of type A fracture is obtained. The same analysis method is used to fuzzy process the boundary interval of each dimension of the 24-dimensional bounding box of type B and type C fracture, and the fuzzy interval corresponding to the boundary interval of each dimension of the 24-dimensional bounding box of type B and type C fracture is obtained.

8. The image diagnosis decision support system based on medical knowledge graph according to claim 7 is characterized in that: The specific method for determining the fracture type corresponding to the diagnostic image to be detected is: The number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is obtained, and the sum of the products between them and the preset coefficients β1 and β2 is used as the selection coefficient corresponding to the 24-dimensional bounding box of the diagnostic image to be detected in different fracture types, and the fracture type corresponding to the maximum selection coefficient is used as the fracture type of the diagnostic image to be detected. Here, 1=β1+β2, satisfying 1>β1>0.5>β2>0.

9. The image diagnosis decision support system based on medical knowledge graph according to claim 8, characterized in that: When the selection coefficients of multiple fracture types are the same and the largest, the number of values ​​of each dimension in the 24-dimensional vector form of the diagnostic image to be detected that are respectively located in the boundary interval of the 24-dimensional bounding box with the same selection coefficient is obtained, and the fracture type with the largest number is taken as the fracture type corresponding to the diagnostic image to be detected. If the number is still the same, the corresponding fracture types are output at the same time; When the number of values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected that are located in the boundary interval and fuzzy interval of each dimension of the 24-dimensional bounding box of different fracture types is 0, the manual review procedure is triggered.

10. The image diagnosis decision support system based on medical knowledge graph according to claim 8, characterized in that: When judging the values ​​of each dimension in the real-time 24-dimensional vector form of the diagnostic image to be detected, first determine whether its dimension value is within the boundary interval of each dimension of the 24-dimensional bounding box of different fracture types. If it is, the corresponding dimension value is judged to belong to the boundary interval of the corresponding fracture type, and the number of boundary interval matches of the corresponding fracture type is increased by 1. If it is not, determine whether it is within the fuzzy interval of each dimension of the 24-dimensional bounding box of each fracture type. If it is, the corresponding dimension value is judged to belong to the fuzzy interval of the corresponding fracture type, and the number of fuzzy interval matches of the corresponding fracture type is increased by 1. Otherwise, no processing is performed.

Images