Ultrasonic evaluation method and system based on postoperative pulmonary complication prediction model

Abstract

The invention relates to the field of model prediction, and provides an ultrasonic evaluation method and system based on a postoperative pulmonary complication prediction model, and the method comprises the steps: carrying out the local evaluation of a target lung ultrasonic image and a target diaphragm ultrasonic image, so as to achieve the basic evaluation result of the lung and diaphragm states; according to the method, each single index and state are evaluated and judged in a targeted manner, an effective evaluation basis is provided for overall recognition, then consistency judgment is performed on basic evaluation results through a weighted association algorithm, intra-group consistency and inter-group consistency evaluation is performed respectively, misjudgment interference and false interference are avoided, the evaluation accuracy is improved, and the evaluation efficiency is improved. According to the method, the risk factors of the postoperative pulmonary complications are analyzed, single and comprehensive risk factors of the postoperative pulmonary complications are analyzed respectively, the accuracy of evaluation is further improved, the comprehensive requirement of evaluation is met through joint evaluation, the evaluation result is more practical, and the evaluation accuracy is improved. According to the invention, the accuracy and robustness of the ultrasonic evaluation method are improved.

Description

Technical Field

[0001] The present invention relates to the field of model prediction, and in particular to an ultrasound evaluation method and system based on a postoperative pulmonary complication prediction model. Background Art

[0002] Lung cancer is one of the most common malignant diseases in the world, with the highest incidence and mortality rates. It has had a profound impact worldwide. The main treatment for lung cancer is surgery. Postoperative lung function and postoperative lung complications are important factors affecting patients' postoperative recovery and survival risks. Therefore, it is extremely important to accurately evaluate the lungs before surgery.

[0003] In the prior art, ultrasound technology has gradually been used to detect the lungs or diaphragm, so as to evaluate lung function before surgery. However, the existing evaluation methods can often only evaluate one of the lung ultrasound or diaphragm ultrasound separately, and usually require manual evaluation and judgment, which not only leads to poor evaluation efficiency and high labor costs, but also a single evaluation of the lung ultrasound or diaphragm ultrasound cannot achieve a comprehensive lung function evaluation and cannot meet actual evaluation needs.

[0004] Therefore, how to design an ultrasonic evaluation method to improve the evaluation efficiency and at the same time meet the comprehensive requirements of actual evaluation has become an urgent problem to be solved. Summary of the invention

[0005] Based on this, the present invention proposes an ultrasound assessment method and system based on a postoperative pulmonary complications prediction model, which first performs local assessments on the target lung ultrasound image and the target diaphragm ultrasound image to achieve basic assessment results of the lung and diaphragm status, and conducts targeted evaluation and judgment on each single indicator and status to provide an effective assessment basis for overall identification, and then designs a weighted association algorithm to make consistency judgments on the basic assessment results, and respectively evaluates the intra-group consistency and inter-group consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results to avoid misjudgment interference and false interference, thereby improving the accuracy of the assessment, thereby performing postoperative pulmonary complications risk factor analysis, and respectively analyzing single postoperative pulmonary complications risk factors and comprehensive postoperative pulmonary complications risk factors, thereby further improving the accuracy of the assessment, and then performing a joint assessment to meet the comprehensiveness requirements of the assessment, so that the assessment results are more in line with reality. The present invention improves the accuracy and robustness of the ultrasound assessment method.

[0006] The present invention proposes an ultrasound assessment method based on a postoperative pulmonary complication prediction model, comprising: Acquire a target lung ultrasound image and a target diaphragm ultrasound image and perform preprocessing; Performing local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result, wherein the local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image; The consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results is judged according to a weighted association algorithm, wherein the weighted association algorithm is used to perform intra-group consistency assessment and inter-group consistency assessment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results; If it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, a postoperative pulmonary complication risk factor analysis is performed based on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results, wherein the postoperative pulmonary complication risk factor analysis includes univariate analysis and multivariate analysis; A joint evaluation is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint evaluation result, and the joint evaluation is used to obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results respectively.

[0007] In summary, according to the above-mentioned ultrasound evaluation method based on the postoperative pulmonary complications prediction model, the target lung ultrasound image and the target diaphragm ultrasound image are first locally evaluated to achieve the basic evaluation results of the lung and diaphragm status, and each single indicator and status is evaluated and judged in a targeted manner to provide an effective evaluation basis for overall identification, and then a weighted association algorithm is designed to make a consistency judgment on the basic evaluation results, and the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are evaluated for intra-group consistency and inter-group consistency respectively to avoid misjudgment interference and false interference, thereby improving the accuracy of the evaluation, and then performing a postoperative pulmonary complication risk factor analysis, and analyzing single postoperative pulmonary complication risk factors and comprehensive postoperative pulmonary complication risk factors respectively, further improving the accuracy of the evaluation, and then performing a joint evaluation to meet the comprehensiveness requirements of the evaluation, so that the evaluation results are more in line with reality. The present invention improves the accuracy and robustness of the ultrasound evaluation method. Specifically, a target lung ultrasound image and a target diaphragm ultrasound image are obtained and preprocessed to avoid image noise and artifact interference, providing a basis for accurate identification, and a local evaluation is performed on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result. The local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image, and different parts are divided for evaluation, thereby improving the overall evaluation efficiency. The lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are judged for consistency according to a weighted association algorithm. The weighted association algorithm is used to perform intra-group consistency evaluation and inter-group consistency evaluation on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results, thereby ensuring the elimination of misjudgment interference and false interference, and improving the accuracy of the evaluation. If the lung ultrasound evaluation results are determined to be If the lung ultrasound assessment results and the diaphragm ultrasound assessment results meet the preset consistency requirements, a postoperative lung complication risk factor analysis is performed based on the lung ultrasound assessment results and the diaphragm ultrasound assessment results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The postoperative lung complication risk factor analysis includes univariate analysis and multivariate analysis, and a comprehensive analysis is performed on multiple factors themselves and between multiple factors to further improve the accuracy of identification. A joint assessment is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint assessment result. The joint assessment is used to respectively obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results, thereby avoiding the incomplete assessment caused by evaluating the status of the lungs or diaphragm alone, and improving the authenticity of the assessment. The present invention improves the accuracy and robustness of the ultrasound assessment method.

[0008] Furthermore, the step of acquiring the target lung ultrasound image and the target diaphragm ultrasound image and performing preprocessing specifically includes: A target lung ultrasound image and a target diaphragm ultrasound image are acquired, and noise reduction processing is performed on the target lung ultrasound image and the target diaphragm ultrasound image. The specific algorithm of the noise reduction processing is as follows: , in, represents the image after noise reduction processing, , Represent the horizontal and vertical coordinates of the pixel points respectively. , denote the horizontal and vertical coordinates of the center of the Gaussian kernel, respectively. represents standard deviation; Then, the target lung ultrasound image and the target diaphragm ultrasound image after the noise reduction process are subjected to artifact removal process. The specific algorithm of the artifact removal process is as follows: , in, represents the image after artifact removal, represents the scale parameter, represents the translation parameter, A two-dimensional signal representing the image transformation, represents the conjugate function.

[0009] Further, the step of locally evaluating the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain the lung ultrasound evaluation result and the diaphragm ultrasound evaluation result specifically includes: Performing regional division on the target lung ultrasound image to obtain multiple target lung ultrasound image regions; Extracting local image features of each target lung ultrasound image region, and performing local evaluation according to a preset lung ventilation loss evaluation rule to obtain a lung ultrasound evaluation result; Dividing the target diaphragm ultrasound images into image groups according to ultrasound types to obtain a B-mode ultrasound image group and an M-mode ultrasound image group; Calculating and obtaining a diaphragm mobility assessment result and a diaphragm thickness assessment result according to the B-mode ultrasound image group and the M-mode ultrasound image group; The diaphragm ultrasound evaluation result is obtained according to the diaphragm mobility evaluation result and the diaphragm thickness evaluation result.

[0010] Furthermore, the step of judging the consistency of the lung ultrasound assessment result and the diaphragm ultrasound assessment result according to the weighted association algorithm specifically includes: The intra-group consistency evaluation was performed on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results respectively. The algorithm of the intra-group consistency evaluation was as follows: , in, It represents the consistency value within the group. Indicates category, and Respectively represent the type ordinal numbers of different comparison objects, represents the weight, represents the confusion matrix; The lung ultrasound assessment results and the diaphragm ultrasound assessment results were then subjected to an inter-group consistency assessment, and the algorithm for the inter-group consistency assessment was as follows: , in, It represents the consistency value between groups. represents the row sum in the confusion matrix, represents the column sum in the confusion matrix; According to the intra-group consistency evaluation and the inter-group consistency evaluation, a weighted correlation consistency coefficient is obtained. The algorithm for obtaining the weighted correlation consistency coefficient is as follows: , in, represents the weighted association consistency coefficient.

[0011] Further, the step of obtaining a weighted correlation consistency coefficient according to the intra-group consistency evaluation and the inter-group consistency evaluation then includes: The consistency is judged based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a risk factor analysis of postoperative pulmonary complications is performed according to a univariate logistic analysis algorithm to obtain the probability of a single risk factor of postoperative pulmonary complications; The single factor logic analysis algorithm is as follows: , , in, represents the single factor logistic analysis model, represents the intercept term of the one-way logistic analysis algorithm, represents the regression coefficient of the univariate logistic analysis algorithm, Represents a single risk factor for postoperative pulmonary complications, Represents the probability of a single risk factor for postoperative pulmonary complications.

[0012] Furthermore, the step of obtaining a weighted correlation consistency coefficient according to the intra-group consistency evaluation and the inter-group consistency evaluation further includes: The consistency is judged based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a postoperative pulmonary complication risk factor analysis is performed according to a multifactorial logic analysis algorithm to obtain a comprehensive postoperative pulmonary complication risk factor probability; The multi-factor logic analysis algorithm is specifically as follows: , , in, represents the linear prediction value of the risk factors for postoperative pulmonary complications, represents the intercept term of the multi-factor logistic analysis algorithm, represents the regression coefficient of the multi-factor logistic analysis algorithm, Indicates the ordinal number of variables of the same type. , represents the probability of comprehensive postoperative pulmonary complications risk factors, represents the probability of different types of risk factors for postoperative pulmonary complications, Indicates the types of risk factors for postoperative pulmonary complications. Represents variables within the same postoperative pulmonary complication risk factor type, Indicates the total number of types, Indicates the type ordinal.

[0013] Furthermore, the step of performing a joint evaluation based on the lung ultrasound analysis result and the diaphragm ultrasound analysis result to obtain a joint evaluation result specifically includes: A joint evaluation is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The specific algorithm of the joint evaluation is as follows: , , in, represents the linear prediction value of the same postoperative pulmonary complication risk factor, represents the intercept term of the joint evaluation, represents the regression coefficient of the risk factor for postoperative pulmonary complications, Indicates the same risk factors for postoperative pulmonary complications, represents the probability of different types of risk factors for postoperative pulmonary complications, represents the joint evaluation probability.

[0014] The present invention proposes an ultrasound assessment system based on a postoperative pulmonary complication prediction model, comprising: A preprocessing module, used for acquiring a target lung ultrasound image and a target diaphragm ultrasound image and performing preprocessing; A local evaluation module, used for performing local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result, wherein the local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image; A consistency judgment module, used for judging the consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results according to a weighted association algorithm, wherein the weighted association algorithm is used for performing intra-group consistency assessment and inter-group consistency assessment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results; A risk factor analysis module, for performing a risk factor analysis of postoperative pulmonary complications according to the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results if it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, so as to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results, wherein the risk factor analysis of postoperative pulmonary complications includes univariate analysis and multivariate analysis; A joint evaluation module is used to perform a joint evaluation based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint evaluation result, wherein the joint evaluation is used to obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results respectively.

[0015] The present invention also provides a storage medium, wherein the storage medium stores one or more programs, and when the programs are executed by a processor, the ultrasound evaluation method based on the postoperative pulmonary complications prediction model as described above is implemented.

[0016] The present invention also provides a computer device, the computer device comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, the ultrasound assessment method based on the postoperative pulmonary complications prediction model as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an ultrasound evaluation method based on a postoperative pulmonary complications prediction model proposed in the first embodiment of the present invention; Figure 2 This is a flow chart of an ultrasound assessment method based on a postoperative pulmonary complications prediction model proposed in a second embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an ultrasound assessment system based on a postoperative pulmonary complications prediction model proposed in the third embodiment of the present invention.

[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] See also Figure 1 , which is a flow chart of an ultrasound evaluation method based on a postoperative pulmonary complication prediction model proposed in the first embodiment of the present invention, the ultrasound evaluation method based on a postoperative pulmonary complication prediction model comprises steps S01 to S05, wherein: Step S01: Acquire a target lung ultrasound image and a target diaphragm ultrasound image and perform preprocessing; It should be noted that in this embodiment, a target lung ultrasound image and a target diaphragm ultrasound image are obtained, and noise reduction processing is performed on the target lung ultrasound image and the target diaphragm ultrasound image. The specific algorithm of the noise reduction processing is as follows: , in, represents the image after noise reduction processing, , Represent the horizontal and vertical coordinates of the pixel points respectively. , denote the horizontal and vertical coordinates of the center of the Gaussian kernel, respectively. represents standard deviation; Then, the target lung ultrasound image and the target diaphragm ultrasound image after the noise reduction process are subjected to artifact removal process. The specific algorithm of the artifact removal process is as follows: , in, represents the image after artifact removal, represents the scale parameter, represents the translation parameter, A two-dimensional signal representing the image transformation, represents the conjugate function.

[0023] Step S02: performing local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result; It should be noted that in this embodiment, the target lung ultrasound image is divided into regions to obtain multiple target lung ultrasound image regions; Extracting local image features of each target lung ultrasound image region, and performing local evaluation according to a preset lung ventilation loss evaluation rule to obtain a lung ultrasound evaluation result; Dividing the target diaphragm ultrasound images into image groups according to ultrasound types to obtain a B-mode ultrasound image group and an M-mode ultrasound image group; Calculating and obtaining a diaphragm mobility assessment result and a diaphragm thickness assessment result according to the B-mode ultrasound image group and the M-mode ultrasound image group; The diaphragm ultrasound evaluation result is obtained according to the diaphragm mobility evaluation result and the diaphragm thickness evaluation result.

[0024] Step S03: performing consistency judgment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results according to a weighted association algorithm; It should be noted that in this embodiment, intra-group consistency evaluation is performed on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results respectively, and the algorithm of the intra-group consistency evaluation is as follows: , in, It represents the consistency value within the group. Indicates category, and Respectively represent the type ordinal numbers of different comparison objects, represents the weight, represents the confusion matrix; The lung ultrasound assessment results and the diaphragm ultrasound assessment results were then subjected to an inter-group consistency assessment, and the algorithm for the inter-group consistency assessment was as follows: , in, It represents the consistency value between groups. represents the row sum in the confusion matrix, represents the column sum in the confusion matrix; According to the intra-group consistency evaluation and the inter-group consistency evaluation, a weighted correlation consistency coefficient is obtained. The algorithm for obtaining the weighted correlation consistency coefficient is as follows: , in, represents the weighted association consistency coefficient.

[0025] Step S04: if it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, then a postoperative lung complication risk factor analysis is performed based on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results; It should be noted that in this embodiment, consistency judgment is performed based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a risk factor analysis of postoperative pulmonary complications is performed according to a univariate logistic analysis algorithm to obtain the probability of a single risk factor of postoperative pulmonary complications; The single factor logic analysis algorithm is specifically as follows: , , in, represents the single factor logistic analysis model, represents the intercept term of the one-way logistic analysis algorithm, represents the regression coefficient of the univariate logistic analysis algorithm, Represents a single risk factor for postoperative pulmonary complications, represents the probability of a single risk factor for postoperative pulmonary complications; The consistency is judged based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a postoperative pulmonary complication risk factor analysis is performed according to a multifactorial logic analysis algorithm to obtain a comprehensive postoperative pulmonary complication risk factor probability; The multi-factor logic analysis algorithm is specifically as follows: , , in, represents the linear prediction value of the risk factors for postoperative pulmonary complications, represents the intercept term of the multi-factor logistic analysis algorithm, represents the regression coefficient of the multi-factor logistic analysis algorithm, Indicates the ordinal number of variables of the same type. , represents the probability of comprehensive postoperative pulmonary complications risk factors, represents the probability of different types of risk factors for postoperative pulmonary complications, Indicates the types of risk factors for postoperative pulmonary complications. Represents variables within the same postoperative pulmonary complication risk factor type, Indicates the total number of types, Indicates the type ordinal.

[0026] Step S05: performing a joint evaluation based on the lung ultrasound analysis result and the diaphragm ultrasound analysis result to obtain a joint evaluation result; It should be noted that in this embodiment, a joint evaluation is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The specific algorithm of the joint evaluation is as follows: , , in, represents the linear prediction value of the same postoperative pulmonary complication risk factor, represents the intercept term of the joint evaluation, represents the regression coefficient of the risk factor for postoperative pulmonary complications, Indicates the same risk factors for postoperative pulmonary complications, represents the probability of different types of risk factors for postoperative pulmonary complications, represents the joint evaluation probability.

[0027] In summary, according to the above-mentioned ultrasound evaluation method based on the postoperative pulmonary complications prediction model, the target lung ultrasound image and the target diaphragm ultrasound image are first locally evaluated to achieve the basic evaluation results of the lung and diaphragm status, and each single indicator and status is evaluated and judged in a targeted manner to provide an effective evaluation basis for overall identification, and then a weighted association algorithm is designed to make a consistency judgment on the basic evaluation results, and the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are evaluated for intra-group consistency and inter-group consistency respectively to avoid misjudgment interference and false interference, thereby improving the accuracy of the evaluation, and then performing a postoperative pulmonary complication risk factor analysis, and analyzing single postoperative pulmonary complication risk factors and comprehensive postoperative pulmonary complication risk factors respectively, further improving the accuracy of the evaluation, and then performing a joint evaluation to meet the comprehensiveness requirements of the evaluation, so that the evaluation results are more in line with reality. The present invention improves the accuracy and robustness of the ultrasound evaluation method. Specifically, a target lung ultrasound image and a target diaphragm ultrasound image are obtained and preprocessed to avoid image noise and artifact interference, providing a basis for accurate identification, and a local evaluation is performed on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result. The local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image, and different parts are divided for evaluation, thereby improving the overall evaluation efficiency. The lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are judged for consistency according to a weighted association algorithm. The weighted association algorithm is used to perform intra-group consistency evaluation and inter-group consistency evaluation on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results, thereby ensuring the elimination of misjudgment interference and false interference, and improving the accuracy of the evaluation. If the lung ultrasound evaluation results are determined to be If the lung ultrasound assessment results and the diaphragm ultrasound assessment results meet the preset consistency requirements, a postoperative lung complication risk factor analysis is performed based on the lung ultrasound assessment results and the diaphragm ultrasound assessment results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The postoperative lung complication risk factor analysis includes univariate analysis and multivariate analysis, and a comprehensive analysis is performed on multiple factors themselves and between multiple factors to further improve the accuracy of identification. A joint assessment is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint assessment result. The joint assessment is used to respectively obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results, thereby avoiding the incomplete assessment caused by evaluating the status of the lungs or diaphragm alone, and improving the authenticity of the assessment. The present invention improves the accuracy and robustness of the ultrasound assessment method.

[0028] See also Figure 2 , which is a flow chart of an ultrasound evaluation method based on a postoperative pulmonary complication prediction model proposed in a second embodiment of the present invention, the ultrasound evaluation method based on a postoperative pulmonary complication prediction model comprises steps S11 to S16, wherein: Step S11: acquiring a target lung ultrasound image and a target diaphragm ultrasound image, performing noise reduction processing on the target lung ultrasound image and the target diaphragm ultrasound image, and then performing artifact removal processing on the target lung ultrasound image and the target diaphragm ultrasound image after the noise reduction processing; Step S12: Divide the target lung ultrasound image into regions to obtain multiple target lung ultrasound image regions, extract local image features of each target lung ultrasound image region, perform local evaluation according to preset lung ventilation loss evaluation rules to obtain lung ultrasound evaluation results, divide the target diaphragm ultrasound image into image groups according to ultrasound types to obtain B-type ultrasound image groups and M-type ultrasound image groups, calculate and obtain diaphragm mobility evaluation results and diaphragm thickness evaluation results according to the B-type ultrasound image groups and the M-type ultrasound image groups, and obtain diaphragm ultrasound evaluation results according to the diaphragm mobility evaluation results and the diaphragm thickness evaluation results; It should be noted that the preset pulmonary ventilation loss assessment rule in the present embodiment is to divide the target lung ultrasound image into multiple areas, and the score of each area is set to 0 to 3 points, the normal ventilation area is 0 point, the moderate lung tissue deaeration area is 1 point, the severe lung tissue deaeration area is 2 points, and the lung consolidation area is 3 points. The scores of all areas are accumulated to obtain the lung ultrasound assessment result. In the present embodiment, the diaphragm mobility assessment result is calculated based on the measurement of the diaphragm mobility during the calm breathing phase and the diaphragm mobility during the forced breathing phase. In the present embodiment, the diaphragm thickness assessment result is calculated based on the measurement of the diaphragm thickness at the end of inspiration and the diaphragm thickness at the end of expiration during calm breathing. The calculation method of the diaphragm thickness assessment result is diaphragm thickness assessment result = (diaphragm thickness at the end of expiration - diaphragm thickness at the end of inspiration) / diaphragm thickness at the end of expiration x 100%.

[0029] Step S13: performing intra-group consistency evaluation on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results respectively, and then performing inter-group consistency evaluation on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results, so as to obtain a weighted correlation consistency coefficient according to the intra-group consistency evaluation and the inter-group consistency evaluation; Step S14: performing consistency judgment according to the weighted correlation consistency coefficient. If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, performing postoperative pulmonary complication risk factor analysis according to the univariate logistic analysis algorithm to obtain the probability of a single postoperative pulmonary complication risk factor; Step S15: performing consistency judgment according to the weighted correlation consistency coefficient. If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, performing postoperative pulmonary complication risk factor analysis according to the multi-factor logic analysis algorithm to obtain the comprehensive postoperative pulmonary complication risk factor probability; Step S16: Perform a joint assessment based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results.

[0030] In summary, according to the above-mentioned ultrasound evaluation method based on the postoperative pulmonary complications prediction model, the target lung ultrasound image and the target diaphragm ultrasound image are first locally evaluated to achieve the basic evaluation results of the lung and diaphragm status, and each single indicator and status is evaluated and judged in a targeted manner to provide an effective evaluation basis for overall identification, and then a weighted association algorithm is designed to make a consistency judgment on the basic evaluation results, and the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are evaluated for intra-group consistency and inter-group consistency respectively to avoid misjudgment interference and false interference, thereby improving the accuracy of the evaluation, and then performing a postoperative pulmonary complication risk factor analysis, and analyzing single postoperative pulmonary complication risk factors and comprehensive postoperative pulmonary complication risk factors respectively, further improving the accuracy of the evaluation, and then performing a joint evaluation to meet the comprehensiveness requirements of the evaluation, so that the evaluation results are more in line with reality. The present invention improves the accuracy and robustness of the ultrasound evaluation method. Specifically, a target lung ultrasound image and a target diaphragm ultrasound image are obtained and preprocessed to avoid image noise and artifact interference, providing a basis for accurate identification, and a local evaluation is performed on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result. The local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image, and different parts are divided for evaluation, thereby improving the overall evaluation efficiency. The lung ultrasound evaluation results and the diaphragm ultrasound evaluation results are judged for consistency according to a weighted association algorithm. The weighted association algorithm is used to perform intra-group consistency evaluation and inter-group consistency evaluation on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results, thereby ensuring the elimination of misjudgment interference and false interference, and improving the accuracy of the evaluation. If the lung ultrasound evaluation results are determined to be If the lung ultrasound assessment results and the diaphragm ultrasound assessment results meet the preset consistency requirements, a postoperative lung complication risk factor analysis is performed based on the lung ultrasound assessment results and the diaphragm ultrasound assessment results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The postoperative lung complication risk factor analysis includes univariate analysis and multivariate analysis, and a comprehensive analysis is performed on multiple factors themselves and between multiple factors to further improve the accuracy of identification. A joint assessment is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint assessment result. The joint assessment is used to respectively obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results, thereby avoiding the incomplete assessment caused by evaluating the status of the lungs or diaphragm alone, and improving the authenticity of the assessment. The present invention improves the accuracy and robustness of the ultrasound assessment method.

[0031] See also Figure 3 , which is a schematic diagram of the structure of an ultrasound evaluation system based on a postoperative pulmonary complications prediction model proposed in the third embodiment of the present invention, the system comprises: A preprocessing module 10 is used to obtain a target lung ultrasound image and a target diaphragm ultrasound image and perform preprocessing; A local evaluation module 20, configured to perform local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result, wherein the local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image; A consistency judgment module 30, used for judging the consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results according to a weighted association algorithm, wherein the weighted association algorithm is used for performing intra-group consistency assessment and inter-group consistency assessment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results; The risk factor analysis module 40 is used to perform a risk factor analysis of postoperative pulmonary complications according to the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results if it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, so as to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results, wherein the risk factor analysis of postoperative pulmonary complications includes univariate analysis and multivariate analysis; The joint evaluation module 50 is used to perform a joint evaluation based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint evaluation result, wherein the joint evaluation is used to obtain the predictive values ​​of the lung ultrasound analysis results and the diaphragm ultrasound analysis results respectively.

[0032] The present invention also proposes a computer storage medium on which one or more programs are stored, and when the programs are executed by a processor, the above-mentioned ultrasound evaluation method based on the postoperative pulmonary complications prediction model is implemented.

[0033] The present invention also proposes a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the above-mentioned ultrasound evaluation method based on the postoperative pulmonary complications prediction model.

[0034] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain storage, communication, propagation or transmission of a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0035] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0036] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0037] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0038] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An ultrasound assessment method based on a postoperative pulmonary complication prediction model, characterized in that: include: Acquire a target lung ultrasound image and a target diaphragm ultrasound image and perform preprocessing; Performing local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result, wherein the local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image; The consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results is judged according to a weighted association algorithm, wherein the weighted association algorithm is used to perform intra-group consistency assessment and inter-group consistency assessment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results; If it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, a postoperative pulmonary complication risk factor analysis is performed based on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results, wherein the postoperative pulmonary complication risk factor analysis includes univariate analysis and multivariate analysis; A joint evaluation is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint evaluation result, and the joint evaluation is used to obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results respectively.

2. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 1, characterized in that: The step of acquiring a target lung ultrasonic image and a target diaphragm ultrasonic image and performing preprocessing specifically includes: A target lung ultrasound image and a target diaphragm ultrasound image are acquired, and noise reduction processing is performed on the target lung ultrasound image and the target diaphragm ultrasound image. The specific algorithm of the noise reduction processing is as follows: ， in, represents the image after noise reduction processing, , Represent the horizontal and vertical coordinates of the pixel points respectively. , denote the horizontal and vertical coordinates of the center of the Gaussian kernel, respectively. represents standard deviation; Then, the target lung ultrasound image and the target diaphragm ultrasound image after the noise reduction process are subjected to artifact removal process. The specific algorithm of the artifact removal process is as follows: ， in, represents the image after artifact removal, represents the scale parameter, represents the translation parameter, A two-dimensional signal representing the image transformation, represents the conjugate function.

3. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 1, characterized in that: The step of locally evaluating the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain the lung ultrasound evaluation result and the diaphragm ultrasound evaluation result specifically includes: Performing regional division on the target lung ultrasound image to obtain multiple target lung ultrasound image regions; Extracting local image features of each target lung ultrasound image region, and performing local evaluation according to a preset lung ventilation loss evaluation rule to obtain a lung ultrasound evaluation result; Dividing the target diaphragm ultrasound images into image groups according to ultrasound types to obtain a B-mode ultrasound image group and an M-mode ultrasound image group; Calculating and obtaining a diaphragm mobility assessment result and a diaphragm thickness assessment result according to the B-mode ultrasound image group and the M-mode ultrasound image group; The diaphragm ultrasound evaluation result is obtained according to the diaphragm mobility evaluation result and the diaphragm thickness evaluation result.

4. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 1, characterized in that: The step of judging the consistency of the lung ultrasound assessment result and the diaphragm ultrasound assessment result according to the weighted association algorithm specifically includes: The intra-group consistency evaluation was performed on the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results respectively. The algorithm of the intra-group consistency evaluation was as follows: ， in, It represents the consistency value within the group. Indicates category, and Respectively represent the type ordinal numbers of different comparison objects, represents the weight, represents the confusion matrix; The lung ultrasound assessment results and the diaphragm ultrasound assessment results were then subjected to an inter-group consistency assessment, and the algorithm for the inter-group consistency assessment was as follows: ， in, It represents the consistency value between groups. represents the row sum in the confusion matrix, represents the column sum in the confusion matrix; According to the intra-group consistency evaluation and the inter-group consistency evaluation, a weighted correlation consistency coefficient is obtained. The algorithm for obtaining the weighted correlation consistency coefficient is as follows: ， in, represents the weighted association consistency coefficient.

5. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 4, characterized in that: The step of obtaining a weighted correlation consistency coefficient according to the intra-group consistency evaluation and the inter-group consistency evaluation then comprises: The consistency is judged based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a risk factor analysis of postoperative pulmonary complications is performed according to a univariate logistic analysis algorithm to obtain the probability of a single risk factor of postoperative pulmonary complications; The single factor logic analysis algorithm is as follows: ， ， in, represents the single factor logistic analysis model, represents the intercept term of the one-way logistic analysis algorithm, represents the regression coefficient of the univariate logistic analysis algorithm, Represents a single risk factor for postoperative pulmonary complications, Represents the probability of a single risk factor for postoperative pulmonary complications.

6. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 4, characterized in that: The step of obtaining a weighted correlation consistency coefficient according to the intra-group consistency evaluation and the inter-group consistency evaluation further includes: The consistency is judged based on the weighted correlation consistency coefficient; If it is determined that the weighted correlation consistency coefficient meets the preset consistency requirement, a postoperative pulmonary complication risk factor analysis is performed according to a multifactorial logic analysis algorithm to obtain a comprehensive postoperative pulmonary complication risk factor probability; The multi-factor logic analysis algorithm is specifically as follows: ， ， in, represents the linear prediction value of the risk factors for postoperative pulmonary complications, represents the intercept term of the multi-factor logistic analysis algorithm, represents the regression coefficient of the multi-factor logistic analysis algorithm, Indicates the ordinal number of variables of the same type. , represents the probability of comprehensive postoperative pulmonary complications risk factors, represents the probability of different types of risk factors for postoperative pulmonary complications, Indicates the types of risk factors for postoperative pulmonary complications. Represents variables within the same postoperative pulmonary complication risk factor type, Indicates the total number of types. Indicates the type ordinal.

7. The ultrasound assessment method based on the postoperative pulmonary complications prediction model according to claim 1, characterized in that: The step of performing a joint evaluation based on the lung ultrasound analysis result and the diaphragm ultrasound analysis result to obtain a joint evaluation result specifically includes: A joint evaluation is performed based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results. The specific algorithm of the joint evaluation is as follows: ， ， in, represents the linear prediction value of the same postoperative pulmonary complication risk factor, represents the intercept term of the joint evaluation, represents the regression coefficient of the risk factor for postoperative pulmonary complications, Indicates the same risk factors for postoperative pulmonary complications, represents the probability of different types of risk factors for postoperative pulmonary complications, represents the joint evaluation probability.

8. An ultrasound assessment system based on a postoperative pulmonary complication prediction model, characterized in that: include: A preprocessing module, used for acquiring a target lung ultrasound image and a target diaphragm ultrasound image and performing preprocessing; A local evaluation module, used for performing local evaluation on the preprocessed target lung ultrasound image and the target diaphragm ultrasound image to obtain a lung ultrasound evaluation result and a diaphragm ultrasound evaluation result, wherein the local evaluation is based on a single evaluation algorithm corresponding to the target lung ultrasound image and the target diaphragm ultrasound image; A consistency judgment module, used for judging the consistency of the lung ultrasound assessment results and the diaphragm ultrasound assessment results according to a weighted association algorithm, wherein the weighted association algorithm is used for performing intra-group consistency assessment and inter-group consistency assessment on the lung ultrasound assessment results and the diaphragm ultrasound assessment results; A risk factor analysis module, for performing a risk factor analysis of postoperative pulmonary complications according to the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results if it is determined that the lung ultrasound evaluation results and the diaphragm ultrasound evaluation results meet the preset consistency requirements, so as to obtain the lung ultrasound analysis results and the diaphragm ultrasound analysis results, wherein the risk factor analysis of postoperative pulmonary complications includes univariate analysis and multivariate analysis; A joint evaluation module is used to perform a joint evaluation based on the lung ultrasound analysis results and the diaphragm ultrasound analysis results to obtain a joint evaluation result, wherein the joint evaluation is used to obtain the predictive value of the lung ultrasound analysis results and the diaphragm ultrasound analysis results respectively.

9. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by the processor, implement the ultrasound assessment method based on the postoperative pulmonary complications prediction model as described in any one of claims 1-7.

10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the ultrasound assessment method based on the postoperative pulmonary complications prediction model described in any one of claims 1-7.

Images