Risk assessment, decision-making methods and devices, electronic devices and media for chronic obstructive pulmonary disease

Abstract

The present disclosure relates to a risk assessment and decision-making method and device for chronic obstructive pulmonary disease, an electronic device and a medium, and relates to the field of biomedical engineering technology. The risk assessment method for chronic obstructive pulmonary disease includes: obtaining a set of multiple lung imaging omics features and age information corresponding to chronic obstructive pulmonary disease at different levels; constructing an evaluation model based on the set lung imaging omics features and the corresponding age information; and evaluating the chronic obstructive pulmonary disease along with the age information based on the evaluation model. The embodiments of the present disclosure can realize the risk assessment and early decision-making of chronic obstructive pulmonary disease.

Description

Technical Field

[0001] The present disclosure relates to the field of biomedical engineering technology, and in particular to a risk assessment and decision-making method and device for chronic obstructive pulmonary disease, an electronic device, and a medium. Background Art

[0002] Chronic obstructive pulmonary disease (COPD) is characterized by persistent airflow limitation. The gold standard for diagnosing and evaluating COPD is the forced expiratory volume in one second (FEV1) and the FEV1 / forced vital capacity (FVC) ratio measured by pulmonary function testing (PFT). Previous studies on COPD have focused on COPD diagnosis and classification, COPD treatment, COPD exacerbation prediction, and COPD assessment. Many age-related changes have been demonstrated in the respiratory and pulmonary immune systems. Age has become one of the factors in a score called “emphasis” (emphysema, age, smoking, body size) to predict the presence and future incidence of clinically significant COPD. COPD has the highest prevalence in the elderly and deserves special consideration in the treatment of this vulnerable population. However, the impact of age on the risk of COPD is unclear.

[0003] As adults age, the size of the chest cavity decreases, limiting lung volume and changing the muscles that aid in breathing. PFT results vary with age in both healthy people and those with COPD. After birth, lung tissue continues to develop and grow to maturity. As a result, the alveoli and small blood vessels in the lungs will multiply, and the lung volume will become larger. The median FEV1 and FVC in the PFT increase with age, linearly from 6 to 18 years until the adolescent growth spurt around 10 years of age for girls and 12 years of age for boys. From 6 to 18 years of age, the median FEV1 / FVC first decreases, then increases, and finally decreases. After the lungs mature, the respiratory function of the lungs gradually decreases with age. Previous studies have shown that in healthy lifelong nonsmokers, both FEV1 and FVC gradually decrease as age increases from 20 to 90 years. FVC and FEV1 also decreased significantly in COPD patients over the four-year follow-up period. FEV1 peaks between 20 and 36 years of age and decreases with age. The prevalence of COPD is 2-3 times higher in people over 60 years of age. The increased burden of COPD in the elderly may be due to age-related changes in lung structure and function that increase susceptibility to COPD. These changes seen in elderly lifelong nonsmokers are characterized by air space expansion due to loss of supporting tissue without alveolar wall destruction, similar to changes seen in COPD. Therefore, it is necessary to assess the risk of COPD at different ages.

[0004] Compared with PFT, computed tomography (CT) is considered to be the most effective method for characterizing and quantifying COPD, for example, quantitatively analyzing airway disease and emphysema in patients with COPD. Since the concept of radiomics was formally proposed in 2012, radiomics of chest CT images has been widely used for prediction of chemotherapy response in non-small cell lung cancer and prediction of pathological aggressiveness in patients with solitary pulmonary nodules. Recently, radiomics has also been used for survival prediction in COPD, as well as prediction of COPD exacerbation. However, radiomics in COPD has not been widely studied. At present, the potential application of radiomics features needs to be further explored in the diagnosis, treatment and follow-up of COPD and future development directions. In particular, as imaging biomarkers reflecting the status of lung parenchyma, radiomics features can be applied to COPD risk assessment to make early COPD risk decisions. Summary of the invention

[0005] The present invention discloses a risk assessment and decision-making method and device for chronic obstructive pulmonary disease, an electronic device, and a medium technology solution.

[0006] According to one aspect of the present disclosure, a method for risk assessment of chronic obstructive pulmonary disease is provided, comprising:

[0007] Obtain multiple lung imaging features and age information corresponding to different grades of COPD;

[0008] Constructing an evaluation model based on the set lung imaging features and corresponding age information;

[0009] Based on the assessment model, an assessment of COPD along with the age information is performed.

[0010] Preferably, before obtaining the set multiple lung imaging features corresponding to COPD at different levels, the set multiple lung imaging features are determined, and the method includes:

[0011] Obtain multiple lung imaging features corresponding to the set screening model and different grades of COPD;

[0012] The set screening model and the set screening rules are used to screen multiple lung imaging omics features corresponding to COPD under the different grades to obtain the set multiple lung imaging omics features; wherein the set screening rules at least include: the grade of COPD.

[0013] Preferably, the method for constructing an evaluation model based on the set lung imaging features and corresponding age information comprises:

[0014] Dividing the set multiple lung imaging omics features into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the classification, and dividing the age information corresponding to the multiple groups of lung imaging omics features into multiple age intervals according to the set intervals, and numbering the number of the age intervals in an increasing manner according to the age;

[0015] Evaluation models are constructed based on the multiple groups of lung imaging features and corresponding labels.

[0016] Preferably, the method for determining the set grouping rules corresponding to the classification includes:

[0017] determining the lung radiomics features corresponding to the lowest grade of the grades as a first subgroup of the plurality of groups;

[0018] respectively determining the lung imaging features corresponding to the other grades as second subgroups of the multiple groups;

[0019] and / or,

[0020] The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes:

[0021] Obtaining the multiple groups of corresponding basic evaluation models to be constructed;

[0022] The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

[0023] Preferably, before constructing the evaluation model based on the set lung imaging omics features and the corresponding age information, the set lung imaging omics features are subjected to nonlinear processing to obtain nonlinear features;

[0024] An evaluation model is constructed based on the set lung imaging features, the nonlinear features and the corresponding age information.

[0025] According to one aspect of the present disclosure, a risk decision method for chronic obstructive pulmonary disease is provided, comprising: the above-mentioned assessment method; and

[0026] Obtaining a risk assessment result of COPD, wherein the risk assessment result at least includes: risk probability and its corresponding COPD grade and age information;

[0027] According to the set zoning rules, the risk of COPD is divided to obtain the risk level;

[0028] Based on the risk assessment result and the risk level, a risk decision for COPD is made to obtain age information corresponding to the risk interval.

[0029] According to one aspect of the present disclosure, a risk assessment device for chronic obstructive pulmonary disease is provided, comprising:

[0030] The first acquisition unit is used to acquire a plurality of lung imaging features and age information corresponding to COPD at different levels;

[0031] A construction unit, used to construct an evaluation model based on the set lung imaging features and corresponding age information;

[0032] An evaluation unit is used to evaluate COPD along with the age information based on the evaluation model.

[0033] According to one aspect of the present disclosure, a risk decision-making device for COPD is provided, comprising: the risk assessment device for COPD as described above; the risk assessment device for COPD is used to generate a risk assessment result for COPD; wherein the risk assessment result at least includes: risk probability and its corresponding COPD grade and age information; and,

[0034] The second acquisition unit is used to obtain the risk assessment results of COPD.

[0035] The risk level unit is used to divide the risk of COPD according to the set zoning rules to obtain the risk level;

[0036] A risk decision unit is used to make a risk decision for COPD based on the risk assessment result and the risk level, and obtain age information corresponding to the risk interval.

[0037] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0038] processor;

[0039] a memory for storing processor-executable instructions;

[0040] Wherein, the processor is configured to: execute the above-mentioned risk assessment method for COPD and / or the risk decision-making method for COPD.

[0041] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned risk assessment method for COPD and / or the risk decision-making method for COPD are implemented.

[0042] In the embodiments of the present disclosure, the disclosed COPD risk assessment, decision-making methods and devices, electronic equipment and medium technology solutions can realize COPD risk assessment and early decision-making, provide clinical assistance for COPD assessment and early warning, and thus solve the current problem of not being able to clearly determine the effect of age on COPD risk quantitative assessment.

[0043] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0044] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0046] Figure 1 A flow chart showing a method for risk assessment of COPD according to an embodiment of the present disclosure;

[0047] Figure 2 A flowchart showing region of interest segmentation and radiomics calculation according to an embodiment of the present disclosure is shown;

[0048] Figure 3 A flowchart of constructing an evaluation model according to an embodiment of the present disclosure is shown;

[0049] Figure 4 A specific implementation flow chart of constructing an evaluation model according to an embodiment of the present disclosure is shown;

[0050] Figure 5 The ROC curve and the corresponding AUC value and C index value of the evaluation model according to the embodiment of the present disclosure are shown;

[0051] Figure 6 The COPD risk probability value corresponding to the evaluation model constructed according to the embodiment of the present disclosure is shown;

[0052] Figure 7 The age-risk curve corresponding to the COPD risk probability value constructed according to the embodiment of the present disclosure is shown;

[0053] Figure 8 A flow chart showing a method for risk decision-making for COPD according to an embodiment of the present disclosure;

[0054] Fig. 9 A risk decision diagram showing age-risk corresponding to patients with different grades of COPD and COPD grade 0 (no COPD) according to an embodiment of the present disclosure;

[0055] Fig.10 is a block diagram of an electronic device 800 according to an exemplary embodiment;

[0056] Fig.11 is a block diagram of an electronic device 1900 according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0058] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0059] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0060] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0061] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present disclosure will not go into details.

[0062] In addition, the present disclosure also provides a risk assessment device for COPD, and / or a risk decision-making device, electronic device, computer-readable storage medium, and program for COPD, all of which can be used to implement any COPD risk assessment method and / or COPD risk decision-making method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to in the corresponding records of the method section and will not be repeated here.

[0063] Figure 1 A flow chart showing a method for risk assessment of COPD according to an embodiment of the present disclosure is shown as follows: Figure 1As shown, the risk assessment method for COPD includes: step S101: obtaining a plurality of set lung imaging features and age information corresponding to COPD at different levels; step S102: constructing an assessment model based on the set lung imaging features and the corresponding age information; step S103: based on the assessment model, assessing COPD with the age information. The risk assessment and early decision-making of COPD can be realized, providing clinical assistance for the assessment and early warning of COPD, thereby solving the problem that the quantitative assessment of COPD risk cannot be clearly determined for age.

[0064] Step S101: Acquire a plurality of lung imaging features and age information corresponding to COPD at different levels.

[0065] In the present disclosure, before obtaining the set multiple lung imaging omics features corresponding to COPD at different levels, the set multiple lung imaging omics features are determined, and the method includes: obtaining a set screening model and multiple lung imaging omics features corresponding to COPD at different levels; using the set screening model and set screening rules to screen the multiple lung imaging omics features corresponding to COPD at different levels to obtain the set multiple lung imaging omics features; wherein the set screening rules at least include: the level of COPD.

[0066] In the embodiments of the present disclosure and other possible embodiments, the set screening model may be one or more of a Lasso (Least absolute shrinkage and selection operator) model, a Lars (minimum angle regression algorithm) model, a ridge regression model or other screening models. Obviously, those skilled in the art may also use other existing screening methods to screen the multiple lung imaging features corresponding to COPD under different grades as needed to obtain the set multiple lung imaging features. The present disclosure does not limit the screening method or model.

[0067] In the embodiments of the present disclosure and other possible embodiments, different grades of COPD are determined by the GOLD (Global Initiative for Chronic Obstructive Lung Disease, GOLD) standard. According to the GOLD standard, the grade of COPD can be determined as COPD stage 0, COPD stage I, COPD stage II, COPD stage III, and COPD stage IV. Among them, COPD grade 0 means no COPD, COPD grade I is mild COPD, COPD grade II is moderate COPD, COPD grade III is severe COPD, and COPD grade IV is critical COPD. Obviously, those skilled in the art can also use other existing methods to grade COPD as needed, and the present disclosure does not limit the method or method of grading COPD.

[0068] Figure 2 FIG. 4 is a flowchart showing the region of interest segmentation and radiomics calculation according to an embodiment of the present disclosure. Figure 2 As shown, before obtaining the set screening model and multiple lung imaging features corresponding to COPD under different grades, it is necessary to segment the lung area as a region of interest (ROI) to obtain a lung area segmentation image; wherein the lung area segmentation image can be a lung area segmentation image of the left lung, a lung area segmentation image of the right lung, or a lung area segmentation image of both lungs (left lung and right lung). Those skilled in the art can also select the lung area segmentation image as needed. At the same time, the method of segmenting the lung area as a region of interest (ROI) to obtain a lung area segmentation image includes: obtaining a preset lung area segmentation model and an original chest image, and segmenting the chest image using the lung area segmentation model to obtain a lung area segmentation image. Wherein, the original chest image can be a chest DR image, a chest CT image, a chest high-resolution CT (HRCT) image or other chest image; the preset lung area segmentation model can use a traditional lung area segmentation method or a neural network model commonly used in the art, which will not be described in detail here.

[0069] In the embodiments of the present disclosure and other possible embodiments, before obtaining the set multiple lung imaging features and age information corresponding to COPD at different levels, it is necessary to determine the region of interest to be analyzed, and obtain the set multiple lung imaging features and age information corresponding to COPD at different levels corresponding to the region of interest to be analyzed. The region of interest to be analyzed may be the left lung, the right lung, or both lungs.

[0070] exist Figure 2 In (A), a chest HRCT image (image size: 512×512×N) is subjected to lung region segmentation using a preset lung region segmentation model to obtain a lung region segmentation image (image size: 512×512×N).

[0071] In the embodiments of the present disclosure and other possible embodiments, the lung region segmentation image and the original chest image are input into the lung imaging omics calculation model to calculate the lung imaging omics corresponding to the original chest image. At the same time, in the lung imaging omics calculation model, the lung parenchyma image is first extracted based on the lung region segmentation image and the original chest image to obtain the original lung parenchyma image; the set filter is obtained, and the original lung parenchyma image is filtered using the set filter to obtain a derived lung parenchyma image; based on the set class of the acquired imaging omics features, the original lung parenchyma image and the derived lung parenchyma image are calculated for lung imaging omics to obtain multiple lung imaging omics features. Among them, the number of the derived lung parenchyma images is the same as the number of the set filters.

[0072] exist Figure 2 In (B), a chest HRCT image (512×512×N) and a chest HRCT image (512×512×N) are input into the lung imaging genomics calculation model to calculate the lung imaging genomics corresponding to the chest HRCT image. Specifically, the set filter is a wavelet filter and / or a LoG filter, and those skilled in the art can select an appropriate filter as needed. The specific meaning of the set class of imaging genomics features can be understood by referring to the detailed description in the lung image processing method and device, electronic device and storage medium (application number: 202110956768.6), and the present disclosure will not be described in detail here.

[0073] In the following embodiments of the present disclosure, the GOLD standard is selected, and according to the GOLD standard, the COPD grade can be determined as COPD grade 0, COPD grade I, COPD grade II, COPD grade III, and COPD grade IV. The setting of the screening rule includes at least: any two grades of COPD.

[0074] For example, COPD stage 0 and having COPD (COPD stage I, COPD stage II, COPD stage III, COPD stage IV), COPD stage 0 and COPD stage I, COPD stage 0 and COPD stage II, COPD stage 0 and COPD stage III, COPD stage 0 and COPD stage IV.

[0075] In the embodiments of the present disclosure and other possible embodiments, the method of using the set screening model and the set screening rules to screen multiple lung imaging omics features corresponding to COPD under different grades to obtain the set multiple lung imaging omics features includes: determining the COPD grade and the imaging omics to be screened corresponding to the COPD grade according to the set screening rules; using the set screening model, establishing the relationship between the COPD grade and the imaging omics to be screened corresponding to the COPD grade, and obtaining the set multiple lung imaging omics features. In the embodiments of the present disclosure, the set screening model is preferably a Lasso model.

[0076] Among them, before determining the COPD grade and the imaging omics to be screened corresponding to the COPD grade according to the set screening rules, the COPD grade is respectively encoded 0-1, and the relationship between the 0-1 encoded COPD grade and the imaging omics to be screened corresponding to the COPD grade is established by using the set screening model, so as to obtain the set multiple lung imaging omics features. For example, the set screening rules are COPD grade 0 and suffering from COPD; after COPD grade 0 is encoded 0-1, it corresponds to 0; after suffering from COPD is encoded 0-1, it corresponds to 1. For another example, the set screening rules are COPD grade 0 and COPD grade III; after COPD grade 0 is encoded 0-1, it corresponds to 0; after COPD grade III is encoded 0-1, it corresponds to 1.

[0077] Step S102: constructing an evaluation model based on the set lung imaging features and corresponding age information.

[0078] In an embodiment of the present disclosure, the method for constructing an evaluation model based on the set lung imaging omics features and the corresponding age information includes: dividing the set multiple lung imaging omics features into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the classification, and dividing the age information corresponding to the multiple groups of lung imaging omics features into multiple age intervals according to the set intervals, and labeling the number of age intervals in ascending order of age; constructing evaluation models based on the multiple groups of lung imaging omics features and the corresponding labels.

[0079] In the embodiments of the present disclosure and other possible embodiments, the age information corresponding to the multiple groups of lung imaging omics features is 40-79 years old, the set interval can be determined as 5 years old, and the age information corresponding to the multiple groups of lung imaging omics features is divided into 8 equidistant age intervals according to the set intervals, namely 40-44, 45-49, 50-54, 55-59, 60-64, 65-69, 70-74, 75-79; the number of the age intervals is numbered in increasing order of age, that is, 40-44 is numbered 1, 45-49 is numbered 2, 50-54 is numbered 3, 55-59 is numbered 4, 60-64 is numbered 5, 65-69 is numbered 6, 70-74 is numbered 7, and 75-79 is numbered 8. At the same time, those skilled in the art can select the set interval according to actual needs.

[0080] In an embodiment of the present disclosure, before dividing the set multiple lung imaging omics features into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the grading, it is determined that the set multiple lung imaging omics features are divided into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the grading, and the method for determining the set grouping rules corresponding to the grading includes: determining the lung imaging omics features corresponding to the lowest grade of the grading as the first subgroup of the multiple groups; and determining the lung imaging omics features corresponding to the other grades as the second subgroup of the multiple groups. For example, the lowest grade of the grading is COPD grade 0, and COPD grade 0 is determined as the first subgroup of the multiple groups.

[0081] In the embodiments of the present disclosure and other possible embodiments, the multiple groups may be four groups, namely, group A, group B, group C and group D, wherein group A, group B, group C and group D respectively include: COPD grade 0 and patients with COPD (COPD grade I, COPD grade II, COPD grade III, COPD grade IV), COPD grade 0 and COPD grade I, COPD grade 0 and COPD grade II, COPD grade 0 and COPD grade III & IV. Among them, the first subgroups in the first group A, group B, group C and group D are all COPD grade 0, and the second subgroups in the first group A, group B, group C and group D are patients with COPD, COPD grade I, COPD grade II, COPD grade III & IV, respectively. Among them, the multiple groups of lung imaging omics features are lung imaging omics features corresponding to the first group A, group B, group C and group D. The COPD grades III & IV are regarded as one grade, and those skilled in the art can combine adjacent COPD grades as needed and regard them as a new grade.

[0082] Figure 3 FIG. 1 is a flowchart of constructing an evaluation model according to an embodiment of the present disclosure. Figure 3 As shown, in an embodiment of the present disclosure, the method of constructing an evaluation model based on the multiple groups of lung imaging omics features and corresponding labels, respectively, includes: obtaining the multiple groups of corresponding basic evaluation models to be constructed; respectively using each group of corresponding lung imaging omics features and corresponding labels to train the respective basic evaluation models to be constructed, to obtain the evaluation models of each group.

[0083] In the embodiments of the present disclosure and other possible embodiments, the basic evaluation model to be constructed may be a survival analysis model (survival Cox model), and the corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group; the COPD risk probability is obtained based on the evaluation models of each group, and the risk assessment is performed based on the COPD risk probability. For example, the evaluation models corresponding to the first group A, the second group B, the third group C and the fourth group D are the first model, the second model, the third model and the fourth model, respectively.

[0084] In the embodiments of the present disclosure and other possible embodiments, when the basic evaluation model to be constructed is a survival analysis model, the first model can perform the survival probability from COPD grade 0 to COPD (the probability of suffering from COPD); the second model can perform the survival probability from COPD grade 0 to COPD grade I (the probability of COPD grade I); the third model can perform the survival probability from COPD grade 0 to COPD grade II (the probability of COPD grade II); the fourth model can perform the survival probability from COPD grade 0 to COPD grades III & IV (the probability of COPD grades III & IV); at the same time, the survival probability can be converted into risk probability.

[0085] Figure 4 A specific implementation flow chart of constructing an evaluation model according to an embodiment of the present disclosure is shown as follows: Figure 4As shown, the first group A, the second group B, the third group C and the fourth group D are used as examples for explanation. The basic evaluation model to be constructed is a survival analysis model (survival Cox model), respectively use the Lasso model to screen the lung imaging omics corresponding to the first group A, the second group B, the third group C and the fourth group D, and obtain the set multiple lung imaging omics features corresponding to the first group A, the second group B, the third group C and the fourth group D; at the same time, respectively divide the first group A, the second group B, the third group C and the fourth group D into multiple age intervals according to the set intervals, and number the number of the age intervals in increasing order according to the age, respectively obtain the first age interval, the second age interval, the third age interval and the fourth age interval corresponding to the first group A, the second group B, the third group C and the fourth group D (1-8); respectively divide the first group A, the second group B, the third group C and the fourth group D into a training set and a test set according to the set ratio, respectively use the training set to train the four basic assessment models to be constructed, and obtain four assessment models, and use the test set and the obtained four assessment models to perform COPD risk assessment. Among them, the set ratio is 7:3, that is, the ratio of the training set to the test set is 7:3.

[0086] In the embodiments of the present disclosure and other possible embodiments, before the respective basic evaluation models to be constructed are trained using the corresponding lung imaging omics features and corresponding labels of each group to obtain the evaluation models of each group, a set significance value is obtained; the significance value of the corresponding lung imaging omics features under the classification of each group is calculated respectively; the corresponding lung imaging omics features are further selected according to the significance value and the set significance value to obtain the lung imaging omics features used for training the basic evaluation model to be constructed. At the same time, the lung imaging omics features used for training the basic evaluation model to be constructed should be consistent with the lung imaging omics features used for testing or verifying the basic evaluation model to be constructed.

[0087] In the embodiments of the present disclosure and other possible embodiments, the method of further selecting the corresponding lung imaging omics features according to the significance value and the set significance value to obtain the lung imaging omics features for the training of the basic evaluation model to be constructed includes: if the significance value is less than or equal to the set significance value, retaining the lung imaging omics features corresponding to the significance value; otherwise, deleting the lung imaging omics features; and obtaining the lung imaging omics features for the training of the basic evaluation model to be constructed. Wherein, the set significance value can be set to any value between 0 and 1, such as 0.1, 0.05, or 0.01.

[0088] Step S103: Based on the evaluation model, evaluate COPD along with the age information.

[0089] In the embodiments of the present disclosure and other possible embodiments, before evaluating COPD along with the age information based on the evaluation model, it is necessary to obtain the set evaluation parameter values ​​of the model; if the evaluation parameter values ​​of the model meet the set evaluation parameter values, the evaluation of COPD along with the age information is performed; otherwise, the evaluation of COPD along with the age information is not performed.

[0090] In the embodiments of the present disclosure and other possible embodiments, the evaluation model is a survival analysis model, and the evaluation parameters of the model may be AUC (area under the curve) value and C index value, and the set evaluation parameter values ​​of the AUC value and the C index value may be configured to be 0.8.

[0091] Figure 5 The ROC curve and the corresponding AUC value and C index value of the evaluation model according to the embodiment of the present disclosure are shown. Figure 5 In the figure, the AUC value and C index value can be used to evaluate the effectiveness of the evaluation model. The first group A, the second group B, the third group C and the fourth group D correspond to the first model, the second model, the third model and the fourth model. Among them, the AUC value / C index value of the first model, the second model, the third model and the fourth model are 0.87 / 0.94, 0.84 / 0.83, 0.94 / 0.89, and 0.97 / 0.86, respectively. Therefore, the AUC value / Cindex value of the above-mentioned first model, the second model, the third model and the fourth model are all less than the set evaluation parameter value of 0.8, so the evaluation parameter value of the model meets the set evaluation parameter value, and the evaluation of COPD with the age information can be performed.

[0092] In the embodiments of the present disclosure and other possible embodiments, the method for evaluating COPD along with the age information based on the evaluation model includes: obtaining a probability value of COPD along with the age information based on the evaluation model; if the probability value is a risk probability, evaluating COPD along with the age information based on the risk probability; otherwise, converting the probability value into a risk probability, and evaluating COPD along with the age information based on the risk probability.

[0093] In the embodiments of the present disclosure and other possible embodiments, the evaluation model may be an evaluation model obtained by training the basic evaluation model to be constructed, such as the above-mentioned four evaluation models.

[0094] For example, the evaluation model is 4 survival analysis models, and the test set (pulmonary imaging genomics features and age information or age range) is input into the survival analysis model to obtain the probability value of the age information as the survival probability; the survival probability needs to be converted into a risk probability, and the COPD is evaluated along with the age information based on the risk probability.

[0095] In the embodiment of the present disclosure and other possible embodiments, the method of converting the survival probability into the risk probability is: risk probability = 1-survival probability. For example, the survival probability corresponding to the age interval number 8 is 0.2, and the risk probability corresponding to the age interval number 8 is 1-0.2=0.8.

[0096] For example, in the embodiments of the present disclosure Figure 4 In the method, the first model, the second model, the third model and the fourth model corresponding to the first group A, the second group B, the third group C and the fourth group D can respectively obtain the first survival probability value, the second survival probability value, the third survival probability value and the fourth survival probability value, which are respectively converted into the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value; based on the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value, the COPD is evaluated along with the age information.

[0097] Figure 6 The COPD risk probability value corresponding to the evaluation model constructed according to the embodiment of the present disclosure is shown, specifically, a scatter distribution statistical graph or trend graph of the COPD risk probability value corresponding to the evaluation model, such as Figure 6 As shown, the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value corresponding to the first model, the second model, the third model and the fourth model in their respective age intervals corresponding to the first group A, the second group B, the third group C and the fourth group D in the embodiment of the present disclosure are given. In the embodiment of the present disclosure and other possible embodiments, the method for evaluating the COPD along with the age information includes: obtaining the risk probability corresponding to the age interval under different grades of the evaluation model; classifying the corresponding risk probabilities according to the grades; obtaining the risk probabilities corresponding to the different grades in the evaluation model according to the results of the classification; drawing scatter distribution statistical graphs or trend graphs of the risk probabilities corresponding to the different grades and the age information (age interval), and then evaluating the COPD along with the age information.

[0098] In the embodiment of the present disclosure and other possible embodiments, the scatter distribution statistical graph may include: each risk probability value and its mean value, maximum value, minimum value and other information.

[0099] Specifically, in Figure 6 In the first group A, the risk probabilities obtained by the first model corresponding to COPD grade 0 and COPD patients are classified according to the grade 0 and COPD patients, and scatter distribution statistics of the risk probabilities corresponding to the grade 0 and COPD patients are obtained, such as Figure 6 Similarly, the second group B is the risk probability obtained by the first model corresponding to COPD grade 0 and COPD grade I; according to the grade 0 and COPD grade I, the corresponding risk probabilities are classified to obtain scatter distribution statistics of the risk probabilities corresponding to grade 0 and COPD grade I, respectively, as shown in FIG. Figure 6 Similarly, the third group C is the risk probability obtained by the first model corresponding to COPD grade 0 and COPD grade II; according to the grade 0 and COPD grade II, the corresponding risk probabilities are classified to obtain scatter distribution statistics of the risk probabilities corresponding to grade 0 and COPD grade II, respectively, as shown in FIG. Figure 6 Similarly, the fourth group D is the risk probability obtained by the first model corresponding to COPD grade 0 and COPD grade II; according to the grade 0 and COPD grade II, the corresponding risk probabilities are classified to obtain the scatter distribution statistics of the risk probabilities corresponding to grade 0 and COPD grade III & IV, respectively, as shown in FIG. Figure 6 As shown in (d1) and (d2) in . Figure 6 It can be seen that with increasing age, the risk probability of COPD shows an increasing trend, whether it is COPD grade 0, COPD grade I, COPD grade II, COPD grade III&IV.

[0100] Figure 7 FIG. 2 shows an age-risk curve corresponding to a COPD risk probability value constructed according to an embodiment of the present disclosure. Figure 7 As shown, specifically, the age-risk curve corresponding to the constructed COPD risk probability value is a trend graph of the age-risk curve. The significance of the trend graphs under each classification obtained by the first model, the second model, the third model and the fourth model corresponding to the first group A, the second group B, the third group C and the fourth group D is less than 0.001.

[0101] In the embodiments of the present disclosure and other possible embodiments, after obtaining the risk probabilities corresponding to different grades in the assessment model according to the classification results, the risk probabilities corresponding to different grades in the assessment model can be fitted to obtain a risk assessment fitting curve; and the risk assessment of subsequent patients can be performed based on the risk assessment fitting curve. Among them, the method of fitting the risk assessment curve can be one or more of linear least squares fitting, exponential function fitting, and power function fitting.

[0102] In an embodiment of the present disclosure, before constructing the evaluation model based on the set lung imaging omics features and the corresponding age information, the set lung imaging omics features are subjected to nonlinear processing to obtain nonlinear features; and the evaluation model is constructed based on the set lung imaging omics features, the nonlinear features and the corresponding age information. Wherein, the method of performing nonlinear processing on the set lung imaging omics features to obtain nonlinear features includes: obtaining a preset neural network; using the preset neural network, performing nonlinear processing on the set lung imaging omics features and the corresponding classification (also called the real classification, label or real value) to obtain nonlinear features.

[0103] In the embodiment of the present disclosure and other possible embodiments, the preset neural network includes: an input layer, a hidden layer connected to the input layer, and an input layer connected to the hidden layer. In the embodiment of the present disclosure, the number of hidden layers can be set to 2. The method of performing nonlinear processing on the set lung imaging genomics features to obtain nonlinear features also includes: obtaining a loss function corresponding to the basic evaluation model to be constructed; based on the preset neural network, predicting the corresponding grade of the set lung imaging genomics features, and the loss function uses the predicted grade and the actual grade to train the preset neural network to obtain nonlinear features.

[0104] Figure 8 A flow chart showing a method for making a decision on the risk of chronic obstructive pulmonary disease according to an embodiment of the present disclosure is shown. Figure 8 As shown, the risk decision-making method for COPD includes: the evaluation method as mentioned above; step S201: obtaining the risk assessment result of COPD, wherein the risk assessment result at least includes: the risk probability and its corresponding COPD grade and age information; step S202: dividing the risk of COPD according to the set zoning rules to obtain the risk level; step S203: making a risk decision for COPD based on the risk assessment result and the risk level to obtain the age information corresponding to the risk interval.

[0105] In the embodiments of the present disclosure and other possible embodiments, the method for determining the set partitioning rules includes: obtaining the number of divided risk levels and setting the risk interval; determining the set partitioning rules for the set risk interval according to the number. For example, the set risk interval is 0-1, and the number of divided risk levels is 4. Then, according to the set partitioning rules, the risk of COPD is divided, and the number of risk levels obtained is 4, namely the first risk level, the second risk level, the third risk level, and the fourth risk level. For example, the intervals of the first risk level, the second risk level, the third risk level, and the fourth risk level are [0,0.25), [0.25,0.5), [0.5,0.75), [0.75,1), respectively. Obviously, those skilled in the art can set the number and the set risk interval according to actual needs.

[0106] In the embodiments of the present disclosure and other possible embodiments, the method of making a risk decision for COPD based on the risk assessment result and the risk level to obtain the age information corresponding to the risk interval includes: obtaining the average value of the risk probability of the risk assessment result in the age interval; making a risk decision for COPD based on the average value and the risk level to obtain the age information corresponding to the risk interval.

[0107] In the embodiments of the present disclosure and other possible embodiments, the method of making a risk decision for COPD based on the average value and the risk level to obtain the age information (age interval) corresponding to the risk interval includes: if the average values ​​corresponding to adjacent age information (age intervals) are respectively within different risk levels, then the COPD grade and age information (age interval) corresponding to the average value are determined to obtain the age information (age interval) of the corresponding COPD grade. Among them, the age information (age interval) is the age information (age interval) for the age information (age interval) risk decision. Before this age information (age interval), it is necessary to prevent and treat COPD or increase exercise to prevent COPD or prevent the aggravation of COPD.

[0108] Fig. 9 A risk decision diagram of age-risk corresponding to COPD of different grades and COPD grade 0 (no COPD) according to an embodiment of the present disclosure is shown. Fig. 9As shown in (A), the COPD risk probability of patients with COPD grades Ⅰ, Ⅱ, Ⅲ & Ⅳ increases with age. Specifically, in the 1st-4th age range, patients with COPD, COPD grades Ⅰ, Ⅱ, and Ⅲ & Ⅳ are basically at mild risk (first risk level). On the other hand, these patients are at moderate risk (second risk level) in the 5th age range, at severe risk (third risk level) in the 6th age range, and at extreme risk (fourth risk level) in the 7th-8th age range. Fig. 9 As shown in (B), the COPD risk of subjects with COPD grade 0 in the four groups increased with age. In general, within the same age range, the risk of COPD in subjects with COPD grade 0 was COPD grade I, grade II, and grade III & IV. With increasing age, the risk of subjects with possible COPD was higher than that of COPD grades I, II, III & IV. Similarly, the risk of subjects with possible COPD grade I was greater than that of COPD grade II, and with increasing age, the risk of subjects with possible COPD grade II was greater than that of aging subjects with COPD grades III & IV. Specifically, for subjects with COPD grade 0, the COPD risk in the 1st to 5th age range of the first group A and the second group B and the 1st to 6th age range of the third group C and the fourth group D was a mild risk (first risk level). The COPD risk in the 6th age range of the first group A, the 6th to 7th age range of the second group B, and the 7th age range of groups C and D was a moderate risk (second risk level). The COPD risk was severe in the 7th-8th age interval in Groups 1A and 2B and in the 8th age interval in Groups C and D. The COPD risk of subjects with COPD grade I (10 years: 6th-7th age interval) progressed slower than that of subjects with COPD grades II and III & IV (5 years: 7th age interval) at the moderate risk level. However, COPD risk did not progress to the extreme risk level (4th risk interval) before the age of 79.

[0109] For subjects with COPD, namely COPD grade I, grade II, and grade III & IV, although the risk of COPD increases with age, patients with COPD, COPD grade I, grade II, and grade III & IV, have basically the same age range in all risk levels. Therefore, age is not only a time point to distinguish "young COPD" (young COPD patients under the age of 50) from non-young COPD, but also can distinguish different COPD risk levels. Regardless of which COPD stage, before the age of 60, it is considered a relatively safe COPD risk level (mild risk, first risk level). For subjects after the age of 60, the pattern of COPD risk level increasing with age is also revealed. The risk level of these subjects increases every five years. Therefore, once COPD patients are over 60 years old, they need to be closely monitored to prevent the progression and deterioration of COPD. If necessary, artificial intervention should be considered, including the addition of appropriate practical exercise and COPD care treatment in the hospital.

[0110] For subjects in COPD grade 0, the COPD risk of possible COPD, COPD grade I, II, and III & IV also increases with age. Our study found that starting from COPD grade 0, the age intervals of each COPD risk level of possible COPD, COPD grade I, grade II, and III & IV are inconsistent. Age can distinguish different COPD risk levels. For subjects with possible COPD and COPD grade I before the age of 65, this is a relatively safe COPD risk level (mild risk). For subjects with possible COPD grade II and III & IV before the age of 70, this is also a relatively safe COPD risk level. For subjects with COPD grade 0, the risk level of COPD grade I increases once every five years after the age of 65, and the risk level of COPD grade II and grade III, IV increases once every five years after the age of 70. Therefore, 65 years old is the starting age for the increase in risk of subjects with possible COPD grade stage, and 70 years old is the starting age for the increase in risk of subjects with possible COPD grade II and grade III & IV. Although COPD risk does not reach extreme risk levels, COPD stage 0 subjects also need to take preventive measures once they are over 65 or 70 years old.

[0111] The execution subject of the risk assessment method for COPD and / or the risk decision method for COPD may be an image processing device, for example, the risk assessment method for COPD and / or the risk decision method for COPD may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the risk assessment method for COPD and / or the risk decision method for COPD may be implemented by a processor calling computer-readable instructions stored in a memory.

[0112] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0113] An embodiment of the present disclosure also proposes a risk assessment device for COPD, which includes: a first acquisition unit, used to acquire a set of multiple lung imaging genomics features and age information corresponding to COPD at different levels; a construction unit, used to construct an assessment model based on the set lung imaging genomics features and the corresponding age information; and an assessment unit, used to evaluate COPD along with the age information based on the assessment model.

[0114] In addition, an embodiment of the present disclosure also proposes a risk decision-making device for COPD, and the risk assessment device for COPD includes: the above-mentioned risk assessment device for COPD; the risk assessment device for COPD is used to generate a risk assessment result for COPD; wherein the risk assessment result at least includes: the risk probability and its corresponding COPD grade and age information; a second acquisition unit is used to obtain the risk assessment result of COPD, a risk level unit is used to divide the risk of COPD according to the set partitioning rules to obtain the risk level; a risk decision unit is used to make a risk decision for COPD based on the risk assessment result and the risk level, and obtain the age information corresponding to the risk interval.

[0115] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0116] The embodiment of the present disclosure also provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above method is implemented. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0117] The embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to perform the above method. The electronic device can be provided as a terminal, a server or other forms of equipment.

[0118] Fig.10 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0119] Reference Fig.10 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0120] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0121] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0122] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0123] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0124] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0125] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0126] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of the components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0127] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0128] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0129] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above method.

[0130] Fig.11 1 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Fig.11, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions that can be executed by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0131] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0132] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0133] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0134] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0135] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0136] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0137] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0138] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0139] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0140] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0141] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for risk assessment of chronic obstructive pulmonary disease, characterized in that: include: Acquire multiple set lung imaging omics features and age information corresponding to COPD at different grades; wherein, before acquiring the multiple set lung imaging omics features corresponding to COPD at different grades, determine the multiple set lung imaging omics features, and the method comprises: using a set screening model and a set screening rule to screen the multiple lung imaging omics features corresponding to COPD at different grades, and obtain the multiple set lung imaging omics features; wherein the set screening rule at least comprises: the grade of COPD; wherein, using a set screening model and a set screening rule to screen the multiple lung imaging omics features corresponding to COPD at different grades, and obtain the method comprises: determining the COPD grade and the imaging omics to be screened corresponding to the COPD grade according to the set screening rule; using the set screening model to establish the relationship between the COPD grade and the imaging omics to be screened corresponding to the COPD grade, and obtain the multiple set lung imaging omics features; An evaluation model is constructed based on the set multiple lung imaging omics features and the corresponding age information; wherein the method for constructing an evaluation model based on the set multiple lung imaging omics features and the corresponding age information comprises: dividing the set multiple lung imaging omics features into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the classification, and dividing the age information corresponding to the multiple groups of lung imaging omics features into multiple age intervals according to the set intervals, and numbering the number of the age intervals in increasing order of age; constructing evaluation models based on the multiple groups of lung imaging omics features and the corresponding labels respectively; wherein the corresponding basic evaluation model to be constructed before the training or construction of the evaluation model is configured as a survival analysis model; Based on the evaluation model, an evaluation of COPD along with the age information is performed; wherein, the method for evaluating COPD along with the age information based on the evaluation model comprises: obtaining a survival probability value of COPD along with the age information based on the evaluation model; converting the survival probability value into a risk probability, and evaluating COPD along with the age information based on the risk probability; wherein, the risk probability = 1 - the survival probability.

2. The evaluation method according to claim 1, characterized in that: Before obtaining the set multiple lung imaging features corresponding to COPD at different levels, the method for determining the set multiple lung imaging features further includes: Before screening the multiple lung imaging omics features corresponding to COPD at different levels by using the set screening model and the set screening rules, the set screening model and the multiple lung imaging omics features corresponding to COPD at different levels are obtained.

3. The evaluation method according to any one of claims 1 or 2, characterized in that: Before determining the COPD grade and the imaging omics to be screened corresponding to the COPD grade according to the set screening rules, the COPD grade is respectively encoded 0-1, and the relationship between the 0-1 encoded COPD grade and the imaging omics to be screened corresponding to the COPD grade is established using the set screening model to obtain the set multiple lung imaging omics features.

4. The evaluation method according to any one of claims 1 or 2, characterized in that: Before obtaining the multiple lung imaging features corresponding to the set screening model and COPD at different levels, it is necessary to segment the lung area as the region of interest to obtain the lung area segmentation image; The lung region segmentation image is configured as one or more of a lung region segmentation image of a left lung, a lung region segmentation image of a right lung, or a lung region segmentation image of both the left lung and the right lung.

5. The evaluation method according to claim 3, characterized in that: Before obtaining the multiple lung imaging features corresponding to the set screening model and COPD at different levels, it is necessary to segment the lung area as the region of interest to obtain the lung area segmentation image; The lung region segmentation image is configured as one or more of a lung region segmentation image of a left lung, a lung region segmentation image of a right lung, or a lung region segmentation image of both the left lung and the right lung.

6. The evaluation method according to claim 4, characterized in that: The method for determining the multiple lung imaging features comprises: The lung region segmentation image and its corresponding original chest image are input into a lung imaging omics calculation model to calculate the lung imaging omics corresponding to the lung region segmentation image in the original chest image.

7. The evaluation method according to claim 5, characterized in that: The method for determining the multiple lung imaging features comprises: The lung region segmentation image and its corresponding original chest image are input into a lung imaging omics calculation model to calculate the lung imaging omics corresponding to the lung region segmentation image in the original chest image.

8. The evaluation method according to any one of claims 4 or 5, characterized in that: The method of inputting the lung region segmentation image and the corresponding original chest image into the lung imaging omics calculation model to calculate the lung imaging omics corresponding to the lung region segmentation image in the original chest image comprises: Extracting a lung parenchyma image based on the lung region segmentation image and its corresponding original chest image to obtain an original lung parenchyma image; Acquire a set filter, and use the set filter to filter the original lung parenchyma image to obtain a derived lung parenchyma image; Based on the set class of the acquired radiomics features, lung radiomics calculation is performed on the original lung parenchyma image and the derived lung parenchyma image to obtain a plurality of lung radiomics features.

9. The evaluation method according to claim 8, characterized in that: The set filter configuration is one or more of a wavelet filter and a LoG filter.

10. The evaluation method according to any one of claims 1, 2, 5-7, and 9, characterized in that: The method for determining the set grouping rules corresponding to the classification includes: determining the lung radiomics features corresponding to the lowest grade of the grades as a first subgroup of the plurality of groups; The lung radiomics features corresponding to other grades are respectively determined as the second subgroups of the multiple groups.

11. The evaluation method according to claim 3, characterized in that: The method for determining the set grouping rules corresponding to the classification includes: determining the lung radiomics features corresponding to the lowest grade of the grades as a first subgroup of the plurality of groups; The lung imaging features corresponding to other grades are respectively determined as the second subgroups of the multiple groups.

12. The evaluation method according to claim 4, characterized in that: The method for determining the set grouping rules corresponding to the classification includes: determining the lung radiomics features corresponding to the lowest grade of the grades as a first subgroup of the plurality of groups; The lung radiomics features corresponding to other grades are respectively determined as the second subgroups of the multiple groups.

13. The evaluation method according to claim 8, characterized in that: The method for determining the set grouping rules corresponding to the classification includes: determining the lung radiomics features corresponding to the lowest grade of the grades as a first subgroup of the plurality of groups; The lung radiomics features corresponding to other grades are respectively determined as the second subgroups of the multiple groups.

14. The evaluation method according to any one of claims 1, 2, 5-7, 9, 11-13, characterized in that: The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes: Obtaining the multiple groups of corresponding basic evaluation models to be constructed; The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

15. The evaluation method according to claim 3, characterized in that: The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes: Obtaining the multiple groups of corresponding basic evaluation models to be constructed; The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

16. The evaluation method according to claim 4, characterized in that: The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes: Obtaining the multiple groups of corresponding basic evaluation models to be constructed; The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

17. The evaluation method according to claim 8, characterized in that: The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes: Obtaining the multiple groups of corresponding basic evaluation models to be constructed; The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

18. The evaluation method according to claim 10, characterized in that: The method of constructing an evaluation model based on the multiple groups of lung imaging features and corresponding labels respectively includes: Obtaining the multiple groups of corresponding basic evaluation models to be constructed; The corresponding lung imaging omics features and corresponding labels of each group are used to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group.

19. The evaluation method according to claim 14, characterized in that: Before respectively using the corresponding lung imaging omics features and corresponding labels of each group to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group, obtaining a set significance value; Calculating the significance value of the corresponding lung imaging features under the classification of each group respectively; The corresponding lung imaging omics features are further selected according to the significance value and the set significance value to obtain lung imaging omics features for training the basic evaluation model to be constructed.

20. The evaluation method according to any one of claims 15 to 18, characterized in that: Before respectively using the corresponding lung imaging omics features and corresponding labels of each group to train the respective basic evaluation models to be constructed to obtain the evaluation models of each group, obtaining a set significance value; Calculating the significance value of the corresponding lung imaging features under the classification of each group respectively; The corresponding lung imaging omics features are further selected according to the significance value and the set significance value to obtain lung imaging omics features for training the basic evaluation model to be constructed.

21. The evaluation method according to claim 19, characterized in that: The method of further selecting the corresponding lung imaging omics features according to the significance value and the set significance value to obtain the lung imaging omics features for training the basic evaluation model to be constructed includes: If the significance value is less than or equal to the set significance value, retaining the lung imaging features corresponding to the significance value; Otherwise, the lung imaging features are deleted; and the lung imaging features used for training the basic evaluation model to be constructed are obtained.

22. The evaluation method according to claim 20, characterized in that: The method of further selecting the corresponding lung imaging omics features according to the significance value and the set significance value to obtain the lung imaging omics features for training the basic evaluation model to be constructed includes: If the significance value is less than or equal to the set significance value, retaining the lung imaging features corresponding to the significance value; Otherwise, the lung imaging features are deleted; and the lung imaging features used for training the basic evaluation model to be constructed are obtained.

23. The evaluation method according to any one of claims 1, 2, 5-7, 9, 11-13, 15-19, 21, and 22, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

24. The evaluation method according to claim 3, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

25. The evaluation method according to claim 4, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

26. The evaluation method according to claim 8, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

27. The evaluation method according to claim 10, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

28. The evaluation method according to claim 14, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

29. The evaluation method according to claim 20, characterized in that: Before constructing the evaluation model based on the set multiple lung imaging omics features and the corresponding age information, nonlinear processing is performed on the set multiple lung imaging omics features to obtain nonlinear features; An evaluation model is constructed based on the set multiple lung imaging features, the nonlinear features and the corresponding age information.

30. The evaluation method according to any one of claims 1, 2, 5-7, 9, 11-13, 15-19, 21, 22, 24-29, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

31. The evaluation method according to claim 3, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

32. The evaluation method according to claim 4, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

33. The evaluation method according to claim 8, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

34. The evaluation method according to claim 10, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

35. The evaluation method according to claim 14, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

36. The evaluation method according to claim 20, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

37. The evaluation method according to claim 23, characterized in that: The method for evaluating COPD along with the age information further includes: Obtain the risk probability corresponding to the age range under different classifications of the assessment model; Classifying the corresponding risk probabilities according to the classification; According to the classification results, the risk probabilities corresponding to different levels in the assessment model are obtained; Scatter distribution statistical graphs or trend graphs of the risk probabilities and age ranges corresponding to the different grades are drawn respectively to evaluate COPD along with the age information.

38. The evaluation method according to claim 30, characterized in that: After obtaining the risk probabilities corresponding to different levels in the assessment model according to the classification results, the risk probabilities corresponding to different levels in the assessment model are fitted to obtain a risk assessment fitting curve; A risk assessment is performed on the patient based on the risk assessment fitting curve.

39. The evaluation method according to any one of claims 31 to 37, characterized in that: After obtaining the risk probabilities corresponding to different levels in the assessment model according to the classification results, the risk probabilities corresponding to different levels in the assessment model are fitted to obtain a risk assessment fitting curve; A risk assessment is performed on the patient based on the risk assessment fitting curve. 40.A risk decision-making method for chronic obstructive pulmonary disease, comprising: The evaluation method according to any one of claims 1 to 39, characterized in that: Obtaining a risk assessment result of COPD, wherein the risk assessment result at least includes: risk probability and its corresponding COPD grade and age range; According to the set zoning rules, the risk of COPD is divided to obtain the risk level; Based on the risk assessment result and the risk level, a risk decision for COPD is made to obtain an age range corresponding to the risk range.

41. The risk decision-making method according to claim 40, characterized in that: The method of making a risk decision for COPD based on the risk assessment result and the risk level to obtain an age range corresponding to the risk range includes: Obtaining an average value of the risk probability of the risk assessment result in the age range; A risk decision for COPD is made based on the average value and the risk level, and an age range corresponding to the risk range is obtained.

42. The risk decision-making method according to claim 41, characterized in that: The method of making a risk decision for COPD based on the average value and the risk level to obtain an age range corresponding to the risk range includes: If the average values ​​corresponding to adjacent age intervals are respectively within different risk levels, the COPD grade and age interval corresponding to the average values ​​are determined to obtain the corresponding COPD grade age interval.

43. A risk assessment device for chronic obstructive pulmonary disease, characterized in that: include: A first acquisition unit is used to acquire a plurality of set lung imaging omics features and age information corresponding to COPD at different grades; wherein, before acquiring the plurality of set lung imaging omics features corresponding to COPD at different grades, determining the plurality of set lung imaging omics features, including: using a set screening model and a set screening rule to screen the plurality of lung imaging omics features corresponding to COPD at different grades, to obtain the plurality of set lung imaging omics features; wherein the set screening rule at least includes: the grade of COPD; wherein, using the set screening model and the set screening rule to screen the plurality of lung imaging omics features corresponding to COPD at different grades, to obtain the plurality of set lung imaging omics features, including: determining the COPD grade and the imaging omics to be screened corresponding to the COPD grade according to the set screening rule; using the set screening model to establish the relationship between the COPD grade and the imaging omics to be screened corresponding to the COPD grade, to obtain the plurality of set lung imaging omics features; A construction unit, for constructing an evaluation model based on the set multiple lung imaging omics features and the corresponding age information; wherein, the construction of the evaluation model based on the set multiple lung imaging omics features and the corresponding age information includes: dividing the set multiple lung imaging omics features into multiple groups of lung imaging omics features according to the set grouping rules corresponding to the classification, and dividing the age information corresponding to the multiple groups of lung imaging omics features into multiple age intervals according to the set intervals, and numbering the number of the age intervals in increasing order of age; constructing the evaluation model based on the multiple groups of lung imaging omics features and the corresponding labels respectively; wherein, the corresponding basic evaluation model to be constructed before the training or construction of the evaluation model is configured as a survival analysis model; An evaluation unit is used to evaluate COPD along with the age information based on the evaluation model; wherein, the evaluation of COPD along with the age information based on the evaluation model comprises: obtaining a survival probability value of COPD along with the age information based on the evaluation model; converting the survival probability value into a risk probability, and evaluating COPD along with the age information based on the risk probability; wherein, the risk probability = 1 - the survival probability.

44. A risk decision-making device for chronic obstructive pulmonary disease, characterized in that: include: The risk assessment device for chronic obstructive pulmonary disease according to claim 43; The COPD risk assessment device is used to generate a COPD risk assessment result; wherein the risk assessment result at least includes: risk probability and its corresponding COPD grade and age information; The second acquisition unit is used to obtain the risk assessment results of COPD. The risk level unit is used to divide the risk of COPD according to the set zoning rules to obtain the risk level; The risk decision unit is used to make a risk decision for COPD based on the risk assessment result and the risk level, and obtain age information corresponding to the risk interval.

45. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to call the instructions stored in the memory to execute the risk assessment method for COPD as described in any one of claims 1 to 39.

46. ​​An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to call the instructions stored in the memory to execute the risk decision method for COPD as described in any one of claims 40-42.

47. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to call the instructions stored in the memory to execute the risk assessment method for COPD described in any one of claims 1 to 39 and the risk decision-making method for COPD described in any one of claims 40-42.

48. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the risk assessment method for COPD described in any one of claims 1 to 39 is implemented.

49. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the risk decision method for COPD described in any one of claims 40-42 is implemented.

50. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by the processor, the risk assessment method for COPD described in any one of claims 1 to 39 and the risk decision-making method for COPD described in any one of claims 40-42 are implemented.

Images