COPD early warning method and system based on chest CT parameters

Abstract

The invention relates to the technical field of medical images, in particular to a COPD early warning method and system based on chest CT parameters, and the method comprises the following steps: based on chest CT image data, extracting pixel data of a lung lobe anatomical region, segmenting an airway tree structure, recognizing a bronchial wall boundary, screening gradient change points, and generating an airway wall boundary point set. According to the method, the lung lobe anatomical area is refined, the airway tree structure is segmented, the boundary of the bronchial wall is accurately positioned, the thickness of the airway wall is calculated, abnormal fluctuation is corrected, the stability of the thickness parameter is improved, the sectional area of the airflow channel is calculated through the thickness parameter, the lung lobe ventilation capacity and ventilation change are analyzed, the lung ventilation imbalance degree is quantified, and the ventilation limited area is screened; analyzing the relationship between the wall thickness and the ventilation change rate, extracting an abnormal growth region, calibrating the ventilation limitation severity, setting an early warning threshold value, calculating an abnormal index mean value, marking a risk region, enhancing the ventilation abnormality recognition hierarchy, and improving the COPD early warning capability.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and in particular to a COPD early warning method and system based on chest CT parameters. Background Art

[0002] The field of medical imaging technology involves the use of imaging technology to visualize the structure and function of various parts of the human body. The core content of this field includes the early identification of different diseases, disease monitoring, and lesion assessment based on medical imaging. Medical imaging technology is widely used in multiple disciplines. It mainly involves the use of imaging equipment such as CT, MRI, and X-rays to obtain high-resolution images, and through image processing, analysis, and optimization technologies, to extract and analyze image data in order to evaluate and study health conditions. The core goal of medical imaging technology is to provide accurate visual information to assist research and application in related medical fields.

[0003] Among them, the COPD early warning method based on chest CT parameters refers to extracting characteristic parameters related to COPD (chronic obstructive pulmonary disease) by processing chest CT image data, thereby providing support for COPD early warning. The subject of this patent involves using imaging data obtained from CT images, combined with medical imaging analysis methods, to conduct a detailed analysis of lung structure and extract key parameters such as lung ventilation, lung morphology, and airway diameter. Through a comprehensive evaluation of parameters and based on quantitative data analysis, early warning information for COPD is generated, thereby helping relevant personnel identify potential risks early. This patent addresses how to effectively assess the potential risks of COPD through CT imaging data and issue early warnings through quantitative analysis, avoiding over-reliance on traditional imaging methods and subjective judgments.

[0004] Existing technologies rely on static analysis methods of medical images. The assessment of lung structure and airway morphology is overly dependent on visual features of images, and a stable quantitative analysis system has not been established. The assessment of airway wall thickness is affected by subjective judgment and cannot accurately reflect the subtle structural changes in the lesion site. The degree of ventilation limitation cannot be effectively correlated with the dynamic changes in airway wall thickness, resulting in one-sided risk assessment. Pulmonary ventilation analysis is mainly based on the overall ventilation function of the lungs, and fails to refine the spatial distribution of ventilation status in each region, ignoring the development trend of local ventilation abnormalities. The identification method of ventilation-restricted areas fails to accurately match the development process of airway lesions, and no effective risk index calculation model is provided, resulting in a lag in COPD warning. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a COPD early warning method and system based on chest CT parameters.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a COPD early warning method based on chest CT parameters, comprising the following steps: S1: Based on chest CT image data, extract pixel data of the lung lobe anatomical area, segment the airway tree structure, identify the bronchial wall boundary, filter the gradient change points, and generate the airway wall boundary point set; S2: Based on the airway wall boundary point set, extract the boundary points of the measurement area within the bronchial branch area, identify the local curvature radius, adjust the measurement path direction, analyze the pixel gradient changes of adjacent points on the measurement path, select boundary points that meet the measurement conditions, calculate the pixel gradient change rate, correct abnormal fluctuations, and obtain airway wall thickness parameters; S3: calling the airway wall thickness parameter, segmenting the alveolar ventilation area, calculating the airflow channel cross-sectional area data, analyzing the lobe ventilation and ventilation variation, and obtaining the pulmonary ventilation imbalance coefficient; S4: calling the lung ventilation imbalance coefficient, screening the ventilation-restricted area, analyzing the thickness and ventilation change rate, extracting the abnormal growth area, and obtaining the airway wall ventilation coupling abnormality index; S5: Call the airway wall ventilation coupling abnormality index, screen the abnormal distribution area, set the warning threshold, calculate the average of the abnormal index, mark the area exceeding the threshold and issue a warning, and output a COPD risk warning response.

[0007] As a further solution of the present invention, the airway wall boundary point set includes bronchial wall boundary points, gradient change points, and pixel gradient change rates; the airway wall thickness parameters include measurement area boundary points, local curvature radius, and adjacent point pixel gradient changes; the lung ventilation imbalance coefficient includes alveolar ventilation area, airflow channel cross-sectional area data, and lobe ventilation change amplitude; the airway wall ventilation coupling abnormality index includes ventilation-restricted area, thickness change rate, and ventilation change rate; the COPD risk warning response includes abnormal distribution area, abnormal index mean, and exceeding threshold area.

[0008] As a further solution of the present invention, the step of obtaining the airway wall boundary point set is specifically as follows: S111: extracting pixel data of the anatomical region of the lung lobe based on the chest CT image data, calculating the pixel gradient change of the region, screening the pixel points that meet the threshold, and generating a set of pixel gradient change points of the lung lobe; S112: Based on the set of lung lobe pixel gradient change points, segment the airway tree structure, extract boundary pixel points, calculate the gradient direction vector, filter the gradient change rate, and generate a set of airway wall candidate points; S113: Based on the airway wall candidate point set, calculate the local gradient mean of the boundary point, analyze the gradient distribution, identify the spatial offset, and use the formula based on the relationship between the gradient and the offset: ; Calculate the boundary gradient offset coefficient of the airway wall boundary points, screen the boundary points that meet the threshold, and generate an airway wall boundary point set; in, Represents the boundary gradient offset coefficient of the airway wall boundary point, Represents candidate boundary points of the airway wall The gradient value at represents the mean gradient of the candidate boundary points, and Representing boundary points The offset in the horizontal and vertical directions, Represents a small positive number used to avoid the denominator being zero, Represents the total number of candidate boundary points of the airway wall.

[0009] As a further solution of the present invention, the step of obtaining the airway wall thickness parameter is specifically as follows: S211: Based on the airway wall boundary point set, extract measurement boundary points in the bronchial branch area, calculate local gradient change values ​​of the boundary points, and screen boundary points that meet a set threshold to obtain a measurement area boundary point set; S212: Based on the measurement area boundary point set, adjust the measurement path direction, match the local curvature trend, analyze the pixel gradient changes of adjacent points on the path, and use the formula: ; Calculate the gradient curvature value of the measurement path, screen the boundary points that meet the measurement conditions, and generate a measurement path boundary point set; in, Represents the gradient curvature value of the measurement path, Represent the gradient values ​​of the differentiated boundary points on the measurement path, Represents the horizontal and vertical offset of the corresponding boundary point, Represents small positive numbers used to avoid denominators being zero; S213: Based on the measurement path boundary point set, analyze the pixel gradient change rate, correct abnormal fluctuations, call the corrected gradient change rate data, calculate the local thickness data of the boundary points, and obtain the airway wall thickness parameter.

[0010] As a further solution of the present invention, the step of obtaining the pulmonary ventilation imbalance coefficient is specifically as follows: S311: Segmenting the alveolar ventilation area based on the airway wall thickness parameter, calculating the local airflow channel cross-sectional area of ​​each area, screening the area based on the regional airflow channel morphological characteristics, removing outliers, and obtaining airflow channel cross-sectional area data; S312: Call the airflow channel cross-sectional area data to identify the corresponding lobe ventilation volume, and perform normalization processing on the lobe ventilation volume using the formula: ; The ventilation change amplitude of the lung lobe is calculated; in, Represents the ventilation change amplitude of the lung lobe, Represents the current lobe ventilation, represents initial lobar ventilation; S313: Based on the ventilation change amplitude of the lung lobes, the degree of difference between the lung lobes is analyzed, and the lung ventilation imbalance coefficient is obtained in combination with the lung lobes' lung ventilation volumes.

[0011] As a further solution of the present invention, the step of obtaining the airway wall ventilation coupling abnormality index is specifically as follows: S411: calling the lung ventilation imbalance coefficient, screening the area with uneven ventilation distribution between each lung lobe, eliminating the area within the ventilation balance range, and obtaining the ventilation restricted area; S412: Based on the ventilation-restricted area, calculate the airway wall thickness in the area and monitor the rate of change of ventilation over time using the formula: ; The ventilation change rate value is calculated; in, Indicates the ventilation change rate value, Representative Moment The ventilation volume, Representative Moment The ventilation volume, represents the total time interval; S413: Analyze the change trend of the ventilation change rate value and the airway wall thickness, extract the abnormal growth area, and calculate the airway wall ventilation coupling abnormality index.

[0012] As a further embodiment of the present invention, the steps for obtaining the COPD risk warning response are specifically as follows: S511: Based on the airway wall ventilation coupling abnormality index, the airway wall thickness, ventilation distribution value, and local flow value are called to calculate the abnormal distribution value, and the abnormal area exceeding the threshold is screened to obtain the average value of the abnormal area; S512: Compare the mean value of the abnormal area with the warning threshold, extract the area beyond the warning range, call the ventilation distribution state and the local resistance coefficient, and filter to obtain the data of the area beyond the threshold; S513: Based on the data of the area exceeding the threshold, the environmental variables and the sample data are called, and the formula is used: ; Calculate the mean of COPD abnormal index and output COPD risk warning response; in, represents the mean value of COPD abnormal index, Representative The abnormal index value of the sample, represents the mean of the sample anomaly index, represents the total number of samples, A measure of the degree of sample bias.

[0013] A COPD early warning system based on chest CT parameters, the COPD early warning system based on chest CT parameters being used to implement the above-mentioned COPD early warning method based on chest CT parameters, the system comprising: The anatomical region analysis module extracts lung pixel data based on chest CT image data, screens lung parenchyma boundaries, segments bronchial tree structures, analyzes grayscale gradients, detects bronchial wall boundaries, analyzes gradient changes at boundary points, calculates bronchial branching angles, and obtains bronchial wall boundary point sets. The airway wall thickness calculation module extracts the boundary points of the measurement area based on the bronchial wall boundary point set, calculates the radial distance of the lumen, analyzes the grayscale gradient, selects boundary points that meet the standards, calculates the thickness difference between boundary points, analyzes local thickness changes, analyzes the thickness distribution of continuous cross-sections of the bronchial wall, adjusts abnormal fluctuation sections, corrects the measurement path, and statistically analyzes the differentiated branch thickness change characteristics to obtain airway wall thickness parameters; The pulmonary airflow distribution analysis module calculates the cross-sectional area of ​​the airway branches based on the airway wall thickness parameter, counts the changes in the ventilation channels of the pulmonary lobes, analyzes the differences in airway ventilation flow rates, and obtains the distribution data of pulmonary ventilation limitation; The ventilation abnormality identification module screens abnormal areas based on the lung ventilation limitation distribution data, analyzes the corresponding relationship between the wall thickness change rate and the ventilation limitation rate, extracts areas with increased ventilation resistance, identifies the ventilation balance of the lung lobes, and obtains the airway wall ventilation abnormality index; The COPD risk grading module sets a warning threshold based on the airway wall ventilation abnormality index, screens the super-threshold area, calculates the spatial distribution, screens the risk area and issues a warning, and obtains a COPD risk warning response.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by parsing chest CT image data, refining the anatomical areas of the lung lobes, segmenting the airway tree structure, and screening key gradient change points, the precise positioning of the bronchial wall boundaries is ensured. Based on the boundary point set, the boundary points of the measurement area are extracted, the airway wall thickness is calculated, and abnormal fluctuations are corrected to improve the stability and continuity of the thickness parameters. The thickness parameters are used to calculate the cross-sectional area of ​​the airflow channel in the alveolar ventilation area, analyze the lung lobe ventilation volume and ventilation changes, accurately quantify the pulmonary ventilation imbalance, further screen the ventilation-restricted areas, analyze the correlation between the airway wall thickness and the ventilation change rate, extract the abnormal growth areas, calibrate the severity of ventilation restriction, and finally set the warning threshold, calculate the mean of the abnormal index, mark the risk areas and generate a warning plan to realize quantitative COPD risk assessment based on CT images, optimize the image data extraction method, enhance the accuracy of airway wall thickness measurement, establish a systematic evaluation mechanism for pulmonary ventilation characteristics, make ventilation abnormality identification more hierarchical, and improve the early warning capability of COPD. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a flow chart for obtaining the airway wall boundary point set in the present invention; Figure 3 This is a flow chart for obtaining airway wall thickness parameters in the present invention; Figure 4 This is a flow chart for obtaining the lung ventilation imbalance coefficient in the present invention; Figure 5 This is a flow chart for obtaining the airway wall ventilation coupling abnormality index in the present invention; Figure 6 This is a flow chart for obtaining COPD risk warning response in the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0018] Example 1 See also Figure 1 The present invention provides a technical solution: a COPD early warning method based on chest CT parameters, comprising the following steps: S1: Based on chest CT image data, extract pixel data of the lung lobe anatomical area, segment the airway tree structure, identify the bronchial wall boundary, filter the gradient change points, and generate the airway wall boundary point set; S2: Based on the airway wall boundary point set, the boundary points of the measurement area within the bronchial branch area are extracted, the local curvature radius is identified, the measurement path direction is adjusted, the pixel gradient changes of adjacent points on the measurement path are analyzed, the boundary points that meet the measurement conditions are selected, the pixel gradient change rate is calculated, abnormal fluctuations are corrected, and the airway wall thickness parameters are obtained; S3: Call the airway wall thickness parameter, segment the alveolar ventilation area, calculate the airflow channel cross-sectional area data, analyze the lobe ventilation and ventilation change amplitude, and obtain the lung ventilation imbalance coefficient; S4: Call the lung ventilation imbalance coefficient, screen the ventilation-restricted area, analyze the thickness and ventilation change rate, extract the abnormal growth area, and obtain the airway wall ventilation coupling abnormality index; S5: Call the airway wall ventilation coupling abnormality index, screen the abnormal distribution area, set the warning threshold, calculate the average of the abnormal index, mark the area exceeding the threshold and issue a warning, and output the COPD risk warning response.

[0019] The airway wall boundary point set includes bronchial wall boundary points, gradient change points, and pixel gradient change rates. The airway wall thickness parameters include the measurement area boundary points, local curvature radius, and pixel gradient changes of adjacent points. The lung ventilation imbalance coefficient includes the alveolar ventilation area, airflow channel cross-sectional area data, and lobe ventilation change amplitude. The airway wall ventilation coupling abnormality index includes the ventilation-restricted area, thickness change rate, and ventilation change rate. The COPD risk warning response includes the abnormal distribution area, abnormal index mean, and the area exceeding the threshold.

[0020] See also Figure 2 , the steps for obtaining the airway wall boundary point set are as follows: S111: extracting pixel data of the anatomical region of the lung lobe based on the chest CT image data, calculating the pixel gradient change of the region, screening the pixel points that meet the threshold, and generating a set of pixel gradient change points of the lung lobe; CT images are analyzed using specific software to identify and differentiate lung tissues of varying densities. This process is accomplished by extracting pixels within a specific threshold range from the image. Pixels represent normal or abnormal lung tissue, and the pixel gradient change in each region is calculated. This value is derived by comparing the density differences between adjacent pixels, which helps to depict the detailed outline of the lung structure and subsequently screen out pixels with significant changes. For example, when distinguishing tumors or lesions, significant pixels indicate the boundaries of abnormal areas, thereby generating a set of lung lobe pixel gradient change points. This point set is key data for determining the location and extent of lesions.

[0021] S112: Based on the set of lung lobe pixel gradient change points, segment the airway tree structure, extract boundary pixels, calculate the gradient direction vector, filter the gradient change rate, and generate a set of airway wall candidate points; In practical applications, it is very important for identifying airway obstruction and evaluating airway lesions. The boundary pixels of the airway area are extracted. The pixels are determined by calculating the direction and magnitude of the pixel gradients in the adjacent areas. The gradient direction vectors of the boundary pixels are calculated. This data is used to evaluate the overall direction and morphology of the airway wall. Combined with the distribution characteristics of the gradient direction vectors, areas with abnormal gradient changes are identified, indicating the specific location of the airway affected by the disease. The gradient change rate with important clinical diagnostic significance is screened. The rate data helps doctors determine the severity and type of airway diseases and generates a set of candidate airway wall points. This dataset can be used for further diagnostic analysis and disease assessment.

[0022] S113: Based on the airway wall candidate point set, calculate the local gradient mean of the boundary points, analyze the gradient distribution, identify the spatial offset, and use the formula based on the relationship between gradient and offset: ; Calculate the boundary gradient offset coefficient of the airway wall boundary points, screen the boundary points that meet the threshold, and generate an airway wall boundary point set; in, Represents the boundary gradient offset coefficient of the airway wall boundary point, Represents candidate boundary points of the airway wall The gradient value at represents the mean gradient of the candidate boundary points, and Representing boundary points The offset in the horizontal and vertical directions, Represents a small positive number used to avoid the denominator being zero, Represents the total number of candidate boundary points on the airway wall; And substitute specific values ​​for calculation to obtain the boundary gradient offset coefficient of the airway wall boundary point; (Candidate boundary points of airway wall Gradient value at ): calculated from CT image data, obtained by calculating the gradient change of adjacent pixels; (mean gradient of candidate boundary points): calculated by taking the mean of the gradient values ​​of all candidate points; 、 (Boundary point Offset in horizontal and vertical directions): Calculated as: ,in( ) is the coordinate of the airway centerline, ( ) are the coordinates of the candidate boundary points; (To prevent small positive numbers with zero denominator): Set to ; (Total number of candidate boundary points): Set to 5 boundary points for example calculation; Assumption: Gradient values ​​of 5 candidate points: ; Compute the mean gradient: ; Coordinates and offset calculation of 5 candidate points: ; ; calculate : , ; , ; , ; , ; , ; calculate : ; ; ; ; ; calculate : ; ; Calculate each term: , , ; ; The results show that the boundary gradient offset coefficient of the airway wall boundary point is 1.665. The numerical value reflects the degree of deviation of the gradient change of the boundary point from the average value. In medical image analysis, this value can be used to determine whether the airway wall has pathological thickening or stenosis. By comparing with the set standard threshold (for example, 1.5), it can be determined whether there is an abnormality in the current airway. By normalizing the gradient offset value to the spatial offset, misjudgment caused by local gradient abnormalities of the airway wall can be avoided, and the detection ability of abnormal airway wall thickness can be improved. The formula uses the gradient mean as the reference value for calculation, which can reduce the interference of individual abnormal points on the overall evaluation, making the detection more stable and reliable.

[0023] See also Figure 3 , the specific steps for obtaining the airway wall thickness parameters are: S211: Based on the airway wall boundary point set, extract measurement boundary points in the bronchial branch area, calculate the local gradient change value of the boundary points, and screen the boundary points that meet the set threshold to obtain the measurement area boundary point set; First, the coordinate information of all points in the airway wall boundary point set is obtained, and based on their positional relationship, the point set belonging to the bronchial branch area is determined to generate the preliminary boundary of the measurement area. Then, the local gradient change value of each boundary point is calculated. This value is obtained by calculating the grayscale value difference of the adjacent pixel points of the boundary point. In CT images, the grayscale value can represent the change of tissue density. For example, if the grayscale values ​​of adjacent pixels are set to 180 and 150 respectively, the gradient change value is calculated as For the entire boundary point set, this calculation is performed on each point to construct a complete gradient change distribution map. Next, the boundary points that meet the set threshold range are screened. The threshold is used to distinguish boundary points from non-boundary points. The reference basis for setting the threshold is the grayscale difference between normal tissue and lesion area. Assuming that the set threshold is 25, all points with gradient change values ​​greater than 25 are retained, and points below 25 are eliminated, and finally the boundary point set of the measurement area is obtained.

[0024] S212: Based on the boundary point set of the measurement area, adjust the measurement path direction, match the local curvature trend, and analyze the pixel gradient changes of adjacent points on the path. The formula is: ; Calculate the gradient curvature value of the measurement path, screen the boundary points that meet the measurement conditions, and generate a measurement path boundary point set; in, Represents the gradient curvature value of the measurement path, Represent the gradient values ​​of the differentiated boundary points on the measurement path, Represents the horizontal and vertical offset of the corresponding boundary point, Represents small positive numbers used to avoid denominators being zero; Based on the set of boundary points in the measurement area, the local curvature radius of the boundary points is calculated. The coordinates of the boundary points are obtained and the curvature change of the adjacent points is calculated. The curvature radius is calculated from the coordinates of the three adjacent points. The direction of the measurement path is adjusted to optimize the path along the local curvature change trend. During the path adjustment process, it is necessary to analyze the pixel gradient changes of adjacent points on the path to calculate the gradient change rate on the measurement path. Set the sample data and assume that the grayscale values ​​of the boundary points are: ; offset ; Small positive number To prevent the denominator from being zero, substitute the following into the calculation: ; ; ; ; The result shows that the gradient curvature value of the measurement path is 11.56. This value can be used to judge the smoothness of the path. If the value is large, it means that the boundary curvature changes dramatically and the measurement path direction needs to be adjusted.

[0025] S213: Based on the measurement path boundary point set, analyzing the pixel gradient change rate, correcting abnormal fluctuations, calling the corrected gradient change rate data, calculating the local thickness data of the boundary points, and obtaining the airway wall thickness parameter; Obtain the pixel grayscale change value of each point on the measurement path, calculate the gradient change ratio between adjacent points, correct abnormal fluctuations, compare the gradient change rates of consecutive points on the measurement path, and detect abnormal jump points. If the gradient change rate of adjacent points exceeds the set range, perform smoothing correction. For example, set the allowable range to ±10%. If the change rate of adjacent points is 25%, adjust it to within 10%. Call the corrected gradient change rate data, calculate the local thickness parameters of the boundary points, and finally obtain the airway wall thickness parameters.

[0026] See also Figure 4 , the specific steps for obtaining the lung ventilation imbalance coefficient are: S311: Based on the airway wall thickness parameter, the alveolar ventilation area is segmented, and the local airflow channel cross-sectional area of ​​each area is calculated. The airflow channel morphological characteristics of the region are combined to screen and remove outliers to obtain the airflow channel cross-sectional area data; First, obtain the patient's chest high-resolution CT (HRCT) image data, use image processing software to segment the airway wall, extract the airway wall thickness information, and apply image segmentation algorithms, such as region growing method or level set method, to separate the alveolar ventilation area from the image to ensure accurate identification of the alveolar structure. Calculate the local airflow channel cross-sectional area of ​​each segmented area. This can be achieved by measuring the airway inner diameter and applying the formula Calculate, where represents the cross-sectional area, It represents the airway diameter. Combined with the morphological characteristics of the regional airflow channel, such as branch angle and length, the data is screened to remove outliers. For example, if a cross-sectional area value deviates significantly from the range of two standard deviations of the mean, it is considered an outlier and removed to obtain the airflow channel cross-sectional area data.

[0027] S312: Call the airflow channel cross-sectional area data to identify the corresponding lobe ventilation volume, and perform normalization processing on the lobe ventilation volume using the formula: ; The ventilation change amplitude of the lung lobe is calculated; in, Represents the ventilation change amplitude of the lung lobe, Represents the current lobe ventilation, represents initial lobar ventilation; First, the cross-sectional area of ​​each airflow channel is classified and summarized according to the lung lobe to which it belongs. The total ventilation volume of each lung lobe can be calculated by multiplying the cross-sectional area of ​​each channel by the corresponding airflow velocity and summing all channels in the same lung lobe. Assume that there are three airflow channels in a lung lobe, and their cross-sectional areas are 2cm 2 , 1.5cm 2 and 1cm 2 , the corresponding air flow velocity is 5cm / s, then the total ventilation of the lung lobe is Then, the ventilation of each lobe is normalized, that is, the ventilation of each lobe is divided by the sum of the ventilation of all lobes to obtain the relative ventilation ratio, and the change range of the ventilation of each lobe is calculated using the formula: ; in, Indicates the amplitude of ventilation change, Indicates the current lobe ventilation. represents the initial lobe ventilation, assuming the initial ventilation is 20cm 3 / s, the current ventilation volume is 22.5cm 3 / s, the ventilation change amplitude is , calculate the ventilation change amplitude of the lung lobe.

[0028] S313: Based on the amplitude of the ventilation change of the lung lobes, the difference between the lung lobes is analyzed, and the lung ventilation imbalance coefficient is obtained by combining the lung lobes with the lung ventilation volume; First, calculate the degree of difference in ventilation change between each lobe. This can be achieved by calculating the standard deviation of the ventilation change of each lobe. The larger the standard deviation, the more significant the difference in ventilation change between each lobe. Combined with the ventilation volume of each lobe, calculate the pulmonary ventilation imbalance coefficient. Multiply the ventilation change of each lobe by the proportion of its corresponding ventilation volume to the total ventilation volume, and then sum the results of all lobes. Assuming there are three lobes, their ventilation change amplitudes are 10%, 15% and 20% respectively, and the corresponding ventilation volumes account for 30%, 40% and 30% respectively, then the pulmonary ventilation imbalance coefficient is , and obtain the lung ventilation imbalance coefficient.

[0029] See also Figure 5 The specific steps for obtaining the airway wall ventilation coupling abnormality index are as follows: S411: Calling the lung ventilation imbalance coefficient, screening the areas with uneven ventilation distribution between each lung lobe, eliminating the areas within the ventilation balance range, and obtaining the ventilation restricted areas; First, the patient's lung CT data is used to extract the ventilation distribution information of each lung lobe, calculate the average ventilation volume of each lung lobe, and normalize it with the total lung ventilation volume to obtain the ventilation ratio of each lung lobe. The ventilation ratio of each lung lobe is compared and the ventilation imbalance between the lung lobes is calculated. If the ventilation ratio of a certain lung lobe is lower than a certain threshold (such as the set lower limit of normal ventilation ratio), it is judged that the lung lobe has ventilation restriction. Assuming that the total lung ventilation volume is 5000mL, the ventilation volume of the left upper lobe is 800mL, the ventilation volume of the right upper lobe is 900mL, and the ventilation volume of the right middle lobe is 100mL. The ventilation volume of the right lower lobe is 1000mL, the ventilation volume of the left lower lobe is 1400mL, and the ventilation volume of the left lower lobe is 900mL. The ventilation proportions of each lobe are 16%, 18%, 20%, 28%, and 18%, respectively. If a certain threshold is set to a ventilation proportion lower than 15%, it is judged as a ventilation-restricted area. Although the left upper lobe is the lowest, it is still within the normal range. Otherwise, it will be classified as a restricted area. The change range of the ventilation volume of each lobe is calculated. If the change range of the ventilation volume of a certain lobe at multiple time points exceeds the set change threshold (such as more than 20%), the ventilation of this area can also be determined to be restricted.

[0030] S412: Based on the ventilation-restricted area, calculate the airway wall thickness within the area and monitor the rate of change of ventilation over time using the formula: ; The ventilation change rate value is calculated; in, Indicates the ventilation change rate value, Representative Moment The ventilation volume, Representative Moment The ventilation volume, represents the total time interval; First, CT image data corresponding to the ventilation-restricted area is extracted, and the contour of the airway wall area is extracted. The thickness of each airway wall is calculated. The difference in the contour distance between the outer wall and the inner wall is measured to obtain the airway wall thickness distribution in the area. The rate of change of ventilation over time is monitored, the ventilation volume at multiple time points is calculated, and the ventilation change rate is obtained using the formula: ; in, Indicates the ventilation change rate, Representative Moment The ventilation volume, Representative Moment The ventilation volume, Represents the total time interval. For example, if the ventilation volume of a ventilation-restricted area is 200 mL, 180 mL, and 150 mL at 0 s, 10 s, and 20 s, respectively, the ventilation change rate is calculated as: ; It indicates that the ventilation volume in this area is on a downward trend and the ventilation rate is decreasing. Combined with the airway wall thickness data of this area, it is analyzed whether the airway wall thickening is positively correlated with the decrease in ventilation rate, and finally the ventilation change rate is calculated.

[0031] S413: Analyze the change trend of the ventilation change rate value and the airway wall thickness, extract the abnormal growth area, and calculate the airway wall ventilation coupling abnormality index; First, compare the airway wall thickness values ​​at multiple time points, calculate their rate of change, and determine the growth rate of airway wall thickness. If the airway wall thickness of a ventilation-restricted area increases by more than a set threshold (such as 0.1 mm / month), it is marked as an abnormal growth area. Combined with the ventilation change rate data, calculate whether the airway wall thickening is accompanied by a decrease in ventilation rate. If the airway wall thickness in a certain area grows faster and the ventilation change rate shows a downward trend, it is considered that there is a pathological abnormality in the area. For example, if the airway wall thickness of a ventilation-restricted area increases from 1.2 mm to 1.6 mm within three months, the growth rate is mm / month, exceeds the set threshold, and at the same time the ventilation change rate in the area drops to -3.0 mL / s, it can be determined as an abnormal growth area, and the airway wall ventilation coupling abnormality index is finally calculated.

[0032] See also Figure 6 The specific steps for obtaining COPD risk warning response are: S511: Based on the airway wall ventilation coupling abnormality index, the airway wall thickness, ventilation distribution value, and local flow value are called to calculate the abnormal distribution value, and the abnormal area exceeding the threshold is screened to obtain the mean value of the abnormal area; By collecting airway wall thickness data from multiple patients, extracting ventilation distribution values ​​at various locations, and calculating local flow values, the thickness of different bronchial branches is measured using airway CT scan data from different patients to obtain airway wall thickness information. Based on the physiological characteristics of different individuals, the ventilation distribution is quantified, and the ventilation indicators are normalized for comparison between different individuals. Local airway resistance is calculated through airflow dynamics, and airway patency is judged based on ventilation data. After normalizing all individual data, the abnormal distribution value of each sample is calculated to screen areas where ventilation and airway wall thickness distribution do not match. For example, when the airway wall in a certain area is thickened but ventilation is reduced, there is an abnormality in that area. The data of all abnormal areas are integrated to calculate the mean of the abnormal index, which can be used to judge abnormal conditions of different individuals and ultimately obtain the mean of the abnormal area.

[0033] S512: Compare the mean value of the abnormal area with the warning threshold, extract the area beyond the warning range, call the ventilation distribution state and local resistance coefficient, and filter out the data of the area beyond the threshold; First, a warning threshold is set. Statistical methods are used to extract the normal ventilation distribution range from healthy individual data. The mean and standard deviation within this range are calculated to set the upper and lower limits of the normal value. The mean of the abnormal area is then compared with the set threshold. If the abnormal mean of a certain area exceeds the warning range, the area is marked as a risk area, the ventilation distribution status is called, the ventilation changes at different time points are calculated, the local resistance coefficient is analyzed, the airway resistance is measured using fluid dynamics methods, and the correlation between airway resistance and ventilation is calculated. All areas are screened, and areas that meet the risk characteristics are extracted to finally obtain data for areas exceeding the threshold.

[0034] S513: Based on the data of the area exceeding the threshold, the environmental variables and sample data are called, and the formula is used: ; Calculate the mean of COPD abnormal index and output COPD risk warning response; in, represents the mean value of COPD abnormal index, Representative The abnormal index value of the sample, represents the mean of the sample anomaly index, represents the total number of samples, Measure the degree of sample bias; Set five sample data , calculate the mean of the anomaly index: ; Calculate the sum of squared deviations: ; ; Finally, the mean value of COPD abnormal index was calculated: ; The results show that the degree of deviation of the abnormal index is small. If the value exceeds the set risk limit, further screening is required and a COPD risk warning response is finally output.

[0035] The COPD early warning system based on chest CT parameters is used to implement the above-mentioned COPD early warning method based on chest CT parameters, and the system includes: The anatomical region analysis module extracts lung pixel data based on chest CT image data, screens lung parenchyma boundaries, segments bronchial tree structures, analyzes grayscale gradients, detects bronchial wall boundaries, analyzes gradient changes at boundary points, calculates bronchial branching angles, and obtains bronchial wall boundary point sets. The airway wall thickness calculation module extracts the boundary points of the measurement area based on the bronchial wall boundary point set, calculates the radial distance of the lumen, analyzes the grayscale gradient, selects boundary points that meet the standards, calculates the thickness difference between boundary points, analyzes local thickness changes, analyzes the thickness distribution of continuous cross-sections of the bronchial wall, adjusts abnormal fluctuation segments, corrects the measurement path, and statistically analyzes the differentiated branch thickness change characteristics to obtain airway wall thickness parameters; The pulmonary airflow distribution analysis module calculates the cross-sectional area of ​​airway branches based on airway wall thickness parameters, counts changes in pulmonary lobe ventilation channels, analyzes differences in airway ventilation flow rates, and obtains distribution data on pulmonary ventilation restriction; The ventilation abnormality identification module, based on the distribution data of pulmonary ventilation limitation, screens abnormal areas, analyzes the relationship between the wall thickness change rate and the ventilation limitation rate, extracts areas with increased ventilation resistance, identifies the ventilation balance of the lung lobes, and obtains the airway wall ventilation abnormality index; The COPD risk grading module sets warning thresholds based on the airway wall ventilation abnormality index, screens areas exceeding the threshold, calculates spatial distribution, screens risk areas and issues warnings, and obtains COPD risk warning responses.

[0036] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A COPD early warning method based on chest CT parameters, characterized in that: The following steps are involved: S1: Based on chest CT image data, extract pixel data of the lung lobe anatomical area, segment the airway tree structure, identify the bronchial wall boundary, filter the gradient change points, and generate the airway wall boundary point set; S2: Based on the airway wall boundary point set, extract the boundary points of the measurement area within the bronchial branch area, identify the local curvature radius, adjust the measurement path direction, analyze the pixel gradient changes of adjacent points on the measurement path, select boundary points that meet the measurement conditions, calculate the pixel gradient change rate, correct abnormal fluctuations, and obtain airway wall thickness parameters; S3: calling the airway wall thickness parameter, segmenting the alveolar ventilation area, calculating the airflow channel cross-sectional area data, analyzing the lobe ventilation and ventilation variation, and obtaining the pulmonary ventilation imbalance coefficient; S4: calling the lung ventilation imbalance coefficient, screening the ventilation-restricted area, analyzing the thickness and ventilation change rate, extracting the abnormal growth area, and obtaining the airway wall ventilation coupling abnormality index; S5: Call the airway wall ventilation coupling abnormality index, screen the abnormal distribution area, set the warning threshold, calculate the average of the abnormal index, mark the area exceeding the threshold and issue a warning, and output a COPD risk warning response.

2. The COPD early warning method based on chest CT parameters according to claim 1, characterized in that: The airway wall boundary point set includes bronchial wall boundary points, gradient change points, and pixel gradient change rates. The airway wall thickness parameters include measurement area boundary points, local curvature radius, and adjacent point pixel gradient changes. The lung ventilation imbalance coefficient includes alveolar ventilation area, airflow channel cross-sectional area data, and lobe ventilation change amplitude. The airway wall ventilation coupling abnormality index includes ventilation-restricted area, thickness change rate, and ventilation change rate. The COPD risk warning response includes abnormal distribution area, abnormal index mean, and exceeding threshold area.

3. The COPD early warning method based on chest CT parameters according to claim 2, characterized in that: The steps for obtaining the airway wall boundary point set are specifically as follows: S111: extracting pixel data of the anatomical region of the lung lobe based on the chest CT image data, calculating the pixel gradient change of the region, screening the pixel points that meet the threshold, and generating a set of pixel gradient change points of the lung lobe; S112: Based on the set of lung lobe pixel gradient change points, segment the airway tree structure, extract boundary pixel points, calculate the gradient direction vector, filter the gradient change rate, and generate a set of airway wall candidate points; S113: Based on the airway wall candidate point set, calculate the local gradient mean of the boundary point, analyze the gradient distribution, identify the spatial offset, and use the formula based on the relationship between the gradient and the offset: ； Calculate the boundary gradient offset coefficient of the airway wall boundary points, screen the boundary points that meet the threshold, and generate an airway wall boundary point set; in, Represents the boundary gradient offset coefficient of the airway wall boundary point, Represents candidate boundary points of the airway wall The gradient value at represents the mean gradient of the candidate boundary points, and Representing boundary points The horizontal and vertical offsets, Represents a small positive number used to avoid the denominator being zero, Represents the total number of candidate boundary points of the airway wall.

4. The COPD early warning method based on chest CT parameters according to claim 3, characterized in that: The steps for obtaining the airway wall thickness parameter are specifically as follows: S211: Based on the airway wall boundary point set, extract measurement boundary points in the bronchial branch area, calculate local gradient change values ​​of the boundary points, and screen boundary points that meet a set threshold to obtain a measurement area boundary point set; S212: Based on the measurement area boundary point set, adjust the measurement path direction, match the local curvature trend, analyze the pixel gradient changes of adjacent points on the path, and use the formula: ； Calculate the gradient curvature value of the measurement path, screen the boundary points that meet the measurement conditions, and generate a measurement path boundary point set; in, Represents the gradient curvature value of the measurement path, Represent the gradient values ​​of the differentiated boundary points on the measurement path, Represents the horizontal and vertical offset of the corresponding boundary point, Represents small positive numbers used to avoid denominators being zero; S213: Based on the measurement path boundary point set, analyze the pixel gradient change rate, correct abnormal fluctuations, call the corrected gradient change rate data, calculate the local thickness data of the boundary points, and obtain the airway wall thickness parameter.

5. The COPD early warning method based on chest CT parameters according to claim 4, characterized in that: The steps for obtaining the lung ventilation imbalance coefficient are specifically as follows: S311: Segmenting the alveolar ventilation area based on the airway wall thickness parameter, calculating the local airflow channel cross-sectional area of ​​each area, screening the area based on the regional airflow channel morphological characteristics, removing outliers, and obtaining airflow channel cross-sectional area data; S312: Call the airflow channel cross-sectional area data to identify the corresponding lobe ventilation volume, and perform normalization processing on the lobe ventilation volume using the formula: ； The ventilation change amplitude of the lung lobe is calculated; in, Represents the ventilation change amplitude of the lung lobe, Represents the current lobe ventilation, represents initial lobar ventilation; S313: Based on the ventilation change amplitude of the lung lobes, the degree of difference between the lung lobes is analyzed, and the lung ventilation imbalance coefficient is obtained in combination with the lung lobes' lung ventilation volumes.

6. The COPD early warning method based on chest CT parameters according to claim 5, characterized in that: The steps for obtaining the airway wall ventilation coupling abnormality index are specifically as follows: S411: calling the lung ventilation imbalance coefficient, screening the area with uneven ventilation distribution between each lung lobe, eliminating the area within the ventilation balance range, and obtaining the ventilation restricted area; S412: Based on the ventilation-restricted area, calculate the airway wall thickness in the area and monitor the rate of change of ventilation over time using the formula: ； The ventilation change rate value is calculated; in, Indicates the ventilation change rate value, Representative Moment The ventilation volume, Representative Moment The ventilation volume, represents the total time interval; S413: Analyze the change trend of the ventilation change rate value and the airway wall thickness, extract the abnormal growth area, and calculate the airway wall ventilation coupling abnormality index.

7. The COPD early warning method based on chest CT parameters according to claim 6, characterized in that: The steps for obtaining the COPD risk warning response are specifically as follows: S511: Based on the airway wall ventilation coupling abnormality index, the airway wall thickness, ventilation distribution value, and local flow value are called to calculate the abnormal distribution value, and the abnormal area exceeding the threshold is screened to obtain the average value of the abnormal area; S512: Compare the mean value of the abnormal area with the warning threshold, extract the area beyond the warning range, call the ventilation distribution state and the local resistance coefficient, and filter to obtain the data of the area beyond the threshold; S513: Based on the data of the area exceeding the threshold, the environmental variables and the sample data are called, and the formula is used: ； Calculate the mean of COPD abnormal index and output COPD risk warning response; in, represents the mean value of COPD abnormal index, Representative The abnormal index value of the sample, represents the mean of the sample anomaly index, represents the total number of samples, A measure of the degree of sample bias.

8. A COPD early warning system based on chest CT parameters, characterized in that: The COPD early warning method based on chest CT parameters according to any one of claims 1 to 7, wherein the system comprises: The anatomical region analysis module extracts lung pixel data based on chest CT image data, screens lung parenchyma boundaries, segments bronchial tree structures, analyzes grayscale gradients, detects bronchial wall boundaries, analyzes gradient changes at boundary points, calculates bronchial branching angles, and obtains bronchial wall boundary point sets. The airway wall thickness calculation module extracts the boundary points of the measurement area based on the bronchial wall boundary point set, calculates the radial distance of the lumen, analyzes the grayscale gradient, selects boundary points that meet the standards, calculates the thickness difference between boundary points, analyzes local thickness changes, analyzes the thickness distribution of continuous cross-sections of the bronchial wall, adjusts abnormal fluctuation sections, corrects the measurement path, and statistically analyzes the differentiated branch thickness change characteristics to obtain airway wall thickness parameters; The pulmonary airflow distribution analysis module calculates the cross-sectional area of ​​the airway branches based on the airway wall thickness parameter, counts the changes in the ventilation channels of the pulmonary lobes, analyzes the differences in airway ventilation flow rates, and obtains the distribution data of pulmonary ventilation limitation; The ventilation abnormality identification module screens abnormal areas based on the lung ventilation limitation distribution data, analyzes the corresponding relationship between the wall thickness change rate and the ventilation limitation rate, extracts areas with increased ventilation resistance, identifies the ventilation balance of the lung lobes, and obtains the airway wall ventilation abnormality index; The COPD risk grading module sets a warning threshold based on the airway wall ventilation abnormality index, screens the super-threshold area, calculates the spatial distribution, screens the risk area and issues a warning, and obtains a COPD risk warning response.

Images