A lung parameter measurement system, method and medium based on lung CT cross section

Abstract

The application relates to the technical field of image processing, and discloses a lung parameter measurement system and method based on a lung CT cross section and a medium. The system comprises the following modules: an image acquisition module for acquiring a lung CT image; a left and right lung segmentation module for processing the lung CT image by using a deep learning model or an image processing algorithm to generate a left and right lung segmentation mask; a skeleton segmentation module for processing the lung CT image by using a deep learning model or an image processing algorithm to generate a skeleton segmentation mask; an anteroposterior diameter positioning module for positioning an anteroposterior median line anteroposterior diameter according to the left and right lung segmentation mask and the skeleton segmentation mask, and determining a left lung anteroposterior diameter and a right lung anteroposterior diameter; and a transverse diameter positioning module for positioning a thoracic transverse diameter according to the left and right lung segmentation mask, the skeleton segmentation mask and the anteroposterior median line anteroposterior diameter, and determining a left lung transverse diameter and a right lung transverse diameter. The application improves the reliability of lung development parameter measurement and provides an accurate and consistent parameter measurement method for child lung development research.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a lung parameter measurement system, method and medium based on lung CT cross-sections. Background Technology

[0002] Computed tomography (CT) is a technique that reconstructs three-dimensional medical images through digital geometric processing. In lung research, plain CT scans are often used for observing lung morphology due to their advantages such as low cost, controllable radiation dose, and fast imaging speed. However, existing research focuses primarily on the detection and segmentation of lung lesions, with limited quantitative analysis of transverse geometric parameters of the lungs (such as anteroposterior diameter and transverse diameter) in studies of the natural evolution of lung development in children.

[0003] Traditional measurement methods typically rely on manual operation, which suffers from problems such as strong subjectivity, large errors, low efficiency, lack of standardization, and insufficient automation, making it difficult to meet the needs for efficient, accurate, and standardized measurements in children's lung development research. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and provide a lung parameter measurement system, method and medium based on lung CT cross-section.

[0005] This invention provides the following technical solution:

[0006] In a first aspect, this disclosure provides a lung parameter measurement system based on a cross-sectional view of a lung CT scan, the system comprising:

[0007] Image acquisition module, used to acquire lung CT images;

[0008] The left and right lung segmentation module is used to process the lung CT image using a first deep learning model or a first image processing algorithm to generate a left and right lung segmentation mask.

[0009] The skeleton segmentation module is used to process the lung CT image using a second deep learning model or a second image processing algorithm to generate a skeleton segmentation mask.

[0010] The anteroposterior diameter positioning module is used to locate the endpoints of the anteroposterior diameter of the anteroposterior midline based on the left and right lung segmentation mask and the bone segmentation mask, and to determine the anteroposterior diameter of the left lung and the anteroposterior diameter of the right lung based on the anteroposterior diameter of the anteroposterior midline.

[0011] The transverse diameter positioning module is used to locate the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and to determine the transverse diameters of the left and right lungs based on the transverse diameters of the thoracic cage.

[0012] Optionally, the left and right lung segmentation module includes:

[0013] The left and right lung segmentation preprocessing unit is used to filter the lung CT image, remove noise points in the lung CT image, obtain the filtered lung CT image, and standardize the filtered lung CT image to obtain the standardized lung CT image.

[0014] The left and right lung segmentation processing unit is used to process the standardized lung CT image using the first deep learning model or the first image processing algorithm to generate an initial left and right lung segmentation mask.

[0015] The left and right lung segmentation post-processing unit is used to perform morphological operations on the initial left and right lung segmentation mask to remove noise points and isolated regions in the initial left and right lung segmentation mask, thereby obtaining the left and right lung segmentation mask.

[0016] Optionally, the skeleton segmentation module includes:

[0017] A bone segmentation preprocessing unit is used to perform histogram equalization on the lung CT images to obtain enhanced lung CT images.

[0018] The bone segmentation processing unit is used to process the enhanced lung CT image using the second deep learning model or the second image processing algorithm to generate an initial bone segmentation mask.

[0019] The bone segmentation post-processing unit is used to perform morphological operations on the initial bone segmentation mask to remove noise points and isolated regions in the initial bone segmentation mask, thereby obtaining the bone segmentation mask.

[0020] Optionally, the anterior and posterior diameter positioning module includes:

[0021] The candidate layer determination unit is used to filter out layers containing at least left lung pixels or right lung pixels from the left and right lung segmentation mask as candidate layers, and to select layers within a preset range of the candidate layers as alternative layers.

[0022] The front-to-back centerline diameter determination unit is used to determine the front end point and the rear end point in each of the candidate layers, and to take the line connecting the front end point and the rear end point as the front-to-back centerline diameter.

[0023] The front and rear centerline diameter measurement unit is used to calculate the length and angle of the front and rear centerline diameter in each of the candidate layers based on the front end point and rear end point in each of the candidate layers.

[0024] The front and rear centerline front and rear diameter filtering unit is used to filter the length and angle of the front and rear centerline front and rear diameters in all the candidate layers to obtain the effective front and rear centerline front and rear diameters.

[0025] The left and right lung anteroposterior diameter measurement unit is used to obtain the left lung anteroposterior diameter and the right lung anteroposterior diameter based on the effective anteroposterior midline anteroposterior diameter and in combination with preset pixel spacing information.

[0026] Optionally, the unit for determining the anterior and posterior diameters of the anterior and posterior midline includes:

[0027] The region of interest determination subunit is used to extract the upper and lower preset rectangular regions between the left and right lungs as regions of interest based on the left and right lung segmentation mask, and to determine the corresponding regions of interest in the bone segmentation mask.

[0028] The front-to-back midline diameter determination subunit is used to extract the midpoint of the lower boundary of the bone segmentation mask in the upper preset range rectangular area as the front point, extract the midpoint of the upper boundary of the bone segmentation mask in the lower preset range rectangular area as the back point, and take the line connecting the front point and the back point as the front-to-back midline diameter.

[0029] The front and rear midline diameter measurement unit includes:

[0030] The front and rear centerline diameter length measurement subunit is used to calculate the length of the front and rear centerline diameter of each of the candidate layers using a first preset length calculation formula and based on the front and rear endpoints of the front and rear centerline diameter of each of the candidate layers.

[0031] The front and rear centerline front and rear diameter angle measurement subunit is used to calculate the angle of the front and rear centerline front and rear diameters in each of the candidate layers using a preset angle calculation formula and based on the front end point and rear end point in each of the candidate layers.

[0032] The formula for calculating the first preset length is as follows:

[0033]

[0034] The formula for calculating the preset angle is:

[0035]

[0036] In the formula, d ami θ is the length of the front-to-back diameter of the front-to-back midline in the candidate layer of the i-th layer. i x is the angle between the front and rear diameters of the front and rear midline in the candidate layer of the i-th layer. tiLet x be the x-coordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the candidate layer of the i-th layer. bi Let y be the x-coordinate of the rear end point of the front-rear diameter of the front-rear midline in the candidate layer of the i-th layer. ti Let y be the ordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the candidate layer of the i-th layer. bi The ordinate of the rear end point of the front-rear diameter of the front-rear midline in the candidate layer of the i-th layer.

[0037] Optionally, the anterior and posterior diameter screening unit for the anterior and posterior midline includes:

[0038] The mean calculation subunit is used to calculate the mean length and mean angle of the front and rear diameters of the front and rear midlines in all the candidate layers;

[0039] The mean rejection subunit is used to reject the front-to-back midline diameters where the difference between the length and the mean length exceeds a length threshold and / or the difference between the angle and the mean angle exceeds an angle threshold, thereby obtaining the effective front-to-back midline diameters from the multiple candidate layers.

[0040] The left and right lung anteroposterior diameter measurement unit includes:

[0041] The line segment extraction subunit is used to extract the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the effective anterior and posterior midline based on the angle of the anteroposterior diameter of the effective anterior and posterior midline in each of the candidate layers, and use them as the theoretical anteroposterior diameter of the left lung and the theoretical anteroposterior diameter of the right lung, respectively.

[0042] The left and right lung anteroposterior diameter calculation subunit is used to obtain the preset coefficient in the preset pixel spacing information, calculate the product of the length of the effective anteroposterior midline and the preset coefficient to obtain the length of the physical anteroposterior midline, calculate the product of the length of the theoretical left lung anteroposterior diameter and the preset coefficient to obtain the length of the left lung anteroposterior diameter, and calculate the product of the length of the theoretical right lung anteroposterior diameter and the preset coefficient to obtain the length of the right lung anteroposterior diameter.

[0043] Optionally, the transverse diameter positioning module includes:

[0044] The transverse diameter determination unit is used to extract the longest line segment perpendicular to the direction of the anteroposterior diameter of the effective anteroposterior midline in the left and right lung segmentation mask based on the angle of the anteroposterior diameter of the effective anteroposterior midline in each of the candidate layers, and use it as the transverse diameter of the thoracic cage, and determine the left and right endpoints of the transverse diameter of the thoracic cage.

[0045] The transverse diameter measurement unit is used to calculate the length of the transverse diameter of the thoracic cavity in each of the candidate layers using a second preset length calculation formula and based on the left and right endpoints of the transverse diameter of the thoracic cavity in each of the candidate layers.

[0046] The left and right lung transverse diameter calculation unit is used to extract the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the thoracic transverse diameter based on the angle of the thoracic transverse diameter in each of the candidate layers, and use them as the theoretical left lung transverse diameter and the theoretical right lung transverse diameter, respectively. The unit calculates the product of the length of the thoracic transverse diameter and the preset coefficient to obtain the length of the physical thoracic transverse diameter. The unit also calculates the product of the length of the theoretical left lung transverse diameter and the preset coefficient to obtain the length of the left lung transverse diameter. Finally, the unit calculates the product of the length of the theoretical right lung transverse diameter and the preset coefficient to obtain the length of the right lung transverse diameter.

[0047] The formula for calculating the second preset length is as follows:

[0048]

[0049] In the formula, d ttk x is the length of the transverse diameter of the thorax in the candidate layer of the k-th layer. lk Let x be the x-coordinate of the left endpoint of the transverse diameter of the thorax in the candidate layer of layer k. rk Let y be the x-coordinate of the right endpoint of the transverse diameter of the thorax in the candidate layer of layer k. lk Let y be the ordinate of the left endpoint of the transverse diameter of the thorax in the candidate layer of layer k. rk The ordinate is the right endpoint of the transverse diameter of the thorax in the candidate layer of the k-th layer.

[0050] Secondly, this disclosure provides a method for measuring lung parameters based on cross-sectional lung CT scans, applied to the lung parameter measurement system based on cross-sectional lung CT scans as described in the first aspect, the method comprising:

[0051] Lung CT images are acquired through the image acquisition module;

[0052] The lung CT images are processed by the left and right lung segmentation module using a first deep learning model or a first image processing algorithm to generate left and right lung segmentation masks.

[0053] The lung CT image is processed by the bone segmentation module using a second deep learning model or a second image processing algorithm to generate a bone segmentation mask.

[0054] The anteroposterior diameter positioning module locates the endpoints of the anteroposterior diameter of the anterior midline based on the left and right lung segmentation masks and the bone segmentation mask, and determines the anteroposterior diameter of the left and right lungs based on the anteroposterior diameter of the anterior midline.

[0055] The transverse diameter positioning module locates the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and determines the transverse diameters of the left and right lungs based on the transverse diameter of the thoracic cage.

[0056] Thirdly, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the lung parameter measurement method based on lung CT cross-sections as described in the second aspect.

[0057] The beneficial effects of this application are:

[0058] The lung parameter measurement system based on transverse CT scans provided in this application includes: an image acquisition module for acquiring lung CT images; a left and right lung segmentation module for processing the lung CT images using a first deep learning model or a first image processing algorithm to generate left and right lung segmentation masks; a skeleton segmentation module for processing the lung CT images using a second deep learning model or a second image processing algorithm to generate skeleton segmentation masks; an anteroposterior diameter localization module for locating the endpoints of the anteroposterior diameter of the anteroposterior midline based on the left and right lung segmentation masks and the skeleton segmentation mask, and determining the anteroposterior diameters of the left and right lungs based on the anteroposterior diameter of the anteroposterior midline; and a transverse diameter localization module for locating the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation masks, the skeleton segmentation mask, and the endpoints of the anteroposterior diameter of the anteroposterior midline, and determining the transverse diameters of the left and right lungs based on the transverse diameter of the thoracic cage. This application improves the reliability of lung development parameter measurement and provides an accurate and consistent parameter measurement method for pediatric lung development research.

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0060] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the various drawings, similar components are numbered similarly.

[0061] Figure 1 A schematic diagram of a lung parameter measurement device based on a cross-sectional CT scan of the lungs, provided in an embodiment of this application, is shown.

[0062] Figure 2 A schematic diagram of a lung CT image provided in an embodiment of this application is shown;

[0063] Figure 3 A schematic diagram of a left and right lung segmentation mask provided in an embodiment of this application is shown;

[0064] Figure 4 A schematic diagram of a skeletal segmentation mask provided in an embodiment of this application is shown;

[0065] Figure 5 This illustration shows a schematic diagram of the anterior-posterior diameter of the midline and the transverse diameter of the thorax provided in an embodiment of this application;

[0066] Figure 6 A schematic diagram of the theoretical anteroposterior diameter of the left lung and the theoretical anteroposterior diameter of the right lung provided in an embodiment of this application is shown;

[0067] Figure 7 A schematic diagram illustrating a theoretical left lung transverse diameter and a theoretical right lung transverse diameter provided in an embodiment of this application is shown;

[0068] Figure 8 A flowchart of a lung parameter measurement method based on a lung CT cross-section provided in this application embodiment is shown.

[0069] Explanation of key component symbols:

[0070] 100 - Lung parameter measurement system based on transverse CT scan of the lungs; 110 - Image acquisition module; 120 - Left and right lung segmentation module; 121 - Left and right lung segmentation preprocessing unit; 122 - Left and right lung segmentation processing unit; 123 - Left and right lung segmentation postprocessing unit; 130 - Skeleton segmentation module; 131 - Skeleton segmentation preprocessing unit; 132 - Skeleton segmentation processing unit; 133 - Skeleton segmentation postprocessing unit; 140 - Anteroposterior diameter localization module; 141 - Alternate slice determination unit; 142 - Anteroposterior diameter determination unit of the anterior-posterior midline; 1421 - Region of interest determination subunit; 1422 - Anteroposterior midline 143-Anterior-posterior diameter determination subunit; 1431-Anterior-posterior midline anteroposterior diameter measurement unit; 1432-Anterior-posterior midline anteroposterior diameter angle measurement subunit; 144-Anterior-posterior midline anteroposterior diameter screening unit; 1441-Mean value calculation subunit; 1442-Mean value removal subunit; 145-Left and right lung anteroposterior diameter measurement unit; 1451-Line segment extraction subunit; 1452-Left and right lung anteroposterior diameter calculation subunit; 150-Transverse diameter positioning module; 151-Thoracic transverse diameter determination unit; 152-Thoracic transverse diameter length measurement unit; 153-Left and right lung transverse diameter calculation unit. Detailed Implementation

[0071] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0072] It should be noted that when an element is said to be "fixed" to another element, it can be directly on the other element or there may be an intervening element. When an element is said to be "connected" to another element, it can be directly connected to the other element or there may be an intervening element. Conversely, when an element is said to be "directly" on another element, there is no intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0073] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0074] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the template description is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0076] Example 1

[0077] like Figure 1 The diagram shown is a schematic diagram of a lung parameter measurement system 100 based on a lung CT cross section in an embodiment of this application. The system includes an image acquisition module 110, a left and right lung segmentation module 120, a bone segmentation module 130, an anterior-posterior diameter positioning module 140, and a transverse diameter positioning module 150.

[0078] Image acquisition module 110 is used to acquire lung CT images.

[0079] Understandably, this embodiment can acquire lung CT (Computed Tomography) images through imaging equipment, such as... Figure 2 As shown, the lung CT image is represented as a gray value matrix of size H×W, with a gray value range of [0, 255].

[0080] The image acquisition module 110 provides the necessary raw data for subsequent segmentation and measurement, and high-quality CT images can ensure the accuracy and reliability of subsequent processing.

[0081] The left and right lung segmentation module 120 is used to process lung CT images using a first deep learning model or a first image processing algorithm to generate left and right lung segmentation masks.

[0082] Optionally, the left and right lung segmentation module 120 includes a left and right lung segmentation preprocessing unit 121, a left and right lung segmentation processing unit 122, and a left and right lung segmentation postprocessing unit 123.

[0083] The left and right lung segmentation preprocessing unit 121 is used to filter the lung CT image, remove noise points in the lung CT image, and obtain the filtered lung CT image.

[0084] Understandably, filtering lung CT images using Gaussian filtering or mean filtering removes noise points, resulting in filtered lung CT images that effectively improve the accuracy of the segmentation model. Furthermore, standardizing the filtered lung CT images by scaling the grayscale value range from [0, 255] to [0, 1] helps the subsequent deep learning model converge better.

[0085] The left and right lung segmentation processing unit 122 is used to process the filtered lung CT image using a first deep learning model or a first image processing algorithm to generate an initial left and right lung segmentation mask.

[0086] Understandably, the filtered lung CT image is processed using a first deep learning model (such as U-Net or SegFormer) or a first image processing algorithm (such as thresholding or watershed algorithm) to generate an initial left and right lung segmentation mask M′ of size H×W with pixel values ​​{0, 1, 2}.

[0087] These deep learning models and image processing algorithms can accurately distinguish between the background, left lung, and right lung. M′[i,j]=0 represents the background, M′[i,j]=1 represents the left lung region, and M′[i,j]=2 represents the right lung region.

[0088] The left and right lung segmentation post-processing unit 123 is used to perform morphological operations on the initial left and right lung segmentation mask to remove noise points and isolated regions in the initial left and right lung segmentation mask, and obtain the left and right lung segmentation mask.

[0089] Understandably, morphological operations (such as closing operations) are performed on the initial left and right lung segmentation mask M′ to remove noise points and isolated regions, making the segmentation result smoother, and finally obtaining the left and right lung segmentation mask M, as shown. Figure 3 As shown.

[0090] The left and right lung segmentation module 120 realizes automatic segmentation of the left and right lungs, reduces manual intervention, improves processing efficiency, and provides accurate left and right lung segmentation masks for subsequent measurements.

[0091] The skeleton segmentation module 130 is used to process lung CT images using a second deep learning model or a second image processing algorithm to generate a skeleton segmentation mask.

[0092] Optionally, the bone segmentation module 130 includes a bone segmentation preprocessing unit 131, a bone segmentation processing unit 132, and a bone segmentation postprocessing unit 133.

[0093] The bone segmentation preprocessing unit 131 is used to perform histogram equalization on the lung CT images to obtain enhanced lung CT images.

[0094] Understandably, histogram equalization of lung CT images can also enhance the contrast between bone and soft tissue, helping to segment bones more accurately and obtain enhanced lung CT images.

[0095] The bone segmentation processing unit 132 is used to process the enhanced lung CT image using a second deep learning model or a second image processing algorithm to generate an initial bone segmentation mask.

[0096] Understandably, the enhanced lung CT image is processed using a second deep learning model (such as U-Net) or a second image processing algorithm (such as thresholding or watershed algorithm) to generate an initial bone segmentation mask S′ with pixel values ​​of {0, 1}.

[0097] Deep learning models and image processing algorithms can accurately distinguish between background and skeletal regions. S′[i,j]=0 represents the background, and S′[i,j]=1 represents the skeletal region.

[0098] It should be noted that deep learning models can handle complex image features, while image processing algorithms are suitable for images with high contrast. In this embodiment, the first deep learning model and the second deep learning model can be the same deep learning model or different deep learning models; similarly, the first image processing algorithm and the second image processing algorithm can be the same image processing algorithm or different image processing algorithms. The deep learning model used can be a two-dimensional segmentation model or a three-dimensional segmentation model, meaning the output can be a two-dimensional numerical matrix or a three-dimensional numerical matrix. The appropriate model is selected based on research needs to improve the accuracy of measuring children's lung development parameters; this embodiment does not limit this selection.

[0099] The bone segmentation post-processing unit 133 is used to perform morphological operations on the initial bone segmentation mask to remove noise points and isolated regions in the initial bone segmentation mask S′, thereby obtaining the bone segmentation mask.

[0100] Understandably, morphological operations (such as dilation and erosion) are performed on the initial bone segmentation mask S′ to smooth the bone segmentation edges, remove noise points and isolated regions in the initial bone segmentation mask, and obtain the bone segmentation mask S, as follows: Figure 4 As shown.

[0101] The skeleton segmentation module 130 provides crucial skeletal reference information for subsequent positioning measurements of the anterior-posterior and transverse diameters by precisely segmenting the skeletal region, thereby improving measurement accuracy.

[0102] The anteroposterior diameter positioning module 140 is used to locate the endpoints of the anteroposterior diameter of the anterior midline based on the left and right lung segmentation mask and the bone segmentation mask, and to determine the anteroposterior diameter of the left lung and the right lung based on the anteroposterior diameter of the anterior midline.

[0103] Optionally, the anteroposterior diameter positioning module 140 includes a candidate layer determination unit 141, an anterior-posterior midline anteroposterior diameter determination unit 142, an anterior-posterior midline anteroposterior diameter measurement unit 143, an anterior-posterior midline anteroposterior diameter screening unit 144, and a left and right lung anteroposterior diameter measurement unit 145.

[0104] The candidate layer determination unit 141 is used to select layers containing at least left lung pixels or right lung pixels from the left and right lung segmentation mask as candidate layers, and to select layers within a preset range of candidate layers as alternative layers.

[0105] Understandably, all slices (slices) of the lung CT image are traversed, and slices containing at least one left lung pixel or one right lung pixel are found in the left and right lung segmentation mask M as candidate slices. Assuming there are a total of N candidate slices, slices within a preset range of sequence numbers (e.g., the middle 20% to 80%) are selected as alternative slices to avoid noise interference that may occur at the top and bottom edges.

[0106] The front-to-back centerline diameter determination unit 142 is used to determine the front end point and the rear end point in each candidate layer, and to take the line connecting the front end point and the rear end point as the front-to-back centerline diameter.

[0107] In one optional implementation, the front-to-back midline diameter determination unit 142 includes a region of interest determination subunit 1421 and a front-to-back midline diameter determination subunit 1422.

[0108] The region of interest determination subunit 1421 is used to extract the upper and lower preset rectangular regions between the left and right lungs as regions of interest based on the left and right lung segmentation masks, and to determine the corresponding regions of interest in the skeleton segmentation mask.

[0109] Understandably, in each alternative layer, based on the left and right lung segmentation mask M, such as Figure 5 The upper and lower rectangular areas shown in the figure are used to extract the upper and lower preset rectangular areas between the left and right lungs (for example, the upper preset rectangular area refers to the lung height 10% higher and 60% lower in the image, and the lower preset rectangular area refers to the lung height 10% lower and 40% higher in the image) as regions of interest, and then the corresponding regions of interest are found in the skeleton segmentation mask S.

[0110] The front-to-back centerline diameter determination subunit 1422 is used to extract the midpoint of the lower boundary of the bone segmentation mask in the upper preset range rectangular area as the front end point, extract the midpoint of the upper boundary of the bone segmentation mask in the lower preset range rectangular area as the back end point, and use the line connecting the front end point and the back end point as the front-to-back centerline diameter.

[0111] Understandably, in each candidate layer, the midpoint of the lower boundary of the skeletal segmentation mask in the upper preset rectangular region is extracted as the front point, and the midpoint of the upper boundary of the skeletal segmentation mask in the lower preset rectangular region is extracted as the back point. These are then mapped to the original image. The front point is represented as (x... t ,y t The endpoint is represented as (x) b ,y b The line connecting the two endpoints is the front-to-back diameter of the front-to-back midline, such as... Figure 5 The dashed lines shown.

[0112] It should be noted that when locating the anteroposterior diameter of the anterior midline, an AI model can also be used to directly predict the endpoints of the anteroposterior diameter of the anterior midline, thereby improving the efficiency of measuring lung development parameters in children. This application does not limit this aspect.

[0113] In addition, after locating the anteroposterior diameter of the midline, not only can the anteroposterior and transverse diameters of the left and right lungs be measured, but also the anteroposterior and transverse diameters of more fine-grained organ physiological structures such as lung lobes can be measured, increasing the dimensions of lung development parameter measurement in children, all of which are within the scope of protection of this application.

[0114] The front and rear centerline diameter measurement unit 143 is used to calculate the length and angle of the front and rear centerline diameter in each candidate layer based on the front end point and rear end point in each candidate layer.

[0115] In one optional embodiment, the front and rear centerline diameter measuring unit 143 includes a front and rear centerline diameter length measuring subunit 1431 and a front and rear centerline diameter angle measuring subunit 1432.

[0116] The front and rear centerline diameter length measurement subunit 1431 is used to calculate the length of the front and rear centerline diameter in each candidate layer using a first preset length calculation formula and based on the front and rear endpoints of the front and rear centerline diameter in each candidate layer.

[0117] Understandably, the length of the front and rear diameters of the front and rear midlines in each candidate layer can be calculated using the first preset length calculation formula and based on the coordinates of the anterior and posterior endpoints of the front and rear midlines in each candidate layer. The first preset length calculation formula is as follows:

[0118]

[0119] In the formula, d ami Let x be the length of the anterior-posterior diameter of the anterior-posterior midline in the i-th candidate layer. ti Let x be the x-coordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the i-th candidate layer. bi Let y be the x-coordinate of the rear end point of the front-rear diameter of the front-rear midline in the i-th candidate layer. ti Let y be the ordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the i-th candidate layer. bi Let be the ordinate of the rear end point of the front-rear diameter of the front-rear midline in the i-th candidate layer.

[0120] The front and rear centerline front and rear diameter angle measurement subunit 1432 is used to calculate the front and rear diameter angles of the front and rear centerlines in each candidate layer using a preset angle calculation formula and based on the front end point and rear end point in each candidate layer.

[0121] Understandably, by using a preset angle calculation formula and based on the coordinates of the front and rear points in each candidate layer, the angle between the front and rear diameters of the front and rear midlines in each candidate layer can be calculated. The preset angle calculation formula is as follows:

[0122]

[0123] In the formula, θ i Let be the angle between the anterior and posterior diameters of the anterior and posterior midline in the i-th candidate layer.

[0124] The front and rear midline diameter filtering unit 144 is used to filter the length and angle of the front and rear midline diameters in all candidate layers to obtain the effective front and rear midline diameters.

[0125] In one alternative implementation, the anterior and posterior diameter screening unit 144 includes a mean calculation subunit 1441 and a mean removal subunit 1442.

[0126] The mean calculation subunit 1441 is used to calculate the mean length and mean angle of the front and rear diameters of the front and rear midlines in all candidate layers.

[0127] Understandably, based on the length of the front and rear diameters of the front and rear midlines in each candidate layer calculated by the front and rear midline diameter length measurement subunit 1431 and the angle of the front and rear midline diameters in each candidate layer calculated by the front and rear midline diameter angle measurement subunit 1432, the average length and average angle of the front and rear midlines of the front and rear midlines in all candidate layers are calculated.

[0128] Mean removal subunit 1442 is used to remove the front-to-back midline diameters where the difference between the length and the mean length exceeds a length threshold and / or the difference between the angle and the mean angle exceeds an angle threshold, thereby obtaining the effective front-to-back midline diameters from multiple candidate layers.

[0129] Understandably, the lengths and angles of the anteroposterior diameters of the anterior and posterior midlines for all candidate layers are filtered to exclude those whose differences from the corresponding mean exceed the corresponding thresholds. For example, the anteroposterior diameters of the anterior and posterior midlines whose lengths differ from the mean lengths by more than 20% of the mean lengths, and / or whose angles differ from the mean angles by more than 10 degrees. Finally, the valid values ​​are retained to obtain the valid anteroposterior diameters of the anterior and posterior midlines from multiple candidate layers.

[0130] The left and right lung anteroposterior diameter measurement unit 145 is used to obtain the left and right lung anteroposterior diameters based on the effective anteroposterior midline anteroposterior diameter and in combination with preset pixel spacing information.

[0131] In one alternative implementation, the left and right lung anteroposterior diameter measurement unit 145 includes a line segment extraction subunit 1451 and a left and right lung anteroposterior diameter calculation subunit 1452.

[0132] The line segment extraction subunit 1451 is used to extract the longest line segment in the left and right lung segmentation masks that is consistent with the direction of the effective anterior-posterior midline, based on the angle of the anteroposterior diameter of the effective anterior-posterior midline in each candidate layer. These segments are then used as the theoretical anteroposterior diameters of the left and right lungs, respectively. Figure 6 The dashed lines shown.

[0133] Understandably, based on the angular direction of the effective anteroposterior diameter of the midline in each candidate layer, the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the effective anteroposterior diameter of the midline is extracted and used as the theoretical anteroposterior diameter of the left lung and the theoretical anteroposterior diameter of the right lung, respectively, to provide key parameters for assessing lung morphology.

[0134] The left and right lung anteroposterior diameter calculation subunit 1452 is used to obtain the preset coefficient in the preset pixel spacing information, calculate the product of the effective anteroposterior diameter of the anterior midline and the preset coefficient to obtain the length of the physical anteroposterior diameter of the anterior midline, calculate the product of the theoretical left lung anteroposterior diameter and the preset coefficient to obtain the length of the left lung anteroposterior diameter, and calculate the product of the theoretical right lung anteroposterior diameter and the preset coefficient to obtain the length of the right lung anteroposterior diameter.

[0135] Understandably, combining lung CT DICOM (Digital Imaging and Communications in Medicine) data, which includes information such as the preset pixel spacing of the image, is crucial for converting pixel length into physical length. Therefore, by extracting the preset coefficients from the preset pixel spacing information and multiplying them by the effective anteroposterior diameter of the anteroposterior midline, we can obtain the actual physical anteroposterior diameter of the anteroposterior midline. Furthermore, by multiplying the preset coefficients from the preset pixel spacing information by the theoretical anteroposterior diameters of the left and right lungs, respectively, we can obtain the actual anteroposterior diameters of the left and right lungs.

[0136] The anteroposterior diameter localization module 140 effectively eliminates outliers through a multi-stage screening strategy, improving the accuracy and reliability of measurement results. It can also accurately measure the length and angle of the anteroposterior diameter, providing key parameters for assessing lung morphology.

[0137] The transverse diameter positioning module 150 is used to locate the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and to determine the transverse diameters of the left and right lungs based on the transverse diameter of the thoracic cage.

[0138] Optionally, the transverse diameter positioning module 150 includes a thoracic transverse diameter determination unit 151, a thoracic transverse diameter length measurement unit 152, and a left and right lung transverse diameter calculation unit 153.

[0139] The transverse diameter determination unit 151 is used to extract the longest line segment perpendicular to the direction of the anteroposterior diameter of the effective anteroposterior midline in the left and right lung segmentation mask based on the angle of the anteroposterior diameter of the effective anteroposterior midline in each candidate layer, and to determine the left and right endpoints of the transverse diameter of the thoracic cage.

[0140] Understandably, among the candidate layers containing the effective anteroposterior diameter of the anteroposterior midline, based on the angular direction of the effective anteroposterior diameter, the longest line segment perpendicular to its direction is found in the left and right lung segmentation mask M, and is taken as the transverse diameter of the thoracic cavity. The left endpoint of the transverse diameter of the thoracic cavity is represented as (x l ,y l ), the right endpoint is represented as (x r ,y r ),like Figure 5 The solid line shown.

[0141] The transverse diameter measurement unit 152 is used to calculate the length of the transverse diameter of the thoracic cavity in each candidate layer using a second preset length calculation formula and based on the left and right endpoints of the transverse diameter of the thoracic cavity in each candidate layer.

[0142] Understandably, the length of the thoracic transverse diameter in each candidate layer can be calculated using the second preset length calculation formula and based on the coordinates of the left and right endpoints of the thoracic transverse diameter in each candidate layer. The second preset length calculation formula is as follows:

[0143]

[0144] In the formula, d ttk x represents the length of the transverse diameter of the thorax in the k-th candidate layer. lk Let x be the x-coordinate of the left endpoint of the transverse diameter of the thorax in the k-th candidate layer. rk Let y be the x-coordinate of the right endpoint of the transverse diameter of the thorax in the k-th candidate layer. lk Let y be the ordinate of the left endpoint of the transverse diameter of the thorax in the k-th candidate layer. rk The ordinate is the right endpoint of the transverse diameter of the thorax in the k-th candidate layer.

[0145] The left and right lung transverse diameter calculation unit 153 is used to extract the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the transverse diameter of the thoracic cage based on the angle of the transverse diameter of the thoracic cage in each candidate layer. These segments are used as the theoretical left lung transverse diameter and the theoretical right lung transverse diameter, respectively. The unit calculates the product of the length of the transverse diameter of the thoracic cage and a preset coefficient to obtain the length of the physical transverse diameter of the thoracic cage. The unit also calculates the product of the length of the theoretical left lung transverse diameter and a preset coefficient to obtain the length of the left lung transverse diameter. Finally, the unit calculates the product of the length of the theoretical right lung transverse diameter and a preset coefficient to obtain the length of the right lung transverse diameter.

[0146] Understandably, based on the angular direction of the transverse diameter of the thoracic cage in each candidate layer, the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the transverse diameter of the thoracic cage is extracted, and used as the theoretical transverse diameter of the left lung and the theoretical transverse diameter of the right lung, respectively, to provide key parameters for assessing lung morphology, such as... Figure 7 The dashed lines shown.

[0147] Next, by multiplying the preset coefficient in the preset pixel spacing information by the length of the transverse diameter of the thoracic cavity, the actual length of the transverse diameter of the thoracic cavity can be obtained. By multiplying the preset coefficient in the preset pixel spacing information by the theoretical length of the transverse diameter of the left lung and the theoretical length of the transverse diameter of the right lung, the actual lengths of the transverse diameter of the left lung and the right lung can be obtained.

[0148] The transverse diameter localization module 150 provides key parameters for a comprehensive assessment of lung morphology by measuring the transverse diameter of the thoracic cavity and the left and right lungs. It achieves a fully automated process from inputting lung CT images to outputting transverse diameter measurement results, thus improving processing efficiency.

[0149] The lung parameter measurement system based on transverse CT scans provided in this application overcomes the shortcomings of existing technologies through modular design, deep learning, multi-stage screening strategies, orientation recognition algorithms, and fully automated processing, achieving significant improvements in robustness, accuracy, and efficiency. The beneficial effects are as follows:

[0150] (1) Higher measurement accuracy and more reliable results: Through precise algorithms and automated processing, the errors caused by manual measurement are reduced, providing accurate parameters for children's lung development research;

[0151] (2) The system design is flexible and highly scalable: It adopts a modular design, with each module being relatively independent, and can be flexibly combined and expanded according to the needs of children's lung development research.

[0152] (3) Fully automated process, greatly improved efficiency: The process from input of lung CT images to output of parameter measurement results is fully automated, without the need for manual intervention, which improves the efficiency of children's lung development research;

[0153] (4) It still performs well in complex scenarios: By adopting a multi-stage screening strategy and filters, it can effectively handle complex situations in children's lung CT images, such as the presence of noise or poor image quality, and ensure the accuracy of measurement results.

[0154] Example 2

[0155] like Figure 8 The diagram shows a flowchart of a lung parameter measurement method based on a lung CT cross-section according to an embodiment of this application. The lung parameter measurement method based on a lung CT cross-section provided in this embodiment is applied to the lung parameter measurement system based on a lung CT cross-section in Embodiment 1, and specifically includes the following steps:

[0156] Step S110: Acquire lung CT images through the image acquisition module;

[0157] Step S120: The lung CT image is processed by the left and right lung segmentation module using the first deep learning model or the first image processing algorithm to generate a left and right lung segmentation mask.

[0158] Step S130: The lung CT image is processed by the bone segmentation module using a second deep learning model or a second image processing algorithm to generate a bone segmentation mask.

[0159] Step S140: The anteroposterior diameter positioning module locates the endpoints of the anteroposterior diameter of the anterior midline based on the left and right lung segmentation mask and the bone segmentation mask, and determines the anteroposterior diameter of the left lung and the anteroposterior diameter of the right lung based on the anteroposterior diameter of the anterior midline.

[0160] In step S150, the transverse diameter positioning module locates the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and determines the transverse diameters of the left and right lungs based on the transverse diameter of the thoracic cage.

[0161] The lung parameter measurement method based on lung CT cross-section provided in this application can achieve the function of the lung parameter measurement system based on lung CT cross-section corresponding to Embodiment 1, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0162] The lung parameter measurement method based on lung CT cross-sections provided in this application improves the reliability of lung development parameter measurement and provides an accurate and consistent parameter measurement method for children's lung development research.

[0163] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the lung parameter measurement method based on lung CT cross-sections described in Embodiment 2.

[0164] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0165] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A lung parameter measurement system based on lung CT cross-sections, characterized in that, The system includes: Image acquisition module, used to acquire lung CT images; The left and right lung segmentation module is used to process the lung CT image using a first deep learning model or a first image processing algorithm to generate a left and right lung segmentation mask. The skeleton segmentation module is used to process the lung CT image using a second deep learning model or a second image processing algorithm to generate a skeleton segmentation mask. The anteroposterior diameter positioning module is used to locate the endpoints of the anteroposterior diameter of the anterior midline based on the left and right lung segmentation mask and the bone segmentation mask, and to determine the anteroposterior diameter of the left lung and the anteroposterior diameter of the right lung based on the endpoints of the anteroposterior diameter of the anterior midline. The transverse diameter positioning module is used to locate the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and to determine the transverse diameters of the left and right lungs based on the endpoints of the transverse diameter of the thoracic cage. The front and rear diameter positioning module includes: The candidate layer determination unit is used to filter out layers containing at least left lung pixels or right lung pixels from the left and right lung segmentation mask as candidate layers, and to select layers within a preset range of the candidate layers as alternative layers. The front-to-back centerline diameter determination unit is used to determine the front end point and the rear end point in each of the candidate layers, and to take the line connecting the front end point and the rear end point as the front-to-back centerline diameter. The front and rear centerline diameter measurement unit is used to calculate the length and angle of the front and rear centerline diameter in each of the candidate layers based on the front end point and rear end point in each of the candidate layers. The front and rear centerline front and rear diameter filtering unit is used to filter the length and angle of the front and rear centerline front and rear diameters in all the candidate layers to obtain the effective front and rear centerline front and rear diameters. The left and right lung anteroposterior diameter measurement unit is used to obtain the left lung anteroposterior diameter and the right lung anteroposterior diameter based on the effective anteroposterior midline anteroposterior diameter and in combination with preset pixel spacing information.

2. The lung parameter measurement system based on lung CT cross-sections according to claim 1, characterized in that, The left and right lung segmentation module includes: The left and right lung segmentation preprocessing unit is used to filter the lung CT image, remove noise points in the lung CT image, obtain the filtered lung CT image, and standardize the filtered lung CT image to obtain the standardized lung CT image. The left and right lung segmentation processing unit is used to process the standardized lung CT image using the first deep learning model or the first image processing algorithm to generate an initial left and right lung segmentation mask. The left and right lung segmentation post-processing unit is used to perform morphological operations on the initial left and right lung segmentation mask to remove noise points and isolated regions in the initial left and right lung segmentation mask, thereby obtaining the left and right lung segmentation mask.

3. The lung parameter measurement system based on lung CT cross-sections according to claim 1, characterized in that, The skeleton segmentation module includes: A bone segmentation preprocessing unit is used to perform histogram equalization on the lung CT images to obtain enhanced lung CT images. The skeleton segmentation processing unit is used to process the enhanced lung CT image using the second deep learning model or the second image processing algorithm to generate an initial skeleton segmentation mask. The bone segmentation post-processing unit is used to perform morphological operations on the initial bone segmentation mask to remove noise points and isolated regions in the initial bone segmentation mask, thereby obtaining the bone segmentation mask.

4. The lung parameter measurement system based on lung CT cross-sections according to claim 1, characterized in that, The unit for determining the anterior and posterior diameters of the anterior and posterior midline includes: The region of interest determination subunit is used to extract the upper and lower preset rectangular regions between the left and right lungs as regions of interest based on the left and right lung segmentation mask, and to determine the corresponding regions of interest in the bone segmentation mask. The front-to-back midline diameter determination subunit is used to extract the midpoint of the lower boundary of the bone segmentation mask in the upper preset range rectangular area as the front point, extract the midpoint of the upper boundary of the bone segmentation mask in the lower preset range rectangular area as the back point, and take the line connecting the front point and the back point as the front-to-back midline diameter. The front and rear midline diameter measurement unit includes: The front and rear centerline diameter length measurement subunit is used to calculate the length of the front and rear centerline diameter of each of the candidate layers using a first preset length calculation formula and based on the front and rear endpoints of the front and rear centerline diameter of each of the candidate layers. The front and rear centerline front and rear diameter angle measurement subunit is used to calculate the angle of the front and rear centerline front and rear diameters in each of the candidate layers using a preset angle calculation formula and based on the front end point and rear end point in each of the candidate layers. The formula for calculating the first preset length is as follows: The formula for calculating the preset angle is: In the formula, The length of the front-to-back diameter of the front-to-back midline in the candidate layer of the i-th layer. The angle between the front and rear diameters of the front and rear midline in the candidate layers of the i-th layer. Let x be the x-coordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the i-th candidate layer. Let x be the x-coordinate of the rear end point of the front-rear diameter of the front-rear midline in the candidate layer of layer i. Let be the ordinate of the anterior endpoint of the anterior-posterior diameter of the anterior-posterior midline in the i-th candidate layer. The ordinate of the rear end point of the front-rear diameter of the front-rear midline in the candidate layer of the i-th layer.

5. The lung parameter measurement system based on lung CT cross-sections according to claim 1, characterized in that, The anterior and posterior diameter screening unit for the anterior and posterior midline includes: The mean calculation subunit is used to calculate the mean length and mean angle of the front and rear diameters of the front and rear midlines in all the candidate layers; The mean rejection subunit is used to reject the front-to-back midline diameters where the difference between the length and the mean length exceeds a length threshold and / or the difference between the angle and the mean angle exceeds an angle threshold, thereby obtaining the effective front-to-back midline diameters from the multiple candidate layers. The left and right lung anteroposterior diameter measurement unit includes: The line segment extraction subunit is used to extract the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the effective anterior and posterior midline based on the angle of the anteroposterior diameter of the effective anterior and posterior midline in each of the candidate layers, and use them as the theoretical anteroposterior diameter of the left lung and the theoretical anteroposterior diameter of the right lung, respectively. The left and right lung anteroposterior diameter calculation subunit is used to obtain the preset coefficient in the preset pixel spacing information, calculate the product of the length of the effective anteroposterior midline and the preset coefficient to obtain the length of the physical anteroposterior midline, calculate the product of the length of the theoretical left lung anteroposterior diameter and the preset coefficient to obtain the length of the left lung anteroposterior diameter, and calculate the product of the length of the theoretical right lung anteroposterior diameter and the preset coefficient to obtain the length of the right lung anteroposterior diameter.

6. The lung parameter measurement system based on lung CT cross-sections according to claim 5, characterized in that, The transverse diameter positioning module includes: The transverse diameter determination unit is used to extract the longest line segment perpendicular to the direction of the anteroposterior diameter of the effective anteroposterior midline in the left and right lung segmentation mask based on the angle of the anteroposterior diameter of the effective anteroposterior midline in each of the candidate layers, and use it as the transverse diameter of the thoracic cage, and determine the left and right endpoints of the transverse diameter of the thoracic cage. The transverse diameter measurement unit is used to calculate the length of the transverse diameter of the thoracic cavity in each of the candidate layers using a second preset length calculation formula and based on the left and right endpoints of the transverse diameter of the thoracic cavity in each of the candidate layers. The left and right lung transverse diameter calculation unit is used to extract the longest line segment in the left and right lung segmentation mask that is consistent with the direction of the thoracic transverse diameter based on the angle of the thoracic transverse diameter in each of the candidate layers, and use them as the theoretical left lung transverse diameter and the theoretical right lung transverse diameter, respectively. The unit calculates the product of the length of the thoracic transverse diameter and the preset coefficient to obtain the length of the physical thoracic transverse diameter. The unit also calculates the product of the length of the theoretical left lung transverse diameter and the preset coefficient to obtain the length of the left lung transverse diameter. Finally, the unit calculates the product of the length of the theoretical right lung transverse diameter and the preset coefficient to obtain the length of the right lung transverse diameter. The formula for calculating the second preset length is as follows: In the formula, The length of the transverse diameter of the thorax in the candidate layer of the k-th layer. Let x be the x-coordinate of the left endpoint of the transverse diameter of the thorax in the candidate layer of layer k. Let x be the x-coordinate of the right endpoint of the transverse diameter of the thorax in the candidate layer of layer k. Let be the ordinate of the left endpoint of the transverse diameter of the thorax in the candidate layer of layer k. The ordinate is the right endpoint of the transverse diameter of the thorax in the candidate layer of the k-th layer.

7. A method for measuring lung parameters based on transverse sections of lung CT scans, characterized in that, The method, applied to the lung parameter measurement system based on lung CT cross-sections as described in any one of claims 1-6, comprises: Lung CT images are acquired through the image acquisition module; The lung CT images are processed by the left and right lung segmentation module using a first deep learning model or a first image processing algorithm to generate left and right lung segmentation masks. The lung CT image is processed by the bone segmentation module using a second deep learning model or a second image processing algorithm to generate a bone segmentation mask. The anteroposterior diameter positioning module locates the endpoints of the anteroposterior diameter of the anterior midline based on the left and right lung segmentation masks and the bone segmentation mask, and determines the anteroposterior diameter of the left and right lungs based on the endpoints of the anteroposterior diameter of the anterior midline. The transverse diameter positioning module locates the endpoints of the transverse diameter of the thoracic cage based on the left and right lung segmentation mask, the skeletal segmentation mask, and the endpoints of the anteroposterior diameter of the anterior and posterior midline, and determines the transverse diameters of the left and right lungs based on the endpoints of the transverse diameter of the thoracic cage.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the lung parameter measurement method based on lung CT cross-sections as described in claim 7.

Images