Health detection system and method based on CT image

Abstract

The invention discloses a health detection system and method based on a CT image, and relates to the technical field of image recognition, an image acquisition module is used for acquiring a lung CT image and lung image related data, and then an image processing analysis module is used for carrying out image quality comprehensive calculation on the lung image related data to obtain a comprehensive image quality coefficient; the method comprises the following steps of: acquiring a lung CT image, determining whether the quality of the corresponding lung CT image meets a detection requirement or not, processing and classifying the matched lung CT image to obtain a classified lung CT image, extracting a lung structure diagram from the classified lung CT image by a data extraction processing module, acquiring lung health index data, performing lung health comprehensive calculation and proportion assignment, and outputting the lung health index data. According to the method, the lung CT image is obtained, the lung overall health index is obtained, the lung overall health index is input into the pre-established lung health evaluation model to obtain the lung health evaluation result, the treatment scheme is determined, and the function of automatically judging and treating lung health according to the lung CT image and related data is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a health detection system and method based on CT images. Background Art

[0002] At present, for the health detection of lungs, clinical symptoms, exercise, imaging examinations and other methods can be used to check whether the lungs are healthy. The specific contents are as follows: Clinical symptoms: In life, if the lung function is normal, there will generally be no symptoms such as coughing, sputum, and shortness of breath, and you need to pay attention to observation. Exercise: If you frequently experience severe panting, darkening of lips, excessive fatigue, etc. during exercise, it means that your lung function may be abnormal, and it is recommended to check in time. Imaging examination: You can go to the hospital to perform corresponding assessments of lung function through imaging examinations such as CT and X-rays. The test results of normal and abnormal lungs, as well as different types of lung diseases are different, and you can judge whether the lungs are healthy.

[0003] The imaging method for lung health examination is more accurate. The existing technology usually uses CT instruments to detect lung health using CT images. After the images are taken, the lung health status is tested and evaluated through manual comparison. The comparison efficiency is low and the test results are not accurate enough. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a health detection system and method based on CT images, which can automatically judge and treat lung health based on lung CT images and related data.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a health detection system based on CT images, comprising:

[0006] Image acquisition module: used to acquire lung CT images and lung image-related data, and send the lung CT images and lung image-related data to the image processing and analysis module, wherein the lung image-related data includes image brightness, image contrast, image resolution and image frame rate;

[0007] Image processing and analysis module: used to mark lung image related data, use the marked lung image related data to perform comprehensive image quality calculation, obtain a comprehensive image quality coefficient, set an image quality coefficient threshold, and determine whether the quality of the corresponding lung CT image meets the detection requirements based on the comparison result of the comprehensive image quality coefficient and the image quality coefficient threshold. If not, send a re-acquisition signal to the image acquisition module for re-acquisition. If it meets, pre-process the lung CT image, extract features and classify the processed lung CT image to obtain a classified lung CT image, and send the classified lung CT image to the data extraction and processing module, wherein the classified lung CT image includes: left upper lobe image, left lower lobe image, right upper lobe image, right middle lobe image and right lower lobe image;

[0008] Data extraction and processing module: used to extract the lung structure diagram from the classified lung CT image and obtain the lung health index data of the corresponding patient, perform comprehensive lung health calculation based on the obtained lung structure diagram and lung health index data, and obtain the comprehensive lung health index, wherein the lung structure diagram includes a lung window diagram and a mediastinum window diagram, and the lung health index data includes vital capacity data, total lung capacity data, and residual volume data; based on the calculated comprehensive lung health index and the classified lung CT image divided into five parts, perform proportional assignment to obtain the overall lung health index, and send the overall lung health index to the health analysis module;

[0009] Health analysis module: used to input the overall lung health index into the pre-established lung health assessment model, and output the lung health assessment result; send the lung health assessment result to the execution module;

[0010] Execution module: used to display and execute the lung health assessment results, and determine the treatment plan based on the lung health assessment results.

[0011] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the process of the image processing and analysis module performing comprehensive calculation of image quality includes the following steps:

[0012] The lung image-related data are marked, wherein the image brightness is marked as Li, the image contrast is marked as Di, the image resolution is marked as Fi, and the image frame rate is marked as Zi; wherein i is the number of acquisition times of the image acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition module;

[0013] The comprehensive calculation formula for image quality is as follows:

[0014]

[0015] Wherein, Ti is the comprehensive image quality coefficient, a is the image brightness correlation coefficient, b is the image contrast correlation coefficient, k1 is the image resolution correlation coefficient, k2 is the image frame rate correlation coefficient, F0 is the preset standard image resolution coefficient, and Z0 is the preset standard image frame rate coefficient;

[0016] Set the image quality coefficient threshold T0

[0017] If Ti ≥ T0, the lung CT image corresponding to the comprehensive image quality coefficient is preprocessed;

[0018] If Ti<T0, a re-capture signal is sent to the image acquisition module.

[0019] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the image processing and analysis module extracts and classifies features of the lung CT image, and segments the entire lung CT image according to the classification result, and the process is as follows:

[0020] The feature extraction of the lungs according to the position is to classify and extract the position of the internal structure of the lungs, wherein the features extracted based on the internal structure of the lungs include:

[0021] Features of the left upper lobe of the lung, features of the left lower lobe of the lung, features of the right upper lobe of the lung, features of the right middle lobe of the lung, and features of the right lower lobe of the lung;

[0022] The lung CT image is classified according to the features extracted from the internal structure of the lung to obtain a classified lung CT image.

[0023] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the data extraction and processing module performs data identification on the lung health index data, wherein the vital capacity data is marked as Hj, the total lung volume data is marked as Sj, and the residual volume data is marked as Cj, wherein j is the number of collection times of the data extraction and processing module, and j=1, 2, 3, ..., m, and m is the total number of collection times of the data extraction and processing module;

[0024] Extract the proportional characteristic coefficients of the lung window image and the mediastinum window image of the lung structure image, and obtain the proportional coefficients of the lung window image and the mediastinum window image;

[0025] Using the formula

[0026] Where Kj is the comprehensive index of lung health, t1 and t2 are both preset proportional coefficients; P1 is the proportional coefficient of the lung window image, and P2 is the proportional coefficient of the mediastinum window image.

[0027] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the calculation process of the proportion assignment of the data extraction processing module is as follows:

[0028]

[0029] Where Krj is the overall lung health index, q1 is the left upper lobe proportion assignment coefficient, q2 is the left lower lobe proportion assignment coefficient, q3 is the right upper lobe proportion assignment coefficient, q4 is the right middle lobe proportion assignment coefficient, and q5 is the right lower lobe proportion assignment coefficient.

[0030] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the process of the health analysis module establishing a lung health assessment model based on the artificial intelligence model is as follows:

[0031] Obtaining preset standard lung health index data and lung structure-related data through a server inside the control center, wherein the standard lung health index data includes standard vital capacity data, standard total lung volume data, and standard residual volume data;

[0032] The artificial intelligence model is trained using preset standard lung health indicator data and lung structure-related data to obtain and store a lung health assessment model.

[0033] In a second aspect, in order to achieve the above-mentioned object, the present invention discloses a health detection method based on CT images, the method comprising the following steps:

[0034] Acquire a lung CT image and lung image-related data, mark the lung image-related data, and use the marked lung image-related data to perform comprehensive image quality calculation to obtain a comprehensive image quality coefficient, wherein the lung image-related data includes image brightness, image contrast, image resolution, and image frame rate;

[0035] An image quality coefficient threshold is set, and whether the quality of the corresponding lung CT image meets the detection requirements is determined according to the comparison result between the comprehensive image quality coefficient and the image quality coefficient threshold. If not, the image is re-collected; if it meets, the lung CT image is pre-processed, and the processed lung CT image is feature extracted and classified to obtain a classified lung CT image;

[0036] Extracting a lung structure diagram and obtaining lung health index data from the classified lung CT image, performing a comprehensive lung health calculation based on the obtained lung structure diagram and lung health index data, and obtaining a comprehensive lung health index, wherein the lung structure diagram includes a lung window diagram and a mediastinum window diagram, and the lung health index data includes vital capacity data, total lung capacity data, and residual volume data;

[0037] Based on the calculated comprehensive lung health index, proportional values ​​are assigned according to the classified lung CT images divided into five parts to obtain the overall lung health index, which is then input into a pre-established lung health assessment model to output the lung health assessment result, based on which a treatment plan is determined.

[0038] In another aspect of the present invention, in order to achieve the above-mentioned purpose, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, a CT image-based health detection system as described above is adopted.

[0039] Beneficial effects of the present invention:

[0040] The present invention collects lung CT images and lung image-related data through an image acquisition module, and then performs comprehensive image quality calculation on the lung image-related data through an image processing and analysis module to obtain a comprehensive image quality coefficient, and sets a threshold value for comparison with the comprehensive image quality coefficient to determine whether the quality of the corresponding lung CT image meets the detection requirements according to the comparison result, and processes and classifies the qualified lung CT images to obtain classified lung CT images, and the data extraction and processing module extracts the lung structure diagram of the classified lung CT images and obtains lung health index data, performs comprehensive lung health calculation to obtain a comprehensive lung health index, and performs proportional assignment based on the calculated comprehensive lung health index to obtain an overall lung health index, and inputs the overall lung health index into a pre-established lung health assessment model to output a lung health assessment result, and determines a treatment plan based on the lung health assessment result, thereby realizing the function of automatically judging and treating lung health according to the lung CT images and related data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0043] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Embodiment 1:

[0046] The following is an introduction to the relevant terms involved in the embodiments of the present application:

[0047] The lung CT image is a cross-sectional schematic diagram of a chest CT inspiratory scan, in which the pleura, heart, bones, etc. have a higher grayscale; the lung parenchyma and tracheal cavity are filled with gas and have a lower grayscale, separated by a slightly brighter wall. The trachea and blood vessels are elliptical in cross section; as the trachea continues to split, the lumen becomes narrower, the wall becomes thinner, and the boundary between the two and the surrounding parenchyma gradually blurs; the pulmonary blood vessels also decrease in grayscale at the edge of the lung as they split. Due to the discharge of gas, the grayscale of the overall lung parenchyma and tracheal cavity increases in the expiratory scan, and most branches are closed and invisible in the image. In fact, imaging defects such as image noise, partial volume effect, motion artifacts, differences in anatomical structures between different individuals, scales, and locations, and tissue lesions will cause changes in the image characteristics of each structure.

[0048] Image preprocessing is the process of sorting out each text image and handing it over to the recognition module for recognition. In image analysis, it is the processing performed on the input image before feature extraction, segmentation and matching. The main purpose of image preprocessing is to eliminate irrelevant information in the image, restore useful real information, enhance the detectability of relevant information and simplify data to the maximum extent, thereby improving the reliability of feature extraction, image segmentation, matching and recognition.

[0049] like Figure 1 As shown, a health detection system based on CT images includes:

[0050] Image acquisition module, image processing and analysis module, data extraction and processing module, health analysis module and execution module;

[0051] The image acquisition module is used to acquire lung CT images and lung image related data, and send the acquired lung CT images and lung image related data to the image processing and analysis module for processing, wherein the image acquisition module acquires the lung CT images by scanning the lung position of a lying patient through a CT detector to obtain a lung CT image; the lung image related data includes image brightness, image contrast, image resolution and image frame rate;

[0052] It should be noted that the acquisition process of the lung image-related data is as follows: the image brightness, image contrast, image resolution and image frame rate are acquired and collected by adjusting the image software; specifically, each lung CT image corresponds to each set of lung image-related data one by one;

[0053] The image processing and analysis module is used to process the lung CT image and lung image-related data images. Specifically, the processing process of the image processing and analysis module includes the following steps:

[0054] The lung image-related data are marked, wherein the image brightness is marked as Li, the image contrast is marked as Di, the image resolution is marked as Fi, and the image frame rate is marked as Zi; wherein i is the number of acquisition times of the image acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition module;

[0055] The image quality is comprehensively calculated using the labeled lung image-related data to obtain a comprehensive image quality coefficient. Specifically, the image quality comprehensive calculation formula of the image processing and analysis module is as follows:

[0056]

[0057] Wherein, Ti is the comprehensive image quality coefficient, a is the image brightness correlation coefficient, b is the image contrast correlation coefficient, k1 is the image resolution correlation coefficient, k2 is the image frame rate correlation coefficient, F0 is the preset standard image resolution coefficient, and Z0 is the preset standard image frame rate coefficient;

[0058] Furthermore, in the specific implementation process, the preset standard image resolution coefficient and the preset standard image frame rate coefficient are obtained by collecting the image resolution and image frame rate in daily life, and then performing multiple simulation calculations and taking the average value of the data;

[0059] Among them, in this embodiment, the image brightness correlation coefficient, image contrast correlation coefficient, image resolution correlation coefficient and image frame rate correlation coefficient are obtained by comprehensive evaluation and calculation based on the influence of external factors when the image brightness, image contrast, image resolution and image frame rate are obtained daily by this application, including human factors, machine detection and environmental factors, etc.; human factors are some factors caused by human operation or improper scanning;

[0060] The image quality coefficient threshold T0 is set, and the calculated comprehensive image quality coefficient Ti is compared with the image quality coefficient threshold T0. According to the comparison result, it is determined whether the quality of the corresponding lung CT image meets the detection requirements. Specifically, the comparison process is as follows:

[0061] If Ti ≥ T0, it means that the quality of the lung CT image meets the later detection standard, and the lung CT image corresponding to the comprehensive image quality coefficient is preprocessed;

[0062] If Ti<T0, it means that the quality of the lung CT image does not meet the later detection standard, and a re-acquisition signal is sent to the image acquisition module, and the image acquisition module re-acquires the lung CT image and lung image-related data;

[0063] The lung CT image is preprocessed to obtain a processed lung CT image, wherein the lung CT image preprocessing includes:

[0064] Image enhancement: Improve image quality by filtering, sharpening, etc., highlight features of interest, and suppress unnecessary details

[0065] Median filter: filter out impulse noise or particle noise and protect image edges;

[0066] Image sharpening: The purpose of image sharpening is to make the edges of the image steeper and clearer.

[0067] The processed lung CT image is segmented. Specifically, the features of the lung CT image are extracted and classified, and the entire lung CT image is segmented according to the classification results. The process is as follows:

[0068] The feature extraction of the lungs according to the position is to classify and extract the position of the internal structure of the lungs, wherein the features extracted based on the internal structure of the lungs include:

[0069] Features of the left upper lobe of the lung, features of the left lower lobe of the lung, features of the right upper lobe of the lung, features of the right middle lobe of the lung, and features of the right lower lobe of the lung;

[0070] Classifying the lung CT images according to the features extracted from the internal structure of the lungs to obtain classified lung CT images, wherein the classified lung CT images include: left upper lobe images, left lower lobe images, right upper lobe images, right middle lobe images, and right lower lobe images;

[0071] The classified lung CT images are sent to the data extraction and processing module for data extraction and processing;

[0072] The data extraction processing module performs data extraction processing on the received lung CT image. Specifically, the extraction processing process of the data extraction processing module includes the following steps:

[0073] Extracting a lung structure map from the classified lung CT image, wherein the lung structure map includes a lung window map and a mediastinum window map, and acquiring lung health index data of the corresponding patient based on the classified lung CT image, wherein the lung health index data includes vital capacity data, total lung capacity data, and residual volume data;

[0074] Based on the obtained lung structure diagram and lung health index data, a comprehensive lung health calculation is performed to obtain a comprehensive lung health index. Specifically, the comprehensive lung health calculation process of the data extraction and processing module includes the following steps:

[0075] Data identification is performed on the lung health index data, wherein the vital capacity data is marked as Hj, the total lung volume data is marked as Sj, and the residual volume data is marked as Cj, wherein j is the number of acquisition times of the data extraction processing module, and j=1, 2, 3, ..., m, and m is the total number of acquisition times of the data extraction processing module;

[0076] Extract the proportional characteristic coefficients of the lung window image and the mediastinum window image of the lung structure image, obtain the proportional coefficient of the lung window image and the proportional coefficient of the mediastinum window image, mark the proportional coefficient of the lung window image as P1, and mark the proportional coefficient of the mediastinum window image as P2;

[0077] The lung window image ratio coefficient and the mediastinum window image ratio coefficient are coefficients for calculating the comprehensive lung health index by giving different proportions to the lung health index at different positions of the lungs;

[0078] Using the formula

[0079] Where Kj is the comprehensive index of lung health, t1 and t2 are both preset proportional coefficients;

[0080] Based on the calculated comprehensive lung health index, the proportion of the classified lung CT images divided into five parts is assigned to obtain the overall lung health index; wherein, the calculation process of the proportion assignment is as follows:

[0081]

[0082] Where Krj is the overall lung health index, q1 is the left upper lobe proportion assignment coefficient, q2 is the left lower lobe proportion assignment coefficient, q3 is the right upper lobe proportion assignment coefficient, q4 is the right middle lobe proportion assignment coefficient, and q5 is the right lower lobe proportion assignment coefficient;

[0083] It should be further explained that the left upper lobe proportion assignment coefficient, the left lower lobe proportion assignment coefficient, the right upper lobe proportion assignment coefficient, the right middle lobe proportion assignment coefficient and the right lower lobe proportion assignment coefficient are obtained by proportion assignment based on the proportions of the five parts of the lung lobes of a large number of normal adults and the positions of the lobes;

[0084] Sending overall lung health indicators to the health analysis module;

[0085] After receiving the transmitted overall lung health index, the health analysis module performs health analysis. Specifically, the analysis process of the health analysis module includes the following steps:

[0086] Inputting the overall lung health index into a pre-established lung health assessment model, and outputting a lung health assessment result; and sending the lung health assessment result to an execution module;

[0087] Wherein, the pre-established lung health assessment model is established based on an artificial intelligence model;

[0088] Specifically, the present invention is further described below by way of embodiments:

[0089] The process of establishing a lung health assessment model based on an artificial intelligence model is as follows:

[0090] Obtaining preset standard lung health index data and lung structure-related data through a server inside the control center, wherein the standard lung health index data includes standard vital capacity data, standard total lung volume data, and standard residual volume data;

[0091] The artificial intelligence model is trained by using preset standard lung health index data and lung structure related data to obtain and store a lung health assessment model. The artificial intelligence model includes a deep convolutional neural network model and an RBF neural network model.

[0092] After receiving the lung health assessment result sent by the health analysis module, the execution module displays and executes the lung health assessment result, and determines a treatment plan based on the lung health assessment result, wherein the treatment plan includes a primary treatment plan, a secondary treatment plan, and a tertiary treatment plan, and the higher the level number, the greater the difficulty of the treatment.

[0093] Embodiment 2: A health detection method based on CT images, comprising the following steps:

[0094] S101: Acquire a lung CT image and lung image-related data, mark the lung image-related data, and use the marked lung image-related data to perform comprehensive image quality calculation to obtain a comprehensive image quality coefficient, wherein the lung image-related data includes image brightness, image contrast, image resolution, and image frame rate;

[0095] S102: setting an image quality coefficient threshold, and determining whether the quality of the corresponding lung CT image meets the detection requirements according to the comparison result of the comprehensive image quality coefficient and the image quality coefficient threshold, if not, re-collecting, if meeting, pre-processing the lung CT image, extracting features from the processed lung CT image and classifying it, to obtain a classified lung CT image;

[0096] S103: extracting a lung structure diagram from the classified lung CT image and obtaining lung health index data, and performing a comprehensive lung health calculation based on the obtained lung structure diagram and lung health index data to obtain a comprehensive lung health index, wherein the lung structure diagram includes a lung window diagram and a mediastinum window diagram, and the lung health index data includes vital capacity data, total lung capacity data, and residual volume data;

[0097] S104: Based on the calculated comprehensive lung health index, proportional values ​​are assigned according to the classified lung CT images divided into five parts to obtain the overall lung health index, which is input into a pre-established lung health assessment model to output a lung health assessment result, and a treatment plan is determined based on the lung health assessment result.

[0098] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0099] It needs to be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0100] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0102] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.

Claims

1. A health detection system based on CT images, characterized in that: include: Image acquisition module: used to acquire lung CT images and lung image-related data, and send the lung CT images and lung image-related data to the image processing and analysis module, wherein the lung image-related data includes image brightness, image contrast, image resolution and image frame rate; Image processing and analysis module: used to mark lung image related data, use the marked lung image related data to perform comprehensive image quality calculation, obtain a comprehensive image quality coefficient, set an image quality coefficient threshold, and determine whether the quality of the corresponding lung CT image meets the detection requirements based on the comparison result of the comprehensive image quality coefficient and the image quality coefficient threshold. If not, send a re-acquisition signal to the image acquisition module for re-acquisition. If it meets, pre-process the lung CT image, extract features and classify the processed lung CT image to obtain a classified lung CT image, and send the classified lung CT image to the data extraction and processing module, wherein the classified lung CT image includes: left upper lobe image, left lower lobe image, right upper lobe image, right middle lobe image and right lower lobe image; Data extraction and processing module: used to extract the lung structure diagram from the classified lung CT image and obtain the lung health index data of the corresponding patient, perform comprehensive lung health calculation based on the obtained lung structure diagram and lung health index data, and obtain the comprehensive lung health index, wherein the lung structure diagram includes a lung window diagram and a mediastinum window diagram, and the lung health index data includes vital capacity data, total lung capacity data, and residual volume data; based on the calculated comprehensive lung health index and the classified lung CT image divided into five parts, perform proportional assignment to obtain the overall lung health index, and send the overall lung health index to the health analysis module; Health analysis module: used to input the overall lung health index into the pre-established lung health assessment model, and output the lung health assessment result; send the lung health assessment result to the execution module; Execution module: used to display and execute the lung health assessment results, and determine the treatment plan based on the lung health assessment results.

2. A health detection system based on CT images according to claim 1, characterized in that: The process of performing comprehensive calculation of image quality by the image processing and analysis module comprises the following steps: The lung image-related data are marked, wherein the image brightness is marked as Li, the image contrast is marked as Di, the image resolution is marked as Fi, and the image frame rate is marked as Zi; wherein i is the number of acquisition times of the image acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition module; The comprehensive calculation formula for image quality is as follows: Wherein, Ti is the comprehensive image quality coefficient, a is the image brightness correlation coefficient, b is the image contrast correlation coefficient, k1 is the image resolution correlation coefficient, k2 is the image frame rate correlation coefficient, F0 is the preset standard image resolution coefficient, and Z0 is the preset standard image frame rate coefficient; Set the image quality coefficient threshold T0 If Ti ≥ T0, the lung CT image corresponding to the comprehensive image quality coefficient is preprocessed; If Ti<T0, a re-capture signal is sent to the image acquisition module.

3. A health detection system based on CT images according to claim 2, characterized in that: The image processing and analysis module extracts and classifies features of the lung CT image and segments the entire lung CT image according to the classification results. The process is as follows: The feature extraction of the lungs according to the position is to classify and extract the position of the internal structure of the lungs, wherein the features extracted based on the internal structure of the lungs include: Features of the left upper lobe of the lung, features of the left lower lobe of the lung, features of the right upper lobe of the lung, features of the right middle lobe of the lung, and features of the right lower lobe of the lung; The lung CT image is classified according to the features extracted from the internal structure of the lung to obtain a classified lung CT image.

4. The CT image-based health detection system according to claim 1, characterized in that: The data extraction and processing module performs data identification on the lung health index data, wherein the vital capacity data is marked as Hj, the total lung capacity data is marked as Sj, and the residual volume data is marked as Cj, wherein j is the number of collection times of the data extraction and processing module, and j=1, 2, 3, ..., m, and m is the total number of collection times of the data extraction and processing module; Extract the proportional characteristic coefficients of the lung window image and the mediastinum window image of the lung structure image, and obtain the proportional coefficients of the lung window image and the mediastinum window image; Where Kj is the comprehensive index of lung health, t1 and t2 are both preset proportional coefficients; P1 is the proportional coefficient of the lung window image, and P2 is the proportional coefficient of the mediastinum window image.

5. The CT image-based health detection system according to claim 4, characterized in that: The calculation process of the data extraction processing module ratio assignment is as follows: Where Krj is the overall lung health index, q1 is the left upper lobe proportion assignment coefficient, q2 is the left lower lobe proportion assignment coefficient, q3 is the right upper lobe proportion assignment coefficient, q4 is the right middle lobe proportion assignment coefficient, and q5 is the right lower lobe proportion assignment coefficient.

6. The CT image-based health detection system according to claim 1, characterized in that: The process of the health analysis module establishing a lung health assessment model based on the artificial intelligence model is as follows: Obtaining preset standard lung health index data and lung structure-related data through a server inside the control center, wherein the standard lung health index data includes standard vital capacity data, standard total lung volume data, and standard residual volume data; The artificial intelligence model is trained using preset standard lung health indicator data and lung structure-related data to obtain and store a lung health assessment model.

7. A health detection method based on CT images, characterized in that: The method comprises the following steps: Acquire a lung CT image and lung image-related data, mark the lung image-related data, and use the marked lung image-related data to perform comprehensive image quality calculation to obtain a comprehensive image quality coefficient, wherein the lung image-related data includes image brightness, image contrast, image resolution, and image frame rate; An image quality coefficient threshold is set, and whether the quality of the corresponding lung CT image meets the detection requirements is determined according to the comparison result between the comprehensive image quality coefficient and the image quality coefficient threshold. If not, the image is re-collected; if it meets, the lung CT image is pre-processed, and the processed lung CT image is feature extracted and classified to obtain a classified lung CT image; Extracting a lung structure diagram and obtaining lung health index data from the classified lung CT image, performing a comprehensive lung health calculation based on the obtained lung structure diagram and lung health index data, and obtaining a comprehensive lung health index, wherein the lung structure diagram includes a lung window diagram and a mediastinum window diagram, and the lung health index data includes vital capacity data, total lung capacity data, and residual volume data; Based on the calculated comprehensive lung health index, proportional values ​​are assigned according to the classified lung CT images divided into five parts to obtain the overall lung health index, which is then input into a pre-established lung health assessment model to output the lung health assessment result, based on which a treatment plan is determined.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: The memory stores a computer program that can be run on the processor. When the processor loads and executes the computer program, a CT image-based health detection system according to any one of claims 1 to 6 is adopted.

Images