A lung lesion analysis system based on parameter response graph and image generation system

Abstract

The present invention implements a lung analysis system based on a parameter response graph and image generation system. It consists of a data collection and management module, an image registration module, a controllable image generation module, a parameter response graph analysis module, and a disease progression assessment module. The data collection and management module interfaces with the hospital information system and CT image collection equipment; the image registration module receives a patient's biphasic CT scan image and generates a registered biphasic CT image; the controllable image generation module receives a patient's single inspiratory phase CT scan image as input and generates a registered expiratory phase CT scan image; the parameter response graph analysis module obtains multiple parameter response graph analysis and assessment results for assessing a patient's organic lung lesions; and the disease progression assessment module predicts a patient's lung function. This solves the problems of difficulty in collecting biphasic CT images and the lack of ability to assess a patient's disease progression, which are common with parameter response graph methods.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a lung lesion analysis system based on a parameter response graph and an image generation system. Background Art

[0002] Chronic obstructive pulmonary disease (COPD) is a chronic respiratory disease characterized by airflow obstruction and lung dysfunction. Smoking is one of the main causes of COPD, but it is also associated with air pollution, infection, chemical contamination, and occupational dust.

[0003] COPD is a chronic disease in which patients may gradually lose lung function without realizing it. Usually, by the time symptoms appear, the disease has already entered a later stage, at which point the loss of lung function is difficult to reverse. Early detection of the disease and timely implementation of effective intervention measures are critical, which can significantly slow the progression of the disease, improve the patient's quality of life, reduce the economic burden on patients and their families, and reduce the risk of death from the disease. In addition, COPD is often accompanied by many serious complications (such as heart disease, osteoporosis, etc.), which impose a huge burden on patients and society. Therefore, early diagnosis and treatment of COPD not only have important clinical value, but are also of great significance to the patient's health and quality of life. In addition, regular follow-up of COPD patients can help monitor disease progression, evaluate treatment effectiveness, and improve patients' quality of life.

[0004] Chest CT plays an important role in the diagnosis and treatment of COPD patients. It can show the type, extent, and distribution of lung lesions, thereby helping doctors evaluate the progression of the disease and the effectiveness of treatment. However, the current analysis of CT scan images is mainly carried out through doctors' naked eye observation and sensory evaluation. There is a lack of quantitative evaluation and quantitative comparison of specific lung lesions, making it difficult to accurately reflect the changes and progression of lung lesions. In addition, current CT examinations can only provide images of lung structure and are not associated with the assessment of lung function and airflow obstruction. It is impossible to use the patient's organic lung lesion information in the CT examination results to estimate the patient's respiratory function performance and evaluate the progression of the disease.

[0005] In recent years, computer-aided diagnosis techniques and quantitative analysis methods based on CT images have been widely used, such as parametric response mapping (PRM). PRM is a lung disease assessment method based on high-resolution CT images. By registering and analyzing end-inspiratory and end-expiratory lung images, it can provide a more accurate quantitative assessment of the patient's emphysema severity, airway wall lesions, pulmonary vascular lesions, and treatment responsiveness. Therefore, PRM has the following value in the diagnosis and treatment of COPD:

[0006] 1. Help establish a direct correlation between a patient's organic lung lesions and functional lesions: PRM can quantitatively assess the damage to lung tissue in different lung regions of a patient, thereby determining their ventilation function, and further helping to determine the relationship between the patient's lung function and organic lesions through subsequent algorithmic research.

[0007] 2. Helps in early diagnosis of COPD: PRM can detect smaller organic lesions in the patient's lungs when the patient has no lung function, thus helping doctors diagnose COPD earlier and take timely measures to prevent further development of the disease.

[0008] 3. Monitor changes in patients' conditions: PRM can quantitatively evaluate and compare the lung lesions shown in multiple CT examinations of COPD patients, thereby monitoring changes in patients' conditions, evaluating the progression of the disease and the effectiveness of treatment.

[0009] As a new lung imaging analysis method, parametric response mapping (PRM) has shown broad application prospects and clinical significance in the diagnosis and treatment of COPD. However, PRM has not been widely used in clinical practice. One of the reasons is that the required biphasic lung CT scan images at the end of deep inspiration and normal expiration are difficult to obtain. For elderly patients or patients with severe conditions, there may be insufficient exhalation or inability to hold the breath for a long time. In addition, the existing PRM analysis method cannot incorporate the historical CT scan results of multiple single inspiratory phases of COPD patients into the analysis to comprehensively assess the progression of the patient's lung lesions. Summary of the Invention

[0010] To address the problem that existing parameter response graph analysis methods can only be used for inspiratory-expiratory biphasic chest CT image pairs from a single examination, and the resulting difficulty in collecting biphasic CT images, lack of ability to assess the patient's disease progression, and inability to utilize them, the present invention first proposes a lung lesion analysis method based on parameter response graphs that is compatible with both single-phase and biphasic chest CT scan images. The method analyzes inspiratory-expiratory biphasic chest CT image pairs and single inspiratory chest CT images to determine the status and development trend of a patient's lung lesions. For inspiratory-expiratory biphasic chest CT image pairs, the method first registers them to obtain a registered biphasic CT image pair. For single inspiratory CT images, the method uses an image generation method to generate a missing expiratory CT image based on the single inspiratory CT image, which has been registered with the inspiratory CT image, similarly obtaining a registered biphasic CT image pair. Finally, the method uses a parameter response graph-based analysis method on the registered biphasic CT image pair to analyze the patient's lung lesions and determine the extent, distribution, and development trend of various distributed lesions. Compared with the existing lung lesion analysis method based on parameter response graph, this method is not only limited to the analysis of paired expiratory-inspiratory biphasic CT scans, but can also realize the parameter response graph analysis of single expiratory phase CT scans commonly used in clinical practice by supplementing the missing inspiratory phase CT scans for single expiratory phase CT scans.

[0011] To complete the missing inspiratory phase CT images for single expiratory phase CT, the present invention proposes a clinical text-guided expiratory phase CT image generation method. The method takes the patient's electronic medical record, respiratory symptom assessment, pulmonary function test results and other clinical texts as well as the patient's inspiratory phase chest CT scan image as input. The method can learn the relationship between the patient's respiratory function clinical phenotype reflected in the clinical text and the patient's lung lesion imaging phenotype reflected in the CT image, thereby converting the given inspiratory phase CT image into an expiratory phase CT image.

[0012] Based on the above-mentioned lung lesion analysis method and expiratory phase CT image generation method, the present invention proposes a lung lesion analysis system based on a parameter response map and an image generation system, which is composed of a data collection and management module, an image registration module, a controllable image generation module, and a parameter response map analysis module:

[0013] The data collection and management module interfaces with the hospital information system and CT image collection equipment to collect patient information and historical CT examination results and input them into the disease progression assessment module. Based on the different types of CT scans, the biphasic CT images are fed into the image registration module, and the single inspiratory phase CT images are fed into the controllable image generation module.

[0014] The image registration module receives the patient's biphasic CT scan image, registers the expiratory phase CT scan image at the end of deep exhalation with the inspiratory phase CT scan image at the end of inspiration, so that the same lung tissue is in the same spatial position in the two different CT images. The obtained registered biphasic CT image is input into the controllable image generation module for training and input into the parameter response map analysis module;

[0015] The controllable image generation module is based on the clinical text-guided expiratory phase CT image generation method. After being trained using the registered biphasic CT images and the corresponding patient clinical text as training data, it can learn the relationship between the patient's respiratory function clinical phenotype and the lung parenchymal lesions and imaging phenotypes. In actual use, it can generate an expiratory phase CT image registered with the inspiratory phase chest CT image based on the patient's single inspiratory phase chest CT image and clinical text such as electronic medical records, respiratory symptom assessments, and pulmonary function test results.

[0016] The parameter response map analysis module receives the inspiration-expiration biphasic CT image pairs generated by the image registration module and the controllable image generation module, uses the voxel classification method to divide the whole lung into normal lung tissue, emphysema, functional small airway damage and chronic obstructive pulmonary disease areas, and calculates the volume proportion of different types of lung tissue in the whole lung and different lung segments to obtain the parameter response map analysis evaluation results for the patient's lung organic lesions; given several historical CT examination results of the same patient, the parameter response map analysis module can provide the type, degree, distribution and development trend of the patient's lung lesions by comparing and analyzing the parameter response map analysis evaluation results, providing doctors with a basis for auxiliary diagnosis and treatment decision-making.

[0017] The specific implementations of each module in the lung lesion analysis system are as follows:

[0018] The specific implementation method of the image registration module is as follows: receiving the expiratory phase CT scan image of the patient at the end of deep exhalation and the CT scan image at the end of inspiration, using the CT image at the end of inspiration as the target image and the expiratory phase CT image as the original image as input to the diffusion model, and the diffusion model learns the correspondence between the features in the patient's biphasic CT image and the biphasic CT images by learning the conditional scoring function; then inputting the output result of the diffusion network into the deformation network to be converted into a registration field that can be directly used for non-rigid transformation of the image, and the obtained registration field is directly applied to the expiratory phase CT image by the spatial transformation layer, and the registered image is obtained after non-rigid transformation.

[0019] The controllable image generation module is based on the expiratory phase CT image generation method guided by the clinical text. The specific implementation of the method is as follows: it is composed of a clinical text encoding model and an expiratory phase CT image generation model. The clinical text encoding model is used to encode the information related to the patient's respiratory function clinical phenotype in the patient's electronic medical record, respiratory symptom assessment and pulmonary function test results into a feature vector; the image generation model includes two processes, diffusion and inverse diffusion. During the diffusion process, the inspiratory phase CT image will first be converted into a feature vector in the latent space by the encoder ε in the variational autoencoder, and the noise will be gradually added through the diffusion process. Then, the inspiratory phase CT feature vector with the noise added will be gradually generated by the clinical text feature inverse diffusion process while removing the noise and generating a feature vector representing the expiratory phase CT image, and the decoder in the variational autoencoder will be used to generate the feature vector representing the expiratory phase CT image. Converted into actual expiratory CT images. The clinical text-guided expiratory CT image generation method introduces clinical text describing the patient's respiratory function into the image generation model. Unlike existing image generation methods, the text in this method does not directly indicate the performance of the generated image, but provides auxiliary information for the model to convert from expiratory CT to inspiratory CT. By learning the relationship between biphasic CT images and clinical text, the model establishes a connection between the clinical phenotype and imaging phenotype of respiratory function in patients with lung diseases, thereby achieving expiratory chest CT image generation based on clinical text such as patient electronic medical records, respiratory symptom assessments, and pulmonary function test results, and inspiratory chest CT images.

[0020] The training and inference process of the Expiratory CT Generation Model (ECTGen) in actual use are both composed of the above-mentioned inspiratory CT image diffusion process and the inverse diffusion process guided by clinical text. Its training objective can be expressed as:

[0021]

[0022] y:={y1,y2,y3,…},

[0023] Where x represents the patient's inspiratory CT image, y1, y2, y3, ... represent clinical texts such as the patient's electronic medical record, pulmonary function test results, respiratory function assessment form, etc., τ θ The clinical text encoding model is obtained by pre-training on a dataset of respiratory disease-related texts, where ∈ represents the noise added during the diffusion process and obeys a Gaussian distribution, and ∈ θ (z t ,t,τ θ(y)) represents the Denoising U-Net model for removing noise, and the model is based on the diffusion step t, the inspiratory phase CT image feature vector z at this step t and the input clinical text code τ θ (y) as input. The purpose of the above training objective is to provide auxiliary information to the model through clinical text such as patient electronic medical records, pulmonary function test results, and respiratory function assessment forms. The model gradually removes the noise added during the diffusion process during the reverse diffusion process and generates expiratory CT images based on clinical text and inspiratory CT images.

[0024] The parameter response map analysis module receives the paired biphasic CT images of the patient after registration generated by the image registration module or the controllable image generation module, and performs a lung lesion analysis based on the parameter response map, thereby realizing a lung lesion analysis that is not limited by single-phase or biphasic CT. The CT parameter response map is a quantitative CT analysis method based on the comparison between biphasic CT images and voxel-by-voxel threshold classification. The analysis method based on the CT parameter response map described in this patent divides the whole lung into normal lung tissue, emphysema, functional small airway damage and pulmonary fibrosis areas by comparing the CT values ​​of the same part of the lung tissue under two different states of inspiration and expiration, and the four different categories of lung tissue are marked in red, yellow, green and purple respectively. The specific classification criteria are as follows:

[0025] (1) <-950 HU in inspiration and <-856 HU in expiration represent emphysema areas, which are indicated by red on the image;

[0026] (2) Inspiratory phase ≥-950HU and expiratory phase <-856HU represents the area of ​​small airway lesions, which is indicated by yellow on the image;

[0027] (3) Inspiratory phase ≥-950HU and expiratory phase ≥-856HU represent the normal area, which is represented by green on the image;

[0028] (4) -600 to -250 HU in the inspiratory or expiratory phase represents the area of ​​pulmonary fibrosis, which is represented by purple on the image.

[0029] The existing parameter response graph analysis method only includes three classifications: normal, emphysema, and functional small airway damage. This method introduces the classification criteria of pulmonary fibrosis into the parameter response graph classification criteria, realizing a comprehensive assessment of the lung lesions of various patients.

[0030] In addition, the module includes a whole lung and lung segment segmentation model on CT images and a result comparison and analysis model. The whole lung and different lung segment segmentation results will be combined with the parameter response map analysis results to estimate the volume proportion of different types of lung tissue in the whole lung and different lung segments. This will help doctors quantitatively evaluate the damage to lung tissue in different parts and provide a basis for subsequent assessment of the patient's respiratory function based on the degree of organic damage to the lungs. The result comparison and analysis model compares the CT examination result images of the same patient and the corresponding parameter response map analysis results, and gives corresponding change trends, evaluation visualization reports and text reports, thereby showing detailed information on the patient's lung lesions, including the degree, distribution and development trend of emphysema, small airway lesions and pulmonary fibrosis, etc., to provide doctors with a basis for auxiliary diagnosis and treatment decisions.

[0031] The technical effects to be achieved by the present invention are:

[0032] 1. The present invention proposes a clinical text-guided expiratory phase CT image generation method. The method takes clinical text such as the patient's electronic medical record, respiratory symptom assessment, pulmonary function test results, and the patient's inspiratory phase chest CT scan image as input. The method can learn the relationship between the patient's respiratory function clinical phenotype reflected in the clinical text and the patient's lung lesion imaging phenotype reflected in the CT image, and between functional lesions and organic lesions. Based on the patient's respiratory function and the lung condition in the inspiratory state, the method estimates the lung condition in the expiratory state, thereby converting a given inspiratory phase CT image into an expiratory phase CT image.

[0033] 2. A lung lesion analysis method based on a parameter response graph and compatible with single-phase and dual-phase chest CT scan images. For existing expiratory-inspiratory dual-phase chest CT images, the method generates a registered dual-phase CT image pair through image registration; for chest CT images with only a single inspiratory phase, the method uses the clinical text-guided expiratory phase CT image generation method to complete the missing expiratory phase CT image that is registered with the inspiratory phase to form a dual-phase CT image pair; finally, the analysis method analyzes the registered dual-phase CT image pair generated by dual-phase or single-phase chest CT based on the parameter response graph to determine the patient's lung lesion condition and development trend. Compared with existing analysis methods, the method proposed in the present invention is not limited to patients who must undergo dual-phase CT examinations.

[0034] 3. The present invention proposes a lung lesion analysis system based on a parameter response diagram and an image generation system. Based on the above-mentioned expiratory phase CT image generation method and lung lesion analysis method, the system can not only analyze the results of a single patient examination, but also analyze multiple examinations of the same patient, including single-phase or double-phase examinations.

[0035] The CT scan results are compared and analyzed, and text and visual analysis reports are generated to evaluate the extent, distribution and development trend of different types of lung lesions, quantitatively monitor the occurrence and development of the disease, and serve as an effective tool for evaluating the severity and course of the disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Pulmonary lesion analysis system architecture based on parametric response maps and image generation system;

[0037] Figure 2 Diagram of the clinical text-guided expiratory CT image generation method;

[0038] Figure 3 Image registration module structure; DETAILED DESCRIPTION

[0039] The following is a preferred embodiment of the present invention and is combined with the accompanying drawings to further describe the technical solution of the present invention, but the present invention is not limited to this embodiment.

[0040] The present invention proposes a lung lesion analysis system based on a parameter response diagram and an image generation system.

[0041] The system mainly consists of data collection and management module, image registration module, controllable image generation module, parameter response graph analysis module and disease progression assessment module. Its overall architecture is as follows: Figure 1 shown

[0042] Module 1: Data collection and management module: This module connects with the hospital information system and CT image collection equipment to collect patient information and historical CT examination results. Depending on the type of CT scan (single-phase or bi-phase CT), the CT images are sent to different subsequent system modules for image processing, parameter response diagram analysis, and disease progression evaluation.

[0043] Module 2: Image Registration Module: This module accepts the patient's biphasic CT scan images and registers the expiratory phase CT scan image at the end of deep exhalation with the inspiratory phase CT scan image at the end of inspiration, so that the same lung tissue is in the same spatial position in the two different CT images. In this way, by analyzing the difference in CT values ​​between the CT images of the same lung tissue in the two different lung states of inspiration and exhalation, an assessment of lung inflation and pathological conditions can be obtained. At the same time, the registered biphasic CT images generated by this module will be used for training in Module 3.

[0044] Module three: controllable image generation module: This module is based on the clinical text-guided expiratory phase CT image generation method and the Stale Diffusion model architecture. It is trained with the registered biphasic CT image pairs generated by the image registration module and the clinical texts such as the patient's electronic medical records, respiratory symptom assessment, and pulmonary function test results corresponding to the images. After training, it can directly generate corresponding, registered expiratory phase CT images based on the clinical text and the single inspiratory phase CT image. The generated biphasic CT image pairs can be used in the parameter response graph analysis module to analyze the lung lesions.

[0045] Module 4 Parameter Response Map Analysis Module: This module accepts the registered biphasic CT images generated by modules 2 and 3, and uses voxel classification to divide the whole lung into normal lung tissue, emphysema, functional small airway damage and pulmonary fibrosis areas. The four different categories of lung tissue are represented in red, yellow, green and purple in the CT image, which makes it easier for doctors to assess the damage to lung tissue in different parts of the body. At the same time, the module calculates the volume proportion of different categories of lung tissue in the whole lung and different lung segments to quantitatively assess the severity of overall lung damage.

[0046] Data collection and management module:

[0047] The data collection and management module is connected to the hospital information system, CT examination equipment and pulmonary function examination equipment to collect and manage the patient's electronic medical records, respiratory symptom assessments, historical CT examination results and corresponding pulmonary function test results: the single inspiratory phase CT image and the corresponding electronic medical record, pulmonary function test results, and respiratory symptom assessment results will be sent to the controllable image generation module to complete the missing expiratory phase CT image and generate a two-phase image pair; the two-phase CT image pair (including the patient's original one and the one generated by this method) will be sent to the image registration module, and the registered two-phase CT image pair will be sent to the parameter response map analysis module.

[0048] Image registration module

[0049] The image registration module receives the patient's expiratory phase CT scan image at the end of deep exhalation and the CT scan image at the end of inspiration. The CT image at the end of inspiration is used as the fixed image, and the CT image at the end of inspiration is used as the moving image. The image registration module uses the time-varying diffeomorphism with mean square metric (TVMSQC) method in the medical registration software ANTs (Advanced Normalization Tools) to achieve registration of the inspiratory and expiratory lung CT scan images. The time-varying diffeomorphism registration method is a physical model-based registration method that assumes that the transformation between images is driven by a continuous velocity field determined by a control function. This method uses an iterative optimization algorithm using mean square error as the similarity metric to find the optimal control function, and uses this to calculate the corresponding velocity field and displacement field. The moving image is then transformed into the space of the fixed image to obtain the registered image.

[0050] Controllable image generation module

[0051] The controllable image is based on the expiratory phase CT image generation method guided by the clinical text. The specific implementation method of the method is as follows: it is composed of a clinical text encoding model and an expiratory phase CT image generation model, and the information related to the patient's respiratory function clinical phenotype in the patient's electronic medical record, respiratory symptom assessment and pulmonary function test results is encoded into a feature vector through the clinical text encoding model; the image generation model includes two processes of diffusion and inverse diffusion. During the diffusion process, the inspiratory phase CT image will first be converted into a feature vector in the latent space by the encoder ε in the variational autoencoder, and the noise will be gradually added through the diffusion process. Then, the inspiratory phase CT feature vector with the noise added will be gradually generated by the clinical text feature inverse diffusion process while removing the noise and generating a feature vector representing the expiratory phase CT image, and the decoder in the variational autoencoder will be used. Converted into actual expiratory CT images. The clinical text-guided expiratory CT image generation method introduces clinical text describing the patient's respiratory function into the image generation model. Unlike existing image generation methods, the text in this method does not directly indicate the performance of the generated image, but provides auxiliary information for the model to convert from expiratory CT to inspiratory CT. By learning the relationship between biphasic CT images and clinical text, the model establishes a connection between the clinical phenotype and imaging phenotype of respiratory function in patients with lung diseases, thereby achieving expiratory chest CT image generation based on clinical text such as patient electronic medical records, respiratory symptom assessments, and pulmonary function test results, and inspiratory chest CT images.

[0052] The training and inference process of the Expiratory CT Generation Model (ECTGen) in actual use are both composed of the above-mentioned inspiratory CT image diffusion process and the inverse diffusion process guided by clinical text. Its training objective can be expressed as:

[0053]

[0054] y:={y1,y2,y3,…},

[0055] Where x represents the patient's inspiratory CT image, y1, y2, y3, ... represent clinical texts such as the patient's electronic medical record, pulmonary function test results, respiratory function assessment form, etc., τ θ The clinical text encoding model is obtained by pre-training on a dataset of respiratory disease-related texts, where ∈ represents the noise added during the diffusion process and obeys a Gaussian distribution, and ∈ θ (z t ,t,τ θ (y)) represents the Denoising U-Net model for removing noise, and the model is based on the diffusion step t, the inspiratory phase CT image feature vector z at this step t and the input clinical text code τ θ (y) as input. The purpose of the above training objective is to provide auxiliary information to the model through clinical text such as patient electronic medical records, pulmonary function test results, and respiratory function assessment forms. The model gradually removes the noise added during the diffusion process during the reverse diffusion process and generates expiratory CT images based on clinical text and inspiratory CT images.

[0056] Parameter Response Graph Analysis Module

[0057] The parameter response map analysis module receives the paired patient biphasic CT images after registration generated by the image registration module or the controllable image generation module, and performs a lung lesion analysis based on the parameter response map, thereby realizing a lung lesion analysis that is not limited by single-phase or biphasic CT. The CT parameter response map is a quantitative CT analysis method based on the comparison between biphasic CT images and voxel-by-voxel threshold classification. The analysis method based on the CT parameter response map described in this patent divides the whole lung into normal lung tissue, emphysema, functional small airway damage and pulmonary fibrosis areas by comparing the CT values ​​of the same part of the lung tissue in two different states of inspiration and exhalation, and the four different categories of lung tissue are marked in red, yellow, green and purple respectively. The specific classification criteria are as follows:

[0058] (1) <-950 HU in inspiration and <-856 HU in expiration represent emphysema areas, which are indicated by red on the image;

[0059] (2) Inspiratory phase ≥-950HU and expiratory phase <-856HU represents the area of ​​small airway lesions, which is indicated by yellow on the image;

[0060] (3) Inspiratory phase ≥-950HU and expiratory phase ≥-856HU represent the normal area, which is represented by green on the image;

[0061] (4) -600 to -250 HU in the inspiratory or expiratory phase represents the area of ​​pulmonary fibrosis, which is represented by purple on the image.

[0062] In addition, the module includes a whole lung and lung segment segmentation model on CT images and a result comparison and analysis model. The whole lung and different lung segment segmentation results will be combined with the parameter response map analysis results to estimate the volume proportion of different types of lung tissue in the whole lung and different lung segments. This will help doctors quantitatively evaluate the damage to lung tissue in different parts and provide a basis for subsequent assessment of the patient's respiratory function based on the degree of organic damage to the lungs. The result comparison and analysis model compares the CT examination result images of the same patient and the corresponding parameter response map analysis results, and gives corresponding change trends, evaluation visualization reports and text reports, thereby showing detailed information on the patient's lung lesions, including the degree, distribution and development trend of emphysema, small airway lesions and pulmonary fibrosis, etc., to provide doctors with a basis for auxiliary diagnosis and treatment decisions.

Claims

1. A lung lesion analysis system based on a parameter response graph and an image generation system, characterized by: A lung lesion analysis method based on parametric response maps and compatible with single-phase and dual-phase chest CT scan images was used to analyze expiratory-inspiratory dual-phase chest CT image pairs and single inspiratory phase chest CT images. The analysis system is based on the lung lesion analysis method and is composed of a data collection and management module, an image registration module, a controllable image generation module, and a parameter response map analysis module. For an exhalation-inhalation biphasic chest CT image, the image registration module first registers the two images, and then the parameter response map analysis module analyzes the registered image pair. For a single inhalation phase chest CT image, the controllable image generation module complements the missing exhalation phase CT image, and the parameter response map analysis module analyzes the generated exhalation-inhalation biphasic chest CT image pair. The data collection and management module is connected to the hospital information system, CT examination equipment and pulmonary function test equipment to collect and manage the patient's electronic medical records, respiratory symptom assessment, historical CT examination results and corresponding pulmonary function test results: the single inspiratory phase CT image and the corresponding electronic medical record, pulmonary function test results and respiratory symptom assessment results will be sent to the controllable image generation module to supplement the missing expiratory phase CT image and generate a biphasic CT image pair; the biphasic CT image pair will be sent to the image registration module; the registered biphasic CT image pair will be sent to the parameter response map analysis module; The image registration module receives the patient's biphasic CT scan image, registers the expiratory phase CT scan image at the end of deep exhalation with the inspiratory phase CT scan image at the end of inspiration, so that the same lung tissue is in the same spatial position in the two different CT images. The obtained registered biphasic CT image is input into the controllable image generation module for training and input into the parameter response map analysis module; The controllable image generation module is based on a clinical text-guided expiratory CT image generation method and a StableDiffusion model architecture. The module uses a text encoder to encode clinical text containing the patient's electronic medical record, respiratory symptom assessment results, and pulmonary function test results into indicative text features, and uses an image encoder to encode the patient's single inspiratory CT into an image potential representation. Based on the indicative text and the image potential representation, the module generates the expiratory CT. The parameter response map analysis module receives the expiratory-inspiratory phase CT image pairs generated by the image registration module and the controllable image generation module, uses a threshold-based voxel classification method to divide the whole lung into normal lung tissue, emphysema, and functional small airway damage areas, calculates the volume proportions of the three different types of lung tissue in the whole lung and different lung segments, and represents the three different types of lung tissue in red, yellow, and green in the CT image; finally, for the same patient, compares and analyzes the results of previous examinations to determine the changes in the patient's lung tissue in each type during the previous examinations; The generation method is based on the Stable Diffusion model framework. It uses clinical text such as the patient's electronic medical record, respiratory symptom assessment, and pulmonary function test results as control information. The Stable Diffusion model is retrained together with the patient's biphasic chest CT scan image. The model learns the relationship between the patient's clinical respiratory function phenotype and the imaging phenotype by diffusing random noise from the inspiratory phase CT scan and then reversely diffusing the random noise to generate the expiratory phase CT scan. The controllable image generation module is based on the clinical text-guided expiratory phase CT image generation method, and is trained with the registered biphasic CT image pairs generated by the image registration module and clinical texts corresponding to the images, such as the patient's electronic medical records, respiratory symptom assessments, and pulmonary function test results. After training, the corresponding, registered expiratory phase CT images can be directly generated based on the clinical text and the single inspiratory phase CT images. The generated biphasic CT image pairs can be used in the parameter response map analysis module to analyze lung lesions.

2. The pulmonary lesion analysis system based on a parameter response graph and an image generation system according to claim 1, characterized in that: The specific implementation method of the image registration module is to receive the expiratory phase CT scan image of the patient at the end of deep exhalation and the CT scan image at the end of inspiration, use the CT image at the end of inspiration as the target image, and use the expiratory phase CT image as the original image to input the diffusion model DiffuseMorph to complete the image registration task. The diffusion model learns the correspondence between the features in the patient's biphasic CT image and the biphasic CT images through a conditional scoring function; then, the output result of the diffusion network is input into the deformation network to be converted into a registration field that can be directly used for non-rigid transformation of the image. The obtained registration field is directly applied to the expiratory phase CT image by the spatial transformation layer, and the registered image is obtained after non-rigid transformation.

3. The pulmonary lesion analysis system based on a parameter response graph and an image generation system according to claim 2, characterized in that: The parameter response map analysis module receives the registered paired patient biphasic CT images generated by the image registration module or the controllable image generation module, and performs analysis based on the CT parameter response map on the patient's chest CT examination results and image sequences, which are not limited to biphasic or single-phase; The CT parameter response map-based analysis method divides the entire lung into normal lung tissue, emphysema, functional small airway damage, and pulmonary fibrosis areas by comparing the CT values ​​of the same part of lung tissue during inspiration and expiration. The four different types of lung tissue are marked in red, yellow, green, and purple, respectively. The specific classification criteria are as follows: (1) Inspiratory phase <-950 HU and expiratory phase <-856 HU represent emphysema areas, which are indicated by red on the image; (2) Inspiratory HU ≥ -950 HU and expiratory HU < -856 HU represent small airway lesions, which are indicated in yellow on the image; (3) Inspiratory phase ≥-950 HU and expiratory phase ≥-856 HU represent the normal area, which is represented by green on the image; (4) -600 to -250 HU in the inspiratory or expiratory phase represents the area of ​​pulmonary fibrosis, which is represented by purple on the image; The parameter response graph analysis module includes a result comparison analysis model, which compares the CT examination result images of the same patient and the corresponding parameter response graph analysis results, and provides corresponding change trend analysis and evaluation results; the parameter response graph analysis module generates a visual result report, showing detailed information on the patient's lung lesions, including the degree, distribution and development trend of emphysema, small airway lesions and pulmonary fibrosis.

Images