Method, device and equipment for analyzing whole-body organ metabolic network and storage medium

Abstract

The application relates to a whole-body organ metabolism network analysis method, device, equipment and storage medium. The method comprises the following steps: collecting a PET image of a subject, obtaining SUV images, Ki images and TAC data according to the PET image, and collecting physiological information, clinical pathology information and daily habit information of the subject; metabolism characteristics are extracted based on the PET images, SUV images and Ki images corresponding to the region of interest; the TAC data of each organ is curve-fitted by using the PET image, and the metabolism disturbance under different organs is represented by using the fitting residual error; a whole-body organ metabolism network is constructed according to the physiological information, clinical pathology information, daily habit information, metabolism characteristics and metabolism disturbance; and the whole-body organ metabolism of the subject is analyzed through the whole-body organ metabolism network. The application avoids individual differences, can more comprehensively capture the metabolism correlation among whole-body organs of a specific disease, and is helpful for early diagnosis, accurate evaluation and individualized treatment of clinical diseases.

Description

Technical Field

[0001] The present application belongs to the field of medical imaging technology, and in particular relates to a method, apparatus, device and storage medium for analyzing a whole-body organ metabolic network. Background Art

[0002] Complex interactions exist between the various organs of the human body, resulting in different physiological states. A healthy human body maintains "homeostasis" and normal circulation and metabolism through dynamic interactions between multiple organ systems. However, inflammation caused by infection or tissue damage may disrupt homeostasis, leading to the development of diseases such as tumors, diabetes, autoimmune diseases, and cardiovascular diseases. Different diseases often have complex causes and clinical manifestations, involving not only multiple physiological processes and metabolic pathways, but also interactions and influences between physiological and metabolic processes, making the diagnosis and treatment of diseases more complex.

[0003] Currently, various medical imaging methods such as CT (Computed Tomography) and MR (Magnetic Resonance Imaging), as well as functional metabolic imaging techniques such as PET (positron emission tomography) and SPECT (single photon emission computed tomography), are commonly used in clinical practice to comprehensively assess the progression of disease and guide the formulation of clinical diagnosis and treatment plans. In recent years, with the emergence and development of whole-body PET scanners, real-time and synchronous observation of the metabolism of whole-body systems and organs has become a reality. For example, based on 18F-FDG dynamic PET, real-time monitoring and assessment of glucose metabolism in whole-body organs can be achieved. However, most current research remains at the imaging level for disease diagnosis, treatment, and response assessment, and the interaction and metabolic associations between whole-body organs are still in the exploratory stage.

[0004] In 2022, Tao Sun et al. published an article titled "Identifying the individual metabolic abnormities from a systemic perspective using whole body PET imaging" in the European Journal of Nuclear Medicine and Molecular Imaging. The article proposed an "individual metabolic abnormality network framework" based on the subject's whole-body 18F-FDG SUV (Standard Uptake Value) images and a normal control database. This framework establishes a standard network through a normal control database, and then inputs the subject's clinical SUV images for analysis, thereby capturing the patient's deviation from the healthy control group at the organ level. By drawing an organ connection map and observing the changed network edge strength, abnormal metabolic connections between organs are revealed.

[0005] However, the existing metabolic network is limited to analyzing individual metabolic abnormalities, which is prone to individual metabolic deviations, making it difficult to extend the metabolic network conclusions obtained from the analysis to the diagnosis, treatment, and evaluation of clinical diseases. At the same time, the existing technology only analyzes the SUV image data of subjects and healthy controls. It has been clinically proven that dynamic PET multi-parameter images can provide better tumor characterization and higher sensitivity and specificity, but they have not yet been included in the study. Therefore, the existing technology urgently needs to be updated based on experimental data. In addition, the existing technology only focuses on the imaging data of the subjects, and the basic physiological information and clinical pathological information of the patients are not included in the analysis scope of the metabolic network, resulting in incomplete and inaccurate metabolic analysis. Summary of the Invention

[0006] The present application provides a whole-body organ metabolic network analysis method, apparatus, device and storage medium, aiming to solve at least one of the above-mentioned technical problems in the prior art to a certain extent.

[0007] In order to solve the above problems, this application provides the following technical solutions:

[0008] A whole-body organ metabolic network analysis method, comprising:

[0009] Acquire PET images of the subject, obtain SUV images, Ki images, and TAC data based on the PET images, and collect physiological information, clinical pathological information, and daily habit information of the subject;

[0010] Perform region of interest analysis on the subject's organs based on disease type, select the region of interest related to the disease type, and extract metabolic features based on the PET images, SUV images, and Ki images corresponding to the region of interest. Use the PET images to perform curve fitting on the TAC data of each organ, and use the fitting residuals to characterize the metabolic disturbance in each organ.

[0011] A whole-body organ metabolic network is constructed based on the physiological information, clinical pathological information, daily habit information, metabolic characteristics, and metabolic disturbances. The metabolic associations between various organs under specific diseases are explored through the whole-body organ metabolic network, and whole-body organ metabolic analysis is performed on the subjects.

[0012] The technical solution adopted in the embodiment of the present application further includes: acquiring a PET image of the subject, and obtaining an SUV image, a Ki image, and TAC data based on the PET image, specifically:

[0013] Whole-body PET imaging of the subject was performed using a 2-meter PET device to collect static PET images and dynamic PET images of the subject, and SUV images, Ki images, and TAC data were obtained through the static PET images and dynamic PET images.

[0014] The technical solution adopted in the embodiment of the present application also includes: collecting the subject's physiological information, clinical pathological information, and daily habit information, specifically:

[0015] The physiological information includes gender, age, weight, height and BMI information; the clinical pathology information includes cytology, histology and serology medical examination information; and the daily habit information includes smoking history and secondhand smoke environment information.

[0016] The technical solution adopted in the embodiment of the present application further includes: performing region of interest analysis on organs of the subject according to the disease type, and before selecting the region of interest related to the disease type, further including:

[0017] A CT image of a subject is acquired based on a CT device, the subject's organs are segmented using the CT image, and the segmentation mask of the organs is adapted to the PET image.

[0018] The technical solution adopted in the embodiment of the present application also includes: performing region of interest analysis on the subject's organs according to the disease type, selecting the region of interest related to the disease type, and extracting metabolic features based on the PET image, SUV image, and Ki image corresponding to the region of interest, and using the PET image to perform curve fitting on the TAC data of each organ, and using the fitting residual to characterize the metabolic disturbance in each organ, specifically:

[0019] A region of interest (ROI) analysis is performed on the segmented organs according to the disease type, and the ROI associated with the disease type is selected. Metabolic features are extracted based on the segmentation mask of the ROI and the adapted PET image, SUV image, and Ki image. The extracted metabolic features include mean SUV, max SUV, mean Ki, and max Ki. The dynamic PET image is used to perform curve fitting on the TAC data of each organ, and the fitting residual is used to characterize the metabolic disturbance in different organs.

[0020] The technical solution adopted in the embodiment of the present application also includes: constructing a whole-body organ metabolic network based on physiological information, clinical pathological information, daily habit information, metabolic characteristics, and metabolic perturbations, mining the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and performing whole-body organ metabolic analysis on the subject, including:

[0021] The whole-body organ metabolic network includes an individual abnormal metabolic network and a group abnormal metabolic network. The individual abnormal metabolic network is constructed by: establishing an individual reference network based on the metabolic characteristics of N healthy control groups, adding a subject to the healthy control group to form an individual subject network; extracting individual difference values ​​between the individual subject network and the reference network, performing a Z-score standardization operation on the individual difference values, and performing a thresholding operation on the individual difference values ​​after the standardization operation, and selecting individual difference values ​​less than and greater than a set confidence interval as significant abnormal metabolism in the individual subject network.

[0022] The technical solution adopted in the embodiment of the present application also includes: constructing a whole-body organ metabolic network based on physiological information, clinical pathological information, daily habit information, and extracted metabolic features, mining the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and performing whole-body organ metabolic analysis on the subject, and also includes:

[0023] The method for constructing the reference network of the abnormal metabolic network of the group includes: establishing a group reference network based on the metabolic characteristics of N healthy control groups, and establishing a group test network based on the metabolic characteristics of the entire disease group; extracting the group difference value between the group test network and the group reference network, and analyzing the abnormal metabolic association between organs / systems according to the group difference value; the abnormal metabolic association analysis process includes: classifying the main organs in the whole body organs, and dividing the whole body organs into the nervous system, respiratory system, circulatory system, digestive system, endocrine system, immune system, urinary system and locomotor system according to physiological characteristics, drawing the association map between organs / systems according to the main organ classification results and the system division results, based on the association map, analyzing the correlation and significance between organs / systems according to the association map, and quantifying and visualizing the organ metabolic association of the group.

[0024] Another technical solution adopted in the embodiment of the present application is: a whole-body organ metabolic network analysis device, comprising:

[0025] Data acquisition module: used to acquire PET images of subjects, obtain SUV images, Ki images and TAC data based on the PET images, and collect physiological information, clinical pathological information and daily habit information of the subjects;

[0026] Feature extraction module: used to perform region of interest analysis on the subject's organs according to the disease type, select the region of interest related to the disease type, and extract metabolic features based on the PET images, SUV images, and Ki images corresponding to the region of interest. The PET images are used to perform curve fitting on the TAC data of each organ, and the fitting residuals are used to characterize the metabolic disturbances in different organs.

[0027] Metabolic analysis module: used to construct a whole-body organ metabolic network based on the physiological information, clinical pathological information, daily habit information, metabolic characteristics and metabolic perturbations, and to explore the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and to perform whole-body organ metabolic analysis on the subjects.

[0028] Another technical solution adopted by the embodiment of the present application is: a device, the device comprising a processor and a memory coupled to the processor, wherein:

[0029] The memory stores program instructions for implementing the whole-body organ metabolic network analysis method;

[0030] The processor is configured to execute the program instructions stored in the memory to control a whole-body organ metabolic network analysis method.

[0031] Another technical solution adopted in the embodiment of the present application is: a storage medium storing program instructions executable by a processor, wherein the program instructions are used to execute the whole-body organ metabolic network analysis method.

[0032] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: the whole-body organ metabolic network analysis method, device, equipment and storage medium of the embodiments of the present application combine the clinical imaging information, physiological information and pathological information of the subject to construct a whole-body organ metabolic network, and comprehensively analyze the interactions between multiple organs or multiple systems under the occurrence of the disease through the whole-body organ metabolic network of individuals and groups, so as to more accurately characterize the metabolic state of whole-body organs under specific diseases, avoid individual differences, and more comprehensively capture the metabolic associations between whole-body organs of specific diseases, so as to more accurately characterize the impact of the disease on whole-body organs or systems, and more comprehensively analyze the interactions between multiple organs in clinical diseases and promote the understanding of their causal relationships, thereby realizing the quantitative and visual analysis of whole-body organ metabolic associations, which is helpful for the early diagnosis, accurate evaluation and personalized treatment of clinical diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the whole body organ metabolic network analysis method according to an embodiment of the present application;

[0034] Figure 2 A schematic diagram of constructing an individual abnormal metabolic network according to an embodiment of the present application;

[0035] Figure 3 This is a schematic diagram of constructing a population abnormal metabolic network according to an embodiment of the present application;

[0036] Figure 4 Schematic diagram of abnormal metabolic associations between organs in lung cancer patients with different smoking groups, where (a) is the abnormal metabolic association analysis results of non-smokers, (b) is the abnormal metabolic association analysis results of light smokers, and (c) is the abnormal metabolic association analysis results of heavy smokers;

[0037] Figure 5 This is a schematic diagram of the structure of a whole-body organ metabolic network analysis device according to an embodiment of the present application;

[0038] Figure 6 This is a schematic diagram of the device structure of an embodiment of the present application;

[0039] Figure 7 A schematic diagram of the structure of the storage medium of an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0041] The terms "first," "second," and "third" in this application are used only for descriptive purposes and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "multiple" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement, etc. between the components under a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications also change accordingly. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products, or devices.

[0042] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0043] Specifically, see Figure 1 , is a flow chart of the whole body organ metabolic network analysis method of the embodiment of the present application. The whole body organ metabolic network analysis method of the embodiment of the present application comprises the following steps:

[0044] S100: Acquire PET images of the subject using a PET device, and obtain SUV images, Ki (dynamic parameter) images, and TAC (time activity curve) data based on the PET images;

[0045] In this step, in order to acquire a complete whole-body PET image of the subject, the embodiment of the present application uses a 2-meter PET device such as uEXPLORER to perform whole-body PET imaging on the subject, acquires static PET images and dynamic PET images of the subject, and obtains SUV images, Ki images and TAC data through the static PET images and dynamic PET images. When performing whole-body organ metabolic network analysis, the whole-body organ metabolic network is constructed by combining the SUV images, Ki images and TAC data to more comprehensively and accurately reflect the metabolic status of whole-body organs.

[0046] S110: Collect the subjects' physiological information, clinical pathological information, and daily habit information;

[0047] In this step, the physiological information collected includes gender, age, weight, height, BMI (Body Mass Index), etc. The clinical pathological information collected includes medical examination information such as cytology, histology and serology, and the daily habit information of the subjects is collected according to specific diseases. For example, for lung cancer patients, information such as their smoking history and secondhand smoke environment needs to be collected.

[0048] Furthermore, when conducting whole-body organ metabolic network analysis, the subjects can be grouped according to their physiological information, clinical pathological information, and daily habit information, and the metabolic parameters of various tracer drugs, abnormal associations between organs / systems, etc. can be analyzed. Through group analysis, a more comprehensive understanding of the preferences or associations of specific diseases with respect to certain specific physiological information, clinical pathological information, and daily habit information can be obtained.

[0049] S120: Acquire a CT image of the subject based on a CT device, segment the subject's organs using the CT image, and fit the segmentation mask of the organs into the PET image;

[0050] In this step, the CT images are used to segment the subject's organs, and the segmentation masks of the organs are adapted to the PET images to facilitate subsequent metabolic network analysis.

[0051] S130: Performing region of interest analysis on the segmented organs according to the disease type, selecting the region of interest related to the disease type, extracting metabolic features based on the adapted PET images, SUV images, and Ki images corresponding to the region of interest, and performing curve fitting on the TAC data of each organ using the dynamic PET images. The residuals of the fitting are used to characterize the metabolic disturbances in different organs.

[0052] In this step, since different diseases correspond to different regions of interest, the embodiment of the present application selects corresponding regions of interest for analysis according to different disease types. For example, for patients with lung cancer, it is necessary to select the thyroid gland, esophagus, spinal cord, sternum, ribs, lungs, heart, liver, spleen, adrenal glands, kidneys, pancreas and muscles from the whole body organs as regions of interest for feature extraction. For brain regions, the insula, nucleus accumbens, anterior cingulate gyrus, amygdala, thalamus, hippocampus, anterior superior temporal gyrus and other regions related to smoking addiction and lung cancer are selected as regions of interest for feature extraction.

[0053] After selecting regions of interest associated with different disease types, metabolic features are extracted based on the segmentation mask of the region of interest and the adapted PET images, SUV images, and Ki images. The extracted metabolic features include but are not limited to meanSUV, maxSUV, meanKi, and maxKi. Simultaneously, curve fitting is performed on the TAC data of each organ using multiple frames of dynamic PET images. The residuals of the fitting are used to characterize the metabolic perturbations in different organs, and metabolic associations between organs are then constructed using multiple feature dimensions.

[0054] S140: Construct a whole-body organ metabolic network based on physiological information, clinical pathological information, daily habit information, and extracted metabolic features and metabolic perturbations. Through the whole-body organ metabolic network, we can explore the metabolic associations between organs under specific diseases and conduct whole-body organ metabolic analysis on subjects.

[0055] In this step, feature extraction is performed by combining clinical imaging data such as SUV images, Ki images, and TAC data, and a whole-body organ metabolic network is constructed by comprehensively considering the subject's physiological information, pathological information, and daily habit information. The metabolic associations between various organs under specific diseases are explored, thereby achieving quantitative characterization and visual analysis of specific disease groups, and more comprehensively and accurately analyzing the development patterns of clinical diseases, which is conducive to assisting in the early diagnosis and treatment evaluation of various diseases.

[0056] Specifically, the whole body organ metabolic network includes individual abnormal metabolic network and group abnormal metabolic network, such as Figure 2 and Figure 3 As shown, Figure 2 This is a schematic diagram of the individual abnormal metabolic network construction in the embodiment of the present application. Figure 3 Schematic diagram of the construction of a population abnormal metabolic network in an embodiment of the present application. The specific method of constructing an individual abnormal metabolic network includes: first, establishing an individual reference network (RefNet) based on the metabolic characteristics of N healthy control groups, and then adding a subject to the healthy control group to form an individual test network (Individual_PatNet); extracting the individual difference values ​​between the individual test network and the individual reference network, and performing a Z-score standardization operation on the individual difference values, that is, converting the individual difference value data into a standard normal distribution with a mean of 0 and a standard deviation of 1, so that the extracted metabolic features can be compared and processed on the same scale; then thresholding the individual difference values ​​after the standardization operation, and selecting individual difference values ​​less than and greater than the set confidence interval as significant abnormal metabolism in the individual test network. Wherein, the confidence interval is set to 95%, that is, difference values ​​less than 1.96 and greater than 1.96 are selected as significant abnormal metabolism in the individual test network.

[0057] Furthermore, to avoid the impact of individual differences, in addition to analyzing individual abnormal metabolic networks, group abnormal metabolic network analysis is also required. The specific method for constructing a reference network for group abnormal metabolic networks is as follows: Similarly, a group reference network is established based on the metabolic characteristics of N healthy control groups, and a group subject network (Group_PatNet) is established based on the metabolic characteristics of the entire disease group. Group difference values ​​between the group subject network and the group reference network are extracted, and the metabolic abnormality associations between organs / systems are analyzed based on the group difference values. The specific analysis process includes: classifying major organs such as the lungs, heart, and kidneys in the body, and dividing the body organs into eight major systems according to their physiological characteristics: the nervous system, respiratory system, circulatory system, digestive system, endocrine system, immune system, urinary system, and locomotor system. Based on the organ classification results and system division results, a correlation map between organs / systems is drawn. The correlation and significance between organs / systems are analyzed based on the correlation map to quantify and visualize the metabolic associations of the group organs.

[0058] It can be understood that the construction of whole-body organ metabolic networks is not limited to the whole-body organ metabolic networks of individuals and groups, but can also be extended to different groups. For example, the whole-body organ metabolic analysis of people with different diseases in different regions such as Asia, Europe, and America can be observed, and group organ metabolic network analysis can be conducted in a cross-group manner.

[0059] In order to verify the feasibility and effectiveness of the embodiments of the present application, the following embodiments use the abnormal metabolic association network of different smoking populations in lung cancer patients to conduct experiments. Figure 4Figure 2 shows the abnormal metabolic associations between organs in lung cancer patients with different smoking groups. (a) shows the abnormal metabolic association analysis results for non-smokers, (b) shows the abnormal metabolic association analysis results for light smokers, and (c) shows the abnormal metabolic association analysis results for heavy smokers. Regions 1 to 20 in the figure represent the regions of interest selected for the experiment, namely: 1-thyroid, 2-esophagus, 3-spinal cord, 4-sternum, 5-ribs, 6-lung, 7-heart, 8-liver, 9-spleen, 10-adrenal gland, 11-kidney, 12-pancreas, 13-muscle, 14-insula, 15-nucleus accumbens, 16-anterior cingulate gyrus, 17-amygdala, 18-thalamus, 19-hippocampus, and 20-anterior superior temporal gyrus. Regions 1 to 13 represent body organs, and regions 14 to 20 represent brain structures. The lower triangle of the matrix illustrates the specific differences in the Pearson correlation coefficients between lung cancer patients and healthy controls with different smoking intensities, while the upper triangle graphically displays the positive / negative correlations and significance marks corresponding to the specific differences. Through analysis, it was found that as the smoking intensity increased, the abnormal metabolic associations between the lungs and other body organs gradually changed from positive correlation to negative correlation, which means that smoking exacerbated the metabolic reversal between the lungs and multiple organs. When the lung metabolism of heavy smokers increased, the metabolism of other organs weakened. At the same time, in the abnormal metabolic associations between brain structure and body organs or brain structure, a positive correlation trend gradually emerged with the increase in smoking intensity, that is, smoking would enhance the metabolic synchronization effect within the brain region and between the brain and other organs. When the metabolism of the brain structure of heavy smokers increased, the metabolism of other body organs or other brain structures also increased significantly. The experimental results demonstrated the feasibility and effectiveness of the present invention.

[0060] Based on the above, the whole-body organ metabolic network analysis method of the embodiment of the present application combines the clinical imaging information, physiological information and pathological information of the subjects to construct a whole-body organ metabolic network, and comprehensively analyzes the interactions between multiple organs or multiple systems under the occurrence of the disease through the whole-body organ metabolic network of individuals and groups, so as to more accurately characterize the metabolic state of whole-body organs under specific diseases, avoid individual differences, and more comprehensively capture the metabolic associations between whole-body organs of specific diseases, so as to more accurately characterize the impact of the disease on whole-body organs or systems, and more comprehensively analyze the interactions between multiple organs in clinical diseases and promote the understanding of their causal relationships, thereby realizing the quantitative and visual analysis of whole-body organ metabolic associations, which is helpful for the early diagnosis, accurate evaluation and personalized treatment of clinical diseases.

[0061] See also Figure 5 , is a schematic diagram of the structure of the whole body organ metabolic network analysis device according to an embodiment of the present application. The whole body organ metabolic network analysis method device 40 according to an embodiment of the present application comprises:

[0062] Data acquisition module 41: used to acquire PET images of the subject, obtain SUV images, Ki images and TAC data based on the PET images, and collect physiological information, clinical pathological information and daily habit information of the subject;

[0063] Feature extraction module 42: used to perform region of interest analysis on the subject's organs according to the disease type, select the region of interest related to the disease type, and extract metabolic features based on the PET image, SUV image and Ki image corresponding to the region of interest, and use the PET image to perform curve fitting on the TAC data of each organ, and use the fitting residual to characterize the metabolic disturbance of each organ;

[0064] Metabolic analysis module 43: used to construct a whole-body organ metabolic network based on the physiological information, clinical pathological information, daily habit information, metabolic characteristics and metabolic disturbances, and to mine the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and to perform whole-body organ metabolic analysis on the subject.

[0065] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0066] The device provided in the embodiment of the present application can be applied in the aforementioned method embodiment. For details, please refer to the description of the aforementioned method embodiment, which will not be repeated here.

[0067] See also Figure 6 , is a schematic diagram of the device structure of an embodiment of the present application. The device 50 includes:

[0068] A memory 51 storing executable program instructions;

[0069] a processor 52 connected to the memory 51;

[0070] The processor 52 is used to call the executable program instructions stored in the memory 51 and perform the following steps: collecting PET images of the subject, obtaining SUV images, Ki images and TAC data based on the PET images, and collecting the subject's physiological information, clinical pathological information and daily habit information; performing region of interest analysis on the subject's organs according to the disease type, selecting the region of interest related to the disease type, and extracting metabolic features based on the PET images, SUV images and Ki images corresponding to the region of interest, and using the PET images to perform curve fitting on the TAC data of each organ, and using the fitting residuals to characterize the metabolic disturbance under each organ; constructing a whole-body organ metabolic network based on the physiological information, clinical pathological information, daily habit information, metabolic features and metabolic disturbance, and using the whole-body organ metabolic network to explore the metabolic associations between various organs under specific diseases, and performing whole-body organ metabolic analysis on the subject.

[0071] The processor 52 may also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip having signal processing capabilities. The processor 52 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor may be a microprocessor or any conventional processor.

[0072] See also Figure 7, is a structural diagram of the storage medium of an embodiment of the present application. The storage medium of the embodiment of the present application stores program instructions 61 that can implement the following steps: collecting PET images of the subject, obtaining SUV images, Ki images and TAC data based on the PET images, and collecting the subject's physiological information, clinical pathological information and daily habit information; performing region of interest analysis on the subject's organs according to the disease type, selecting the region of interest related to the disease type, and extracting metabolic features based on the PET images, SUV images and Ki images corresponding to the region of interest, and using the PET images to perform curve fitting on the TAC data of each organ, and using the fitting residual to characterize the metabolic disturbance under each organ; constructing a whole-body organ metabolic network based on the physiological information, clinical pathological information, daily habit information, metabolic features and metabolic disturbance, and mining the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and performing whole-body organ metabolic analysis on the subject. Among them, the program instructions 61 can be stored in the above-mentioned storage medium in the form of a software product, including several instructions for enabling a device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage media include: various media that can store program instructions, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0074] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A whole-body organ metabolic network analysis method, characterized in that: include: Acquire PET images of the subject, obtain SUV images, Ki images, and TAC data based on the PET images, and collect physiological information, clinical pathological information, and daily habit information of the subject; Perform region of interest analysis on the subject's organs based on disease type, select the region of interest related to the disease type, and extract metabolic features based on the PET images, SUV images, and Ki images corresponding to the region of interest. Use the PET images to perform curve fitting on the TAC data of each organ, and use the fitting residuals to characterize the metabolic disturbance in each organ. A whole-body organ metabolic network is constructed based on the physiological information, clinical pathological information, daily habit information, metabolic characteristics, and metabolic disturbances. The metabolic associations between various organs under specific diseases are explored through the whole-body organ metabolic network, and whole-body organ metabolic analysis is performed on the subjects.

2. The whole body organ metabolic network analysis method according to claim 1, characterized in that: The step of acquiring a PET image of the subject and obtaining an SUV image, a Ki image, and TAC data based on the PET image is as follows: Whole-body PET imaging of the subject was performed using a 2-meter PET device to collect static PET images and dynamic PET images of the subject, and SUV images, Ki images, and TAC data were obtained through the static PET images and dynamic PET images.

3. The whole body organ metabolic network analysis method according to claim 2, characterized in that: The collection of the subject's physiological information, clinical pathological information, and daily habit information is specifically as follows: The physiological information includes gender, age, weight, height and BMI information; the clinical pathology information includes cytology, histology and serology medical examination information; and the daily habit information includes smoking history and secondhand smoke environment information.

4. The whole body organ metabolic network analysis method according to any one of claims 1 to 3, characterized in that: The analysis of regions of interest of organs throughout the body of the subject according to the disease type, before selecting the regions of interest related to the disease type, further includes: A CT image of a subject is acquired based on a CT device, the subject's organs are segmented using the CT image, and the segmentation mask of the organs is adapted to the PET image.

5. The whole body organ metabolic network analysis method according to claim 4, characterized in that: The method involves performing region of interest analysis on the subject's organs based on the disease type, selecting a region of interest related to the disease type, and extracting metabolic features based on the PET images, SUV images, and Ki images corresponding to the region of interest. The PET images are then used to perform curve fitting on the TAC data of each organ, and the residuals of the fitting are used to characterize the metabolic disturbance of each organ. Specifically, A region of interest (ROI) analysis is performed on the segmented organs according to the disease type, and the ROI related to the disease type is selected. Metabolic features are extracted based on the segmentation mask of the ROI and the adapted PET image, SUV image, and Ki image. The extracted metabolic features include mean SUV, max SUV, mean Ki, and max Ki. The dynamic PET images are used to perform curve fitting on the TAC data of each organ, and the fitting residuals are used to characterize the metabolic disturbances in different organs.

6. The whole body organ metabolic network analysis method according to claim 5, characterized in that: The whole-body organ metabolic network is constructed based on physiological information, clinical pathological information, daily habit information, metabolic characteristics, and metabolic perturbations. The metabolic associations between organs under specific diseases are mined through the whole-body organ metabolic network, and whole-body organ metabolic analysis of the subject is performed, including: The whole-body organ metabolic network includes an individual abnormal metabolic network and a group abnormal metabolic network. The individual abnormal metabolic network is constructed by: establishing an individual reference network based on the metabolic characteristics of N healthy control groups, adding a subject to the healthy control group to form an individual subject network; extracting individual difference values ​​between the individual subject network and the reference network, performing a Z-score standardization operation on the individual difference values, and performing a thresholding operation on the individual difference values ​​after the standardization operation, and selecting individual difference values ​​less than and greater than a set confidence interval as significant abnormal metabolism in the individual subject network.

7. The whole body organ metabolic network analysis method according to claim 6, characterized in that: The method of constructing a whole-body organ metabolic network based on physiological information, clinical pathological information, daily habit information, metabolic characteristics, and metabolic perturbations, mining the metabolic associations between organs under specific diseases through the whole-body organ metabolic network, and performing whole-body organ metabolic analysis on the subject also includes: The method for constructing the reference network of the abnormal metabolic network of the group includes: establishing a group reference network based on the metabolic characteristics of N healthy control groups, and establishing a group subject network based on the metabolic characteristics of the entire disease group; extracting the group difference value between the group subject network and the group reference network, and analyzing the abnormal metabolic association between organs / systems according to the group difference value; the abnormal metabolic association analysis process includes: classifying the main organs in the whole body organs, and dividing the whole body organs into the nervous system, respiratory system, circulatory system, digestive system, endocrine system, immune system, urinary system and locomotor system according to physiological characteristics, drawing the association map between organs / systems according to the main organ classification results and the system division results, analyzing the correlation and significance between organs / systems according to the association map, and quantifying and visualizing the organ metabolic association of the group.

8. A whole-body organ metabolic network analysis device, characterized in that: include: Data acquisition module: used to acquire PET images of subjects, obtain SUV images, Ki images and TAC data based on the PET images, and collect physiological information, clinical pathological information and daily habit information of the subjects; Feature extraction module: used to perform region of interest analysis on the subject's organs according to the disease type, select the region of interest related to the disease type, and extract metabolic features based on the PET images, SUV images, and Ki images corresponding to the region of interest. The PET images are used to perform curve fitting on the TAC data of each organ, and the fitting residuals are used to characterize the metabolic disturbances in different organs. Metabolic analysis module: used to construct a whole-body organ metabolic network based on the physiological information, clinical pathological information, daily habit information, metabolic characteristics and metabolic perturbations, and to explore the metabolic associations between various organs under specific diseases through the whole-body organ metabolic network, and to perform whole-body organ metabolic analysis on the subjects.

9. A device, characterized in that The device includes a processor and a memory coupled to the processor, wherein: The memory stores program instructions for implementing the whole-body organ metabolic network analysis method according to any one of claims 1 to 7; The processor is configured to execute the program instructions stored in the memory to control a whole-body organ metabolic network analysis method.

10. A storage medium, characterized in that: The device stores program instructions executable by a processor, wherein the program instructions are used to execute the whole-body organ metabolic network analysis method according to any one of claims 1 to 7.

Images