An intelligent medical management system for the entire course of cancer patients

Abstract

The present invention discloses an intelligent medical management system for the entire course of disease for tumor patients, which relates to the technical field of medical management. By using image data sets and environmental data information, the tumor growth state can be monitored in real time, and by applying convolutional neural network technology to train the disease course prediction model, the tumor growth and metastasis risk can be more accurately evaluated, providing a scientific basis to guide treatment decisions. The disease prediction module estimates the migration evaluation index Qpzs by linearly normalizing the growth coefficient Szxs and the environmental impact coefficient Hyxs. This comprehensive evaluation method can effectively estimate the metastasis risk of the tumor, provide important risk warnings for clinicians, and facilitate timely adjustment of treatment strategies. The medical management module can accurately evaluate the condition of tumor patients by comparing and analyzing the evaluation threshold P with the migration evaluation index Qpzs. Based on this evaluation result, corresponding medical measures can be taken.

Description

Technical Field

[0001] The present invention relates to the technical field of medical management, and in particular to an intelligent medical management system for the entire course of disease for tumor patients. Background Art

[0002] In the modern medical field, intelligent medical management systems have become a key tool to improve the efficiency and accuracy of disease diagnosis and treatment. Especially in the field of tumor treatment, with the development of medical technology, systematic and intelligent management methods have played a vital role in optimizing the patient treatment process and improving the treatment effect. Tumors are a complex disease involving multiple stages, and their treatment and management need to comprehensively consider the primary site of the tumor, metastasis, and the overall health of the patient.

[0003] Although current medical technologies and systems have made significant progress in tumor detection and treatment, there are still deficiencies in the assessment of tumor state migration risk. Existing systems often lack a comprehensive assessment of tumor growth status and environmental factors, resulting in insufficient accuracy and timeliness in predicting tumor metastasis risk. There are certain defects in capturing small changes in tumors and metastasis risks, making it difficult to detect metastatic lesions as early as possible. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent medical management system for the entire course of disease for cancer patients, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent medical management system for the entire course of disease for tumor patients, including a scanning monitoring module, an image processing module, a disease course tracking module, a disease prediction module and a medical management module;

[0006] The scanning monitoring module is used to obtain tomographic images of the tumor patient's body based on imaging technology, and use molecular probes to identify biomarkers in the tumor patient's body to determine the primary site of the tumor;

[0007] The image processing module is used to pre-process the tomographic image, remove noise, smooth the image, and perform geometric correction, and to identify and extract effective features in the tomographic image, and to improve the image quality based on image enhancement technology to generate an image data set;

[0008] The disease course tracking module is used to detect and obtain the tumor growth status data information in the tumor patient based on the image data set, and obtain the relevant environmental data information around the tumor in combination with the primary site of the tumor to build a disease database, train a disease course prediction model based on the convolutional neural network technology, and build a growth coefficient Szxs based on the tumor growth status data information;

[0009] The disease prediction module is used to construct the environmental impact coefficient Hyxs based on the relevant environmental data information, and estimate the migration assessment index Qpzs by linearly normalizing the growth coefficient Szxs and the environmental impact coefficient Hyxs;

[0010] The medical management module is used to pre-set an evaluation threshold value P, and compare and analyze the evaluation threshold value P with the migration evaluation index Qpzs to evaluate the current condition of the tumor patient and take corresponding medical measures according to the condition.

[0011] Preferably, the scanning monitoring module includes a scanning unit and a position determination unit;

[0012] The scanning unit is used to obtain a tomographic image of the tumor patient's body through multi-angle X-ray scanning, and to generate a tissue image of the tumor in the body by magnetic resonance imaging to distinguish soft tissue structures;

[0013] The position determination unit is used to track biomarkers by labeling molecular probes with radioactive isotopes and labeling specific biomarkers with magnetic nanoparticles to enhance image contrast, wherein the biomarkers include but are not limited to carcinoembryonic antigen, prostate specific antigen or mutant gene.

[0014] Preferably, the image processing module includes a preprocessing unit and an image enhancement unit;

[0015] The preprocessing unit is used to use wavelet denoising technology to decompose the data information in the tomographic image and the tissue image through wavelet transform, remove the noise component in the wavelet domain, reconstruct several image frames back to the original domain through inverse transform, adjust the brightness by histogram equalization, stretch the range of the image, and adjust the contrast of the image;

[0016] The image enhancement unit is used to standardize the tomographic images and tissue images into a unified format, sort them in chronological order, and align images acquired from different viewing angles.

[0017] Preferably, the disease course tracking module includes a data extraction unit and a modeling unit;

[0018] The data extraction unit is used to detect and obtain the tumor growth status data information in the tumor patient's body based on the image data set, and at the same time, in combination with the primary site of the tumor, obtain the relevant environmental data information around the tumor, wherein the tumor growth status data information includes the blood vessel lumen diameter Xgqz, the blood vessel wall thickness Xbhd, the blood vessel density Xgmd and the blood flow velocity Xlsd at each monitoring time point, and the mean value Xlsd of the blood flow velocity within the monitoring period is obtained by a statistical mean algorithm avg ;

[0019] The tumor surrounding environment data information includes the oxygen partial pressure Yfy, the concentration Myyz of immunosuppressive factors and the pH value in the tumor tissue.

[0020] Preferably, the modeling unit is used to preliminarily construct an original model based on convolutional neural network technology, and train and test the original model with tumor growth status data information and tumor surrounding environment related data information, and use the trained original model as a disease course recognition model, respectively obtain feature information within the disease course recognition model, and use the acquired feature information to train and test the disease course recognition model, and finally use the trained disease course recognition model as a disease course prediction model.

[0021] Preferably, according to the tumor growth status data information, the blood flow velocity Xlsd and the blood vessel wall thickness Xbhd are linearly normalized to calculate the blood vessel maturity Xcd, which is specifically obtained according to the following formula:

[0022]

[0023] Where i = 1, 2, 3, ..., n, n represents the monitoring period, Xgqz represents the diameter of the vascular lumen, Xlsd i Expressed as the blood flow velocity at the i-th monitoring time point, Xlsd avg It is represented as the mean value of blood flow velocity during the monitoring period, and a1, a2 and a3 are all weight values;

[0024] The growth coefficient Szxs is obtained by the following formula:

[0025]

[0026] Wherein, Xgmd represents the blood vessel density, α and β are weight values, and C represents the first correction constant.

[0027] Preferably, the disease prediction module includes an environmental analysis unit and a comprehensive analysis unit;

[0028] The environmental analysis unit is used to construct the environmental impact coefficient Hyxs according to the relevant environmental data information, which is obtained in the following way:

[0029]

[0030] Wherein, Yfy represents the oxygen partial pressure in the tumor tissue, pH represents the acidity and alkalinity, Myyz represents the concentration of the immunosuppressive factor, b1, b2 and b3 are all weight values, and U represents the second correction constant.

[0031] Preferably, the comprehensive analysis unit is used to input the growth coefficient Szxs and the environmental impact coefficient Hyxs into the disease course prediction model to construct a migration assessment index Qpzs, and the migration assessment index Qpzs is obtained by the following formula:

[0032]

[0033] Wherein, F1 and F2 are weight values, and K represents the third correction constant.

[0034] Preferably, the medical management module includes a comparison unit and a management unit;

[0035] The comparison unit is used to compare and analyze the migration evaluation index Qpzs with the evaluation threshold P to evaluate the current condition of the tumor patient. The specific comparison and analysis content is as follows:

[0036] If the migration assessment index Qpzs exceeds the assessment threshold P, it means that there is a risk of tumor migration in the current tumor patient, and an early warning instruction will be issued;

[0037] If the migration assessment index Qpzs does not exceed the assessment threshold P, it means that the tumor in the current tumor patient does not have the risk of migration, and no additional warning instructions will be issued at this time.

[0038] Preferably, the management unit will take corresponding medical measures based on the comparison and analysis results in the comparison unit, specifically including:

[0039] If an early warning order is issued, further imaging examinations will be conducted to examine the expansion of the tumor in the patient's body, and PET scans will be performed to detect the metabolic activity of the tumor. Blood tests will be used to identify the presence of circulating tumor cells to confirm whether the tumor has metastasized. Biopsy of abnormal areas of the patient's tumor will be performed to obtain tissue samples to determine the nature and extent of the metastasis.

[0040] If no additional warning instructions are issued, biochemical tests will continue to be performed according to the established follow-up plan, symptoms of cancer patients will be monitored, the current treatment plan will be maintained, including chemotherapy, radiotherapy, targeted therapy or immunotherapy, adaptive adjustments will be made based on the response and side effects of cancer patients, and psychological counseling will be provided regularly.

[0041] The present invention provides an intelligent medical management system for the entire course of disease for tumor patients, which has the following beneficial effects:

[0042] (1) The scanning monitoring module combines imaging technology and molecular probes to accurately obtain tomographic images of tumor patients and identify biomarkers, thereby accurately determining the primary site of the tumor. This high-precision positioning capability helps to develop more targeted treatment plans and optimize treatment effects. Using image data sets and environmental data information, it can monitor the growth status of tumors in real time, and by applying convolutional neural network technology to train the course prediction model, it can more accurately evaluate the growth and metastasis risk of tumors, providing a scientific basis to guide treatment decisions. The disease prediction module estimates the migration evaluation index Qpzs by linearly normalizing the growth coefficient Szxs and the environmental impact coefficient Hyxs. This comprehensive evaluation method can effectively estimate the metastasis risk of tumors, provide important risk warnings for clinicians, and facilitate timely adjustment of treatment strategies. The medical management module can accurately evaluate the condition of tumor patients by comparing and analyzing the evaluation threshold P with the migration evaluation index Qpzs. Based on this evaluation result, corresponding medical measures can be taken to further implement personalized treatment plans to improve treatment effects and optimize patient prognosis. In short, this system further enhances the disease management capabilities of cancer patients through high-precision image acquisition and processing, comprehensive disease course monitoring and prediction, and personalized medical intervention, providing an effective support tool for clinical practice.

[0043] (2) The scanning unit uses multi-angle X-ray scanning technology to obtain cross-sectional images of the tumor patient's body. This method can show the anatomical location, size and relationship of the tumor with surrounding tissues in detail, helping doctors to accurately understand the spatial distribution of the tumor and its interaction with surrounding structures. At the same time, it combines MRI technology to generate high-contrast soft tissue images, which helps to distinguish the tiny structural differences between the tumor and the surrounding soft tissue, thereby more accurately identifying the detailed characteristics of the tumor. The location determination unit can accurately track biomarkers in the body by using molecular probes labeled with radioactive isotopes. This technology improves image contrast and enhances the visualization of primary tumors and their metastatic lesions.

[0044] (3) Through convolutional neural network technology, the modeling unit can initially build an original model and use tumor growth status data information and tumor surrounding environment data information to train and test the model. This advanced deep learning technology can effectively extract and learn complex features in the data and build a model that can accurately identify the course of the disease. The original model that has been initially trained is further trained and tested to obtain feature information of the course of disease recognition model. By continuously optimizing the course of disease recognition model, it is ensured that it can accurately capture and analyze tumor growth and environmental changes, thereby improving the accuracy and reliability of prediction.

[0045] (4) The blood flow velocity Xlsd and the vascular wall thickness Xbhd are processed by linear normalization to calculate the vascular maturity Xcd. This calculation method takes into account the blood flow velocity and vascular wall thickness during the monitoring period, and normalizes them by setting the weight value, so that the evaluation of vascular maturity is more comprehensive and accurate. The growth coefficient Szxs is calculated according to the vascular density Xgmd and other weight values. This formula takes into account the vascular density and related weight values. Through the accurate calculation of the growth coefficient, it can effectively reflect the growth characteristics of the tumor and provide a scientific basis for the prediction of the course of disease. The course of disease prediction model, which has been trained and tested many times, can combine the tumor growth status and environmental parameters to provide accurate prediction of the course of disease. This helps to identify the changing trend of the tumor at an early stage, predict the possible migration risk and the progression of the disease, and thus provide scientific decision support for doctors. Based on the accurate results of the course of disease prediction model, a more personalized treatment plan can be formulated to improve the targetedness and effectiveness of the treatment. This personalized treatment plan can be adjusted according to the patient's specific course of disease and environmental parameters to optimize the treatment effect. Through systematic training and testing of the original model, the course of disease recognition model and the course of disease prediction model, the modeling unit ensures the stability and accuracy of the model. Multiple training and optimization of the model improve the ability to handle complex data and enhance the reliability of the prediction results. In general, the modeling unit of the present invention accurately constructs and optimizes the course of disease prediction model through convolutional neural network technology, and provides an efficient course of disease prediction tool for tumor patients through scientific calculation of vascular maturity and growth coefficient. The system not only improves the accuracy of prediction, but also supports the formulation of personalized treatment plans, thereby significantly improving the scientificity and effectiveness of tumor management.

[0046] (5) The environmental impact coefficient Hyxs provides key environmental variable data for disease prediction, enabling treatment strategies to be optimized for specific tumor microenvironment conditions. Doctors can adjust treatment plans or intervention measures based on changes in the environmental impact coefficient, thereby improving the accuracy and effectiveness of treatment. By monitoring and analyzing the environmental impact coefficient Hyxs, early warning of tumor migration and progression can be achieved, and changes in environmental factors can be identified and responded to in a timely manner, which helps reduce the risk of further deterioration of the disease and allows appropriate medical intervention measures to be taken.

[0047] (6) By comparing the migration assessment index Qpzs with the assessment threshold P, the system can scientifically determine whether the tumor has a migration risk. This assessment method can timely identify potential metastasis risks and provide a solid basis for subsequent medical intervention. In short, the system helps to timely detect and respond to tumor migration through the assessment of tumor migration, the setting of early warning mechanisms, health management, and comprehensive patient care. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1The present invention is a block diagram of an intelligent medical management system for the entire course of disease for tumor patients.

[0049] Figure 2 This is a block diagram of the medical management system of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] Example 1

[0052] See also Figure 1 The present invention provides an intelligent medical management system for the entire course of disease for tumor patients, including a scanning monitoring module, an image processing module, a disease course tracking module, a disease prediction module and a medical management module;

[0053] The scanning monitoring module is used to obtain tomographic images of the tumor patient's body based on imaging technology, and use molecular probes to identify biomarkers in the tumor patient's body to determine the primary site of the tumor;

[0054] The image processing module is used to pre-process the tomographic image, remove noise, smooth the image, and perform geometric correction, and to identify and extract effective features in the tomographic image, improve the image quality based on image enhancement technology to generate an image data set, which is conducive to subsequent analysis;

[0055] The disease course tracking module is used to detect and obtain the tumor growth status data information in the tumor patient based on the image data set, and obtain the relevant environmental data information around the tumor in combination with the primary site of the tumor to build a disease database, train a disease course prediction model based on the convolutional neural network technology, and build a growth coefficient Szxs based on the tumor growth status data information;

[0056] The disease prediction module is used to construct the environmental impact coefficient Hyxs based on the relevant environmental data information, and estimate the migration assessment index Qpzs by linearly normalizing the growth coefficient Szxs and the environmental impact coefficient Hyxs;

[0057] The medical management module is used to pre-set an evaluation threshold value P, and compare and analyze the evaluation threshold value P with the migration evaluation index Qpzs to evaluate the current condition of the tumor patient and take corresponding medical measures according to the condition.

[0058] During the operation of this system, through the integrated scanning monitoring module, the system can use advanced imaging technology and molecular probes to accurately obtain tomographic images in tumor patients and effectively identify biomarkers. This high-resolution imaging and biomarker detection method can accurately locate the primary site of the tumor, thus providing a reliable basis for subsequent treatment. The image processing module pre-processes the acquired tomographic images, including denoising, image smoothing and geometric correction, and improves the image quality through image enhancement technology. This processing improves the clarity and information content of the image, laying the foundation for accurate identification of tumor growth status and characteristics. The disease course tracking module can detect the growth status of the tumor in real time based on the processed image data set, and obtain relevant environmental data information in combination with the primary site of the tumor. By establishing a disease database and applying convolutional neural network technology to train the disease course prediction model, it can achieve accurate tracking of tumor growth dynamics and provide a scientific basis for disease course evaluation and management. The disease prediction module constructs the growth coefficient Szxs and the environmental impact coefficient Hyxs by comprehensively analyzing the tumor growth status and environmental factors, and performs linear normalization processing on them to accurately estimate the migration assessment index Qpzs. This comprehensive assessment capability can predict the migration risk of tumors early and help doctors develop personalized treatment plans. The medical management module presets the assessment threshold P and compares it with the migration assessment index Qpzs to further realize the real-time assessment of the condition of tumor patients. When the migration assessment index Qpzs exceeds the preset threshold, the system can automatically issue a warning instruction and take corresponding medical measures based on the assessment results. In short, the system further improves the disease management efficiency and treatment accuracy of tumor patients by integrating advanced scanning monitoring, image processing, disease tracking, disease prediction and medical management modules, providing comprehensive and scientific decision-making support for clinicians, thereby improving the treatment effect and prognosis of tumor patients.

[0059] Example 2

[0060] Please refer to Figure 1 ,Specifically: the scanning monitoring module includes a scanning unit and a position determination unit;

[0061] The scanning unit is used to obtain tomographic images of the tumor patient's body through multi-angle X-ray scanning, which can provide detailed anatomical location of the tumor, and is widely used to detect the location, size and relationship of the primary tumor with surrounding tissues, and to generate tissue images of the tumor in the body using magnetic resonance imaging (MRI) to distinguish soft tissue structures, with high contrast for soft tissues, which helps to identify the subtle structure of the tumor;

[0062] The position determination unit is used to track biomarkers by labeling molecular probes with radioactive isotopes and labeling specific biomarkers with magnetic nanoparticles to enhance image contrast, wherein the biomarkers include but are not limited to carcinoembryonic antigen (CEA), prostate-specific antigen (PSA) or mutant genes (such as EGFR, KRAS).

[0063] Among them, biomarkers refer to molecules or chemicals that can reflect specific physiological or pathological processes in organisms.

[0064] The image processing module includes a preprocessing unit and an image enhancement unit;

[0065] The preprocessing unit is used to use wavelet denoising technology to decompose the data information in the tomographic image and the tissue image through wavelet transform, remove the noise component in the wavelet domain, reconstruct several image frames back to the original domain through inverse transform, adjust the brightness by histogram equalization, stretch the range of the image, and adjust the contrast of the image;

[0066] The image enhancement unit is used to standardize the tomographic images and tissue images into a unified format, sort them in chronological order, and align images acquired from different perspectives to ensure consistency. The alignment method can be to translate or rotate the images.

[0067] In this embodiment, the scanning unit uses multi-angle X-ray scanning and magnetic resonance imaging (MRI) technology to obtain detailed tomographic images of tumor patients. This multi-faceted image acquisition capability can not only accurately locate the primary site of the tumor, but also display the size of the tumor and its relationship with surrounding tissues in detail, especially the comparison of soft tissue structures, help identify the subtle structure of the tumor, and provide accurate anatomical information and pathological characteristics for clinicians. The position determination unit enhances the contrast of the image through molecular probes labeled with radioactive isotopes and biomarkers labeled with magnetic nanoparticles. The application of biomarkers such as carcinoembryonic antigen, prostate-specific antigen and mutant genes can improve the sensitivity and specificity of the image to tumor cells, which is convenient for accurately identifying and locating tumors and their metastatic sites. The preprocessing unit effectively removes the noise component in the image and adjusts the brightness and contrast of the image through wavelet denoising technology and histogram equalization. This processing not only improves the clarity and readability of the image, but also ensures the accuracy of the image data, providing high-quality input data for subsequent analysis. The image enhancement unit aligns images acquired from different perspectives through data standardization and time sequence sorting to ensure image accuracy and reliability. This standardization process helps maintain consistency in data across multiple scans and at different time points, further avoiding diagnostic errors caused by image inconsistencies. Overall, the scanning monitoring module and image processing module further improve the diagnostic accuracy and monitoring capabilities of tumors through precise image acquisition and efficient image processing, providing reliable technical support for developing personalized treatment plans and improving treatment effects.

[0068] Example 3

[0069] Please refer to Figure 1 ,Specifically: the disease course tracking module includes a data extraction unit and a modeling unit;

[0070] The data extraction unit is used to detect and obtain the tumor growth status data information in the tumor patient's body based on the image data set, and at the same time, in combination with the primary site of the tumor, obtain the relevant environmental data information around the tumor, wherein the tumor growth status data information includes the blood vessel lumen diameter Xgqz, the blood vessel wall thickness Xbhd, the blood vessel density Xgmd and the blood flow velocity Xlsd at each monitoring time point, and the mean value Xlsd of the blood flow velocity within the monitoring period is obtained by a statistical mean algorithm avg ;

[0071] The tumor surrounding environment data information includes the oxygen partial pressure Yfy, the concentration Myyz of immunosuppressive factors and the pH value in the tumor tissue.

[0072] In this embodiment, the data extraction unit can extract detailed tumor growth status data information from the image data set. These parameters comprehensively reflect the vascularization characteristics and physiological state of the tumor, which helps to gain a deeper understanding of the growth dynamics and vascular supply of the tumor. The mean blood flow velocity Xlsd obtained by the statistical algorithm avg , provides the average blood flow velocity data during the monitoring period. This information helps to evaluate the blood supply of the tumor, monitor its changing trend over time, and further analyze the growth and development of the tumor. The data extraction unit also obtains data information about the environment around the tumor. These environmental factors have an important impact on the growth and metastasis of the tumor. Understanding these parameters can help better evaluate the tumor microenvironment and predict its possible behavior patterns. Combining tumor growth status data and environmental data information, the modeling unit can establish a comprehensive disease database. By systematically analyzing and modeling these data, the course of the tumor can be tracked more accurately, and its possible metastasis trend and growth pattern can be predicted. By comprehensively monitoring the tumor growth status and surrounding environment, more detailed disease information can be provided to doctors. Based on this information, doctors can formulate more personalized and accurate treatment plans to improve the treatment effect and patient prognosis. Overall, the course tracking module of the system provides the ability to deeply understand the development of tumors and predict their behavior patterns by extracting and comprehensively analyzing tumor growth status and environmental data.

[0073] Example 4

[0074] Please refer to Figure 1 Specifically: the modeling unit is used to preliminarily construct an original model based on convolutional neural network technology, and train and test the original model with tumor growth status data information and tumor surrounding environment related data information, and use the trained original model as a disease course recognition model, respectively obtain feature information in the disease course recognition model, and use the acquired feature information to train and test the disease course recognition model, and finally use the trained disease course recognition model as a disease course prediction model.

[0075] According to the tumor growth status data information, the blood flow velocity Xlsd and the vascular wall thickness Xbhd are linearly normalized to calculate the vascular maturity Xcd, which is obtained according to the following formula:

[0076]

[0077] Where i = 1, 2, 3, ..., n, n represents the monitoring period, Xgqz represents the diameter of the vascular lumen, Xlsd i Expressed as the blood flow velocity at the i-th monitoring time point, Xlsd avgIt is represented as the mean value of blood flow velocity in the monitoring period, a1, a2 and a3 are all weight values, where 0<a1≤1, 0<a2≤1, 0<a3≤1, and a1+a2+a3=1;

[0078] The above-mentioned blood vessel lumen diameter Xgqz can obtain detailed images of blood vessels and measure the lumen diameter by injecting contrast agents and using CT scanning.

[0079] Blood flow velocity Xlsd can measure the blood flow velocity through ultrasonic Doppler technology. The change of blood flow velocity can reflect the flow rate in blood vessels and the flow state of blood.

[0080] Blood vessel wall thickness Xbhd The thickness of the blood vessel wall can be measured by ultrasound or MRI technology.

[0081] The growth coefficient Szxs is obtained by the following formula:

[0082]

[0083] Wherein, Xgmd represents the blood vessel density, α and β are weight values, wherein 0<α≤1, 0<β≤1, and α+β=1, and C represents the first correction constant.

[0084] The above-mentioned vascular density Xgmd can be used to evaluate the vascular density within the tumor through contrast-enhanced CT (CECT) or enhanced MRI. High vascular density is usually associated with the invasiveness and metastatic ability of the tumor.

[0085] In this embodiment, the modeling unit uses the convolutional neural network CNN technology to preliminarily construct the original model. By training and testing the tumor growth state data information and the relevant environmental data information around the tumor, the accuracy and robustness of the model are optimized. The application of CNN can effectively extract complex feature information, improve the accuracy of disease course identification, and use it for subsequent prediction and analysis. By calculating the vascular maturity Xcd, it is helpful to accurately assess the maturity of the blood vessels and further understand their impact on tumor growth. The growth coefficient Szxs is calculated by integrating the vascular density Xgmd, which can comprehensively reflect the support of the vascular network for tumor growth. The setting of the weight value allows the model to flexibly adjust the sensitivity of different factors, thereby providing a more scientific growth coefficient and supporting in-depth analysis and prediction of the course of disease. By extracting and training the feature information in the course of disease identification model and using it as a course of disease prediction model, the growth trend and risk factors of the tumor can be deeply analyzed. The trained course of disease prediction model can accurately identify changes in the course of disease and provide a scientific basis to guide treatment decisions. In general, this modeling unit further improves the ability to predict the course of disease and formulate treatment plans through advanced convolutional neural network technology, accurate vascular maturity Xcd assessment and scientific growth coefficient Szxs calculation.

[0086] Example 5

[0087] Please refer to Figure 1 ,Specifically: the disease prediction module includes an environmental analysis unit and a comprehensive analysis unit;

[0088] The environmental analysis unit is used to construct the environmental impact coefficient Hyxs according to the relevant environmental data information, which is obtained in the following way:

[0089]

[0090] Wherein, Yfy represents the oxygen partial pressure in the tumor tissue, pH represents the acidity and alkalinity, Myyz represents the concentration of the immunosuppressive factor, b1, b2 and b3 are all weight values, wherein 0<b1≤1, 0<b2≤1, 0<b3≤1, and b1+b2+b3=1, and U represents the second correction constant.

[0091] Among them, the oxygen partial pressure Yfy in tumor tissue is usually lower than that in normal tissue. The hypoxic environment (pO2 lower than 1-2 mmHg) can activate hypoxia-inducible factors (HIFs), promote epithelial-mesenchymal transition (EMT) and angiogenesis, thereby enhancing the migration ability of tumor cells, and the hypoxic environment promotes the invasiveness and metastasis of tumor cells. The oxygen partial pressure level of tumor tissue can be directly measured by the tissue oxygen partial pressure sensor, which is very important for evaluating the hypoxic area and optimizing the treatment strategy.

[0092] The acidity of the tumor microenvironment is usually lower than that of normal tissue (pH < 6.8), and the acidic environment will activate matrix metalloproteinases (MMPs) and change the adhesion between cells. Among them, the pH value of the tumor microenvironment is monitored by a body fluid analysis instrument;

[0093] The concentration of immunosuppressive factors Myyz refers to the concentration of transforming growth factor β, which can usually be obtained through enzyme-linked immunosorbent assay. The principle of enzyme-linked immunosorbent assay is to detect the concentration of immunosuppressive factors through antibody-antigen reaction and enzyme-labeled antibodies. It is widely used to measure the concentration of immunosuppressive factors in body fluids (such as serum, plasma, and tissue fluid).

[0094] It should be noted that immunosuppressive factors can inhibit or weaken the function of the immune system, help tumor cells escape immune surveillance, and thus promote their migration and metastasis.

[0095] In this embodiment, the environmental analysis unit constructs the environmental impact coefficient Hyxs based on the environmental data information around the tumor. Through the comprehensive analysis of multiple groups of key environmental parameters, the impact of the environment on tumor growth and migration can be evaluated in multiple dimensions. The accurate evaluation of the environmental analysis unit provides doctors with detailed data on the tumor environment, so that the treatment strategy can be adjusted according to environmental changes, which helps to formulate more personalized treatment plans and improve treatment effects. It can also more accurately predict the development trend of the tumor and possible migration risks. Accurate predictions help to detect changes in the disease early and take corresponding intervention measures, thereby improving the effectiveness of disease management. In short, the disease prediction module of the system further improves the accuracy of tumor disease prediction and the degree of personalization of treatment strategies by scientifically constructing the environmental impact coefficient Hyxs and comprehensively analyzing the key factors of the tumor microenvironment.

[0096] Example 6

[0097] Please refer to Figure 1 Specifically: the comprehensive analysis unit is used to input the growth coefficient Szxs and the environmental impact coefficient Hyxs into the disease course prediction model to construct the migration evaluation index Qpzs, and the migration evaluation index Qpzs is obtained by the following formula:

[0098]

[0099] In the formula, F1 and F2 are both weight values, wherein 0<F1≤1, 0<F2≤1, and F1+F2=1, and K represents the third correction constant.

[0100] The medical management module includes a comparison unit and a management unit;

[0101] The comparison unit is used to compare and analyze the migration evaluation index Qpzs with the evaluation threshold P to evaluate the current condition of the tumor patient. The specific comparison and analysis content is as follows:

[0102] If the migration assessment index Qpzs exceeds the assessment threshold P, it means that there is a risk of tumor migration in the current tumor patient, and an early warning instruction will be issued;

[0103] If the migration assessment index Qpzs does not exceed the assessment threshold P, it means that the tumor in the current tumor patient does not have the risk of migration, and no additional warning instructions will be issued at this time.

[0104] The management unit will take corresponding medical measures based on the comparison and analysis results in the comparison unit, including:

[0105] If an early warning order is issued, further imaging examinations will be conducted to examine the expansion of the tumor in the patient's body, and PET scans will be performed to detect the metabolic activity of the tumor to help identify active metastatic areas. Blood tests will be used to identify the presence of circulating tumor cells to confirm whether the tumor has metastasized. Biopsy of abnormal areas of the patient's tumor will be performed to obtain tissue samples to determine the nature and extent of the metastasis.

[0106] Among them, the nature of metastasis refers to the specific characteristics and biological behavior of tumor metastasis, which includes: 1. Determining whether the metastatic tumor cells are consistent with the cell type of the primary tumor. For example, when breast cancer metastasizes to the lungs, the cancer cells in the biopsy sample should be the same as the original breast cancer cells; 2. Detecting whether the metastatic tumor has specific gene mutations or gene rearrangements, which may affect the behavior of the tumor and its response to treatment.

[0107] The extent of metastasis refers to the extent and severity of the metastatic tumor. This includes: 1. Determining whether there are multiple metastatic lesions to understand the extent of metastasis; 2. Detecting whether the metastasis involves lymph nodes. Lymph node metastasis usually means that the disease is more serious and may require more aggressive treatment.

[0108] It should be noted that circulating tumor cells (CTCs) refer to tumor cells that are shed from primary tumors or metastatic tumors into the blood. These cells circulate in the blood and may form new tumors in other parts, i.e. metastasis. The detection of circulating tumor cells (CTCs) can be used to detect tumor metastasis or recurrence at an early stage.

[0109] If no additional warning instructions are issued, biochemical tests will continue to be performed according to the established follow-up plan to monitor changes in symptoms of cancer patients, ensure timely detection of any abnormalities, maintain the current treatment plan, which may include chemotherapy, radiotherapy, targeted therapy or immunotherapy, and make adaptive adjustments based on the cancer patient's response and side effects. Regular psychological counseling will also be provided to help patients cope with possible anxiety and stress.

[0110] In this embodiment, the comprehensive analysis unit constructs a migration assessment index Qpzs by inputting the growth coefficient Szxs and the environmental impact coefficient Hyxs into the course prediction model. The index combines the influence of tumor growth status and environmental factors, and provides a quantitative basis for assessing the risk of tumor migration. The comparison unit can identify whether there is a migration risk in the tumor patient's body based on the comparison analysis of the migration assessment index Qpzs and the assessment threshold P. If the assessment index Qpzs exceeds the threshold, an early warning instruction will be issued in time. This mechanism ensures the early identification of potential migration risks, helps to take intervention measures in time, and further avoids further deterioration of the disease. After issuing the early warning instruction, the system will start further inspection procedures, including imaging examinations, PET scans, blood tests and biopsies. These measures can provide a detailed understanding of the expansion of the tumor, metabolic activity, and whether there are circulating tumor cells, thereby confirming the nature and extent of tumor metastasis. This process ensures a comprehensive assessment of tumor migration and provides a scientific basis for subsequent treatment. If no additional warning instructions are issued, the system will continue to conduct biochemical tests according to the established follow-up plan, monitor changes in patients' symptoms, maintain the existing treatment plan, and make adaptive adjustments. Regular psychological counseling can also help patients cope with anxiety and stress, improve treatment experience and quality of life. Based on the analysis results of the migration assessment index, the medical management module can take appropriate medical measures for specific conditions. Overall, the medical management module of the system further realizes the precise management and optimized treatment of cancer patients by comprehensively evaluating the risk of tumor migration and implementing personalized medical measures. This not only improves the ability to identify and warn of tumor migration risks, but also ensures the scientific nature of the treatment plan and the overall health management level of the patient.

[0111] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent medical management system for the entire course of disease for cancer patients, characterized by: It includes scanning monitoring module, image processing module, disease course tracking module, disease prediction module and medical management module; The scanning monitoring module is used to obtain tomographic images of the tumor patient's body based on imaging technology, and use molecular probes to identify biomarkers in the tumor patient's body to determine the primary site of the tumor; The image processing module is used to pre-process the tomographic image, remove noise, smooth the image, and perform geometric correction, and to identify and extract effective features in the tomographic image, and to improve the image quality based on image enhancement technology to generate an image data set; The disease course tracking module is used to detect and obtain the tumor growth status data information in the tumor patient based on the image data set, and obtain the relevant environmental data information around the tumor in combination with the primary site of the tumor to build a disease database, train a disease course prediction model based on the convolutional neural network technology, and build a growth coefficient Szxs based on the tumor growth status data information; According to the tumor growth status data information, the blood flow velocity Xlsd and the vascular wall thickness Xbhd are linearly normalized to calculate the vascular maturity Xcd, which is obtained according to the following formula: Where i = 1, 2, 3, ..., n, n represents the monitoring period, Xgqz represents the diameter of the vascular lumen, Xlsd i Expressed as the blood flow velocity at the i-th monitoring time point, Xlsd avg It is represented as the mean value of blood flow velocity during the monitoring period, and a1, a2 and a3 are all weight values; The growth coefficient Szxs is obtained by the following formula: In the formula, Xgmd represents the blood vessel density, α and β are weight values, and C represents the first correction constant; The disease prediction module is used to construct an environmental impact coefficient Hyxs according to relevant environmental data information, and estimate the migration assessment index Qpzs by linearly normalizing the growth coefficient Szxs and the environmental impact coefficient Hyxs; The disease prediction module includes an environmental analysis unit and a comprehensive analysis unit; The environmental analysis unit is used to construct the environmental impact coefficient Hyxs according to the relevant environmental data information, which is obtained in the following way: Wherein, Yfy represents the oxygen partial pressure in the tumor tissue, pH represents the acidity and alkalinity, Myyz represents the concentration of the immunosuppressive factor, b1, b2 and b3 are all weight values, and U represents the second correction constant; The comprehensive analysis unit is used to input the growth coefficient Szxs and the environmental impact coefficient Hyxs into the disease course prediction model to construct a migration assessment index Qpzs, and the migration assessment index Qpzs is obtained by the following formula: In the formula, F1 and F2 are weight values, and K represents the third correction constant; The medical management module is used to pre-set an evaluation threshold value P, and compare and analyze the evaluation threshold value P with the migration evaluation index Qpzs to evaluate the current condition of the tumor patient and take corresponding medical measures according to the condition.

2. According to claim 1, an intelligent medical management system for the entire course of disease for cancer patients is characterized by: The scanning monitoring module includes a scanning unit and a position determination unit; The scanning unit is used to obtain a tomographic image of the tumor patient's body through multi-angle X-ray scanning, and to generate a tissue image of the tumor in the body by magnetic resonance imaging to distinguish soft tissue structures; The position determination unit will track biomarkers by labeling molecular probes with radioactive isotopes, and label magnetic nanoparticles as specific biomarkers to enhance image contrast, wherein the biomarkers include but are not limited to carcinoembryonic antigen, prostate specific antigen or mutant gene.

3. The intelligent medical management system for the entire course of disease for cancer patients according to claim 1, characterized in that: The image processing module includes a preprocessing unit and an image enhancement unit; The preprocessing unit is used to use wavelet denoising technology to decompose the data information in the tomographic image and the tissue image through wavelet transform, remove the noise component in the wavelet domain, reconstruct several image frames back to the original domain through inverse transform, adjust the brightness by histogram equalization, stretch the range of the image, and adjust the contrast of the image; The image enhancement unit is used to standardize the data of the tomographic image and the tissue image to obtain a unified format, and to sort them in chronological order, and to align the images acquired from different viewing angles.

4. The intelligent medical management system for the entire course of disease for cancer patients according to claim 1, characterized in that: The disease course tracking module includes a data extraction unit and a modeling unit; The data extraction unit is used to detect and obtain the tumor growth status data information in the tumor patient's body based on the image data set, and at the same time, in combination with the primary site of the tumor, obtain the relevant environmental data information around the tumor, wherein the tumor growth status data information includes the blood vessel lumen diameter Xgqz, the blood vessel wall thickness Xbhd, the blood vessel density Xgmd and the blood flow velocity Xlsd at each monitoring time point, and the mean value Xlsd of the blood flow velocity within the monitoring period is obtained by a statistical mean algorithm avg ; The tumor surrounding environment data information includes the oxygen partial pressure Yfy, the concentration Myyz of immunosuppressive factors and the pH value in the tumor tissue.

5. The intelligent medical management system for the entire course of disease for cancer patients according to claim 4, characterized in that: The modeling unit is used to preliminarily construct an original model based on convolutional neural network technology, and train and test the original model with tumor growth status data information and tumor surrounding related environment data information, and use the trained original model as a disease course recognition model, respectively obtain feature information in the disease course recognition model, and use the acquired feature information to train and test the disease course recognition model, and finally use the trained disease course recognition model as a disease course prediction model.

6. The intelligent medical management system for the entire course of disease for cancer patients according to claim 1, characterized in that: The medical management module includes a comparison unit and a management unit; The comparison unit is used to compare and analyze the migration evaluation index Qpzs with the evaluation threshold P to evaluate the current condition of the tumor patient. The specific comparison and analysis content is as follows: If the migration assessment index Qpzs exceeds the assessment threshold P, it means that there is a risk of tumor migration in the current tumor patient, and an early warning instruction will be issued; If the migration assessment index Qpzs does not exceed the assessment threshold P, it means that the tumor in the current tumor patient does not have the risk of migration, and no additional warning instructions will be issued at this time.

7. The intelligent medical management system for the entire course of disease for cancer patients according to claim 6, characterized in that: The management unit will take corresponding medical measures based on the comparison and analysis results in the comparison unit, including: If an early warning order is issued, further imaging examinations will be conducted to examine the expansion of the tumor in the patient's body, and PET scans will be performed to detect the metabolic activity of the tumor. Blood tests will be used to identify the presence of circulating tumor cells to confirm whether the tumor has metastasized. Biopsy of abnormal areas of the patient's tumor will be performed to obtain tissue samples to determine the nature and extent of the metastasis. If no additional warning instructions are issued, biochemical tests will continue to be performed according to the established follow-up plan, symptoms of cancer patients will be monitored, the current treatment plan will be maintained, including chemotherapy, radiotherapy, targeted therapy or immunotherapy, adaptive adjustments will be made based on the response and side effects of cancer patients, and psychological counseling will be provided regularly.

Images