Tumor microenvironment response type radiotherapy strategy making method

Abstract

The invention relates to the technical field of tumor treatment, in particular to a tumor microenvironment response type radiotherapy strategy making method, which comprises the following steps: S1, tumor microenvironment dynamic interaction analysis: monitoring and evaluating signal transmission and interaction between cells in a tumor microenvironment in real time, and identifying key factors influencing a radiotherapy effect; s2, dynamic monitoring of the circulating tumor cells: evaluating changes of the circulating tumor cells in the radiotherapy process by analyzing the number, phenotype and gene characteristics of the circulating tumor cells; s3, self-adaptive radiotherapy strategy adjustment: adjusting a radiotherapy scheme in real time; s4, feedback mechanism and prognosis evaluation: establishing a feedback mechanism, regularly evaluating the treatment effect by monitoring the tumor microenvironment and circulating tumor cell change, and optimizing the treatment scheme according to the evaluation result. According to the invention, accurate regulation and control of the radiotherapy scheme are realized, so that the accuracy and the treatment effect of personalized treatment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tumor treatment, and in particular to a method for formulating a tumor microenvironment responsive radiotherapy strategy. Background Art

[0002] The treatment of tumors has always been the focus of medical research, and radiotherapy, as an important cancer treatment method, is widely used in various types of tumors. With the development of science and technology, radiotherapy technology has continued to improve, and its accuracy and effectiveness have also increased accordingly. However, the complexity of the tumor microenvironment and the heterogeneity of tumor cells make it difficult for a single radiotherapy plan to achieve the ideal therapeutic effect. Therefore, it is urgent to formulate personalized radiotherapy strategies based on the dynamic changes of the tumor microenvironment to improve the treatment effect and patient quality of life.

[0003] Current radiotherapy plans are usually based on static evaluation and lack real-time feedback mechanisms for dynamic monitoring of tumor microenvironment changes and circulating tumor cells. This leads to the neglect of individual differences among patients and makes it difficult to timely identify the tumor's response to treatment, which in turn affects the treatment effect. In addition, existing technologies are also insufficient in the dynamic evaluation of key biomarkers and the optimization of treatment plans. They fail to effectively integrate multiple biological signal data and lack scientific evaluation of radiotherapy effects, thus limiting the personalization and accuracy of radiotherapy.

[0004] The present invention aims to provide a method for formulating a tumor microenvironment-responsive radiotherapy strategy, which can accurately identify the key factors affecting the effect of radiotherapy and dynamically optimize the treatment plan according to the specific situation of the patient, thereby improving the effectiveness of radiotherapy, reducing damage to healthy tissues, and significantly improving the survival rate and quality of life of patients. Summary of the invention

[0005] The present invention provides a method for formulating a tumor microenvironment-responsive radiotherapy strategy.

[0006] The method for formulating a tumor microenvironment-responsive radiotherapy strategy includes the following steps:

[0007] S1, Dynamic interaction analysis of tumor microenvironment: Real-time monitoring and evaluation of signal transduction and interaction between cells in the tumor microenvironment, identification of key factors affecting the effect of radiotherapy, including the interaction between cytokines, immune cells and tumor-associated fibroblasts, including:

[0008] S11, signal transduction network construction: by collecting the expression data of relevant cytokines in the tumor microenvironment, constructing the intercellular signal transduction network, clarifying the interaction between different cell types, and revealing the path and intensity of signal transduction;

[0009] S12, dynamic monitoring implementation: using biosensors and imaging techniques to track changes in cell-cell interactions in the tumor microenvironment, including the activation state of immune cells and the response of tumor-associated fibroblasts;

[0010] S13, Identification and analysis of key factors: Identify key factors in the signal transduction network and analyze their effects on tumor cell survival, proliferation and migration before and after radiotherapy;

[0011] S2, Dynamic monitoring of circulating tumor cells (CTC): By analyzing the number, phenotype and gene characteristics of circulating tumor cells, the changes during radiotherapy are evaluated;

[0012] S3, Adaptive radiotherapy strategy adjustment: Based on the results of dynamic interaction analysis of the tumor microenvironment and circulating tumor cell (CTC) monitoring, the radiotherapy plan, including dose, irradiation time and frequency, is adjusted in real time;

[0013] S4, Feedback mechanism and prognosis assessment: Establish a feedback mechanism to regularly evaluate the treatment effect by monitoring changes in the tumor microenvironment and circulating tumor cells (CTCs), and optimize the treatment plan based on the evaluation results.

[0014] Optionally, the signal transmission network construction in S11 includes:

[0015] S111, data collection and preprocessing: collect the expression data of cytokines in the tumor microenvironment, including concentration, time series and related cell types, and standardize the expression data;

[0016] S112, correlation analysis: Pearson correlation coefficient was used to calculate the correlation between cytokines to identify potential signal transduction relationships;

[0017] S113, network construction: based on the correlation analysis results, construct an intercellular signaling network, where nodes represent different cytokines, edges represent the interaction between them, and edge weights are determined according to the strength of the correlation;

[0018] S114, Path and Strength Analysis: Apply Dijkstra algorithm to analyze the shortest path and signal strength in the network.

[0019] Optionally, the dynamic monitoring implementation in S12 includes:

[0020] S121, Biosensor data collection: Use biosensors to monitor key biological signals in the tumor microenvironment in real time, including cytokine concentrations, pH, oxygen levels, and collect data on the activation status of immune cells (proliferation rate of T cells, cytokine release) and the response of tumor-associated fibroblasts (matrix protein production rate);

[0021] S122, Application of imaging technology: Visualize the cell-cell interactions in the tumor microenvironment, including the migration and aggregation of immune cells and the physical changes of tumor-associated fibroblasts, through dynamic imaging technology (multiphoton microscopy, magnetic resonance imaging), and generate a series of time-series image data;

[0022] S123, Data Analysis: Based on the collected biosensor data and generated time series image data, the Bayesian dynamic network model was applied to analyze the changes in cell-cell interactions in the tumor microenvironment at different times, and to construct the dynamic relationship of cell-cell interactions to capture the interaction process between immune cells and tumor-associated fibroblasts at different time points, and to predict the dynamic changes before and after radiotherapy.

[0023] Optionally, the Bayesian dynamic network model in S123 includes:

[0024] S1231, introduction of time dependency: In order to deal with the time-dependent characteristics of the tumor microenvironment, time-dependent parameters are added to describe the interactive changes at different moments;

[0025] S1232, add external variable correction: In order to adapt to the dynamic changes of the microenvironment before and after radiotherapy, introduce the external control variable U t , represents the change of radiotherapy conditions;

[0026] S1233, introduction of nonlinear interaction terms: considering that the interaction between cells in the tumor microenvironment is nonlinear, nonlinear terms are added and approximated by kernel functions;

[0027] S1234, Dynamically adjust model weights: Introduce a time-dependent weight adjustment mechanism α t , dynamically adapt to changes in the tumor microenvironment during radiotherapy;

[0028] S1235, updating of posterior probability: the microenvironment changes before and after radiotherapy are continuously updated through posterior probability.

[0029] Optionally, the identification and analysis of key factors in S13 includes:

[0030] S131, Node centrality analysis of signaling networks: Identify key factors by calculating the centrality of each node (i.e., cytokine or other biomarker) in the signaling network, including:

[0031] Degree centrality: calculates the degree of each node, that is, the number of connections with other nodes;

[0032] Betweenness centrality: Calculates the number of times each node is on the shortest path in the network;

[0033] S132, Analysis of the effects of key factors on tumor cell survival and proliferation: Once the key factors were identified, a linear regression model was used to analyze the effects of the key factors on tumor cell survival and proliferation before and after radiotherapy;

[0034] S133, Analysis of the influence of key factors on tumor cell migration: For the analysis of tumor cell migration, a multivariate regression model was used to analyze the relationship between key factors and tumor cell migration rate before and after radiotherapy.

[0035] Optionally, the dynamic monitoring of circulating tumor cells (CTC) in S2 includes:

[0036] S21, Circulating tumor cell number and phenotype analysis: Use liquid biopsy technology to detect the number of circulating tumor cells in the patient's blood in real time, and analyze the phenotype of circulating tumor cells by flow cytometry and immunofluorescence labeling to identify different types of circulating tumor cells (such as epithelial, mesenchymal, etc.). By regularly detecting the number and phenotypic changes of circulating tumor cells, evaluate the response of the tumor during radiotherapy and correlate it with the treatment effect;

[0037] S22, Analysis of genetic characteristics of circulating tumor cells: Single-cell genome sequencing technology is used to analyze the genetic characteristics of circulating tumor cells, identify gene mutations or expression changes associated with radiotherapy resistance, and determine the gene mutations or adaptive changes produced by tumor cells during radiotherapy.

[0038] Optionally, the circulating tumor cell quantity and phenotype analysis in S21 includes:

[0039] S211, Detection of circulating tumor cell count: Using liquid biopsy technology, blood samples from patients are collected in real time, circulating tumor cells are extracted, and the number of circulating tumor cells per unit of blood is calculated by statistical methods;

[0040] S212, Circulating tumor cell phenotyping and classification: Flow cytometry and immunofluorescence labeling were used to perform phenotypic analysis on the detected circulating tumor cells to identify different types of circulating tumor cells, including epithelial and mesenchymal cells. Marker proteins (such as EpCAM and vimentin) were used to distinguish the types of circulating tumor cells, and support vector machines (SVM) were used to classify circulating tumor cells.

[0041] S213, Treatment response evaluation: The response of the tumor to radiotherapy was evaluated by regularly detecting the number and phenotypic changes of circulating tumor cells. The therapeutic effect of radiotherapy was evaluated using a linear regression model based on the trend of changes in the number of circulating tumor cells and the dynamic changes of different circulating tumor cell types.

[0042] Optionally, the analysis of circulating tumor cell gene features in S22 includes:

[0043] S221, single-cell genome sequencing: single-cell isolation technology is used to separate circulating tumor cells (CTCs) at the single-cell level. Single-cell genome sequencing technology is used to comprehensively analyze the genetic characteristics of circulating tumor cells (CTCs) and obtain gene mutations, copy number changes and gene expression profiles;

[0044] S222, Gene mutation or expression identification: Use stochastic gradient descent regression (SGD) model to detect gene mutation or expression changes;

[0045] S223, Radiotherapy resistance assessment: By identifying gene mutations or expression changes, a logistic regression model is used to predict the association between gene mutations and radiotherapy resistance, to determine whether tumor cells have developed resistance or adaptive changes during radiotherapy.

[0046] Optionally, the adaptive radiotherapy strategy adjustment in S3 includes:

[0047] S31, adjust the radiation dose according to immune cell activity: when immune cell activation increases, the radiation dose is reduced, and when cytokine concentrations indicate that the intensity of growth-promoting signals in the tumor microenvironment reaches a threshold intensity, the radiation dose is increased;

[0048] S32, adjust the irradiation time according to the monitoring results of circulating tumor cells: when the number of circulating tumor cells decreases and the phenotype does not change within the predetermined range, maintain the irradiation time; when the number or phenotype of circulating tumor cells changes beyond the predetermined range (indicating that the tumor cells are adaptable or resistant to radiotherapy), extend the irradiation time;

[0049] S33, adjust the frequency of radiotherapy according to the growth rate of the tumor: when the signal transmission rate in the tumor microenvironment is monitored to drop below the rate threshold and the production rate of circulating tumor cells is lower than the specified standard, reduce the frequency of radiotherapy; when the growth rate of tumor cells accelerates and the number of circulating tumor cells exceeds the specified increase, increase the frequency of radiotherapy.

[0050] Optionally, the feedback mechanism and prognosis assessment in S4 include:

[0051] S41, Establish a feedback mechanism: Establish a real-time feedback mechanism by regularly monitoring the cytokine concentration, immune cell activity, and the number and phenotypic changes of circulating tumor cells (CTCs) in the tumor microenvironment.

[0052] S42, prognostic assessment: based on the real-time feedback mechanism monitoring of cytokine concentrations, immune cell activity, and the number and phenotypic changes of circulating tumor cells (CTCs), the patient's prognosis was predicted using a multivariate regression model;

[0053] S43, treatment plan optimization: Based on the results of the prognostic evaluation, the treatment plan is dynamically adjusted using a feedback mechanism. If the evaluation value is lower than the response threshold, the treatment plan is optimized by increasing the radiotherapy dose, extending the irradiation time, or adjusting the radiotherapy frequency.

[0054] Beneficial effects of the present invention:

[0055] The present invention, through real-time monitoring and evaluation of the tumor microenvironment, especially the dynamic interactive analysis of cytokines, immune cells and tumor-associated fibroblasts, can adjust the radiotherapy plan in real time during radiotherapy, including dosage, irradiation time and frequency. Through the identification of signal transmission networks and key factors, combined with CTC dynamic monitoring data, precise regulation of radiotherapy plans is achieved, thereby improving the accuracy and therapeutic effect of personalized treatment.

[0056] The present invention, by regularly monitoring biomarkers such as CTC number, immune cell activity and cytokine concentration, combined with a multivariate regression model, can quantitatively analyze the patient's response to treatment and dynamically optimize the treatment plan, so that the radiotherapy plan can be adjusted at any time according to the patient's response, effectively reducing damage to healthy tissues while ensuring effective control of tumor cells.

[0057] The present invention, through the application of multiple biosensors and imaging technologies, tracks the changes in the tumor microenvironment in real time, and combines the Bayesian dynamic network model and regression analysis of key factors to comprehensively predict tumor response and drug resistance development before and after radiotherapy, which is used to continuously optimize radiotherapy plans, thereby improving the patient's prognosis and quality of life, and significantly enhancing the effect of personalized precision treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A schematic diagram of a formulation method flow chart of an embodiment of the present invention;

[0060] Figure 2 Schematic diagram of dynamic interaction analysis of tumor microenvironment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0062] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0063] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0064] like Figure 1-Figure 2 As shown, the method for formulating a tumor microenvironment-responsive radiotherapy strategy includes the following steps:

[0065] S1, Dynamic interaction analysis of tumor microenvironment: Real-time monitoring and evaluation of signal transduction and interaction between cells in the tumor microenvironment, identification of key factors affecting the effect of radiotherapy, including the interaction between cytokines, immune cells and tumor-associated fibroblasts, to achieve precise adjustment of treatment plans, including:

[0066] S11, signal transduction network construction: by collecting the expression data of relevant cytokines in the tumor microenvironment, constructing the intercellular signal transduction network, clarifying the interaction between different cell types, and revealing the path and intensity of signal transduction;

[0067] S12, Dynamic Monitoring Implementation: Using biosensors and imaging techniques to track changes in cell-cell interactions in the tumor microenvironment, including the activation state of immune cells and the response of tumor-associated fibroblasts;

[0068] S13, Identification and analysis of key factors: Identify key factors in the signal transduction network and analyze their effects on tumor cell survival, proliferation and migration before and after radiotherapy;

[0069] S2, Dynamic monitoring of circulating tumor cells (CTC): By analyzing the number, phenotype and gene characteristics of circulating tumor cells, the changes during radiotherapy are evaluated;

[0070] S3, Adaptive radiotherapy strategy adjustment: Based on the results of dynamic interaction analysis of the tumor microenvironment and circulating tumor cell (CTC) monitoring, the radiotherapy plan, including dose, irradiation time and frequency, is adjusted in real time to respond to changes in the microenvironment and CTCs and optimize the treatment effect;

[0071] S4, Feedback mechanism and prognosis assessment: Establish a feedback mechanism to regularly evaluate the treatment effect by monitoring the changes in the tumor microenvironment and circulating tumor cells (CTCs), and optimize the treatment plan based on the evaluation results to improve the patient's survival rate and quality of life;

[0072] Through the above content, accurate adjustment of radiotherapy plan can be achieved, the treatment effect and individualized treatment level can be improved, and based on real-time feedback mechanism and adaptive strategy, it can respond to microenvironment changes in a timely manner, thereby optimizing the treatment plan and improving the patient's survival rate and quality of life.

[0073] The signal transmission network construction in S11 includes:

[0074] S111, data collection and preprocessing: collect the expression data of cytokines in the tumor microenvironment, including concentration, time series and related cell types, and standardize the expression data;

[0075] S112, Correlation analysis: Pearson correlation coefficient was used to calculate the correlation between cytokines to identify potential signal transduction relationships, expressed as:

[0076]

[0077] Among them, r xy is the Pearson correlation coefficient between variables x and y, x i is the i-th observation, y i is the ith observation value, is the sample mean of variable x, is the sample mean of variable y;

[0078] S113, network construction: Based on the correlation analysis results, an intercellular signaling network is constructed. The nodes represent different cytokines, and the edges represent the interaction between them. The weight of the edge is determined according to the correlation strength, which is expressed as:

[0079] w ij =|r xy |;

[0080] Among them, w ijis the weight of the edge between node i and node j, r xy is the Pearson correlation coefficient between two cytokines (or nodes);

[0081] S114, Path and Strength Analysis: Apply Dijkstra algorithm to analyze the shortest path and signal strength in the network to reveal the main signal transmission path and the role of key factors in signal transmission;

[0082] The Dijkstra algorithm specifically includes:

[0083] (1) Initialization: Set a distance value d[v] for all nodes, which represents the shortest path distance from the source node s to the node v, and set an empty visited node set Use a priority queue to store the current distance of each node, expressed as:

[0084]

[0085] (2) Select the shortest path node: Select the node u with the smallest distance value d[u] from the unvisited nodes, and add u to the visited node set S, expressed as:

[0086] u=argmin v∈v\s d[v];

[0087] S = S ∪ {u};

[0088] (3) Update the distances of adjacent nodes: For all neighbor nodes v of node u (i.e., there is an edge (u, v)), check whether v can be reached closer through u. If so, update d[v], which is expressed as:

[0089] d[v]=min(d[v],d[u]+w uv );

[0090] Among them, w uv is the weight of edge (u,v), which indicates the signal transmission strength from node u to node v;

[0091] (4) Repeat the operation: Repeat the selection of shortest path nodes and the updating of the distances between adjacent nodes until all nodes have been visited (i.e., S = V), or the shortest path from the source node s to the target node has been found;

[0092] (5) Output the shortest path: For each node v, the final shortest path distance is stored in d[v], and the specific shortest path can be found by backtracking the path from the source node s to v;

[0093] Through the above content, the interactive relationship between cytokines in the tumor microenvironment and the key signal transmission pathways are accurately revealed. By applying correlation analysis and the shortest path algorithm, the intensity and efficiency of signal transmission can be quantitatively evaluated, thereby identifying the main factors affecting the effect of radiotherapy. This provides precise guidance for tumor treatment strategies, optimizes radiotherapy plans, and improves the accuracy and efficacy of individualized treatment.

[0094] The dynamic monitoring implementation in S12 includes:

[0095] S121, Biosensor data collection: Use biosensors to monitor key biological signals in the tumor microenvironment in real time, including cytokine concentrations, pH, oxygen levels, and collect data on the activation status of immune cells (proliferation rate of T cells, cytokine release) and the response of tumor-associated fibroblasts (matrix protein production rate);

[0096] S122, Application of imaging technology: Visualize the cell-cell interactions in the tumor microenvironment, including the migration and aggregation of immune cells and the physical changes of tumor-associated fibroblasts, through dynamic imaging technology (multiphoton microscopy, magnetic resonance imaging), and generate a series of time-series image data;

[0097] S123, Data Analysis: Based on the collected biosensor data and generated time series image data, the Bayesian dynamic network model was applied to analyze the changes in cell-cell interactions in the tumor microenvironment at different times, and to construct the dynamic relationship of cell-cell interactions to capture the interaction process between immune cells and tumor-associated fibroblasts at different time points, and to predict the dynamic changes before and after radiotherapy;

[0098] Through the above content, it is possible to track the changes in cell interactions in the tumor microenvironment in real time and accurately. Using the Bayesian dynamic network model, the time series of these interactions can be quantitatively analyzed to capture the dynamic changes in the microenvironment before and after radiotherapy, providing accurate data support for personalized adjustment of treatment plans, and improving the real-time responsiveness of radiotherapy plans and the accuracy of efficacy prediction.

[0099] The Bayesian dynamic network model in S123 includes:

[0100] S1231, introduction of time dependency: In order to deal with the time-dependent characteristics of the tumor microenvironment, time-dependent parameters are added to describe the interactive changes at different times. The changes in the time series are represented by t, and the state transition of the Bayesian dynamic network model is expressed as:

[0101]

[0102] Among them, X tis the state at time t, indicating the interaction state between immune cells and tumor-associated fibroblasts at the current moment, P(X t |X t-1 ,T) is the current state X at time t t At the previous moment, the state X t-1 and the conditional probability under the time-dependent parameter T, X t-1 is the state at time t-1, indicating the interaction state between immune cells and fibroblasts at the previous moment. T is a time-dependent parameter used to describe the changes in cell interactions at different time points. P(X t-1 |X t ,T) is the given previous moment X t-1 and time-dependent parameter T, predicting the current time X t The probability, P(X t |T) is the cell state X at the current time t under the condition given by the time-dependent parameter T t The probability distribution of P(X t-1 |T) is the cell state X at the previous time t-1 under the condition given by the time-dependent parameter T. t-1 The probability distribution of

[0103] S1232, add external variable correction: In order to adapt to the dynamic changes of the microenvironment before and after radiotherapy, introduce the external control variable U t , represents the change of radiotherapy conditions, and the updated Bayesian dynamic network model is expressed as:

[0104]

[0105] Among them, P(X t |X t-1 ,U t ) is the state X at the previous time t-1 t-1 and external variable U t Under the condition that the state X at the current time t t The conditional probability, U t are external variables related to radiotherapy, such as irradiation intensity and dose frequency;

[0106] S1233, introduction of nonlinear interaction terms: Considering that the interaction between cells in the tumor microenvironment is nonlinear, nonlinear terms are added and approximated by kernel functions, expressed as:

[0107]

[0108] Among them, P′(X t |X t-1 ,U t) is the state probability after nonlinear transformation, that is, given the state X at the previous moment t-1 and external variable U t In the case of t The state probability, and For state X t-1 and X t The nonlinear transformation of is the state after nonlinear transformation at the given current moment and radiotherapy conditions t In the case of The conditional probability of Under given radiotherapy conditions U t In the case of The conditional probability of Under given radiotherapy conditions U t In the case of The conditional probability of

[0109] S1234, Dynamically adjust model weights: Introduce a time-dependent weight adjustment mechanism α t , dynamically adapt to the changes in the tumor microenvironment during radiotherapy, expressed as:

[0110]

[0111] Among them, P′(X t |X t-1 ,U t ,α t ) is the state X at the previous moment t-1 , external variable U t and dynamic weight α t Under the condition that, at the current moment X t The state probability, α t is the time-dependent dynamic weight factor, P(α t ·X t-1 |α t ·X t ,U t ) is the value at the given current time X t , external variable U t and dynamic weight α t Under the condition that t-1 The conditional probability, P(α t ·X t |U t ) is given by the external variable U t and dynamic weight α t Under the condition that, at the current moment Xt The conditional probability of the state, P(α t ·X t-1 |U t ) is given by the external variable U t and dynamic weight α t Under the condition that t-1 Conditional probabilities of states;

[0112] S1235, update of posterior probability: the microenvironment changes before and after radiotherapy are continuously updated through posterior probability, expressed as:

[0113]

[0114] Among them, P(X t |D 1:t ) is the observation data D from time 1 to time t 1:t Under the condition, the state X at time t t The posterior probability, D 1:t is all the observed data from time 1 to time t, P(D t |X t ) is the state X at the given current moment t Under the condition of t The conditional probability, P(D t |D 1:t-1 ) is all the observed data D before a given time 1:t-1 Under the condition of t The conditional probability of the observed data;

[0115] Through the above content, it is possible to more accurately capture the complex cell-to-cell interactions in the tumor microenvironment and dynamically adapt to changes in radiotherapy conditions, so that the model can integrate biosensor and imaging data in real time, and gradually update the prediction of the state of the tumor microenvironment, thereby improving the personalization and accuracy of radiotherapy plans. Through the introduction of dynamic weights, the model can also flexibly adjust the impact of key factors at different time points, help optimize treatment strategies, and improve treatment effects and the accuracy of patient prognosis assessments.

[0116] The key factor identification and analysis in S13 include:

[0117] S131, Node centrality analysis of signaling networks: Identify key factors by calculating the centrality of each node (i.e., cytokine or other biomarker) in the signaling network, including:

[0118] Degree centrality: Calculate the degree of each node, that is, the number of connections with other nodes, expressed as:

[0119] C D(v) = deg(v);

[0120] Where deg(v) represents the degree of node v;

[0121] Betweenness centrality: Calculates the number of times each node is on the shortest path in the network, reflecting its importance as a bridge for signal transmission, expressed as:

[0122]

[0123] Among them, σ st is the total number of shortest paths from node s to node t, σ st (v) is the number of shortest paths passing through node v;

[0124] S132, Analysis of the effects of key factors on tumor cell survival and proliferation: Once the key factors are identified, a linear regression model is used to analyze the effects of key factors on tumor cell survival and proliferation before and after radiotherapy, expressed as:

[0125] Y=β0+β1X1+β2X2+…+β n X n +∈;

[0126] Among them, Y represents the survival or proliferation rate of tumor cells, X1, X2,…, X n Indicates the concentration or expression level of key factors, β1, β2, …, β n is the corresponding regression coefficient, indicating the effect of each factor on tumor cell survival and proliferation, and ∈ is the error term;

[0127] S133, Analysis of the influence of key factors on tumor cell migration: For the analysis of tumor cell migration, a multivariate regression model was used to analyze the relationship between key factors and tumor cell migration rate before and after radiotherapy, expressed as:

[0128] M=γ0+γ1X1+γ2X2+…+γ n X n +η;

[0129] Where M represents the migration rate of tumor cells, X1, X2,…, X n represents the concentration or activation state of the key factor, γ1,γ2,…,γ n is the regression coefficient, which represents the effect of each factor on tumor cell migration, and η is the error term;

[0130] Through the above content, the core factors that affect the effect of radiotherapy in the tumor microenvironment can be accurately identified. Combined with the regression model, the specific effects of these factors on tumor cell survival, proliferation and migration before and after radiotherapy can be analyzed. The role of key factors can be quantified, providing a scientific basis for the optimization of radiotherapy plans. By capturing complex cell-to-cell interactions through quantitative analysis, it is helpful to improve the personalized and precise treatment effect of radiotherapy, and significantly improve the basis and effectiveness of treatment decisions.

[0131] Dynamic monitoring of circulating tumor cells (CTCs) in S2 includes:

[0132] S21, Circulating tumor cell number and phenotype analysis: Use liquid biopsy technology to detect the number of circulating tumor cells in the patient's blood in real time, and analyze the phenotype of circulating tumor cells by flow cytometry and immunofluorescence labeling to identify different types of circulating tumor cells (such as epithelial, mesenchymal, etc.). By regularly detecting the number and phenotypic changes of circulating tumor cells, evaluate the response of the tumor during radiotherapy and correlate it with the treatment effect;

[0133] S22, analysis of genetic characteristics of circulating tumor cells: single-cell genome sequencing technology is used to analyze the genetic characteristics of circulating tumor cells, identify gene mutations or expression changes associated with radiotherapy resistance, and determine the gene mutations or adaptive changes of tumor cells during radiotherapy;

[0134] Through the above content, the response of tumors during radiotherapy can be tracked in real time, providing early evaluation of treatment effects, non-invasively obtaining tumor progression information, identifying potential drug-resistant gene mutations and cell adaptive changes, and providing a scientific basis for timely adjustment of radiotherapy plans. At the same time, CTC dynamic monitoring can provide accurate data support for the optimization of personalized treatment plans, thereby improving the effectiveness of treatment and patient prognosis.

[0135] Circulating tumor cell population and phenotypic analysis in S21 includes:

[0136] S211, Detection of circulating tumor cell count: Using liquid biopsy technology, blood samples from patients are collected in real time, circulating tumor cells are extracted, and the number of circulating tumor cells per unit of blood is calculated by statistical methods, expressed as:

[0137]

[0138] Among them, N CTC Indicates the number of circulating tumor cells per unit of blood, CTC total represents the total number of circulating tumor cells detected, V blood represents the volume of blood extracted;

[0139] S212, Circulating tumor cell phenotype analysis and classification: Flow cytometry and immunofluorescence labeling were used to perform phenotypic analysis on the detected circulating tumor cells to identify different types of circulating tumor cells, including epithelial and mesenchymal cells. Marker proteins (such as EpCAM and vimentin) were used to distinguish the types of circulating tumor cells, and support vector machines (SVM) were used to classify circulating tumor cells, expressed as:

[0140]

[0141] Where y is the classification result, which is used to determine whether the CTC is epithelial (y = 1) or mesenchymal (y = -1), K(x i ,x) is the kernel function used to compare the input feature x and the sample feature x i The similarity between i and b are the parameters of the support vector machine, and n is the total number of support vectors;

[0142] S213, Treatment response evaluation: The response of the tumor during radiotherapy was evaluated by regularly detecting the number and phenotypic changes of circulating tumor cells. According to the trend of changes in the number of circulating tumor cells and the dynamic changes of different circulating tumor cell types, the linear regression model was used to evaluate the therapeutic effect of radiotherapy, which was expressed as:

[0143] E=θ0+θ1N CTC +θ2T CTC ;

[0144] Among them, E represents the therapeutic effect of radiotherapy, N CTC Indicates the number of CTCs, T CTC represents the ratio of different CTC types (such as the ratio of epithelial type / stromal type), θ0, θ1, and θ2 are regression coefficients used to measure the impact of each variable (CTC quantity and type ratio) on the treatment effect E;

[0145] Through the above content, different types of CTCs, such as epithelial and mesenchymal types, can be accurately identified, revealing the response of tumors during radiotherapy. By regularly monitoring the number and phenotypic changes of CTCs, the treatment effect can be evaluated in a timely manner, providing a scientific basis for the personalized adjustment of radiotherapy plans, thereby improving the accuracy and effectiveness of treatment.

[0146] Analysis of circulating tumor cell gene signatures in S22 includes:

[0147] S221, single-cell genome sequencing: single-cell isolation technology is used to separate circulating tumor cells (CTCs) at the single-cell level. Single-cell genome sequencing technology is used to comprehensively analyze the genetic characteristics of circulating tumor cells (CTCs) and obtain gene mutations, copy number changes and gene expression profiles;

[0148] S222, Gene mutation or expression identification: Use the stochastic gradient descent regression (SGD) model to detect gene mutations or expression changes. Stochastic gradient descent regression is used to minimize the loss function to find the optimal regression coefficient, expressed as:

[0149]

[0150] in, represents the estimated model parameters, y i is the actual gene expression or mutation value, x i is the input feature (gene expression value) in the sequencing data, θ is the regression coefficient of the model, which represents the impact of each gene mutation or expression change on the output, and n is the number of samples, which represents the number of samples of gene mutation or expression data involved in the regression analysis;

[0151] S223, Radiotherapy resistance assessment: Based on the identified gene mutations or expression changes, a logistic regression model is used to predict the association between gene mutations and radiotherapy resistance, to determine whether tumor cells have developed resistance or adaptive changes during radiotherapy, expressed as:

[0152]

[0153] Where P(N|G) is the given gene mutation G1, G2, …, G n After that, the probability of tumor cells developing drug resistance, G1, G2, …, G n represents the mutation or expression change of the gene, λ0 is the constant term of the model, that is, the baseline value when all gene mutations are 0, λ1,λ2,…,λ n Indicates the impact of each gene mutation or expression change on the drug resistance of tumor cells;

[0154] Through the above content, it is possible to effectively analyze the genetic mutations and adaptive changes of tumor cells during radiotherapy, evaluate the risk of drug resistance in real time, provide accurate data support at the genetic level, and help dynamically adjust personalized radiotherapy plans, thereby improving treatment outcomes and preventing the development of tumor cell resistance.

[0155] Adaptive radiotherapy strategy adjustments in S3 include:

[0156] S31, adjust the radiotherapy dose according to the activity of immune cells: when the activation of immune cells is enhanced, the radiotherapy dose is reduced to avoid excessive damage to the immune system; when the cytokine concentration indicates that the growth-promoting signal intensity in the tumor microenvironment has reached the intensity threshold, the radiotherapy dose is increased to improve the damage effect of tumor cells;

[0157] The intensity threshold is set by analyzing the effect of cytokine concentration in the tumor microenvironment on tumor cell proliferation and immune cell activity. The experiment will test different concentrations of cytokines to observe the growth rate and immune response of tumor cells at different concentrations. Through statistical analysis, an inflection point value is selected as the intensity threshold. That is, when the growth-promoting signal intensity exceeds this value, the proliferation of tumor cells accelerates and the immune system cannot effectively inhibit its growth, which is expressed as:

[0158]

[0159] Among them, T intensity is the intensity threshold, R tumor is the proliferation rate of tumor cells, C factor is the cytokine concentration, is the rate of change of tumor cell proliferation rate to cytokine concentration;

[0160] S32, adjust the irradiation time according to the monitoring results of circulating tumor cells: when the number of circulating tumor cells decreases and the phenotype does not change within the predetermined range, maintain the irradiation time; when the number or phenotype of circulating tumor cells changes beyond the predetermined range (indicating that the tumor cells are adaptable or resistant to radiotherapy), extend the irradiation time to increase the exposure time of tumor cells to radiotherapy and enhance the killing effect;

[0161] The changes in the predetermined range are set by analyzing the historical data of the number and phenotype of circulating tumor cells (CTCs) of healthy and tumor cells under different radiotherapy conditions. By analyzing the fluctuation range of CTCs at different stages of radiotherapy, combined with statistical normal distribution or other distribution models, reasonable upper and lower limits are set, expressed as:

[0162] Δ CTC =μ CTC ±z·σ CTC ;

[0163] Among them, Δ CTC is the threshold range of the predetermined change, μ CTC is the mean of the number of CTCs, z is the coefficient of the confidence interval (for example, the z value corresponding to a 95% confidence interval is 1.96), σ CTC is the standard deviation of the number of CTCs;

[0164] S33, adjust radiotherapy frequency according to tumor growth rate: when the signal transmission rate in the tumor microenvironment is monitored to drop below the rate threshold and the circulating tumor cell production rate is lower than the specified standard, reduce the radiotherapy frequency to reduce the cumulative damage to healthy tissues; when the growth rate of tumor cells accelerates and the number of circulating tumor cells exceeds the specified increase, increase the radiotherapy frequency to quickly inhibit tumor spread and migration;

[0165] The rate threshold is set by analyzing the change in the signal transmission rate in the tumor microenvironment. The signal transmission rate is experimentally observed at different stages of radiotherapy. The propagation speed of cytokine and immune cell signals between tumor cells, the attenuation curve of signal transmission in the tumor microenvironment is fitted using experimental data, and the rate threshold is set by the inflection point of the curve, which is expressed as:

[0166]

[0167] Among them, T rate is the rate threshold, is the rate of change of signal strength over time;

[0168] The prescribed standard is set based on the data difference between healthy people and tumor patients. By analyzing the CTC production rate of different individuals, a reasonable interval is found as the standard value of the CTC production rate. Exceeding this standard indicates tumor deterioration, which is expressed as:

[0169]

[0170] Among them, S CTC is the specified CTC generation rate standard, N CTC For a specific time interval t interval The number of CTCs generated within

[0171] The specified increase range is set by analyzing the experimental data of the CTC number growth rate, and a reasonable increase range is set. According to the regression analysis of historical data, the trend of CTC growth when the tumor worsens is found, and the increase range is set by its slope, which is expressed as:

[0172]

[0173] Among them, A increase is the increase in the specified number of CTCs, is the growth rate of the number of CTCs over time;

[0174] Through the above content, the dose, irradiation time and frequency of radiotherapy can be accurately adjusted to provide personalized treatment plans, and the radiotherapy strategy can be timely optimized according to the response of tumor cells to avoid damage to healthy tissues caused by excessive irradiation, while enhancing the killing effect on tumor cells. This dynamic adjustment mechanism can improve the treatment effect, reduce side effects, significantly improve the patient's prognosis, and improve the quality of life.

[0175] The feedback mechanisms and prognostic assessments in S4 include:

[0176] S41, Establish a feedback mechanism: Establish a real-time feedback mechanism by regularly monitoring the cytokine concentration, immune cell activity, and the number and phenotypic changes of circulating tumor cells (CTCs) in the tumor microenvironment.

[0177] S42, prognosis assessment: Based on the cytokine concentration, immune cell activity, and the number and phenotypic changes of circulating tumor cells (CTCs) monitored by the real-time feedback mechanism, the patient's prognosis is predicted by a multivariate regression model, expressed as:

[0178] E′=α0+α1Δ CTC +α2I immune +α3C factor +∈;

[0179] Among them, E′ is the evaluation value of the treatment effect, Δ CTC The number and phenotype of circulating tumor cells. immune is the immune cell activity, C factor is the cytokine concentration, α0, α1, α2, α3: regression coefficients, used to measure the impact of each variable on the treatment effect, ∈ is the error term;

[0180] S43, treatment plan optimization: Based on the results of the prognostic evaluation, the treatment plan is dynamically adjusted using a feedback mechanism. If the evaluation value is lower than the response threshold, it indicates that the tumor responds poorly to the current radiotherapy regimen. The treatment plan is optimized by increasing the radiotherapy dose, extending the irradiation time, or adjusting the radiotherapy frequency to improve the efficacy.

[0181] The response threshold is set by statistically analyzing the treatment data of a large number of patients, combining the relationship between the patient's biomarkers (such as CTC number, immune cell activity, cytokine concentration, etc.) and the radiotherapy effect, to determine whether the tumor has an effective response to the current treatment plan, including:

[0182] Data collection and analysis: Collect treatment data of multiple patients, including the number of circulating tumor cells (CTCs), immune cell activity, cytokine concentrations, and treatment effects of patients (such as tumor shrinkage rate or survival rate, etc.);

[0183] Model building: Use a multivariate regression model to analyze the relationship between biomarkers and treatment effects, fit the main factors affecting the response, and obtain the optimal response value range of each biomarker based on the model;

[0184] Setting of response threshold: The value of the key biomarker fitted by the model is set as the response threshold. The response threshold usually depends on the individual situation of the patient and is based on the change rate of the biomarker or the quantitative comprehensive score, expressed as:

[0185] T response =w1ΔCTC +w2I immune +w3C factor ;

[0186] Among them, T response is the reaction threshold, Δ CTC is the change rate of circulating tumor cells (CTC), I immune is the immune cell activity, C factor is the cytokine concentration, w1, w2, and w3 are the coefficients of the regression model, indicating the weight of each variable on the response;

[0187] Through the above content, it is possible to dynamically track the patient's response to treatment, and based on the prognostic evaluation of the multivariate regression model, the impact of biomarkers on the treatment effect is quantitatively analyzed, thereby providing accurate efficacy prediction. The advantage of this mechanism is that it can timely identify changes in treatment effects and optimize treatment plans in a data-driven manner, thereby improving efficacy while reducing damage to healthy tissues, significantly improving patients' treatment prognosis and quality of life.

[0188] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0189] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for formulating a tumor microenvironment-responsive radiotherapy strategy, characterized in that: The following steps are involved: S1, Dynamic interaction analysis of tumor microenvironment: Real-time monitoring and evaluation of signal transduction and interaction between cells in the tumor microenvironment, identification of key factors affecting the effect of radiotherapy, including the interaction between cytokines, immune cells and tumor-associated fibroblasts, including: S11, signal transduction network construction: by collecting the expression data of relevant cytokines in the tumor microenvironment, constructing the intercellular signal transduction network, clarifying the interaction between different cell types, and revealing the path and intensity of signal transduction; S12, Dynamic Monitoring Implementation: Using biosensors and imaging techniques to track changes in cell-cell interactions in the tumor microenvironment, including the activation state of immune cells and the response of tumor-associated fibroblasts; S13, Identification and analysis of key factors: Identify key factors in the signal transduction network and analyze their effects on tumor cell survival, proliferation and migration before and after radiotherapy; S2, Dynamic monitoring of circulating tumor cells: By analyzing the number, phenotype and gene characteristics of circulating tumor cells, their changes during radiotherapy are evaluated; S3, Adaptive radiotherapy strategy adjustment: Based on the results of dynamic interaction analysis of the tumor microenvironment and circulating tumor cell monitoring, the radiotherapy plan, including dose, irradiation time and frequency, is adjusted in real time; S4, Feedback mechanism and prognosis assessment: Establish a feedback mechanism to regularly evaluate the treatment effect by monitoring changes in the tumor microenvironment and circulating tumor cells, and optimize the treatment plan based on the evaluation results.

2. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 1, characterized in that: The signal transmission network construction in S11 includes: S111, data collection and preprocessing: collect the expression data of cytokines in the tumor microenvironment, including concentration, time series and related cell types, and standardize the expression data; S112, correlation analysis: Pearson correlation coefficient was used to calculate the correlation between cytokines to identify potential signal transduction relationships; S113, network construction: based on the correlation analysis results, construct an intercellular signaling network, where nodes represent different cytokines, edges represent the interaction between them, and edge weights are determined according to the strength of the correlation; S114, Path and Strength Analysis: Apply Dijkstra algorithm to analyze the shortest path and signal strength in the network.

3. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 2, characterized in that: The dynamic monitoring implementation in S12 includes: S121, Biosensor Data Collection: Use biosensors to monitor key biological signals in the tumor microenvironment in real time, including cytokine concentrations, pH, oxygen levels, and collect data on the activation status of immune cells and the response of tumor-associated fibroblasts; S122, Application of imaging technology: Visualize the cell-cell interactions in the tumor microenvironment, including the migration and aggregation of immune cells and the physical changes of tumor-associated fibroblasts, through dynamic imaging technology (multiphoton microscopy, magnetic resonance imaging), and generate a series of time-series image data; S123, Data Analysis: Based on the collected biosensor data and generated time series image data, the Bayesian dynamic network model was applied to analyze the changes in cell-cell interactions in the tumor microenvironment at different times, and to construct the dynamic relationship of cell-cell interactions to capture the interaction process between immune cells and tumor-associated fibroblasts at different time points, and to predict the dynamic changes before and after radiotherapy.

4. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 3, characterized in that: The Bayesian dynamic network model in S123 includes: S1231, introduction of time dependency: In order to deal with the time-dependent characteristics of the tumor microenvironment, time-dependent parameters are added to describe the interactive changes at different moments; S1232, add external variable correction: In order to adapt to the dynamic changes of the microenvironment before and after radiotherapy, introduce external control variables , represents the change of radiotherapy conditions; S1233, introduction of nonlinear interaction terms: considering that the interaction between cells in the tumor microenvironment is nonlinear, nonlinear terms are added and approximated by kernel functions; S1234, Dynamically adjust model weights: Introduce a time-dependent weight adjustment mechanism , dynamically adapt to changes in the tumor microenvironment during radiotherapy; S1235, updating of posterior probability: the microenvironment changes before and after radiotherapy are continuously updated through posterior probability.

5. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 4, characterized in that: The identification and analysis of key factors in S13 include: S131, Node centrality analysis of signal transmission network: Identify key factors by calculating the centrality of each node in the signal transmission network, including: Degree centrality: calculates the degree of each node, that is, the number of connections with other nodes; Betweenness centrality: Calculates the number of times each node is on the shortest path in the network; S132, Analysis of the effects of key factors on tumor cell survival and proliferation: Once the key factors were identified, a linear regression model was used to analyze the effects of the key factors on tumor cell survival and proliferation before and after radiotherapy; S133, Analysis of the impact of key factors on tumor cell migration: For the analysis of tumor cell migration, a multivariate regression model was used to analyze the relationship between key factors and tumor cell migration rate before and after radiotherapy.

6. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 1, characterized in that: The dynamic monitoring of circulating tumor cells in S2 includes: S21, Circulating tumor cell number and phenotype analysis: Use liquid biopsy technology to detect the number of circulating tumor cells in the patient's blood in real time, and analyze the phenotype of circulating tumor cells by flow cytometry and immunofluorescence labeling to identify different types of circulating tumor cells. By regularly detecting the number and phenotypic changes of circulating tumor cells, the response of the tumor during radiotherapy is evaluated and associated with the treatment effect; S22, Analysis of genetic characteristics of circulating tumor cells: Single-cell genome sequencing technology is used to analyze the genetic characteristics of circulating tumor cells, identify gene mutations or expression changes associated with radiotherapy resistance, and determine the gene mutations or adaptive changes produced by tumor cells during radiotherapy.

7. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 6, characterized in that: The analysis of circulating tumor cell numbers and phenotypes in S21 includes: S211, Detection of circulating tumor cell count: Using liquid biopsy technology, blood samples from patients are collected in real time, circulating tumor cells are extracted, and the number of circulating tumor cells per unit of blood is calculated by statistical methods; S212, Circulating Tumor Cell Phenotyping and Classification: Flow cytometry and immunofluorescence labeling were used to perform phenotypic analysis on the detected circulating tumor cells to identify different types of circulating tumor cells, including epithelial and mesenchymal cells. Marker proteins were used to distinguish the types of circulating tumor cells, and support vector machines were used to classify circulating tumor cells. S213, Treatment response evaluation: The response of the tumor to radiotherapy was evaluated by regularly detecting the number and phenotypic changes of circulating tumor cells. The therapeutic effect of radiotherapy was evaluated using a linear regression model based on the trend of changes in the number of circulating tumor cells and the dynamic changes of different circulating tumor cell types.

8. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 7, characterized in that: The analysis of circulating tumor cell gene characteristics in S22 includes: S221, single-cell genome sequencing: single-cell isolation technology is used to separate circulating tumor cells at the single-cell level. Single-cell genome sequencing technology is used to comprehensively analyze the genetic characteristics of circulating tumor cells and obtain gene mutations, copy number changes and gene expression profiles; S222, Gene mutation or expression identification: Use stochastic gradient descent regression models to detect gene mutations or expression changes; S223, Radiotherapy resistance assessment: By identifying gene mutations or expression changes, a logistic regression model is used to predict the association between gene mutations and radiotherapy resistance, to determine whether tumor cells have developed resistance or adaptive changes during radiotherapy.

9. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 1, characterized in that: The adaptive radiotherapy strategy adjustment in S3 includes: S31, adjust the radiation dose according to immune cell activity: when immune cell activation increases, the radiation dose is reduced, and when cytokine concentrations indicate that the intensity of growth-promoting signals in the tumor microenvironment reaches a threshold intensity, the radiation dose is increased; S32, adjusting the irradiation time according to the monitoring results of circulating tumor cells: when the number of circulating tumor cells decreases and the phenotype does not change within a predetermined range, maintaining the irradiation time; when the number or phenotype of circulating tumor cells changes beyond a predetermined range, extending the irradiation time; S33, adjust the frequency of radiotherapy according to the growth rate of the tumor: when the signal transmission rate in the tumor microenvironment is monitored to drop below the rate threshold and the production rate of circulating tumor cells is lower than the specified standard, reduce the frequency of radiotherapy; when the growth rate of tumor cells accelerates and the number of circulating tumor cells exceeds the specified increase, increase the frequency of radiotherapy.

10. The method for formulating a tumor microenvironment-responsive radiotherapy strategy according to claim 1, characterized in that: The feedback mechanism and prognostic assessment in S4 include: S41, Establish feedback mechanism: Establish real-time feedback mechanism by regularly monitoring cytokine concentrations, immune cell activity, and the number and phenotypic changes of circulating tumor cells in the tumor microenvironment. S42, prognostic assessment: based on the real-time feedback mechanism monitoring of cytokine concentrations, immune cell activity, and the number and phenotypic changes of circulating tumor cells, the patient's prognosis is predicted by a multivariate regression model; S43, treatment plan optimization: Based on the results of the prognostic evaluation, the treatment plan is dynamically adjusted using a feedback mechanism. If the evaluation value is lower than the response threshold, the treatment plan is optimized by increasing the radiotherapy dose, extending the irradiation time, or adjusting the radiotherapy frequency.

Images