Gastric cancer postoperative MRD dynamic monitoring system based on multi-biomarker fusion

Abstract

The invention relates to the technical field of medical information management, and particularly discloses a stomach cancer postoperative MRD dynamic monitoring system based on multi-biomarker fusion, which is used for solving the problem that in the prior art, CT and MRI equipment cannot dynamically adjust parameters according to real-time recurrence risk of a stomach cancer postoperative patient, so that the stomach cancer postoperative MRD dynamic monitoring system is poor in reliability. The system comprises a biomarker data acquisition module and a recurrence risk analysis module, and further comprises a CT equipment parameter adjustment module, an MR I equipment parameter adjustment module, a feedback control module and an examination means optimization module. Through fusion of multiple biomarkers, dynamic monitoring of gastric cancer postoperative MRD is realized, CT and MRI parameters are adaptively adjusted based on the recurrence risk of a patient, imaging precision is improved, equipment operation is optimized, radiation and imaging time are reduced, and precise CT and MRI imaging equipment parameter management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information management, and more specifically, to a dynamic monitoring system for MRD after gastric cancer surgery based on multi-biomarker fusion. Background Art

[0002] Gastric cancer is a highly malignant digestive tract tumor. Although surgical resection is the main treatment, there is still a high risk of recurrence after surgery. Minimal Residual Lesions MRD (Magnetic Resonance Disease) can cause gastric cancer recurrence or metastasis. Therefore, dynamic monitoring of postoperative MRD is crucial for timely detection of recurrence risk. At present, MRD monitoring mainly relies on traditional methods such as imaging examination and biomarker monitoring, but these methods have limitations in sensitivity, specificity and real-time dynamic monitoring. CT and MRI equipment play a vital role in monitoring the risk of recurrence in postoperative patients, and the working parameters of these imaging devices (such as scanning frequency, image resolution, etc.) are set to fixed values. Although this fixed parameter setting is suitable for most routine examinations, it is insufficient in monitoring high-risk recurrence of MRD after gastric cancer surgery, especially in scenarios requiring high-precision or frequent dynamic monitoring. It cannot be dynamically adjusted according to the patient's real-time recurrence risk, which will lead to insufficient monitoring of high-risk patients. The equipment parameter adjustment lacks close integration with the patient's specific biological data and recurrence risk prediction, and does not have personalized monitoring parameter adjustment. The existing equipment does not have an efficient feedback control mechanism and cannot automatically adjust parameters according to real-time monitoring results to keep the imaging equipment in the best working state. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides a system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion. By fusing multiple biomarkers, dynamic monitoring of MRD after gastric cancer surgery is realized, CT and MRI parameters are adaptively adjusted based on the patient's recurrence risk, imaging accuracy is improved, equipment operation is optimized, radiation and imaging time are reduced, and accurate CT and MRI imaging equipment parameter management is realized. After gastric cancer surgery, there may be micro-residual lesions (MRD) in the patient's body, and these residual lesions may cause cancer recurrence. The imaging parameters of the CT device, such as scanning frequency and radiation dose, need to be dynamically adjusted according to the patient's recurrence risk. When the risk of MRD recurrence is high, increasing the scanning frequency can capture more subtle changes in lesions, thereby improving the accuracy of diagnosis. At the same time, increasing the radiation dose can enhance the clarity of the image, allowing doctors to more accurately judge the condition. However, in order to avoid unnecessary radiation exposure, when the risk of recurrence is low, reducing the scanning frequency and radiation dose is a suitable choice to reduce the radiation dose burden of the patient. The key imaging parameter of the MRI device is resolution. When the risk of MRD recurrence is high, higher resolution can provide more detailed tissue imaging and help find subtle lesions. By dynamically adjusting the resolution, the resolution can be improved when the risk is high and the level of detail of the image can be increased. When the risk of recurrence is low, the resolution can be appropriately reduced, the imaging speed needs to be accelerated, unnecessary scanning time needs to be reduced, and the imaging efficiency needs to be optimized without affecting the accuracy of disease monitoring. In order to improve the accuracy and timeliness of MRD monitoring, the imaging parameters of CT and MRI equipment need to be dynamically adjusted according to the patient's risk of recurrence. Traditional equipment parameter settings are usually fixed and cannot flexibly respond to changes in the patient's condition. Through the fusion analysis of multi-biomarker (such as genome, transcriptome, proteome, metabolome) data, the system can calculate the recurrence risk value of MRD in real time. Based on this risk value, the scanning frequency and radiation dose of the CT device, as well as the resolution of the MRI device, can be personalized to improve the accuracy of monitoring. Specifically, the CT device calculates the optimal scanning frequency and radiation dose through random matrix theory to ensure that the scanning frequency is increased when the risk of recurrence is high to capture more image details. For MRI equipment, the fractional calculus method can dynamically adjust the resolution to adapt to changes in historical data, so that the device can improve the resolution when high-precision imaging is required. In addition, the feedback control module optimizes the adjustment path of the equipment by monitoring the deviation between the equipment parameters and the expected parameters, ensuring that the CT and MRI equipment can provide the best imaging effect in actual operation. This dynamic adjustment mechanism driven by biomarker data not only improves the effectiveness of MRD monitoring after gastric cancer surgery, but also reduces unnecessary radiation exposure or imaging time, allowing patients to receive more accurate and personalized management of CT and MRI imaging equipment parameters.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A postoperative MRD dynamic monitoring system for gastric cancer based on multi-biomarker fusion includes a biomarker data acquisition module and a recurrence risk analysis module, and also includes a CT device parameter adjustment module, an MRI device parameter adjustment module, a feedback control module and an inspection means optimization module. The biomarker data acquisition module is connected to the recurrence risk analysis module, the recurrence risk analysis module is connected to the CT device parameter adjustment module and the MRI device parameter adjustment module, the recurrence risk analysis module, the CT device parameter adjustment module and the MRI device parameter adjustment module are connected to the feedback control module, the CT device parameter adjustment module and the MRI device parameter adjustment module are connected to the inspection means optimization module, the recurrence risk analysis module fuses and analyzes the genome data, transcriptome data, proteome data and metabolome data of postoperative gastric cancer patients through a preset recurrence risk assessment formula to obtain the risk curvature data of MRD, the CT device parameter adjustment module uses the risk curvature data of MRD combined with the current state of the CT device and random disturbance to generate a random matrix, and obtains the maximum eigenvalue of the matrix to obtain the optimal CT scanning frequency and CT radiation dose adjustment amount, and the MRI device parameter adjustment module dynamically adjusts the resolution of the MRI device through fractional calculus combined with the risk curvature data of MRD and historical data.

[0006] As a further scheme of the present invention, the biomarker data acquisition module obtains the patient's genomic data, transcriptomic data, proteomic data and metabolomic data after gastric cancer surgery from the patient's biochemical samples. The genomic data, transcriptomic data, proteomic data and metabolomic data are obtained through ctDNA liquid biopsy, RNA sequencing, mass spectrometry analysis and metabolomics analysis, respectively.

[0007] As a further solution of the present invention, the recurrence risk assessment formula preset in the recurrence risk analysis module fuses and analyzes the multiple biomarker data collected by the biomarker data acquisition module through the Riemann geometry curvature formula to obtain the patient's MRD real-time recurrence risk analysis value, which is used as a basis for dynamic adjustment of CT and MRI equipment. The preset recurrence risk assessment formula is:

[0008]

[0009] Where: t is the current time, R(t) is the MRD recurrence risk value calculated based on the biomarker data at the current time, i and j are the dimension indexes of the biomarker, X is the set of biomarker data, and g ij (X) is the metric relationship between biomarkers in high-dimensional space, X i is the data of the i-th biomarker, X j is the data of the jth biomarker.

[0010] As a further solution of the present invention, in the CT equipment parameter adjustment module, the scanning frequency and radiation dose of the CT equipment are dynamically adjusted by the random matrix and the MRD recurrence risk value to improve the monitoring frequency and imaging effect. The parameter adjustment formula of the CT equipment is:

[0011] f s (t),D(t)=λ max (A(t))

[0012] Where: f s (t) is the scanning frequency of the CT device at the current moment, D(t) is the CT radiation dose at the current moment, A(t) is the state matrix of the CT device, including the historical scanning frequency, radiation dose and R(t) of the CT device, λ max (A(t)) is the maximum eigenvalue of the matrix A(t).

[0013] As a further solution of the present invention, in the MRI device parameter adjustment module, the resolution of the MRI device is dynamically adjusted by applying a fractional calculus formula according to the MRI recurrence risk value and the historical operation data of the MRI device. The parameter adjustment formula of the MRI device is:

[0014]

[0015] Where: r MRI (t) is the resolution of MRI at the current moment, r0 is the initial resolution of the MRI device, and k is the adjustment gain coefficient, which is set according to actual needs. is a fractional calculus operator, which represents the historical adjustment effect of the device. α is the order of the fractional derivative, which is set according to actual needs and is used to adjust the degree of dependence of the resolution of the current MRI device on historical information.

[0016] As a further solution of the present invention, in the feedback control module, the device parameters and monitoring results from the CT device parameter adjustment module and the MRI device parameter adjustment module are received, the error between the actual device parameters and the expected parameters is obtained, the adjustment path of the CT and MRI devices is optimized through the preset feedback control equation, and the optimization result is fed back to the CT device parameter adjustment module and the MRI device parameter adjustment module to form a closed-loop feedback control. The preset feedback control equation is:

[0017]

[0018] Where: S is the action function, which represents the accumulated action during the equipment adjustment process, p s The scanning frequency f of the CT scanning equipment s The conjugate momentum of (t), m sis the inertia coefficient of the CT scanning equipment frequency change, p r is the MRI equipment resolution r MRI The conjugate momentum of (t), m r is the inertia coefficient of the MRI device resolution change, V(f s (t),r MRI (t)) is f s (t), r MRI (t) Contribution terms of CT imaging and MRI imaging status to postoperative MRD in gastric cancer patients.

[0019] As a further solution of the present invention, in the feedback control equation of the feedback control module,

[0020] As a further solution of the present invention, the inspection means optimization module selects the best CT and MRI equipment operation modes based on the risk of MRD recurrence after gastric cancer surgery and the feedback control results, and applies the results to the CT equipment parameter adjustment module and the MRI equipment parameter adjustment module. The inspection mode selection formula is:

[0021]

[0022] Where: M is the currently selected examination method, which is a combination of different scanning frequencies and radiation doses for CT equipment and a combination of different resolutions and scanning times for MRI. x is the equipment working mode index, and m is x is the xth mode in the set of optional working modes for CT or MRI equipment, ω x Mode m x The weight coefficient for the current MRD recurrence risk R(t), f m (R) is the adaptive function for the current MRD recurrence risk value R(t), which is set according to actual needs.

[0023] Compared with the prior art, the technical effects of the present invention are as follows: the present invention can dynamically adjust the scanning frequency and radiation dose of CT and the resolution of MRI according to the individual recurrence risk of the patient. By introducing random matrix theory and fractional-order calculus models, the adaptive adjustment capability of imaging parameters is greatly improved, ensuring higher imaging accuracy at high recurrence risks, while optimizing equipment operation under low recurrence risks, reducing the patient's radiation dose and imaging time. The feedback control module in the system further optimizes the adjustment path of the equipment through closed-loop control, ensuring that the equipment is always in the best working state at different stages of the disease. This personalized imaging solution significantly improves the accuracy, efficiency and safety of postoperative monitoring of gastric cancer, and provides patients with more accurate and effective CT and MRI imaging equipment parameter management. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] like Figure 1 As shown, the present invention proposes a postoperative MRD dynamic monitoring system for gastric cancer based on multi-biomarker fusion, including a biomarker data acquisition module and a recurrence risk analysis module, and also includes a CT device parameter adjustment module, an MRI device parameter adjustment module, a feedback control module and an inspection means optimization module. The biomarker data acquisition module is connected to the recurrence risk analysis module, the recurrence risk analysis module is connected to the CT device parameter adjustment module and the MRI device parameter adjustment module, the recurrence risk analysis module, the CT device parameter adjustment module, and the MRI device parameter adjustment module are connected to the feedback control module, and the CT device parameter adjustment module and the MRI device parameter adjustment module are connected to the inspection means optimization module. The recurrence risk analysis module fuses and analyzes the genomic data, transcriptomic data, proteomic data and metabolomic data of postoperative gastric cancer patients through a preset recurrence risk assessment formula to obtain the risk curvature data of MRD. The CT device parameter adjustment module uses the risk curvature data of MRD in combination with the current state of the CT device and random disturbances to generate a random matrix, and obtains the maximum eigenvalue of the matrix to obtain the optimal CT scanning frequency and CT radiation dose adjustment amount. The MRI device parameter adjustment module dynamically adjusts the resolution of the MRI device through fractional calculus in combination with the risk curvature data of MRD and historical data.

[0027] The present invention can dynamically adjust the scanning frequency and radiation dose of CT and the resolution of MRI according to the individual recurrence risk of the patient. By introducing random matrix theory and fractional-order calculus models, the adaptive adjustment capability of imaging parameters is greatly improved, ensuring higher imaging accuracy at high recurrence risk, while optimizing equipment operation at low recurrence risk, reducing the patient's radiation dose and imaging time. The feedback control module in the system further optimizes the adjustment path of the equipment through closed-loop control, ensuring that the equipment is always in the best working state at different stages of the disease. This personalized imaging solution significantly improves the accuracy, efficiency and safety of postoperative monitoring of gastric cancer, and provides patients with more accurate and effective CT and MRI imaging equipment parameter management.

[0028] It should be noted that the biomarker data acquisition module obtains the patient's genomic data, transcriptomic data, proteomic data and metabolomic data after gastric cancer surgery from the patient's biochemical samples. The genomic data, transcriptomic data, proteomic data and metabolomic data are obtained through ctDNA liquid biopsy, RNA sequencing, mass spectrometry analysis and metabolomics analysis, respectively.

[0029] The selection of genome, transcriptome, proteome and metabolome as biomarkers is to comprehensively capture the dynamic changes of minimal residual disease (MRD) in patients after gastric cancer surgery. Genomic data detects cancer-related gene mutations through ctDNA liquid biopsy to reveal the genetic characteristics of cancer; transcriptome data monitors changes in gene expression through RNA sequencing to reflect the active state of cancer cells; proteome data detects the expression of tumor-related proteins through mass spectrometry analysis to reveal the final product of cancer biological activities; metabolome data captures abnormal metabolism of cancer cells through metabolomics analysis. The fusion of these data can make up for the shortcomings of traditional imaging methods in sensitivity, specificity and real-time monitoring, provide real-time basis for personalized adjustment of CT and MRI equipment parameters, and improve the accuracy and effectiveness of monitoring.

[0030] It should be noted that the recurrence risk assessment formula preset in the recurrence risk analysis module fuses and analyzes the various biomarker data collected by the biomarker data acquisition module through the Riemann geometry curvature formula to obtain the patient's MRD real-time recurrence risk analysis value, which is used as the basis for dynamic adjustment of CT and MRI equipment. The preset recurrence risk assessment formula is:

[0031]

[0032] Where: t is the current time, R(t) is the MRD recurrence risk value calculated based on the biomarker data at the current time, i and j are the dimension indexes of the biomarker, X is the set of biomarker data, and g ij (X) is the metric relationship between biomarkers in high-dimensional space, X i is the data of the i-th biomarker, X j is the data of the jth biomarker.

[0033] By using the Riemannian geometry curvature formula to fuse multiple biomarker data, the recurrence risk analysis module can mathematically analyze the patient's genomic, transcriptomic, proteomic and metabolomic data and assess the patient's minimal residual disease (MRD) recurrence risk in real time. ij(X) established the complex geometric relationship of biomarkers in high-dimensional space, accurately reflecting the interaction and overall changes between them. In this way, the recurrence risk R(t) at the current moment can be dynamically and accurately calculated, which provides a basis for real-time adjustment of parameters for CT and MRI equipment, enabling the equipment to dynamically adjust the scanning frequency, radiation dose and resolution according to specific risks, solving the problem of lack of sensitivity, specificity and real-time performance in traditional imaging monitoring methods, and greatly improving the monitoring effect of patients with high recurrence risk.

[0034] In order to clearly illustrate the above technical solution, a specific example 1 is now provided for detailed description.

[0035] Example 1

[0036] Four types of biomarker data were collected from patients after gastric cancer surgery, namely genomic, transcriptomic, proteomic and metabolomic data. These data were used to calculate the patient's minimal residual disease (MRD) recurrence risk and dynamically adjust the imaging parameters of CT and MRI equipment.

[0037] Biomarker data collection

[0038] The following data were obtained from the patient's biochemical samples:

[0039] Genomic data: KRAS mutation detected in the gene, data X 1 =1 (indicates the presence of gene mutation, the numerical code is 1).

[0040] Transcriptome data: mRNA expression of cancer-related genes increased by 50%, data X 2 =1.5 (baseline is 1).

[0041] Proteomic data: The level of tumor-related proteins increased by 40%, data X 3 =1.4.

[0042] Metabolomics data: Lactate levels increased by 30%, data X 4 =1.3.

[0043] These data constitute the biomarker data set: X = {X 1 =1,X 2 =1.5,X 3 =1.4,X 4 =1.3}.

[0044] High-dimensional space representation

[0045] These biomarker data X i is mapped to a high-dimensional feature space, where each X iIt is a dimension of a high-dimensional space. For example, dimension 1 represents the genome, dimension 2 represents the transcriptome, dimension 3 represents the proteome, and dimension 4 represents the metabolome.

[0046] Use of Riemannian geometry curvature formula

[0047] The Riemann geometry curvature formula is used to calculate the recurrence risk R(t), which is:

[0048]

[0049] Specific explanation: g ij (X): The metric tensor represents the geometric relationship between different landmarks. Assume that the metric tensor g ij The value of (X) is:

[0050]

[0051] This tensor represents the correlation between genomic data and transcriptomic, proteomic, and metabolomic data. For example, the correlation between genomic data and transcriptomic data is 0.2, while the correlation between genomic and proteomic data is lower, only 0.1.

[0052] Biomarker change rate

[0053] Biomarker X i Rate of change over time Assume the following:

[0054] Genomic data changes slowly.

[0055] Transcriptome data changes rapidly.

[0056] The protein group data showed moderate changes.

[0057] Metabolomics data changes rapidly.

[0058] Calculation of risk of recurrence

[0059] Substituting these data into the Riemann geometry curvature formula, the calculation steps for the recurrence risk are as follows:

[0060] First calculate

[0061]

[0062] Then, combined with the metric tensor g ij (X):

[0063]

[0064] Finally, calculate the sum of the integral corresponding to the trajectory γ to obtain the recurrence risk at the current moment:

[0065]

[0066] Therefore, the risk of MRD relapse at the current moment is 0.0714 times the linear proportion of time t.

[0067] Based on the calculated risk of MRD recurrence, CT and MRI equipment can dynamically adjust scanning frequency, radiation dose, and resolution.

[0068] It should be noted that in the CT equipment parameter adjustment module, the scanning frequency and radiation dose of the CT equipment are dynamically adjusted through the random matrix and the MRD recurrence risk value to improve the monitoring frequency and imaging effect. The parameter adjustment formula of the CT equipment is:

[0069] f s (t),D(t)=λ max (A(t))

[0070] Where: f s (t) is the scanning frequency of the CT device at the current moment, D(t) is the CT radiation dose at the current moment, A(t) is the state matrix of the CT device, including the historical scanning frequency, radiation dose and R(t) of the CT device, λ max (A(t)) is the maximum eigenvalue of the matrix A(t).

[0071] In order to clearly illustrate the specific analysis and calculation process of the above formula, Example 2 is calculated and analyzed in combination with actual set data.

[0072] Example 2

[0073] In the MRD recurrence risk monitoring of gastric cancer patients after surgery, the recurrence risk value R(t)=0.07 was obtained through the analysis of biomarker data. In order to optimize the imaging effect of the CT device, the scanning frequency and radiation dose of the CT device were dynamically adjusted using the random matrix and the recurrence risk value to improve the monitoring frequency and imaging quality. The specific steps include:

[0074] (1) Construction of CT equipment status matrix: The CT equipment has recorded the following historical parameters in the past few monitoring cycles:

[0075] Past scanning frequency: f s history =[2.5,3.0,2.8](unit: Hz)

[0076] Past radiation dose: D history =[4.0,4.2,4.1](unit: mSv)

[0077] Recurrence risk value at the current moment: R(t) = 0.07

[0078] Using these historical data and recurrence risk values, the state matrix A(t) of the CT device is constructed, which includes the influence of historical scanning frequency, radiation dose and current recurrence risk.

[0079] (2) Calculate the maximum eigenvalue of the state matrix

[0080] In order to dynamically adjust the scanning frequency and radiation dose of the CT device, it is necessary to calculate the maximum eigenvalue λ of the state matrix A(t) max (A(t)), first calculate the eigenvalues ​​of the matrix A(t).

[0081] λ(A(t))={5.92,0.05,-0.01}

[0082] Among them, the maximum eigenvalue λ max (A(t))=5.92.

[0083] (3) Dynamically adjust CT equipment parameters

[0084] According to the maximum eigenvalue λ max (A(t))=5.92, adjust the scanning frequency and radiation dose of the CT equipment:

[0085] f s (t) = f s base +λ max (A(t))×k1

[0086] D(t)=D base +λ max (A(t))×k2

[0087] The initial reference scanning frequency is f s base =2.5Hz, the initial radiation dose is D base =4.0mSv, adjustment coefficients k1=0.1, k2=0.05.

[0088] (4) Calculate new scanning frequency and radiation dose

[0089] The maximum eigenvalue λ max Substituting (A(t))=5.92 into the formula, we get the new scanning frequency and radiation dose:

[0090] New scanning frequency: f s (t) = 2.5 + 5.92 × 0.1 = 3.092 Hz

[0091] New radiation dose: D(t) = 4.0 + 5.92 × 0.05 = 4.296 mSv

[0092] Based on the recurrence risk value of 0.07 and historical scanning parameters, the scanning frequency of the CT device was dynamically adjusted from 2.5Hz to 3.092Hz, and the radiation dose was increased from 4.0mSv to 4.296mSv. This dynamic adjustment ensures that the CT device can provide a higher scanning frequency and clearer imaging effects when the current recurrence risk is high. Through the dynamic adjustment of the random matrix and recurrence risk value, the CT device can optimize the scanning parameters according to the specific situation of the patient, improve monitoring efficiency and imaging effects. When the risk of recurrence is high, the system will automatically increase the scanning frequency and radiation dose to ensure higher-precision image monitoring. This flexible dynamic adjustment mechanism greatly enhances the detection ability of tiny residual lesions compared to traditional CT devices with fixed parameters.

[0093] It should be noted that in the MRI equipment parameter adjustment module, the resolution of the MRI equipment is dynamically adjusted using the fractional calculus formula according to the MRI recurrence risk value and the historical operation data of the MRI equipment. The parameter adjustment formula of the MRI equipment is:

[0094]

[0095] Where: r MRI (t) is the resolution of MRI at the current moment, r0 is the initial resolution of the MRI device, and k is the adjustment gain coefficient, which is set according to actual needs. is a fractional calculus operator, which represents the historical adjustment effect of the device. α is the order of the fractional derivative, which is set according to actual needs and is used to adjust the degree of dependence of the resolution of the current MRI device on historical information.

[0096] In order to clearly illustrate the specific analysis and calculation process of the above formula, Example 3 is calculated and analyzed in combination with actual set data.

[0097] Example 3

[0098] Patients undergoing gastric cancer surgery receive MRI monitoring, and the risk of recurrence is analyzed through biomarker analysis to obtain R(t) = 0.08. In order to optimize the MRI imaging effect, this system dynamically adjusts the resolution r of the MRI device based on the patient's recurrence risk value and the historical operating data of the MRI device using the fractional calculus formula MRI (t), enabling MRI equipment to provide higher resolution at high risk of recurrence, thereby improving the accuracy of lesion detection. The specific steps include:

[0099] (1) Initial parameter setting

[0100] The initial resolution of the MRI device is r0 = 1.2 mm, and the gain factor is 0.05. The order of the fractional calculus α = 0.7 is used to balance the impact of the device history adjustment effect and the real-time recurrence risk.

[0101] (2) Historical operation data of the equipment

[0102] The resolution of MRI images in the past few years is as follows:

[0103] Historical resolution: r history =[1.1,1.3,1.25]

[0104] Time: t history =[t1, t2, t3], where t1, t2, t3 are the time points of historical imaging. In addition, the current recurrence risk value is 0.08.

[0105] (3) Fractional calculus calculation

[0106] Apply fractional calculus formula to dynamically adjust MRI resolution:

[0107]

[0108] Where: r MRI (t) is the resolution of MRI at the current moment, r0 is the initial resolution of the MRI device, and k is the adjustment gain coefficient, which is set according to actual needs. is a fractional calculus operator, which represents the historical adjustment effect of the device. α is the order of the fractional derivative, which is set according to actual needs and is used to adjust the degree of dependence of the resolution of the current MRI device on historical information.

[0109] (4) Specific calculation of fractional calculus

[0110] Use historical resolution history To perform fractional calculus calculations, first perform fractional calculus based on historical operation data:

[0111]

[0112] Among them, τ is the integral variable

[0113] When the recurrence risk at t1, t2, and t3 is very low, 0.08, the fractional integral is used to calculate

[0114] (5) Calculate the current resolution

[0115] Substituting the result of fractional calculus into the formula, we can get the resolution of the MRI device at the current moment:

[0116] r MRI(t) = r0 + k 0.06

[0117] Among them, the initial resolution is 1.2mm, the gain coefficient is 0.05, and the calculated r MRI (t) = 1.203mm. Through the above calculation, the resolution of the MRI device at the current moment is dynamically adjusted from the initial value of 1.2mm to 1.203mm. Due to the high current risk of recurrence, the fractional-order calculus combines the influence of historical data, and the system provides a slight resolution improvement, so that the device can better capture the imaging details of minimal residual lesions (MRD). In this embodiment, the fractional-order calculus formula combines the patient's risk of recurrence and the historical operating data of the equipment to achieve dynamic adjustment of MRI resolution. This adjustment mechanism can accurately improve the resolution at a high risk of recurrence while maintaining reliance on historical data, thereby achieving personalized imaging optimization. This method is more flexible and accurate than the traditional fixed-resolution MRI imaging method, and greatly improves the MRD monitoring effect of patients after gastric cancer surgery.

[0118] It should be noted that in the feedback control module, the device parameters and monitoring results from the CT device parameter adjustment module and the MRI device parameter adjustment module are received, the error between the actual device parameters and the expected parameters is obtained, the adjustment path of the CT and MRI devices is optimized through the preset feedback control equation, and the optimization result is fed back to the CT device parameter adjustment module and the MRI device parameter adjustment module to form a closed-loop feedback control. The preset feedback control equation is:

[0119]

[0120] Where: S is the action function, which represents the accumulated action during the equipment adjustment process, p s The scanning frequency f of the CT scanning equipment s The conjugate momentum of (t), m s is the inertia coefficient of the CT scanning equipment frequency change, p r is the MRI equipment resolution r MRI The conjugate momentum of (t), m r is the inertia coefficient of the MRI device resolution change, V(f s (t),r MRI (t)) is f s (t), r MRI (t) Contribution terms of CT imaging and MRI imaging status to postoperative MRD in gastric cancer patients.

[0121] It should be noted that in the feedback control equation of the feedback control module,

[0122] It should be noted that the examination method optimization module selects the best CT and MRI equipment operation modes based on the risk of MRD recurrence after gastric cancer surgery and the feedback control results, and applies the results to the CT equipment parameter adjustment module and the MRI equipment parameter adjustment module. The examination mode selection formula is:

[0123]

[0124] Where: M is the currently selected examination method, which is a combination of different scanning frequencies and radiation doses for CT equipment and a combination of different resolutions and scanning times for MRI. x is the equipment working mode index, and m is x is the xth mode in the set of optional working modes for CT or MRI equipment, ω x Mode m x The weight coefficient for the current MRD recurrence risk R(t), f m (R) is the adaptive function for the current MRD recurrence risk value R(t), which is set according to actual needs.

[0125] In order to clearly illustrate the specific analysis and calculation process of the above formula, Example 4 is calculated and analyzed in combination with actual set data.

[0126] Example 4

[0127] Patients undergoing gastric cancer surgery are undergoing dynamic MRD monitoring. The system uses multi-biomarker fusion analysis to determine the current recurrence risk R(t) = 0.09. In order to optimize the operating parameters of CT and MRI equipment, the system needs to optimize the equipment adjustment path through feedback control equations and select the best imaging mode in the inspection method optimization module. The specific steps include:

[0128] (1) Solution and analysis of feedback control module

[0129] First, the system receives the current operating parameters from the CT device and the MRI device:

[0130] The scanning frequency f of the CT device s (t) = 3.2 Hz, radiation dose D(t) = 4.5 mSv.

[0131] The resolution of MRI equipment MRI (t) = 1.25 mm.

[0132] The adjustment path of the equipment is optimized through the feedback control equation:

[0133]

[0134] 1) Solve for conjugate momentum

[0135] According to the definition in the feedback equation:

[0136] Conjugate Momentum of CT Equipment

[0137] Conjugate Momentum of MRI Devices

[0138] S is set as the action function, which reflects the relationship between the operating status of the equipment and the condition. The conjugate momentum is calculated by the gradient of the current equipment parameters:

[0139] p s =2.5 (based on the gradient of CT scanning frequency change), p r =1.8 (based on the gradient of MRI resolution change).

[0140] 2) Inertia coefficient of the equipment

[0141] The inertia coefficient of the equipment is m s 、m r They represent the changing inertia of CT scanning frequency and MRI resolution, respectively, reflecting the response speed of the system to changes in these parameters:

[0142] Set the CT equipment inertia coefficient m s =1.2, MRI equipment inertia coefficient m r =1.1.

[0143] 3) Calculation of imaging contribution

[0144] Imaging contribution V(f s (t),r MRI (t)) reflects the impact of the current operating status of CT and MRI equipment on imaging quality. According to the formula:

[0145]

[0146] Setting: k s =0.3, k r =0.4.

[0147] Computational imaging contribution: V(f s (t),r MRI (t)) = 0.3 × (3.2) 2 +0.4×(1.25) 2 =3.697.

[0148] 4) Solving feedback control equations

[0149] Now substitute the known conjugate momentum, inertia coefficient and imaging contribution into the feedback control equation:

[0150]

[0151] Therefore, the rate of change of the action quantity is -7.774, indicating that it is necessary to adjust the operating state of the equipment through feedback control to return the equipment parameters to the optimal state.

[0152] (2) Solution and analysis of inspection means optimization module

[0153] Based on the feedback control results, the system selects the best working mode of CT and MRI equipment in the inspection means optimization module. 1)

[0155]

[0156] Where: M is the currently selected examination method, which is a combination of different scanning frequencies and radiation doses for CT equipment and a combination of different resolutions and scanning times for MRI. x is the equipment working mode index, and m is x is the xth mode in the set of optional working modes for CT or MRI equipment, ω x Mode m x The weight coefficient for the current MRD recurrence risk R(t), f m (R) is the adaptive function for the current MRD recurrence risk value R(t), which is set according to actual needs.

[0157] Assume the system has the following working modes:

[0158] Mode set of CT equipment: low frequency mode (f s =2.5Hz), high frequency mode (f s =3.5Hz)

[0159] Mode collection of MRI equipment: low resolution mode (r MRI =1.1mm), high resolution mode (r MRI =1.3mm).

[0160] 2) The weight coefficient is determined by the historical performance of the device mode:

[0161] High frequency CT mode weight ω CT,high =0.7, high frequency MRI mode weight ω MRI,high =0.6, fitness function f m (R) reflects the performance of the device model under the current recurrence risk R(t) = 0.09:

[0162] f m (R) = 1.5 × R (t) corresponds to the CT high frequency mode, f m (R) = 1.2 × R(t) corresponds to the MRI high frequency mode.

[0163] 3) Best working mode selection

[0164] Calculate the evaluation value of each working mode:

[0165] CT high frequency mode: 0.7×1.5×0.09=0.0945;

[0166] MRI high-frequency mode: 0.6 × 1.2 × 0.09 = 0.0648;

[0167] Therefore, the high-frequency mode (f s = 3.5 Hz) and the high-resolution mode of the MRI device (r MRI =1.3mm) is the current best working mode.

[0168] According to the optimization results of the feedback control equation, the scanning frequency of the CT device and the resolution of the MRI device are adjusted. The system selects the high-frequency mode of CT and the high-resolution mode of MRI through the inspection means optimization module. This optimization ensures that under the current high risk of recurrence, the CT and MRI equipment can provide the best imaging effect and ensure accurate monitoring of the condition of patients after gastric cancer surgery. Example 4 shows how the system dynamically adjusts the operating parameters of CT and MRI equipment through the feedback control module and the inspection means optimization module, and improves the imaging accuracy by selecting the optimal mode. This closed-loop feedback control mechanism ensures that the equipment is always in the best operating state under different recurrence risk conditions.

[0169] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0170] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic monitoring system for MRD after gastric cancer surgery based on multi-biomarker fusion, comprising a biomarker data acquisition module and a recurrence risk analysis module, characterized in that: It also includes a CT equipment parameter adjustment module, an MRI equipment parameter adjustment module, a feedback control module and an inspection means optimization module. The biomarker data acquisition module is connected to the recurrence risk analysis module, the recurrence risk analysis module is connected to the CT equipment parameter adjustment module and the MRI equipment parameter adjustment module, the recurrence risk analysis module, the CT equipment parameter adjustment module, and the MRI equipment parameter adjustment module are connected to the feedback control module, the CT equipment parameter adjustment module and the MRI equipment parameter adjustment module are connected to the inspection means optimization module. The recurrence risk analysis module integrates and analyzes the genomic data, transcriptomic data, proteomic data and metabolomic data of gastric cancer postoperative patients through a preset recurrence risk assessment formula to obtain the risk curvature data of MRD. The CT equipment parameter adjustment module uses the risk curvature data of MRD in combination with the current state of the CT equipment and random disturbances to generate a random matrix, and obtains the maximum eigenvalue of the matrix to obtain the optimal CT scanning frequency and CT radiation dose adjustment amount. The MRI equipment parameter adjustment module dynamically adjusts the resolution of the MRI equipment through fractional calculus in combination with the risk curvature data of MRD and historical data.

2. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 1, characterized in that: The biomarker data acquisition module obtains the patient's genomic data, transcriptomic data, proteomic data and metabolomic data after gastric cancer surgery from the patient's biochemical samples. The genomic data, transcriptomic data, proteomic data and metabolomic data are obtained through ctDNA liquid biopsy, RNA sequencing, mass spectrometry analysis and metabolomics analysis, respectively.

3. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 2, characterized in that: The recurrence risk assessment formula preset in the recurrence risk analysis module fuses and analyzes the various biomarker data collected by the biomarker data acquisition module through the Riemann geometry curvature formula to obtain the patient's MRD real-time recurrence risk analysis value, which is used as the basis for dynamic adjustment of CT and MRI equipment. The preset recurrence risk assessment formula is: Where: t is the current time, R(t) is the MRD recurrence risk value calculated based on the biomarker data at the current time, i and j are the dimension indexes of the biomarker, X is the set of biomarker data, and g ij (X) is the metric relationship between biomarkers in high-dimensional space, X i is the data of the i-th biomarker, X j is the data of the jth biomarker.

4. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 3, characterized in that: In the CT equipment parameter adjustment module, the scanning frequency and radiation dose of the CT equipment are dynamically adjusted through the random matrix and the MRD recurrence risk value to improve the monitoring frequency and imaging effect. The parameter adjustment formula of the CT equipment is: f s (t),D(t)=λ max (A(t)) Where: f s (t) is the scanning frequency of the CT device at the current moment, D(t) is the CT radiation dose at the current moment, A(t) is the state matrix of the CT device, including the historical scanning frequency, radiation dose and R(t) of the CT device, λ max (A(t)) is the maximum eigenvalue of the matrix A(t).

5. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 3, characterized in that: In the MRI equipment parameter adjustment module, the resolution of the MRI equipment is dynamically adjusted using the fractional calculus formula according to the MRI recurrence risk value and the historical operation data of the MRI equipment. The parameter adjustment formula of the MRI equipment is: Where: r MRI (t) is the resolution of MRI at the current moment, r0 is the initial resolution of the MRI device, and k is the adjustment gain coefficient, which is set according to actual needs. is a fractional calculus operator, which represents the historical adjustment effect of the device. α is the order of the fractional derivative, which is set according to actual needs and is used to adjust the degree of dependence of the resolution of the current MRI device on historical information.

6. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 5, characterized in that: In the feedback control module, the device parameters and monitoring results from the CT device parameter adjustment module and the MRI device parameter adjustment module are received, the error between the actual device parameters and the expected parameters is obtained, the adjustment path of the CT and MRI devices is optimized through the preset feedback control equation, and the optimization result is fed back to the CT device parameter adjustment module and the MRI device parameter adjustment module to form a closed-loop feedback control. The preset feedback control equation is: Where: S is the action function, which represents the accumulated action during the equipment adjustment process, p s The scanning frequency f of the CT scanning equipment s The conjugate momentum of (t), m s is the inertia coefficient of the CT scanning equipment frequency change, p r is the MRI equipment resolution r MRI The conjugate momentum of (t), m r is the inertia coefficient of the MRI device resolution change, V(f s (t),r MRI (t)) is f s (t), r MRI (t) Contribution terms of CT imaging and MRI imaging status to postoperative MRD in gastric cancer patients.

7. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 6, characterized in that: In the feedback control equation of the feedback control module, 8. The system for dynamic monitoring of MRD after gastric cancer surgery based on multi-biomarker fusion according to claim 7, characterized in that: The examination method optimization module selects the best CT and MRI equipment operation modes based on the risk of MRD recurrence after gastric cancer surgery and the feedback control results, and applies the results to the CT equipment parameter adjustment module and the MRI equipment parameter adjustment module. The examination mode selection formula is: Where: M is the currently selected examination method, which is a combination of different scanning frequencies and radiation doses for CT equipment and a combination of different resolutions and scanning times for MRI. x is the equipment working mode index, and m is x is the xth mode in the set of optional working modes for CT or MRI equipment, ω x Mode m x The weight coefficient for the current MRD recurrence risk R(t), f m (R) is the adaptive function for the current MRD recurrence risk value R(t), which is set according to actual needs.

Images