Tumor dose monitoring method and system based on radiotherapy

Abstract

The invention discloses a tumor dose monitoring method and system based on radiotherapy, and relates to the technical field of medical care informatics. The tumor dose monitoring method and system based on radiotherapy comprises the following steps: S1, acquiring tumor dose data by using an implantable optical fiber dose detector, and performing data cleaning and normalization processing on the tumor dose data; s2, performing preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and constructing a three-dimensional convolutional neural network model to refine three-dimensional dose distribution; s3, analyzing deviation intensity according to a comparison result of the tumor dose evaluation value and the reference body surface dose, performing grading judgment on the deviation intensity, generating an adjustment suggestion, and forming a control flow for regulating closed-loop feedback; and S4, focusing the deep estimation points of the target region to count the deviation distribution characteristics, and generating structured correction data for subsequent reconstruction input and risk prompt generation. The problem that in-vivo tumor area three-dimensional dose distribution cannot be accurately reduced through body surface dose monitoring is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of healthcare informatics, and particularly to a tumor dose monitoring method and system based on radiotherapy. Background Art

[0002] With the development of radiotherapy technology towards high-dose, precise positioning, and multi-angle irradiation, the role of dose monitoring in ensuring treatment accuracy and safety has become increasingly prominent. In recent years, the research focus of tumor dose monitoring methods and systems has gradually shifted from plan execution consistency verification to real-time feedback and individualized dose control.

[0003] For example, the invention with the publication number: CN118588235A discloses a precise control system for radioactive drug dosage, including: a microfluidic drug reservoir, a high-precision micropump, a precision dosage control unit, a drug concentration monitoring module, a data analysis module, a dosage adjustment module, and a user interface: the microfluidic drug reservoir loads radioactive drugs, the high-precision micropump releases drugs according to a preset dosage, and the precision dosage control unit is connected to the microfluidic drug reservoir, the drug concentration monitoring module, and the dosage adjustment module.

[0004] For example, the invention with the publication number: CN119517302A discloses an intelligent medical management method and system based on radiotherapy for malignant tumors, including the following steps: obtaining holographic image data corresponding to the patient's clinical image data; inputting the holographic image data into a trained deep learning model to identify the malignant tumor target area and its attributes; calculating the dose of radioactive particles based on the malignant tumor target area and its attributes; generating a 3D printing instruction according to the malignant tumor target area; obtaining dose distribution monitoring data of radioactive particles in the treatment area; analyzing the uniformity of radioactive particles according to the dose distribution monitoring data; generating a treatment plan and a treatment risk assessment according to the malignant tumor target area, attributes, and the uniformity of radioactive particles.

[0005] The dose information obtained by these methods is limited to the body surface and cannot reflect the true energy deposition process of the ray in the complex tissue structure in the body. Especially when treating deep tumors, due to tissue density changes, scattering effects, and the uncertainty of the beam path, there may be a significant deviation between the body surface dose and the actual target area dose, resulting in a decrease in dose reconstruction accuracy.

[0006] Therefore, in view of the above problems, there is an urgent need for a tumor dose monitoring method and system based on radiotherapy. Summary of the Invention

[0007] Technical Problems to be Solved

[0008] In view of the deficiencies of the prior art, the present invention provides a method and system for monitoring tumor dose based on radiotherapy, which solves the problem that surface dose monitoring is difficult to accurately restore the three-dimensional dose distribution of the tumor area in the body.

[0009] Technical Solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for monitoring tumor dose based on radiotherapy, comprising the following steps: S1, using an implantable fiber optic dose detector to collect tumor dose data, and performing data cleaning and normalization processing on the tumor dose data; S2, performing preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and constructing a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; S3, analyzing the deviation intensity based on the comparison result between the tumor dose assessment value and the reference body surface dose, performing graded judgment on the deviation intensity and generating adjustment suggestions, forming a control process of closed-loop feedback; S4, focusing on the statistical deviation distribution characteristics of the deep estimation point of the target area, and generating structured correction data for subsequent reconstruction input and risk prompt generation.

[0011] Furthermore, the specific steps of collecting tumor dose data using an implantable fiber optic dose detector are as follows: an implantable fiber optic dose detector is used, which is deployed in the tumor target area and its periphery to sense radiation-induced light signals in real time and collect tumor dose data; the tumor dose data includes instantaneous radiation dose, detection point coordinates, beam source coordinates, estimated point coordinates, photon beam energy, tissue CT value and reference body surface dose; wherein, the instantaneous radiation dose of each detection point is obtained through photoelectric conversion, signal amplification and analog-to-digital conversion; the spatial position of the fiber optic probe is calibrated through preoperative CT scanning, the patient coordinate system is constructed, and the detection point coordinates, beam source coordinates and estimated point coordinates in the patient's body are obtained; the photon beam energy of the radiation used for treatment is obtained through the radiotherapy equipment control system; the tissue CT value of the tissue corresponding to the detection point is read from the patient's preoperative CT image; the tissue angle of the current beam relative to the patient coordinate system is read in real time by connecting to the control system of the radiotherapy accelerator; and the reference body surface dose is obtained through the TLD detector attached to the patient's body surface.

[0012] Furthermore, the specific steps for cleaning and normalizing the tumor dose data are as follows: use the sliding window method combined with the three-fold standard difference constant detection algorithm to eliminate tumor dose data that obviously deviates from the normal range; use millisecond-level time alignment and linear interpolation methods to fill in the instantaneous missing tumor dose data; use a rigid registration algorithm to align the detector space coordinates with the patient's preoperative CT image coordinates to ensure three-dimensional spatial consistency; use the Kalman filter algorithm to denoise the continuously collected instantaneous radiation dose; use unit conversion and maximum and minimum normalization algorithms to normalize the tumor dose data and unify the data scale.

[0013] Further, the specific steps for preliminary dose estimation and physical modeling compensation of the preprocessed tumor dose data are as follows: Take N detection points, calculate the sum of the squares of the coordinate differences in the transverse direction, the longitudinal direction, and the vertical direction between the estimation point and the i-th detection point, add a very small term, and finally take the square root of the result to obtain the spatial distance between the i-th detection point and the estimation point in the patient coordinate system; Multiply this spatial distance by the exponential decay factor, take the negative value as the exponent, and then calculate the value of this power function with the natural constant as the base to obtain the weight of the current detection point; Multiply this weight by the instantaneous radiation dose to obtain the weighted value of this point, repeat the above process to sum over N detection points, and the sum result is used as the numerator; Only repeat the calculation of the power function for N detection points to obtain the weight of the current estimation point, without multiplying by the instantaneous radiation dose, and the sum result is used as the denominator; Divide the numerator by the denominator to obtain the spatial interpolation dose evaluation value, and complete the preliminary dose estimation for the area where the detector is not installed; Obtain the photon beam energy, irradiation angle, detection point coordinates, beam source coordinates, and tissue CT value, multiply the photon beam energy, the cosine value of the tissue angle, and the tissue CT value, divide the product of the three by the square of the spatial distance between the estimation point coordinates and the beam source coordinates, add a very small term, and then multiply the sum value by the physical weight to obtain the first part; Multiply the instantaneous radiation dose by the measured weight to obtain the second part; Calculate the sum of the two parts to obtain the physical modeling dose evaluation value, and perform physical modeling compensation on the dose values of each estimation point in the three-dimensional space.

[0014] Further, the specific steps for constructing a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution are as follows: Perform weighted fusion on the spatial interpolation dose evaluation value and the physical modeling dose evaluation value to obtain the tumor dose evaluation value, and use the tumor dose evaluation value to generate an intermediate dose reconstruction map jointly driven by physical and observed data; Use the patient's preoperative CT image, tumor dose data, and intermediate dose reconstruction map as the combined input, construct a three-dimensional convolutional neural network model and carry out training and prediction, complete the dose information for the area where the detection point is not installed and refine the overall dose distribution; Perform weighted fusion on the network prediction result and the intermediate dose reconstruction map to generate a unified final three-dimensional dose map; Use the rigid registration algorithm to align the coordinates of the final three-dimensional dose map with the patient's preoperative CT image to achieve precise matching of the spatial image and the dose field.

[0015] Further, the specific steps for analyzing the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference surface dose are as follows: Compare the tumor dose evaluation value of each estimated point in the final three-dimensional dose map with the reference surface dose one by one, and calculate the comprehensive deviation intensity value of each estimated point; Subtract the reference surface dose from the tumor dose evaluation value of the estimated point and then divide by the reference surface dose to represent the relative dose deviation; Then, multiply the relative dose deviation by the tissue CT value of the estimated point as the first part; Calculate the sum of the squares of the lateral, longitudinal, and vertical coordinate differences between the estimated point and the beam source in the spatial coordinates, and divide the result by the square of the spatial scale normalization constant to obtain the second part; Add the above two parts of the results to obtain the comprehensive deviation intensity value.

[0016] Further, the specific steps for grading and determining the deviation intensity and generating adjustment suggestions to form a control process of a regulatory closed-loop feedback are as follows: Compare the absolute value of the comprehensive deviation intensity value with the deviation thresholds. The deviation thresholds include a first-level deviation threshold and a second-level deviation threshold, and perform grading judgment according to the comparison result: If the comprehensive deviation intensity value is less than or equal to the first-level deviation threshold, it is marked as the safe area; If the comprehensive deviation intensity value is greater than the first-level deviation threshold and less than the second-level deviation threshold, it is marked as the mild deviation area, and a recommended adjustment plan is generated: Fine-tune the irradiation direction and readjust the incident angle; Increase or decrease the tumor dose at the current position according to the actual situation of the patient; If the comprehensive deviation intensity value is greater than or equal to the second-level deviation threshold, it is marked as the severe deviation area, issue a recommended instruction to pause irradiation, and prompt the clinician to re-evaluate the treatment plan; Automatically generate an irradiation control parameter adjustment suggestion form according to the grading result and the recommended strategy and send it to the clinician; The clinician adjusts the irradiation control parameters according to the adjustment suggestion form, recalculates the comprehensive deviation intensity value, compares the comprehensive deviation intensity value with the deviation threshold, and verifies whether the adjustment achieves the expected control effect; If the deviation control target is still not met, automatically enter the next round of regulation, continue to optimize the parameters until the comprehensive deviation intensity value is in the safe area.

[0017] Further, the specific steps for focusing on the statistical deviation distribution characteristics of the deep estimated points in the target area are as follows: After completing the output of the final three-dimensional dose map and the calculation of the comprehensive deviation intensity value, screen out the deep estimated points located in the deep part of the target area, and extract their corresponding tumor dose evaluation values, tissue CT values, estimated point coordinates, and beam source coordinates; For these deep estimated points, aggregate their comprehensive deviation intensity values, and combine the tissue CT value distribution and the spatial depth information to statistically analyze the deviation characteristics in each CT interval and distance level, and establish a mapping relationship between the deviation behavior and the organizational structure attributes.

[0018] Further, the specific steps for generating structured calibration data for subsequent reconstruction input and risk prompt generation are as follows: Using the mapping relationship between deviation behaviors and organizational structure attributes, a spatial correction factor is constructed based on the existing tumor dose evaluation value and the comprehensive deviation intensity value to compensate for the error of the tumor dose evaluation value at the deep estimation point; The spatial correction factor is used as an incremental input to participate in the subsequent reconstruction process of the final three-dimensional dose map; The tissue CT values, detection point coordinates, beam source coordinates, photon beam energy, and comprehensive deviation intensity value in the deep region are reorganized into training samples to further optimize the weight configuration of the spatial dose reconstruction network; The reconstructed final three-dimensional dose map is named the three-dimensional dose map multi-level dose distribution visualization map. The internal space grid is divided with the tumor target area as the boundary, and the mean value of the comprehensive deviation intensity value and the difference between the comprehensive deviation intensity values before and after correction in each grid are marked to generate the target area response stability distribution map, which intuitively reflects the response differences of each area in the target area to the changes in irradiation parameters; The spatial correction factor generated in the deep region of the current patient is bound to the preoperative CT image of the patient to form structured index data for subsequent pre-treatment loading and calling; When the corrected area is close to the area corresponding to the reference body surface dose and the boundary of sensitive anatomical structures, a restricted reinforcement suggestion identifier is automatically added when generating the irradiation control parameter adjustment suggestion table to assist doctors in making more information-supported judgments when making dose enhancement or compensation decisions.

[0019] The second aspect of the present invention provides a tumor dose monitoring system based on radiotherapy, including: a tumor dose data acquisition and preprocessing module, a dose evaluation and three-dimensional mapping module, a deviation identification and closed-loop feedback module, and a deep dose error backtracking module, where: The tumor dose data acquisition and preprocessing module is used to collect tumor dose data using an implantable fiber optic dose detector and perform data cleaning and normalization processing on the tumor dose data; The dose evaluation and three-dimensional mapping module is used to perform preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data and construct a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; The deviation identification and closed-loop feedback module is used to analyze the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference body surface dose, perform hierarchical determination on the deviation intensity and generate adjustment suggestions to form a control process of regulatory closed-loop feedback; The deep dose error backtracking module is used to focus on the statistical deviation distribution characteristics of the deep estimation points in the target area and generate structured calibration data for subsequent reconstruction input and risk prompt generation.

[0020] Beneficial Effects

[0021] The present invention has the following beneficial effects:

[0022] (1) The tumor dose monitoring method and system based on radiotherapy perform preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and construct a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution, forming a tumor dose evaluation mechanism that integrates physics and observation, and improving the estimation accuracy of the dose in non-detected areas.

[0023] (2) The tumor dose monitoring method and system based on radiotherapy input the patient's preoperative CT image, tumor dose data and intermediate dose reconstruction map into the three-dimensional convolutional neural network model together to train and generate a spatially continuous final three-dimensional dose map, making up for the blind spots in data acquisition and effectively improving the complete modeling ability of the dose distribution in deep tissues.

[0024] (3) The tumor dose monitoring method and system based on radiotherapy compare the tumor dose estimation value with the reference surface dose, construct a deviation intensity quantification model by combining the tissue CT value and spatial position, calculate the comprehensive deviation intensity value, and the system can automatically generate control parameter suggestions based on the deviation level and dynamically adjust the irradiation settings, realizing a closed-loop dose control feedback.

[0025] (4) The tumor dose monitoring method and system based on radiotherapy statistically analyze the deviation distribution characteristics by combining the tissue CT value and spatial position for the deep estimation points in the target area, generate a spatial correction factor and use it for the incremental training of the neural network, bind the correction factor to the preoperative CT image, and construct an individualized correction template, improving the ability to identify and adaptively correct the deep dose error, and at the same time realizing the precise control of the patient's tumor dose by the system.

[0026] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of a tumor dose monitoring method based on radiotherapy;

[0028] Figure 2 It is a structural diagram of a tumor dose monitoring system based on radiotherapy;

[0029] Figure 3 It is a visualization diagram of multi-level dose distribution of a three-dimensional dose map;

[0030] Figure 4 It is a stability distribution diagram of target area response. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0032] Please refer to Figures 1-4 , the embodiments of the present invention provide a technical solution: a tumor dose monitoring method and system based on radiotherapy, including the following steps: S1, using an implantable fiber optic dose detector to collect tumor dose data, and performing data cleaning and normalization processing on the tumor dose data; S2, performing preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and constructing a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; S3, analyzing the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference body surface dose, performing grading determination on the deviation intensity and generating adjustment suggestions, and forming a control process of a regulation closed-loop feedback; S4, focusing on the deep estimation points in the target area to statistically analyze the deviation distribution characteristics, generating structured correction data for subsequent reconstruction input and risk prompt generation.

[0033] Specifically, the specific steps of using the implantable fiber optic dose detector to collect tumor dose data are as follows: An implantable fiber optic dose detector is used and arranged in and around the tumor target area. By precise positioning, it is ensured to cover the dose change range of the target area, and the radiation-induced optical signal is sensed in real time to collect the tumor dose data; the tumor dose data includes instantaneous radiation dose, detection point coordinates, beam source coordinates, estimation point coordinates, photon beam energy, tissue CT value, and reference body surface dose; among them, through photoelectric conversion, signal amplification, and analog-to-digital conversion, the fluorescence signal excited by radiation is converted into a digital electrical signal to obtain the instantaneous radiation dose of each detection point; through preoperative CT scanning, the spatial position of the fiber optic probe is calibrated, a patient coordinate system is constructed, and the detection point coordinates, beam source coordinates, and estimation point coordinates in the patient's body are obtained by using the rigid registration method to match the dose collection with the spatial position; the photon beam energy of the ray used in the treatment is obtained through the radiotherapy equipment control system, which is a key physical parameter for simulating ray penetration and energy deposition in physical modeling; the tissue CT value of the tissue where the corresponding detection point is located is read from the preoperative CT image of the patient, and this value reflects the tissue density characteristics; by connecting with the control system of the radiotherapy accelerator, the tissue angle of the current beam relative to the patient coordinate system is read in real time to provide a spatial reference for the subsequent dose direction factor; the reference body surface dose is obtained through the TLD detector attached to the patient's body surface, which is used as a benchmark index for dose deviation evaluation and control calibration to assist in constructing a comprehensive deviation intensity value function.

[0034] In this implementation scheme, real-time dose data acquisition for multiple points and deep parts of the tumor target area and its periphery is achieved through an implantable fiber optic dose detector, breaking through the limitation of traditional surface monitoring in terms of spatial depth; the spatial coordinates of the detection points, beam sources, and estimation points are obtained through preoperative CT registration to achieve precise matching of dose data with the patient's anatomical structure, ensuring the consistency and integrity of the data; at the same time, key physical information such as photon beam energy, tissue CT value, and irradiation angle is introduced to provide a physical basis for subsequent dose modeling; combined with surface reference dose data, it lays a fusion foundation for deviation analysis and closed-loop regulation, thereby improving the system's ability to restore the true dose distribution in the body and the precision control level of individualized radiotherapy.

[0035] Specifically, the specific steps for data cleaning and normalization of tumor dose data are as follows: Using the sliding window method combined with the three-times standard deviation outlier detection algorithm, local statistical analysis is performed on the dose changes of each detection point within a continuous time period to eliminate tumor dose data that significantly deviates from the normal range, reducing the interference of instantaneous noise and abnormal jumps on model training; using the millisecond-level time alignment and linear interpolation method to fill in the tumor dose data that is instantaneously missing during the acquisition process due to factors such as detection delay and communication interference, maintaining the integrity and continuity of the time series data; using the rigid registration algorithm to register the spatial coordinates of the detector with the coordinates of the patient's preoperative CT image, and ensuring the one-to-one correspondence between all tumor dose data and tissue structure information by constructing a unified three-dimensional space mapping relationship; using the Kalman filter algorithm to perform time series modeling and denoising processing on the continuously acquired instantaneous radiation dose, reducing high-frequency fluctuation interference and enhancing the dynamic stability of the data; using the unit conversion and maximum-minimum normalization algorithm to normalize the tumor dose data, unifying the values from different sources and scales into the standard dimension range, and improving the model calculation efficiency and data comparability.

[0036] In this implementation scheme, by introducing a variety of data cleaning and normalization strategies, the quality and consistency of tumor dose data are improved: The sliding window and outlier detection algorithm are used to effectively eliminate local noise and outliers, ensuring the stability and reliability of the data; the time alignment and interpolation completion mechanism solves the problem of short-term data loss during the acquisition process, ensuring the continuity of the time series; the rigid registration algorithm realizes the one-to-one mapping between dose data and the CT space, providing a spatial basis for subsequent three-dimensional modeling; the Kalman filter enhances the smoothness of the instantaneous dose value and suppresses high-frequency fluctuations; the normalization process unifies the data dimension and optimizes the calculation efficiency of subsequent model training and fusion input. These processing means jointly construct high-quality and structured tumor dose data, providing a solid data foundation for the subsequent three-dimensional reconstruction and deviation identification of the system.

[0037] Specifically, the specific steps for preliminary dose estimation and physical modeling compensation of the preprocessed tumor dose data are as follows: Take N detection points, calculate the sum of the squares of the coordinate differences in the transverse direction, the longitudinal direction, and the vertical direction between the estimation point and the i-th detection point, add a minimum term, and finally take the square root of the result to obtain the spatial distance between the i-th detection point and the estimation point in the patient coordinate system; Multiply this spatial distance by the exponential decay factor and take the negative value as the exponent, and then calculate the value of this power function with the natural constant as the base to obtain the weight of the current detection point; Among them, the exponential decay factor is obtained by fitting and optimizing on multiple patient data by minimizing the mean square error between the spatially interpolated dose evaluation value and the instantaneous radiation dose in historical cases, and is used to reflect the optimal decay rate of the influence of spatial distance on dose attenuation; Multiply this weight by the instantaneous radiation dose as the weighted value of this point, repeat the above process to sum the N detection points, and the summation result is used as the numerator; Only repeat the calculation of the power function for the N detection points to obtain the weight of the current estimation point, without multiplying by the instantaneous radiation dose, and the summation result is used as the denominator; Divide the numerator by the denominator to obtain the spatially interpolated dose evaluation value, and complete the preliminary dose estimation for the area where the detector is not deployed; Obtain the photon beam energy, irradiation angle, detection point coordinates, beam source coordinates, and tissue CT value, multiply the photon beam energy, the cosine value of the tissue angle, and the tissue CT value, divide the product of the three by the square of the spatial distance between the estimation point coordinates and the beam source coordinates and add a minimum term, and then multiply the sum value by the physical weight to obtain the first part; Multiply the instantaneous radiation dose by the measured weight to obtain the second part; Calculate the sum of the two parts to obtain the physical modeling dose evaluation value, and perform physical modeling compensation on the dose values of each estimation point in three-dimensional space; Among them, based on the least mean square error fitting algorithm of historical patient tumor cases, the measured weight and the physical weight are repeatedly trained and optimized between the known instantaneous radiation dose distribution and the three-dimensional dose distribution output, and the value ranges of both are [0,1].

[0038] Among them, the specific calculation formula for the spatially interpolated dose evaluation value is:

[0039]

[0040] In the formula, K (x,y,z) represents the spatially interpolated dose evaluation value, D i represents the instantaneous radiation dose, N represents the total number of deployed detection points participating in the interpolation calculation, x, y, z represent the current estimation point coordinates, x i , y i , z i represent the detection point coordinates of the i-th detection point, k represents the exponential decay factor, and ∈ represents the minimum term.

[0041] Among them, the specific calculation formula for the physical modeling dose evaluation value is:

[0042]

[0043] In the formula, W (x,y,z) represents the physical model dose evaluation value, E represents the photon beam energy, θ represents the tissue angle, x, y, z represent the detector point coordinates of the current estimation point, x0, y0, z0 represent the beam source coordinates, H represents the tissue CT value of the estimation point, D s represents the instantaneous radiation dose obtained by weighting adjacent detector points, α represents the physical weight, β represents the measured weight, and ∈ represents the minterm.

[0044] In this implementation scheme, by performing spatial interpolation estimation and physical modeling compensation on the preprocessed tumor dose data, the dose restoration accuracy of the area without detectors is effectively improved: First, a weight model is constructed using the spatial distance and the exponential decay function to achieve continuous dose completion of the estimation point and avoid spatial blanks caused by insufficient detection coverage; Second, combined with key physical parameters such as photon beam energy, irradiation angle, and tissue CT value, a dose compensation model based on radiation transmission characteristics is constructed to further enhance the response ability of the dose distribution to the anatomical structure and the incident direction; The dual-path fusion of spatial interpolation and physical modeling significantly improves the accuracy of the system's description of the complex dose field in the body.

[0045] Specifically, the specific steps to construct a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution are as follows: Weightedly fuse the spatial interpolation dose evaluation value and the physical modeling dose evaluation value, and comprehensively integrate the two types of estimation information according to the set fusion ratio to obtain the tumor dose evaluation value, which is used as a unified representation compatible with structural and physical characteristics; Use the tumor dose evaluation value to generate an intermediate dose reconstruction map jointly driven by physical and observational data, providing a dose input basis with spatial continuity and preliminary credibility for network training; Use the patient's preoperative CT image, tumor dose data, and intermediate dose reconstruction map as joint inputs to construct a three-dimensional convolutional neural network model, and carry out training and prediction on a preset sample set. Through the deep feature extraction ability of the network, complete the dose information of the area without detection points, improve the restoration ability of spatial details and boundary transition areas, and further refine the overall dose distribution; Weightedly fuse the network prediction result and the intermediate dose reconstruction map, make full use of the detail advantages of AI prediction and the global continuity of the original modeling map to generate a unified final three-dimensional dose map, ensuring local accuracy and global consistency; Use a rigid registration algorithm to align the coordinates of the final three-dimensional dose map with the patient's preoperative CT image, establish the correspondence between the image space and the dose space, and achieve precise matching of the spatial image and the dose field, providing structured input for subsequent deviation analysis and feedback control.

[0046] In this implementation scheme, by fusing the spatially interpolated dose evaluation value with the physically modeled dose evaluation value, an intermediate dose reconstruction map is constructed, providing a structurally complete and physically credible training basis for the three-dimensional convolutional neural network. By jointly inputting the patient's preoperative CT image and tumor dose data, the network is enabled to have a multi-dimensional perception ability of the spatial structure and tissue characteristics, thereby achieving precise completion of the dose in the area without detection points and refining and optimizing the overall distribution. Finally, by fusing the AI prediction result with the intermediate map, a high-resolution three-dimensional dose map is output, and it is aligned with the preoperative image using rigid registration to achieve the spatial matching of the dose field and the patient's anatomical structure, thus significantly improving the integrity and accuracy of the system in dose restoration in deep and sparse areas.

[0047] Specifically, the specific steps for analyzing the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference body surface dose are as follows: Compare the tumor dose evaluation value of each estimated point in the final three-dimensional dose map with the reference body surface dose one by one to ensure that they are in the same spatial coordinate system, and calculate the comprehensive deviation intensity value of each estimated point to quantify the dose deviation risk at that point; Subtract the reference body surface dose from the tumor dose evaluation value of the estimated point and then divide it by the reference body surface dose, which represents the relative dose deviation at that point, and this deviation can reflect the degree of deviation of the dose output from the standard level; Then, multiply the relative dose deviation by the tissue CT value of the estimated point as the first part to introduce the influence factor of tissue density and enhance the sensitivity of the deviation value to the response characteristics of different tissues; Calculate the sum of the squares of the coordinate differences in the horizontal, longitudinal, and vertical directions between the estimated point and the beam source in the spatial coordinates, which reflects the relative spatial relationship between its position and the radiation path, and divide this result by the square of the spatial scale normalization constant to make different depth positions comparable, obtaining the second part; Among them, the spatial scale normalization constant is calculated by statistically averaging the spatial distances between the estimated points in the tumor target area and the beam source among historical patients, and is used to unify the position difference measurement criteria in different treatment scenarios; Add the above two parts of the results to obtain the comprehensive deviation intensity value, providing a structured numerical basis for subsequent deviation grading and response control.

[0048] Among them, the specific calculation formula for the comprehensive deviation intensity value is:

[0049]

[0050] In the formula, P (x,y,z) represents the comprehensive deviation intensity value of the estimated point, D f(x,y,z) represents the tumor dose evaluation value, D r represents the reference body surface dose, H represents the tissue CT value of the estimated point, x, y, z represent the coordinates of the detection point of the estimated point, x0, y0, z0 represent the coordinates of the beam source, and L represents the spatial scale normalization constant.

[0051] In this implementation scheme, by constructing a comprehensive deviation intensity value, the deviation degree between the tumor dose evaluation value and the reference surface dose is systematically quantified, and the tissue CT value and spatial depth information are fused, so that the deviation evaluation not only reflects the absolute dose difference, but also takes into account the combined effects of tissue density and position factors, enhancing the tissue sensitivity and spatial resolution ability of deviation identification; this deviation intensity index provides an accurate quantitative basis for subsequent high-risk area identification, dose grading judgment and automatic regulation strategy generation, significantly improving the system's perception ability of abnormal dose behavior and the reliability of regulation response.

[0052] Specifically, the specific steps of grading and determining the deviation intensity and generating adjustment suggestions to form a control process of closed-loop feedback regulation are as follows: Compare the absolute value of the comprehensive deviation intensity value with the deviation thresholds. The deviation thresholds include a first-level deviation threshold and a second-level deviation threshold, and conduct grading judgment according to the comparison result: If the comprehensive deviation intensity value is less than or equal to the first-level deviation threshold, it is marked as the safe area; if the comprehensive deviation intensity value is greater than the first-level deviation threshold and less than the second-level deviation threshold, it is marked as the mild deviation area, and a recommended adjustment plan is generated: fine-tune the irradiation direction and readjust the incident angle; increase or decrease the tumor dose at the current position according to the actual situation of the patient; if the comprehensive deviation intensity value is greater than or equal to the second-level deviation threshold, it is marked as the severe deviation area, issue a command to recommend suspending irradiation, and prompt the clinician to re-evaluate the treatment plan; according to the grading result and recommended strategy, automatically generate an adjustment suggestion form for irradiation control parameters and send it to the clinician; the clinician adjusts the irradiation control parameters according to the adjustment suggestion form, recalculates the comprehensive deviation intensity value, compares the comprehensive deviation intensity value with the deviation threshold, and verifies whether the adjustment achieves the expected control effect; if the deviation control target is still not met, automatically enter the next round of regulation, continue to optimize the parameters until the comprehensive deviation intensity value is in the safe area.

[0053] In this implementation scheme, by establishing a grading and determination mechanism based on the comprehensive deviation intensity value, accurate identification and response classification of dose deviations at different levels are realized; combined with the set deviation thresholds, corresponding adjustment strategies are formulated for the safe area, mild deviation area and severe deviation area respectively, and an adjustment suggestion form for irradiation control parameters is automatically generated and introduced into the clinician decision-making link, constructing a man-machine collaborative regulation feedback process; the system supports verifying the adjustment effect and multi-round iterative optimization, effectively improving the management ability of abnormal dose behavior and the individual adaptability of treatment plans during radiotherapy.

[0054] Specifically, the specific steps for estimating the statistical deviation distribution characteristics of deep points in the target area are as follows: After the output of the final 3D dose map and the calculation of the comprehensive deviation intensity value, based on the coordinate depth threshold and the target area boundary conditions, deep estimation points located deep in the target area and far from the body surface are selected, and the dose distribution accuracy and potential deviation risks in these areas are focused on; the corresponding tumor dose evaluation values, tissue CT values, estimation point coordinates, and beam source coordinates are extracted to ensure that the data comes from a registered and unified coordinate system and retains the spatial orientation of the structural information; for these deep estimation points, their comprehensive deviation intensity values are aggregated, and by summarizing the deviation magnitudes of multiple points, a structurally consistent deep deviation data set is formed, and combined with the tissue CT value distribution and spatial depth information, a multi-dimensional parameter matrix is established for classification analysis; the deviation characteristics in each CT interval and distance level are statistically analyzed, the common error types and spatial distribution trends in high-density and low-density tissues are identified, and finally, the mapping relationship between the deviation behavior and the organizational structure attributes is established, providing a model basis and data support for the construction of subsequent correction factors.

[0055] In this implementation plan, by aggregating and analyzing the deviation intensity of deep estimation points in the target area, combined with tissue CT values and spatial depth information, the deviation distribution laws under different tissue densities and spatial levels are systematically explored, making up for the problem of insufficient recognition ability of traditional dose monitoring for deep areas; by constructing the mapping relationship between the deviation behavior and the organizational structure attributes, a data foundation is laid for establishing a structure-dependent error compensation mechanism, which helps to improve the dose estimation accuracy of the system in a complex tissue environment and the perception and modeling ability of deep dose anomalies.

[0056] Specifically, the specific steps for generating structured calibration data for subsequent input reconstruction and risk warning generation are as follows: Utilize the mapping relationship between deviation behaviors and organizational structure attributes to construct a spatial correction factor based on the existing tumor dose evaluation values and comprehensive deviation intensity values, which is used to compensate for the error of the tumor dose evaluation value at the deep estimation point; The spatial correction factor is used as an incremental input to participate in the subsequent reconstruction process of the final three-dimensional dose map; Reorganize the tissue CT values, detection point coordinates, beam source coordinates, photon beam energy, and comprehensive deviation intensity values in the deep region into training samples to further optimize the weight configuration of the spatial dose reconstruction network; Name the reconstructed final three-dimensional dose map as the three-dimensional dose map multi-level dose distribution visualization map, divide the internal space grid with the tumor target area as the boundary, label the mean value of the comprehensive deviation intensity value and the difference between the comprehensive deviation intensity values before and after correction in each grid, generate the target area response stability distribution map, and intuitively reflect the response differences of each area in the target area to the changes in irradiation parameters; Bind the spatial correction factor generated in the deep region of the current patient to the preoperative CT image of the patient to form structured index data for subsequent pre-treatment loading and calling; When the corrected area is close to the area corresponding to the reference surface dose and the boundary of sensitive anatomical structures, automatically append a restricted enhancement suggestion identifier when generating the irradiation control parameter adjustment suggestion table, which is used to assist doctors in making more information-supported judgments when making dose enhancement or compensation decisions.

[0057] In this case, Table 1, the data table of the three-dimensional dose map multi-level dose distribution visualization map, records the tumor dose evaluation situations of five estimation samples under different spatial positions and tissue density conditions. Each sample includes the estimation point coordinates (x, y, z), tissue CT value, and the corresponding calculated tumor dose evaluation value, and the deviation levels are divided accordingly. The estimation point coordinates of Sample 1 are (0.1, 0.15, 0.05), the tissue CT value is 55, and the corresponding tumor dose evaluation value is 1.20, belonging to the severe deviation area; Sample 2 is located at (-0.12, -0.08, -0.1), the tissue CT value is -40, and the dose evaluation value is 0.90, which is determined as the mild deviation area;

[0058] The estimation point coordinates of Sample 3 are (0.054, 0.1, 0.12), the tissue CT value is 15, and the corresponding dose evaluation value is 0.65, which is also classified as the mild deviation area; Sample 4 is located at (-0.07, -0.1, 0.0), the tissue CT value is -80, and the tumor dose evaluation value is 0.45, which is determined as the safe area; The estimation point coordinates of Sample 5 are (0.02, 0.0, -0.15), the tissue CT value is 90, and the tumor dose evaluation value is 0.80, which also falls in the mild deviation area.

[0059] Table 1 Data table of the three-dimensional dose map multi-level dose distribution visualization map

[0060]

[0061]

[0062] As Figure 3 shown, it is a visualization diagram of the multi-level dose distribution of the three-dimensional dose map. In the figure, purple represents the severe deviation area; orange is the mild deviation area; yellow indicates the safe area, which may be in the dose transition or marginal area. This hierarchical visualization method can assist doctors in intuitively judging whether the dose covers the target area and whether it overflows into the risk area. At the same time, it can also be used for subsequent deviation analysis and adjustment of control strategies.

[0063] In addition, in the embodiments described in Table 2, the data table of the target area response stability distribution map records the dose response of five target area samples under different spatial positions and tissue density conditions. Each sample includes the estimated point coordinates, tumor dose evaluation value, reference body surface dose, tissue CT value, and comprehensive deviation intensity value. The estimated point coordinates of Sample 1 are (0.10, -0.10, 0.20), the tumor dose evaluation value is 1.15, the reference body surface dose is 1.0, the tissue CT value is 50, and the comprehensive deviation intensity value is 0.78; the estimated point coordinates of Sample 2 are (-0.40, 0.30, -0.30). Under the low-density tissue with a tissue CT value of -80, the tumor dose evaluation value is 0.85, the reference body surface dose is 0.9, and the comprehensive deviation intensity value is 0.62; Sample 3 is located at (0.35, -0.25, 0.10), the tissue CT value is 20, the tumor dose evaluation value is 1.05, the reference body surface dose is 1.0, and the comprehensive deviation intensity value is 0.45; the estimated point coordinates of Sample 4 are (-0.20, 0.15, -0.05), the tissue CT value is -30, and the corresponding tumor dose evaluation value is 0.65, the reference body surface dose is 0.7, and the comprehensive deviation intensity value is 0.35; Sample 5 is at the estimated point coordinates (0.05, 0.00, 0.30), the tissue CT value is 100, the tumor dose evaluation value is 1.25, the reference body surface dose is 1.0, and the comprehensive deviation intensity value is 0.81.

[0064] Table 2 Data Table of Target Area Response Stability Distribution Map

[0065] Target area sample x y z <![CDATA[D f(x,y,z) > <![CDATA[D r > H <![CDATA[P (x,y,z) <!-- 9 -->]]> 1 0.1 -0.1 0.2 1.15 1.0 50 0.78 2 -0.4 0.3 -0.3 0.85 0.9 -80 0.62 3 0.35 -0.25 0.1 1.05 1.0 20 0.45 4 -0.2 0.15 -0.05 0.65 0.7 -30 0.35 5 0.05 0.0 0.3 1.25 1.0 100 0.81

[0066] As Figure 4 shown, it is a target area response stability distribution map. Each point represents a spatial grid unit in the tumor target area. The closer the color is to yellow, the greater the response difference in this area before and after dose adjustment, and the lower the stability; the darker the purple color, the more stable the response in this area. This map can be used to analyze the areas in the target area that are sensitive or fluctuate violently to irradiation parameters, and assist doctors in identifying potential unstable areas or dose control blind spots.

[0067] In this implementation, by constructing a spatial correction factor based on the mapping relationship between deviation behavior and organizational structure, directional error compensation for the estimated tumor dose in the deep region of the target area is achieved, and it is incorporated as an increment into the reconstruction process of the final three-dimensional dose map, significantly improving the accuracy of tumor dose estimation in the deep region. At the same time, the tissue CT value, the coordinates of the estimated point, and the photon beam energy are integrated into the training samples to optimize the weight configuration of the spatial dose reconstruction network and enhance the model's adaptability to complex organizational structures. By constructing a multi-level dose distribution visualization map of the three-dimensional dose map and a target area response stability distribution map, the sensitivity of different regions to irradiation parameter changes is visually presented. The spatial correction factor is bound to the patient's preoperative CT image to form structured index data, providing support for rapid loading and retrospective calling before treatment. Restriction reinforcement suggestion marks are automatically added near the risk area to assist doctors in making more robust decisions based on data during dose enhancement or compensation operations, improving the system's individualized regulation ability and clinical safety.

[0068] As Figure 2 shown, the second aspect of the present invention provides a tumor dose monitoring system based on radiotherapy, including: a tumor dose data acquisition and preprocessing module, a dose evaluation and three-dimensional mapping module, a deviation identification and closed-loop feedback module, and a deep dose error backtracking module, where: the tumor dose data acquisition and preprocessing module is used to collect tumor dose data using an implantable fiber optic dose detector and perform data cleaning and normalization processing on the tumor dose data; the dose evaluation and three-dimensional mapping module is used to perform preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data and construct a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; the deviation identification and closed-loop feedback module is used to analyze the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference surface dose, perform hierarchical determination on the deviation intensity, generate adjustment suggestions, and form a control process for regulating closed-loop feedback; the deep dose error backtracking module is used to focus on the statistical deviation distribution characteristics of the deep estimated points in the target area and generate structured correction data for subsequent reconstruction input and risk prompt generation.

[0069] In this implementation, by constructing a four-level structured functional module covering data acquisition, dose modeling, deviation identification, and deep backtracking, a complete process from real-time multi-point deep acquisition, three-dimensional dose fine reconstruction, to intelligent deviation identification and feedback control is realized. The system not only improves the ability to restore the true dose distribution in the tumor area but also has the ability to dynamically respond to high-risk areas and adaptively correct deep errors, forming an individualized radiotherapy monitoring and regulation mechanism driven by data, structure-related, and closed-loop controlled, significantly enhancing the accuracy, safety, and intelligence level of tumor radiotherapy.

[0070] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0071] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A tumor dose monitoring method based on radiotherapy, characterized in that, The following steps are involved: S1, using an implantable fiber optic dose detector to collect tumor dose data, and performing data cleaning and normalization on the tumor dose data; S2, performs preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and constructs a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; S3, analyzing the deviation intensity based on the comparison results between the tumor dose assessment value and the reference body surface dose, classifying and determining the deviation intensity and generating adjustment suggestions, thus forming a control process of closed-loop feedback; S4, focusing on the statistical deviation distribution characteristics of the deep estimation points in the target area, generates structured correction data for subsequent reconstruction input and risk prompt generation.

2. The tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps of collecting tumor dose data using an implantable optical fiber dose detector are as follows: An implantable fiber optic dose detector is used and arranged in the tumor target area and its periphery to sense radiation-induced light signals in real time and collect tumor dose data; the tumor dose data includes instantaneous radiation dose, detection point coordinates, beam source coordinates, estimated point coordinates, photon beam energy, tissue CT value and reference surface dose; wherein, the instantaneous radiation dose of each detection point is obtained through photoelectric conversion, signal amplification and analog-to-digital conversion; the spatial position of the fiber optic probe is calibrated through preoperative CT scanning, the patient coordinate system is constructed, and the detection point coordinates, beam source coordinates and estimated point coordinates in the patient's body are obtained; the photon beam energy of the radiation used for treatment is obtained through the radiotherapy equipment control system; the tissue CT value of the tissue corresponding to the detection point is read from the patient's preoperative CT image; the tissue angle of the current beam relative to the patient coordinate system is read in real time by connecting to the control system of the radiotherapy accelerator; and the reference surface dose is obtained through the TLD detector attached to the patient's body surface.

3. A tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps of data cleaning and normalization processing of tumor dose data are as follows: The sliding window method combined with the three-fold standard difference constant detection algorithm was used to eliminate tumor dose data that obviously deviated from the normal range. The millisecond-level time alignment and linear interpolation method were used to fill in the instantaneous missing tumor dose data. The rigid registration algorithm was used to align the detector space coordinates with the patient's preoperative CT image coordinates to ensure three-dimensional spatial consistency. The Kalman filter algorithm was used to denoise the continuously collected instantaneous radiation dose. The unit conversion and maximum and minimum normalization algorithms were used to normalize the tumor dose data to unify the data scale.

4. The tumor dose monitoring method based on radiotherapy according to claim 1, wherein: The specific steps of performing preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data are as follows: Take N detection points, calculate the sum of the squares of the coordinate differences in the horizontal direction, the squares of the coordinate differences in the vertical direction, and the squares of the coordinate differences in the perpendicular direction between the estimated point and the i-th detection point, add a very small term, and finally take the square root of the result to obtain the spatial distance between the i-th detection point and the estimated point in the patient coordinate system; multiply this spatial distance by the exponential decay factor, take the negative value as the exponent, and then calculate the value of this power function with the natural constant as the base to obtain the weight of the current detection point; multiply this weight by the instantaneous radiation dose to obtain the weighted value of this point. Repeat the above process to sum over N detection points, and the sum result is used as the numerator; only repeat the calculation of the power function for N detection points to obtain the weight of the current estimated point without multiplying by the instantaneous radiation dose, and the sum result is used as the denominator; divide the numerator by the denominator to obtain the spatial interpolation dose evaluation value, and complete the preliminary dose estimation for the area where the detector is not arranged. Obtain the photon beam energy, irradiation angle, detection point coordinates, beam source coordinates, and tissue CT value. Multiply the photon beam energy, the cosine value of the tissue angle, and the tissue CT value, divide the product of the three by the square of the spatial distance between the estimated point coordinates and the beam source coordinates, add a very small term, and then multiply the sum value by the physical weight to obtain the first part; multiply the instantaneous radiation dose by the measured weight to obtain the second part; calculate the sum of the two parts to obtain the physical modeling dose evaluation value, and perform physical modeling compensation on the dose values of each estimated point in the three-dimensional space.

5. A tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps for constructing a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution are as follows: Perform weighted fusion on the spatial interpolation dose evaluation value and the physical modeling dose evaluation value to obtain the tumor dose evaluation value, and use the tumor dose evaluation value to generate an intermediate dose reconstruction map jointly driven by physical and observed data; use the patient's preoperative CT image, tumor dose data, and intermediate dose reconstruction map as joint inputs, construct a three-dimensional convolutional neural network model, and carry out training and prediction to complete the dose information in the area where the detection point is not arranged and refine the overall dose distribution; perform weighted fusion on the network prediction result and the intermediate dose reconstruction map to generate a unified final three-dimensional dose map; use the rigid registration algorithm to align the coordinates of the final three-dimensional dose map with the patient's preoperative CT image to achieve precise matching of the spatial image and the dose field.

6. The tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps for analyzing the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference surface dose are as follows: Compare the tumor dose evaluation value of each estimated point in the final three-dimensional dose map with the reference surface dose one by one, and calculate the comprehensive deviation intensity value of each estimated point; subtract the reference surface dose from the tumor dose evaluation value of the estimated point and then divide by the reference surface dose to represent the relative dose deviation; then, multiply the relative dose deviation by the tissue CT value of the estimated point as the first part; Calculate the sum of the squares of the coordinate differences in the horizontal, vertical, and perpendicular directions between the estimated point and the beam source in the spatial coordinates, and divide the result by the square of the spatial scale normalization constant to obtain the second part; add the results of the above two parts to obtain the comprehensive deviation intensity value.

7. A tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps for grading and determining the deviation intensity, generating adjustment suggestions, and forming a control process for a regulatory closed-loop feedback are as follows: Compare the absolute value of the comprehensive deviation intensity value with the deviation threshold. The deviation threshold includes a primary deviation threshold and a secondary deviation threshold. Perform hierarchical judgment based on the comparison result: If the comprehensive deviation intensity value is less than or equal to the primary deviation threshold, it is marked as the safe area; If the comprehensive deviation intensity value is greater than the primary deviation threshold and less than the secondary deviation threshold, it is marked as the mild deviation area, and a recommended adjustment plan is generated: Fine-tune the irradiation direction and readjust the incident angle; Increase or decrease the tumor dose at the current position according to the actual situation of the patient; If the comprehensive deviation intensity value is greater than or equal to the secondary deviation threshold, it is marked as the severe deviation area, and a command to recommend suspending irradiation is issued, and the clinician is prompted to re-evaluate the treatment plan; According to the grading results and recommended strategies, automatically generate an adjustment suggestion table for irradiation control parameters and send it to the clinician; The clinician adjusts the irradiation control parameters according to the adjustment suggestion table, recalculates the comprehensive deviation intensity value, compares the comprehensive deviation intensity value with the deviation threshold, and verifies whether the adjustment has achieved the expected control effect; If the deviation control target is still not met, automatically enter the next round of regulation, continue to optimize the parameters until the comprehensive deviation intensity value is in the safe area.

8. A tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps for estimating the deviation distribution characteristics of the deep points in the focused target area are as follows: After completing the output of the final three-dimensional dose map and the calculation of the comprehensive deviation intensity value, screen out the deep estimation points located in the deep part of the target area, and extract their corresponding tumor dose evaluation values, tissue CT values, estimation point coordinates, and beam source coordinates; For these deep estimation points, aggregate their comprehensive deviation intensity values, and combine the tissue CT value distribution and spatial depth information to statistically analyze the deviation characteristics in each CT interval and distance level, and establish a mapping relationship between the deviation behavior and the organizational structure attributes.

9. A tumor dose monitoring method based on radiotherapy according to claim 1, characterized in that: The specific steps for generating structured correction data for subsequent reconstruction input and risk prompt generation are as follows: Using the mapping relationship between the deviation behavior and the organizational structure attributes, construct a spatial correction factor based on the existing tumor dose evaluation value and the comprehensive deviation intensity value, and use it to compensate for the error of the tumor dose evaluation value of the deep estimation point; The spatial correction factor is used as an incremental input to participate in the subsequent reconstruction process of the final three-dimensional dose map; Reorganize the tissue CT value, detection point coordinates, beam source coordinates, photon beam energy, and comprehensive deviation intensity value in the deep area into training samples to further optimize the weight configuration of the spatial dose reconstruction network; Name the reconstructed final three-dimensional dose map as the three-dimensional dose map multi-level dose distribution visualization map, divide the internal space grid with the tumor target area as the boundary, annotate the mean value of the comprehensive deviation intensity value in each grid and the difference between the comprehensive deviation intensity values before and after correction, and generate a target area response stability distribution map to intuitively reflect the response differences of each area in the target area to the changes in irradiation parameters; Bind the spatial correction factor generated in the deep region of the current patient to the patient's preoperative CT image to form structured index data for subsequent loading and calling before treatment; when the corrected area is close to the reference surface dose corresponding area and the boundary of sensitive anatomical structures, automatically attach a restricted enhancement suggestion identifier when generating the irradiation control parameter adjustment suggestion table, which is used to assist doctors in making more informed judgments when making dose enhancement or compensation decisions.

10. A tumor dose monitoring system based on radiotherapy, comprising: Tumor dose data acquisition and preprocessing module, dose evaluation and three-dimensional mapping module, deviation identification and closed-loop feedback module, deep dose error backtracking module, where: The tumor dose data acquisition and preprocessing module is used to collect tumor dose data using an implantable fiber optic dose detector, and perform data cleaning and normalization processing on the tumor dose data; The dose evaluation and three-dimensional mapping module is used to perform preliminary dose estimation and physical modeling compensation on the preprocessed tumor dose data, and construct a three-dimensional convolutional neural network model to refine the three-dimensional dose distribution; The deviation identification and closed-loop feedback module is used to analyze the deviation intensity according to the comparison result between the tumor dose evaluation value and the reference surface dose, perform hierarchical determination on the deviation intensity and generate adjustment suggestions to form a control process for regulating closed-loop feedback; The deep dose error backtracking module is used to focus on the statistical deviation distribution characteristics of the deep estimation points in the target area, and generate structured correction data for subsequent reconstruction input and risk prompt generation.

Images