A radiation therapy plan scoring method, system, device, and medium

Abstract

The application relates to the technical field of radiotherapy, and discloses a radiotherapy plan scoring method, system, device and medium. The method comprises the following steps: acquiring CT images, dose distribution data and structure delineation files in a radiotherapy plan to be evaluated; determining the range of each target region and the range of each critical organ according to the structure delineation files and the CT images; determining the target region score of each target region based on the dose distribution data and the range of each target region; determining the organ score of each critical organ based on the dose distribution data and the range of each critical organ; and obtaining a total plan score and outputting a scoring report according to all the target region scores and all the organ scores. The scheme of the application solves the pain points of traditional manual evaluation, has the advantages of strong objectivity, high quantification and clear mathematical explainability, and has important clinical significance for improving the radiotherapy quality control level and reducing the work burden of medical personnel.

Description

Technical Field

[0001] This invention relates to the field of radiotherapy technology, and in particular to a radiotherapy planning scoring method, system, equipment, and medium. Background Technology

[0002] Radiotherapy is a key component of comprehensive treatment for malignant tumors, and the quality of its treatment plan directly affects the tumor control effect and the risk of treatment-related toxic side effects for patients. In clinical practice, an ideal radiotherapy plan must simultaneously meet two core and mutually restrictive objectives: first, ensuring that the target area (such as the tumor region) receives a sufficient and uniform prescribed dose to avoid tumor control failure due to insufficient dose or damage to normal tissues caused by excessive dose; second, strictly limiting the radiation dose to surrounding organs at risk, such as the spinal cord, lungs, heart, and esophagus, within their clinically tolerable safety thresholds to reduce the incidence of radiation complications.

[0003] Currently, clinical assessment of radiotherapy plan quality primarily relies on subjective judgment by physicians or physicists through manual observation of dose distribution maps and dose-volume histograms. This traditional assessment model is highly subjective, with results heavily dependent on the assessor's personal experience and subjective biases. Inconsistent standards and conclusions among different assessors often compromise the objectivity and fairness of the assessment. Secondly, it suffers from poor quantification and comparability. Existing methods lack unified, quantitative comprehensive evaluation indicators, making it difficult to accurately quantify and objectively compare the quality of different radiotherapy plans, hindering the rapid selection and optimization of optimal treatment options. Finally, it suffers from low mathematical interpretability. The assessment process is largely based on qualitative descriptions and visual judgments, lacking clear mathematical model support. This makes it difficult to trace, verify, and reproduce the logic behind the assessment results, reducing the scientific rigor and credibility of the assessment process.

[0004] Therefore, there is an urgent need for a radiotherapy planning scoring method, system, equipment, and medium. Summary of the Invention

[0005] In view of this, the present invention proposes a radiotherapy planning scoring method, system, computer equipment and computer-readable medium, which solves the pain points of traditional manual assessment, and has the advantages of strong objectivity, high degree of quantification and clear mathematical interpretability. It has urgent and important clinical significance and application value for improving the standardization level of radiotherapy quality control, assisting clinical decision-making and reducing the workload of medical staff.

[0006] To achieve the above objectives, one aspect of the present invention provides a radiotherapy planning scoring method, specifically including the following steps: Obtain CT images, dose distribution data, and structural delineation files from the radiotherapy plan to be evaluated; Based on the structural delineation file and the CT images, determine the extent of each target region and the extent of each organ at risk; Based on the dose distribution data and the range of each target region, a target region score is determined for each target region; Based on the dose distribution data and the range of each organ at risk, an organ score is determined for each organ at risk; Based on the scores of all the target areas and all the organs, the total planned score is obtained and a scoring report is output.

[0007] In some implementations, determining the extent of each target region and each organ at risk based on the structural delineation file and the CT images includes: The first contour data of each target region and the second contour data of each organ at risk are parsed from the structure delineation file; For each target region, its first contour data is mapped to the coordinate system of the CT image, and a binary mask is generated based on the mapping result to determine the target region range corresponding to the target region; For each of the organs at risk, its second contour data is mapped to the coordinate system of the CT image, and a binary mask is generated based on the mapping result to determine the range of the organs at risk corresponding to the organs at risk.

[0008] In some implementations, a target score for each target region is determined based on the dose distribution data and the range of each target region, including: Based on the CT images, the dose distribution data is resampled. For each target region, target region DVH data is generated based on its corresponding target region range and the dose distribution data after resampling. Based on the preset target area prescription dose and the target area DVH data, the cold spot area and hot spot area are determined; The cold spot area and the hot spot area are normalized respectively, and the normalized cold spot area and hot spot area are mapped to cold spot sub-score and hot spot sub-score respectively according to the cold spot tolerance threshold and the hot spot tolerance threshold. The sum of the cold spot score and the hot spot score is taken as the target area score.

[0009] In some implementations, the cold spot area and hot spot area are determined based on a preset target area prescription dose and the target area DVH data, including: Based on the preset target area prescription dose, determine the target dose value and the upper limit of the dose; The target region DVH data are standardized; The cold spot area is obtained by performing an integral calculation based on the standardized target area DVH data and the target dose value; The hot spot area is obtained by performing an integral operation based on the standardized target area DVH data, the upper dose limit, and the target dose value.

[0010] In some implementations, an organ score is determined for each organ at risk based on the dose distribution data and the range of each organ at risk, including: For each organ at risk, organ DVH data is generated based on the corresponding organ at risk range and the dose distribution data after resampling. Based on the organ type corresponding to the endangered organ, determine the preset safety upper limit curve corresponding to the endangered organ; Based on the preset safety upper limit curve and the organ DVH data, the dose excess area is determined; The dose excess area is normalized, and the normalized dose excess area is mapped to the organ score based on the organ tolerance threshold corresponding to the organ.

[0011] In some implementations, a preset safety upper limit curve corresponding to the organ at risk is determined based on the organ type corresponding to the organ at risk, including: If the organ type is a serial organ, obtain the organ dose threshold corresponding to the endangered organ, and construct a step function with the organ dose threshold as the boundary as the preset safety upper limit curve; If the organ type is a parallel organ, obtain several dose-volume threshold pairs corresponding to the organ at risk, and fit all the threshold points based on a preset interpolation algorithm, and use the fitting result as the preset safety upper limit curve.

[0012] In some implementations, a planned total score is obtained and a scoring report is output based on the scores of all said target areas and all said organs, including: The total target score is obtained by multiplying the score of each target region by a preset weighting coefficient and then summing the results. Sum the scores of each organ to obtain the total organ score; The total score of the target area is summed with the total score of the organ to obtain the total planned score of the radiotherapy plan. The scoring report is generated and output based on each target region and its score, each organ at risk and its score, and the total planned score.

[0013] Another aspect of the present invention provides a radiotherapy planning scoring system, comprising: The acquisition unit is configured to acquire CT images, dose distribution data, and structural delineation files from the radiotherapy plan to be evaluated. The mask generation unit is configured to determine the extent of each target region and the extent of each organ at risk based on the structure drawing file and the CT image; The target scoring unit is configured to determine the target score for each target region based on the dose distribution data and the range of each target region. An organ scoring unit is configured to determine an organ score for each organ at risk based on the dose distribution data and the range of each organ at risk. The total score unit is configured to obtain a planned total score and output a score report based on the scores of all said target areas and all said organs.

[0014] In another aspect of the present invention, a computer device is provided, comprising: at least one processor; and a memory storing a computer program executable on the processor, the computer program performing the steps of the method described above when executed by the processor.

[0015] In another aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method steps.

[0016] The present invention has at least the following beneficial technical effects: The radiotherapy plan scoring method and system of the present invention, by standardizing image data, dose distribution data, structural delineation data, and dose-volume histogram data under a unified spatial benchmark, and constructing differentiated quantitative scoring mechanisms for the target area and organs at risk respectively, achieves simultaneous and objective assessment of the adequacy and safety of radiotherapy plans. Furthermore, by transforming the degree of deviation of target area dose coverage from safety constraints, dose exceeding limits, and dose-volume distribution of organs at risk into calculable and comparable scoring results, the present invention provides a consistent quantitative evaluation benchmark and reproducible ranking basis for different radiotherapy plans. This overcomes the problems of strong subjectivity and difficulty in horizontal comparison in traditional manual experience-based assessments, providing stable and reliable technical support for radiotherapy plan quality review and optimization decisions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0018] Figure 1A block diagram of an embodiment of the radiotherapy planning scoring method provided by the present invention; Figure 2 This is a schematic diagram of an embodiment of the general processing procedure for the radiotherapy planning scoring method provided by the present invention; Figure 3 A schematic diagram illustrating an embodiment of the radiotherapy planning scoring method provided by the present invention applied to lung cancer; Figure 4 This is a schematic diagram of an embodiment comparing the radiotherapy planning scoring method provided by the present invention with a clinical reference method; Figure 5 A schematic diagram of an embodiment of the radiotherapy planning and scoring system provided by the present invention; Figure 6 A schematic diagram of the structure of an embodiment of the computer device provided by the present invention; Figure 7 This is a schematic diagram of an embodiment of the computer-readable storage medium provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to specific examples and the accompanying drawings.

[0020] It should be noted that all uses of "first" and "second" in the embodiments of the present invention are for the purpose of distinguishing two entities or parameters with the same name but different names. It is clear that "first" and "second" are only for the convenience of expression and should not be construed as limiting the embodiments of the present invention. Subsequent embodiments will not explain this in detail.

[0021] To achieve the above objectives, this invention proposes a mathematically interpretable radiotherapy plan scoring method applicable to various types of tumor radiotherapy plans. Through data preprocessing, target volume and organ-at-risk scoring calculations, and comprehensive score output, it achieves objective, quantifiable, and efficient evaluation of radiotherapy plan quality, outputting mathematically interpretable and clinically validated scoring results to support quality control and optimization decisions in clinical radiotherapy planning.

[0022] like Figure 1 As shown, the radiotherapy plan scoring method includes the following steps: Step S100: Obtain CT (Computed Tomography) images, dose distribution data, and structural delineation files from the radiotherapy plan to be evaluated; Step S200: Based on the structural delineation file and CT images, determine the extent of each target area and the extent of each organ at risk; Step S300: Based on the dose distribution data and the range of each target area, determine the target area score for each target area; Step S400: Based on the dose distribution data and the extent of each organ at risk, determine the organ score for each organ at risk; Step S500: Based on the scores of all target areas and all organs, obtain the total planned score and output a scoring report.

[0023] It should be noted that the radiotherapy planning data to be evaluated is usually stored in medical digital imaging and communication standard formats, including CT image sequences, dose files, structural delineation files, and DVH (Dose-Volume Histogram) datasets in CSV (Comma-Separated Values) format.

[0024] CT images provide a spatial reference for the patient's anatomy. Dose distribution data characterizes the dose allocation of the radiotherapy plan in three-dimensional space and is typically stored in DICOM RT-Dose format. Structural delineation files identify the spatial location of the target area and organs at risk in the CT images. These files are obtained by physicians or physicists delineating the outlines of the defined target area and organs at risk on the CT images and are typically stored in DICOM RT-Structure format. To ensure consistency in subsequent calculations, CT images, dose distribution data, and structural delineation files are registered in the same spatial coordinate system, establishing spatial relationships between data from different sources. Target areas include tumor regions, and organs at risk include the spinal cord, lungs, heart, and esophagus.

[0025] The radiotherapy planning scoring method of this invention, through dose-volume distribution modeling under a unified spatial benchmark, transforms target dose coverage and organ-at-risk dose safety into calculable quantitative scoring results, and further generates a unified total plan score. This achieves a reproducible and comparable objective evaluation process for radiotherapy plan quality. It can output mathematically interpretable and clinically validated scoring results, supporting quality control and optimization decisions in clinical radiotherapy planning.

[0026] In some implementations, determining the extent of each target region and the extent of each organ at risk based on the structural delineation file and CT images includes: parsing first contour data of each target region and second contour data of each organ at risk from the structural delineation file; for each target region, mapping its first contour data to the coordinate system of the CT image, and generating a binary mask based on the mapping result to determine the target region extent corresponding to the target region; for each organ at risk, mapping its second contour data to the coordinate system of the CT image, and generating a binary mask based on the mapping result to determine the organ at risk extent corresponding to the organ at risk.

[0027] It should be noted that the first contour data is a three-dimensional spatial point sequence of the target area in the CT image, and the second contour data represents a three-dimensional spatial point sequence of the organs at risk in the CT image. The first and second contour data are in the same or mappable coordinate system as the CT image. By performing coordinate transformation on the contour data, the first or second contour data is uniformly mapped to the coordinate system of the CT image, thereby ensuring that subsequent spatial constraints and dose statistics are performed under the same spatial reference.

[0028] For each target region, its first contour data is mapped to the coordinate system of the CT image. Then, a binary mask is generated in the voxel space of the CT image based on the mapped contour boundary. Voxels located within the target region contour boundary are marked as valid voxels, while those outside the boundary are marked as invalid voxels, thus obtaining the corresponding target region range. The target region range is used to define the spatial area involved in subsequent dose distribution data for target dose volume distribution statistics and target region scoring calculations.

[0029] For each organ at risk, its second contour data is mapped to the coordinate system of the CT image. A binary mask is then generated in the voxel space of the CT image based on the mapped contour boundaries. Voxels located within the contour boundaries of the organ at risk are marked as valid voxels, while those outside are marked as invalid voxels, thus obtaining the corresponding organ at risk extent. This organ at risk extent is used to define the spatial region involved in subsequent dose distribution data for dose volume distribution statistics and organ score calculation.

[0030] In summary, by parsing, spatially mapping, and generating binary masks from the contour data in the structural delineation file, a spatial correspondence between the target area and the range of organs at risk and CT images and dose distribution data was established, providing a unified and reproducible spatial constraint basis for the subsequent calculation of target area scores and organ scores.

[0031] In some implementations, such as Figure 2As shown, based on dose distribution data and the range of each target area, the target area score for each target area is determined, including: resampling the dose distribution data according to the CT image; generating target area DVH data for each target area based on its corresponding target area range and the resampling dose distribution data; determining the cold spot area and hot spot area based on the preset target area prescription dose and target area DVH data; normalizing the cold spot area and hot spot area respectively, and mapping the normalized cold spot area and hot spot area to cold spot sub-score and hot spot score respectively according to the cold spot tolerance threshold and hot spot tolerance threshold; and using the sum of the cold spot score and hot spot score as the target area score. The determination of cold spot area and hot spot area based on preset target area prescription dose and target area DVH data includes: determining the target dose value and dose limit value according to the preset target area prescription dose; standardizing the target area DVH data; performing integral calculation based on the standardized target area DVH data and target dose value to obtain the cold spot area; and performing integral calculation based on the standardized target area DVH data, dose limit value and target dose value to obtain the hot spot area.

[0032] It's important to note that resampling is used to adjust the dose distribution data to a spatial resolution and voxel grid consistent with the CT image. This ensures that data from different sources have consistent voxel sizes and alignment within the same spatial coordinate system, thus avoiding spatial deviations during subsequent spatial constraints and volumetric statistics based on the target area. For example, by performing linear interpolation on the dose distribution data, dose values ​​are redistributed to voxel positions that correspond one-to-one with the voxels in the CT image, resulting in resampled dose distribution data that is spatially consistent with the CT image. This can be achieved using ResampleImageFilter (a core class for medical image resampling) in SimpleITK (an open-source image analysis toolkit).

[0033] After completing the spatial alignment of the dose data, target region DVH data can be generated for each target region. The target region DVH data is used to describe the volume distribution corresponding to different dose levels within the target region. It is constructed by: statistically analyzing the proportion of voxels corresponding to each dose interval within the set of voxels defined by the target region, and forming a correspondence between dose and volume.

[0034] After generating the target area DVH data, the data is standardized to convert the volume distribution from absolute volume to a relative volume percentage. This eliminates the influence of volume differences between different target areas on the scoring results, thereby improving the comparability of target area scores between different target areas. The standardization is achieved by converting the relative volume to a percentage using the formula "Relative volume = Actual volume / Maximum volume × 100%" and sorting the dose array to ensure monotonically increasing values. Here, "Actual volume" refers to the absolute physical volume accumulated in the target area at or below the corresponding dose value, and "Maximum volume" is the total volume segmented from the target area in the CT image.

[0035] The target dose and upper dose limit specified in the radiotherapy plan for the target area are obtained. Dose volume distribution data segments below the target prescribed dose are designated as data segments corresponding to areas of insufficient dose coverage, while those above the target prescribed dose but below the upper dose limit are designated as data segments corresponding to areas of excessive dose. Integral operations are performed on the data segments corresponding to the insufficient dose coverage areas and the data segments corresponding to the excessive dose areas to obtain the cold spot area characterizing the degree of insufficient dose coverage and the hot spot area characterizing the degree of excessive dose.

[0036] The formula for calculating the area of ​​a cold spot is as follows: ; In the formula, The area of ​​the cold spot. The target dose. This represents the relative volume of the target area receiving a dose ≥ d, with a value ranging from 0 to 1. For example, 0.7 represents 70% of the target volume receiving a dose ≥ d. represents the relative volume of the target region where the received dose is less than d. Use max to ensure the result is non-negative.

[0037] The formula for calculating the hot spot area is as follows: ; In the formula, For the area of ​​the hot spot, This is the upper limit of the dosage.

[0038] The cold spot area and hot spot area are normalized separately, as shown in the following expressions: ; In the formula, The normalized cold spot area, This represents the normalized area of ​​the hot spot. This is the maximum dose in the target area, which is the highest dose value among all points within the target area.

[0039] Based on the cold spot tolerance threshold and the hot spot tolerance threshold, the normalized cold spot area and hot spot area are mapped to cold spot sub-score and hot spot score, respectively. The cold spot tolerance threshold and the hot spot tolerance threshold are used to characterize the clinically acceptable dose deviation and serve as reference benchmarks for the mapping rules between cold spot sub-score and hot spot score.

[0040] The expression for the cold spot score is as follows: ; In the formula, Score for cold spots. The cold spot weight can be preset to... . The maximum score for the target area can be preset to... . The cold spot tolerance threshold can be preset to [value]. .

[0041] The expression for the hot spot score is as follows: ; In the formula, This represents the score for hotspots. The hotspot tolerance threshold can be preset to [value]. .

[0042] The sum of the cold spot score and the hot spot score is taken as the target area score for the corresponding target region, which is used to comprehensively characterize the overall quality level of the target region in terms of dose coverage adequacy and dose escalation control. The expression for the target area score is as follows: ; In the formula, Score the target area.

[0043] In summary, by spatially constraining the target area range with the resampled dose distribution data, and combining the prescription dose interval with piecewise integration and normalization mapping of the target area dose volume distribution, a unified quantitative evaluation of the degree of insufficient target area dose coverage and dose exceeding the limit is achieved, thereby forming comparable and reproducible target area score results.

[0044] In some implementations, such as Figure 2As shown, based on dose distribution data and the range of each endangered organ, the organ score for each endangered organ is determined, including: for each endangered organ, generating organ DVH data corresponding to the endangered organ based on its corresponding endangered organ range and resampled dose distribution data; determining the preset safety upper limit curve corresponding to the endangered organ according to the organ type; determining the dose excess area based on the preset safety upper limit curve and organ DVH data; normalizing the dose excess area and mapping the normalized dose excess area to the organ score according to the organ tolerance threshold corresponding to the organ. Specifically, determining the preset safety upper limit curve corresponding to the endangered organ according to the organ type includes: if the organ type is a serial organ, obtaining the organ dose threshold corresponding to the endangered organ and constructing a step function with the organ dose threshold as the boundary as the preset safety upper limit curve; if the organ type is a parallel organ, obtaining several dose-volume threshold pairs corresponding to the endangered organ and fitting all threshold points based on a preset interpolation algorithm, using the fitting result as the preset safety upper limit curve.

[0045] Organ DVH data is generated for each organ at risk. Organ DVH data describes the volume distribution at different dose levels within the organ at risk. Specifically, organ DVH data is generated by statistically analyzing the volume distribution at different dose levels within a set of voxels defined by the organ at risk. After generating the organ DVH data, it is standardized using the same process as for target area DVH data, which will not be described further here.

[0046] Based on clinical dose tolerance characteristics, organs at risk are classified into two categories: sequential organs and parallel organs. Sequential organs are those that are dose-sensitive, where exceeding the local dose limit could lead to serious complications, such as the spinal cord and esophagus. Parallel organs are those where local dose exceeding the limit is partially tolerable and overall function is less affected, such as the lungs and heart. Pre-defined safety upper limit curves are constructed for the two categories of organs using different methods. These pre-defined safety upper limit curves describe the maximum acceptable dose limit constraints for organs at risk under different volume percentages.

[0047] The following uses the spinal cord and esophagus as examples to illustrate the process of constructing the safety upper limit curve for sequential organs: (1) Spinal cord: Based on the clinical safe dose standard (QUANTEC guidelines), the upper limit of safe dose (i.e., organ dose threshold) is set at 45.0 Gy, and the formula for the upper limit of safe dose curve is as follows: , In the formula, For the spinal cord at dose The safe volume percentage is calculated using a step function, which means that 100% of the volume is allowed to be irradiated when the dose is ≤45.0Gy, and no volume is allowed to be irradiated when the dose exceeds 45.0Gy, reflecting the strict protection of organs in series. (2) Esophagus: Based on the clinical safe dose standard (QUANTEC guidelines), the upper limit of safe dose (i.e., organ dose threshold) is set at 56.0 Gy, and the formula for the upper limit of safe dose curve is as follows: , In the formula, For esophagus in dose The safe volume ratio below is consistent with the logic of the spinal cord, avoiding irradiation of the esophagus beyond the safe dose.

[0048] The following uses the lungs and heart as examples to illustrate the process of constructing the safety upper limit curve for parallel organs: (1) Lungs: Based on the dose-volume safety threshold groups in the QUANTEC guidelines, such as [(0.0,1.0), (5.0,0.50), (10.0,0.40), (20.0,0.20), (30.0,0.15),(40.0,0.10)], where the first value in each dose-volume threshold pair is the dose, and the second value is the safe volume percentage at the corresponding dose. Continuous safety upper limit curves are constructed using a cubic spline interpolation function (i.e., a preset interpolation algorithm). This ensures the curve is smooth and closely matches clinical safety requirements for different dose ranges in the lungs. The cubic spline interpolation function is expressed as follows: ( ∈[ , ], In the formula, i is the index of the dose-volume safety threshold group; (2) Heart: Based on the dose-volume safety threshold groups in the QUANTEC guidelines, such as [(0.0,1.0), (25.0,0.10), (30.0,0.30), (40.0,0.050)], the upper limit safety curve was constructed using the same cubic spline interpolation method as for the lungs. This reflects the heart's moderate tolerance to low and medium doses and the strict limitation of high doses.

[0049] The organ dose-volume histogram data is aligned and compared with the preset safety upper limit curves corresponding to each organ at risk. The dose-volume distribution data segments in the organ dose-volume histogram data that exceed the constraint range of the preset safety upper limit curve are identified. The data segments that exceed the constraint range are then integrated to obtain the dose excess area that characterizes the degree of dose exceeding the limit of the organ at risk.

[0050] Taking the heart as an example, the formula for calculating the area under the safety upper limit curve corresponding to the heart is as follows: ; In the formula, This represents the area under the safety upper limit curve corresponding to the heart.

[0051] Furthermore, the formula for calculating the excess dose area is as follows: ; In the formula, The excess area corresponding to the heart dose.

[0052] The excess area is normalized as shown in the following expression: ; In the formula, This represents the dose excess area corresponding to the heart after normalization.

[0053] The formula for calculating organ scores is as follows: ; In the formula, The organ corresponding to the heart is scored. To minimize the impact on the maximum score of organs, such as the heart, the maximum score can be preset to [value]. =3.0, the maximum lung score can be preset to 3.0. The maximum score for the spinal cord can be preset to... The maximum score for the esophagus can be preset to 1. . To mitigate the impact on organ tolerance thresholds, such as the heart tolerance threshold, a preset threshold can be established. The lung tolerance threshold can be preset to 1. The spinal cord tolerance threshold can be preset to 1. The esophageal tolerance threshold can be preset to 1. .

[0054] In summary, by constructing organ DVH data within the scope of organs at risk and combining it with dose-volume safety upper limit curves corresponding to different organ types, the degree to which the actual dose-volume distribution exceeds the safety constraints is integrally quantified and normalized, thus achieving a unified quantitative evaluation of the radiation safety of organs at risk and generating comparable and reproducible organ scores.

[0055] In some implementations, such as Figure 2As shown, based on the scores of all target areas and all organs, the total planned score is obtained and a scoring report is output, including: multiplying the score of each target area by a preset weighting coefficient and summing the results to obtain the total target area score; summing the scores of each organ to obtain the total organ score; summing the total target area score and the total organ score to obtain the total planned score of the radiotherapy plan; and generating and outputting a scoring report based on each target area and its score, each organ at risk and its score, and the total planned score.

[0056] It should be noted that the preset weighting coefficients are used to reflect the differences in the relative importance of different target areas within the overall treatment goal. Their setting can be based on factors such as the clinical priority of the target area, differences in lesion type, or differences in treatment goals, thereby enabling the total target area score to more accurately reflect the overall level of treatment adequacy. The preset weighting coefficients are configured by the user or generated by preset rules during the initialization phase and remain consistent throughout the same radiotherapy plan scoring process to ensure the comparability of total plan scores between different radiotherapy plans. If both high-dose and low-dose target areas exist simultaneously, a weighted sum is used to obtain the total target area score for multiple target areas.

[0057] Organ scores are used to characterize the radiation risk level of each endangered organ under the current radiotherapy plan. By summing the organ scores of each endangered organ, the total organ score can be obtained, which can form a comprehensive quantitative evaluation result of the overall treatment safety.

[0058] The overall plan score comprehensively reflects the overall quality level of the radiotherapy plan in terms of both treatment adequacy and safety. The scoring report can present the name of each target area and its corresponding target area score, the name of each organ at risk and its corresponding organ score in a structured data format, and simultaneously display the overall plan score. This helps users quickly locate specific structures in the radiotherapy plan that have insufficient dose coverage or organ dose exceeding the limit risk.

[0059] In summary, by weighting and summing the target area scores and organ scores, a unified total plan score was constructed and output in the form of a scoring report, providing an intuitive and comparable quantitative expression of results for the quality assessment and optimization of radiotherapy plans.

[0060] In some embodiments, the application of the radiotherapy planning scoring method of the present invention to the processing of lung cancer cases is shown as follows. Figure 3 As shown. (Through) Figure 3 The processing can simultaneously quantify the adequacy of target dose coverage for lung cancer and the safety of organs at risk of radiation exposure, and output the results in a unified scoring format, thereby improving the objectivity and comparability of radiotherapy plan quality assessment.

[0061] In some implementations, taking the Clinical Standard Diagnosis and Evaluation (DDM) scoring method for lung cancer as an example, the target volume scoring rules of the DDM scoring method are shown in Table 1. The organ at risk scoring rules of the DDM scoring method are shown in Table 2.

[0062] Table 1

[0063] Table 2

[0064] To verify the effectiveness of the radiotherapy planning scoring method of this invention, 20 real clinical cases of lung cancer radiotherapy were selected. All cases included complete CT image sequences, dose distribution files, structural delineation files, and DVH data stored in CSV format. This method was applied to conduct a scoring experiment. All data used in the experiment were anonymized to protect patient privacy.

[0065] For each case, the scoring process was strictly performed according to the method described above. To evaluate the clinical rationality of the scoring results of this method, the total scores (denoted as AUC scores) calculated using this method for 20 cases were compared with the results (denoted as DDM scores) of the traditional assessment methods used clinically, as shown in Tables 1 and 2. Statistical correlation analysis was performed on the two groups of scores. The calculated Spearman rank correlation coefficient was used. Kendall rank correlation coefficient Both correlation coefficients reached statistical significance. This result indicates that the scoring results of this method are in good agreement with those of the traditional DDM method in terms of case ranking and overall trend. Furthermore, a scatter plot was plotted with the DDM score on the horizontal axis and the AUC score of this method on the vertical axis, as shown in the attached figure. Figure 4 As shown, the data points are concentrated, and the linear fitting trend line shows a stable upward trend, which further intuitively verifies that there is a positive correspondence between the two scoring results.

[0066] In summary, the radiotherapy plan scoring method provided by this invention exhibits significant consistency with traditional clinical assessment methods, effectively reflecting differences in radiotherapy plan quality. Furthermore, based on a standardized mathematical process, this method achieves objectivity, quantification, and interpretability in the assessment process, serving as a reliable tool for assisting in the evaluation of radiotherapy plan quality.

[0067] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 5 As shown, embodiments of the present invention also provide a radiotherapy planning scoring system, comprising: Acquisition unit 110 is configured to acquire CT images, dose distribution data and structural delineation files from the radiotherapy plan to be evaluated; The mask generation unit 120 is configured to determine the extent of each target area and the extent of each organ at risk based on the structural delineation file and CT image. The target scoring unit 130 is configured to determine the target score for each target region based on dose distribution data and the range of each target region. Organ scoring unit 140 is configured to determine the organ score for each organ at risk based on dose distribution data and the range of each organ at risk; The total score unit 150 is configured to obtain the planned total score and output a score report based on the scores of all target areas and all organs.

[0068] The radiotherapy planning scoring system of this invention achieves simultaneous and objective assessment of the adequacy and safety of radiotherapy plans by standardizing image data, dose distribution data, structural delineation data, and dose-volume histogram data under a unified spatial benchmark, and by constructing differentiated quantitative scoring mechanisms for the target area and organs at risk. Furthermore, by converting the degree of deviation of target area dose coverage, dose exceedance, and dose-volume distribution of organs at risk from safety constraints into calculable and comparable scoring results, it provides a consistent quantitative evaluation benchmark and reproducible ranking criteria for different radiotherapy plans. This overcomes the problems of strong subjectivity and difficulty in cross-comparison of traditional manual experience-based assessments, providing stable and reliable technical support for radiotherapy plan quality review and optimization decisions.

[0069] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 6 As shown, an embodiment of the present invention also provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, it performs the steps of the method described above.

[0070] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 7 As shown, embodiments of the present invention also provide a computer-readable storage medium 40, which stores a computer program 410 that, when executed by a processor, performs the methods described above.

[0071] Finally, it should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium for the program can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The above computer program embodiments can achieve the same or similar effects as any of the corresponding foregoing method embodiments.

[0072] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the functionality of various illustrative components, blocks, modules, circuits, and steps has been generally described. Whether this functionality is implemented as software or as hardware depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the embodiments disclosed herein.

[0073] The above are exemplary embodiments disclosed in this invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments of this invention as defined by the claims. The functions, steps, and / or actions of the methods according to the disclosed embodiments described herein do not need to be performed in any particular order. The sequence numbers of the disclosed embodiments of this invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. Furthermore, although the elements disclosed in the embodiments of this invention may be described or claimed individually, they may be understood as multiple unless explicitly limited to a singular number.

[0074] It should be understood that, as used herein, the singular form “a” is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, “and / or” refers to any and all possible combinations of one or more of the associated listed items.

[0075] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A method for scoring radiotherapy plans, characterized in that, include: Obtain CT images, dose distribution data, and structural delineation files from the radiotherapy plan to be evaluated; Based on the structural delineation file and the CT images, determine the extent of each target region and the extent of each organ at risk; Based on the dose distribution data and the range of each target region, a target region score is determined for each target region; Based on the dose distribution data and the range of each organ at risk, an organ score is determined for each organ at risk; Based on the scores of all the target areas and all the organs, the total planned score is obtained and a scoring report is output.

2. The radiotherapy planning scoring method according to claim 1, characterized in that, Based on the structural delineation file and the CT images, determine the extent of each target region and the extent of each organ at risk, including: The first contour data of each target region and the second contour data of each organ at risk are parsed from the structure delineation file; For each target region, its first contour data is mapped to the coordinate system of the CT image, and a binary mask is generated based on the mapping result to determine the target region range corresponding to the target region; For each of the organs at risk, its second contour data is mapped to the coordinate system of the CT image, and a binary mask is generated based on the mapping result to determine the range of the organs at risk corresponding to the organs at risk.

3. The radiotherapy planning scoring method according to claim 1, characterized in that, Based on the dose distribution data and the range of each target region, a target region score is determined for each target region, including: Based on the CT images, the dose distribution data is resampled. For each target region, target region DVH data is generated based on its corresponding target region range and the dose distribution data after resampling. Based on the preset target area prescription dose and the target area DVH data, the cold spot area and hot spot area are determined; The cold spot area and the hot spot area are normalized respectively, and the normalized cold spot area and hot spot area are mapped to cold spot sub-score and hot spot sub-score respectively according to the cold spot tolerance threshold and the hot spot tolerance threshold. The sum of the cold spot score and the hot spot score is taken as the target area score.

4. The radiotherapy planning scoring method according to claim 3, characterized in that, Based on the preset target area prescription dose and the target area DVH data, the cold spot area and hot spot area are determined, including: Based on the preset target area prescription dose, determine the target dose value and the upper limit of the dose; The target region DVH data are standardized; The cold spot area is obtained by performing an integral calculation based on the standardized target area DVH data and the target dose value; The hot spot area is obtained by performing an integral operation based on the standardized target area DVH data, the upper dose limit, and the target dose value.

5. The radiotherapy planning scoring method according to claim 3, characterized in that, Based on the dose distribution data and the extent of each organ at risk, an organ score is determined for each organ at risk, including: For each organ at risk, organ DVH data is generated based on the corresponding organ at risk range and the dose distribution data after resampling. Based on the organ type corresponding to the endangered organ, determine the preset safety upper limit curve corresponding to the endangered organ; Based on the preset safety upper limit curve and the organ DVH data, the dose excess area is determined; The dose excess area is normalized, and the normalized dose excess area is mapped to the organ score based on the organ tolerance threshold corresponding to the organ.

6. The radiotherapy planning scoring method according to claim 5, characterized in that, Based on the organ type corresponding to the endangered organ, a preset safety upper limit curve corresponding to the endangered organ is determined, including: If the organ type is a serial organ, obtain the organ dose threshold corresponding to the endangered organ, and construct a step function with the organ dose threshold as the boundary as the preset safety upper limit curve; If the organ type is a parallel organ, obtain several dose-volume threshold pairs corresponding to the organ at risk, and fit all the threshold points based on a preset interpolation algorithm, and use the fitting result as the preset safety upper limit curve.

7. The radiotherapy planning scoring method according to claim 1, characterized in that, Based on the scores of all described target areas and all described organs, a total planned score is obtained and a scoring report is output, including: The total target score is obtained by multiplying the score of each target region by a preset weighting coefficient and then summing the results. Sum the scores of each organ to obtain the total organ score; The total score of the target area is summed with the total score of the organ to obtain the total planned score of the radiotherapy plan. The scoring report is generated and output based on each target region and its score, each organ at risk and its score, and the total planned score.

8. A radiotherapy planning and scoring system, characterized in that, include: The acquisition unit is configured to acquire CT images, dose distribution data, and structural delineation files from the radiotherapy plan to be evaluated. The mask generation unit is configured to determine the extent of each target region and the extent of each organ at risk based on the structure drawing file and the CT image; The target scoring unit is configured to determine the target score for each target region based on the dose distribution data and the range of each target region. An organ scoring unit is configured to determine an organ score for each organ at risk based on the dose distribution data and the range of each organ at risk. The total score unit is configured to obtain a planned total score and output a score report based on the scores of all said target areas and all said organs.

9. A computer device, comprising: At least one processor; as well as A memory storing a computer program executable on the processor, characterized in that the processor executes the program by performing the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it performs the steps of the method as described in any one of claims 1 to 7.

Images