Methods, devices, and equipment for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis.

Abstract

This invention discloses a method, device, and equipment for evaluating dose limits for organs at risk in tumor radiotherapy planning based on spatial distance analysis, relating to the field of tumor radiotherapy technology. Specifically, based solely on geometric statistics, before dose calculation, a three-dimensional Euclidean distance transformation is used to obtain the shortest distance distribution from all voxels of the organs at risk to the target area after anisotropic normalization, directly forming an individualized dose limit and weight template. The output of this invention is a distance-voxel histogram and its derived cumulative proportions and rates of change, from which several geometric indicators are extracted. Combined with a preset set of geometric rules, individualized suggestions for dose limit thresholds and optimization weights corresponding to different doses are directly obtained. Compared with existing technologies, this invention does not perform dose prediction, nor does it require generating auxiliary contours or performing forward / backward dose calculations. Instead, it provides individualized and executable dose limit and weight suggestions before dose calculation, significantly reducing optimization iterations and improving consistency, with highly interpretable results.

Description

Technical Field

[0001] This invention relates to the field of tumor radiotherapy technology, and in particular to a method, apparatus and equipment for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis. Background Technology

[0002] Radiotherapy planning typically relies on post-dose metrics such as dose-volume histograms (DVH) for evaluation and iterative optimization. However, this method requires dose calculation before obtaining the DVH, and the DVH cannot directly reflect the three-dimensional spatial relationship between the target area and the organ at risk (OAR). Furthermore, it is difficult to provide quantitative guidance before planning for individualized dose limits caused by structural differences in different patients, resulting in numerous optimization iterations and impacting the timeliness and consistency of the plan. Summary of the Invention

[0003] In view of the above, the present invention aims to provide a method, device and equipment for evaluating the dose limit of organs at risk in tumor radiotherapy planning based on spatial distance analysis. Specifically, it relates to a scheme that, without relying on dose calculation, performs quantitative analysis based on the geometric spatial relationship between the target area and the organs at risk, thereby providing individualized guidance for the dose limit and optimization weight of organs at risk, in order to solve the specific problems mentioned above.

[0004] The technical solution adopted in this invention is as follows:

[0005] In a first aspect, the present invention provides a method for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis, comprising:

[0006] Step S1: Import the localization CT sequence, target area delineation structure, and DICOM data of organs at risk delineation structure;

[0007] Step S2: Without dose calculation, perform a three-dimensional Euclidean distance transformation on the data after normalizing the anisotropic voxel spacing to obtain the shortest spatial distance Di from each voxel of the organ at risk to the target area delineation structure. When the voxel of the organ at risk overlaps with the target area, Di is taken as 0.

[0008] Step S3: Repeat step S2 for all n voxels of the organs at risk to obtain a distance sequence, and take the maximum value Dmax of the shortest distance from it;

[0009] Step S4: Adaptively divide the data into segments according to the interval [0, Dmax], with the number of segments m≥10 and the segment width being Dmax / m, or determine the segment width according to the Freedman–Diaconis criterion.

[0010] Step S5: Count the number of voxels in each grade interval, draw a distance-voxel histogram, and calculate the cumulative percentage curve and the rate of change curve; furthermore, the distance-voxel histogram includes three modes: absolute quantity histogram, relative percentage histogram, and cumulative distribution curve.

[0011] Step S6: Based on the preset geometric rule set, according to the geometric indicators, cumulative proportion curve and rate of change curve in the histogram, generate individualized adjustment suggestions for the limit thresholds and optimization weights for different doses that endanger organs.

[0012] Step S7: Output the adjustment suggestions, which are used to set limit thresholds or target weights before the plan is optimized.

[0013] In at least one of the possible implementations, the shortest spatial distance is obtained by traversing and calculating the shortest Euclidean distance from the i-th voxel of the endangered organ to the target mask and taking the minimum value, or by looking up the distance transformation result in a table.

[0014] In at least one of the possible implementations, the binning employs a near-target subdivision strategy: using a subdivision width smaller than the global binning width within the range r ≤ d0.

[0015] In at least one possible implementation, the cumulative percentage curve is smoothed and its derivative is taken to obtain the rate of change curve, wherein the smoothing process is Savitzky-Golay filtering or spline smoothing.

[0016] In at least one possible implementation, the geometric indices include at least Pδ=C(δ), quantiles d5%, d25%, d50%, d75%, d95%, and the peak position and peak value of the rate of change k(r). Therefore, further, a distance crowding index DCI=∑exp(−β·ci)·Pi can be constructed, where ci is the center of the i-th quantile, Pi is the relative proportion, and β∈[0.2,1.0]. When DCI exceeds a threshold, stricter adjustment recommendations are given for low-dose limits and near-target shell weights. Furthermore, the rule set, based on the magnitude and peak position of Pδ and k(r) within the range of r≤3 mm, provides suggested intervals for the adjustment percentage Δ∈[5%,50%] of {Llow, Lmid, Lhigh} and {Wlow, Wmid, Whigh}, and outputs a shell weight template.

[0017] In at least one of the possible implementations, the distance calculation is accelerated using a KD-tree, an octree nearest neighbor search, or a combination of fast traversal and Euclidean distance transformation; thereafter, the bundle-direction shortest distance d_beam can be calculated.

[0018] As mentioned above, H(r) can represent the distance histogram; C(r) can represent the cumulative proportion; k(r) can represent the rate of change; DCI can represent the distance crowding index; Llow / Lmid / Lhigh can represent the low / medium / high dose limit thresholds respectively; Wlow / Wmid / Whigh can represent the corresponding optimization weights respectively.

[0019] In a second aspect, the present invention provides a device for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis, comprising:

[0020] The data input module is used to import localization CT sequence data, target area delineation structures, and DICOM data of organs at risk delineation structures;

[0021] The voxel distance calculation module is used to perform a three-dimensional Euclidean distance transformation on the above data after normalizing the anisotropic voxel spacing without dose calculation, to obtain the shortest spatial distance Di from each voxel of the organ at risk to the target area delineation structure. When the voxel of the organ at risk overlaps with the target area, Di is taken as 0.

[0022] The voxel distance sorting module is used to repeat step S2 for all n voxels of organs at risk, obtain a distance sequence, and take the maximum value Dmax of the shortest distance from it;

[0023] The grading module is used for adaptive grading according to the interval [0, Dmax]. The number of gradings m≥10 and the grading width is Dmax / m, or the grading width is determined according to the Freedman–Diaconis criterion.

[0024] The plotting module is used to count the number of voxels in each grade interval, draw a distance-voxel histogram, and calculate the cumulative percentage curve to obtain the rate of change curve.

[0025] The geometric analysis module is used to generate individualized adjustment suggestions for limit thresholds and optimization weights for different doses affecting organs, based on a preset set of geometric rules and geometric indicators extracted from histograms, cumulative percentage curves, and rate of change curves.

[0026] The evaluation guidance module is used to output the adjustment suggestions and to set limit thresholds or target weights before the plan is optimized.

[0027] Thirdly, the present invention provides an electronic device comprising: one or more processors, a memory, and one or more computer programs, the memory being a non-volatile storage medium, wherein the one or more computer programs are stored in the memory, the one or more computer programs including instructions that, when executed by the device, cause the electronic device to perform the method as described in the first aspect or any possible implementation thereof.

[0028] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method as described in the first aspect or any possible implementation thereof.

[0029] Fifthly, the present invention also provides a computer program product, which, when executed by a computer, performs the method described in the first aspect or any possible implementation thereof. In one possible design of the fifth aspect, the relevant program involved in the product may be stored wholly or partially on a memory packaged with a processor, or may be stored wholly or partially on a storage medium not packaged with a processor.

[0030] It should be understood that the second to fifth aspects of the embodiments of this application are consistent with the technical solutions of the first aspect of the embodiments of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be described again.

[0031] The main design concept of this invention lies in rapidly and interpretably outputting individualized limits and weight settings that can be directly used in the optimizer, based solely on the geometric relationship between the target area and organs at risk, without dose calculation. This significantly reduces iterations and improves consistency. The main logical chain involves obtaining the shortest distance from the EDT, followed by adaptive grading and outputting histograms, cumulative percentages, and rates of change. Finally, a template is derived using geometric indicators and a rule set. As can be seen, this invention can still provide executable individualized limits even with zero historical cases and no dose calculation. That is, it transforms the task objective from DVH prediction to a limit and weight suggestion generation mechanism driven by geometric statistics, completing the entire process and outputting parameter templates that can be directly called by the TPS without dose calculation.

[0032] While existing technologies have shown a correlation between voxel distance and OAR dose, they still lack: a reproducible implementation path for obtaining the "distance-voxel" statistical characteristics based solely on delineating the structure before dose calculation; a unified approach for anisotropic voxel distances; and an engineered scheme for mapping geometric statistics into "limit threshold / weight adjustment suggestions" that can be directly used for plan optimization.

[0033] In summary, the technical approach of this invention is to obtain the shortest distance distribution from all voxels of the organ at risk to the target area using a three-dimensional Euclidean distance transformation after anisotropic normalization, based solely on geometric statistics, before dose calculation. This directly forms an individualized limit and weight template. Compared with existing technologies, this invention does not perform dose prediction and does not require generating auxiliary contours or performing forward / backward dose calculations. The output of this invention is a distance-voxel histogram and its derived cumulative proportion and rate of change curves. Several geometric indicators are extracted from these curves and combined with a preset set of geometric rules to directly obtain individualized suggestions for limit thresholds and optimization weights corresponding to different doses. Finally, a template / parameter table that can be directly imported can be generated based on this. This invention can obtain individualized and executable limit and weight suggestions before dose calculation, significantly reducing optimization iterations and improving consistency. The results are highly interpretable and decoupled from the system, thus enabling cross-platform portability. Attached Figure Description

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described below with reference to the accompanying drawings, wherein:

[0035] Figure 1 A flowchart illustrating the method for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis, provided in an embodiment of the present invention.

[0036] Figure 2 This is a schematic diagram illustrating the shortest distance Di from the i-th voxel in an organ at risk to the target region, provided in an embodiment of the present invention.

[0037] Figure 3 Example diagrams of different distance-voxel histograms formed by different objects provided in embodiments of the present invention;

[0038] Figure 4 This is a schematic diagram of a tumor radiotherapy planning organ-at-risk limit evaluation device based on spatial distance analysis, provided in an embodiment of the present invention.

[0039] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0040] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0041] This invention proposes an embodiment of a method for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis. Specifically, as follows: Figure 1 and Figure 2As shown, it includes:

[0042] Step S1: Import the localization CT sequence, target area delineation structure, and DICOM data of organs at risk delineation structure;

[0043] Step S2: Without dose calculation, perform a three-dimensional Euclidean distance transformation on the data after normalizing the anisotropic voxel spacing to obtain the shortest spatial distance Di from each voxel of the organ at risk to the target area delineation structure. When the voxel of the organ at risk overlaps with the target area, Di is taken as 0.

[0044] To elaborate, the shortest spatial distance can be obtained by traversing and calculating the shortest Euclidean distance from the i-th voxel of the endangered organ to the target mask and taking the minimum value, or by looking up the distance transformation result in a table.

[0045] Step S3: Repeat step S2 for all n voxels of the organs at risk to obtain a distance sequence, and take the maximum value Dmax of the shortest distance from it;

[0046] Step S4: Adaptively divide the data into segments according to the interval [0, Dmax], with the number of segments m≥10 and the segment width being Dmax / m, or the segment width is determined according to the Freedman–Diaconis criterion; in some preferred embodiments, the segmentation adopts a near-target subdivision strategy: within the range r≤d0, a subdivision width smaller than the global segment width is used.

[0047] Step S5: Count the number of voxels within each tier, plot a distance-voxel histogram, and calculate the cumulative percentage curve and rate of change curve. In practice, the cumulative percentage curve can be smoothed and its derivative can be taken to obtain the rate of change curve. The smoothing process can be Savitzky-Golay filtering or spline smoothing. Therefore, the distance-voxel histogram includes three modes: absolute quantity histogram, relative percentage histogram, and cumulative distribution curve.

[0048] Step S6: Based on the preset geometric rule set, according to the geometric indicators, cumulative proportion curve and rate of change curve in the histogram, generate individualized adjustment suggestions for the limit thresholds and optimization weights for different doses that endanger organs.

[0049] Step S7: Output the adjustment suggestions, which are used to set limit thresholds or target weights before the plan is optimized.

[0050] The aforementioned geometric indices include at least Pδ=C(δ), quantiles d5%, d25%, d50%, d75%, d95%, and the peak position and peak value of the rate of change k(r). Therefore, further, a distance crowding index DCI=∑exp(−β·ci)·Pi can be constructed, where ci is the center of the i-th tier, Pi is the relative proportion, and β∈[0.2,1.0]. When DCI exceeds a threshold, stricter adjustment recommendations are given for low-dose limits and near-target shell weights. Furthermore, based on the magnitude and peak position of Pδ and k(r) within the range of r≤3 mm, the rule set provides suggested intervals for the adjustment percentage Δ∈[5%,50%] of {Llow, Lmid, Lhigh} and {Wlow, Wmid, Whigh}, and outputs a shell weight template.

[0051] The distance calculation method mentioned above can be accelerated by using, but is not limited to, KD-tree, octree nearest neighbor search, or a combination of fast traversal and Euclidean distance transformation; furthermore, the shortest distance d_beam in the beam direction can be calculated.

[0052] Based on the above embodiments, the overall process flow of the method is further described below:

[0053] Step 1: Data Input. Import DICOM RT data, including localization CT sequences, target delineation structures (such as GTV / CTV / PTV), and organ at risk delineation structures (OAR) masks. Read voxel spacing and perform anisotropic normalization; perform topological repair and resampling of structures as necessary.

[0054] Step 2: Distance Calculation. A 3D Euclidean distance transformation is performed on the target mask to obtain a signed or unsigned distance field. For voxels of organs at risk, the shortest distance to the target surface is taken as Di. When a voxel falls inside the target area, Di = 0. To improve efficiency, KD-tree / octree nearest-neighbor search, fast traversal methods, or GPU parallel acceleration can be combined. Optionally, the beam-direction distance d_beam (the shortest distance along the beam direction) can be calculated to distinguish nearest-neighbor voxels related to beam geometry.

[0055] Step 3: Distance Sort. Obtain the distance sequence {D1,…,Dn} for all n voxels of the organs at risk, and set Dmax=max(Di).

[0056] Step 4: Grading. Adaptive grading is performed within the interval [0, Dmax], with the number of gradations m ≥ 10, preferably m = min(100, ⌈Dmax / 1mm⌉), and the grading width is Dmax / m; or the Freedman–Diaconis criterion is used to determine the grading width h = 2·IQR(d) / n^(1 / 3). Near-target subdivision: A smaller grading width is used in the region r ≤ d0 (e.g., 3~5 mm).

[0057] Step 5: Derivation Curves. Statistically calculate the absolute number of voxels Ni and their relative proportion Pi for each segment, generating a histogram H(r). Calculate the cumulative proportion C(r) = ∑H(≤r) / n and the rate of change k(r) = dC(r) / dr. If necessary, use Savitzky-Golay or spline smoothing to handle noise. The curvature κ(r) can be calculated to characterize the points of change in adhesion.

[0058] Step 6: Index Extraction and Generation of Limit and Weight Suggestions. Define Pδ=C(δ), where δ is a clinically common distance threshold such as 1~3 mm; extract quantiles d5%, d25%, d50%, d75%, and d95%; optionally construct the distance crowding index DCI=∑exp(−β·ci)·Pi (ci is the center of the i-th level, β∈[0.2,1.0]) to quantify the degree of near-target crowding; statistically analyze the proportion of the 0–3, 3–7, and 7–10 mm shell layers. Based on rule set R (configurable by location and energy): if P1.0 ≥ T1 and k(r) has a main peak at r ≤ 2 mm, then the low dose limit Low is reduced by Δ1 ∈ [10%, 30%], and the weight of Wlow near the target shell is increased; if P3.0 ≤ T2 and C(5 mm) ≥ T3, then Lmid / Lhigh remains unchanged or is slightly reduced; if DCI ≥ T4 or d25% ≤ 1.5 mm, it is recommended to increase the weight of the mid-to-high dose gradient control or set the minimum / maximum dose-guided dose roll-off in the outer ring; if d75% ≥ 5 mm and the peak value of k(r) > 3 mm, then the low dose limit can be moderately relaxed to ensure coverage.

[0059] Step 7: Output Evaluation Results and Provide Guidance. Output suggested ranges and template files (JSON / CSV or TPS script), including the adjustment percentage Δ for {Llow, Lmid, Lhigh} and {Wlow, Wmid, Whigh}, shell weights, and relevant thresholds. Finally, export the limit and weight parameters to generate a template or script compatible with the treatment planning system. Optional steps include writing parameters into custom tags in the DICOM RT Plan / Protocol.

[0060] In summary, the main design concept of this invention lies in obtaining the shortest distance distribution from all voxels of the organ at risk to the target area using a three-dimensional Euclidean distance transformation after anisotropic normalization, based solely on geometric statistics, before dose calculation. This directly forms an individualized limit and weight template. Compared to existing technologies, this invention does not perform dose prediction and does not require generating auxiliary profiles or performing forward / backward dose calculations. The output of this invention is a distance-voxel histogram and its derived cumulative proportion and rate of change curves. Several geometric indicators are extracted from these curves and combined with a preset set of geometric rules to directly obtain individualized suggestions for limit thresholds and optimization weights corresponding to different doses. Finally, a template / parameter table that can be directly imported can be generated based on this. This invention can obtain individualized and executable limit and weight suggestions before dose calculation, significantly reducing optimization iterations and improving consistency. Furthermore, the results are highly interpretable and decoupled from the system, thus enabling cross-platform portability.

[0061] Finally combined Figure 3 As shown, a radiotherapy example is used for verification: the two cases in the figure have the same prescription and similar volume, but the spatial adhesion between the OAR (small intestine / rectum) and PTV is different; patient A has P1.0=0.35 and the main peak of k(r) is located at 1.5 mm; patient B has P1.0=0.12 and the main peak is located at 3.2 mm. According to the rule set, for A, it is recommended to reduce Llow by 20% and increase the weight of the near-target shell; for B, it is recommended to reduce it only slightly by 10%. Actual planning shows that, according to the above-mentioned recommendations of the present invention, the V15Gy of the small intestine can be reduced by about 6.8% and 3.1% respectively while ensuring PTV coverage, and the number of optimization iterations can be reduced by about 40%.

[0062] Corresponding to the above embodiments and preferred solutions, the present invention also provides an embodiment of a tumor radiotherapy planning organ-at-risk limit assessment device based on spatial distance analysis, such as... Figure 4 As shown, it may specifically include the following components:

[0063] Data input module 201 is used to import localization CT sequence data, target area delineation structure and DICOM data of organ at risk delineation structure;

[0064] The voxel distance calculation module 202 is used to perform a three-dimensional Euclidean distance transformation on the above data after normalizing the anisotropic voxel distance without dose calculation, to obtain the shortest spatial distance Di from each voxel of the organ at risk to the target area delineation structure. When the voxel of the organ at risk overlaps with the target area, Di is taken as 0.

[0065] The voxel distance sorting module 203 is used to repeat step S2 for all n voxels of the organs at risk, obtain the distance sequence, and take the maximum value Dmax of the shortest distance from it;

[0066] The grading module 204 is used for adaptive grading according to the interval [0, Dmax], with the number of gradings m≥10 and the grading width being Dmax / m, or the grading width is determined according to the Freedman–Diaconis criterion.

[0067] The plotting module 205 is used to count the number of voxels in each grade interval, plot a distance-voxel histogram, and calculate the cumulative percentage curve to obtain the rate of change curve.

[0068] The geometric analysis module 206 is used to generate individualized adjustment suggestions for limit thresholds and optimization weights for different doses affecting organs based on a preset set of geometric rules and geometric indicators extracted from histograms, cumulative percentage curves and rate of change curves.

[0069] The evaluation guidance module 207 is used to output the adjustment suggestions and to set the limit threshold or target weight before the plan is optimized.

[0070] In other embodiments of the present invention, another device for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis is also provided, mainly comprising:

[0071] Data input module: Reads CT and structural DICOM data and performs mask preprocessing and resampling;

[0072] Geometric distance calculation module: performs EDT / nearest point search, outputs {Di} and Dmax; optional GPU parallel and beam-direction distance calculation;

[0073] The grading and statistics module includes adaptive and near-target subdivision grading, generating histograms H(r), cumulative curves C(r), rates of change k(r), and quantiles.

[0074] Limited suggestion generation module: Based on the indicator and rule set R, output the adjustment percentage Δ, shell weight and template of {Llow, Lmid, Lhigh} and {Wlow, Wmid, Whigh};

[0075] Display and Export Module: Interactively displays charts and suggestions, and exports templates to the treatment plan system.

[0076] Data flow between modules: 10→20→30→40→50. The system can be deployed on workstations, servers, or in the cloud; it can interface with existing TPS systems via scripts or APIs.

[0077] It should be understood that the division of components in the tumor radiotherapy planning organ-at-risk dose limit evaluation device based on spatial distance analysis mentioned in the above embodiments is only a logical functional division. In actual implementation, all or part of these components can be integrated into a single physical entity, or they can be physically separated. Furthermore, all of these components can be implemented entirely through software calls via processing elements; alternatively, some components can be implemented through software calls via processing elements, while others can be implemented in hardware. For example, a certain module can be a separate processing element or integrated into a chip in an electronic device. The implementation of other components is similar. Moreover, all or part of these components can be integrated together or implemented independently. During implementation, each step of the above method or each of the above components can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0078] For example, these components can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs). Alternatively, these components can be integrated together to form a system-on-a-chip (SOC).

[0079] It should be emphasized again that the evaluation method provided by the present invention may specifically include the following steps: data import, geometric distance calculation, tiered statistics and curve derivation, index extraction, generation of limit and weight suggestions based on the rule set, display and export; wherein the distance calculation adopts voxel anisotropic spacing normalization and three-dimensional Euclidean distance transformation (EDT) or nearest point search acceleration algorithm to obtain the shortest distance Di from each organ at risk voxel to the target area; adaptive tiering within the range of [0, Dmax], counting the number of voxels in each tier, forming a distance-voxel histogram and cumulative proportion curve C(r), and calculating the rate of change k(r)=dC(r) / dr; constructing geometric indices Pδ (shell proportion from the target area 0~δ mm), C(r), k(r), and outputting the up / down percentage range Δ of low / medium / high dose limit thresholds {Llow, Lmid, Lhigh} and target weights {Wlow, Wmid, Whigh} according to the rule set; generating a limit template or parameter table that can be directly imported into the treatment planning system for individualized settings.

[0080] Therefore, this invention also provides a tumor radiotherapy planning system for limiting doses to organs at risk based on spatial distance analysis, including: a data input module, a geometric distance calculation module, a classification and statistics module, a dose limit suggestion generation module, and a display and export module; wherein, the geometric distance calculation module performs a three-dimensional Euclidean distance transformation before dose calculation to obtain the shortest distances Di and Dmax from each voxel of the organ at risk to the target area; the classification and statistics module adaptively classifies according to [0, Dmax], generating a distance-voxel histogram, a cumulative percentage curve, and a rate of change curve; the dose limit suggestion generation module outputs adjustment suggestions for {Llow, Lmid, Lhigh} and {Wlow, Wmid, Whigh} based on geometric indicators and rule sets; the display and export module displays charts and exports suggestions in the form of templates or parameter tables for use by the treatment planning system.

[0081] Furthermore, the system supports near-target subdivision and grading, shell weight template export, and GPU parallel computing. As with the above-described method and device embodiments, the system also supports two modes: drawing separately or merging drawings of a single or multiple organs at risk.

[0082] Based on the above embodiments and preferred solutions, those skilled in the art will understand that, in actual operation, the technical concept involved in this invention can be applied to various implementation methods. The following embodiments are used as illustrative examples:

[0083] (1) An electronic device. The device may specifically include: one or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the steps / functions of the foregoing embodiments or equivalent embodiments.

[0084] Specifically, the electronic device can be a computer-related electronic device, such as, but not limited to, various computing terminals and electronic products.

[0085] Specifically, the processor, communication interface, and memory can all communicate with each other via a communication bus. The processor may be a central processing unit (CPU), DSP, microcontroller, or digital signal processor, and may also include a GPU, an embedded neural network processing unit (NPU), and an image signal processor (ISP). The processor may also include a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. Furthermore, the processor may have the function of operating one or more software programs, which can be stored in a storage medium such as memory. The aforementioned memory / storage medium may include: non-volatile memory, such as a non-removable disk, USB flash drive, portable hard drive, optical disc, etc., as well as read-only memory (ROM), random access memory (RAM), etc.

[0086] Even though the present invention does not limit the specific form of the electronic device, for the purpose of illustrative purposes, it is used as an example. Figure 5 The present invention provides a structural schematic diagram of an embodiment of an electronic device. Specifically, the electronic device 900 includes a processor 910 and a memory 930. The processor 910 and the memory 930 can communicate with each other through an internal connection path to transmit control and / or data signals. The memory 930 is used to store computer programs, and the processor 910 is used to call and run the computer programs from the memory 930. The processor 910 and the memory 930 can be combined into a single processing device, but more commonly they are independent components. The processor 910 executes the program code stored in the memory 930 to achieve the aforementioned functions. In specific implementations, the memory 930 can also be integrated into the processor 910, or it can be independent of the processor 910.

[0087] In addition, to further enhance the functionality of the electronic device 900, it may also include one or more of the following: an input unit 960, a display unit 970, an audio circuit 980, a camera 990, and a sensor 901. The audio circuit may also include a speaker 982, a microphone 984, etc. The display unit 970 may include a display screen.

[0088] Furthermore, the aforementioned electronic device 900 may also include a power supply 950 for providing electrical energy to various devices or circuits in the electronic device 900.

[0089] It should be understood that Figure 5The electronic device 900 shown is capable of implementing the various processes of the method provided in the foregoing embodiments. The operation and / or function of each component in the electronic device 900 can respectively implement the corresponding processes in the above method embodiments. For details, please refer to the foregoing descriptions of the embodiments of methods, devices, etc.; to avoid repetition, detailed descriptions are appropriately omitted here.

[0090] It should be understood that Figure 5 The processor 910 in the illustrated electronic device 900 can be a system-on-a-chip (SoC). The processor 910 may include a central processing unit (CPU) and may further include other types of processors, such as a graphics processing unit (GPU), which will be described in detail below.

[0091] In summary, the various processors or processing units inside the processor 910 can work together to implement the previous method flow, and the corresponding software programs of each processor or processing unit can be stored in the memory 930.

[0092] (2) A computer data storage medium storing a computer program or the above-described device, which, when executed, causes a computer to perform the steps / functions of the foregoing embodiments or equivalent embodiments.

[0093] In several embodiments provided by this invention, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer data storage medium. Based on this understanding, certain technical solutions of this invention, or the parts that contribute to the prior art, or parts of such technical solutions, can be embodied in the form of software products as described below.

[0094] It should be noted in particular that the storage medium may refer to a server or a similar computer device, specifically, that is, the aforementioned computer program or the aforementioned device is stored in the storage device of the server or similar computer device.

[0095] (3) A computer program product (which may include the above-described device), which, when run on a terminal device, causes the terminal device to execute the method for evaluating organ-at-risk limits in tumor radiotherapy planning based on spatial distance analysis in the foregoing embodiments or equivalent implementations.

[0096] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above implementation methods can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the above-mentioned computer program products may include, but are not limited to, APPs.

[0097] In this embodiment of the invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0098] Those skilled in the art will recognize that the modules, units, and method steps described in the embodiments disclosed in this specification can be implemented using electronic hardware, computer software, and a combination of electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0099] Furthermore, the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. In particular, for embodiments such as apparatus and devices, since they are basically similar to the method embodiments, the relevant parts can be referred to the description of the method embodiments. The apparatus, devices, and other embodiments described above are merely illustrative, and the modules, units, etc., described as separate components may or may not be physically separate, that is, they may be located in one place or distributed in multiple places, such as nodes in a system network. Specifically, some or all of the modules and units can be selected according to actual needs to achieve the purpose of the above-described embodiment solutions. Those skilled in the art can understand and implement this without creative effort.

[0100] The above description of the structure, features, and effects of the present invention is based on the embodiments shown in the figures. However, the above are only preferred embodiments of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred methods can be reasonably combined and matched by those skilled in the art to form a variety of equivalent solutions without departing from or changing the design concept and technical effects of the present invention. Therefore, the present invention is not limited to the scope of implementation shown in the figures. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments, that do not exceed the spirit covered by the specification and figures, should be within the protection scope of the present invention.

Claims

1. A method for evaluating a dose limit of an organ at risk in a tumor radiotherapy plan based on spatial distance analysis, characterized by, The method comprises the following steps: Step S1, importing the DICOM data of the positioning CT sequence data, the target region delineation structure and the organ at risk delineation structure; Step S2, performing three-dimensional Euclidean distance transformation on the above data after anisotropic voxel spacing normalization, to obtain the shortest spatial distance Di of each voxel of the organ at risk to the target region delineation structure, wherein Di is 0 when the organ at risk voxel overlaps with the target region; Step S3, repeating step S2 for all n voxels of the organ at risk to obtain a distance sequence, and taking the maximum value Dmax of the shortest distance therefrom; Step S4, adaptively binning in the interval [0, Dmax], the binning number m is greater than or equal to 10 and the binning width is Dmax / m, or the binning width is determined according to the Freedman-Diaconis criterion; Step S5, counting the number of voxels in each bin interval, drawing a distance-voxel histogram, and calculating a cumulative proportion curve to obtain a change rate curve, comprising: performing smoothing processing on the cumulative proportion curve and taking the derivative thereof to obtain the change rate curve, wherein the smoothing processing is Savitzky-Golay filtering or spline smoothing; Step S6, based on a preset set of geometric rules, generating individualized adjustment suggestions for the limit threshold and the optimized weight of the organ at risk at different doses according to the geometric indicators extracted from the histogram, the cumulative proportion curve and the change rate curve; Step S7, outputting the adjustment suggestions for setting the limit threshold or the target weight before plan optimization.

2. The method of claim 1, wherein the method is a method of evaluating a dose-limiting organ at risk in a tumor radiotherapy plan based on spatial distance analysis. The shortest spatial distance is obtained by traversing the calculation of the shortest Euclidean distance from the i-th voxel of the organ at risk to the target region mask and taking the minimum value, or by using the distance transformation result to obtain the table.

3. The method of claim 1, wherein the method is a method of evaluating a dose-limiting organ in a tumor radiotherapy plan based on a spatial distance analysis. The binning adopts a near-target subdivision strategy: a subdivision width smaller than the global binning width is used in the range of r≤d0.

4. The method of claim 1, wherein the method is a method of evaluating a dose-limiting organ in a tumor radiotherapy plan based on a spatial distance analysis. The geometric indicators at least include Pδ=C(δ), quantiles d5%, d25%, d50%, d75% and d95%, and the main peak position and peak value of the change rate k(r).

5. The method of claim 1, wherein the method is a method of evaluating a dose-limiting organ in a tumor radiotherapy plan based on a spatial distance analysis. The distance calculation adopts KD-tree, or octree nearest point search, or a combination of fast marching and Euclidean distance transformation.

6. A device for evaluating organ-at-risk dose limits in tumor radiotherapy planning based on spatial distance analysis, characterized in that, The method comprises the following steps: A data input module is configured to import the DICOM data of the positioning CT sequence data, the target region delineation structure and the organ at risk delineation structure; A voxel distance calculation module is configured to perform three-dimensional Euclidean distance transformation on the above data after anisotropic voxel spacing normalization, to obtain the shortest spatial distance Di of each voxel of the organ at risk to the target region delineation structure, wherein Di is 0 when the organ at risk voxel overlaps with the target region; A voxel distance sorting module is configured to repeat step S2 for all n voxels of the organ at risk to obtain a distance sequence, and take the maximum value Dmax of the shortest distance therefrom; A binning module is configured to adaptively bin in the interval [0, Dmax], the binning number m is greater than or equal to 10 and the binning width is Dmax / m, or the binning width is determined according to the Freedman-Diaconis criterion; The drawing module is configured to count the number of voxels in each sub-interval, draw a distance-voxel histogram, and calculate an accumulative proportion curve to obtain a change rate curve, including: performing smoothing on the accumulative proportion curve and deriving the change rate curve after the smoothing, wherein the smoothing is Savitzky-Golay filtering or spline smoothing; The geometric analysis module is configured to generate individualized adjustment suggestions for the dose limit threshold and the optimized weight of the OAR based on a preset geometric rule set and geometric indexes extracted from the histogram, the accumulative proportion curve, and the change rate curve; The evaluation guidance module is configured to output the adjustment suggestions for setting the dose limit threshold or the target weight before plan optimization.

7. An electronic device, comprising: The computer program is executed by the processor to implement the method for evaluating the dose limit of the OAR in the tumor radiotherapy plan based on spatial distance analysis according to any one of claims 1-5. The computer program is executed by the processor to implement the method for evaluating the dose limit of the OAR in the tumor radiotherapy plan based on spatial distance analysis according to any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method for evaluating the dose limit of the OAR in the tumor radiotherapy plan based on spatial distance analysis according to any one of claims 1-5.

9. A computer program product comprising a computer program, characterized in that, ​

Images