Method and system for planning gold marker implantation position based on dual-path x-ray imaging geometry

Abstract

This application provides a method and system for planning the implantation location of gold markers based on dual-channel X-ray imaging geometry, relating to the field of image-guided radiotherapy technology. The method includes acquiring a patient's CT image data; determining several gold marker implantation points based on the CT image data; combining the gold marker implantation points according to a preset aggregation rule to construct several gold marker point sets; evaluating the resolvability of the gold marker point set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging; and evaluating the non-overlapping nature of the gold marker point set based on the projection position of each gold marker implantation point in the two-channel DR imaging. This invention uses CyberKnife dual-channel projection geometry to quantitatively evaluate resolvability and non-overlapping, enabling preoperative planning of optimal implantation schemes, avoiding tracking failures caused by two-dimensional projection issues, and significantly improving treatment safety and efficiency.

Description

Technical Field

[0001] This invention relates to the field of image-guided radiotherapy technology, and in particular to a method and system for planning the implantation location of gold markers based on dual-path X-ray imaging geometry. Background Technology

[0002] In the field of image-guided radiotherapy, gold marker tracking technology is widely used for real-time localization of soft tissue tumors such as those in the liver and pancreas. Its basic principle involves implanting multiple gold markers inside or near the tumor, and using an imaging system to acquire real-time data on the positional changes of these gold markers, thereby calculating the spatial movement of the tumor.

[0003] In the CyberKnife system, gold marker tracking is not based on continuous acquisition of 3D images, but rather relies on two X-ray sources with a fixed angle (approximately ±45°) to acquire 2D DR images. The system calculates the 3D pose of the gold marker and tumor by identifying the projection position of the gold marker in the two DR images. However, existing gold marker implantation site planning still has the following significant problems: (1) In current clinical practice, the location of gold marker implantation is mainly selected based on the three-dimensional spatial location of the tumor in CT images. The focus is on whether the gold marker is located near the tumor and whether it meets the anatomical safety requirements. However, it ignores the fact that the identification requirements for tracking may not be met in the actual two-dimensional projection.

[0004] (2) Multiple gold markers are reasonably distributed in three-dimensional space, but they may overlap, be too close to each other, or be blocked by bony structures in one or two DR imaging, which may lead to the inability to stably and accurately identify and distinguish each gold marker, resulting in tracking failure.

[0005] (3) In the existing process, whether the gold marker meets the tracking requirements is often only discovered after implantation, during the planning CT scan and treatment plan establishment. Once it is confirmed that the gold marker cannot be stably identified, it is often necessary to re-implant the gold marker, postpone treatment or abandon the tracking plan, which not only increases the burden on patients, but also significantly reduces the efficiency of the treatment process.

[0006] This paper proposes a method, system, computer equipment, computer-readable storage medium, and computer program product for planning the implantation site of gold markers based on dual-channel X-ray imaging geometry. Summary of the Invention

[0007] This specification provides a method, system, computer device, computer-readable storage medium, and computer program product for planning the implantation location of gold markers based on dual-channel X-ray imaging geometry. By performing projection simulation and traceability quantification assessment of the gold marker implantation location based on CyberKnife dual-channel X-ray imaging geometry before gold marker implantation, it overcomes the problems of existing gold marker implantation processes that rely solely on three-dimensional CT geometry, ignore projection occlusion and overlap under dual-channel DR imaging, and lead to late detection of traceability issues.

[0008] This application provides a method for planning the implantation site of a gold marker based on dual-path X-ray imaging geometry, which employs the following technical solution: Acquire the patient's CT image data; Based on the CT image data, several gold implantation sites were determined. The gold marker implantation points are combined according to preset aggregation rules to construct several gold marker point sets; The properties of each gold-labeled point set are evaluated; specifically, the corresponding two-channel DR imaging is determined based on the dual-channel X-ray imaging geometric model; the resolvability of the gold-labeled point set is evaluated based on the projection distance between any two gold-labeled implanted points in the two-channel DR imaging; and the non-overlapping property of the gold-labeled point set is evaluated based on the projection position of each gold-labeled implanted point in the two-channel DR imaging. Based on the property evaluation results of the gold marker point set, a planning strategy for gold marker implantation locations is constructed.

[0009] Optionally, evaluating the resolvability of the gold marker set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging includes: Traverse all gold implantation points in the gold implantation point set to form point pairs that contain any two different gold implantation points; For each point pair combination, the two-dimensional projection coordinates of the two corresponding gold implantation points in the two-channel DR imaging are obtained respectively. Based on the two-dimensional projection coordinates, calculate the projection distance of the point pair combination in the first DR imaging and its projection distance in the second DR imaging. If every projection distance of each point pair in the gold reference point set meets the resolution condition, then the gold reference point set is considered to be resolvable.

[0010] Optionally, the step of determining that the gold point set is distinguishable if the projection distance of each point pair in the gold point set meets the resolution condition includes: Determine whether the two projection distances of the point pair combination are both not less than the resolvable distance threshold; If so, the point pair combination is deemed to have passed the projection separation test; If all point pairs in the gold-labeled point set pass the projection separation test, then the gold-labeled point set is considered to be distinguishable.

[0011] Optionally, evaluating the non-overlapping nature of the gold marker set based on the projection position of each gold marker implantation point in the two-channel DR imaging includes: Iterate through each gold implantation point in the gold implantation point set; Obtain the simulated projection path of the gold implantation point in the two-channel DR imaging; Structural occlusion verification is performed on the gold implantation point based on each simulated projection path of the gold implantation point. Perform inter-gold label projection overlap verification on the gold label implantation points; If the gold label implantation point passes both the structural occlusion check and the inter-gold label projection overlap check, then the gold label implantation point is considered to have passed the visibility check. If all gold-labeled implanted points in the gold-labeled point set pass the visibility check, then the gold-labeled point set is considered to have non-overlapping properties.

[0012] Optionally, the structural occlusion verification of the gold implantation point based on each simulated projection path of the gold implantation point includes: For each simulated projection path, extract the path segment from the X-ray source to the gold implantation point from the simulated projection path; Determine whether there are no high-density regions on the path segment; the high-density region refers to a region where the CT value (Henry's units) exceeds a preset high-density threshold; If so, then it is determined that the simulated projection path does not have structural occlusion.

[0013] Optionally, the step of constructing a planning strategy for gold marker implantation sites based on the property evaluation results of the gold marker point set includes: If the set of gold markers simultaneously possesses both distinguishability and non-overlapping properties, then the set of gold markers is deemed to be traceable. Based on the basic information of the traceable gold marker set, a planning strategy for the gold marker implantation location is generated.

[0014] This application provides a gold implantation site planning system based on dual-path X-ray imaging geometry, which employs the following technical solution: The acquisition module is used to acquire the patient's CT image data; The positioning module is used to determine several gold implantation points based on the CT image data. The combination module is used to combine the gold label implantation points according to preset aggregation rules to construct several gold label point sets; The evaluation module is used to evaluate the properties of each of the gold standard point sets. The strategy construction module is used to construct a planning strategy for gold marker implantation locations based on the property evaluation results of the gold marker point set.

[0015] Optionally, the evaluation module includes: The model building submodule is used to determine the corresponding two-channel DR imaging based on the dual-channel X-ray imaging geometric model. The distinguishability assessment submodule is used to assess the distinguishability of the gold marker set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging. The non-overlap assessment submodule is used to assess the non-overlap of the gold marker set based on the projection position of each gold marker implantation point in the two-channel DR imaging. Optionally, the distinguishability assessment submodule includes: The combination unit is used to traverse all gold implantation points in the gold implantation point set and form point pair combinations containing any two different gold implantation points. The acquisition unit is used to acquire, for each point pair combination, the two-dimensional projection coordinates of the two gold implantation points in the two-channel DR imaging; The distance calculation unit is used to calculate the projection distance of the point pair combination in the first DR imaging and its projection distance in the second DR imaging based on the two-dimensional projection coordinates. The distinguishability assessment unit is used to determine that the gold point set is distinguishable if the projection distance of each point pair combination in the gold point set meets the distinguishability condition.

[0016] Optionally, the distinguishability assessment unit includes: The projection separation verification subunit is used to determine whether the two projection distances of the point pair combination are both not less than the resolvable distance threshold. If so, the point pair combination is deemed to have passed the projection separation test; The distinguishability assessment subunit is used to determine that the gold reference point set is distinguishable if all point pair combinations in the gold reference point set pass the projection separation test.

[0017] Optionally, the non-overlap evaluation submodule includes: A traversal unit is used to traverse each gold implantation point in the gold implantation point set; The path acquisition unit is used to acquire the simulated projection path of the gold implantation point in the two-channel DR imaging; A structural occlusion verification unit is used to perform structural occlusion verification on the gold implantation point based on each simulated projection path of the gold implantation point. The gold standard inter-projection overlap verification unit is used to verify the inter-projection overlap of the gold standard implantation points. The distinguishability assessment unit is used to determine that the gold implantation point has passed the visibility test if the gold implantation point passes both the structural occlusion test and the inter-gold projection overlap test. If all gold-labeled implanted points in the gold-labeled point set pass the visibility check, then the gold-labeled point set is considered to have non-overlapping properties.

[0018] Optionally, the structure occlusion verification unit includes: The path segment identification subunit is used to extract the path segment from the X-ray source to the gold implantation point from each simulated projection path. The occlusion determination subunit is used to determine whether there is no high-density region on the path segment; the high-density region refers to the region where the CT value (Henry's unit) exceeds a preset high-density threshold. If so, then it is determined that the simulated projection path does not have structural occlusion.

[0019] Optionally, the strategy construction module includes: The property prediction submodule is used to determine that the gold marker set is traceable if the gold marker set has both distinguishability and non-overlapping properties. The strategy generation submodule is used to generate a planning strategy for the gold marker implantation location by combining the basic information of the traceable gold marker set.

[0020] This specification also provides a computer device, wherein the computer device includes: Processor; and, A memory that stores computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0021] This specification also provides a computer-readable storage medium that stores one or more programs / instructions that, when executed by a processor, implement any of the methods described above.

[0022] This specification also provides a computer program product, wherein the computer program product includes: a computer program / instruction, which, when executed by a processor, implements any of the methods described above.

[0023] This invention introduces the dual-path X-ray imaging geometric model of the CyberKnife system into the planning stage before gold marker implantation. It systematically simulates and quantitatively evaluates the projection performance of the gold marker implantation point under tracking conditions, so as to accurately identify and avoid the risk of untrackability caused by projection overlap, occlusion or insufficient separation before operation, reduce the probability of tracking failure after implantation, significantly reduce rework in the treatment process and additional trauma to patients, and greatly improve the gold marker tracking success rate and the overall efficiency and safety of radiotherapy. Attached Figure Description

[0024] Figure 1A flowchart illustrating a method for planning the implantation site of a gold marker based on dual-path X-ray imaging geometry, provided as an embodiment of this specification; Figure 2 A schematic diagram of a gold implantation site planning system based on dual-path X-ray imaging geometry, provided as an embodiment of this specification; Figure 3 A schematic diagram of the structure of a computer device provided in the embodiments of this specification; Figure 4 This is a schematic diagram of a computer-readable storage medium provided for an embodiment of this specification. Detailed Implementation

[0025] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0026] Exemplary embodiments of the invention will now be described more fully with reference to the accompanying drawings. While conforming to the inventive concept, the features, structures, characteristics, or other details described in a particular embodiment may be combined in one or more other embodiments in a suitable manner.

[0027] The terms “and / or” or “and / or” include all combinations of any one or more of the listed items.

[0028] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0029] Figure 1A flowchart illustrating a method for planning the implantation site of a gold marker based on dual-path X-ray imaging geometry, provided in this specification, includes: S1 acquires the patient's CT image data; S2 determines several gold implantation points based on the CT image data; S3 combines the gold label implantation points according to preset aggregation rules to construct several gold label point sets; S4 performs a property evaluation on each of the aforementioned gold standard point sets; Based on the property evaluation results of the gold marker point set, S5 constructs a planning strategy for the gold marker implantation location.

[0030] The main application of this invention is in the preoperative traceability assessment and planning optimization of gold marker implantation in image-guided radiotherapy (IGRT), especially suitable for high-precision radiotherapy systems that rely on real-time tracking of dual-channel X-ray images, such as the CyberKnife system.

[0031] This invention is not dependent on a specific tumor location or a single gold standard number, and has a wide range of applications, especially for high-risk sites such as the liver and pancreas. For sites with large tumor movement, complex surrounding anatomy, and high requirements for gold standard tracking, this invention can significantly improve the success rate of gold standard tracking and has high clinical application value.

[0032] In actual clinical applications, the planning of the gold marker implantation position usually relies on the operator's experience. Due to the lack of a unified and quantitative evaluation method, problems such as the gold marker projection spacing being too small or being obscured by high-density anatomical structures are very likely to occur, which will lead to the failure of subsequent tracking model establishment or insufficient tracking accuracy, thereby affecting the accuracy and safety of radiotherapy.

[0033] Addressing the significant shortcomings of existing technologies in gold marker implantation planning, this invention provides a method for assessing the traceability of gold markers and planning their implantation location by combining CT image data with dual-path X-ray imaging geometry. Before implantation, the resolvability and non-overlap of the gold marker under dual-path X-ray imaging are evaluated to solve the problem of existing gold marker implantation processes relying solely on three-dimensional CT geometry while neglecting actual tracking imaging conditions. This improves the success rate of gold marker tracking and the safety of radiotherapy. Specifically, this invention includes: S1 acquires the patient's CT image data; The patient was scanned using a CT simulation localization scanning device to acquire three-dimensional CT data containing the tumor target area and surrounding tissues. .

[0034] The three-dimensional CT data is preprocessed. In one embodiment of this specification, spatial calibration and normalization are performed on the three-dimensional CT data to obtain CT image data. .

[0035] To facilitate subsequent registration with the imaging geometry model of the CyberKnife system, a three-dimensional patient coordinate system consistent with the CyberKnife treatment system will be established or identified. The CT image data and the coordinates of the anatomical structures defined therein will be uniformly transformed into the patient coordinate system, serving as the reference coordinate system for all subsequent spatial calculations and projection simulations.

[0036] S2 determines several gold implantation points based on the CT image data; Among them, gold label refers to a metal Fiducial Marker.

[0037] S21 Locates the tumor target area outline and the tumor geometric center from the CT image data; In one embodiment of this specification, based on CT image data The tumor target area outline is delineated manually or automatically to determine the tumor voxel set. Among them, tumor voxel collection It is the set of coordinates of all tumor voxels.

[0038] Calculating the geometric center of the tumor based on tumor voxel set Specifically, The coordinates of each tumor voxel are as follows: .

[0039] S22 combines the tumor target area contour with the tumor geometric center to construct a preset spatial range; S221 Determines the pre-defined anatomical range based on the location of the tumor target area contour. The preset anatomical range is limited to the anatomical space within the specific location of the tumor. In a specific embodiment, the specific location of the tumor may be the same liver lobe (segment) as the tumor.

[0040] S222 combined with tumor geometric center With the pre-set anatomical range Construct a preset spatial range .

[0041] Among them, for the preset spatial range Each candidate point in It satisfies the following preset region conditions: candidate points It is a point in three-dimensional space, that is, Candidate points The specific lobe (segment) of the liver where the tumor is located. Within the range, that is, Candidate points Geometric center of tumor The Euclidean distance is less than or equal to the maximum permissible implantation distance. ,Right now In other words, .

[0042] S23 Divide the candidate implantation area from the preset spatial range based on the anatomical structure information; Specifically, by combining anatomical information, high-risk areas such as blood vessels, bile ducts, intestines, and other areas that cannot be punctured are identified; high-risk areas are then eliminated from the pre-defined spatial range to obtain safe candidate implantation areas.

[0043] This invention achieves its goals by defining a preset spatial range. Conduct anatomical safety constraint screening to eliminate high-risk areas (points).

[0044] S24 samples the candidate implantation area according to a preset sampling method to obtain multiple gold-labeled implantation points.

[0045] Based on the candidate implantation area, perform regular or random sampling in the CT coordinate system to extract several gold-labeled implantation points.

[0046] Summarize all gold-labeled implantation points and construct the original point set. .

[0047] In one embodiment of this specification, any two gold implantation points in the original point set Satisfying the minimum distance constraint: any two gold implantation points The distance is greater than or equal to the minimum interval distance; that is, , .

[0048] After acquiring and preprocessing the patient's three-dimensional CT data, this invention determines the three-dimensional spatial location of the tumor. Based on this, it identifies candidate implantation areas suitable for gold standard implantation, thereby providing a reliable imaging basis for subsequent gold standard location calculation and facilitating preoperative planning of gold standard implantation location based on three-dimensional CT data.

[0049] S3 combines the gold label implantation points according to preset aggregation rules to construct several gold label point sets; From the set of original points At least three gold-labeled implantation sites are randomly selected to construct a gold-labeled site set for subsequent stability evaluation.

[0050] In one embodiment of this specification, the gold-labeled point set ,in, .

[0051] S4 performs a property evaluation on each of the aforementioned gold standard point sets; In radiotherapy equipment such as CyberKnife, the real-time position of the tumor is not obtained through direct three-dimensional imaging. Instead, it is observed by two-dimensional projection of gold markers within the body using digital radiography (DR) imaging with a fixed angle between the two beams, and the three-dimensional spatial pose of the tumor is calculated based on the projection matching. Therefore, whether the gold markers can be stably and clearly distinguished and identified directly depends on their resolvability and non-overlapping properties under the aforementioned two-beam X-ray imaging geometry.

[0052] In current clinical practice, the implantation location of gold markers is usually selected solely based on 3D CT images, lacking a systematic assessment of whether they are "traceable" under the actual imaging geometry of CyberKnife. This discrepancy results in some gold markers having a reasonable geometric position in 3D space, but experiencing occlusion, overlap, or insufficient separation in dual-path X-ray projection, thus making them unsuitable for real-time tracking.

[0053] This invention introduces a dual-path fixed X-ray imaging geometric model (approximately ±45°) from the CyberKnife system before gold label implantation. This model is used to perform projection simulation pre-evaluation of candidate gold label implantation points, thereby screening out a planning strategy for gold label implantation positions with good traceability under actual tracking conditions before surgery. This provides clinicians with an intuitive and reliable implantation reference.

[0054] S41 determines the corresponding two-channel DR imaging based on the dual-channel X-ray imaging geometric model; Based on the equipment parameters of the CyberKnife system, a dual-channel X-ray imaging geometric model consistent with the CyberKnife system is established, which involves two-channel DR imaging, specifically including: the first-channel DR imaging and the second-channel DR imaging.

[0055] Among them, the first-channel DR imaging characterization starts from the position of the first X-ray source. The X-rays are emitted, penetrate the patient, and finally reach the plane of the first detector. The complete imaging chain that forms the image.

[0056] The second-path DR imaging characterization is from the location of the second X-ray source. The X-rays are emitted, penetrate the patient, and finally reach the plane of the second detector. The complete imaging chain that forms the image.

[0057] The X-ray sources from the two sources are oriented at approximately +45° and 10° respectively in the patient's coordinate system. The field direction is 45°, and the angle between the two X-ray sources relative to the patient's coordinate system is... .

[0058] Before the calculation, the CT coordinate system and the CyberKnife imaging coordinate system are spatially registered to ensure that the coordinates of all spatial points (tumor, candidate gold marker location, etc.) are projected and calculated in a unified patient coordinate system.

[0059] This invention introduces a fixed ±45° dual-channel X-ray imaging geometric model in the CyberKnife system as the core constraint for gold marker planning. Subsequently, the projection performance of the gold marker implantation point is evaluated based on the actual imaging geometry of CyberKnife, avoiding the evaluation bias caused by relying solely on 3D CT geometry. This makes the gold marker implantation planning more consistent with the real treatment environment and highly aligned with clinical practice.

[0060] S42 calculates the two-dimensional projection position of each gold implantation point in the two-channel X-ray imaging and generates the corresponding two-dimensional projection coordinates. Specifically, for any constructed candidate gold marker set, for each gold marker implantation point within the set... The two-dimensional projection coordinates of X-rays in the first-channel DR imaging were calculated using a dual-channel X-ray imaging geometric model. and its two-dimensional projection coordinates in the second-channel DR imaging. .

[0061] in, ; . , This represents the perspective projection operator based on the intersection of the ray and the detector.

[0062] This invention can overlay the calculated projection results onto a simulated DR image for intuitive observation of the distribution of different gold implantation points in a two-dimensional projection.

[0063] S43 evaluates the resolvability of the gold marker set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging. Based on the relationship between points, it ensures that the independent projection of each gold label implantation point can be accurately matched and identified, and the projection separation is judged based on the distance between the gold label implantation points to determine the distinguishability.

[0064] This invention evaluates the distinguishability of gold markers in two-dimensional images by quantitatively analyzing the distance between the two-dimensional projected coordinates of any two gold marker implantation points on the same detector plane and comparing it with a preset minimum distinguishable distance threshold. This distance criterion, based on the physical nature of projection separation, ensures the stable and accurate differentiation and identification of the independent projection signal of each gold marker implantation point. Based on the projection separation of each gold marker implantation point, the distinguishability of the gold marker point set is evaluated.

[0065] S431 traverses all gold implantation points in the gold implantation point set to form point pairs containing any two different gold implantation points; In one embodiment of this specification, for those comprising Gold Standard Implantation Points Set Enumerate all pairwise combinations to form point-to-point combinations. .

[0066] Among them, point-to-point combinations The number of indivual, .

[0067] S432 For each point pair combination, obtain the two-dimensional projection coordinates of the two gold implantation points in the two-channel DR imaging; In one embodiment of this specification, for point-to-point combinations It includes two gold-labeled implantation sites, namely , .

[0068] Obtain the first gold label implantation point The two-dimensional projection coordinates in two-channel DR imaging specifically include: its two-dimensional projection coordinates in the first-channel DR imaging. and its two-dimensional projection coordinates in the second-channel DR imaging. .

[0069] Obtain the second gold standard implantation point The two-dimensional projection coordinates in two-channel DR imaging specifically include: its two-dimensional projection coordinates in the first-channel DR imaging. and its two-dimensional projection coordinates in the second-channel DR imaging. .

[0070] S433 calculates the projection distance of the point pair combination in the first DR imaging and its projection distance in the second DR imaging based on the two-dimensional projection coordinates. In one embodiment of this specification, for point-to-point combinations Calculate point-pair combinations Two gold standard implantation points , The projection distance in two-channel DR imaging. The preferred projection distance is the Euclidean distance.

[0071] Specifically, calculate point-pair combinations. Two gold standard implantation points , First projection distance in first-channel DR imaging .in, .

[0072] Calculate point-pair combinations Two gold standard implantation points , Second projection distance in second-channel DR imaging .in, .

[0073] S434 If every projection distance of each point pair in the gold reference point set meets the resolution condition, then the gold reference point set is deemed to be resolvable.

[0074] The projection distance is compared with a preset resolvable distance threshold to determine whether the gold label implantation point can be stably distinguished under each projection viewpoint.

[0075] Specifically, it is determined whether the two projected distances of the point pair combination are both not less than the resolvable distance threshold; if so, the point pair combination is deemed to meet the resolution condition and pass the projection separation test; otherwise, the point pair combination is deemed to not meet the resolution condition and fail the projection separation test.

[0076] In one embodiment of this specification, a resolvable distance threshold is defined for single-channel DR imaging. When satisfied Then it is considered that the two gold-labeled implantation points , The point pair combination Verification was performed using projection separation.

[0077] If all point pairs in the gold-labeled point set pass the projection separation test, then the gold-labeled point set is considered to be distinguishable.

[0078] S44 evaluates the non-overlapping property of the gold marker set based on the projection position of each gold marker implantation point in the two-channel DR imaging. Non-overlap assessment is used to ensure that gold implantation sites are not confused with other gold implantation sites or other high-density structures in the same gold implantation site set during DR imaging.

[0079] S441 traverses each gold implantation point in the gold implantation point set; S442 obtains the simulated projection path of the gold implantation point in the two-channel DR imaging; Based on the dual-path X-ray imaging geometric model established in step S41, the gold implantation point... The simulations showed X-rays originating from two different sources and passing through the gold implantation point. The simulated projection path that ultimately reaches the corresponding detector plane. .

[0080] Specifically, the simulation starts from the first X-ray source. Departure, passing through the gold standard implantation points Finally, it reaches the plane of the first detector. Simulated projection path Simulation from the second X-ray source Departure, passing through the gold standard implantation points Finally, it reaches the plane of the second detector. Simulated projection path .

[0081] S443 performs structural occlusion verification on the gold implantation point based on each simulated projection path of the gold implantation point. Specifically, for each simulated projection path, the path segment from the X-ray source to the gold label implantation point is extracted from the simulated projection path; it is determined whether there is no high-density area on the path segment; if so, it is determined that there is no structural obstruction on the simulated projection path. High-density areas refer to regions where the CT value (Henness units) exceeds a preset high-density threshold. Specifically, high-density areas represent voxels with higher density than gold standard values, such as high-density tissues like bone and soft tissues.

[0082] If there are no high-density regions on any of the simulated projection paths of the gold label implantation point, the gold label implantation point is considered to have passed the structural occlusion verification; otherwise, the gold label implantation point is considered to have failed the structural occlusion verification.

[0083] The structural occlusion verification of this invention is used to determine whether there are voxels with a higher density than the gold standard along the simulated projection path of X-rays reaching the detector plane. If the maximum CT value (Henness units) on the path appears before the gold standard location, and this value exceeds the typical contrast threshold between the gold standard and soft tissue, then the gold standard is determined to be at risk of being occluded in that imaging path.

[0084] S444 performs a gold label implantation point projection overlap verification; The inter-gold standard projection overlap check is used to determine whether the projection of the gold standard implantation point is too close to the projection of other gold standards within the point set. Given that the distinguishability assessment in step S43 has already guaranteed the overall projection separation of the gold standard point set based on a larger threshold, the inter-gold standard projection overlap check in this step can be implemented in the following preferred manner: if the gold standard point set has been determined to meet the distinguishability in step S43, then the gold standard implantation point can be directly considered to have passed the inter-gold standard projection overlap check.

[0085] If you need to perform the inter-gold standard projection overlap verification independently, then do the following: For each DR imaging session, obtain the gold standard implantation point. The two-dimensional projected coordinates of the gold-labeled implantation points and other gold-labeled implantation points within the same gold-labeled point set on the plane of the detector. Calculate the gold standard implantation point The Euclidean distance between the projection of the original gold marker and every other gold marker implantation point within the same gold marker point set is used as the original distance value. The original distance value is then compared with a preset projection overlap determination threshold. The projection overlap determination threshold is a very small positive value, typically not greater than the size of a single pixel in the imaging system.

[0086] If for all other gold-labeled implantation points within the gold-labeled point set, in two-channel DR imaging, their relationship with the gold-labeled implantation points... If the projection distances are all greater than or equal to the projection overlap threshold, it indicates that the gold implantation points... In this DR imaging, there was no projection overlap with other gold-labeled implantation sites, thus confirming the gold-labeled implantation site. If the inter-gold standard projection overlap is verified, then the gold standard implantation point is considered to have failed the inter-gold standard projection overlap verification.

[0087] S445 If the gold implantation point passes both the structural occlusion check and the inter-gold projection overlap check, then the gold implantation point is deemed to have passed the visibility check. S446 If all gold implantation points in the gold marker set pass the visibility check, then the gold marker set is deemed to have non-overlapping properties.

[0088] This invention, through projection separation and projection simulation calculation of dual-channel DR imaging, can identify in advance gold label implantation strategies that overlap, are too close, or are indistinguishable in two-dimensional projection, avoiding the situation where the gold label cannot be tracked only after implantation, and effectively avoiding the problem of "reasonable in three-dimensional space but untrackable in two-dimensional projection".

[0089] This invention is based on clear judgment conditions for projection distance and overlapping projection. Each step of its implementation has a clear geometric meaning, avoiding black box evaluation results. The evaluation process has clear physical meaning and geometric interpretability, making it easy for clinicians to understand and accept.

[0090] Based on the property evaluation results of the gold marker point set, S5 constructs a planning strategy for the gold marker implantation location.

[0091] S51 If the set of gold markers simultaneously possesses distinguishability and non-overlapping properties, then the set of gold markers is deemed to possess traceability. In one specific embodiment of this specification, the traceability criteria for any set of gold markers under dual-channel DR imaging are defined as follows: (1) The gold standard point set is resolvable: In two-channel DR imaging, the projection distance between any two gold standard implantation points in the gold standard point set satisfies the resolvability condition. (2) The gold marker set has non-overlapping property: any gold marker implantation point in the gold marker set does not overlap with other gold markers or obvious high-density areas in any DR imaging.

[0092] If the above conditions are met, then the gold marker set is determined to have the trackability required for CyberKnife tracking under the CyberKnife dual-path X-ray imaging geometry.

[0093] S52 combines the basic information of the traceable gold marker set to generate a planning strategy for the gold marker implantation location.

[0094] S521 recommends implantation sites based on traceable gold-labeled sites; S522 obtains the number of recommended implantation points in the traceable gold standard point set, and the spatial location of each recommended implantation point; The recommended implantation point is the recommended three-dimensional spatial coordinates or spatial region of the gold standard.

[0095] S523 determines the non-recommended implantation information based on the structural occlusion verification results and the projection overlap verification results between the gold standard points in the set of recommended implantation points; the non-recommended implantation information includes: overlapping projection areas and a description of non-recommended implantation.

[0096] For overlapping projection areas that do not meet the traceability criteria, a disclaimer for implantation will be provided to assist clinical decision-making. The disclaimer could state that overlap occurs within a ±45° projection direction, posing a risk of projection overlap.

[0097] S524 combines the number of recommended implantation points, the spatial location of each recommended implantation point, and at least one of the information on non-recommended implantation points to construct a planning strategy for the gold standard implantation location.

[0098] S525 selects at least one planning strategy for a gold-labeled implantation site from all planning strategies for gold-labeled implantation sites as the preferred planning option; In one embodiment of this specification, To select a better implantation strategy from multiple traceable gold standard sites, a scoring function can be established to quantitatively evaluate and rank the traceable gold standard sites. The scoring function can be constructed based on one or more evaluation indicators, including but not limited to: projection separation index, spatial distribution index, and quantity preference index.

[0099] Among them, the projection separation index is used to reflect the distinguishability of the scheme under real tracking imaging conditions. For example, it calculates the average projection distance of all point pairs in the gold standard point set in two-channel DR imaging. The spatial distribution index is used to evaluate the geometric distribution characteristics of the gold standard points in three-dimensional space. For example, it calculates the volume and surface area of ​​the polygons or polyhedra they form, or evaluates the uniformity of the distance between points. The quantity preference index is set according to clinical practice experience. For example, a base score can be assigned to schemes containing a specific number of gold standards to conform to routine clinical practice.

[0100] The planning strategies for each gold-label implantation site are ranked according to their scores; based on the ranking results, the planning strategy for at least one gold-label implantation site is selected as the preferred planning scheme.

[0101] The optimal planning scheme is presented through the overlay of three-dimensional CT images, projection simulation diagrams of two-dimensional DR imaging, or structured data, so as to provide clinicians with a reference for preoperative decision-making.

[0102] This invention not only outputs recommended implantation sites or regions for gold standard implantation, but also clearly identifies the reasons for not recommending implantation, enhancing the understandability and clinical acceptability of the planning results, and providing clinicians with intuitive and interpretable implantation planning references.

[0103] This invention performs multi-view X-ray projection simulations on multiple candidate gold marker implantation points before gold marker implantation. By analyzing the spacing and overlap risk of each gold marker implantation point in the two-dimensional projection, the traceability of the corresponding gold marker point set is assessed. This move the traceability assessment forward to the preoperative (pre-implantation) planning stage, which can identify and warn of untraceable implantation plans in advance, reduce the incidence of tracking failure after gold marker implantation, reduce treatment process adjustments / rework caused by gold marker projection occlusion or overlap, and reduce additional trauma to patients. It significantly reduces the incidence of repeated implantation, delayed treatment, or abandonment of tracking plans, and effectively improves the success rate of establishing CyberKnife gold marker tracking models and overall treatment efficiency.

[0104] This invention relies solely on conventionally acquired CT image data and known imaging geometry parameters of the CyberKnife system, requiring no additional hardware or radiation exposure. It is highly compatible with existing radiotherapy procedures, easy to implement in engineering, and easy to integrate into existing radiotherapy planning systems or preoperative planning software.

[0105] In addition, this invention focuses on the traceability assessment of candidate gold implantation sites under dual-channel DR imaging conditions before gold implantation. It can complement other gold implantation planning methods, such as planning methods based on three-dimensional rigid body geometric stability and anatomical safety, to form a complete and reliable gold implantation decision support system.

[0106] Figure 2A schematic diagram of a gold marker implantation site planning system based on dual-channel X-ray imaging geometry, provided as an embodiment of this specification, is shown. The system includes: The acquisition module 210 is used to acquire the patient's CT image data; The positioning module 220 is used to determine several gold implantation points based on the CT image data. The combination module 230 is used to combine the gold label implantation points according to a preset aggregation rule to construct a number of gold label point sets; Evaluation module 240 is used to evaluate the properties of each of the gold standard point sets; The strategy construction module 250 is used to construct a planning strategy for the implantation location of gold markers based on the property evaluation results of the gold marker point set.

[0107] Optionally, the evaluation module 240 includes: The model building submodule is used to determine the corresponding two-channel DR imaging based on the dual-channel X-ray imaging geometric model. The distinguishability assessment submodule is used to assess the distinguishability of the gold marker set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging. The non-overlap assessment submodule is used to assess the non-overlap of the gold marker set based on the projection position of each gold marker implantation point in the two-channel DR imaging. Optionally, the distinguishability assessment submodule includes: The combination unit is used to traverse all gold implantation points in the gold implantation point set and form point pair combinations containing any two different gold implantation points. The acquisition unit is used to acquire, for each point pair combination, the two-dimensional projection coordinates of the two gold implantation points in the two-channel DR imaging; The distance calculation unit is used to calculate the projection distance of the point pair combination in the first DR imaging and its projection distance in the second DR imaging based on the two-dimensional projection coordinates. The distinguishability assessment unit is used to determine that the gold point set is distinguishable if the projection distance of each point pair combination in the gold point set meets the distinguishability condition.

[0108] Optionally, the distinguishability assessment unit includes: The projection separation verification subunit is used to determine whether the two projection distances of the point pair combination are both not less than the resolvable distance threshold. If so, the point pair combination is deemed to have passed the projection separation test; The distinguishability assessment subunit is used to determine that the gold reference point set is distinguishable if all point pair combinations in the gold reference point set pass the projection separation test.

[0109] Optionally, the non-overlap evaluation submodule includes: A traversal unit is used to traverse each gold implantation point in the gold implantation point set; The path acquisition unit is used to acquire the simulated projection path of the gold implantation point in the two-channel DR imaging; A structural occlusion verification unit is used to perform structural occlusion verification on the gold implantation point based on each simulated projection path of the gold implantation point. The gold standard inter-projection overlap verification unit is used to verify the inter-projection overlap of the gold standard implantation points. The distinguishability assessment unit is used to determine that the gold implantation point has passed the visibility test if the gold implantation point passes both the structural occlusion test and the inter-gold projection overlap test. If all gold-labeled implanted points in the gold-labeled point set pass the visibility check, then the gold-labeled point set is considered to have non-overlapping properties.

[0110] Optionally, the structure occlusion verification unit includes: The path segment identification subunit is used to extract the path segment from the X-ray source to the gold implantation point from each simulated projection path. The occlusion determination subunit is used to determine whether there is no high-density region on the path segment; the high-density region refers to the region where the CT value (Henry's unit) exceeds a preset high-density threshold. If so, then it is determined that the simulated projection path does not have structural occlusion.

[0111] Optionally, the strategy construction module 250 includes: The property prediction submodule is used to determine that the gold marker set is traceable if the gold marker set has both distinguishability and non-overlapping properties. The strategy generation submodule is used to generate a planning strategy for the gold marker implantation location by combining the basic information of the traceable gold marker set.

[0112] The functions of the system in this embodiment have been described in the above method embodiments. Therefore, for any parts not detailed in this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0113] Figure 3This is a schematic diagram of the structure of a computer device provided in an embodiment of this specification. The computer device includes a memory 301 and a processor 302. The memory 301 is used to store computer-executable instructions. When the computer-executable instructions are executed by the processor 302, they can implement the steps of the above-described method embodiment.

[0114] Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium 400 provided in an embodiment of this specification. The computer-readable storage medium 400 stores one or more computer programs, which, when executed by a processor, can implement the steps of the above-described method embodiments.

[0115] This specification also provides a computer program product, including a computer program / computer executable instructions, which, when executed by a processor, can implement the steps of the above-described method embodiments.

[0116] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. When the computer program is executed, it may include the processes of the embodiments of the above methods.

[0117] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for planning the implantation site of a gold marker based on dual-path X-ray imaging geometry, characterized in that, include: Acquire the patient's CT image data; Based on the CT image data, several gold implantation sites were determined. The gold marker implantation points are combined according to preset aggregation rules to construct several gold marker point sets; The properties of each gold-labeled point set are evaluated; specifically, the corresponding two-channel DR imaging is determined based on the dual-channel X-ray imaging geometric model; the distinguishability of the gold-labeled point set is evaluated based on the projection distance between any two gold-labeled implantation points in the two-channel DR imaging. The non-overlapping property of the gold marker set is evaluated based on the projection position of each gold marker implantation point in the two-channel DR imaging. Based on the property evaluation results of the gold marker point set, a planning strategy for gold marker implantation locations is constructed.

2. The method for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry as described in claim 1, characterized in that, The step of evaluating the resolvability of the gold marker set based on the projection distance between any two gold marker implantation points in the two-channel DR imaging includes: Traverse all gold implantation points in the gold implantation point set to form point pairs that contain any two different gold implantation points; For each point pair combination, the two-dimensional projection coordinates of the two corresponding gold implantation points in the two-channel DR imaging are obtained respectively. Based on the two-dimensional projection coordinates, calculate the projection distance of the point pair combination in the first DR imaging and its projection distance in the second DR imaging. If every projection distance of each point pair in the gold reference point set meets the resolution condition, then the gold reference point set is considered to be resolvable.

3. The method for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry as described in claim 2, characterized in that, If the projection distance of each point pair in the gold reference point set meets the resolution condition, then the gold reference point set is deemed to be resolvable, including: Determine whether the two projected distances of the point pair combination are both not less than the resolvable distance threshold; If so, the point pair combination is deemed to have passed the projection separation test; If all point pairs in the gold-labeled point set pass the projection separation test, then the gold-labeled point set is considered to be distinguishable.

4. The method for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry as described in claim 1, characterized in that, The step of evaluating the non-overlapping nature of the gold marker set based on the projection position of each gold marker implantation point in the two-channel DR imaging includes: Iterate through each gold implantation point in the gold implantation point set; Obtain the simulated projection path of the gold implantation point in the two-channel DR imaging; Structural occlusion verification is performed on the gold implantation point based on each simulated projection path of the gold implantation point. Perform inter-gold label projection overlap verification on the gold label implantation points; If the gold label implantation point passes both the structural occlusion check and the inter-gold label projection overlap check, then the gold label implantation point is considered to have passed the visibility check. If all gold-labeled implanted points in the gold-labeled point set pass the visibility check, then the gold-labeled point set is considered to have non-overlapping properties.

5. The method for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry as described in claim 4, characterized in that, The structural occlusion verification of the gold implantation point based on each simulated projection path of the gold implantation point includes: For each simulated projection path, extract the path segment from the X-ray source to the gold implantation point from the simulated projection path; Determine whether there are no high-density regions on the path segment; the high-density region refers to a region where the CT value exceeds a preset high-density threshold. If so, then it is determined that the simulated projection path does not have structural occlusion.

6. The method for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry as described in claim 1, characterized in that, The strategy for planning the implantation site of gold markers based on the property evaluation results of the gold marker point set includes: If the set of gold markers simultaneously possesses both distinguishability and non-overlapping properties, then the set of gold markers is deemed to be traceable. Based on the basic information of the traceable gold marker set, a planning strategy for the gold marker implantation location is generated.

7. A system for planning the implantation location of a gold marker based on dual-path X-ray imaging geometry, characterized in that, include: The acquisition module is used to acquire the patient's CT image data; The positioning module is used to determine several gold implantation points based on the CT image data. The combination module is used to combine the gold label implantation points according to preset aggregation rules to construct several gold label point sets; An evaluation module is used to evaluate the properties of each set of gold-labeled points; specifically, it determines the corresponding two-channel DR imaging based on a dual-channel X-ray imaging geometric model; it evaluates the resolvability of the gold-labeled point set based on the projection distance between any two gold-labeled implanted points in the two-channel DR imaging; and it evaluates the non-overlapping property of the gold-labeled point set based on the projection position of each gold-labeled implanted point in the two-channel DR imaging. The strategy construction module is used to construct a planning strategy for gold marker implantation locations based on the property evaluation results of the gold marker point set.

8. A computer device, characterized in that, The computer device includes: Processor; and, A memory storing computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs / instructions, which, when executed by a processor, implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program / instruction, which, when executed by a processor, implements the method as described in any one of claims 1-6.

Images