Systems, devices, and methods for managing patient imaging

Abstract

A computer-implemented method for managing cone-beam computed tomography (CBCT) imaging of a patient. The method includes acquiring (102) RTP information for radiotherapy planning (RTP). The RTP is used to apply a radiation dose distribution to the patient to achieve at least one radiotherapy objective. The method further includes determining (104) a measure of the sensitivity of the RTP to changes in the patient's anatomical structures based on the acquired RTP information. The measure of sensitivity is a function of location within the patient or a function of the direction of the radiotherapy beam in the RTP. The method further includes generating (106) an imaging protocol for acquiring reconstructed CBCT images of the patient's volume based on the determined sensitivity by: setting the value of at least one parameter in the imaging protocol such that the image quality of the reconstructed CBCT images of the patient's volume meets an image quality objective for an image processing task. The image quality objective prioritizes image quality at locations within the patient's volume where the RTP is sensitive to changes in anatomical structures. The imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter.

Description

Technical Field

[0001] Embodiments of this disclosure relate to systems, apparatus, and methods for managing patient imaging. More specifically, embodiments of this disclosure relate to a computer-implemented method for managing cone-beam computed tomography (CBCT) imaging of a patient, as well as a management node, a radiotherapy apparatus, and a computer program product configured to perform the method for managing cone-beam computed tomography imaging of a patient. Background Technology

[0002] Radiation therapy (one of the cornerstones of cancer treatment) uses ionizing radiation to damage or destroy unhealthy cells in the human or animal body. During treatment, ionizing radiation is formed into beams and directed to unhealthy cells in the body, such as tumors.

[0003] Radiation therapy (RT) is performed according to a radiation therapy plan to deliver a radiation dose distribution to a patient to achieve a range of radiation therapy goals. These goals may include, for example, a minimum radiation dose to the tumor, an upper limit on the radiation dose to healthy organs at risk of radiation damage, and an upper limit on the total radiation dose to the patient. The actual dose distribution depends on treatment parameters such as beam direction, dose per energy, number of beams, beam weighting, and exposure time. The area identified as requiring treatment (e.g., the area containing the tumor) is called the clinical target volume (CTV). The area to be treated is called the planned target volume (PTV), and is typically the CTV plus some margins added to ensure effective treatment of the CTV. Areas where the treatment dose is not ideal are called organs at risk (OARs).

[0004] Radiation therapy planning is the process of determining a radiation therapy plan to deliver an appropriate dose distribution that will meet the goals of radiation therapy. During radiation therapy planning, the patient's anatomical regions are modeled using three-dimensional images of the patient (e.g., computed tomography (CT) images, referred to as planning CT). Image segmentation is performed to define different regions within the images (called partitions), and different goals and constraints may be defined for different partitions. The result of radiation therapy planning is the configuration and / or order in which the radiation therapy system delivers the radiation dose distribution to the patient, as instructed by the radiation therapy plan. For example, a radiation therapy plan may include parameters specifying, for example, the direction, cross-sectional shape, energy, and intensity of each radiation beam to be delivered into the patient's body. A radiation therapy plan may include a series of dose fractions of radiation therapy delivered over a predetermined time period, wherein each treatment delivers a specific fraction of a prescribed total dose. For example, the total radiation dose may be divided into approximately 3 to 40 fractions per day. Radiation therapy planning can be performed using a treatment planning system such as Monaco®. Radiation therapy planning may also be referred to as radiation therapy planning or treatment planning.

[0005] Image-guided radiography (IGRT) is a technique used to improve treatment accuracy by capturing a patient's anatomy during fractionated dose administration using intravenous imaging and ensuring that the planned dose distribution is accurately aligned with the patient's anatomy. Cone-beam computed tomography (CBCT) is the most widely used imaging modality in IGRT. CBCT imaging of patients undergoing IGRT is performed according to an imaging protocol. The imaging protocol may include a CBCT imaging acquisition protocol (for performing the CBCT scan) and / or a CBCT imaging reconstruction protocol (for processing the raw data from the CBCT scan into 3D reconstructed CBCT images).

[0006] Adaptive radiotherapy (ART) is a technique that uses imaging to evaluate and adjust radiotherapy plans. In inter-fractional ART, images acquired during a RT (radiotherapy) phase are analyzed offline and used to adjust the radiotherapy plan for future phases (i.e., changes are made between fractions). In intra-fractional ART, images acquired during a RT phase are analyzed online (i.e., analyzed in real time during that phase) and used to adjust the radiotherapy plan for that phase (i.e., changes are made during fractions). ART can thus improve the accuracy of RT treatment, for example, by ensuring that the radiotherapy plan takes into account any changes in the patient's anatomy.

[0007] A drawback of IGRT and ART is that the additional dose (referred to as imaging dose) generated by CBCT imaging performed during treatment may increase the risk of secondary cancers. For more information, see Alaei, P., & Spezi, E., *Phys. Med.*, Vol. 31, No. 7, 2015. To minimize the risk of secondary cancers, it is crucial to keep the CBCT imaging dose as low as possible during radiotherapy. Minimizing CBCT acquisition and reconstruction time is also advantageous, for example, to improve patient comfort, treat more patients in a given time, and track faster patient movement, as is the case with ART. However, minimizing imaging dose and imaging time must be balanced with CBCT image quality (e.g., the signal-to-noise ratio and / or image resolution of CBCT images). Parameters in the CBCT acquisition protocol, such as the projection angle of the CBCT projection (e.g., the density of projection angles along the scan arc), the gantry rotation speed of the CBCT projection, and the intensity (mAs) and energy (kV) of the imaging source, affect image quality. For example, increasing source intensity (by increasing X-ray tube current (mA) and / or exposure time (s)) improves the signal-to-noise ratio (SNR) of the acquired image. Increasing source energy enhances X-ray penetration, thus improving image quality by increasing the SNR in the detector; however, increasing source energy can also reduce image contrast by decreasing absorption differences between different tissues (i.e., absorption differentials). For instance, Xuanhao, Z et al., published in *Measurement* 194, 111061 in 2022, and Yan, H et al., published in *Phys. Med. Biol.* 57, 2063 in 2012, investigated the impact of imaging protocol parameters on image quality. Image quality is also affected by parameters in the CBCT reconstruction protocol, such as voxel size and the number of iterations in the reconstruction algorithm.

[0008] In radiotherapy applications, sufficiently high image quality is crucial for accurately performing image processing tasks such as image contouring and image segmentation, which are key components of radiotherapy planning. Chen, GP, et al. described the need for high-quality CT images in radiotherapy planning in their 2017 paper published in Physics and Imaging in Radiation Oncology 4 (6-11).

[0009] CBCT imaging protocols can be generated based on a patient's body mass index (BMI) or water equivalent thickness (WET) to maximize CBCT image quality for radiotherapy guidance. When generating the imaging protocol, parameters such as source intensity, source energy, exposure time, and / or detector gain can be selected to achieve the desired penetration, contrast, and / or artifact reduction. For example, the radiographic depth of a patient's tissue (expressed as WET) can be used to determine the imaging intensity and exposure time required to penetrate the tissue to achieve a specific minimum image quality. Higher density tissues or thicker areas of the patient require higher intensity and longer exposure times. Similarly, a patient's BMI can indicate whether a higher or lower source intensity and exposure time should be used to achieve sufficient image contrast with minimal radiation dose. Summary of the Invention

[0010] High-quality CBCT images are crucial for RT applications such as radiotherapy planning, IGRT, and ART, as CBCT image quality affects the accuracy of subsequent image processing tasks such as image reconstruction, image contouring, and image segmentation. The accuracy of image processing tasks, in turn, impacts the accuracy of subsequent RT treatment. For example, image segmentation is typically performed on reconstructed CBCT images to identify the shape and location of patient anatomy at the time of treatment application (e.g., for IGRT and / or ART), and therefore, sufficient image quality of the CBCT images acquired during treatment for accurate organ delineation and dose calculation is essential. Thus, a balance must be struck between minimizing CBCT imaging dose and / or imaging time (for acquisition and / or reconstruction) and acquiring sufficiently high-quality reconstructed CBCT images for subsequent image processing tasks.

[0011] According to a first aspect of this disclosure, a computer-implemented method for managing CBCT imaging of a patient is provided. The method includes acquiring radiotherapy plan (RTP) information. The RTP is used to apply a radiation dose distribution to the patient to achieve at least one radiotherapy objective. The method further includes determining a measure of the sensitivity of the RTP to changes in the patient's anatomical structures based on the acquired RTP information. The sensitivity measure is a function of the location within the patient or a function of the direction of the radiotherapy beam in the RTP. The method further includes generating an imaging protocol based on the determined sensitivity measure for acquiring reconstructed CBCT images of the patient's volume. The imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter. The imaging protocol is generated by setting the values ​​of at least one parameter in the imaging protocol such that the image quality of the reconstructed CBCT images of the patient's volume meets an image quality objective for an image processing task. The image quality objective prioritizes image quality at locations within the patient's volume where the RTP is sensitive to changes in anatomical structures.

[0012] According to another aspect of this disclosure, a management node for managing CBCT imaging of a patient is provided. The management node includes processing circuitry configured to acquire RTP information of a radiotherapy unit (RTP). The RTP is used to apply a radiation dose distribution to the patient to achieve at least one radiotherapy objective. The management node is further configured to determine a measure of the sensitivity of the RTP to changes in the patient's anatomical structures based on the acquired RTP information. The sensitivity measure is a function of the location within the patient's body or a function of the direction of the radiotherapy beam in the RTP. The management node is further configured to generate an imaging protocol for acquiring reconstructed CBCT images of the patient's volume based on the determined sensitivity by: setting the value of at least one parameter in the imaging protocol such that the image quality of the reconstructed CBCT images of the patient's volume meets an image quality objective for an image processing task. The image quality objective prioritizes the image quality of locations within the patient's volume where the RTP is sensitive to changes in anatomical structures. The imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter.

[0013] According to another aspect of this disclosure, a computer program product is provided, comprising a computer-readable medium embodying computer-readable code configured to cause the computer or processor, when executed by a suitable computer or processor, to perform a method according to one or more aspects or examples of this disclosure.

[0014] According to another aspect of this disclosure, a radiotherapy device is provided, which includes the management node of this disclosure.

[0015] Therefore, this disclosure provides systems, apparatus, and methods for managing CBCT imaging of patients. By prioritizing image quality at locations within the patient volume where RTP is sensitive to changes in the patient's anatomy, the imaging dose applied to the patient and / or the imaging time for image acquisition and / or reconstruction can be minimized, while acquiring reconstructed CBCT images that meet the image quality requirements for a given image processing task. This current technology thus ensures the accuracy of RT treatment tasks that can be performed based on reconstructed CBCT images.

[0016] Embodiments of this disclosure can be implemented in digital electronic circuits, or in computer hardware, firmware, software, or in combination. Embodiments of this disclosure can be implemented as a computer program or computer program product, i.e., a computer program tangibly embodied in a non-transitory information carrier (e.g., embodied in a machine-readable storage device or a transmitted signal) for execution by or control of one or more hardware modules. The computer program can be a standalone program, a portion of a computer program, or more than one computer program, and can be written in any programming language (including compiled or interpreted languages), and can be deployed in any form (including as a standalone program or as a module, component, subroutine, or other unit suitable for a data processing environment).

[0017] This disclosure is illustrated by way of specific embodiments. Other embodiments not expressly described herein may still fall within the scope of the claims. Unless otherwise expressly or implicitly stated, the steps of the method according to the embodiments of this disclosure may be performed in different orders and still achieve the desired result. Attached Figure Description

[0018] Exemplary embodiments will now be described by way of example only, with reference to the following figures, wherein:

[0019] Figure 1 This is a flowchart of a computer-implemented method for managing CBCT imaging of patients;

[0020] Figure 2 This is a series of images illustrating example methods for managing CBCT imaging in patients;

[0021] Figure 3 It is a geometric layout diagram of cone-beam projection scanning and reconstruction;

[0022] Figure 4 This is a diagram of a cone-beam CT scanner;

[0023] Figure 5 This is a block diagram illustrating the management nodes used to manage CBCT imaging of patients;

[0024] Figure 6 This is a schematic diagram of a radiotherapy device; and

[0025] Figure 7 This is a block diagram illustrating a radiotherapy system suitable for managing CBCT imaging in patients. Detailed Implementation

[0026] Now for reference Figures 1 to 7 Describes all aspects and details of this disclosure.

[0027] Figure 1 This is a flowchart illustrating a computer-implemented method 100 for managing CBCT imaging of a patient according to the present disclosure. Method 100 is designed to meet the need for acquiring high-quality images required for image processing tasks, while minimizing the imaging dose applied to the patient and / or image acquisition and / or reconstruction time. Method 100 can be used for image-guided radiotherapy and / or adaptive radiotherapy.

[0028] At step 102, method 100 includes obtaining radiotherapy planning information for a radiotherapy plan. The RTP is used to apply a radiation dose distribution to the patient to achieve at least one radiotherapy objective. The radiotherapy planning information may refer to information generated during the patient-specific radiotherapy planning process (the process of generating the RTP). RTP information may include one or more of the following: the patient's RTP; the patient's radiation dose distribution; the gradient of the patient's radiation dose distribution (also referred to as dose gradient distribution or dose gradient map); radiation flux map; the patient's dose volume histogram (DVH); the radiation dose applied to the patient as a function of the direction of the radiotherapy beam in the RTP; the monitoring unit (MU) as a function of the direction of the radiotherapy beam in the RTP (e.g., gantry angle or control point of the radiotherapy beam); images of the patient (e.g., CT images or MRI images); segmented images of the patient (e.g., including the target area and one or more OARs); a patient model (e.g., a 3D patient model); the configuration of the radiotherapy system used to apply the radiation dose distribution; one or more parameters used to configure the radiotherapy system (e.g., one or more of the following: RT beam weights, RT beam angles, dose histogram volume information, number of RT beams, dose per RT beam, isocenter and plane of rotation); and the application sequence of the radiotherapy system used to apply the radiation dose distribution.

[0029] RTP information can be obtained by receiving RTP information from another entity or retrieving RTP information from computer memory. Alternatively, obtaining RTP information may include generating RTP information, for example, by performing a radiotherapy planning procedure; performing an optimization procedure; using a machine learning model; and / or performing other methods known in the art for generating radiotherapy planning information.

[0030] At step 104, method 100 includes determining a sensitivity measure of the RTP to changes in the patient's anatomy based on the acquired radiotherapy planning information. The sensitivity measure can be a function of location (e.g., voxel) within the patient's body. For example, the sensitivity measure can be a function of location (i.e., position, e.g., voxel position / location) in an image of the patient (where the image can be included in the RTP information). Alternatively, the sensitivity measure can be a function of the direction of the radiotherapy beam in the RTP.

[0031] Sensitivity measures can represent the degree to which the radiotherapy treatment (RTP) needs to be adjusted to achieve one or more of at least one radiotherapy target due to changes in the patient's anatomy. For example, a sensitivity measure as a function of position within the patient can represent the degree to which the RTP needs to be adjusted due to changes in the patient's anatomy at multiple locations within the patient. As another example, a sensitivity measure as the radiotherapy beam direction in the RTP can represent the sensitivity of the RTP to changes in the patient's anatomy in multiple RT beam directions within the RTP (e.g., at multiple gantry angles or control points within the RTP).

[0032] Sensitivity measures may include one or more of the following: the gradient of the radiation dose distribution as a function of location within the patient; a scale of changes in patient anatomy as a function of location within the patient, such changes requiring adjustment of the RTP to achieve one or more of at least one radiotherapy target; the radiation dose distribution as a function of location within the patient; the radiation applied to the patient as a function of the direction of the radiotherapy beam in the RTP; and a monitoring unit applied according to the RTP as a function of the direction of the radiotherapy beam (i.e., radiation applied to the patient according to the RTP / monitoring unit). The monitoring unit is a measure of the amount of radiation to be applied. As used herein, the dose gradient distribution may include a dose gradient vector field.

[0033] A large dose gradient indicates that the RTP is sensitive to changes in anatomical structure because it indicates a significant change in dose requirement at that location within the patient's body. For example, this location might correspond to the boundary between the PTV and the OAR. Radiotherapy planning will be highly sensitive to changes in the patient's anatomy at this location because moving the OAR to the intended location of the PTV would result in the OAR receiving a significantly higher radiation dose than planned, potentially violating radiotherapy goals. Similarly, if a portion of the PTV moves to the intended location of the OAR, the PTV will receive a lower radiation dose than planned, which could again violate radiotherapy goals. Therefore, this location requires higher image resolution (see step 106), for example, to accurately delineate areas of different dose requirements. Figure 1Example of Method 100 (where sensitivity measures include dose gradient distribution) Reference Figure 2 Describe it.

[0034] Sensitivity metrics can include both dose gradient distribution and radiation dose distribution. Including radiation dose distribution in the sensitivity metric helps identify locations within a patient's body where the radiotherapy plan is sensitive to changes in anatomical structure, because if the dose gradient is high but the dose is low at a given location, changes in the patient's anatomical structure at that location are unlikely to violate any RT treatment goals. For example, the RT treatment goal for RTP might require that the dose applied to the OAR not exceed a threshold. If the dose at a given location mentioned above is significantly below that threshold dose value, changes in the patient's anatomical structure at that location will not violate the RT treatment goal. Therefore, at these locations, image quality does not need to be prioritized (see step 106 below).

[0035] For a given RT beam direction, a larger planned dose (e.g., monitoring unit) applied to the patient indicates that the RTP is sensitive to changes in anatomical structure, as it indicates that the RTP is highly sensitive to anatomical changes for that RT beam direction. This is because if the expected dose value is high (e.g., high MU) for a given RT beam direction, the radiation applied in that RT beam direction is more likely to violate RT treatment goals due to changes in the patient's anatomy than radiation applied in a different RT beam direction with a lower expected dose value (lower MU). For example, if a large dose applied along that RT beam direction is directed at a first location (e.g., a tumor) within the patient, but is instead applied to a second location within the patient due to changes in the patient's anatomy (e.g., due to anatomical movement), the radiotherapy goals may be violated (e.g., because the dose received at the first location is too low to effectively treat the tumor, and / or the second location corresponds to healthy tissue and therefore receives too high a dose). Therefore, for CBCT image acquisitions corresponding to RT beam directions with higher MU values, prioritizing image quality is beneficial (see step 106).

[0036] Changes in a patient's anatomy may include one or more of the following (caused by one or more of the following): soft tissue movement; changes in the shape of soft tissue structures; and changes in the overall patient anatomy. For example, movement of organs or other soft tissues may include periodic movement such as breathing or cardiac movement. Movement of organs or other soft tissues may additionally or alternatively include transient movement, such as movement due to transient bubbles. Changes in the shape of soft tissue structures may include changes in organs and / or radiation therapy target areas (such as tumors). Changes in the overall patient anatomy may include cumulative changes, such as changes due to weight loss, weight gain, muscle growth, muscle loss, surgery, and / or injury.

[0037] Determining the sensitivity measure of RTP to changes in patient anatomy may include performing at least one of the following: an analysis process; an optimization process; and / or a machine learning (ML) process. Using an ML process to determine the sensitivity measure of RTP to changes in patient anatomy may include inputting radiotherapy planning information into an ML model. The ML model is operable to output the sensitivity measure.

[0038] Determining the sensitivity of RTP to changes in patient anatomy may include: obtaining predictions of patient movement during CBCT imaging and / or radiotherapy; and assessing the sensitivity of RTP to the predicted patient movement. For example, if predicted movement at a location within the patient's body would result in a violation of at least one RT treatment objective, that location can be identified as sensitive. Predictions of patient movement can be obtained based on measurements of patient movement (e.g., Michael J. Zelefsky et al., Radiotherapy and Oncology, Vol. 50, No. 2, 1999, pp. 225–234). Predictions of patient movement can be obtained using deep learning models (e.g., Oscar Pastor-Serrano et al., Phys. Med. Biol, 68 085018, 2023).

[0039] Performing the analysis process to determine the 104 sensitivity metric may include using other treatment planning tools, such as plan robustness and plan sensitivity analysis.

[0040] The results of any analytical method mentioned in step 104 can be used to train an AI model to perform step 104. In a further implementation, an optimization process can be used to determine the sensitivity metric. An example of such a method is provided in the literature by Unkelbach J et al., published on November 12, 2018 in Physical Medicine & Biology, 63(22), 30418942.

[0041] At step 106, method 100 includes an imaging protocol for generating reconstructed CBCT images of the patient's volume (i.e., patient volume) based on a determined sensitivity metric. The imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter. Therefore, the imaging protocol can be an image acquisition protocol for acquiring the patient's CBCT projection (for subsequent image reconstruction), and / or an image reconstruction protocol for performing image reconstruction on the acquired CBCT projection to obtain reconstructed CBCT images of the patient.

[0042] The imaging protocol is generated in step 106 by setting the value of at least one parameter in the imaging protocol so that the image quality of the reconstructed CBCT images of the patient meets the image quality target of the image processing task. This image quality target prioritizes image quality at locations within the patient volume where the RTP is sensitive to anatomical changes. The image quality target may prioritize image quality at locations within the patient volume where the RTP is sensitive to anatomical changes, rather than locations within the patient volume where the RTP is less sensitive to anatomical changes. The image quality target may be based on a determined sensitivity metric (e.g., expressed using it). The image quality of the reconstructed CBCT images may include one or more of the following (e.g., expressed using one or more of the following): signal-to-noise ratio (SNR), noise, spatial resolution, contrast resolution, contrast-to-noise ratio (CNR), Hounsfield fidelity, image uniformity, and geometric accuracy.

[0043] Prioritizing image quality at locations within the patient's volume where RTP is sensitive to anatomical changes is beneficial, as the accuracy of image processing tasks is most critical for RT applications (such as accurate RT application) at these locations. For example, the accuracy of image processing tasks (e.g., image reconstruction, contouring, segmentation, deformation, registration) is most important for meeting the RT treatment goals of RTP at these locations.

[0044] At least one CBCT imaging acquisition parameter may include one or more of the following: imaging radiation source position; imaging detector position; imaging projection angle; imaging radiation source intensity; source (e.g., X-ray) tube current for one or more projections; exposure time for one or more projections; imaging radiation source energy for one or more projections; number of projections per gantry angle range; gantry rotation speed for one or more projections; gantry angle range; plane of rotation; isocenter; image projection angle for one or more projections; imaging beam shape for one or more projections; detector offset for one or more projections; detector sensitivity for one or more projections; and detector gain for one or more projections. During a CBCT scan, any one or more of these parameters may vary with different projections (i.e., any of these parameters may be defined for one or more projections, or may be defined as a function of projection angle / number / position). Generating an imaging protocol may include determining the value of at least one of these CBCT imaging acquisition parameters based on the projection angles in the imaging protocol.

[0045] At least one CBCT imaging reconstruction parameter may include one or more of the following: voxel size of one or more regions of the patient volume; number of voxels in one or more regions of the reconstructed CBCT image; voxel density in one or more regions of the reconstructed CBCT image; voxel distribution in one or more regions of the reconstructed CBCT image; one or more regularization terms (in the reconstruction algorithm); number of iterations (in the reconstruction algorithm); and stopping criteria (in the reconstruction algorithm). Any one or more of these parameters may vary at different locations within the imaged volume (i.e., any one of these parameters may be defined for one or more voxels, or may be defined as a function of location in the reconstructed CBCT image). Generating an imaging protocol may include determining the value of at least one of these CBCT imaging reconstruction parameters based on the patient's location in the reconstructed CBCT image.

[0046] Prioritizing image quality at locations within the patient volume where the RTP is sensitive to anatomical changes can be achieved by improving image quality at sensitive locations based on a determined sensitivity metric (e.g., by increasing voxel density at more sensitive locations relative to less sensitive locations). Alternatively, prioritizing image quality at locations within the patient volume where the RTP is sensitive to anatomical changes can be achieved indirectly, for example, by improving image quality at certain CBCT projection angles (such as projection angles with higher sensitivity metrics) relative to lower sensitivity metrics. For example, the source intensity and / or source energy of a CBCT projection with higher sensitivity metrics can be increased relative to the source intensity and / or source energy of a CBCT projection with lower sensitivity metrics. Both direct and indirect methods for prioritizing image quality at locations within the patient volume where the RTP is sensitive to anatomical changes are described in more detail below.

[0047] Image processing tasks involve performing image processing tasks on reconstructed CBCT images of the patient. Image processing tasks may include one or more of the following: image reconstruction, image segmentation, image contouring; identification of target regions; identification of organs at risk; identification of isocenters; identification of isocenter offsets (e.g., due to patient movement); image distortion; and / or image registration (e.g., for tracking patient tissue movement). The confidence level associated with the output of the image processing task may be affected by image quality at locations within the patient volume where RTP is sensitive to changes in anatomical structure.

[0048] Image quality goals may aim to balance a first requirement for optimizing the image quality of reconstructed CBCT images to accomplish the image processing task with one or both of the following: a second requirement for minimizing the total imaging radiation dose administered to the patient during CBCT image acquisition and a third requirement for minimizing the total computation time for image reconstruction. This balance can be achieved by prioritizing the image quality of (i) locations within the patient volume where the RTP is sensitive to anatomical changes, and / or (ii) projections within the CBCT scan where the RTP is sensitive to anatomical changes. For example, image quality goals may drive improvements in the image quality of reconstructed CBCT images at certain locations within the patient volume and / or at projection angles within the CBCT scan to improve the quality and / or robustness of the image processing task, but not to such an extent that the patient receives unnecessarily high imaging doses and / or unnecessarily long computation times. Therefore, image quality goals may reduce the image quality of reconstructed CBCT images at locations within the patient volume where the RTP is less sensitive to anatomical changes and / or at projections within the CBCT scan where the RTP is less sensitive to anatomical changes. For real-time ART, minimizing computation time is particularly advantageous because patient movement can occur rapidly (i.e., within a short period of time). This can include movements caused by breathing, digestion, blood circulation, sneezing, convulsions, etc. Reducing computation time allows for faster tracking of movement and incorporation into adjustments to the RT treatment plan, resulting in more accurate treatment application.

[0049] Image quality objectives can include performance criteria for image processing tasks performed on reconstructed CBCT images. Therefore, ensuring that the image quality of reconstructed CBCT images meets image quality objectives can include ensuring that image processing tasks performed on reconstructed CBCT images of a patient meet performance criteria. For example, for image segmentation, performance criteria can include the maximum level of uncertainty regarding partition boundaries or contours. Therefore, image quality objectives can drive improvements in image quality for locations where segmentation methods struggle to identify partition boundaries (e.g., organ contours) within the patient volume. For example, in model-based segmentation, the level of uncertainty can include a threshold external energy value; for instance, performance criteria can include a requirement that the external energy is below a threshold external energy value. Alternatively, determining whether an image processing task meets performance criteria can include deep learning methods. Mehrtash A et al. provide an example of image segmentation in IEEE Trans MedImaging. 2020 Dec;39(12):3868-3878.

[0050] Image quality targets can be determined based on the patient's planned CT scan, or they can be predefined.

[0051] Locations within the patient volume where RTP is sensitive to anatomical changes may include locations and / or projection angles where sensitivity metrics meet sensitivity criteria. Sensitivity criteria may include one or more of the following: threshold radiation dose gradient; reference-scale anatomical changes in the RTP that will require adjustment to achieve at least one or more of the RT treatment goals; the radiation threshold level to be applied to the patient; and the MU threshold level to be applied to the patient.

[0052] For example, sensitivity criteria may include a threshold dose gradient value, and locations that meet sensitivity criteria may include locations where the gradient of the radiation dose distribution is higher than the threshold dose gradient value. Locations requiring higher quality imaging are characterized by steep dose gradients because this indicates that partitions within the patient body with different needs (e.g., partitions containing tumors versus partitions containing OARs) are relatively close to each other. Sensitivity criteria may exclude dose gradient values ​​at the skin-air interface where a high dose gradient is expected. This is because high-quality images of the skin-air interface are generally not required, as acquiring the external body contour (for dose calculation) requires significantly less radiation than acquiring the internal contour.

[0053] In an example where the sensitivity metric includes a dose gradient distribution, radiotherapy planning information may include the patient's radiation dose distribution, and determining the sensitivity metric may include calculating a gradient of the radiation dose distribution based on its location within the patient's body. The radiation dose distribution may be generated during radiotherapy planning for the patient. Therefore, the radiation dose distribution may be determined based on the radiotherapy plan, or it may be stored during radiotherapy planning.

[0054] Setting the value of at least one parameter in the imaging protocol to satisfy an image quality target may include selecting a value for at least one CBCT imaging acquisition parameter for a projection that satisfies a sensitivity criterion, which differs from the value of at least one CBCT imaging acquisition parameter for a projection that does not meet the sensitivity criterion. For example, a higher imaging intensity; a slower gantry rotation speed; and / or a smaller projection angle spacing may be selected for a projection that satisfies the sensitivity criterion. For some projections, at least one CBCT imaging acquisition parameter value may change abruptly. Alternatively, at least one CBCT imaging acquisition parameter value may change more slowly for different projections (e.g., a continuous function of the CBCT projection direction / angle). In some embodiments, setting the value of at least one CBCT imaging acquisition parameter may include, for example, applying a modulation function (also referred to as a modulation signal) to a set of reference values ​​for at least one CBCT imaging acquisition parameter based on a reference imaging protocol. The modulation function may be selected to satisfy the image quality target. In some examples, radiation depth may be used to determine the parameter value required to obtain a specified image quality (signal-to-noise ratio). This is beneficial for minimizing imaging dose during image acquisition.

[0055] Setting the value of at least one parameter in the imaging protocol to meet image quality targets may include selecting a value for at least one CBCT imaging reconstruction parameter that varies with location (e.g., voxel) within the patient. For example, the value of at least one CBCT imaging reconstruction parameter for a location (e.g., voxel) within the patient that meets sensitivity criteria may differ from the value of at least one CBCT imaging reconstruction parameter for a location (e.g., voxel) that does not meet sensitivity criteria. For example, at least one CBCT imaging reconstruction parameter may include voxel size, and a larger voxel size may be selected for a location / voxel that meets sensitivity criteria compared to a voxel size selected for a location / voxel that does not meet sensitivity criteria. Therefore, the voxel size can be set such that the image quality of the reconstructed CBCT image meets the image quality targets of the image processing task. For example, during real-time ART, this is beneficial for reducing the computation time for image reconstruction.

[0056] Setting the value of at least one parameter in the imaging protocol may include simultaneously setting the values ​​of CBCT imaging acquisition parameters and CBCT imaging reconstruction parameters to achieve a protocol that best meets image quality objectives.

[0057] Setting the value of at least one parameter in the imaging protocol to satisfy an image quality target may include selecting a parameter in the imaging protocol and setting the value of that parameter. In some embodiments, a combination of parameters in the imaging protocol may be selected, and the value of each of these parameters may be set to achieve the image quality target. At least one parameter may be selected based on the premise that the parameter (or combination of parameters) is suitable for adjustment to satisfy the image quality target.

[0058] Setting the value of at least one parameter can include determining the relationship between the parameter and the image quality of the reconstructed image. For example, image quality can be determined for different imaging protocols (and therefore different values ​​for at least one parameter in the imaging protocol). Image quality can be determined using analytical functions that correlate image quality with imaging protocols (e.g., imaging acquisition parameters and / or imaging reconstruction parameters). Those skilled in the art will understand that the relationship between the parameters of an imaging protocol and the image quality of the reconstructed image acquired using that imaging protocol can be analytically derived. Alternatively, one or more ML models can be used to predict the image quality for a given imaging protocol. In some instances, using ML in this way improves processing efficiency and accuracy. Methods for correlating image acquisition parameters with a specific location / region of interest can be based on known methods used for acquiring localization scans for magnetic resonance (MR) and CT acquisitions.

[0059] Setting the value of at least one parameter may include setting a value based on the degree to which the parameter affects the image quality of reconstructed CBCT images of locations within the patient volume that are sensitive to anatomical changes in RTP. For example, a parameter that has a greater impact on the image quality of reconstructed CBCT images of locations within the patient volume that are sensitive to anatomical changes in RTP may be set to a different value than a parameter with a smaller impact.

[0060] Step 106 of generating an imaging protocol for acquiring reconstructed CBCT images of the patient volume by setting the value of at least one parameter in the imaging protocol may include performing one or more of the following: an analysis procedure; an optimization procedure; and / or an ML procedure, as discussed below.

[0061] Step 106, which generates an imaging protocol for the patient, may include generating a new imaging protocol. A new imaging protocol can be generated by mapping a sensitivity metric to parameters of the imaging protocol. The new imaging protocol can be generated based on the planned CT structure and the dose distribution to be applied (e.g., by inputting the planned CT structure and dose distribution into an ML model).

[0062] Setting the value of at least one parameter in the imaging protocol may include mapping a sensitivity metric to that parameter. For example, mapping a sensitivity metric to at least one parameter may include applying a scaling factor. This scaling factor may be determined based on an image quality objective (e.g., to ensure that the image quality objective is met).

[0063] Setting the value of at least one parameter in the imaging protocol may include: determining a modulation function based on a sensitivity metric; and applying the modulation function to at least one parameter (e.g., in a reference imaging protocol) to obtain the imaging protocol. A scalable modulation function ensures that image quality targets are met. For example, determining the modulation function may include applying a scaling factor. The scaling factor may be determined such that the total reconstruction time of the imaging protocol is below a threshold total reconstruction time, and / or that the total imaging dose of the imaging protocol is below a threshold total imaging dose. Reference Figure 2 (c) describes an example of scaling the modulation function in this way. Now, an example of determining the modulation function based on a sensitivity metric is described.

[0064] For example, setting the value of at least one parameter in the imaging protocol may include projecting a determined sensitivity metric (wherein the determined sensitivity metric is a function of location within the patient) according to the geometry of the patient's CBCT imaging to obtain a projected sensitivity metric as a function of the CBCT projection angle. The determined sensitivity metric as a function of location may include a vector field (such as a dose gradient distribution). Projecting the determined sensitivity metric according to the CBCT imaging geometry may include projecting the vector field onto the plane of the CBCT detector according to a projection angle along the CBCT scan arc. Projecting the sensitivity metric according to the CBCT imaging geometry may further include obtaining magnitudes of the in-plane components and optionally averaging them over the detector plane. Thus, the projected sensitivity metric may include the average projected value of the sensitivity metric as a function of the CBCT projection angle.

[0065] Setting the value of at least one parameter in the imaging protocol may further include determining the value of at least one CBCT imaging acquisition parameter based on the CBCT projection angle, according to a projection sensitivity metric and an image quality target. Determining the value of at least one CBCT imaging acquisition parameter may include applying a scaling factor to the projection sensitivity metric such that the image quality of the reconstructed CBCT images of the patient meets the image quality target of the image processing task. For example, at least one CBCT imaging acquisition parameter as a function of the CBCT projection angle may be determined by applying a scaling factor to the average projection value of the sensitivity metric based on the CBCT projection angle. The value of the scaling factor may be determined such that the image quality of the reconstructed CBCT images of the patient (according to the imaging protocol) meets the image quality target of the image processing task. For example, the CBCT imaging acquisition parameter may be the CBCT imaging intensity. Modulating the CBCT imaging intensity in this way based on a planar projection sensitivity metric will result in projections with a larger component of the dose gradient perpendicular to the beam axis using higher intensity. This results in projections using higher beam intensity for imaging-sensitive regions, such as the boundary between high and low doses.

[0066] The determined sensitivity metric may include a radiation dose gradient as a function of location within the patient's body. According to this example, the radiotherapy planning information obtained in step 102 may include the patient's radiation dose distribution (generated during the radiotherapy planning process). The radiation dose distribution can be used (in step 104) to determine a dose gradient distribution corresponding to a sensitivity metric of RTP to changes in anatomical structures (as a function of location within the patient's body). Generating the imaging protocol in step 106 may include: projecting the dose gradient distribution according to the CBCT imaging geometry to obtain a projected dose gradient (referencing...). Figure 2(A more detailed description of an example method for generating the projection dose gradient); and determining the value of at least one CBCT imaging acquisition parameter such that the image quality of the reconstructed CBCT image of the patient meets the image quality objectives of the image processing task. Determining the value of at least one CBCT imaging acquisition parameter may include normalizing the projection dose gradient and using the normalized projection dose gradient to modulate at least one CBCT imaging acquisition parameter according to the CBCT projection angle. For example, the normalized projection dose gradient may be used to modulate the imaging source intensity as a function of the projection angle (such that for projections with a larger component of the dose gradient perpendicular to the beam axis, e.g., a projection with a dose gradient perpendicular to the beam axis, a higher intensity beam is used).

[0067] In another example, projecting the determined sensitivity metric according to the CBCT imaging geometry may include projecting a vector field perpendicular to the detector plane according to the projection angle along the CBCT scan arc. Projecting the determined sensitivity metric according to the CBCT imaging geometry may further include acquiring the magnitude of the out-of-plane component of the sensitivity metric, and optionally averaging the component on the detector plane to obtain an average out-of-plane projection value of the sensitivity metric as a function of the CBCT projection angle. Thus, the projection sensitivity metric may include an average out-of-plane projection value of the sensitivity metric as a function of the CBCT projection angle. Setting the value of at least one parameter in the imaging protocol may include determining the value of at least one CBCT imaging acquisition parameter based on the projection sensitivity metric and image quality targets according to the CBCT projection angle. Determining the value of at least one CBCT imaging acquisition parameter may include applying a scaling factor to the projection sensitivity metric such that the image quality of the reconstructed CBCT image of the patient meets the image quality targets of the image processing task. The value of the scaling factor may be determined such that the image quality of the reconstructed CBCT image of the patient (according to the imaging protocol) meets the image quality targets of the image processing task. For example, the CBCT imaging acquisition parameter may be the density of the CBCT projection angle along the CBCT scan arc. Modulating CBCT angular density in this way, based on an out-of-plane projection sensitivity metric, results in higher projection density when the projection travels through sensitive regions, such as the boundary between high and low doses. Alternatively, the CBCT imaging acquisition parameter can be the gantry rotation speed along the CBCT scan, and the value of the gantry rotation speed can be determined based on the out-of-plane projection sensitivity metric, such that a higher out-of-plane projection sensitivity metric corresponds to a slower rotation speed (i.e., an inverse relationship). This results in the use of a slower gantry rotation speed when the projection travels through sensitive regions.

[0068] In another example, setting the value of at least one parameter in the imaging protocol may include determining the value of at least one CBCT imaging reconstruction parameter based on location within the patient volume, using a determined sensitivity metric (where the determined sensitivity metric is a function of the location across the patient volume) and an image quality target. Determining the value of at least one CBCT reconstruction acquisition parameter may include applying a scaling factor to the determined sensitivity metric such that the image quality of the reconstructed CBCT image of the patient meets the image quality target of the image processing task. For example, the determined sensitivity metric may include a radiation dose gradient as a function of location within the patient volume, and at least one CBCT imaging reconstruction parameter may include voxel density in the reconstructed image. Thus, the dose gradient can be used to modulate the voxel density based on location in the reconstructed image (such as using a higher voxel density in reconstructions of locations within the patient volume where RTP is sensitive to anatomical changes).

[0069] In another example, setting the value of at least one parameter in the imaging protocol may include determining the value of at least one CBCT imaging reconstruction parameter based on the CBCT projection angle, according to a determined sensitivity metric (where the determined sensitivity metric is a function of the RT beam direction in the RTP) and an image quality target. For example, the MU of each control point / gantry angle of the RTP (e.g., for VMAT application) may be mapped to the intensity of the CBCT projection in the imaging protocol (as a function of the CBCT projection angle).

[0070] As a further example, sensitivity metrics (e.g., normalized projection dose gradients) can be used to modulate the number of iterations in the reconstruction algorithm (so that more iterations are used when reconstructing projections that are sensitive to changes in anatomical structures in the RTP, thus prioritizing the image quality of these projections).

[0071] In each example, the mapping of sensitivity metric to the value of at least one parameter can be determined such that the image quality of the patient's reconstructed CBCT images meets the image quality target of the image processing task.

[0072] Step 106 of generating an imaging protocol may include generating multiple candidate imaging protocols for the patient; and selecting one of the multiple candidate imaging protocols. One of the multiple candidate imaging protocols may be selected based on selection criteria, which may include at least one of the following: total imaging radiation dose conforming to the candidate imaging protocol; image quality of the reconstructed image conforming to the candidate imaging protocol; total imaging and / or reconstruction time conforming to the candidate imaging protocol; and the extent to which the candidate imaging protocol meets the image quality target. The selection criteria may include multiple criteria and a priority ranking. For example, if two candidate imaging protocols meet the criteria for priority ranking as first priority to the same extent, then the criteria ranked as second priority are considered.

[0073] Step 106, which generates an imaging protocol for the patient, may include selecting an imaging protocol from a set of predefined imaging protocols. For example, step 106 may include determining which of the predefined imaging protocols will provide reconstructed CBCT images of the patient, wherein the image quality of the reconstructed CBCT images of the patient meets the image quality objectives of the image processing task.

[0074] Generating an imaging protocol by performing an optimization process (in step 106) may include applying an optimization procedure to the imaging protocol. This optimization procedure may attempt to optimize the imaging protocol to the extent that it meets image quality objectives for the image processing task by adjusting at least one parameter in the imaging protocol. These image quality objectives prioritize image quality at locations within the patient volume where the RTP is sensitive to changes in anatomical structure (which may be determined based on a sensitivity metric). Optimization may be subject to one or more constraints. These constraints may include, for example, one or more of the following: the maximum total imaging dose of the imaging protocol; the maximum total image acquisition time of the imaging protocol; the maximum total reconstruction computation time of the imaging protocol; physical constraints (e.g., system / hardware constraints); clinical constraints; and image quality constraints (e.g., based on the determined sensitivity metric). Any suitable optimization algorithm may be used, such as gradient descent.

[0075] The optimization process can be performed by an optimizer. The optimizer's input can include one or more of the following: a cost function, one or more optimizable parameters, one or more constraints, and a reference objective for optimization. The reference objective can include an image quality objective of the image processing task. The reference objective can include one or more further objectives of the imaging protocol. One or more optimizable parameters can include at least one parameter in the imaging protocol. The cost function can include terms representing the reference objective and / or one or more constraints. For example, the cost function can include a mathematical expression representing the extent to which the imaging protocol satisfies the image quality objective of the image processing task. The cost function can include the difference between the expected image quality and the desired image quality that meets the image quality objective. The image quality objective, cost function, and / or constraints can be based on a determined sensitivity metric (e.g., expressed using it). The image quality acquired by the imaging protocol can be defined according to the performance criteria of the image processing task. The image quality acquired by the imaging protocol can be defined, for example, based on signal-to-noise ratio level, directional signal-to-noise ratio level, gradient uncertainty, spatial resolution test, and / or Henle unit (HU) uncertainty. The image quality acquired by the imaging protocol can be used to determine the corresponding uncertainty of the outcome of the image processing task (e.g., image segmentation) and the impact of this uncertainty on the quality of the radiotherapy plan. Therefore, the cost function may include RTP quality metrics, such as dose-related metrics, like the uncertainty of the calculated / expected treatment dose. As mentioned above, one or more constraints may include one or more of the following: the maximum total imaging dose of the imaging protocol; the maximum total image acquisition time of the imaging protocol; the maximum total reconstruction computation time of the imaging protocol; physical constraints (e.g., system / hardware constraints); clinical constraints; and image quality constraints (e.g., based on a determined sensitivity metric).

[0076] The optimizer's output may include the value of at least one parameter in the imaging protocol, and (optionally) the result of an image quality target. To determine the output, the optimizer may change the optimizable parameters to minimize the cost function.

[0077] Step 106, which generates an imaging protocol for the patient, may include adjusting a reference imaging protocol, for example, using an analysis or iterative optimization process. For example, at least one parameter in the reference imaging protocol may be iteratively changed until the imaging protocol is optimized according to image quality targets. In some embodiments, previously acquired CBCT images may be used to adjust the acquisition parameters. For example, previously acquired CBCT images may be CBCT images from previous fractions of the patient's radiotherapy.

[0078] Generating 106 imaging protocols for a patient using the ML process may include inputting: (i) TP information; and (ii) image quality targets for the image processing task into the ML model. The ML model is operable to output an imaging acquisition protocol for acquiring reconstructed CBCT images of the patient that meet the image quality targets for the image processing task.

[0079] Method 100 may further include an imaging protocol for training an ML model to generate reconstructed CBCT images for acquiring patient volumes by: (i) generating training data for training the ML model; and (ii) updating trainable parameters of the ML model using the training data. Generating training data for the ML model may include (for multiple patients): performing analysis and / or optimization procedures. Figure 1 Steps 102 to 106 involve generating an imaging acquisition protocol for the patient and adding radiotherapy planning information, image quality targets for image processing tasks, and the imaging acquisition protocol generated for the patient's CBCT imaging to the training dataset.

[0080] In some examples, generating training data for an ML model may involve generating training data using a plan robustness assessment, where at least one parameter in the imaging protocol changes, and an image processing task is performed on reconstructed CBCT images corresponding to each imaging protocol. Reconstructed CBCT images for each imaging protocol can be simulated based on the (planned) CT. For each simulated CBCT image, an image quality objective for the image processing task can be evaluated. For example, the image processing task could be organ segmentation, and the image quality objective could be expressed using performance metrics for organ segmentation (e.g., uncertainty in the generated contours) and total imaging dose. This data can then be used to train the ML model.

[0081] Method 100 may further include initiating CBCT imaging of the patient according to the generated imaging protocol. Initiating CBCT imaging of the patient may include outputting the generated imaging protocol to, for example, a processor and / or an imaging system.

[0082] In short, Figure 1 Method 100 provides an improved approach for managing CBCT imaging. By taking into account the sensitivity of RTP to changes in patient anatomy, an imaging protocol is generated that prioritizes image quality at locations where accurate image processing is most needed for precise RTP application (e.g., locations most useful to clinicians). This reduces the imaging dose applied to the patient and / or the imaging time for acquisition and / or reconstruction compared to existing methods, while still enabling accurate image processing and RTP application.

[0083] Figure 2 These are a series of images illustrating methods according to some embodiments of this disclosure. Figure 2The method shown can correspond to Figure 1 Method 100.

[0084] Figure 2 (a) Depicts the radiation dose distribution to be applied to the patient according to a volumetric intensity-modulated arc therapy (VMAT) radiotherapy plan for the treatment of prostate cancer. The RTP was created in a planning CT scan of the three-dimensional patient volume. Figure 2 The image shown in (a) is the axial dose distribution. The dose is described as a grayscale color map, with darker colors indicating higher doses. Solid lines delineate regions such as PTV 201 (containing the prostate cancer cells to be treated), OAR 202 (containing the rectum), and the right femoral head 203a and left femoral head 203b. Figure 2 The dose distribution depicted in (a) is determined during the patient's treatment planning process, i.e., when the radiotherapy plan is generated. Figure 2 (a) The radiation dose distribution can correspond to radiotherapy planning information (such as in the reference). Figure 1 (As described in step 102 of method 100).

[0085] Figure 2 The 3D dose distribution depicted in (a) was used to determine the sensitivity measure of RTP to changes in patient anatomy (corresponding to...). Figure 1 (Step 104 in the original text). For this, the radiation dose gradient within the patient volume (i.e., the volume defined by the 3D dose distribution) needs to be calculated. This produces a vector field that includes the 3D dose gradient vector for each voxel in the patient volume. The high dose gradient at the skin-air interface (where the planned dose decreases rapidly) is excluded from the dose gradient calculation, allowing subsequent analysis to focus on dose changes within the body, rather than at the skin-air interface.

[0086] (Clipped) dose gradient vector field in Figure 2 (b) is represented as a grayscale image, showing the magnitude of the dose gradient along the axial plane. The darkest areas represent the highest dose gradient values. In other words, the darkest areas are those with the greatest rate of change in dose (the dose to be applied to the patient according to the radiotherapy plan). Figure 2As shown in (b), region 204, including the maximum dose gradient, is located at the boundary between the prostate and rectum, i.e., the prostate-rectum interface. This is a critical delineation area in radiotherapy planning because the prostate is part of PTV 201, while the rectum is part of OAR 202. Therefore, the dose distribution changes drastically at the identified boundary, and sufficient image quality is essential for accurately delineating this boundary for RT applications (e.g., for IGRT, ART, etc.). The consequence of this drastic dose change is that minor changes in patient anatomy (e.g., due to patient movement, weight gain, digestive, urinary processes, etc.) may be sufficient to prevent the radiotherapy plan from achieving its objectives. In other words, in regions with high dose gradients, RTP is sensitive to changes in anatomy. For example, a primary goal of RTP may include applying a minimum dose to PTV 201 to effectively treat the tumor. If the patient's anatomy changes between treatment planning and dose application, and this change causes a portion of PTV 201 to move across the identified boundary into the low-dose region of OAR 202, the dose applied to PTV 201 during treatment may drop below the minimum dose, thus violating the first RT treatment objective. A second objective of RTP may include an upper limit on the dose that can be applied to OAR 202, for example, limiting damage to the rectum during treatment. If a change in patient anatomy causes a portion of OAR 202 to move into the high-dose region intended for PTV 201, the dose applied to OAR 202 may exceed the upper limit, thus violating the second RT treatment objective. Because the dose change occurs abruptly at the identified boundary (i.e., the dose gradient is high in this region), the change in patient anatomy only needs to be small to violate RTP. In other words, at the boundary, RTP is very sensitive to changes in patient anatomy, and the dose gradient provides a measure of this sensitivity. A threshold dose gradient value (and optionally, a threshold dose) can be used as a sensitivity criterion to identify locations within the patient volume where RTP is sensitive to changes in anatomy. It should be understood that, despite Figure 2 (b) The dose gradient is depicted in two dimensions, but the determined dose gradient is defined in three-dimensional space.

[0087] An imaging protocol is then generated to acquire reconstructed CBCT images of the patient volume. The reconstructed CBCT images can be used for IGRT and / or adaptive radiotherapy. Therefore, the reconstructed CBCT images can be used to ensure the correct dose is applied to different regions of the patient to meet RT treatment goals. Image quality is more important in regions with high dose gradients than in regions with low dose gradients because these regions are more prone to RTP violations due to changes in patient anatomy. Therefore, accurately understanding the patient anatomy at locations within the patient volume where RTP is sensitive to anatomical changes is more important than accurately understanding the patient anatomy at other locations in the reconstructed images. In this example, the generated imaging protocol is an image acquisition protocol. Prioritizing image quality at locations within the patient volume where RTP is sensitive to anatomical changes during imaging protocol generation minimizes the imaging dose while still acquiring sufficient data to generate reconstructed CBCT images with sufficient detail for accurate IGRT and / or adaptive radiotherapy. The generated imaging protocol can correspond to... Figure 1 Step 106.

[0088] To generate the imaging protocol, the following steps need to be performed:

[0089] (i) Dose gradient vector field Figure 2 (b) is depicted as being projected onto the detector plane to achieve different CBCT projection angles (i.e., the angular positions of the imaging source and the imaging detector along the CBCT scan arc). The magnitude of the projected dose gradient vector is determined based on its position on the detector plane.

[0090] (ii) Apply a tapered filter to make the projected dose gradient near the detector center more important than the projected dose gradient near the detector edge (because the region that is sensitive to changes in anatomy and is beneficial for high-quality images is closer to the detector center). Other types of filters can also be used to achieve this purpose.

[0091] (iii) Calculate the average intensity value of each projection by averaging the detector plane.

[0092] (iv) The average intensity value (i.e., the average projected dose gradient intensity) is normalized (i.e., scaled) according to a certain standard to provide a normalized average intensity function. This standard may correspond to a reference... Figure 1 The image quality target is described (the normalization steps used in this example will be described in more detail below). Figure 2 (c) The normalized average intensity function (a function of the number of projections) is plotted. In this example, the projections are equidistantly distributed along the CBCT scan arc, such that the number of projections is proportional to the projection angle on the scan arc.

[0093] (v) A normalized average intensity function is used to modulate the imaging source tube current (mA) in a reference CBCT image acquisition protocol. This provides the image acquisition protocol.

[0094] Examples disclosed herein may include performing one or more of the steps described above.

[0095] Figure 2 The dose gradient projection intensities plotted in (c) indicate the projections with the highest in-plane dose gradients. These projections with the highest in-plane dose gradients are those that capture adjacent locations where significant changes in the patient's dose requirement have occurred (indicating that the RTP is sensitive to changes in the patient's anatomy). Therefore, it is more advantageous to prioritize the image quality of these projection angles over those with lower in-plane dose gradients.

[0096] To achieve this, Figure 2 The normalized average intensity plotted in (c) is used as the modulation function of the imaging source current in the imaging protocol for subsequent CBCT acquisition. In this case, the normalization step mentioned above includes normalizing the average dose gradient projection intensity function so that image quality targets are met when the normalized function is used to modulate the source current. In this example, the image quality target requires optimizing the image quality of the reconstructed CBCT image to complete image processing tasks (e.g., image segmentation, image registration) based on the requirement that the total imaging dose applied to the patient by the CBCT imaging protocol does not exceed a threshold. The requirement to optimize the image quality for image segmentation and / or image registration is achieved by using the normalized function in the imaging protocol. Figure 2 The normalized average intensity modulated imaging source current in (c) is satisfied because it ensures that higher source currents are used for imaging of the projections that contribute most to imaging sensitive areas within the patient (important for image segmentation / registration), thus improving image quality in these areas (e.g., improving CNR, SNR, spatial resolution, etc.). Therefore, the normalization (i.e., scaling factor) of the average dose gradient projection intensity function is determined such that the total imaging dose applied to the patient by the CBCT image acquisition protocol does not exceed a threshold when the imaging source tube current in the reference CBCT image acquisition protocol is modulated by the normalized average intensity. Thus, the image quality target is met.

[0097] To demonstrate the advantages of this method, CBCT image reconstruction of patient volume was simulated under three different imaging protocols, and the results are as follows: Figure 2 (d) Figure 2 (e) and Figure 2 As shown in (f).

[0098] Figure 2(d) shows an axial view of a simulated reconstructed CBCT image of the patient volume acquired using a reference CBCT imaging protocol (where the imaging intensity has not yet been modulated according to the method described above). This reconstruction is referred to as the baseline. The prostate-rectum interface 205 imaged in the baseline reconstruction is pixelated and difficult to discern.

[0099] Figure 2 (e) shows an axial view of a simulated reconstructed CBCT image of the patient volume obtained by increasing the imaging intensity in the reference CBCT imaging protocol by 100% for all projections. The prostate-rectum interface 206 is much clearer in this reconstruction compared to the baseline reconstruction, but the total imaging dose applied to the patient is doubled.

[0100] Figure 2 (f) shows the method by Figure 2 (c) An axial view of a simulated reconstructed CBCT image of the patient volume obtained by modulating the imaging intensity in a reference CBCT imaging protocol using a normalized mean intensity function. The image quality around the prostate-rectum interface 207 is again superior to the baseline reconstruction (e.g., measured by signal-to-noise ratio, uncertainty in interface location, and steepness of the intensity gradient), but the total imaging dose is now only 38% higher than the baseline reconstruction. Therefore, the method disclosed herein allows for accurate delineation of adjacent PTV and OAR regions at the prostate-rectum interface while administering a lower total imaging dose to the patient (e.g., relative to the baseline reconstruction). Figure 2 (e) Acquisition protocol). Accurate delineation of these regions is crucial for detecting whether the prostate-rectum interface has shifted or changed between radiotherapy planning and radiotherapy application. If so, CBCT images can be used for patient repositioning (e.g., IGRT) and / or adjustment of radiotherapy plans (e.g., ART).

[0101] exist Figure 2 In the example method described, the imaging acquisition protocol is generated by modulating the imaging intensity in the reference imaging acquisition protocol. However, it should be understood that one or more other parameters in the imaging acquisition protocol can be modulated (alternatively or alternatively), such as the projection sampling density along the scan arc (i.e., the number of projections at each gantry angular position) or the gantry rotation speed. For example, by increasing the sampling density of the projections with the highest projection dose gradient intensity (or decreasing the gantry rotation speed), improved image quality can be achieved at locations within the patient's body where the radiotherapy plan is sensitive to changes in the patient's anatomy.

[0102] In addition, according to Figure 2 The method described herein, the imaging acquisition protocol is obtained by referencing a reference imaging acquisition protocol (corresponding to...) Figure 2(d) The baseline reconstruction is generated by starting with and modulating one of the imaging acquisition parameters (imaging intensity). However, in an alternative implementation, the imaging acquisition protocol can be generated from scratch.

[0103] Figure 2 The imaging protocol generated in the method is an imaging acquisition protocol. In an alternative implementation, the imaging protocol can be an imaging reconstruction protocol. For example, image quality goals can be met by increasing the voxel density at locations within the patient volume that are sensitive to changes in anatomical structure via RTP (e.g., reducing voxel size) (e.g., scaling voxel density by a sensitivity metric as a function of location within the patient).

[0104] Figure 3 The geometry of a typical cone-beam projection acquisition device is shown, which can be used for image acquisition and image reconstruction techniques according to the techniques disclosed herein. For simplicity, only the xy-plane is shown; skilled readers will understand that the beam also extends to the z-axis perpendicular to the xy-plane. In this example, the acquisition device captures projection data of an object 302 (e.g., a patient). An X-ray source 304 generates and emits X-rays 306 to the object 302. In CBCT, X-rays can be considered as beams of light emitted from a point source. Detectors (or multiple detectors) 308 capture the projections, which are a set of line integrals along the path radiated from the source 304. Multiple projections of the image can be acquired from different angles by rotating the source 304 and detectors 308 around the center of the image 310. In this example, the source 304 and detectors 308 can be rotated in an arc along an orbital path 312 (referred to herein as the scan arc or CBCT scan arc). In this way, the xy-plane can be rotated counterclockwise around the origin (or the center of image 310) to maintain the relative positional relationship between the light source 304 and the detector 308 while traversing the orbital path 312. Of course, other configurations of the imaging system are possible; for example, the light source can be configured to rotate, and a full circle of detectors can be configured to capture the projection, or multiple light sources can be arranged circumferentially around a full circle of detectors. Furthermore, the imaging system can rotate the light source along a helical path to capture projection data along the axis of the object of interest 302 (along the z-axis in this example).

[0105] The attenuation of the intensity of rays passing through object 302 can be measured by processing the signal received from detector 308. By performing a series of projection measurements on object 302 at different projection angles, a sine curve can be constructed from the projection data, mapping the spatial dimension of the detector array to the projection angle dimension. The intensity attenuation caused by a specific volume within the object will be depicted as a sine wave along the spatial dimension of the detector perpendicular to the system's rotation axis. The sine wave amplitude corresponding to object volumes farther from the rotation center is greater than that corresponding to object volumes closer to the rotation center. The phase of each sine wave in the sine curve corresponds to its relative angular position with respect to the rotation axis. An image can be reconstructed by performing image reconstruction techniques (such as the inverse Radon transform) on the projection data in the sine curve, where the reconstructed image corresponds to a cross-sectional slice or volume of object 302. Detector 308 may include underlying detector elements (such as pixels or pixel boxes) rather than a single active region. The measured ray intensity can then be considered as a function of the underlying intensity signal acquired on the detector elements of the detector. This has the advantage of reducing the influence of random noise, which can interfere with the intensity (especially low intensities) measured on a single detector element. For example, the measured radiation intensity can be the average (mean, mode, or median) of the intensity of the individual detector elements at the bottom layer.

[0106] Figure 4 The geometry of a cone-beam projection acquisition device is shown, which is incorporated into a medical CT scanner 400. A radiation source 404 within the CT scanner (not depicted) emits an X-ray beam that passes through a patient supported on an examination table. A detector 408 captures the attenuated X-rays. The radiation source 404 and detector 408 can be configured to rotate within the CT scanner gantry to acquire projection measurements at a range of different projection angles.

[0107] CBCT image acquisition protocols typically involve CBCT projection at equidistant locations along the scan arc with constant intensity and energy. However, as... Figure 4 As shown, the angular intervals between measurement orientations need not be equal. For example, according to the embodiments disclosed herein, higher density projection angles can be used to improve the image quality of reconstructed CBCT images and prioritize image quality at locations within the patient's body where RTP is sensitive to anatomical changes. For the remainder of the rotation, a set of densely sampled projections within a small sub-arc can be combined with projections of lower sampling density to obtain improved image quality in some desired areas while minimizing imaging dose. Francien G. Bossema's paper, "Optimization of Projection Angle Selection in Computed Tomography" (Master's Thesis in Mathematics, Leiden University), provides information on optimizing projection angle selection in computed tomography.

[0108] Image reconstruction methods can take into account the curvature within the gantry (or the gantry itself). For example, in one implementation, curvature can be considered when determining the location where the isocentric ray strikes the detector. The method can then determine the intensity at the isocentric location through interpolation.

[0109] Return to reference Figure 1 and Figure 2 The method, the imaging protocol generated in step 106, may include methods for using the above-mentioned... Figure 3 and Figure 4 The apparatus described herein acquires an imaging acquisition protocol for projected images. The imaging protocol generated in step 106 may (additionally or alternatively) include methods for acquiring images based on the above description. Figure 3 and Figure 4 The image reconstruction protocol described herein uses the apparatus to acquire projected images and generate reconstructed CBCT images.

[0110] Figure 5 This is a block diagram illustrating an example management node 500 according to an example of the present disclosure, which can implement... Figure 1 Method 100 is shown. For example, management node 500 can implement this after receiving appropriate instructions from computer program 550. Figure 1 Method 100.

[0111] refer to Figure 5 The management node 500 includes a processor or processing circuitry 502, and may include a memory 504 and an interface 506. The processing circuitry 502 is operable to perform the functions described in the reference above. Figure 1 The discussion covers some or all of the steps of method 100. Memory 504 may contain elements executable by processing circuitry 502, enabling management node 500 to perform... Figure 1 Instructions for some or all of the steps of method 100 shown. These instructions may also include instructions for performing one or more telecommunications and / or data communication protocols. The instructions may be stored in the form of a computer program 550. In some examples, the processor or processing circuitry 502 may include one or more microprocessors or microcontrollers, and other digital hardware that may include digital signal processors (DSPs), application-specific digital logic, etc. The processor or processing circuitry 502 may be implemented by any type of integrated circuit, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA). The processor or processing circuitry 502 may include a graphics processing unit (GPU). The memory 504 may include one or more types of memory suitable for the processor, such as read-only memory (ROM), random access memory, cache memory, flash memory devices, optical storage devices, solid-state drives, hard disk drives, etc.

[0112] In some examples discussed above, a management node may be incorporated into the radiotherapy apparatus, and examples of this disclosure also provide a radiotherapy device including a management node as discussed above. The radiotherapy apparatus can be used for image-guided RT and / or radiotherapy-guided arthroplasty (ART).

[0113] Figure 6 A radiotherapy apparatus suitable for performing radiotherapy and / or image acquisition is depicted. A cross-section through the radiotherapy apparatus 600 includes a radiation head 610 and a beam receiving device (detector) 602, both of which are attached to a rack 604. The radiation head 610 includes a radiation source 612 that emits a radiation beam 606. The radiation head 610 also includes a beam shaping device 618 that controls the size and shape of the radiation field associated with the beam.

[0114] The beam receiving device 602 is configured to receive radiation emitted from the radiating head 610 for the purpose of absorbing and / or measuring the radiated beam. In the view shown, the radiating head 610 and the beam receiving device 602 are positioned radially opposite each other.

[0115] The rack 604 is rotatable and supports the radiation head 610 and beam receiver 602, allowing them to rotate about a rotation axis 608 that coincides with the patient's longitudinal axis. The rack provides rotation of the radiation head 610 and beam receiver 602 in a plane perpendicular to the patient's longitudinal axis (e.g., the sagittal plane). Three rack orientations can be defined. , , , making The direction is perpendicular to the frame rotation axis. The direction extends from the point on the gantry corresponding to the radiator head 610 towards the rotation axis of the gantry. Therefore, from the patient's reference frame, The direction rotates as the frame rotates.

[0116] The radiotherapy apparatus 600 also includes a support surface or examination table 620 on which the subject (or patient) is supported during radiotherapy or image acquisition. The radiation head 610 is configured to rotate about a rotation axis 608, such that the radiation head 610 directs radiation toward the subject from various angles around the subject to distribute the radiation dose received by healthy tissue over a larger area of ​​healthy tissue while establishing a prescribed radiation dose at the target area.

[0117] The radiotherapy device 600 is configured to apply a radiation beam toward a radiation isocenter, which is located approximately on the rotation axis 608 at the center of the gantry 604, regardless of the placement angle of the radiation head 610.

[0118] The dimensions of the rotatable frame 604 and the radiator head 610 are designed to allow for a central hole 622. The central hole 622 provides an opening large enough to allow the subject to be positioned without accidentally contacting the radiator head 610 or other mechanical components as the frame rotates around the subject.

[0119] A radiation head 610 emits a radiation beam 606 along a beam axis 624 (or radiation axis or beam path), wherein the beam axis 624 defines the direction of radiation emitted by the radiation head 610. The radiation beam 606 is incident on a beam receiving device 602, which may include at least one of a beam blocker and / or a radiation detector. The beam receiving device 602 is attached to a frame 604 on the diameter-opposite side of the radiation head 610 to attenuate and / or detect the radiation beam after it has passed through a subject.

[0120] The axis 624 of the radiation beam can be defined, for example, as the center or the point of maximum intensity of the radiation beam 606.

[0121] Beam shaping device 618 limits the diffusion range of radiated beam 606. Beam shaping device 618 is configured to adjust the shape and / or size of the radiation field generated by the radiation source. Beam shaping device 618 achieves this by defining a variable-shaped aperture (also referred to as a window or opening) to collimate radiated beam 606 into a selected cross-sectional shape. In this example, beam shaping device 618 may be provided by a combination of a diaphragm and an MLC. Beam shaping device 618 may also be referred to as a beam corrector.

[0122] The radiotherapy device 600 can be configured to provide both coplanar and non-coplanar (also known as tilted) radiotherapy modes. In coplanar treatment, radiation is emitted in a plane perpendicular to the rotation axis of the radiation head 610. In non-coplanar treatment, radiation is emitted at an angle not perpendicular to the rotation axis. To apply coplanar and non-coplanar treatment, the radiation head 610 can be moved between at least two positions, one where radiation is emitted in a plane perpendicular to the rotation axis (coplanar configuration) and the other where radiation is emitted in a plane not perpendicular to the rotation axis (non-coplanar configuration).

[0123] In a coplanar configuration, the radiator 610 is positioned to rotate about a rotation axis in a first plane. In a non-coplanar configuration, the radiator is tilted relative to the first plane, such that the radiation field generated by the radiator is oriented at an angle of tilt relative to the first plane and the rotation axis. In a non-coplanar configuration, the radiator 610 is positioned to rotate in a corresponding second plane that is parallel to and offset from the first plane. The radiation beam is emitted at an angle of tilt relative to the second plane, and therefore the beam sweeps out in a cone shape as the radiator rotates.

[0124] In one configuration, when the radiotherapy equipment is in both coplanar and non-coplanar modes, the beam receiving device 602 can be held in the same position relative to the rotatable gantry. Therefore, the beam receiving device 602 is configured to rotate about a rotation axis in the same plane in both coplanar and non-coplanar modes. This can be the same plane as the plane in which the radiation head rotates. In an alternative configuration, the beam receiving device 601 can also be rotated.

[0125] The beam shaping device 610 is configured to reduce the diffusion of the radiation field in a non-coplanar configuration compared to a coplanar configuration.

[0126] The radiotherapy apparatus 600 includes a controller 630, which is programmed to control a radiation source 612, a beam receiving device 606, and a gantry 602. The controller 630 can perform functions or operations such as radiotherapy planning, treatment execution, image acquisition, image processing, motion tracking, motion management, and / or other tasks involved in the radiotherapy process.

[0127] The controller 630 is programmed to control various components of the device 600, such as the frame 604, the radiator 610, the beam receiving device 602, and the support surface 620, in order to acquire projection data (i.e., the projected image) suitable for image reconstruction.

[0128] The hardware components of controller 630 may include one or more computers (e.g., general-purpose computers, workstations, servers, terminals, portable / mobile devices, etc.); processors (e.g., central processing units (CPUs), graphics processing units (GPUs), microprocessors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), dedicated or specially designed processors, etc.); memory / storage devices, such as memory (e.g., read-only memory (ROM), random access memory (RAM), flash memory, hard disk drives, optical disks, solid-state drives (SSDs), etc.); input devices (e.g., keyboards, mice, touchscreens, microphones, buttons, knobs, trackballs, joysticks, handles, controllers, etc.); output devices (e.g., displays, printers, speakers, vibration devices, etc.); circuitry; printed circuit boards (PCBs); or other suitable hardware. The software components of controller 630 may include operating device software, application software, etc.

[0129] The radiator 610 may be connected to a head actuator 614, which is configured to actuate the radiator 610, for example, between a coplanar configuration and one or more non-coplanar configurations, or, for example, to actuate the radiation source 612 and / or detector 602 in response to the detection of bending. This may involve translation and rotation of the radiator 610 relative to the rack. In some implementations, the head actuator may include a curved guide along which the radiator 610 may move to adjust the position and angle of the radiator 610. A controller 630 may control the configuration of the radiator 630 via the head actuator 614.

[0130] Beam shaping apparatus 618 includes a shaping actuator 616. The shaping actuator is configured to control the position of one or more elements in beam shaping apparatus 618 to shape radiation beam 606. In some implementations, beam shaping apparatus 616 includes an MLC (Multi-Layer Cylinder), and shaping actuator 616 includes means for actuating blades of the MLC. Beam shaping apparatus 618 may further include a diaphragm, and shaping actuator 616 may include means for actuating a diaphragm block. Controller 630 may control beam shaping apparatus 618 via shaping actuator 616.

[0131] Figure 7 This is a block diagram illustrating an implementation of a radiotherapy system 700 suitable for performing CBCT imaging of a patient volume according to an embodiment. For example, the radiotherapy system 700 includes a computing system 710, in which a set of instructions can be executed to cause the computing system 710 to perform the methods (or steps thereof) discussed herein. The computing system 710 can implement a CBCT imaging management system. The computing system 710 may also be referred to as a controller. Specifically, the methods described herein can be implemented by a processor or controller circuitry 711 of the computing system 710.

[0132] The computing system 710 should be considered as including any number or set of machines, such as computing devices, that individually or collectively execute a set (or more sets) of instructions to perform any one or more methods discussed herein. That is, the hardware and / or software may be housed in a single computing device or distributed across multiple computing devices within the computing system. In some implementations, one or more elements of the computing system may be connected (e.g., networked to) other machines, such as a local area network (LAN), intranet, extranet, or the Internet. One or more elements of the computing system may operate as a server or client computer in a client-server network environment, or act as a peer-to-peer computer in a peer-to-peer (or distributed) network environment. One or more elements of the computing system may be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), cellular phone, network appliance, server, network router, switch, or bridge, or any machine capable of executing a set of instructions (executed sequentially or otherwise) specifying the actions to be taken by that machine.

[0133] The computing system 710 includes controller circuitry 711 and memory 713 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), such as synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM). Memory 713 may include static memory (e.g., flash memory, static random access memory (SRAM), etc.) and / or auxiliary memory (e.g., data storage devices), which communicate with each other via a bus (not shown). Memory 713 can be used to store or buffer projected data until image processing is required.

[0134] The controller circuit 711 represents one or more general-purpose processors, such as microprocessors, central processing units, accelerated processing units, etc. More specifically, the controller circuit 711 may include a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor implementing combinations of instruction sets. The controller circuit 711 may also include one or more special-purpose processing devices, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, etc. The one or more processors of the controller circuit may have a multi-core design. The controller circuit 711 is configured to execute processing logic for performing the operations and steps discussed herein.

[0135] The computing system 710 may further include network interface circuitry 715. The computing system 710 may be communicatively coupled to input device 720 and / or output device 730 via input / output circuitry 716. In some implementations, input device 720 and / or output device 730 may be elements of the computing system 710. Input device 720 may include alphanumeric input devices (e.g., keyboard or touchscreen), cursor control devices (e.g., mouse or touchscreen), audio devices (such as microphones), and / or haptic input devices. Output device 730 may include audio devices (such as speakers), video display units (e.g., liquid crystal display (LCD) or cathode ray tube (CRT)), and / or haptic output devices. In some implementations, input device 720 and output device 730 may be provided as a single device or separate devices.

[0136] In some implementations, the computing system 710 may include image processing circuitry 714. Image processing circuitry 714 may be configured to process image data 770 (e.g., images, imaging data, projections, projection data), such as medical images acquired from one or more imaging data sources, treatment devices 750, and / or image acquisition devices 740. Image processing circuitry 714 may be configured to process or preprocess image data 770. For example, image processing circuitry 714 may convert received image data to a specific format, size, resolution, etc. Image processing circuitry 714 may be configured to perform image reconstruction. In some implementations, image processing circuitry 714 may be combined with controller circuitry 711.

[0137] In some implementations, the radiotherapy system 700 may further include an image acquisition device 740 and / or a treatment device 750. The image acquisition device 740 and the treatment device 750 may be provided as a single device. In some implementations, the treatment device 750 is configured to, for example, perform imaging in addition to providing treatment and / or perform imaging during treatment.

[0138] The image acquisition device 740 can be configured to perform CBCT. The image acquisition device 740 can also be configured to perform positron emission tomography (PET), computed tomography (CT), magnetic resonance imaging (MRI), single positron emission tomography (SPECT), X-ray, etc.

[0139] Image acquisition device 740 can be configured to output image data 770, which is accessible to computing system 710. Treatment device 750 can be configured to output treatment data 760, which is accessible to computing system 710. Treatment data 760 can be obtained from an internal data source (e.g., from memory 713) or from an external data source (such as treatment device 750 or an external database).

[0140] The methods described above can be implemented by a computer program. A computer program may include computer code (e.g., instructions) arranged to instruct a computer to perform the functions of one or more of the methods described above. For example, regarding... Figure 1 and / or Figure 2 The steps of the described method can be executed by computer code. The steps of the above method can be executed in any suitable order. The computer program and / or code for performing such methods may be provided on one or more computer-readable media or more generally on a computer program product to a device such as a computer. The computer-readable media may be transient or non-transient. One or more computer-readable media may be, for example, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, or a propagation medium for data transmission, such as a medium for downloading code via the Internet. Alternatively, one or more computer-readable media may take the form of one or more physical computer-readable media, such as semiconductor or solid-state memory, magnetic tape, removable computer floppy disk, random access memory (RAM), read-only memory (ROM), rigid disk, and optical disk, such as CD-ROM, CD-R / W, or DVD. Instructions may also reside wholly or at least partially within memory 913 and / or controller circuitry 911 during execution by computing system 910, which also constitute computer-readable storage media.

[0141] In one implementation, the modules, components and other features described herein may be implemented as discrete components or integrated into the functionality of hardware components such as ASICs, FPGAs, DSPs or similar devices.

[0142] A "hardware component" is a tangible (e.g., non-transitory) physical component (e.g., a group or more processors) capable of performing certain operations and which can be configured or arranged in some physical manner. A hardware component may include dedicated circuitry or logic permanently configured to perform certain operations. A hardware component may include dedicated processors, such as FPGAs or ASICs. A hardware component may also include programmable logic or circuitry temporarily configured by software to perform certain operations.

[0143] Furthermore, these modules and components can be implemented as firmware or functional circuitry within a hardware device. Further, modules and components can be implemented using any combination of hardware devices and software components, or solely using software (e.g., code stored or otherwise embodied in a machine-readable medium or transmission medium).

[0144] Unless otherwise specifically indicated, it should be understood, as is apparent from the following discussion, that throughout the description, the use of terms such as “receive,” “determine,” “compare,” “realize,” “maintain,” “identify,” “acquire,” “access,” etc., refers to the actions and processes of a computer system or similar electronic computing device that manipulates data represented as physical (electronic) quantities in the registers and memories of the computer system and transforms that data into other data similarly represented as physical quantities in the computer system’s memory or registers or other such information storage, transmission, or display devices.

[0145] It should be noted that the above examples are illustrative and not limiting of this disclosure, and those skilled in the art will be able to devise many alternative embodiments without departing from the scope of the appended claims or numbered embodiments. The word "comprising" does not exclude the presence of elements or steps other than those listed in the claims or embodiments, and "a" or "an" does not exclude multiple, and a single processor or other unit may perform the functions of several units recited in the claims or numbered embodiments. Any reference numerals in the claims or numbered embodiments should not be construed as limiting their scope.

Claims

1. A computer-implemented method for managing cone-beam computed tomography (CBCT) imaging of a patient, the method comprising: Obtain RTP information for radiotherapy planning (RTP), wherein the RTP is used to apply a radiation dose distribution to the patient in order to achieve at least one radiotherapy objective; The sensitivity measure of the RTP to changes in the patient's anatomical structure is determined based on the acquired RTP information, wherein the sensitivity measure is a function of the location within the patient's body or a function of the direction of the radiotherapy beam in the RTP; as well as Based on the determined sensitivity metric, an imaging protocol for acquiring reconstructed CBCT images of the patient's volume is generated using the following methods, wherein the imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter: The image quality of the reconstructed CBCT image of the patient volume is set such that it meets the image quality target of the image processing task, wherein the image quality target preferentially considers the image quality of the RTP locations within the patient volume that are sensitive to changes in anatomical structure.

2. The method of claim 1, wherein the sensitivity metric represents the degree to which the RTP needs to be adjusted to achieve one or more of the at least one radiotherapy target due to changes in the patient's anatomy.

3. The method of claim 1 or 2, wherein the sensitivity measure includes one or more of the following: The gradient of the radiation dose distribution as a function of the patient's location; The scale of changes in patient anatomy as a function of the patient's location within the patient's body, which require adjustments to the RTP to achieve one or more of the at least one radiotherapy target; The radiation dose distribution as a function of location within the patient's body; Radiation applied to the patient as a function of the direction of the radiotherapy beam in the RTP; as well as Monitoring units (MUs) applied to the patient as a function of the direction of the radiotherapy beam in the RTP.

4. The method as described in any of the preceding claims, wherein the location of the RTP in the patient's body that is sensitive to changes in anatomical structure includes the location where the sensitivity measure meets the sensitivity criteria.

5. The method of claim 4, wherein the sensitivity criteria include one or more of the following: a threshold radiation dose gradient; a reference-scale anatomical change in the RTP that would require adjustment to achieve one or more of the at least one radiotherapy target; a threshold radiation dose; a radiation threshold level to be applied to the patient; and a threshold number of monitoring units to be applied to the patient.

6. The method as described in any of the preceding claims, wherein the anatomical changes in the patient include one or more of the following: Soft tissue movement; Changes in soft tissue shape; and Overall changes in the patient's anatomical structure.

7. The method of any of the preceding claims, wherein the image quality objective seeks to balance a first requirement for optimizing the image quality of the reconstructed CBCT images to accomplish the image processing task with one or both of the following: a second requirement for minimizing the total imaging radiation dose applied to the patient during CBCT image acquisition and a third requirement for minimizing the total computation time for image reconstruction.

8. The method as claimed in any of the preceding claims, wherein the image quality objective includes performance criteria for the image processing task performed on the reconstructed CBCT image.

9. The method of any of the preceding claims, wherein the determined sensitivity metric is a function of the location within the patient, and setting the value of at least one parameter in the imaging protocol comprises: The determined sensitivity metric is projected based on the geometry of the CBCT image of the patient to obtain a projection sensitivity metric as a function of the CBCT projection angle; as well as The value of at least one CBCT imaging acquisition parameter is determined based on the projection sensitivity metric and the image quality target, according to the CBCT projection angle.

10. The method of any of the preceding claims, wherein the determined sensitivity metric is a function of the location within the patient, and setting the value of at least one parameter in the imaging protocol comprises: The value of at least one CBCT imaging reconstruction parameter is determined based on the determined sensitivity metric and the image quality target, according to its location within the patient volume.

11. The method as claimed in any of the preceding claims, wherein the at least one CBCT imaging acquisition parameter includes at least one of the following: The intensity of the imaging radiation source projected once or multiple times; Imaging source current projected once or multiple times; Exposure time for one or more projections; The energy of the imaging radiation source projected once or multiple times; The rack rotation speed for one or more projections; The range of rack angles for one or more projections; A rotating plane that is projected once or multiple times; The isocenter of one or more projections; The projection angle of an image projected once or multiple times; Number of projections within each CBCT acquisition angle range; The shape of the imaging beam projected once or multiple times; Detector offset from one or more projections; Detector sensitivity for single or multiple projections; and Detector gain from one or more projections.

12. The method as claimed in any of the preceding claims, wherein the at least one CBCT imaging reconstruction parameter comprises at least one of the following: The voxel size of one or more regions in the reconstructed CBCT image; The number of voxels in one or more regions of the reconstructed CBCT image; Voxel density of one or more regions of the reconstructed CBCT image; The voxel distribution of one or more regions in the reconstructed CBCT image; One or more regularization terms; Number of iterations; as well as Stop criteria.

13. The method as claimed in any of the preceding claims, wherein generating the imaging protocol comprises: Multiple candidate imaging protocols are generated for the patient; as well as Choose one of the multiple candidate imaging protocols to implement.

14. The method of claim 13, wherein selecting one of the plurality of candidate imaging protocols for implementation includes selecting according to a selection criterion, the selection criterion including at least one of the following: Total imaging radiation dose conforming to the candidate imaging protocol; Image quality of the reconstructed CBCT image conforming to the candidate imaging protocol; Total imaging and / or reconstruction time conforming to the candidate imaging protocol; and To what extent do the candidate imaging protocols meet the image quality targets? 15. The method as described in any of the preceding claims, wherein: Determine the sensitivity measure of the RTP to changes in the patient's anatomical structure; and / or An imaging protocol for generating reconstructed CBCT images of the patient's volume; Includes performing at least one of the following: Analysis process; Optimization process; and / or Machine learning (ML) process.

16. The method of claim 15, wherein performing the optimization process to generate an imaging protocol for the patient comprises: An optimization procedure is applied to the imaging protocol, wherein the optimization procedure attempts to optimize the degree to which the imaging protocol meets the image quality target of the image processing task by adjusting at least one parameter in the imaging protocol.

17. The method of claim 15 or 16, wherein an imaging protocol is used to generate reconstructed CBCT images of the patient volume using an ML process; include: The RTP information and the image quality target of the image processing task are input into an ML model, wherein the ML model is operable to output the imaging protocol for acquiring reconstructed CBCT images of the patient that satisfy the image quality target of the imaging processing task.

18. The method of any one of claims 15 to 17, further comprising: The ML model is trained using the following methods to generate an imaging protocol for the patient: Generate training data for training the ML model; as well as The trainable parameters of the ML model are updated using the training data; wherein generating training data for the ML model includes multiple patients: The steps of claim 1 are performed using an analysis process and / or an optimization process to generate the imaging protocol for the patient; as well as The RTP information and the generated imaging protocol are added to the training dataset to obtain reconstructed CBCT images of the patient.

19. The method of any of the preceding claims, wherein determining the sensitivity measure of the RTP to the anatomical changes in the patient comprises: Obtain predictions of patient movement during the CBCT imaging of the patient and / or during radiotherapy of the patient; as well as Assess the sensitivity of the RTP to the predicted patient movement.

20. The method of any of the preceding claims, wherein the image processing task includes one or more of the following: image reconstruction; image segmentation; image contouring; target identification; dangerous organ identification; image registration; and motion tracking.

21. The method of any of the preceding claims, wherein the RTP information comprises one or more of the following: the patient's RTP; the patient's radiation dose distribution; the gradient of the patient's radiation dose distribution; a radiation flux map; the patient's dose-volume histogram (DVH); a monitoring unit (MU) as a function of the direction of the radiotherapy beam conforming to the RTP; an image of the patient; a segmented image of the patient; a patient model; the at least one radiotherapy target; a configuration of the radiotherapy system for applying the radiation dose distribution; one or more parameters for configuring the radiotherapy system; and an application sequence of the radiotherapy system for applying the radiation dose distribution.

22. A management node for managing cone-beam computed tomography (CBCT) imaging of a patient, the management node including processing circuitry configured to cause the management node to: Obtain RTP information for radiotherapy planning (RTP), wherein the RTP is used to apply a radiation dose distribution to the patient in order to achieve at least one radiotherapy objective; The sensitivity measure of the RTP to changes in the patient's anatomical structure is determined based on the acquired RTP information, wherein the sensitivity measure is a function of the location within the patient's body or a function of the direction of the radiotherapy beam in the RTP; as well as Based on the determined sensitivity metric, an imaging protocol for acquiring reconstructed CBCT images of the patient's volume is generated using the following methods, wherein the imaging protocol includes values ​​for at least one CBCT imaging acquisition parameter and / or at least one CBCT imaging reconstruction parameter: The image quality of the reconstructed CBCT image of the patient volume is set such that it meets the image quality target of the image processing task, wherein the image quality target preferentially considers the image quality of the RTP locations within the patient volume that are sensitive to changes in anatomical structure.

23. The management node of claim 22, wherein the processing circuitry is further configured to cause the management node to perform the method of any one of claims 2 to 21.

24. A radiotherapy device comprising a management node as described in claim 22 or 23.

25. A computer program product comprising a computer-readable medium embodying computer-readable code configured to cause the computer or processor, when executed by a suitable computer or processor, to perform the method as described in any one of claims 1 to 21.

Images