Method and apparatus for automatically determining radiofrequency ablation treatment risk

Abstract

Systems and methods for cardiac radiofrequency ablation treatment and planning are disclosed. In some examples, a computing device receives a first image of a patient captured for a treatment plan. The computing device also receives target definition data characterizing a target region of the patient for processing. Further, the computing device receives a second image of the patient captured on the day and prior to the processing. The computing device determines whether the organ of the patient is at risk based on the first image, the target definition data, and the second image. The computing device also provides for display a risk indication of the patient based on the determination. For example, the risk indication may include a processing target region and an organ-at-risk region superimposed over the second image. In some examples, the risk indication includes an expected dose level.

Description

[0001] CROSS REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. application serial number 17 / 810,159, filed on June 30, 2022, entitled “METHODS AND APPARATUS FOR AUTOMATICALLY DETERMINING RADIOABLATION TREATMENT RISK,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] Aspects of the present disclosure relate generally to medical diagnostic and treatment systems, and more particularly to providing radiofrequency ablation diagnostic, treatment planning, and delivery systems for treating conditions such as cardiac arrhythmias. Background Art

[0004] Various techniques can be used to capture and image metabolic, electrical, and anatomical information of a patient. For example, positron emission tomography (PET) is a metabolic imaging technique that produces tomographic images representing the distribution of positron-emitting isotopes in the body. Computed tomography (CT) and magnetic resonance imaging (MRI) are anatomical imaging techniques that use x-rays and magnetic fields, respectively, to create images. Images from these exemplary techniques can be combined with each other to generate composite anatomical and functional images, such as PET / CT or PET / MRI. For example, software systems such as Velocity CT from Varian Medical Systems, Inc. TM Software) can combine different types of images using an image fusion process to warp and / or register images to produce a combined image.

[0005] Medical professionals (such as electrophysiologists and radiation oncologists) rely on these images to identify target areas for treatment. For example, in cardiac radiofrequency ablation, medical professionals jointly diagnose arrhythmias, identify areas for ablation, prescribe radiation treatment, and create a radiofrequency ablation treatment plan. Before treating a patient, the patient may be scanned using one or more anatomical imaging techniques to obtain patient images. An electrophysiologist may identify one or more areas (e.g., targets) of a patient's organs for treatment based on the images, such as determining the patient's heart to treat arrhythmias. Once the target area is defined by the electrophysiologist, the radiation oncologist may prescribe radiation treatment, such as including many portions of radiation to be delivered, radiation doses to be delivered to the target area (e.g., within the area identified by the electrophysiologist), and the maximum dose that can be delivered to adjacent organs at risk. In addition, a dosimetrist may create a radiofrequency ablation treatment plan based on the prescribed radiation treatment. In some examples, a radiation oncologist may review and approve the treatment plan. In addition, an electrophysiologist may review the location, size, and shape of the defined target area to confirm that the target location defined by the radiofrequency ablation treatment plan is appropriate. Summary of the invention

[0006] Systems and methods for cardiac radiofrequency ablation treatment and planning are disclosed. In some examples, prior to treatment, an imaging device scans a patient using one or more of any suitable anatomical imaging techniques (such as CT, MRI, or PET) to obtain one or more images of the patient. The image can identify the organ to be treated, as well as healthy organs that do not require treatment but may be close to the organ to be treated (e.g., OAR) or a portion of the organ. A treatment plan is then formulated based on the images obtained. For example, a medical professional can identify one or more regions of the organ for treatment based on the image. In addition, a radiation oncologist can determine the radiation dose to be delivered to the target area based on the region identified by the medical professional and the image. In addition, the treatment planning system can store a treatment plan (TP) image and target definition data characterizing the target area and the radiation dose to be delivered in a data repository. The patient can then be scheduled for treatment based on the treatment plan, typically a few days or weeks after the TP image is obtained.

[0007] On the day of treatment, an imaging device (such as an imaging device located on or near the treatment device) scans the patient to obtain one or more additional images of the patient (i.e., treatment delivery (TD) images). In addition, the treatment application device obtains target definition data characterizing the target area and the radiation dose from a data repository and displays the target area on one of the TD images. For example, the treatment application device can determine the location of the target area within one or more TD images, and can display an overlay of the target area at the determined location on one of the TD images. Prior to treatment, a medical professional (such as a medical professional who will control the treatment device to provide a dose to the patient) can determine whether providing a dose to the target area is still acceptable based on the positioning of the organ (such as an OAR), as shown by the target area overlay displayed at the determined location on the TD image.

[0008] In some examples, the processing application system obtains the TP image and the target definition data from the data repository, and automatically determines whether an organ (e.g., any OAR) of the patient is at risk based on the TP image, the target definition data, and one or more TD images. For example, the processing application system can calculate one or more dose volume histograms (DVHs) based on the relative positioning of the target area relative to one or more OARs in the additional image, and can determine whether one or more DVH dose constraints are violated based on the calculated DVH. For example, if a portion of the OAR is at risk of receiving a dose higher than a predetermined threshold when the radiation dose is applied to the target area, the processing application system can determine that the DVH dose constraint is violated. In other examples, the processing application system can determine the relative positioning between organs (such as OARs) in the TP image (e.g., an image obtained before the treatment plan) and the TD image (e.g., an image obtained for treatment delivery), and if the organ moves more than a predetermined distance, it can be determined that the OAR dose constraint is violated. However, in other examples, the processing application system can determine the positioning (e.g., distance) between the target area and the organ (such as OAR) in the TP image, and another relative positioning between the target area and the same organ in the TD image. The treatment application system can determine that the OAR dose constraint is violated based on the relative positioning determined for each of the TP and TD images. For example, the treatment planning system can compare (e.g., subtract) the determined relative positioning and can determine that the OAR dose constraint is violated based on the comparison (e.g., the difference equals or exceeds a predetermined threshold).

[0009] If any risk is determined, the treatment application can generate an alarm. For example, the treatment application can provide one or more visual or audible alarms that notify the medical professional of the determined risk. In some examples, the medical professional can provide input to the treatment planning system to change the target area based on the alarm. In some examples, the treatment application can prevent any dose from being provided to the patient until the medical professional "clears" the alarm. In some examples, permission from at least a minimum number of medical professionals (e.g., two) is required before the treatment application allows a dose to be provided to the patient. For example, before allowing any dose to be provided to the patient, the treatment application may require at least two medical professionals to enter their credentials (e.g., log in) and clear the alarm.

[0010] In some embodiments, a system includes a database and a computing device that is communicatively coupled to the database. The computing device is configured to receive a first image (e.g., a TP image) of a patient. For example, the computing device can receive magnetic resonance (MR) image data, computed tomography (CT) image data, or positron emission tomography (PET) image data from an image scanning system. The first image can be captured during a treatment plan (e.g., before the day of treatment). The computing device is also configured to receive target definition data that characterizes a target area of ​​a patient for treatment. For example, the target definition data can include DVH data that characterizes the expected dose level of each part of the target area. In addition, the computing device is configured to receive a second image (e.g., a TD image) of the patient. The second image can be captured on the day of treatment (e.g., when the patient is on a treatment table before receiving a prescribed treatment). The computing device is configured to determine whether an organ (e.g., an OAR) of the patient is at risk based on the first image, the target definition data, and the second image. The computing device is also configured to provide a risk indication for display based on the determination.

[0011] In some embodiments, a computer-implemented method includes receiving a first image (e.g., a TP image) of a patient. The first image may be captured during a treatment plan (e.g., before the day of treatment). The computer-implemented method also includes receiving target definition data representing a target area of ​​the patient for treatment. For example, the target definition data may include DVH data representing the expected dose level of each portion of the target area. In addition, the computer-implemented method includes receiving a second image (e.g., a TD image) of the patient. The second image may be captured on the day of treatment (e.g., when the patient lies on a treatment table before receiving a prescribed treatment). The computer-implemented method also includes determining whether an organ (e.g., an OAR) of the patient is at risk based on the first image, the target definition data, and the second image. The computer-implemented method also includes providing a risk indication for display based on the determination.

[0012] In some examples, a non-transitory computer-readable medium stores instructions that, when executed by at least one processor, cause at least one processor to perform an operation that includes receiving a first image (e.g., a TP image) of a patient. The first image may be captured during a treatment plan (e.g., before the day of treatment). The operation also includes receiving target definition data representing a target area of ​​the patient for treatment. For example, the target definition data may include DVH data representing the expected dose level of each portion of the target area. In addition, the operation includes receiving a second image (e.g., a TD image) of the patient. The second image may be captured on the day of treatment (e.g., when the patient is on a treatment table before receiving a prescribed treatment). The operation also includes determining whether an organ (e.g., an OAR) of the patient is at risk based on the first image, the target definition data, and the second image. The operation also includes providing a risk indication for display based on the determination.

[0013] In some examples, a system including at least one computing device includes a component for receiving a first image (e.g., a TP image) of a patient. The first image may have been captured during a treatment plan (e.g., before the day of treatment). The system also includes a component for receiving target definition data representing a target area of ​​the patient for treatment. For example, the target definition data may include DVH data representing the expected dose level of various parts of the target area. In addition, the system includes a component for receiving a second image (e.g., a TD image) of the patient. The second image may be captured on the day of treatment (e.g., when the patient is lying on a treatment table before receiving a prescribed treatment). The system also includes a component for determining whether an organ (e.g., an OAR) of the patient is at risk based on the first image, the target definition data, and the second image. The system also includes a component for providing a risk indication for display based on the determination.

[0014] In some embodiments, a system includes a database and a computing device that is communicatively coupled to the database. The computing device is configured to receive a first image of a patient. For example, the computing device may receive magnetic resonance (MR) image data, computed tomography (CT) image data, or positron emission tomography (PET) image data from an image scanning system. The first image may be captured during a treatment plan (e.g., before the day of treatment). The computing device is also configured to display an indication of a first organ-at-risk region and a first target region superimposed on the first image. In addition, the computing device is configured to receive a second image of the patient. The second image may be captured on the day of treatment (e.g., when the patient lies on a treatment table before receiving a prescribed treatment). The computing device is also configured to determine a second organ-at-risk region within the second image. The second organ-at-risk region of the second image may include the same organ as the organ within the first organ-at-risk region of the first image. For example, the second organ-at-risk region of the second image may overlap at least partially with the first organ-at-risk region of the first image. The computing device is also configured to determine a second target region within the second image based on the first target region, the first organ-at-risk region, and the second organ-at-risk region. The computing device is also configured to provide an indication of the second organ-at-risk region and the second target region superimposed on the second image for display.

[0015] In some embodiments, a computer-implemented method includes receiving a first image of a patient. The first image may be captured during a treatment plan (e.g., before the day of treatment). The computer-implemented method also includes displaying an indication of a first organ-at-risk region and a first target region superimposed on the first image. In addition, the computer-implemented method includes receiving a second image of the patient. The second image may be captured on the day of treatment (e.g., when the patient is lying on a treatment table before receiving a prescribed treatment). The computer-implemented method also includes determining a second organ-at-risk region within the second image. The computer-implemented method also includes determining a second target region within the second image based on the first target region, the first organ-at-risk region, and the second organ-at-risk region. The computer-implemented method also includes providing an indication of a second organ-at-risk region and a second target region superimposed on the second image for display.

[0016] In some examples, a non-transitory computer-readable medium stores instructions that, when executed by at least one processor, cause the at least one processor to perform an operation that includes receiving a first image of a patient. The first image can be captured during a treatment plan (e.g., before the day of treatment). The operation also includes displaying an indication of a first organ-at-risk region and a first target region superimposed on the first image. In addition, the operation includes receiving a second image of the patient. The second image can be captured on the day of treatment (e.g., when the patient is on a treatment table before receiving a prescribed treatment). The operation also includes determining a second organ-at-risk region within the second image. The operation also includes determining a second target region within the second image based on the first target region, the first organ-at-risk region, and the second organ-at-risk region. The operation also includes providing an indication of a second organ-at-risk region and a second target region superimposed on the second image for display.

[0017] In some examples, a system including at least one computing device includes a component for receiving a first image of a patient. The first image may be captured during a treatment plan (e.g., before the day of treatment). The system also includes a component for displaying an indication of a first organ-at-risk region and a first target region superimposed on the first image. In addition, the system includes a component for receiving a second image of the patient. The second image may be captured on the day of treatment (e.g., when the patient is on a treatment table before receiving a prescribed treatment). The system also includes a component for determining a second organ-at-risk region within the second image. The system also includes a component for determining a second target region within the second image based on the first target region, the first organ-at-risk region, and the second organ-at-risk region. The system also includes a component for providing an indication of a second organ-at-risk region and a second target region superimposed on the second image for display. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The features and advantages of the present disclosure will be more fully disclosed or become apparent in the following detailed description of example embodiments. Figure 1 are considered together, wherein like numerals refer to like parts, and wherein.

[0019] Figure 1 illustrates a processing plan and application system according to some embodiments;

[0020] Figure 2 illustrates a block diagram of an exemplary computing device according to some embodiments;

[0021] Figure 3 The diagram shows a method according to some embodiments Figure 1 An exemplary portion of a treatment plan and application system;

[0022] Figure 4A and Figure 4B illustrates an image identifying a target region and an organ at risk (OAR) region according to some embodiments;

[0023] Figure 5A , Figure 5B and Figure 5C illustrates a portion of a graphical user interface identifying whether any risks have been identified for which treatment is provided in accordance with some embodiments;

[0024] Figure 6 is a flow chart of an example method of determining treatment risk according to some embodiments; and

[0025] Figure 7 is a flow chart of an example method of displaying calculated target and OAR regions according to some embodiments. DETAILED DESCRIPTION

[0026] The description of the preferred embodiments is intended to be read in conjunction with the accompanying drawings, which should be considered as part of the entire written description of these disclosures. Although the present disclosure is susceptible to various modifications and alternative forms, specific embodiments are shown by way of example in the accompanying drawings and will be described in detail herein. From the following detailed description of these exemplary embodiments in conjunction with the accompanying drawings, the objects and advantages of the claimed subject matter will become more apparent.

[0027] However, it should be understood that the present disclosure is not intended to be limited to the specific forms disclosed. On the contrary, the present disclosure covers all modifications, equivalents and alternatives that fall within the spirit and scope of these exemplary embodiments. The terms "coupled", "coupled", "operably coupled", "operably connected", etc. should be broadly understood to refer to connecting devices or components together mechanically, electrically, wired, wirelessly or otherwise, so that the connection allows the related devices or components to operate (e.g., communicate) as expected by virtue of the relationship.

[0028] Correctly identifying and defining target areas of patient organs for treatment is critical to developing and optimizing treatment plans. For example, delivering doses to unintended areas may cause harm to the patient, such as when a prescribed dose is applied to any portion of an organ at risk (OAR) that is not intended to be treated. For example, CRA treatments are often planned to deliver high single-fraction radiation doses to a portion of the cardiac anatomy. Some organs and structures near the treatment area are highly sensitive to external beam radiation, such as the stomach and esophagus. Protecting these structures from high doses of radiation is a primary goal when planning CRA treatments, as the effects of exceeding the dose limitations of these organs can be severe.

[0029] At least in some cases, the anatomy of a patient's organs may be different on the day of treatment than when the patient was initially scanned to determine the patient's treatment plan. When this occurs, there is no guarantee that any dose determined in the intimal treatment plan to any OAR will remain valid. In fact, depending on any changes in the patient's anatomy, the OAR may now be subjected to a higher dose than originally determined in the initial treatment plan. Among other advantages, the embodiments described herein can improve radiofrequency ablation treatment planning systems used by medical professionals, such as cardiac radiofrequency ablation treatment systems for cardiac radiofrequency ablation treatment planning, by automatically determining whether a patient's OAR is at an unacceptably high risk level on the day of treatment.

[0030] Turning to the attached figure, Figure 1 A block diagram of a treatment planning and application system 100 is illustrated, which includes an imaging device 102, a treatment planning computing device 106, a treatment application computing device 108, one or more target definition computing devices 104, a processing device 110, and a database 116 communicatively coupled via a communication network 118. For example, the imaging device 102 may be a CT scanner, an MR scanner, a PET scanner, an electrophysiological imaging device, or an electrocardiogram (ECG) imager. In some examples, the imaging device 102 may be a PET / CT scanner or a PET / MR scanner. The processing device 110 may be a photon (such as a Varian TM TrueBeam radiotherapy system) or proton radiotherapy device. In some examples, the target definition computing device 104, the treatment plan computing device 106, the treatment application computing device 108, and the processing device 100 can be part of a cardiac radiofrequency ablation treatment system 126 that allows radiofrequency ablation treatment of a patient. For example, the radiofrequency ablation treatment system 126 can allow a defined dose to be delivered to one or more treatment areas of a patient.

[0031] Each target definition computing device 104, processing plan computing device 106, and processing application computing device 108 can be any suitable computing device, including any suitable hardware or hardware and software combination for processing data. For example, each computing device can include one or more processors, one or more field programmable gate arrays (FPGAs), one or more application specific integrated circuits (ASICs), one or more state machines, digital circuit devices, or any other suitable circuit devices. In addition, each computing device can send data to and receive data from the communication network 118. For example, each target definition computing device 104, processing plan computing device 106, and processing application computing device 108 can be a server, such as a cloud-based server, a computer, a laptop, a mobile device, a workstation, or any other suitable computing device.

[0032] For example, Figure 2 An exemplary computing device 200 is illustrated, which may be an example of any of the goal definition computing device 104, the processing plan computing device 106, and the processing application computing device 108. The exemplary computing device 200 includes one or more processors 201, a working memory 202, one or more input and output (I / O) devices 203, an instruction memory 207, a transceiver 204, one or more communication ports 207, and a display 206, all of which are operably coupled to one or more data buses 208. The data bus 208 allows communication between the various devices. The data bus 208 may include a wired or wireless communication channel.

[0033] Processor 201 may include one or more different processors, each processor having one or more cores. Each different processor may have the same or different structures. Processor 201 may include one or more central processing units (CPUs), one or more graphics processing units (GPUs), application specific integrated circuits (ASICs), digital signal processors (DSPs), etc.

[0034] The instruction memory 207 may store instructions that may be accessed (e.g., read) and executed by the processor 201. For example, the instruction memory 207 may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a removable disk, a CD-ROM, any non-volatile memory, or any other suitable memory. The processor 201 may be configured to perform a specific function or operation by executing a code embodying the function or operation stored on the instruction memory 207. For example, the processor 201 may be configured to execute a code stored in the instruction memory 207 to perform one or more of any functions, methods, or operations disclosed herein.

[0035] In addition, the processor 201 may store data in the working memory 202 and read data from the working memory 202. For example, the processor 201 may store a working instruction set (such as instructions loaded from the instruction memory 207) in the working memory 202. The processor 201 may also use the working memory 202 to store dynamic data created during the operation of the computing device 200. The working memory 202 may be a random access memory (RAM) such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), or any other suitable memory.

[0036] Input-output device 203 may include any suitable device that allows data input or output. For example, input-output device 203 may include one or more of a keyboard, a touchpad, a mouse, a stylus, a touch screen, physical buttons, a speaker, a microphone, or any other suitable input or output device.

[0037] For example, communication port(s) 209 may include a serial port, such as a universal asynchronous receiver / transmitter (UART) connection, a universal serial bus (USB) connection, or any other suitable communication port or connection. In some examples, communication port(s) 209 allow executable instructions to be programmed in instruction memory 207. In some examples, communication port(s) 209 allow data such as image data to be transferred (e.g., uploaded or downloaded).

[0038] Display 206 can be any suitable display, such as a 3D viewer or monitor. Display 206 can display user interface 205. User interface 205 can enable user interaction with computing device 200. For example, user interface 205 can be a user interface of an application, which allows a user (e.g., a medical professional) to view or manipulate a model to define a target area for treatment of a patient as described herein. In some examples, a user can interact with user interface 205 by using input-output device 203 (such as a mouse). In some examples, display 206 can be a touch screen, wherein user interface 205 is displayed on the touch screen. In some examples, display 206 displays an image (e.g., an image slice) of scanned image data.

[0039] The transceiver 204 allows communication with a network such as Figure 1 For example, if Figure 1If the communication network 118 is a cellular network, the transceiver 204 is configured to allow communication with the cellular network. In some examples, the transceiver 204 is selected based on the type of communication network 118 in which the exemplary computing device 200 will operate. The processor(s) 201 are operable to receive a signal from a network (such as a cellular network) via the transceiver 204. Figure 1 The communication network 118 of the network can be used to receive data or send data to the network.

[0040] Return to see Figure 1 , the database 116 may be a remote storage device (e.g., including non-volatile memory), such as a cloud-based server, a disk (e.g., a hard disk), a storage device on another application server, a networked computer, or any other suitable remote storage device. In some examples, the database 116 may be a local storage device of one or more of the target definition computing device 104, the processing plan computing device 106, and the processing application computing device 108, such as a hard disk, non-volatile memory, or a USB memory stick.

[0041] The communication network 118 may be Networks, cellular networks (such as network), The communication network 118 may include a wireless local area network (LAN), a satellite network, a network utilizing a radio frequency (RF) communication protocol, a near field communication (NFC) network, a wireless metropolitan area network (MAN) connecting multiple wireless LANs, a wide area network (WAN), or any other suitable network. The communication network 118 may provide access to, for example, the Internet.

[0042] The imaging device 102 may be operable to scan an image (such as an image of an organ of a patient) and provide image data 103 (e.g., measurement data) identifying and characterizing the scanned image to the communication network 118. Alternatively, the imaging device 102 may be operable to acquire electrical imaging, such as a cardiac ECG image. For example, the imaging device 102 may scan a structure (e.g., an organ) of a patient and may send image data 103 identifying one or more slices of a 3D volume of the scanned structure to one or more of the treatment planning computing device 106 and the treatment application computing device 108 via the communication network 118. In some examples, the imaging device 102 stores the image data 103 in the database 116, and one or more of the treatment planning computing device 106 and the treatment application computing device 108 may retrieve the image data 103 from the database.

[0043] In some examples, the process plan computing device 106 is operable to communicate with the process application computing device 108 and the goal definition computing device 104 via the communication network 118. In some examples, one or more of the process plan computing device 106, the process application computing device 108, and the goal definition computing device 104 communicate with each other (e.g., by storing and retrieving data from the database 116) via the database 116. In some examples, one or more of the process plan computing devices 106 and one or more of the process application computing devices 108 are part of a cloud-based network that allows resource sharing and communication with each device.

[0044] In some examples, one or more exemplary computing devices 104 and 106 are located in a first area 122 of a medical facility 120, while computing device 108 and treatment device 100 are located in a second area 124 of the medical facility 120. Thus, treatment planning and application system 100 allows multiple EPs to collaborate to determine target areas.

[0045] Generate images before processing your application

[0046] As described herein, prior to treatment planning (e.g., prior to treatment), the image scanning device 102 may scan the patient to obtain one or more treatment planning (TP) images. The images may identify the patient's anatomical structure by illustrating the patient's various organs. In addition, the image scanning device 102 may store image data 103 representing the images in a database 116. Based on the images, one or more medical professionals operating one or more treatment plan calculation devices 106 may determine a treatment plan for the patient. The treatment plan may identify a treatment target area of ​​the patient, as well as a radiation dose to be delivered to the target area.

[0047] For example, the treatment plan computing device 106 may execute an application that causes a user interface (e.g., user interface 205) to be generated that may be displayed to a medical professional (such as a dosimetrist). The executed application may assist the medical professional in defining a target area for treatment of the patient. For example, the dosimetrist may operate the treatment plan computing device 106 to define a treatment target area for the patient. In some examples, the treatment plan may also identify one or more OAR regions in the TP image. The treatment plan computing device 106 may store target definition data characterizing the treatment plan in the database 116.

[0048] On the day of treatment (e.g., before treatment), the patient is scanned (e.g., using a linear accelerator integrated kV cone beam CT) to obtain one or more treatment delivery (TD) images. The treatment application computing device 108 may also obtain one or more TP images and target definition data from the database 116. Although the TP image may identify the original anatomical structure of the patient when the TP image was captured, the TD image may identify the current anatomical structure of the patient. In at least some cases, the current anatomical structure of the patient may be different from the original anatomical structure of the patient. As such, the treatment plan originally prescribed for the patient may not be appropriate because the dose may be applied to the patient at an area and dose level that was not previously considered.

[0049] For example, on the day of treatment, the treatment application computing device 108 may display the TP image obtained from the image scanning device 102 for treatment planning, along with an overlay of the treatment target region defined by the target definition data and an indication of one or more OAR regions. Figure 4A A TP image 400 is illustrated, which identifies various structures such as structures 417, 419, and 421, and also includes a TP OAR region 402 defined by a dashed circle, and a TP treatment target region 404. As shown, the TP treatment target region 404 identifies portions distinguished by a hashing technique, wherein each portion corresponds to a different expected dose level (e.g., DVH level). For example, a first portion 405 may identify an area in the TP treatment target region 404 that is expected to receive the highest dose. In addition, a second portion 407 may identify an area in the TP treatment target region 404 that is expected to receive the next highest dose (e.g., less than the first portion 405), and a third portion 409 may identify an area in the TP treatment target region 404 that is expected to receive the next highest dose (i.e., less than the second portion 407). A fourth portion 411 may identify an area in the TP treatment target region 404 that is expected to receive a minimum dose level (i.e., a dose less than the dose of the third portion 409 but greater than the minimum dose, such as no dose at all). In this example, the TP OAR region 402 overlaps with the fourth region 411 in the overlap region 420 , but does not overlap with any of the first region 405 , the second region 407 , and the third region 409 .

[0050] Return to see Figure 1, the processing application computing device 108 can also display the TP image on the day of treatment and the indication overlap of the treatment target area defined by the target definition data and one or more OAR areas corresponding to the TP image. The OAR can be manually or automatically depicted using various available algorithms. For example, the processing application computing device 108 can display the TP image and can receive input from a medical professional (such as a dosimetrist) that characterizes one or more corresponding OAR areas. If done manually, the dosimetrist can, for example, "draw" the corresponding OAR area onto the display using a user interface tool provided by the treatment planning software. The processing application computing device 108 can generate OAR data characterizing the OAR area based on the input, and the OAR data can be stored in the database 116.

[0051] The treatment application computing device 108 may display the TP image with an indication overlay of the treatment target region defined by the target definition data, and any determined OAR regions (eg, defined by the OAR data). Figure 4B A TD image 450 is illustrated, which includes a TD OAR region 452 and a TD treatment target region 454. The TD OAR region 452 may correspond to a TP OAR region determined by a medical professional (e.g., based on the TD image 450). In addition, similar to the TP treatment target region 404, the TD treatment target region 454 identifies portions that are distinguished by different hashes in this example, wherein each portion corresponds to a different expected dose level (e.g., DVH level). For example, the first portion 455 may identify an area in the TD treatment target region 454 that is expected to receive the highest dose. In addition, the second portion 457 may identify an area in the TD treatment target region 454 that is expected to receive the next highest dose (i.e., less than the first portion 405), and the third portion 459 may identify an area in the TD treatment target region 454 that is expected to receive the next highest dose (i.e., less than the second portion 457). The fourth portion 461 may identify an area in the TD treatment target region 454 that is expected to receive the lowest dose level (i.e., a dose less than the dose of the third portion 459 but greater than the minimum dose, such as no dose at all).

[0052] In some examples, the processing application computing device 108 determines the TD treatment target region 454 based on applying one or more transformation models (e.g., algorithms) to one or more of the TP treatment target region 404, the TP OAR region 402, and the TD OAR region 452. For example, the processing application computing device 108 can identify corresponding structures between the TP image 400 and the TD image 450, such as structures 417, 419, and 421. In some examples, the processing application computing device 108 identifies corresponding structures based on inputting the TP image 400 and the TD image 450 to a trained machine learning model and receiving output data elements characterizing similar structures between the input images as output. In some examples, the medical professional provides input to the processing application computing device 108 to identify similar structures between the TP image 400 and the TD image 450.

[0053] In addition, based on the determined corresponding structure, the processing application computing device 108 applies a transformation model to determine the mapping between the TP image 400 and the TD image 450. For example, the processing application computing device 108 can determine the location of the structure of each of the TP image 400 and the TD image 450. The location can be defined by a bounding box, which includes the range of each dimension in two dimensions (e.g., X range and Y range). In some examples, the location identifies the pixel range of the corresponding image in each dimension in multiple dimensions (e.g., two-dimensional or three-dimensional). In some examples, the location identifies a single point (e.g., pixel) of the image based on two-dimensional coordinates (e.g., X, Y position). For example, a single point can be the center of each structure. The processing application computing device 108 can apply the transformation model to the determined location to determine the mapping (e.g., two-dimensional mapping from the TP image 400 to the TD image 454). For example, the transformation model can be a deformable image registration (DIR) algorithm. The DIR algorithm can be executed to map the spatial correspondence between the two images. For example, the output generated by the executed DIR algorithm can include a vector that defines the mapping between the two images.

[0054] In addition, and based on the TP treatment target area 404 and the determined mapping, the treatment application computing device 108 generates image data characterizing the TD treatment target area 454. In this example, the TD treatment target area 454 overlaps with the fourth portion 461 at the overlap area 470, and overlaps with the third portion 459 at the overlap area 472. For example, the area of ​​the overlap area 420 is smaller than the combined area of ​​the overlap areas 470 and 472. Therefore, if the TP treatment plan is implemented, the TD OAR area 452 may receive a higher dose level than originally expected at the TP OAR area 402. Based on viewing the TD image 450, the TD OAR area 452, and the TD treatment target area 454, the medical professional responsible for managing the treatment plan may decide not to provide treatment, or may decide to change the treatment plan before it is implemented.

[0055] Determining organ risk

[0056] Return to see Figure 1 As described herein, the processing application computing device 108 may determine whether an organ of the patient is at risk based on one or more of the TP image, the target definition data, and the one or more additional TD images.

[0057] For example, in some examples, the processing application computing device 108 may determine the relative positioning of the target region to one or more OAR regions within the current image. As an example, the processing application computing device 108 may determine the distance between the TD OAR region 452 and the TD processing target region 454. In some examples, the calculated distance may be from the outermost edge of the OAR region to the outermost edge of the processing target region (e.g., the closest distance). In some examples, the calculated distance may be from the center of the OAR region to the center of the processing target region. If the calculated distance is less than a predetermined threshold, the processing application computing device 108 may determine that the OAR dose constraint has been violated.

[0058] In other examples, the processing application computing device 108 may determine the relative positioning between an organ (such as an OAR) in a TP image and a later acquired TD image, and if the organ moves more than a predetermined distance, it may be determined that the organ is at risk. For example, the processing application computing device 108 may determine the position (e.g., distance) of an organ in a TP image relative to another organ, such as the position of one of the structures 417, 419, 421 within the TP image 400 relative to another structure, and may further determine the position of the organ in the TD image, such as the position of the same structure 417, 419, 421 within the TD image 450 relative to the same other structure 417, 419, 421. The processing application computing device 108 may then compare the positions of the TP image and the TD image to determine whether the organ has moved more than a predetermined amount. For example, if the organ has moved more than a predetermined threshold (e.g., whether the organ has moved closer to or farther away from another organ than a predetermined threshold), the processing application computing device 108 may determine that the OAR dose constraint has been violated. For example, if the heart moves at least 3 mm toward the esophagus, the OAR constraint may be violated.

[0059] In some examples, the processing application computing device 108 determines the volume of the organ within the TP image and the volume of the same organ within the TD image. If the absolute value of the difference between the calculated volumes is greater than a predetermined threshold, the processing application computing device 108 may determine that the OAR dose constraint is violated.

[0060] However, in other examples, the processing application computing device 108 may determine a position (e.g., a distance) between a target region in a TP image and an organ (such as an OAR), and another relative position between the target region in a TD image and the same organ. The processing application computing device 108 may determine that the organ is at risk based on the relative positions determined for each of the TP and TD images. For example, the processing application computing device 108 may compare (e.g., subtract) the determined relative positions, and may determine whether an OAR dose constraint is violated (e.g., a difference equals or exceeds a predetermined threshold) based on the comparison.

[0061] In some examples, the processing application computing device 108 may calculate one or more dose volume histograms (DVHs) for one or more portions of the OAR region of the TP image, such as any of the portions 455, 457, 459, 462 of the TP OAR region 452 of the TP image 450 (e.g., Figure 4B), and may determine whether one or more DVH dose constraints are violated based on the calculated DVH. For example, the processing application computing device 108 may determine an expected dose level within a TP overlap region (such as the initial overlap region 420) of a TP image (e.g., an image taken during the treatment plan). In addition, the processing application computing device 108 may determine the initial overlap region 420 (such as Figure 4A ), and the area can be multiplied by the expected dose level within the fourth portion 411 to determine the expected dose level within the TP overlap region 420. Similarly, the processing application computing device 108 determines the TD dose level within the TD overlap regions 470, 472. For example, the processing application computing device 108 can determine the dose level within each of the overlapping regions 470, 472, and these dose levels can be added to determine the TD dose level. The processing application computing device 108 can compare the expected dose level with the TD dose level to determine whether the DVH dose constraint is violated. For example, the processing application computing device 108 can determine the difference between the TD dose level and the expected dose level, and the difference can be compared with a predetermined threshold. If the difference is greater than the predetermined threshold, the processing application computing device 108 determines that the DVH dose constraint is violated.

[0062] In some examples, when a portion of the OAR region is at risk of receiving a dose above a predetermined threshold (e.g., if a radiation dose specified by the treatment plan is applied to the target region), the treatment application computing device 108 may determine that a DVH dose constraint is violated. For example, the treatment application computing device 108 may determine that the OAR region overlaps with a portion of the current treatment target region, and may determine whether the dose level associated with the portion of the current treatment target region is above a predetermined threshold. If the dose level is above the predetermined threshold, the treatment application computing device 108 determines that a DVH dose constraint is violated.

[0063] Generate alert

[0064] In some examples, the processing application computing device 108 displays an indication of whether any constraints are violated. For example, as described herein, the processing application computing device 108 can determine whether any OAR or DVH dose constraints are violated and can display an indication of whether any OAR and DVH dose constraints are violated within a user interface.

[0065] For example, Figure 5AA graphical user interface (GUI) 500 is illustrated that can be displayed, for example, by the display 206. The GUI 500 includes a DVH chart 502 and a risk alert pane 504. The DVH chart 502 can include a graph of the DVH calculated for each of one or more organs or organ parts. For example, a first graph 505 can correspond to the esophagus, while a second graph 507 can correspond to the target volume. In this example, no constraints are violated. Therefore, the risk alert pane 504 indicates that no risk is detected.

[0066] like Figure 5B As illustrated in FIG. 5 , the risk alert pane 504 of the GUI 500 includes a risk alert that a dose threshold has been exceeded (DVH dose constraint violation). In this example, an alert may be generated based on the DVH calculated for the first graph 505 because it indicates that the esophagus may receive more than Figure 5A Higher doses as indicated. Figure 5C , GUI 500 shows a TD target region 522 and a TD OAR region 524, each of which is superimposed on a TD image 520. In this example, the processing application computing device 108 can determine, for example, based on an overlap region 530 of the TD target region 522 and the TD OAR region 524, that the OAR dose constraint has been violated. Therefore, the processing application computing device 108 can display a risk alert for an OAR dose violation within the alert pane 504. In some examples, each risk alert is associated with an alert identification number (e.g., an alert ID). For example, Figure 5B The exceeded dose threshold may be associated with alarm identification number 0x0001, while Figure 5C The OAR dose violation of may be associated with an alarm identification number of 0x0100. The alarm identification number identifies the specific constraint that was violated. The processing application computing device 108 may display the corresponding alarm identification number for each alarm.

[0067] Return to see Figure 1In some examples, a medical professional (such as a dosimetrist) can operate a treatment plan computing device 106 to develop an initial treatment plan for a patient. For cardiac radiofrequency ablation, an electrophysiologist can also participate in developing a treatment plan. The initial treatment plan can be determined based on the TP image obtained for the patient, and the initial treatment target area and the expected dose level (e.g., DVH) within the initial treatment target area can be identified. Then, the patient can be scheduled for treatment. On the day of treatment, before any dose is applied, the patient is scanned to generate image data 103, which characterizes a TD image with a field of view corresponding to the treatment area. This scan can be performed by a linear accelerator integrated kV cone beam CT or any other type of scanner near or integrated with the processing device 110. The current anatomical structure of the patient's organs (such as organs in the patient's chest area) is captured in the TD image. The processing application computing device 108 can apply a transformation model to the image and the TD image to generate output data that characterizes the anatomical changes between the images. Based on the output data and the initial treatment target area, the processing application computing device 108 determines the current treatment target area within the current image. In addition, the treatment application computing device 108 determines an expected dose level within the current treatment target region and determines whether the current treatment target region includes any organs at risk (ie, OARs).

[0068] In some examples, the processing application computing device 108 displays a comparison of the TP treatment target area relative to the TP image, and a comparison of the TD treatment target area relative to the TD image, including any calculated dose levels. For example, the processing application computing device 108 can display the expected dose level for any organ (including any organ being treated and any OAR). In addition, and based on the determined dose level for any OAR, the processing application computing device 108 can determine whether any constraints are violated (e.g., a specific dose threshold for the OAR is exceeded). If the processing application computing device 108 determines that a constraint is violated, the processing application computing device 108 can provide an alarm, such as an auditory or visual alarm. In some examples, the processing application computing device 108 sends a message (e.g., an email or SMS message) to one or more predetermined recipients to determine the alarm.

[0069] Figure 3An exemplary portion of the treatment application computing device 108 is illustrated. In this example, the treatment application computing device 108 includes an image reconstruction engine 302, a treatment day (TD) target determination engine 304, a treatment plan (TP) target reconstruction engine 306, and a treatment risk determination engine 308. In some examples, one or more of the image reconstruction engine 302, the treatment day (TD) target determination engine 304, the treatment plan (TP) target reconstruction engine 306, and the treatment risk determination engine 308 may be implemented in hardware. In some examples, one or more of the image reconstruction engine 302, the treatment day (TD) target determination engine 304, the treatment plan (TP) target reconstruction engine 306, and the treatment risk determination engine 308 may be implemented as an executable program that is stored in a tangible, non-transitory memory such as a memory device. Figure 2 The executable program may be executed by one or more processors (such as Figure 2 Processor 201) executes.

[0070] In this example, the database 116 stores TP image data 315, TP target definition data 317, risk determination data 319, and other data. The TP image data 315 characterizes the patient TP images taken for treatment planning. The TP target definition data 317 characterizes the treatment region of the corresponding initial image (such as the TP treatment target region 404), the expected dose level within the treatment region, and may also characterize one or more OAR regions (such as the TP OAR region 402). In addition, the risk determination data 319 may characterize risk data, such as constraints associated with the risk of the treatment region (e.g., OAR dose constraints and DVH dose constraints, rules).

[0071] The TP plan target reconstruction engine 306 obtains the TP image data 315 and the TP target definition data 317 from the database 116. Based on the TP target definition data 317 and the TP image data 315, the TP plan target reconstruction engine 306 generates the TP target data 307 representing the TP image, which includes the TP treatment target region and one or more TP OAR regions. For example, the TP plan target reconstruction engine 306 may generate target region image data indicating the TP treatment target region based on the TP target definition data 317, and may also generate TP OAR image data indicating the TP OAR region based on the TP target definition data 317. The TP plan target reconstruction engine 306 may overlay the target region image data and the TP OAR image data on the TP image represented by the TP image data 315 to construct a final TP output image, and may generate the TP target data 307 representing the final TP output image.

[0072] In addition, on the day of treatment, the patient is scanned, for example, using an imager 355 (e.g., a linear accelerator integrated with a kV cone beam CT) to obtain treatment day image data 301. An image reconstruction engine 302 can obtain the patient's image data 301 and can reconstruct an image based on the obtained image data 301. In some examples, the reconstructed image can be a three-dimensional image of one or more organs of the patient. The image reconstruction engine 302 generates image reconstruction data 303 representing the reconstructed image and provides the image reconstruction data 303 to a target determination engine 304.

[0073] The TD target determination engine 304 receives the image reconstruction data 303 from the image reconstruction engine 302, and also obtains the TP target definition data 317 from the database 116. The TD target determination engine 304 also receives the TP target data 307 from the TP plan target reconstruction engine 306. Based on the TP target data 307, the TP target definition data 317, and the image reconstruction data 303, the TD target determination engine 304 generates TD target data 305, and the TD target data 305 represents a TD image including a current treatment target region and one or more TD OAR regions. For example, the TD target determination engine 304 can determine a mapping between the image reconstruction data 303 and the TP target data 307 (e.g., based on identifying corresponding structures and applying a transformation model, as described herein). In addition, in some examples, based on the TP treatment target region represented by the TP target data 307 and the determined mapping, the TD target determination engine 304 generates TD target image data representing the TD treatment target region, and generates TD OAR image data. In some examples, the TP plan target reconstruction engine 306 receives input from a user (such as a medical professional) that identifies and characterizes a TD OAR region (as described herein), and generates TD OAR image data based on the received input. The TD target determination engine 304 can overlay the TD target image data and the TD OAR image data on the TD image characterized by the image reconstruction data 303 to construct a final TD output image, and can generate TD target data 305 that characterizes the final TD output image.

[0074] The treatment risk determination engine 308 receives the TD target data 305 from the TD target determination engine 304, receives the TP target data 307 from the TP plan target reconstruction engine 306, and obtains the risk determination data 319 from the database 116. The treatment risk determination engine 308 also obtains the risk determination data 319 from the database 116, and generates the risk alert data 309 representing one or more risk alerts based on the TD target data 305, the TP target data 307, and the risk determination data 319. For example, the risk determination data 319 may represent one or more DVH dose constraints. The treatment risk determination engine 308 may determine the relative positioning of the OARs within the TP image represented by the TP target data 307 and the current image represented by the TD target data 305, and may calculate one or more dose volume histograms (DVHs) based on the relative positioning. In addition, the treatment risk determination engine 308 may determine whether one or more DVH dose constraints are violated based on the DVH. For example, if a radiation dose is applied to a target region and a portion of the OAR is at risk of receiving a dose above a predetermined threshold (characterized by a DVH dose constraint), the treatment risk determination engine 308 may determine that the DVH dose constraint is violated.

[0075] In other examples, the risk determination data 319 characterizes one or more OAR dose constraints. For example, each OAR dose constraint may include a threshold. In some examples, the processing risk determination engine 308 may determine the relative positioning between an organ (such as an OAR) in a TP image and a current image, and may determine that the OAR dose constraint is violated when the organ moves more than a predetermined distance characterized by the OAR dose constraint. In some examples, the processing risk determination engine 308 may determine the positioning (e.g., distance) between a target area in a TP image and an OAR, and another positioning between a target area in a TD image and the same OAR. Based on the relative positioning determined for each TP and TD image, the processing risk determination engine 308 may determine that the OAR dose constraint is violated. For example, the processing risk determination engine 308 may compare (e.g., subtract) the determined relative positioning, and may determine that the OAR dose constraint is violated when the difference equals or exceeds a predetermined threshold characterized by the OAR dose constraint.

[0076] In some examples, based on determining an overlap area between the current target region and the current OAR region (such as an overlap area 530 of the TD target region 522 and the TD OAR region 524), the treatment risk determination engine 308 determines that the OAR dose constraint has been violated. For example, the treatment risk determination engine 308 can determine that the dose level corresponding to the overlap area exceeds a predetermined threshold characterized by the OAR dose constraint. In some examples, the treatment risk determination engine 308 determines that the OAR dose constraint has been violated when the overlap area includes at least a predetermined percentage (e.g., 10%) of the current OAR region.

[0077] When a constraint (e.g., a rule) is violated, the processing risk determination engine 308 may generate risk alert data 309 representing one or more risk alerts. For example, the risk alert data 309 may identify one or more of a constraint identification value (e.g., a constraint ID), a TI image represented by the TP target data 307 (e.g., a corresponding TI image ID), and a TD image represented by the TD target data 305 (e.g., a corresponding TD image ID). The processing risk determination engine 308 may store the risk alert data 309 in the database 116. In some examples, the processing risk determination engine 308 provides the risk alert data 309 to the display 206 for display.

[0078] The treatment risk determination engine 308 may also generate overlay image data 311 based on the TD target data 305 and the TP target data 307, the overlay image data 311 characterizing the OAR region and the target region superimposed on the image (such as the TP image or the TD image). For example, the overlay image data 311 may include a TD target region (such as the TD target region 522) and a TD OAR region (such as the TD OAR region 524), each region superimposed on a TD image (such as the TD image 520). In some examples, the treatment risk determination engine 308 may generate overlay image data 311, the overlay image data 311 including the TD target region and the TD OAR region each superimposed on the TI image. In other examples, the treatment risk determination engine 308 may generate overlay image data 311, the overlay image data 311 including the TD image superimposed on the TI image. The treatment risk determination engine 308 may store the overlay image data 311 in the database 116. In some examples, the treatment risk determination engine 308 provides the overlay image data 311 to the display 206 for display.

[0079] Figure 6A flow chart of an example method 600 is illustrated, which may be performed, for example, by a treatment application computing device 108. Beginning at step 602, the treatment application computing device 108 receives a first image (e.g., a TP image) of a patient captured prior to a treatment plan. For example, the image may be a CT image. The image may be stored in a database such as the database 116. On the day of treatment, the treatment application computing device 108 may obtain the image (such as the TP image data 315) from the database 116. Additionally, in step 604, the treatment application computing device 108 may receive target definition data characterizing a target area of ​​the patient for treatment. For example, the treatment application computing device 108 may obtain the TP target definition data 317 corresponding to the obtained image.

[0080] Continuing to step 606, the processing application computing device 108 may receive a second image (e.g., a TD image) of the patient. For example, the image may be a cone beam CT image. At step 608, the processing application computing device 108 determines whether an organ of the patient is at risk based on the first image, the target definition data, and the second image. For example, as described herein, the processing application computing device 108 may determine whether a constraint, such as an OAR dose constraint or a DVH dose constraint, is violated based on the first image, the target definition data, and the second image.

[0081] At step 610, if it is determined that there is a risk, the method proceeds to step 612, where a risk alert is displayed based on the determined risk. For example, the processing application computing device 108 may determine to generate risk alert data 309 based on the determined one or more risks (e.g., constraint violations), and may provide at least a portion of the risk alert data 309 for display (such as, provided to the display 206). For example, the processing application computing device 108 may display a "DVH dose violation" or "OAR dose violation" alert within the alert pane 504. However, if no risk is determined at step 610, the method proceeds to step 614, where the processing application computing device 108 provides a no risk indication for display. For example, the processing application computing device 108 may display a "no risk detected" indication within the alert pane 504. The method then ends.

[0082] Figure 77 is a flow chart of an example method 700, which may be performed, for example, by a treatment application computing device 108. Starting at step 702, the treatment application computing device 108 receives a first image of a patient captured during a treatment plan. For example, before the day of treatment, the patient may lie on a table of the image scanning device 102, and a TP image of the patient may be captured. For example, the TP image may be a CT image. The TP image may be stored in a database such as the database 116. On the day of treatment, the treatment application computing device 108 may obtain an image (such as the TP image data 315) from the database 116. At step 704, the treatment application computing device 108 displays an indication of a first organ at risk region (such as a TP OAR region) and a first target region (such as a TP target region) superimposed on the first image. For example, as described herein, the treatment application computing device 108 may display a TP OAR region 402 and a TP treatment target region 404 superimposed on the TP image 400.

[0083] Continuing to step 706, the processing application computing device 108 receives a second image of the patient. For example, on the day of treatment, the patient can lie on the treatment table 110 and be scanned to obtain a TD image. The patient can be scanned by the onboard imager of the device 110 to obtain a cone beam CT image. At step 708, the processing application computing device 108 determines a second OAR region (e.g., a TD OAR region) within the second image. For example, the processing application computing device 108 can display the second image and can also receive input from a medical professional that characterizes the second OAR region (e.g., the medical professional can "draw" the second OAR region on a user interface that displays the second image) or can automatically outline using a known computing algorithm.

[0084] At step 710, the processing application computing device 108 determines a second target region (e.g., a TD target region) within the second image based on the first target region, the first OAR region, and the second OAR region. For example, as described herein, the processing application computing device 108 may apply a transformation model to the first image and the second image to generate output data characterizing anatomical changes between the images. Based on the output data and the first target region, the processing application computing device 108 may determine the second target region within the second image.

[0085] Continuing to step 712, the processing application computing device 108 displays an indication of the second OAR region and the second target region superimposed on the second image. For example, the processing application computing device 108 can generate overlapping image data 311, which includes the second target region (such as the TD target region 522) and the second OAR region (such as the TD OAR region 524), each of which is superimposed on the second image (such as the TD image 520). The processing application computing device 108 can provide the overlapping image data 311 to the display 206 for display. The method then ends.

[0086] In some examples, a system includes a database and a computing device that is communicatively coupled to the database. The computing device is configured to receive a first image of a patient (such as a TP image). The computing device is also configured to receive target definition data that characterizes a target area of ​​the patient for treatment. In addition, the computing device is configured to receive a second image of the patient (such as a TD image). The computing device is also configured to determine whether an organ of the patient is at risk based on the first image, the target definition data, and the second image. The computing device is also configured to provide a risk indication for display based on the determined result.

[0087] In some examples, the first image is captured before the second image, and the second image is captured on the day of treatment. In some examples, the target definition data characterizes a first organ-at-risk region and a first treatment target region. In some examples, the computing device is configured to determine a second treatment target region based on the first organ-at-risk region, the first treatment target region, and the second organ-at-risk region. The second organ-at-risk region may include the same organs as the first organ-at-risk region.

[0088] In some examples, the computing device is configured to provide a first image for display and receive input data characterizing a second organ-at-risk region. In some examples, the computing device is configured to determine a structure within the first image and the second image. The computing device is also configured to determine a mapping between the first image and the second image based on the structure. In addition, the computing device is configured to determine a second treatment target region based on the mapping.

[0089] In some examples, the computing device is configured to determine an overlapping area between the second treatment target region and the second organ-at-risk region. The computing device is further configured to determine a risk to the patient's organ based on the overlapping area. In some examples, the target definition data characterizes a first dose level within the first treatment target region. In some examples, the computing device is configured to determine a second dose level within the overlapping area, and determine the risk to the patient's organ based on the second dose level.

[0090] In some examples, the computing device is configured to superimpose the second treatment target region and the second organ-at-risk region on the second image. In some examples, the risk indication includes the second treatment target region and the second organ-at-risk region superimposed on the second image.

[0091] In some examples, a computer-implemented method includes receiving a first image of a patient (e.g., a TP image). The computer-implemented method also includes receiving target definition data characterizing a target area of ​​the patient for treatment. In addition, the computer-implemented method includes receiving a second image of the patient (e.g., a TD image). The computer-implemented method also includes determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image. The computer-implemented method also includes providing a risk indication for display based on the determination.

[0092] In some examples, the first image is captured before the second image, and the second image is captured on the day of treatment. In some examples, the target definition data characterizes a first organ at risk region and a first treatment target region. In some examples, the method further includes determining a second treatment target region based on the first organ at risk region, the first treatment target region, and the second organ at risk region.

[0093] In some examples, the computer-implemented method includes displaying a first image, and receiving input data characterizing a second organ-at-risk region. In some examples, the computer-implemented method includes determining a structure within the first image and the second image. The method also includes determining a mapping between the first image and the second image based on the structure. In addition, the method includes determining a second treatment target region based on the mapping.

[0094] In some examples, the computer-implemented method includes determining an overlap region between the second treatment target region and the second organ-at-risk region. The computer-implemented method also includes determining a risk to the patient's organ based on the overlap region.

[0095] In some examples, the target definition data characterizes a first dose level within the first treatment target region. In some examples, the method includes determining a second dose level within the overlapping region. In some examples, the method includes determining a risk to an organ of the patient based on the second dose level.

[0096] In some examples, the computer-implemented method includes superimposing the second treatment target region and the second organ-at-risk region on the second image. In some examples, the risk indication includes the second treatment target region and the second organ-at-risk region superimposed on the second image.

[0097] In some examples, a non-transitory computer-readable medium stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations, the operations comprising: receiving a first image of a patient (e.g., a TP image). The operations also include receiving target definition data characterizing a target area of ​​the patient for treatment. In addition, the operations include receiving a second image of the patient (e.g., a TD image). The operations also include determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image. The operations also include providing a risk indication for display based on the determination.

[0098] In some examples, the first image is captured before the second image, and the second image is captured on the day of treatment. In some examples, the target definition data characterizes a first organ at risk region and a first treatment target region. In some examples, the operations also include determining a second treatment target region based on the first organ at risk region, the first treatment target region, and the second organ at risk region.

[0099] In some examples, the operation includes providing a first image for display and receiving input data characterizing a second organ-at-risk region. In some examples, the operation includes determining a structure within the first image and the second image. The operation also includes determining a mapping between the first image and the second image based on the structure. In addition, the operation includes determining a second treatment target region based on the mapping.

[0100] In some examples, the operation includes determining an overlap region between the second treatment target region and the second organ-at-risk region. The operation also includes determining a risk to the patient's organ based on the overlap region.

[0101] In some examples, the target definition data characterizes a first dose level within the first treatment target region. In some examples, the operation includes determining a second dose level within the overlap region. In some examples, the operation includes determining a risk to an organ of the patient based on the second dose level.

[0102] In some examples, the operation includes superimposing the second treatment target region and the second organ-at-risk region on the second image. In some examples, the risk indication includes the second treatment target region and the second organ-at-risk region superimposed on the second image.

[0103] In some examples, a system includes components for receiving a first image of a patient. The system also includes components for receiving target definition data characterizing a target area of ​​the patient for treatment. In addition, the system includes components for receiving a second image of the patient. The system also includes components for determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image. The system also includes components for providing a risk indication for display based on the determination.

[0104] In some examples, the first image is captured before the second image, and the second image is captured on the day of treatment. In some examples, the target definition data characterizes a first organ at risk region and a first treatment target region. In some examples, the system includes a component for determining a second treatment target region based on the first organ at risk region, the first treatment target region, and the second organ at risk region.

[0105] In some examples, the system includes components for displaying the first image and receiving input data characterizing a second organ-at-risk region. In some examples, the system includes components for determining a structure within the first image and the second image. The system also includes components for determining a mapping between the first image and the second image based on the structure. In addition, the system includes components for determining a second treatment target region based on the mapping.

[0106] In some examples, the system includes a component for determining an overlap region between the second treatment target region and the second organ-at-risk region. The system also includes a component for determining a patient organ risk based on the overlap region.

[0107] In some examples, the target definition data characterizes a first dose level within the first treatment target region. In some examples, the system includes a component for determining a second dose level within the overlapping region. In some examples, the system includes a component for determining a patient organ risk based on the second dose level.

[0108] In some examples, the system includes means for superimposing the second treatment target region and the second organ at risk region on the second image. In some examples, the risk indication includes the second treatment target region and the second organ at risk region superimposed on the second image.

[0109] Although the above method refers to the illustrated flowchart, it can be appreciated that many other ways can be used to perform the actions associated with the method. For example, the order of some operations can be changed, and some operations described can be optional.

[0110] In addition, the methods and systems described herein may be embodied at least in part in the form of computer-implemented processes and devices for practicing these processes. The disclosed methods may also be embodied at least in part in the form of tangible, non-transient machine-readable storage media encoded with computer program code. For example, the steps of the method may be embodied in hardware, in executable instructions executed by a processor (e.g., software), or in a combination thereof. For example, the medium may include RAM, ROM, CD-ROM, DVD-ROM, BD-ROM, hard drive, flash memory, or any other non-transient machine-readable storage medium. When the computer program code is loaded into a computer and executed by the computer, the computer becomes a device for practicing the method. The method may also be embodied at least in part in the form of a computer, into which the computer program code is loaded or executed, so that the computer becomes a special-purpose computer for practicing the method. When implemented on a general-purpose processor, the computer program code segment configures the processor to create a specific logic circuit. These methods may alternatively be embodied at least in part in a dedicated integrated circuit for performing these methods.

[0111] The foregoing is provided to illustrate, explain, and describe the disclosed embodiments. Modifications and adjustments to these embodiments will be apparent to those skilled in the art and may be made without departing from the scope or spirit of these disclosures.

Claims

1. A system comprising: database; as well as A computing device, communicatively coupled to the database and configured to: receiving a first image of a patient; receiving target definition data characterizing a target area of ​​said patient for treatment; receiving a second image of the patient; determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image; as well as Based on the determination, a risk indication is provided for display. 2 . The system of claim 1 , wherein the first image is captured before the second image, and the second image is captured on the day of treatment.

3. The system of claim 1 or claim 2, wherein the target definition data characterizes a first organ-at-risk region and a first treatment target region, and wherein the computing device is configured to: Based on the first organ-at-risk region, the first treatment target region, and the second organ-at-risk region, a second treatment target region is determined.

4. The system of claim 3, wherein the computing device is configured to: providing the first image for display; and Input data characterizing the second organ-at-risk region is received.

5. The system of claim 3 or claim 4, wherein the computing device is configured to: determining structures within the first image and the second image; Based on the structure, determining a mapping between the first image and the second image: and Based on the mapping, the second processing target area is determined.

6. The system of claim 3 or claim 4, wherein the computing device is configured to: determining an overlapping region between the second treatment target region and the second organ-at-risk region; and Based on the overlapping region, the risk to the organ of the patient is determined.

7. The system of claim 6, wherein the target definition data characterizes a first dose level within the first treatment target area, and wherein the computing device is configured to: determining a second dose level within the overlapping region; and Based on the second dose level, the risk to the organ of the patient is determined.

8. The system of claim 3 or claim 4, wherein the computing device is configured to: The second treatment target region and the second organ-at-risk region are superimposed on the second image, wherein the risk indication includes the second treatment target region and the second organ-at-risk region superimposed on the second image.

9. A computer-implemented method comprising: receiving a first image of a patient; receiving target definition data characterizing a target area of ​​said patient for treatment; receiving a second image of the patient; determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image; as well as Based on the determination, a risk indication is provided for display.

10. The computer-implemented method of claim 9, wherein the first image is captured before the second image, and the second image is captured on a day of treatment.

11. The computer-implemented method of claim 9 or claim 10, wherein the target definition data characterizes a first organ-at-risk region and a first treatment target region, the method further comprising: Based on the first organ-at-risk region, the first treatment target region, and the second organ-at-risk region, a second treatment target region is determined.

12. The computer-implemented method of claim 11 , further comprising: providing the first image for display; as well as Input data characterizing the second organ-at-risk region is received.

13. The computer-implemented method of claim 11 or claim 12, further comprising: determining structures within the first image and the second image; Based on the structure, determining a mapping between the first image and the second image: and Based on the mapping, the second processing target area is determined.

14. The computer-implemented method of claim 11 or claim 12, further comprising: determining an overlapping area between the second treatment target area and the second organ-at-risk area; as well as Based on the overlapping region, the risk to the organ of the patient is determined.

15. The computer-implemented method of claim 14, wherein the target definition data characterizes a first dose level within the first treatment target area, and wherein the method further comprises: determining a second dose level within the overlapping region; as well as Based on the second dose level, the risk to the organ of the patient is determined.

16. The computer-implemented method of claim 11 or claim 12, further comprising: The second treatment target region and the second organ-at-risk region are superimposed on the second image, wherein the risk indication includes the second treatment target region and the second organ-at-risk region superimposed on the second image.

17. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: receiving a first image of a patient; receiving target definition data characterizing a target area of ​​said patient for treatment; receiving a second image of the patient; determining whether an organ of the patient is at risk based on the first image, the target definition data, and the second image; as well as Based on the determination, a risk indication is provided for display.

18. The non-transitory computer readable medium of claim 17, wherein the first image is captured before the second image, and the second image is captured on a day of treatment.

19. The non-transitory computer readable medium of claim 17 or claim 18, wherein the target definition data characterizes a first organ at risk region and a first treatment target region, and wherein the operation further comprises determining a second treatment target region based on the first organ at risk region, the first treatment target region, and a second organ at risk region.

20. The non-transitory computer readable medium of claim 19, wherein the operations further comprise: providing the first image for display; as well as Input data characterizing the second organ-at-risk region is received.

Images