Method and apparatus for determining radio frequency ablation therapy

Abstract

Systems and methods for cardiac radiofrequency ablation treatment planning are disclosed. In some examples, a computing device receives image volume and dose matrix data. The computing device generates a first mesh of an organ substructure for an organ based on a substructure contour of the organ. Further, the computing device generates a second mesh of an isodose volume based on the dose matrix data. The computing device displays the first mesh of the organ substructure and the second mesh of the isodose volume within the same scene. In some examples, the computing device samples a plurality of dose values, determines a representative dose value for each of a plurality of points along a surface of the dose matrix, and generates an image for display based on the representative dose value. In some examples, a segmentation model is generated for display based on the representative dose value.

Description

TECHNICAL FIELD

[0001] Aspects of the present disclosure generally relate to medical diagnostic and treatment systems, and more particularly, to providing radiofrequency ablation diagnostic, treatment planning, and delivery systems for diagnosing and treating diseases, such as cardiac arrhythmias. BACKGROUND

[0002] Various techniques can be employed to capture or image metabolic, electrical, and anatomical information of a patient. For example, positron emission tomography (PET) is a metabolic imaging technique that produces tomographic images representative of the distribution of positron emitting isotopes within 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 example techniques can be combined with one another to generate a composite anatomical and functional image. For example, a software system, such as VelocityAI® software from Varian Medical Systems, Inc., uses an image fusion process to combine different types of images to warp and / or register the images to produce a composite image. TM

[0003] In cardiac radiofrequency ablation, medical professionals work together to diagnose cardiac arrhythmias, identify regions for ablation, prescribe radiation therapy, and create a radiofrequency ablation treatment plan. Typically, each of the different medical professionals receives supplemental medical training to specialize in different aspects of the treatment process. For example, an electrophysiologist can identify one or more regions or targets of a patient's heart to treat cardiac arrhythmias based on the patient's anatomical structure and electrophysiological properties. For example, the electrophysiologist can use a combined PET and cardiac CT image as input to manually define a target region for ablation. Once the electrophysiologist defines the target region, a radiation oncologist can prescribe radiation therapy, including, for example, the number of radiation fractions to be delivered, the radiation dose to be delivered to the target region, and the maximum dose to be delivered to a neighboring organ at risk. Once the radiation dose is prescribed, a dosimetrist can typically create a radiofrequency treatment plan based on the prescribed radiation therapy. The radiation oncologist typically then reviews and approves the treatment plan to be delivered. Prior to delivering the radiofrequency ablation treatment plan, the electrophysiologist can want to know the location, size, and shape of the dose region of the defined target volume to confirm that the target location of the patient defined by the radiofrequency ablation treatment plan is correct.

[0004] ​Within a cardiac radiofrequency ablation workflow, each medical professional uses a system designed to accomplish their task. For example, an electrophysiologist can work within a system that allows viewing of 3-dimensional (3D) rendered surfaces and images from the system, such as cardiac CT images, cardiac MR images, and PET / CT images. The electrophysiologist can be satisfied with viewing 3D images, such as 3D surface renderings. On the other hand, a radiation therapy professional can work within a specialized system, such as a treatment planning system, that records radiation therapy prescriptions or treatment goals and optimizes a treatment plan to closely meet these goals. Aspects of a treatment planning system can include: importing and displaying previously acquired two-dimensional (2D) planning CT or MR images; inputting radiation therapy prescriptions, including treatment objectives and constraints; contouring or segmenting a target region to be irradiated on a 3D rendering using stacked 2D CT slices; optimizing a treatment plan with respect to the radiation therapy prescriptions; and exporting the treatment plan to a radiation delivery system. There is an opportunity to improve cardiac radiofrequency ablation planning systems used by medical professionals for cardiac radiofrequency ablation diagnosis and radiation therapy planning. SUMMARY

[0005] Systems and methods for cardiac radiofrequency ablation diagnosis and planning are disclosed. In some examples, a computer-implemented method includes receiving: substructure data identifying a substructure contour of an organ; and dose matrix data of the organ. The method further includes generating a first mesh of the substructure of the organ based on the substructure data. The method further includes generating a second mesh of an isodose volume based on the dose matrix data. Further, the method includes displaying the first mesh of the substructure of the organ and the second mesh of the isodose volume within the same scene or workspace.

[0006] 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 comprising receiving: substructure data identifying a substructure contour of an organ; and dose matrix data of the organ. The operations further include generating a first mesh of the substructure of the organ based on the substructure data. Further, the operations include generating a second mesh of an isodose volume based on the dose matrix data. The operations further include displaying the first mesh of the substructure of the organ and the second mesh of the isodose volume within the same scene or workspace.

[0007] In some examples, a system includes a computing device configured to receive: substructure data identifying a substructure contour of an organ; and dose matrix data identifying a dose for the organ. The computing device is further configured to generate a first mesh of an organ substructure for the organ based on the substructure data. Further, the computing device is configured to generate a second mesh of an isodose volume based on the dose matrix data. The computing device is further configured to display the first mesh of the organ substructure and the second mesh of the isodose volume within a same scene or workspace.

[0008] In some examples, a method includes means for receiving substructure data identifying a substructure contour of an organ and dose matrix data identifying a dose for the organ. The method further includes means for generating a first mesh of an organ substructure for the organ based on the substructure data. The method further includes means for generating a second mesh of an isodose volume based on the dose matrix data. Further, the method includes means for displaying the first mesh of the organ substructure and the second mesh of the isodose volume within a same scene or workspace. BRIEF DESCRIPTION OF DRAWINGS

[0009] The features and advantages of the present disclosure will be more fully understood from the following detailed description of example embodiments taken in conjunction with the accompanying drawings. The detailed description shall not be treated as limiting the example embodiments. The detailed description of the example embodiments shall be taken in conjunction with the drawings, which are described below. Figure One Consideration is given to the drawings, where like elements are numbered alike.

[0010] Figure 1 A cardiac radiofrequency ablation treatment planning system is illustrated in accordance with some embodiments;

[0011] Figure 2 A block diagram of a radiofrequency ablation treatment planning computing device is illustrated in accordance with some embodiments;

[0012] Figure 3 An electrophysiologist (EP) workspace provided by an EP workspace computing device is illustrated in accordance with some embodiments;

[0013] Figure 4 A radiation oncologist (RO) workspace provided by an RO workspace computing device is illustrated in accordance with some embodiments;

[0014] Figure 5A A method of generating a parallel display of structure and dose volume meshes is illustrated in accordance with some embodiments;

[0015] Figure 5B A mesh display in accordance with a method of Figure 5A in accordance with some embodiments;

[0016] Figure 6A A determination of surface color for a substructure is illustrated in accordance with some embodiments;

[0017] Figure 6B a three-dimensional image of a substructure with surface colors is illustrated in accordance with some embodiments;

[0018] Figure 7 mapping of a three-dimensional surface mesh to a segmented model is illustrated in accordance with some embodiments;

[0019] Figure 8A is a flowchart of an example method of displaying images within a RO workspace in accordance with some embodiments; Figure 4 is a flowchart of an example method of displaying images within a RO workspace in accordance with some embodiments;

[0020] Figure 8B is a flowchart of an example method of displaying images within a RO workspace in accordance with some embodiments; Figure 3 is a flowchart of an example method of displaying images within a RO workspace in accordance with some embodiments;

[0021] Figure 9 is a flowchart of an example method of displaying three-dimensional meshes in accordance with some embodiments; and

[0022] Figure 10 is a flowchart of an example method of displaying adjusted models of organs in accordance with some embodiments. DETAILED DESCRIPTION

[0023] The description of the preferred embodiments is intended to be read in connection with the accompanying drawings, which are to be considered part of the entire written description. While the disclosure is amenable to various modifications and alternative forms, specific embodiments have been shown by way of example in the drawings and will be described in detail in this document. The objectives and other advantages of the claimed subject matter will become more apparent from the following detailed description of the example embodiments when considered in conjunction with the drawings.

[0024] It should be understood, however, that the disclosure is not intended to be limited to the particular forms disclosed. Rather, the disclosure is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the example embodiments. The terms “coupled,” “coupled to,” “operably connected,” “operably connected to,” and the like, should be construed broadly and are intended to encompass a mechanical connection, an electrical connection, a magnetic connection, a wireless connection, a physical connection, and / or any other connection via which devices or components are intended to be coupled for purposes of the subject disclosure.

[0025] Turning to the drawings, Figure 1A block diagram of a radioablation diagnosis and treatment planning system 100 is illustrated. In some embodiments, the system 100 can be a cardiac diagnosis and treatment planning system including an imaging device 102, an electrophysiologist (EP) workspace computing device 104, a radio-oncologist (RO) workspace computing device 106, a shared EP and RO workspace computing device 108, and a database 116 communicatively coupled over a communication network 118. For example, the imaging device 102 can be a CT scanner, an MR scanner, a PET scanner, an electrophysiology imaging device, an ECG, or an ECG imager. In some examples, the imaging device 102 can be a PET / CT scanner or a PET / MR scanner.

[0026] The EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108 can each be any suitable computing device, including any suitable hardware or hardware and software combination, for processing data. For example, each 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 circuitry, or any other suitable circuitry. Additionally, each can transmit data to and receive data from the communication network 118. For example, each of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace 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.

[0027] For example, Figure 2 A radiofrequency ablation diagnosis and treatment planning computing device 200 is illustrated, which can include one or more of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108. Reference is made to Figure 2 The radiofrequency ablation diagnosis and treatment planning computing device 200 can include one or more processors 201, a working memory 202, one or more input / output devices 203, an instruction memory 207, a transceiver 204, one or more communication ports 207, and a display 206, all operably coupled to one or more data buses 208. The data buses 208 allow communication between the various devices. The data buses 208 can include wired or wireless communication channels.

[0028] The processor 201 can include one or more different processors, each having one or more cores. Each different processor can have the same or different architecture. The processor 201 can 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.

[0029] The instruction memory 207 can store instructions that can be accessed (e.g., read) and executed by the processor 201. For example, the instruction memory 207 can be a non-transitory computer-readable storage medium, such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, removable disks, CD-ROMs, any non-volatile memory, or any suitable memory. The processor 201 can be configured to perform a certain function or operation by executing code stored on the instruction memory 207 that embodies the function or operation. For example, the processor 201 can be configured to execute code stored in the instruction memory 207 to perform one or more of any of the functions, methods, or operations disclosed herein.

[0030] Additionally, the processor 201 can store data to and read data from the working memory 202. For example, the processor 201 can store a working instruction set to the working memory 202, such as instructions loaded from the instruction memory 207. The processor 201 can also use the working memory 202 to store dynamic data created during operation of the radiofrequency ablation diagnosis and treatment planning computing device 200. The working memory 202 can be a random access memory (RAM), such as static random access memory (SRAM) or dynamic random access memory (DRAM), or any other suitable memory.

[0031] The input-output device 203 can include any suitable device that allows data input or output. For example, the input-output device 203 can include one or more of a keyboard, a touchpad, a mouse, a stylus, a touchscreen, a physical button, a speaker, a microphone, or any other suitable input or output device.

[0032] For example, the communication port(s) 209 can 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, the communication port(s) 209 allow for encoding of executable instructions in the instruction memory 207. In some examples, the communication port(s) 209 allow for transmission (e.g., upload or download) of data, such as image data.

[0033] The display 206 can be any suitable display, such as a 3D viewer or monitor. The display 206 can display the user interface 205. The user interface 205 can enable a user to interact with the radio ablation diagnosis and treatment planning computing device 200. For example, the user interface 205 can be a user interface of an application that allows a user (e.g., a medical professional) to view or manipulate scan images. In some examples, a user can interact with the user interface 205 by engaging the input-output device 203. In some examples, the display 206 can be a touchscreen, where the user interface 205 is displayed on the touchscreen. In some examples, the display 206 displays images (e.g., image slices) of scan image data.

[0034] The transceiver 204 allows for communication with a network, such as the communication network 118. For example, if the communication network 118 is a cellular network, the transceiver 204 is configured to allow for communication with the cellular network. In some examples, the transceiver 204 is selected based on the type of communication network 118 in which the radio ablation diagnosis and treatment planning computing device 200 will operate. The processor(s) 201 are operable to receive data from or send data to a network, such as the communication network 118, via the transceiver 204. Figure 1 Figure 1 The transceiver 204 allows for communication with a network, such as the communication network 118. For example, if the communication network 118 is a cellular network, the transceiver 204 is configured to allow for communication with the cellular network. In some examples, the transceiver 204 is selected based on the type of communication network 118 in which the radio ablation diagnosis and treatment planning computing device 200 will operate. The processor(s) 201 are operable to receive data from or send data to a network, such as the communication network 118, via the transceiver 204. Figure 1

[0035] Referring back to Figure 1 , the database 116 can 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 memory device on another application server, a networked computer, or any other suitable remote storage. In some examples, the database 116 can be a local storage device, such as a hard drive, non-volatile memory, or a USB stick, for one or more of the following: the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108.

[0036] The communication network 118 can be a network, a cellular network (such as a network), network, a satellite network, a wireless local area network (LAN), 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 can provide access to, for example, the Internet.

[0037] ​​The imaging device 102 is operable to scan an image, such as an image of a patient’s organ, and provide image data 103 (e.g., measurement data) to the communication network 118 that identifies and characterizes the scanned image. Alternatively, the imaging device 102 is operable to acquire electrical imaging, such as a cardiac ECG image. For example, the imaging device 102 can scan a patient’s structure (e.g., an organ), and can transmit image data 103 identifying one or more slices of a 3D volume of the scanned structure to one or more of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108 over the communication network 118. In some examples, the imaging device 102 stores the image data 103 in the database 116 from which one or more of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108 can retrieve the image data 103.

[0038] In some examples, the EP workspace computing device 104 is operable to communicate with one or more of the RO workspace computing device 106, and the shared EP and RO workspace computing device 108. Similarly, in some examples, the RO workspace computing device 106 is operable to communicate with one or more of the EP workspace computing device 104, and the shared EP and RO workspace computing device 108. In some examples, the shared EP and RO workspace computing device 108 is operable to communicate with one or more of the EP workspace computing device 104 and the RO workspace computing device 106. In some examples, one or more of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108 communicate with each other through the database 116 (e.g., by storing and retrieving data from the database 116).

[0039] In some examples, an electrophysiologist operates the EP workspace computing device 104, while a radiation oncologist operates the RO workspace computing device 106, and one or more of the electrophysiologist and the radiation oncologist operate the shared EP and RO workspace computing device 108. In some examples, one or more EP workspace computing devices 104 are located in a first area 122 of a medical facility, while one or more RO workspace computing devices 106 are located in a second area 124 of the medical facility 120, and one or more shared EP and RO workspace computing devices 108 are located in a third area of the medical facility 120. Although optionally illustrated as part of the medical facility 120, in some examples, one or more of the EP workspace computing devices 104, the RO workspace computing devices 106, and the shared EP and RO workspace computing devices 108 can be located in separate medical facilities. In some examples, one or more of the EP workspace computing devices 104, the RO workspace computing devices 106, and the shared EP and RO workspace computing devices 108 share resources (such as processing resources, memory resources, software (e.g., applications), or any other resources) and / or communicate with each other over the cloud. For example, each of the EP workspace computing devices 104, the RO workspace computing devices 106, and the shared EP and RO workspace computing devices 108 can be part of a cloud-based network that allows for resource sharing and communicate with each other.

[0040] The EP workspace computing device 104 can allow an electrophysiologist to view 3D images, such as 3D images generated from the image data 103, and can also allow for viewing of multi-modality images and fusion (e.g., cardiac CT scans, cardiac MR scans, echocardiograms, ECGI electronic maps, PET / CT scans, single photon emission computed tomography (SPECT) scans) and organ structure (e.g., segmentation) models, such as a 17-segment model representing basal, mid-cavity, and apical levels of the ventricles of the heart. For example, the RO workspace computing device 106 can allow a radiation oncologist to view and manipulate treatment planning CT scans (e.g., based on the image data 103), treatment planning tools, dose displays, treatment doses, dose prescriptions, and dose volume histograms (DVHs). The shared EP and RO workspace computing device 108 can allow an electrophysiologist to view and manipulate grids of structures (e.g., cardiac substructures) and dose volumes, such as 3D grids.

[0041] In some examples, each of the EP workspace computing device 104, the RO workspace computing device 106, and the shared EP and RO workspace computing device 108 executes a respective application, wherein each application is specifically tailored (e.g., customized) according to the expectations of the corresponding medical professional. For example, the RO workspace computing device 106 may execute an RO application specifically tailored to the expectations and tasks of a radiation oncologist. The EP workspace computing device 104 may execute an EP application specifically tailored to the expectations and tasks of an electrophysiologist, and the shared EP and RO workspace computing device 108 may execute one or more applications specifically tailored to the expectations of one or both of an electrophysiologist and a radiation oncologist.

[0042] In some examples, in response to input from the electrophysiologist, the EP workspace computing device 104 performs an action. Additionally, in response to the input, the EP workspace computing device 104 may generate EP adjustment data 105 identifying and characterizing the action, and may transmit the EP adjustment data 105 to the RO workspace computing device 106. In response to receiving the EP adjustment data 105, the RO workspace computing device 106 may perform another action.

[0043] For example, an electrophysiologist may provide input to the EP workspace computing device 104 (e.g., via the input / output device 203), and in response, the EP workspace computing device 104 may align a segmentation model (e.g., a 17-segment model) with a structure of an organ (e.g., a ventricle of the heart). The EP workspace computing device 104 may also generate EP adjustment data 105 identifying and characterizing the alignment, and may transmit the EP adjustment data 105 to the RO workspace computing device 106. In response to receiving the EP adjustment data 105, the RO workspace computing device 106 may display the 17 segments in the planning CT image. Thus, the radiation oncologist operating the RO workspace computing device 106 may view the 17 segments displayed in the planning CT image. Alternatively, the EP workspace computing device 104 may transmit the EP adjustment data 105 to the shared EP and RO workspace computing device 108. For example, in response to receiving the EP adjustment data 105, the shared EP and RO workspace computing device 108 may display the 17 segments in the planning CT image.

[0044] As another example, an electrophysiologist can provide input to the EP workspace computing device 104 (e.g., through the input / output device 203), and in response, the EP workspace computing device 104 can create a target (e.g., a target region of a structure). The EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes the target, and can further transmit the generated EP adjustment data 105 to the RO workspace computing device 106. In response, the RO workspace computing device 106 can generate an image of the target (e.g., a 3D volume), and can display the image of the target to, for example, a radiation oncologist. Alternatively, the EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes the target, and can further transmit the generated EP adjustment data 105 to the shared EP and RO workspace computing device 108. In response, the shared EP and RO workspace computing device 108 can generate an image of the target (e.g., a 3D volume), and can display the image of the target to, for example, a radiation oncologist.

[0045] Further, in some examples, the electrophysiologist can provide a second input to the EP workspace computing device 104 to edit the target. In response to the second input, the EP workspace computing device 104 can edit the target according to the second input. The EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes the edit to the target, and can further transmit the generated EP adjustment data 105 to the RO workspace computing device 106. In response, the RO workspace computing device 106 can edit the image of the target according to the edit to the target identified by the EP adjustment data 105, and can display the edited image to the radiation oncologist. Alternatively, the shared EP and RO workspace computing device 108 can receive the EP adjustment data 105, and the radiation oncologist can edit the target according to the edit identified by the EP adjustment data 105.

[0046] In some examples, the radiation oncologist can provide input to the RO workspace computing device 106. In response, the RO workspace computing device 106 performs an action. Further, the RO workspace computing device 106 can generate RO adjustment data 107 that identifies and characterizes the action, and can transmit the RO adjustment data 107 to the EP workspace computing device 104. In response to receiving the RO adjustment data 107, the EP workspace computing device 104 can perform another action.

[0047] As an example, and continuing the example above, the radiation oncologist can provide input to the RO workspace computing device 106 to provide a second edit to the displayed target. In response, the RO workspace computing device 106 can edit the displayed target according to the input edit. Additionally, the RO workspace computing device 106 can generate RO adjustment data 107 that identifies and characterizes the second edit, and can transmit the RO adjustment data 107 to the EP workspace computing device 102. The EP workspace computing device 102 can receive the RO adjustment data 107, and can edit the target according to the second edit identified by the RO adjustment data 107. Alternatively, the shared EP and RO workspace computing device 108 can receive the RO adjustment data 107, and the electrophysiologist can edit the target according to the edit identified by the RO adjustment data 107.

[0048] Accordingly, embodiments described herein can allow various medical professionals, such as electrophysiologists and radiation oncologists, to more effectively collaborate during the generation of a treatment plan. For example, embodiments can allow real-time communication between the EP workspace computing device 104 and the RO workspace computing device 106. Further, the communication allows edits (e.g., changes, updates) to a workspace of one medical professional (e.g., the electrophysiologist workspace on the EP workspace computing device 104) that are based on edits performed by another medical professional to another workspace (e.g., the workspace of the radiation oncologist on the RO workspace computing device 106). Alternatively, the communication allows edits (e.g., changes, updates) to a workspace of one medical professional (e.g., the electrophysiologist workspace on the EP workspace computing device 104) that are based on edits performed by another medical professional to another workspace (e.g., the workspace of the radiation oncologist on the RO workspace computing device 106), and received by the shared EP and RO workspace to collaborate in the shared EP and RO workspace.

[0049] Figure 3 The EP workspace 302 is illustrated as being provided by the EP workspace computing device 104. The EP workspace computing device 104 includes an input / output device 203, such as a keyboard, for allowing a user (such as an electrophysiologist) to provide input. For example, the EP workspace computing device 104 can display the EP workspace 302 in response to executing an application, such as an application specifically made for electrophysiologists.

[0050] In this example, the EP workspace 302 displays various ablation volume images 304A, 304B, 304C, 304D. For example, the various ablation volume images 304A, 304B, 304C, 304D can have been captured by the imaging device 102. In some examples, the EP workspace computing device 104 allows the electrophysiologist to identify regions of the ablation volume image 304A with one or more identification icons 306. The EP workspace 302 also displays a segmentation model 310 of the organ (in this example, a 17-segment model of the heart ventricle) and a 3D image 312 of the organ.

[0051] Figure 4 The RO workspace 402 is illustrated as being provided by the RO workspace computing device 106. The RO workspace computing device 106 includes an input / output device 203, such as a keyboard, for allowing a user (such as a radiation oncologist) to provide input. The RO workspace computing device 106 can display the RO workspace 402 in response to executing an application, such as an application specifically made for a radiation oncologist. In this example, the RO workspace 402 displays various image scans 404A, 404B, 404C as well as a 3D substructure grid 406. The image scan 404A can be a scan taken from the top of a person (e.g., looking down at the head of the person). The image scan 404B can be a scan taken from the front of the person. The image scan 404C can be a scan taken from the side (e.g., right side) of the person. The RO workspace 402 also displays a menu window 408 that allows selection of images for display.

[0052] Referring back to Figure 3 , the EP workspace 302 allows the electrophysiologist to select one or more regions 308 of the segmentation model 310. In some examples, the EP workspace 302 changes the color of the selected regions 308 to indicate selection. In response to selecting the regions 308, the EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes the selected regions 308. The EP workspace computing device 104 can transmit the EP adjustment data 105 to the RO workspace computing device 106.

[0053] In some examples, the EP workspace 302 includes a drawing tool that allows the electrophysiologist to identify (e.g., define) regions of a structure 330 displayed in the ablation volume image 304B. For example, the regions of the structure 330 can be regions that the electrophysiologist wants to identify or protect from radiofrequency ablation. In response to identifying the regions of the structure 330, the EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes the identified regions of the structure. The EP workspace computing device 104 can transmit the EP adjustment data 105 to the RO workspace computing device 106.

[0054] For example, the EP workspace 302 can provide an icon, such as a “send” icon, that when selected (e.g., clicked) can cause the EP workspace computing device 104 to transmit the EP adjustment data 105 to the RO workspace computing device 106. In some examples, a menu (e.g., a drop-down menu) allows the electrophysiologist to select one or more RO workspace computing devices 106. In response, the EP workspace 302 can transmit the EP adjustment data 105 to the selected RO workspace computing devices 106.

[0055] Referring back to Figure 4 In response to receiving the EP adjustment data 105, the RO workspace computing device 106 can identify the corresponding portion 411 of the organ 410 in the image scan 404B. The RO workspace computing device 106 can apply one or more algorithms to determine the corresponding portion 411 of the organ 410. For example, the RO workspace computing device 106 can identify the corresponding portion 411 of the organ 410 by highlighting a perimeter of the corresponding portion 411 of the organ 410. Thus, the radiologist can easily see the area identified (e.g., targeted) by the electrophysiologist operating the EP workspace computing device 104.

[0056] Referring back to Figure 3 And also in response to selecting the area 308, the EP workspace 302 can automatically edit (e.g., update) the 3D image 312. For example, the EP workspace 302 can change a color of the corresponding portion 314 of the 3D image 312 based on the selected area 308. The EP workspace 302 can also allow the electrophysiologist to rotate the 3D image 312. For example, the electrophysiologist can rotate the 3D image 312 about the longitudinal axis 316, where the 3D image 312 is updated according to the rotation.

[0057] Referring back to Figure 4, the RO workspace 402 can include a drawing tool that allows the radiation oncologist to select a portion 411 of the organ 410 in the image scan 404B. In some examples, the workspace 402 highlights the selected portion 411. In response to selecting the portion 411, the RO workspace 402 can generate RO adjustment data 107 that identifies and characterizes the selected portion 411. The RO workspace computing device 106 can transmit the RO adjustment data 107 to the EP workspace computing device 104. For example, the RO workspace 402 can provide an icon, such as a “send” icon, that, when selected (e.g., clicked), can cause the RO workspace computing device 106 to transmit the RO adjustment data 107 to the EP workspace computing device 104. In some examples, a menu (e.g., a drop-down menu) allows the radiation oncologist to select one or more EP workspace computing devices 104. In response, the RO workspace 402 can transmit the RO adjustment data 107 to the selected EP workspace computing devices 104.

[0058] Referring to Figure 3 In response to receiving the RO adjustment data 107, the EP workspace computing device 104 can identify a corresponding portion 314 of the 3D image 312. The EP workspace computing device 104 can apply one or more algorithms to determine the corresponding portion 314 of the 3D image 312. The EP workspace computing device 104 can identify the corresponding portion 314 of the 3D image 312 by highlighting the portion with a different (e.g., and configurable) color. Thus, the electrophysiologist can easily see the area identified (e.g., targeted) by the radiation oncologist operating the RO workspace computing device 106.

[0059] Additionally, in some examples, the EP workspace computing device 104 and the RO workspace computing device 106 can provide audio and / or video communication between the electrophysiologist and the radiation oncologist. For example, and referring to Figure 3 The EP workspace 302 can include a communication window 320 that displays a video of the radiation oncologist 321 operating the RO workspace computing device 106. Audio received from the RO workspace computing device 106 can be provided through one or more speakers of the EP workspace computing device 104.

[0060] Similarly, and referring to Figure 4The RO workspace computing device 106 can include a communication window 420 that displays video of the electrophysiologist 421 operating the EP workspace computing device 104. Audio received from the EP workspace computing device 104 can be provided through one or more speakers of the RO workspace computing device 106. In some examples, the communication windows 320 and 420 can provide messaging (e.g., chat) capabilities in which the radiation oncologist 321 and the electrophysiologist 421 can exchange messages.

[0061] In some examples, the communication windows 320 and 420 allow for sharing (e.g., transmitting and receiving) annotations, status (e.g., volume status, approval status, treatment plan status (e.g., completed, in progress, etc.)), or any other relevant information. Additionally, in some examples, the EP workspace computing device 104 and / or the RO workspace computing device 106 can store any such information in the database 116.

[0062] While various examples are illustrated in which data is generated and transmitted from one of the EP workspace computing device 104 and the RO workspace computing device 106 to the other to cause the recipient of the data to take action, one of ordinary skill in the art having the benefit of these disclosures will recognize other examples. For example, the EP workspace computing device 104 can generate EP adjustment data 105 that identifies and characterizes any action taken with respect to the EP workspace 302, and the RO workspace computing device 106 can take any suitable action in response to receiving the EP adjustment data 105. Similarly, the RO workspace computing device 106 can generate RO adjustment data 107 that identifies and characterizes any action taken with respect to the RO workspace 402, and the EP workspace computing device 104 can take any suitable action in response to receiving the RP adjustment data 107.

[0063] Figure 5A The method 500 illustrates a parallel display of the generated structure and dose volume mesh, and Figure 5B The method 500 illustrates a parallel display of the generated structure and dose volume mesh, and

[0064] From step 502, input data is received. For example, the input data can include a CT image volume, radiotherapy (RT) structure contours of an organ substructure (in this example, a cardiac substructure), and dose matrix data identifying a corresponding RT dose matrix (e.g., as a 3D grid of voxels) for a given treatment plan. In some examples, at least a portion of the input data is obtained from the database 116. In some examples, the CT image volume is received from the imaging device 102. In some examples, the dose matrix data is received from the RO computing device 106. For example, a radiation oncologist can determine a dose prescription (e.g., a number of doses and organ locations for the doses) for a treatment plan. The radiation oncologist can provide the dose prescription to the RO computing device 106 (e.g., through the user interface 205). A physicist or dosimetrist can develop a treatment plan to satisfy (e.g., based on) the dose prescription (e.g., through the RO computing device 106 or the shared EP and RO workspace computing device 108). The treatment plan can include generating a plan image. For example, each of the dose prescription, the treatment plan, and the plan image can be stored in the database 116. The RO computing device 106 can generate a dose matrix based on the developed treatment plan and / or the plan image. For example, the RO computing device 106 can execute one or more dose matrix algorithms known in the art to generate dose matrix data identifying and characterizing the dose matrix. The RO computing device 106 can store the dose matrix data in the database 116.

[0065] In step 504, the cardiac substructure 3D mesh 554 is generated. The cardiac substructure 3D mesh 554 can be generated, for example, by generating a voxelized volume of the cardiac substructure and then determining (e.g., computing) the substructure surface mesh 552 based on the voxelized volume of the cardiac substructure. For example, the shared EP and RO workspace computing device 108 can execute an image-based meshing algorithm that operates on the voxelized volume of the cardiac substructure to determine the substructure surface mesh 552. For example, the image-based meshing algorithm can be a marching cubes algorithm, a marching tetrahedra algorithm, or a neighbor cell algorithm.

[0066] Continuing with step 506, a threshold is applied to each RT dose matrix (as identified in the received dose matrix data) to generate an isodose volume 558. The threshold is a value based on a desired isodose display (e.g., selectable by an electrophysiologist provided on a configuration menu). For example, the isodose volume 558 can include regions where the dose is above the threshold. Then, an isodose 3D surface mesh 556 is generated based on the isodose volume 558. For example, the shared EP and RO workspace computing device 108 can execute an image-based meshing algorithm that operates on the isodose volume 558 to generate the isodose 3D surface mesh 556. In some examples, multiple isodose 3D surface meshes 556 are generated, each based on a corresponding threshold. For example, one isodose 3D surface mesh 556 can be generated based on a 10 gray (Gy) threshold, and another isodose 3D surface mesh 556 can be generated based on a 25 Gy threshold.

[0067] In step 508, the generated 3D meshes (including the cardiac substructure 3D mesh 554 and the isodose 3D surface mesh 556) are displayed (e.g., together) as one image. For example, the cardiac substructure 3D mesh 554 and the isodose 3D surface mesh 556 can be displayed within a 3D viewer or workspace. The isodose 3D surface mesh 556 is displayed such that it appears within the corresponding portion of the cardiac substructure 3D mesh 554. For example, the isodose 3D surface mesh 556 can overlay the corresponding portion of the cardiac substructure 3D mesh 554 that will receive a dose. In some examples, the shared EP and RO workspace computing device 108 allows the output image 560 to be moved and / or rotated through the EP workspace. In some examples, an electrophysiologist can be able to remotely control the position and orientation of a camera of the imaging device 102 from the shared EP and RO workspace computing device 108 to provide image data 103 from different angles.

[0068] Figure 6A A 3D RT dose matrix 602 of a heart ventricle 604 is illustrated. Sample points 606 are determined along a line 607 that is perpendicular to a tangent 609 of a region of the 3D RT dose matrix 602 defined along a contour of the organ structure. For example, the shared EP and RO workspace computing device 108 can select a sample point 606 along each of a plurality of lines 607 that are tangent to a region of the 3D RT dose matrix 602 defined along a contour of the organ structure. The number of sample points 606 and the distance between sample points 606 can be configured by a user, such as an electrophysiologist operating the shared EP and RO workspace computing device 108.

[0069] Each sample point 606 has a corresponding value 608. For example, the value 608 can indicate a number of doses at a location of the 3D RT dose matrix 602 corresponding to each sample point 606. The shared EP and RO workspace computing device 108 can execute an aggregation function 610 to determine a representative value 612 based on the corresponding values 608 of the sample points 606. For example, the representative value 612 can be an average of the values 608, a maximum of the values 608, or a minimum of the values 608. In some examples, the shared EP and RO workspace computing device 108 executes any suitable aggregation function 610 that determines the representative value 612 based on the values 608.

[0070] Based on a color map that associates colors with the representative values 612, the shared EP and RO workspace computing device 108 can determine surface colors 616 of a substructure, such as the ventricle 604. For example, the shared EP and RO workspace computing device 108 can generate a mesh based on the output image 560 that includes various colors on its surface, such as illustrated by the substructure surface 620.

[0071] Figure 6B A 3D image 650 of a substructure with surface colors is illustrated. For example, the shared EP and RO workspace computing device 108 can have determined and generated the surface colors as described herein, such as with respect to Figure 6A In this example, the 3D image 650 is a ventricle 652, and more specifically, a 3D image of a ventricular tachycardia circuit of a portion of the ventricle 652. The various colors on the various surfaces can indicate various levels of dose on those surfaces. For example, as illustrated, the ventricle 652 includes a first epicardial surface 660, a second epicardial surface 668, a myocardial surface 662, and an endocardial surface 664. Each of the first epicardial surface 660, the second epicardial surface 668, the myocardial surface 662, and the endocardial surface 664 display colors based on dose along those respective surfaces. Thus, each segment of the ventricle 652 (e.g., epicardial, myocardial, and endocardial segments) is projected to an inner or outer surface such that each point on the surface indicates the dose received at that particular location. Thus, the dose information is provided to an electrophysiologist in a manner that facilitates understanding and appreciation of the various surfaces of the structure that received the dose and the relative amount of the dose.

[0072] Figure 7 An example is illustrated in which the determined surface dose values representing the dose of the sample points along the surface of the myocardium are projected onto a 17-segment model of the ventricle, allowing the dose to be displayed on a 2D map of the ventricle.

[0073] In this example, the colored substructure model 702 is mapped to the 3D surface mesh 704 so that the 3D surface mesh 704 is displayed with the corresponding colors. The colors of the surface of the colored substructure model 702 can be determined as described herein (such as with respect to the substructure surface 620, for example) In some examples, the dose values representative of the dose are projected to the endocardial wall (i.e., the inner layer of the myocardium), rather than the epicardial wall (i.e., the outer layer of the myocardium), for example. Figure 6A

[0074] The shared EP and RO workspace computing device 108 can also identify portions of the 3D surface mesh 704 that correspond to the 17-segment model (such as the 17-segment model 710). Based on the identified portions of the 3D surface mesh 704 and the colors of the various portions of the colored substructure model 702, the shared EP and RO workspace computing device 108 can generate a colored 17-segment display.

[0075] For example, for each segment of the 17-segment display 720 (e.g., before displaying it with a color), the shared EP and RO workspace computing device 108 can determine the corresponding portion in the 3D surface mesh 704. The shared EP and RO workspace computing device 108 can then identify the segment number of the portion in the 3D surface mesh 704 and, based on the segment number, determine the color (e.g., value) of the corresponding portion of the colored substructure model 702. The shared EP and RO workspace computing device 108 then associates the segment of the 17-segment display 720 with the color that is the same as the color of the corresponding portion of the colored substructure model 702. In some examples, the shared EP and RO workspace computing device 108 generates (e.g., computes) segment-specific dose volume histograms (DVHs) and stores them in a database (such as the database 116).

[0076] Referring to Figure 6A , Figure 6B and Figure 7 , although various colors are used to generate images that indicate dose levels, other ways of providing (e.g., displaying) dose information are also contemplated. For example, in addition to using colors, other dose level identifiers can be used, such as washover coverage, translucent coverage, shading, hashing, or any other suitable technique. The dose information can help an electrophysiologist, for example, assess whether a planned ablation volume meets expectations for treatment. The dose information can help an electrophysiologist, for example, identify whether a computed treatment plan will result in the expected ablation location and / or volume of appropriate dose coverage.

[0077] Figure 8A ​is a flowchart of an example method 800, e.g., that can be performed by the RO workspace computing device 106. Beginning with step 802, a first signal is received. The first signal identifies a first event within an electrophysiologist workspace. For example, the RO workspace computing device 106 can receive the EP adjustment data 105 from the EP workspace computing device 104 identifying and characterizing a selection of one or more segments of a segment model, such as a 17-segment model, for a ventricle. In step 804, a first action is determined to be applied to a first image displayed within the RO workspace based on the first signal. For example, the RO workspace 402 can display a first 3D image of a heart of a patient. For example, the first action can be to determine one or more portions of the heart corresponding to the selected region.

[0078] In step 806, a second image is generated based on applying the first action to the first image within the RO workspace. For example, the RO workspace computing device 106 can generate a second 3D image of the heart of the patient with the determined portions identified (e.g., highlighted, outlined, colored, etc.). The RO workspace computing device 106 can display the second 3D image within the RO workspace 402. In step 808, the second image is displayed within the RO workspace. In some examples, the RO workspace computing device 106 generates a cardiac radiofrequency ablation treatment plan based on the second image. In some examples, the RO workspace computing device 106 transmits the cardiac radiofrequency ablation treatment plan to a radiation therapy delivery system to deliver a dose to the patient. The method then ends.

[0079] Figure 8B is a flowchart of an example method 850, e.g., that can be performed by the EP workspace computing device 104. Beginning with step 852, a first signal is received. The first signal identifies a first event within a radiation oncologist workspace. For example, the EP workspace computing device 104 can receive the RO adjustment data 107 from the RO workspace computing device 106 identifying and characterizing a change in a dose applied to a ventricle. In step 854, a first action is determined to be applied to a first image displayed within the EP workspace based on the first signal. For example, the EP workspace 302 can display a first 3D image of a ventricle. For example, the first action can be to determine a portion of the ventricle to which the changed dose is to be applied.

[0080] In step 856, a second image is generated based on applying the first action to the first image within the EP workspace. For example, the EP workspace computing device 104 can generate a second 3D image of the ventricle in one color, but the dose to portions of the ventricle is a different color. The EP workspace computing device 104 can display the second 3D image within the EP workspace 302. In step 858, the second image is displayed within the EP workspace. In some examples, the EP workspace computing device 104 generates a cardiac radiofrequency ablation treatment plan based on the second image. In some examples, the EP workspace computing device 104 transmits the cardiac radiofrequency ablation treatment plan to a radiation therapy delivery system to deliver the dose to the patient. The method then ends.

[0081] Figure 9 is a flowchart of an example method 900, for example, that can be performed by the shared EP and RO workspace computing device 108. Beginning with step 902, a first signal is received that identifies an image volume of an organ. For example, the shared EP and RO workspace computing device 108 can receive image data 103 from the imaging device 102 that identifies and characterizes a CT image volume. In step 904, a second signal is received. The second signal identifies dose matrix data for applying a dose to the organ. For example, the shared EP and RO workspace computing device 108 can receive dose matrix data from the RO computing device 106.

[0082] Continuing with step 906, a first three-dimensional mesh of the organ is generated based on the first signal. For example, the shared EP and RO workspace computing device 108 can execute one or more algorithms that operate on at least a portion of the received image volume to generate the first three-dimensional mesh of the organ. In some examples, the shared EP and RO workspace computing device 108 computes the first three-dimensional mesh by executing a marching cubes algorithm. In step 908, a second three-dimensional mesh of a dose volume of the dose is generated based on the second signal. For example, the shared EP and RO workspace computing device 108 can execute one or more algorithms that operate on at least a portion of the received dose matrix data to generate the second three-dimensional mesh of the dose volume. In some examples, the shared EP and RO workspace computing device 108 computes the second three-dimensional mesh by first generating a voxelized volume of a cardiac substructure and then executing a marching cubes algorithm.

[0083] In step 910, the second three-dimensional mesh of dose volumes is superimposed on the first three-dimensional mesh of the organ to generate a third three-dimensional mesh. In step 912, the third three-dimensional mesh is displayed. For example, the shared EP and RO workspace computing device 108 can display the three-dimensional mesh to an electrophysiologist in a 3D viewer, the three-dimensional mesh including the second three-dimensional mesh of dose volumes superimposed on the first three-dimensional mesh of the organ. In some examples, the shared EP and RO workspace computing device 108 generates a cardiac radiofrequency ablation treatment plan based on the three-dimensional mesh. In some examples, the shared EP and RO workspace computing device 108 transmits the cardiac radiofrequency ablation treatment plan to a radiation therapy delivery system to deliver the dose to the patient. The method then ends.

[0084] Figure 10 is a flowchart of an example method 1000, for example, that can be performed by the radiofrequency ablation diagnosis and treatment planning computing device 200. Beginning with step 1002, the computing device 200 displays a model of an organ. In step 1004, the computing device 200 receives a first signal identifying an adjustment to a first parameter of the model of the organ. Proceeding to step 1006, the computing device 200 adjusts the model of the organ based on the first signal. For example, the computing device 200 can adjust the first parameter according to the first signal, and can regenerate the model of the organ based on the adjusted first parameter. In step 1008, the computing device displays the adjusted model of the organ. For example, the computing device 200 can display a three-dimensional model of the organ. The method then ends.

[0085] In some examples, the computer-implemented method includes receiving substructure data identifying a substructure contour of an organ and dose matrix data. For example, the dose matrix data can identify a dose of the organ. The method further includes generating a first mesh of an organ substructure for the organ based on the substructure data. The method further includes generating a second mesh of isodose volumes based on the dose matrix data. Further, the method includes displaying the first mesh of the organ substructure and the second mesh of isodose volumes within the same scene.

[0086] In some examples, the method includes generating a voxelized volume of the substructure contour and executing an image based on a meshing algorithm operating on the voxelized volume of the substructure contour.

[0087] In some examples, the method includes obtaining a dose threshold and filtering the dose matrix data based on the dose threshold. In some examples, the method includes executing a marching cubes algorithm operating on the filtered dose matrix data.

[0088] In some examples, the method includes associating a plurality of dose value ranges with a unique identifier, and determining the unique identifier for each surface point of the plurality of surface points of the second mesh based on the plurality of dose value ranges. In some examples, the unique identifier is a color.

[0089] In some examples, the method includes determining each dose value of the plurality of dose values along a tangent line of each surface point of the plurality of surface points. The method further includes determining a representative dose value for each surface point of the plurality of surface points based on the corresponding plurality of dose values. The method further includes determining a unique identifier for each surface point of the plurality of surface points based on the corresponding representative dose value.

[0090] In some examples, the method includes mapping the unique identifier for each surface point of the plurality of surface points to the segmentation model. The method further includes generating an image of the segmentation model based on the mapped unique identifier. The method further includes displaying the image of the segmentation model.

[0091] In some examples, the method includes applying a color wash to the segmentation model based on the mapped unique identifier.

[0092] 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 including receiving substructure data and dose matrix data, the substructure data identifying a substructure contour of an organ. The operations further include generating a first mesh of an organ substructure for the organ based on the substructure data. Further, the operations include generating a second mesh of an isodose volume based on the dose matrix data. The operations further include displaying the first mesh of the organ substructure and the second mesh of the isodose volume within the same scene.

[0093] In some examples, the operations include generating a voxelized volume of the substructure contour, and executing an image based on a meshing algorithm operating on the voxelized volume of the substructure contour.

[0094] In some examples, the operations include obtaining a dose threshold, and filtering the dose matrix data based on the dose threshold. In some examples, generating the second mesh of the isodose volume includes executing a marching cubes algorithm operating on the filtered dose matrix data.

[0095] In some examples, the operations include associating a plurality of dose value ranges with a unique identifier, and determining the unique identifier for each surface point of the plurality of surface points of the second mesh based on the plurality of dose value ranges. In some examples, the unique identifier is a color.

[0096] In some examples, the operations include determining each dose value of a plurality of dose values along a tangent line of each surface point of the plurality of surface points. The operations further include determining a representative dose value for each surface point of the plurality of surface points based on the corresponding plurality of dose values. The operations further include determining a unique identifier for each surface point of the plurality of surface points based on the corresponding representative dose values.

[0097] In some examples, the operations include mapping the unique identifier for each surface point of the plurality of surface points to the segmentation model. The operations further include generating an image of the segmentation model based on the mapped unique identifiers. The operations further include displaying the image of the segmentation model.

[0098] In some examples, the operations include applying a washout to the segmentation model based on the mapped unique identifiers.

[0099] In some examples, a system includes a computing device configured to receive substructure data identifying a substructure contour of an organ and dose matrix data. The computing device is further configured to generate a first mesh of an organ substructure for the organ based on the substructure data. Further, the computing device is configured to generate a second mesh of an isodose volume based on the dose matrix data. The computing device is further configured to display the first mesh of the organ substructure and the second mesh of the isodose volume within a same scene of a 3D viewer or workspace.

[0100] In some examples, the computing device is configured to generate a voxelized volume of the substructure contour and execute an image-based meshing algorithm that operates on the voxelized volume of the substructure contour.

[0101] In some examples, the computing device is configured to obtain a dose threshold and filter the dose matrix data based on the dose threshold. In some examples, the computing device is configured to execute a marching cubes algorithm that operates on the filtered dose matrix data.

[0102] In some examples, the computing device is configured to associate a plurality of dose value ranges with the unique identifier and determine the unique identifier for each surface point of the plurality of surface points of the second mesh based on the plurality of dose value ranges. In some examples, the unique identifier is a color.

[0103] In some examples, the computing device is configured to determine each dose value of a plurality of dose values along a tangent line of each surface point of the plurality of surface points. The computing device is further configured to determine a representative dose value for each surface point of the plurality of surface points based on the corresponding plurality of dose values. The computing device is further configured to determine a unique identifier for each surface point of the plurality of surface points based on the corresponding representative dose values.

[0104] In some examples, the computing device is configured to map a unique identifier of each surface point of the plurality of surface points to the segmentation model. The computing device is further configured to generate an image of the segmentation model based on the mapped unique identifiers. The computing device is further configured to display the image of the segmentation model.

[0105] In some examples, the computing device is configured to apply a washout to the segmentation model based on the mapped unique identifiers.

[0106] In some examples, the method includes means for receiving substructure data identifying a substructure contour of an organ and dose matrix data. The method further includes means for generating a first mesh of an organ substructure for the organ based on the substructure data. The method further includes means for generating a second mesh of an isodose volume based on the dose matrix data. Further, the method includes means for displaying the first mesh of the organ substructure and the second mesh of the isodose volume within a same scene of a 3D viewer or workspace.

[0107] In some examples, the method includes means for generating a voxelized volume of the substructure contour and means for executing a marching cubes algorithm operating on the voxelized volume of the substructure contour.

[0108] In some examples, the method includes means for obtaining a dose threshold and filtering the dose matrix data based on the dose threshold. In some examples, the method includes means for executing a marching cubes algorithm operating on the filtered dose matrix data.

[0109] In some examples, the method includes means for associating a plurality of dose value ranges with a unique identifier and determining the unique identifier of each surface point of the plurality of surface points of the second mesh based on the plurality of dose value ranges. In some examples, the unique identifier is a color.

[0110] In some examples, the method includes means for determining each dose value of the plurality of dose values along a tangent line of each surface point of the plurality of surface points. The method further includes means for determining a representative dose value of each surface point of the plurality of surface points based on the corresponding plurality of dose values. The method further includes means for determining a unique identifier of each surface point of the plurality of surface points based on the corresponding representative dose values.

[0111] In some examples, the method includes means for mapping a unique identifier of each surface point of the plurality of surface points to the segmentation model. The method further includes generating an image of the segmentation model based on the mapped unique identifiers. The method further includes means for displaying the image of the segmentation model.

[0112] In some examples, the method includes means for applying a wash color to the segmentation model based on the mapped unique identifier.

[0113] While the above method is described with reference to the illustrated flow diagrams, it will be appreciated that many other ways of executing the actions associated with the method can be used. For example, the order of some operations can be changed and some operations described can be optional.

[0114] Additionally, the methods and systems described herein can be implemented at least in part in the form of computer-implemented processes and apparatuses for practicing those processes. The disclosed methods can also be implemented at least in part in the form of tangible, non-transitory computer-readable storage media encoded with computer program code. For example, the steps of the methods can be embodied in hardware, executable instructions (e.g., software) executed by a processor, or a combination of both. For example, the media can include RAM, ROM, CD-ROM, DVD-ROM, BD-ROM, hard disk drives, flash memory, or any other non-transitory machine-readable storage media known in the art. When the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the methods. The methods can also be embodied in the form of a computer becoming a special purpose computer when the computer program code is loaded into and executed by the computer, such that the computer becomes a special purpose computer for practicing the methods. When implemented on a general-purpose processor, the computer program code segments configure the processor to create specific logic circuits. The methods can alternatively be embodied in a special-purpose integrated circuit for performing the methods.

[0115] The foregoing is provided for purposes of explaining and describing the embodiments of the present disclosure. Modifications and adaptations to these embodiments will be apparent to those skilled in the art and can be made without departing from the scope or spirit of the disclosure.

Claims

1. A computer-implemented method comprising: receiving substructure data and dose matrix data, wherein the substructure data identifies a substructure outline of an organ; generating a first mesh of an organ substructure for the organ based on the substructure data; generating a second grid of isodose volumes based on the dose matrix data, comprising: associating a plurality of dose value ranges with a unique identifier, and determining the unique identifier for each of a plurality of surface points of the second grid based on the plurality of dose value ranges; as well as The first grid of the organ substructure and the second grid of the isodose volume are displayed within the same scene.

2. The computer-implemented method of claim 1 , wherein generating the first mesh of the organ substructure comprises: generating a voxelized volume of the substructure outline; as well as An image-based gridding algorithm is executed, the image-based gridding algorithm operating on the voxelized volume of the substructure outline.

3. The computer-implemented method of claim 1 , wherein generating the second grid of the isodose volume further comprises: Obtaining dose thresholds; as well as Based on the dose threshold, the dose matrix data is filtered.

4. The computer-implemented method of claim 3 , wherein generating the second grid of the isodose volume further comprises: An image-based gridding algorithm is executed, the image-based gridding algorithm operating on the filtered dose matrix data. The computer-implemented method of claim 1 , wherein the organ is a heart.

6. The computer-implemented method of claim 1 , wherein determining the unique identifier for each surface point in the plurality of surface points of the second grid comprises: determining each of a plurality of dose values ​​along a tangent line to each of the plurality of surface points; determining a representative dose value for each of the plurality of surface points based on the corresponding plurality of dose values; as well as The unique identifier is determined for each surface point of the plurality of surface points based on the corresponding representative dose value.

7. The computer-implemented method of claim 6 , further comprising: mapping the unique identifier for each surface point in the plurality of surface points to a segmentation model; generating an image of the segmentation model based on the mapped unique identifier; as well as The image of the segmentation model is displayed.

8. The computer-implemented method of claim 7, wherein generating the image of the segmentation model comprises: Color washing is applied to the segmentation model based on the mapped unique identifier.

9. The computer-implemented method of claim 1, wherein the unique identifier is a color.

10. 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 substructure data and dose matrix data, wherein the substructure data identifies a substructure outline for an organ; generating a first mesh of an organ substructure for the organ based on the substructure data; generating a second grid of isodose volumes based on the dose matrix data, comprising: associating a plurality of dose value ranges with a unique identifier, and determining the unique identifier for each of a plurality of surface points of the second grid based on the plurality of dose value ranges; as well as The first grid of the organ substructure and the second grid of the isodose volume are displayed within the same scene.

11. The non-transitory computer-readable medium of claim 10, wherein generating the first mesh of the organ substructure comprises: generating a voxelized volume of the substructure outline; as well as An image-based gridding algorithm is executed, the image-based gridding algorithm operating on the voxelized volume of the substructure outline.

12. The non-transitory computer-readable medium of claim 10, wherein determining the unique identifier for each surface point of the plurality of surface points of the second grid comprises: determining each of a plurality of dose values ​​along a tangent line to each of the plurality of surface points; determining a representative dose value for each of the plurality of surface points based on the corresponding plurality of dose values; as well as The unique identifier is determined for each surface point of the plurality of surface points based on the corresponding representative dose value.

13. The non-transitory computer-readable medium of claim 12, wherein the operations further comprise: mapping the unique identifier for each surface point in the plurality of surface points to a segmentation model; generating an image of the segmentation model based on the mapped unique identifier; as well as The image of the segmentation model is displayed.

14. A system comprising: A computing device configured to: receiving substructure data and dose matrix data, wherein the substructure data identifies a substructure outline for an organ; generating a first mesh of an organ substructure for the organ based on the substructure data; generating a second grid of isodose volumes based on the dose matrix data, comprising: associating a plurality of dose value ranges with a unique identifier, and determining the unique identifier for each of a plurality of surface points of the second grid based on the plurality of dose value ranges; as well as The first grid of the organ substructure and the second grid of the isodose volume are displayed within the same scene.

15. The system of claim 14, wherein generating the first mesh of the organ substructure comprises: generating a voxelized volume of the substructure outline; as well as An image-based gridding algorithm is executed, the image-based gridding algorithm operating on the voxelized volume of the substructure outline.

16. The system of claim 14, wherein determining the unique identifier for each surface point in the plurality of surface points of the second grid comprises: determining each of a plurality of dose values ​​along a tangent line to each of the plurality of surface points; determining a representative dose value for each of the plurality of surface points based on the corresponding plurality of dose values; as well as The unique identifier is determined for each surface point of the plurality of surface points based on the corresponding representative dose value.

17. The system of claim 16, wherein the computing device is configured to: mapping the unique identifier for each surface point in the plurality of surface points to a segmentation model; generating an image of the segmentation model based on the mapped unique identifier; and The image of the segmentation model is displayed.

Images