Methods and apparatus for radiation resection therapy

Abstract

Systems and methods for radioablation treatment planning are disclosed. In some examples, a computing device provides a user interface for display that allows a medical professional to define a treatment target region for a patient. The user interface may allow the medical professional to select the treatment region using an interactive target map generated for the patient. The computing device also receives image data from a patient imaging system, such as image data identifying a 3D volume of a scanned structure of the patient. The computing device may generate a 3D image of the scanned structure for display based on the received image data, and may overlay the 3D image with a target region map that the medical professional can manipulate to define a treatment target region for the patient. The computing device may transmit the defined target region to a treatment system for treating the patient.

Description

Technical Field

[0001] Aspects of the present disclosure generally relate to medical diagnostic and treatment systems, and more particularly to providing a radiation ablation diagnostic, treatment planning, and delivery system for the diagnosis and treatment of conditions such as cardiac arrhythmias.

Background Art

[0002] A variety of techniques can be used to read or image a patient's metabolic, electrical, and anatomical information. For example, positron emission tomography (PET) is a metabolic imaging technique that generates tomographic images representing the distribution of positron-emitting isotopes in the body. CT (computed tomography) and MRI (magnetic resonance imaging) are anatomical imaging techniques that create images using X-rays and magnetic fields, respectively. Images from these exemplary techniques can be combined with each other to generate composite anatomical and functional images. For example, software systems such as Varian Medical Systems Inc.'s Velocity® software use an image fusion process to combine different types of images, deform and / or register the images, and generate a combined image.

[0003] In cardiac radioresection, medical professionals collaborate to diagnose cardiac arrhythmias, identify the resection area, prescribe radiation therapy, and develop a radioresection treatment plan. Typically, various medical professionals receive complementary medical training and therefore specialize in different aspects of treatment development. For example, an electrophysiologist can identify one or more areas or targets of the patient's heart for the treatment of cardiac arrhythmias based on the patient's anatomy and electrophysiology. For instance, an electrophysiologist may use combined PET and cardiac CT images as input to manually define the target area for resection. Once the target area is defined by the electrophysiologist, a radiation oncologist can prescribe radiation therapy, including, for example, the number of fractions of radiation to be delivered, the radiation dose delivered to the target area, and the maximum dose to adjacent organs at risk. Once the radiation dose is prescribed, a dosimeter can typically create a radioresection treatment plan based on the prescribed radiation therapy. It is then common for the radiation oncologist to review and approve the treatment plan. Furthermore, before finalizing the radiosurgery treatment plan, electrophysiologists may want to understand the location, size, and shape of the dose area of ​​the defined target volume in order to confirm that the patient's target location defined by the radiosurgery treatment plan is correct. [Overview of the project] [Problems that the invention aims to solve]

[0004] To create and optimize treatment plans, it is essential to appropriately identify and define the target regions of the patient's organs for treatment. For example, an overly comprehensive target region may result in a defined target volume that includes areas that do not require treatment, while an underly comprehensive target region may result in a defined target volume that does not include areas that should be treated. Therefore, there is a need to improve the radiotherapy planning systems used by medical professionals, such as the cardiac radiotherapy system used for cardiac radioresection diagnosis and radiotherapy planning. [Means for solving the problem]

[0005] This invention discloses systems and methods for the diagnosis, treatment, and planning of cardiac radioresection. In some examples, a computing device is provided to display a user interface that enables a medical professional to define a target area of ​​a patient for treatment. The user interface may enable the medical professional to select a treatment area using an interactive target map generated for the patient. The computing device also receives image data, such as image data from an imaging system for the patient that identifies the 3D volume of the patient's scanned structures. Based on the received image data, the computing device may generate a 3D image of the scanned structures for display and overlay a target area map onto the 3D image that the medical professional can manipulate to define the target area of ​​treatment for the patient. Once defined, the computing device can transmit the defined target area to a treatment system for treating the patient.

[0006] In some examples, the system includes a computing device configured to receive a first input that identifies a therapeutic target region of a patient's organ and to receive a scan image of the organ. The computing device is further configured to generate a first digital model of the organ type. Furthermore, the computing device is configured to determine the alignment of the scan image with respect to the first digital model. Furthermore, the computing device is configured to generate a second digital model that includes at least a portion of the scan image and the first digital model. The computing device is further configured to store the second digital model in a data repository.

[0007] In some examples, a method performed by a computer includes receiving a first input that identifies a patient's organ, receiving a scan image of the organ, generating a first digital model of the type of organ, determining the alignment of the scan image to the first digital model, generating a second digital model that includes at least a portion of the scan image and the first digital model, and storing the second digital model in a data repository.

[0008] In some examples, a non-temporary computer-readable medium for storing instructions, the instructions, when executed by at least one processor, causes the at least one processor to perform a process that includes receiving a first input identifying a patient's organ and receiving a scan image of the organ. The process further includes generating a first digital model of the type of organ. The process further includes determining the alignment of the scan image with respect to the first digital model. The process further includes generating a second digital model that includes at least a portion of the scan image and the first digital model. The process further includes storing the second digital model in a data repository.

[0009] In some examples, the method includes means for receiving a first input that identifies a therapeutic target region of a patient's organ and for receiving a scan image of the organ. The method further includes means for generating a first digital model of the type of organ. The method further includes means for determining the alignment of the scan image with respect to the first digital model. The method further includes means for generating a second digital model that includes at least a portion of the scan image and the first digital model. The method further includes means for storing the second digital model in a data repository.

[0010] The features and advantages of this disclosure will be more fully disclosed or revealed in the following detailed description of exemplary embodiments. The detailed description of exemplary embodiments, where similar numbers indicate similar parts, will be considered together with the following accompanying drawings. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 shows several embodiments of cardiac radioresection diagnostic and treatment systems. [Figure 2] Figure 2 shows block diagrams of target definition computing devices according to several embodiments. [Figure 3] Figure 3 shows exemplary portions of the cardiac radioresection treatment system of Figure 1 in several embodiments. [Figure 4A] Figure 4A shows some examples of graphical user interfaces in several embodiments. [Figure 4B] Figure 4B shows some examples of graphical user interfaces in several embodiments. [Figure 4C] Figure 4C shows some examples of graphical user interfaces in several embodiments. [Figure 4D] Figure 4D shows some examples of graphical user interfaces in several embodiments. [Figure 4E] Figure 4E shows some examples of graphical user interfaces in several embodiments. [Figure 4F] Figure 4F shows some examples of graphical user interfaces in several embodiments. [Figure 5A] Figure 5A shows some examples of graphical user interfaces in several embodiments. [Figure 5B] Figure 5B shows some examples of graphical user interfaces in several embodiments. [Figure 6A] Figure 6A shows some examples of graphical user interfaces in several embodiments. [Figure 6B] Figure 6B shows a part of a graphical user interface according to some embodiments. [Figure 6C] Figure 6C shows a part of a graphical user interface according to some embodiments. [Figure 6D] Figure 6D shows a part of a graphical user interface according to some embodiments. [Figure 6E] Figure 6E shows a part of a graphical user interface according to some embodiments. [Figure 7A] Figure 7A shows a two-dimensional segment model according to some embodiments. [Figure 7B] Figure 7B shows a three-dimensional segment model according to some embodiments. [Figure 7C] Figure 7C shows a three-dimensional segment model with a septal margin according to some embodiments. [Figure 8] Figure 8 shows the editing options of the two-dimensional segment model of Figure 7A according to some embodiments. [Figure 9] Figure 9 illustrates the editing options of the three-dimensional segment model of Figure 7B according to some embodiments. [Figure 10] Figure 10A shows the selection of segments within a segment model according to some embodiments. Figure 10B shows a three-dimensional segment model identifying the selected segments according to some embodiments. [Figure 11] Figure 11 is a flowchart of an exemplary method for generating an examination for a patient according to some embodiments. [Figure 12] Figure 12 is a flowchart of an exemplary method for generating an interactive map for identifying a treatment target region according to some embodiments. [Figure 13A] Figure 13A is a flowchart of an exemplary method for generating a digital model according to some embodiments. [Figure 13B]FIG. 13B is a flowchart of an exemplary method for adjusting the orientation of the digital model of FIG. 13A according to some embodiments.

DETAILED DESCRIPTION OF THE INVENTION

[0012] The description of the preferred embodiments is intended to be read in connection with the accompanying drawings, which are considered to be a part of the entire written description of the present disclosure. The present disclosure is capable of various modifications and alternative forms, but specific embodiments are illustrated by the drawings and described in detail herein. The objects and advantages of the claimed subject matter will become more apparent from the following detailed description of these exemplary embodiments in connection with the accompanying drawings.

[0013] However, it should be understood that the present disclosure is not intended to be limited to the particular forms disclosed. Rather, the present disclosure is directed to all modifications, equivalents, and alternatives falling within the spirit and scope of these exemplary embodiments. Terms such as "coupled," "coupled to," "operatively coupled," "operatively connected," etc. are to be broadly understood as connecting devices or components together, whether mechanically, electrically, wired, wirelessly, or otherwise, such that the connected devices or components can operate (e.g., communicate) with each other as intended by their relationship.

[0014] Referring to the drawings, Figure 1 is a block diagram of a cardiac radioresection diagnostic and treatment system 100, which includes an imaging device 102, a treatment planning calculator 106, one or more target definition calculators 104, and a database 116 that is communicably connected via a communication network 118. The imaging device 102 may be, for example, a CT scanner, an MR scanner, a PET scanner, an electrophysiological imaging device, an ECG, or an ECG imaging device. In some examples, the imaging device 102 may be a PET / CT scanner or a PET / MR scanner. In some examples, the imaging device 102 and the treatment planning calculator 106 may be part of a radioresection treatment system 126 that enables radioresection treatment to be administered to a patient. For example, the radioresection treatment system 126 may enable the delivery of defined doses to one or more treatment areas of a patient.

[0015] Each target definition calculator 104 and treatment planning calculator 106 may be any suitable calculator including any suitable hardware or combination of hardware and software for processing data. For example, each may 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 circuits, or any other suitable circuits. Furthermore, each may transmit data to and receive data from the communication network 118. For example, each of the target definition calculator 104 and treatment planning calculator 106 may be a server such as a cloud-based server, a computer, a laptop, a mobile device, a workstation, or any other suitable calculator.

[0016] For example, Figure 2 shows a computing device 200, which can be an example of a target definition computing device 104 and a treatment planning computing device 106, respectively. The computing device 200 includes one or more processors 201, working memory 202, one or more input / output devices 203, instruction memory 207, 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 buses 208 enable communication between various devices. The data buses 208 may include wired or wireless communication channels.

[0017] The processor 201 may include one or more separate processors, each having one or more cores. Each of the separate processors may have the same or different architecture. The 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), and the like.

[0018] 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-transient computer-readable storage medium such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, removable disk, CD-ROM, any non-volatile memory, or any other suitable memory. The processor 201 may be configured to perform a particular function or operation by executing code that embodies the function or operation stored on the instruction memory 207. For example, the processor 201 may be configured to execute code stored on the instruction memory 207 to perform one or more of any functions, methods, or operations disclosed herein.

[0019] Furthermore, the processor 201 can store data in the working memory 202 and read data from the working memory 202. For example, the processor 201 can store a set of working instructions in 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 the operation of the radiosurgical resection diagnostic and treatment planning calculation device 200. The working memory 202 may be random access memory (RAM), such as static random access memory (SRAM) or dynamic random access memory (DRAM), or any other suitable memory.

[0020] The input / output device 203 may include any suitable device that enables data input or output. For example, the input / output device 203 may include one or more of the following: a keyboard, touchpad, mouse, stylus, touchscreen, physical buttons, speaker, microphone, or any other suitable input or output device.

[0021] The communication port 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, the communication port 209 enables programming of executable instructions in the instruction memory 207. In some examples, the communication port 209 enables the transfer of data, such as image data (e.g., uploading or downloading).

[0022] 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 user interaction with the computing device 200. For example, the user interface 205 may be a user interface for an application that enables a user (e.g., a medical professional) to view or manipulate a model to define a target area for patient treatment, as described herein. In some examples, the user can interact with the user interface 205 by utilizing the input / output device 203. In some examples, the display 206 may be a touchscreen, and the user interface 205 is displayed on that touchscreen. In some examples, the display 206 displays images of scanned image data (e.g., image slices).

[0023] The transceiver 204 enables communication with a network such as the communication network 118 in Figure 1. For example, if the communication network 118 in Figure 1 is a cellular network, the transceiver 204 is configured to enable communication with the cellular network. In some examples, the transceiver 204 is selected based on the type of communication network 118 on which the radiopharmaceutical resection diagnostic and treatment planning calculation device 200 will operate. The processor 201 can operate via the transceiver 204 to receive data from or transmit data to a network such as the communication network 118 in Figure 1.

[0024] Returning to Figure 1, the database 116 may be a remote storage device (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 may be a local storage device such as a hard drive, non-volatile memory, or a USB stick for one or more target definition calculators 104 and treatment planning calculators 106.

[0025] The communication network 118 may be a cellular network such as a WiFi® network or a 3GPP® network, a Bluetooth® network, a satellite network, a wireless local area network (LAN), a network utilizing radio frequency (RF) communication protocols, 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, for example, provide access to the Internet.

[0026] The imaging device 102 is operable to scan images such as images of a patient's organs and provide image data 103 (e.g., measurement data) identifying and characterizing the scanned images to the communication network 118. Alternatively, the imaging device 102 is operable to acquire electrical imaging such as cardiac ECG images. For example, the imaging device 102 may scan a patient's structure (e.g., an organ) and transmit image data 103 identifying one or more slices of the 3D volume of the scanned structure to one or more target definition calculators 104 and treatment planning calculators 106 via the communication network 118. In some examples, the imaging device 102 may store the image data 103 in a database 116, and one or more target definition calculators 104 and treatment planning calculators 106 may retrieve the image data 103 from the database 116.

[0027] In some examples, the target definition computer 104 can be configured to communicate with the treatment planning computer 106 via a communication network 118. In some examples, the target definition computer 104 and the treatment planning computer 106 communicate with each other via a database 116 (for example, by storing and retrieving data from the database 116). In some examples, one or more target definition computers 104 and one or more treatment planning computers 106 are part of a cloud-based network that enables resource sharing and communication between each device.

[0028] In some examples, an electrophysiologist (EP) operates the target definition calculator 104, as described herein, to define the target area for treatment of the patient. In some examples, the target definition calculator 104 generates target data that identifies the target area of ​​the patient and transmits this target data to the treatment planning calculator 106. A radiation oncologist can operate the treatment planning calculator 106 to provide the patient with treatment via the imaging device 102. In some examples, the target area is integrated into a radiation ablation treatment plan for treating the patient.

[0029] In some examples, one or more target definition calculators 104 are located in a first area 122 of the medical facility 120, and one or more target definition calculators 104 are located in a second area 124 of the medical facility 120. In this way, the cardiac radioresection diagnostic and treatment system 100 allows multiple EPs to cooperate in determining the target area. For example, one EP may operate the first target definition calculator 104 at the first medical facility 122, and a second EP may operate the second target definition calculator 102 at the second medical facility 124. The first and second target definition calculators 104 can communicate via a communication network 118, for example, by transmitting and receiving data related to (e.g., defining) the target area (e.g., a proposed target area). Each EP may adjust the target area by operating the corresponding target definition calculator 104, and the target area may be finalized when both EPs agree on the target area.

[0030] [Inspection generation] The target definition calculator 102 can run an application that generates a user interface (e.g., user interface 205) that may be displayed to medical professionals such as EPs. The run application can enable medical professionals to define a target area of ​​a patient for treatment. For example, the user interface can enable medical professionals to select an examination type (e.g., CT, ECG, MRI, etc.). The examination type may identify the type of imaging for the patient. For example, the examination type may identify the type of image taken for the patient.

[0031] Depending on the selection of the test type (e.g., via a dropdown menu), the running application automatically provides a selection of test categories for the selected test type through the user interface. A test category can identify a list of functions (or test localizations) for a particular test type. For example, assuming a medical professional selects "ECG" as the test type, the user interface may provide a selection of one or more test categories, such as "Electronic." As another example, for the test types "CT," "MR," "PET / SPECT," and "US," the test category "Structural" may be provided. Additional test categories may include "Metabolism" or any other appropriate test category. In some examples, only one test category may be available for a single test type (e.g., "Electronic" for the "ECG" test type), and in this way, the running application may automatically select a single test category for the selected test type.

[0032] Once an examination category is selected, the application being executed may allow the user to select an examination localization via the user interface. An examination localization can identify a common target area of ​​the patient's organ being treated, such as one or more segments of the heart. The examination localizations displayed for selection may be determined by the selected examination category and / or examination type. For example, assuming the examination type is "ECG" and the examination category is "Electrocautery," the application being executed may, via the user interface, provide a selection of one or more examination localizations, specifically including "VT exit site," "VT inlet site," and "VT inlet and exit site." As another example, also assuming the examination type is "CT" and the examination category is "Structural," the application being executed may, via the user interface, provide a selection of one or more examination localizations, including "Wound."

[0033] In some examples, once a healthcare professional selects the test type, test category, and test localization, the running application may provide an interactive model of an organ or part thereof for display, such as a 17-segment model representing the basal level, middle level, and apex of the ventricle of the heart. The interactive model may allow the healthcare professional to select one or more parts of the organ being treated. For example, assuming the interactive model is a 17-segment model of the ventricle of the heart, the interactive model may allow the healthcare professional to select one or more of the 17 segments (e.g., segments 1-17). The healthcare professional can select each segment by, for example, clicking on each segment (e.g., using input / output device 203). Once each segment is selected, in some examples, the running application may change the color of each segment or provide some other indication that a segment has been selected. In some examples, the color of each selected segment is determined by the selected test category. For example, the running application may display segments selected for the "Structural" test category in gray and segments selected for the "Electrical" test category in orange.

[0034] In some examples, the application being executed can display the names of the different parts of an organ. For instance, the executed application can display the name of one of the 17 segments in a 17-segment model when a medical professional drags the cursor over a segment.

[0035] In some examples, the user interface allows healthcare professionals to save records in a database such as database 116, where the records identify the selected test type, test category, test localization, and any selected portion (e.g., segment) of the interactive model. In some examples, the running application allows healthcare professionals to name the record, select the test date, and provide notes related to the record, all of which may be stored in the database as part of the record.

[0036] [Target Selection] The executed application may further enable medical professionals to identify target areas for treatment. For example, the executed application may display one or more examination category maps, each examination category map (e.g., “heatmap”) corresponding to an examination category. Each examination category map may identify one or more parts of the patient’s organs, such as a 17-segment model of the ventricles of the heart. Furthermore, each examination category map provides a display of previously identified characteristics of the patient (e.g., examination localization) corresponding to the examination category. For example, an “electrical map” may provide a display of one or more arrhythmia origins identified in “electrical” type examinations performed on the patient, while a “structural map” may provide a display of one or more scar locations identified in “structural” type examinations performed on the patient. Data identifying previous examinations on the patient may be stored, for example, in a database 116. The target definition calculator 104 can acquire data to generate examination category maps.

[0037] In some examples, each examination category map displays a numerical value corresponding to a selection for each of one or more parts of a patient's organs. For example, assuming a 17-segment model, the application being performed may display each segment in a specific color based on the number of times that segment has been selected as of clinical interest for that examination category. For example, for an "electrical map," segments that have never been selected (e.g., during previous examinations) may be displayed in white, segments selected up to a threshold amount (e.g., once) may be displayed in light orange, and segments selected more than a threshold amount may be displayed in dark orange.

[0038] Each inspection category map can display segments in different colors (e.g., different shades of color) based on the corresponding selection range. For example, for a "structure map," segments that have never been selected may be displayed in white, segments selected up to a threshold amount may be displayed in light gray, and segments selected above the threshold amount may be displayed in dark gray. In some examples, the executed application may also provide a bar graph showing the range and corresponding color for each inspection category map.

[0039] In some examples, the executed application may display each segment of the examination category map in a specific color based on the proportion of times that segment has been selected as a clinical interest. The target definition calculator 104 may retrieve patient data from the database 116 and determine the number of times each segment has been selected across all examination types for each examination category (e.g., electrical, structural, etc.). Based on the number of selections for each segment, the target definition calculator 104 may determine the total number of selections for each examination category. Furthermore, for each segment, the target definition calculator 104 may determine the proportion of times that segment has been selected for the examination category based on the number of examinations for that particular examination category and the total number of selections for the segment (e.g., (number of selections for segment / total number of examinations) * 100)).

[0040] For example, for the "Electrical Map," segments that have never been selected before may be displayed in white, segments where the selection rate for the "Electrical" inspection category reaches a threshold may be displayed in light orange, and segments where the selection rate for the "Electrical" inspection category exceeds the threshold may be displayed in dark orange. Similarly, for the "Structural Map," segments that have never been selected before may be displayed in white, segments where the selection rate for the "Structural" inspection category reaches a threshold may be displayed in light gray, and segments where the selection rate for the "Structural" inspection category exceeds the threshold may be displayed in dark gray. In some examples, the executed application may further provide a bar graph showing the percentage and corresponding color for each inspection category map.

[0041] The threshold amounts described herein may be configurable. For example, a medical professional may provide threshold amounts to the target definition calculator 104 through a user interface provided by the executed application, and the target definition calculator 104 may store the thresholds in the database 116.

[0042] In some examples, the target definition calculator 104 generates a probability map. In some examples, the probability map may be in the same format as the examination category map. For example, if the examination category map is a 17-segment model, the probability map may also be a 17-segment model. The probability map can show the probability of treatment for one or more parts of an organ based on those parts of the organ identified by one or more examination category maps. In one example, the target definition calculator 104 determines the number of selections offered to each part of the organ (e.g., a segment) regardless of the examination category (e.g., the total number of selections offered to a segment across all examination categories). For example, the probability map can combine two or more examination category maps to provide a representation of how many times one or more parts of an organ have been selected (e.g., as shown by the individual examination category maps). Based on the determined number of selections for each part, the application being executed displays the corresponding parts of the probability map in the corresponding color or uses another appropriate representation, such as corresponding hatching.

[0043] In some examples, the target definition calculator 104 determines the percentage of times each part is selected across all test categories. Based on the determined percentage for each part, the executed application displays the corresponding part of the probability map in the corresponding color or uses any other appropriate display.

[0044] In some examples, the target definition calculator 104 determines the average amount of each part selected across all test categories. For example, the target definition calculator 104 may determine the average amount of each part by determining the number of times a part was selected across all test categories and dividing by the number of test categories. Based on the determined average values ​​of each part, the executed application displays the corresponding parts of the probability map in corresponding colors, or uses any other appropriate display.

[0045] In some examples, the target definition calculator 104 assigns a weight (e.g., a multiplier) to each test category. For example, the target definition calculator 104 may determine the number of selections for a first part of the probability map as described above, and determine a first weighting value by multiplying the sum of the selections by a first value. Similarly, the target definition calculator 104 may determine the number of selections for a second part of the probability map as described above, and determine a second weighting value by multiplying the sum of the selections by a second value. The first value may be less than or greater than the second value. Based on the first and second weighting values, the target definition calculator 104 may display the corresponding parts of the probability map in corresponding colors, or use any other appropriate display.

[0046] In some examples, the target definition calculator 104 may weight each test category map equally, regardless of how many times a corresponding part of an organ is selected within the corresponding test category. For example, the target definition calculator 104 may display the test category map according to the proportion of times each part of an organ is selected within its test category, as described above. The target definition calculator 104 may determine the value of each part based on the percentage of its segment within each test category. Based on the determined value of each part, the executed application displays the corresponding part of the probability map in the corresponding color or uses any other appropriate display. In some examples, the target definition calculator 104 weights the proportion for each part (e.g., applies a multiplier) and determines a value based on the weighted proportion. The multiplier may be different for at least two segments. In some examples, the executed application allows a medical professional to construct the multiplier. The target definition calculator 104 may store the multipliers in the database 116.

[0047] In some examples, the executed application can generate a target definition model so that a medical professional can identify a target area for treatment (e.g., an ablation area). This target definition model may be a 17-segment model of the ventricle of the heart. In some examples, the medical professional can select one or more parts of the target definition model to identify the target area. In the 17-segment model example, the medical professional can select a segment by clicking on it (e.g., using input / output device 203). In some examples, the executed application may change the color of the selected segment or otherwise indicate the selected segment to the medical professional.

[0048] Furthermore, in some examples, the target definition calculator 104 may determine whether a selected portion is "unlikely" or unlikely to be selected based on the probability map and / or the corresponding test category map (e.g., the values ​​used to generate the test category map). For example, the target definition calculator 104 may apply one or more rules (e.g., algorithms) to the values ​​determined to generate the test category map in order to determine whether a selected portion is unlikely. Data identifying and characterizing the rules may be stored, for example, in the database 116. As an example, one rule may specify that a selected portion (e.g., a segment) corresponding to a proportion in the probability map below a threshold is "unlikely". As another example, another rule may specify that a selected portion corresponding to a number of selections shown in the probability map below a threshold is "unlikely". The rules are not limited to these examples, and any appropriate rules may be adopted.

[0049] In some cases, one or more trained machine learning models can be applied to patient data to determine whether a selected segment is likely to occur. For example, machine learning models, such as those based on neural networks or decision trees, may be trained on historical patient data to determine areas that are likely to be treated. The trained machine learning model can be applied to a particular patient's treatment history data (e.g., treatment data stored in database 116) and selected segments for that patient to classify the selected segments as likely or unlikely. The model may also be applied to a wide range of diagnostic data, such as medical images and electrodiagnostic tests (e.g., ECG, ECGI, old catheter maps, etc.).

[0050] The executed application generates a message (e.g., via a pop-up window) indicating the impossibility of a selected segment that is deemed "impossible." Medical professionals can review the warning and dismiss it by providing input through the user interface.

[0051] [Target Alignment] Based on the target definition model, the target definition computing device 104 can generate a three-dimensional (3D) model of the corresponding structure (e.g., an organ). For example, assuming the target definition model is a two-dimensional (2D) 17-segment model of the ventricle of the heart, the target definition computing device 104 can generate a 3D representation of the 17-segment model. The 3D model can identify the base, sinus, apex, and vertex regions of the ventricle of the heart. For example, the 3D representation of the 17-segment model may be based on the shape of the surface mesh of the left ventricular structure.

[0052] For example, Figure 7A shows a 2D cardiac model 700, which includes a 2D ventricular model 702 adjacent to a right ventricular model 704. As shown, the 2D ventricular model 702 includes 17 segments, each identified by a corresponding numerical value. Key 706 identifies the ventricular portion associated with each segment.

[0053] Figure 7B shows the 3D ventricular model 720, which is a 3D representation of the 2D ventricular model 702. The 3D ventricular model 720 identifies the base 724, mid-hole 726, apex 728, and apex 730 regions of the ventricle of the heart, each part containing structures along the long axis 722 of the 3D model 720.

[0054] Figure 7C shows a 3D cardiac model 750, which includes a 3D ventricular model 720 adjacent to the right ventricle model 760. The 3D ventricular model 720 includes a basal region 724 from the upper end of the central plane 754 to the upper end of the basal plane 752, a central region 726 from the upper end of the apical plane 756 to the upper end of the central plane 754, and an apical region 728 from the upper end of the apex 730 to the upper end of the apical plane 756. Furthermore, the 3D cardiac model 750 includes a septal contour 762 that defines the boundary between the right ventricle model 760 and the 3D ventricular model 720. Along the septal contour 762, the uppermost point 764 where the upper end of the basal plane 752 contacts the right ventricle 760 is illustrated.

[0055] The target definition calculation device 104 can generate model data that identifies and characterizes one or more of the 2D model 702, the 3D ventricular model 720, and the 3D cardiac model 750, and store that data in the database 116.

[0056] In some examples, a medical professional may provide input to the target definition calculator 104 (for example, via the input / output device 203) to adjust one of the 2D model 702, the 3D ventricular model 720, and the 3D cardiac model 750. The executed application can receive the input and adjust the corresponding model as described herein.

[0057] For example, Figure 8 shows a 2D cardiac model 700 having drag points 802 and 804. A medical professional can provide input to the target definition calculator 104 to adjust the position of the anterior interventricular groove 803 by adjusting the drag point 802. Similarly, a medical professional can provide input to the target definition calculator 104 to adjust the position of the posterior interventricular groove 805 by adjusting the drag point 804. The drag points 802 and 804 are configured to slide along the outer edge of the 2D model 702.

[0058] Medical professionals can make adjustments to 3D models such as 3D ventricle 720. For example, Figure 9 illustrates 3D ventricle model 720 with drag points 902, 904, 906, 908, and 910 that allow for adjustment. Medical professionals can adjust the position of the anterior interventricular groove 956 by adjusting drag point 906. Similarly, medical professionals can adjust the position of the posterior interventricular groove 954 by adjusting drag point 908. In this way, alignment with ventricles such as the right ventricle 760 becomes possible.

[0059] Medical professionals can also adjust the orientation of the 3D ventricular model 720 by adjusting the drag point 902. For example, if a medical professional drags the drag point 902 to the right, the 3D ventricular model 720 will "tilt" to the right (e.g., by a few degrees). Medical professionals can also adjust the length 980 by adjusting the drag point 902 along the long axis 722. For example, a medical professional can cause the 3D ventricular model 720 to elongate by dragging the drag point 902 upwards, and the 3D ventricular model 720 to shorten by dragging the drag point 902 downwards. In some examples, adjustments to the length 980 result in equal or nearly equal changes in lengths 980A, 980B, and 980C.

[0060] By dragging the drag point 904, the base region 724 can be extended (for example, by dragging the drag point 904 upwards) or shortened (for example, by dragging the drag point 904 downwards). For example, by dragging the drag point 904, the length 980A can be changed. Similarly, by dragging the drag point 910, the vertex region 730 can be extended or shortened, and its length 940 can be changed.

[0061] Figures 10A and 10B illustrate the generation of resection volume based on selected target segments. For example, Figure 10A shows a 2D segment model 1002A, which may be a target-defining model. Figure 10B shows the corresponding 3D segment model 1002B. The 2D segment model 1002A illustrates a left ventricle 1008 with a specific wall thickness 1006A (e.g., 10 mm) measured from the artificial inner surface 1010A. The inner surface surrounds the center point 1004A. Furthermore, Figure 10A shows a selected segment 1012A (e.g., segment 9 of a 17-segment model of the ventricle), which may have been selected by a medical professional.

[0062] The 3D segment model 1002B includes the left ventricle 1008B, which has a wall thickness 1006B measured from the artificial inner surface 1010B. The artificial inner surface 1010B surrounds the side line 1004B. The side line 1004B corresponds to the center point 1004A. Figure 10B also shows the resected volume 1012B, which corresponds to the selected segment 1012A.

[0063] Therefore, if a medical professional selects segment 1012A, the target definition calculator 104 can automatically generate the excision volume 1012B of the 3D segment model 1002B and display the 3D segment model 1002B.

[0064] Returning to Figure 1, the target definition calculator 104 can acquire patient image data 103. The image data 103 includes images of scanned structures of the patient. For example, the image data 103 may include 3D volumes of scanned structures of the patient. The scanned structures may correspond to organs or parts thereof identified by a 3D representation model. The target definition calculator 104 may map the 3D models of the corresponding structures to the images of the scanned structures. For example, the target definition calculator 104 can determine the initial alignment of the 3D models to the scanned structures in the images. To determine the initial alignment, the target definition calculator 104 may execute an alignment algorithm. For example, the initial alignment of a 17-segment model having the anatomical structure of the left ventricle is described below.

[0065] First, the contour of the interventricular septum on the left ventricular surface is identified by artificially expanding the uploaded left and right ventricles and detecting the intersection of their surfaces. The long axis is determined based on the geometric shape of the left ventricle and the orientation of the septal surface. Next, the basal surface, sinus surface, and apical cross-sectional surface are identified based on the following steps: The apex of the basal surface is positioned corresponding to the uppermost point of the septal outline perpendicular to the long axis. The apical surface segment is positioned at the extreme apex of the ventricle with a predetermined thickness (e.g., 10 mm) along the long axis. The apical, sinus, and basal surfaces are uniformly distributed along the long axis. Furthermore, the segments are positioned based on the following steps: The position of the septal segment is determined by the anterior and posterior interventricular grooves. It is identified corresponding to the anterior and lowermost points of the septal contour. Next, the other basal and sinus segments are uniformly distributed throughout the ventricular wall in the basal and sinus sections, respectively. At the apex, four segments are positioned at 90-degree angles. These are arranged such that the apical septum segment is centrally aligned with the basal, mid-posterior-lateral, and anterior-lateral segments.

[0066] The target definition calculator 104 can then overlay the 3D model onto the image according to the determined alignment to generate a 3D structural image. The executed application can then be provided for displaying the 3D structural image (for example, an image of the scanned structure superimposed on the 3D model).

[0067] Once mapped, the executed application allows medical professionals to adjust the alignment and / or orientation of the 3D model relative to the image, as described herein. For example, the target definition calculator 104 may determine the long axis along the 3D model and further determine the boundaries of the treatment target area on the 3D model. The executed application may include one or more “drag points” along the 3D model, and medical professionals can drag each point to a new location (e.g., using the input / output device 203) to adjust parts of the 3D model with respect to structures in the image. Medical professionals can also drag the long axis to a new position to change the orientation of the 3D model relative to structures in the image.

[0068] In some examples, the 3D model includes a target area map that a medical professional can manipulate to define the target area (e.g., ablation area) for a patient's treatment. Initially, the target area map corresponds to the image portion defined by the 3D model, which corresponds to the selected portion (e.g., segment) of the target definition model (e.g., target area map). For example, if a medical professional selects segments 17 and 16 of a 17-segment model for excision, the target definition calculator 104 determines the corresponding segments as defined by the 3D model. In some examples, the application being executed displays the target area map in distinct colors. Furthermore, those portions of scanned structures in the image that fall within the determined 3D portion may be displayed in a color that is highlighted (e.g., red). A medical professional may adjust drag points to refine the target area map. For example, a medical professional may adjust one or more drag points to define the contour of the target area map of the 3D model.

[0069] In some examples, the target definition calculator 104 determines whether each medical professional's adjustment violates one or more predetermined rules. If an adjustment violates a rule, the executed application may display a pop-up message with a warning. The rules may include, for example, determining whether the current alignment deviates from the initial alignment by a threshold amount, e.g., a threshold percentage. Medical professionals may view and address the warning, or dismiss it. The application of the rules serves as a "normality check" for each adjustment.

[0070] In some examples, the application allows a medical professional to select one or more other organs that may be displayed in relation to the 3D structural image. For example, the application may allow a medical professional to select the display of the esophagus or lungs adjacent to the 3D structural image of the ventricles of the heart. The display of other organs may include the display of a 3D model of that organ. In some examples, the display includes scan images of the corresponding organs in the patient. These features can assist medical professionals in alignment and explain how other organs will be affected by the proposed treatment (e.g., as identified by the ablation area).

[0071] In some examples, the application being run allows panning and zooming of the entire 3D structural image. In some examples, the application being run includes pre-configured selections (e.g., presets) for specific viewpoints of the 3D structural image. These pre-configured selections may be configurable by a medical professional.

[0072] Once the medical professional completes the alignment, they may provide input to the running application (e.g., via input / output device 203) for saving the 3D structural images to a data repository such as database 116. In some examples, the target definition calculator 104 sends the 3D structural images to the treatment planning calculator 106 to provide treatment to the patient based on the identified ablation areas.

[0073] Figure 3 shows an exemplary portion of the cardiac radioresection diagnostic and treatment system of Figure 1. In this example, the target definition calculator 104 includes a test definition generation engine 302, a target selection engine 304, and an alignment determination engine 306. In some examples, one or more of the test definition generation engine 302, the target selection engine 304, and the alignment determination engine 306 may be implemented in hardware. In some examples, one or more of the test definition generation engine 302, the target selection engine 304, and the alignment determination engine 306 may be executed by one or more processors, such as the processor 201 in Figure 2, or they may be executable programs stored in tangible non-transient memory, such as the instruction memory 207 in Figure 2.

[0074] In this example, each target definition calculation unit 104 includes a test definition generation engine 302, a target selection engine 304, and an alignment determination engine 306, and can receive user input 301. For example, a medical professional may provide user input 301 via an input / output device 203 or the touchscreen of the display 206. User input 301 may also be received within a graphical user interface (GUI) provided by the running application. Each of the test definition generation engine 302, the target selection engine 304, and the alignment determination engine 306 can receive data from the GUI (e.g., user input 301) and can provide data to the GUI, such as data for display.

[0075] The test definition generation engine 302 can generate test definition data 303 that identifies a test data record based on user input 301. The test data record may identify the test type, test category, test localization, and any selected portion (e.g., segment) of the interactive model, as described herein. The test data record may also identify the name of the test data record, the date of the test data record, and any remarks provided by the medical professional, as described herein. The test definition generation engine 302 provides the test definition data 303 to the target selection engine 304. In some examples, the test definition generation engine 302 stores the test definition data 303 in the database 116.

[0076] The target selection engine 304 can perform operations to identify target areas for treatment. For example, the target selection engine 304 may generate one or more examination category maps for display, each examination category map (e.g., “heatmap”) corresponding to an examination category. Each examination category map may identify one or more parts of a patient’s organs, such as a 17-segment model of the ventricles of the heart. Furthermore, the target selection engine 304 may generate probability maps for display, which in some examples may be the same form as the examination category maps. The probability maps may show the probability of treatment for each part of an organ based on the organ parts identified by the examination category maps (e.g., using different colors), as described herein. For example, the target selection engine 304 may retrieve patient data 310 of a corresponding patient from the database 116. The patient data 310 may identify previous examinations the patient has received and any corresponding examination data records for those treatments. Based on the patient data 310, the target selection engine 304 may determine the extent to which treatment is possible for the patient, as described herein.

[0077] The target selection engine 304 may further generate target definition models for display, such as a 17-segment model of the ventricle of the heart, so that a medical professional can identify a target area for treatment (e.g., an ablation area). The medical professional can provide user input 301 to select one or more parts of the target definition model to identify a target area. In some examples, the target selection engine 304 determines whether the selection is "unlikely" or not, as described herein, and if the selection is determined to be unlikely, displays a warning about the selection (e.g., via a pop-up window). The target selection engine 304 generates selection target data 305 that identifies the selected parts of the target definition model and provides the selection target data 305 to the alignment determination engine 306.

[0078] The alignment determination engine 306 can perform operations to generate a 3D model of a part of an organ corresponding to an organ or target definition model and provide it for display. Furthermore, the alignment determination engine 306 may acquire patient image data 103 that identifies a corresponding scan structure, such as a 3D image of the patient's ventricle. The alignment determination engine 306 may determine the alignment of the image to the 3D model and superimpose the 3D model onto the image according to the determined alignment to generate a 3D structural image. The alignment determination engine 306 may then provide a 3D structural image for display, such as one that is displayed on the display 206.

[0079] Furthermore, the alignment determination engine 306 may receive user input 301 that identifies and characterizes adjustments to the 3D structural image. In response to the user input 301, the alignment determination engine 306 can adjust the 3D structural image accordingly. For example, the alignment determination engine 306 may improve the alignment of the 3D model to the image, or it may define a target region map that identifies the treatment target area by adjusting the drag points. The alignment determination engine 306 may generate target definition data 307 that identifies and characterizes the 3D structural image including the target region map, and may store the target definition data 307 in the database 116.

[0080] In some examples, the alignment determination engine 306 determines whether each medical professional's adjustment violates one or more predetermined rules. If the adjustment violates a rule, the alignment determination engine 306 may display a pop-up message with a warning. In some examples, the alignment determination engine 306 receives one or more user inputs 301 that identify a selection of one or more other organs that may be displayed in combination with the 3D structural image. In response, the alignment determination engine 306 displays a 3D model of such organ. In some examples, the alignment determination engine 306 displays image data 103 of the corresponding organ of the patient.

[0081] In some examples, the alignment determination engine 306 receives one or more user inputs 301 that specify a pan or zoom operation. In response, the alignment determination engine 306 can pan or zoom across the 3D structured image. In some examples, the alignment determination engine 306 receives one or more user inputs 301 that specify a pre-configured selection for a particular viewpoint of the 3D structured image. The alignment determination engine 306 may adjust the 3D structured image according to the selected viewpoint and display the adjusted 3D structured image.

[0082] Figure 4A shows a first portion 402 of the GUI 400, which allows medical professionals such as EPs to define target areas for treatment (e.g., ablation). The GUI 400 may be generated by an application run by the target definition calculator 104 and may be displayed to medical professionals on a display such as the display 206.

[0083] GUI400 facilitates many steps for defining the target area for treatment, including generating examination data records, identifying target areas for treatment, aligning the target areas to images of the patient's organs, and more. These steps are represented by examination icons 406, target selection icons 408, and alignment icons 410, each of which is illustrated under the target definition icon 404. By selecting one of the examination icons 406, target selection icons 408, and alignment icons 410, a portion of GUI400 corresponding to that step may be presented to the user.

[0084] To begin target definition, the first section 402 includes a test icon 401, which, if selected, enables the generation of a new test data record. Page 402 also includes a report icon 411, if selected, which generates a report based on the corresponding test data record. The report may include data identifying and characterizing the alignment of the selected target region to the test data record, any selected target region (e.g., a segment), scanned images of the patient (e.g., scanned by the imaging device 102), and images of the patient's organs.

[0085] Figure 4B shows a second portion 420 of the GUI 400 that may be displayed when a healthcare professional selects the additional test icon 401 in Figure 4A. For example, the second portion 420 may be a pop-up window that appears when a healthcare professional clicks the additional test icon 401. The second portion 420 includes a test type drop-down menu 424, a test category drop-down menu 428, and a test localization drop-down menu 430.

[0086] The examination type dropdown menu 424 allows medical professionals to select the examination type for examination type recording. For example, as shown in Figure 4B, the examination type dropdown menu 424 can allow medical professionals to select from multiple examination types (e.g., imaging types) such as CT, catheter mapping, ECG, ECGI, and MRI.

[0087] Once a medical professional selects a test type, GUI400 automatically determines one or more test categories based on the selected test type. Each test category can identify a list of characteristics (or test localizations) for a particular test type. The medical professional can view the available test categories using the test category dropdown menu 426. For example, and as shown in Figure 4D, the medical professional can select the "Electrocautery" test category when the test type is "ECG".

[0088] Once a test category is selected, GUI400 automatically determines one or more test localizations based on the selected test category and / or test type. Test localizations can identify common target areas of the patient's organs to be treated, such as one or more segments of the heart. For example, as shown in Figure 4D, in the test localization dropdown menu 430, if the selected test type is "ECG" and the selected test category is "Electrocardiogram," a healthcare professional can select the test localizations "VT Exit Site," "VT Inlet Site," or "VT Inlet and Exit Site."

[0089] Returning to Figures 4B, 4C, and 4D, the second part 420 also includes a test name text box 426 that allows a healthcare professional to provide a name for the test record, a test date selection box 432 that allows the selection of a date (e.g., the current date), and a remarks text box 434 that allows a healthcare professional to enter remarks (e.g., treatment notes, reminders, notes to other healthcare professionals, etc.).

[0090] Furthermore, the second part 420 includes an interactive model 422. In this example, the interactive model 422 is a 17-segment model representing the segments of the ventricles of the heart. A medical professional can select one or more segments of the interactive model 422 that may be areas for treatment. For example, as shown in Figure 4E, a medical professional can select a first segment 423A (e.g., segment 11), a second segment 423B (e.g., segment 16), and a third segment 423C (e.g., segment 15). Furthermore, in some examples, when the cursor 489 is placed over a segment (e.g., segment 4), the GUI 400 displays the name of the segment (e.g., via a pop-up window). In this example, the cursor 489 appears over segment 4 of the interactive model 422, and in response, the GUI 400 displays a name box 425 that identifies segment 4 as the “subbasal” portion of the ventricles of the heart.

[0091] To create a test data record, a medical professional can click the add icon 490. In response, 104 generates data that identifies and characterizes the information provided to the GUI 400 and saves the generated data to a data repository, such as in the database 116. If the medical professional wishes to redo the process and not save the test data record, they can click the cancel icon 492. As a result, any input provided is cleared, and in some examples, the first part 402 appears as shown in Figure 4A.

[0092] Referring to Figure 4F, GUI 400 may include a third section 478 that displays a summary of the generated test data record. For example, GUI 400 may display section 478 in response to a healthcare professional clicking the additional icon 490 in Figure 4E. In some examples, GUI 400 displays section 478 in response to a healthcare professional clicking the test icon 406 in Figure 4A.

[0093] The third section 478 contains display areas for the inspection category 480A, inspection name 480B, selected segment 480C, acquisition date 480D, and remarks 480E for each generated inspection data record. The inspection category 480A corresponds to the selected inspection category 428 for each generated inspection data record. Similarly, the inspection name 480B, acquisition date 480D, and remarks 480E correspond to the inspection name 426, inspection date 432, and remarks 434 for each inspection data record.

[0094] In this example, two outlines are illustrated, including a first examination outline 495A and a second examination outline 495B. The first examination outline 495A includes the "Structural" examination category 480A, in addition to the corresponding interactive model 491 showing selected segments 11, 15, and 16. The second examination outline 495B includes the "Electrical" examination category 480A, in addition to corresponding to the interactive model 4912 showing selected segments 10 and 15. In some examples, when the cursor 489 is placed over the corresponding part of the interactive model, the GUI 400 displays the name of the segment (e.g., via a pop-up window). In this example, the cursor 489 appears over segment 10 of the interactive model 492, and in response, the GUI 400 displays a name box 493 identifying segment 0 as the "middle and lower" part of the ventricle of the heart.

[0095] Figure 5A shows the target selection unit 501 of the GUI 400. For example, as described above with respect to Figures 4A to 4F, once an examination data record is generated, the GUI 400 may display the target selection unit 501 to the medical professional. In some examples, the GUI 400 displays the target selection unit 501 in response to the medical professional clicking the target selection icon 408 in Figure 4A.

[0096] In this example, the target selection unit 501 displays a first examination category map 510 based on the examination category 428 "electrical" and a second examination category map 520 based on the examination category 428 "structural". As described herein, each examination category map 510, 520 can identify one or more parts of a patient's organs, such as a 17-segment model of the ventricles of the heart. Furthermore, each examination category map 510, 520 provides a display of examinations previously performed on the patient corresponding to the corresponding examination category. Furthermore, each examination category map 510, 520 is displayed together with its corresponding bar graphs 512, 522. Furthermore, each examination category map 510, 520 is displayed together with its corresponding bar graphs 512, 522. Each bar graph 512, 522 shows the determined therapeutic dose range for each examination category and shows their corresponding hatching used within the segments of each examination category map 510, 520.

[0097] The target selection unit 502 also includes a probability map 502 that shows the probability of treatment for one or more parts of the patient's organs (in this example, the patient's heart) based on those parts of organs identified by the examination category maps 510, 520. The probability map 502 is displayed with corresponding bar graphs 506 that show the probability range of treatment segments, as described herein, and their corresponding hatchings used within the segments of the probability map 502.

[0098] Furthermore, the target selection unit 502 includes a target definition map 530, which in this embodiment is in the form of a 17-segment model of the ventricles of the heart. The target definition map 530 allows a medical professional to identify a target area for treatment. For example, a medical professional may select a segment of the target definition map 530 to identify a target area 532 (for example, by using the input / output device 203 to manipulate the cursor 489). In this example, the target area 532 includes segment 17 of the target definition map 530.

[0099] Figure 5B is similar to Figure 5A, but the healthcare professional may select segment 16 of the target definition map 530 to identify the target region 542. Once the healthcare professional has identified the target regions 532, 542 by selecting a portion of the target definition map 530, the healthcare professional can proceed to the next step by clicking the "Next" icon 545.

[0100] Figure 6A shows the alignment portion 601 of the GUI 400 displaying a 3D structural image 602, which includes a 3D segment model 606 superimposed on a scan image 604. The 3D segment model 606 may be, for example, a 3D segment model of the ventricles of a heart. The scan image 604 may be an image scanned by the image scanning device 102, such as a 3D volume of scanned structures of a patient. The 3D structural image 602 also includes a target region map 648 that defines a target region for treatment of the patient. The target region map 648 may, at least initially (e.g., before adjustment by the EP), correspond to one or more selected target regions of the target definition map, such as target regions 532, 542, etc. of the target definition map 530. In some examples, the target region map 648 is displayed in explicit color. In some examples, explicit hatching is used to display the target region map 648, or any other preferred mechanism is used that allows the EP to easily determine the contour of the target region map 648. Furthermore, as shown, the vertical axis 650 passes through the top 608 of the 3D structure image 602.

[0101] In some examples, the alignment unit 601 may display a reference character 680. The reference character 680 is displayed from a viewpoint that follows the orientation of the 3D structural image 602. For example, if the orientation of the 3D structural image 602 is such that it is displayed from above so that the corresponding organs are located within the patient, the reference character 680 is displayed from above. This allows the EP to easily determine from what viewpoint and / or orientation the 3D structural image 602 is currently being displayed.

[0102] In some examples, the alignment unit 601 may include a text input box 640 that allows a value to be entered. In this example, the value entered is the myocardial thickness (e.g., left ventricular myocardial thickness). The myocardial thickness can be used to reconstruct the intraventricular myocardial surface onto which all identified target segments are projected, as described below. For example, the target definition calculator 104 can execute an algorithm to generate the final 3D target volume by combining the selected segments and all regions bounded by the underlying projections. If the user (e.g., EP) has not edited the myocardial thickness, a default value such as 10 mm is used. For example, the target definition calculator 104 can generate a 3D target volume based on the selected segments, as described here. For example, in the example of the heart, the target definition calculator 104 may take the selected segments (e.g., part of the epicardial wall) and extrude the volume toward the center of the left ventricle, having a depth based on the wall thickness definition.

[0103] In some examples, the alignment unit 601 includes one or more adjustment icons 655 that enable adjustment of the 3D structural image 602. For example, the adjustment icons 655 can enable zoom in, zoom out, panning, and rotation functions.

[0104] Referring to Figure 6B, the alignment unit 601 may display one or more drag points, such as drag points 670A, 670B, that allow the EP to make adjustments to the 3D structure image 602. For example, the EP can adjust the vertical axis 650 by dragging drag point 670A to a new position. In response, the GUI 400 adjusts the orientation of the scanned image 604 relative to the 3D segment model 606. Similarly, the EP can adjust the target region map 648 by dragging drag point 670B to a new position.

[0105] In some examples, GUI400 allows the creation or deletion of drag points. For example, EP may right-click on a drag point such as drag point 670B and select the "Delete" option to remove the drag point. Similarly, EP may right-click on a part of the 3D segment model 606 and select the "Add" option to add a drag point.

[0106] Figure 6C shows the 3D structural image 602 after the EP provides input to rotate the 3D structural image 602 clockwise around the vertical axis 650. In this example, a drag point 670C may allow the EP to adjust the anterior interchamber groove 686 of the 3D structural image 602.

[0107] The adjustment icon 655 may allow the EP to display images of additional organs, such as organs adjacent to the organ identified by the scan image 604. For example, and referring to Figure 6D, the EP can select the adjustment icon 655 to display the organ selection box 675, which allows the EP to select one or more organs to display.

[0108] For example, assuming that EP selects "lungs" (e.g., "lung_R_P" for the right lung, "lung_L_P" for the left lung) and "esophagus", GUI400 may display renderings (e.g., 3D renderings) of the first organ 685 (e.g., lungs) and the second organ 687 (e.g., esophagus), as shown in Figure 6E. The renderings may be, for example, 3D models pre-stored in database 116. In other examples, the renderings may be scan images of the corresponding structures of the patient.

[0109] Figure 11 is a flowchart of an exemplary method 1100 that may be carried out, for example, by a target definition calculator 104. Starting in step 1102, a first input is received. The first input identifies the type of test to be selected. For example, the EP may use an input / output device 203 to provide input to an execution application that displays a GUI, such as GUI 400, on a display 206. The EP may select a test type 424 displayed within a portion 420 of GUI 400.

[0110] In step 1104, multiple test categories are provided for display. The number of categories is determined based on the selected test type. For example, GUI 400 may display multiple test categories in the test category dropdown menu 428. Proceeding to step 1106, a second input is received. The second input identifies the selected test category from among the multiple test categories. For example, EP can select one of the multiple test categories displayed in the test category dropdown menu 428.

[0111] In step 1108, multiple test localizations are provided for display. The multiple test localizations are determined based on the selected test category. For example, GUI 400 may display multiple test localizations in the test localization dropdown menu 430. In step 1110, a third input is received. The third input identifies the selected test localization from among the multiple test localizations. For example, EP can select one of the multiple test localizations displayed in the test localization dropdown menu 430.

[0112] The process proceeds to step 1112, where the selected test type, selected test category, and selected test localization are stored in the data repository. For example, 104 can generate a test data record that identifies the selected test category and selected test localization, and store the test data record in database 116. The process then terminates.

[0113] Figure 12 is a flowchart of an exemplary method 1200 that may be performed, for example, by a target definition calculator 104. Starting in step 1202, a test data record is obtained for the patient. The test data record identifies several tests performed on the patient. For example, the target definition calculator 104 may obtain test definition data 303 from a database 116 about the patient. In step 1204, a test category is determined for each of the tests. For example, each of the tests may be associated with a test category such as "electrical" or "structural". In step 1206, the number of tests for each different category is determined. Furthermore, in step 1208, a treatment target area is determined for each of the tests. For example, each of the tests may be associated with one or more segments that are the target of treatment.

[0114] Proceeding to step 1210, a first map is generated for each test category based on the number of corresponding test and treatment target areas. For example, the target definition calculator 104 may determine for each test category the proportion of corresponding tests that treat each of multiple segments of the patient's organs. For example, each of the first maps may be a test category map 510, 520.

[0115] In step 1212, a second map is generated. The second map is generated based on the first map and the corresponding therapeutic target area. For example, the second map may show the probability of testing one or more parts of the patient's organs based on those parts identified in the first map. The second map may be, for example, a probability map 502 showing the probability of treatment for one or more parts of the patient's organs based on those parts of the organs identified by the test category maps 510, 520.

[0116] In step 1214, the first map and the second map are provided for display. For example, the first map and the second map may be displayed within the target selection portion 501 of the GUI 400. The method then terminates.

[0117] Figure 13A is a flowchart of an exemplary method 1300 that may be performed, for example, by a target definition calculator 104. In step 1302, first data is received. The first data identifies a therapeutic target region of the patient's organ. For example, the target definition calculator 104 may determine the therapeutic target region based on a segment of a target definition map 530 selected by the EP to identify the target region 532. In step 1304, an image of the patient's organ is acquired. For example, the target definition calculator 104 may acquire an image, such as a 3D volume image, of the patient's organ scanned by an image scanning device 102.

[0118] The process proceeds to step 1306, where a first digital model of the patient's organ type is generated. For example, the target definition calculator 104 can generate a 3D model of the patient's organ, such as a 3D ventricular model 720 or a 3D segment model 1002B. In step 1308, the alignment of the patient's organ image and the first digital model is determined. Furthermore, in step 1310, a second digital model is generated. The second digital model includes an image of the patient's organ and at least a portion of the first digital model. For example, the target definition calculator 104 can generate a 3D structural image 602 by overlaying a 3D segment model 606 onto a scanned image 604. In step 1312, the second digital model is provided for display. For example, the target definition calculator 104 may display the second digital model to the EP. The process then terminates.

[0119] Figure 13B is a flowchart of an exemplary method 1350 that may be performed, for example, by a target definition computing device 104. Beginning in step 1352, a digital model is provided for display. The digital model consists of a portion of the patient's organs and a second digital model of the organ type. For example, the digital model may be generated according to method 1300 in Figure 13A. In step 1354, an input is received. This input identifies alignment adjustments to the digital model. For example, 104 may receive input from the EP using an input / output device 203 to make adjustments to the 3D structural image 602 by dragging one or more drag points 670, as described herein.

[0120] The process proceeds to step 1356, where adjustments to the digital model are determined based on the input. For example, this adjustment may be a change in the orientation of the patient's organ images with respect to a second digital model. For example, the EP can adjust the orientation by dragging one or more drag points 670 to move the vertical axis 650. In some examples, the adjustment may be a change to the target region map of the digital model. For example, the adjustment may be to the target region map 648 of the 3D structural image 602.

[0121] In step 1358, the digital model sis is regenerated based on the determined adjustments. Furthermore, in step 1360, the regenerated digital model is provided for display. In some examples, 104 transmits the regenerated digital model to a radiosurgery treatment system 126 for treating a patient. The method then terminates.

[0122] In some examples, the system includes a computing device. The computing device is configured to receive a first input that identifies a patient's organ and to receive a scan image of the organ. The computing device is also configured to generate a first digital model of the organ type. Furthermore, the computing device is configured to determine the alignment of the scan image to the first digital model. The computing device is also configured to generate a second digital model that includes at least a portion of the scan image and the first digital model. The computing device is further configured to store the second digital model in a data repository. In some examples, receiving the first input corresponds to selecting a portion of a displayed target definition map. In some examples, the organ is the heart. In some examples, the computing device is configured to provide a second digital model for display.

[0123] In some examples, the computing device is configured to receive a second input that identifies adjustments to the alignment of scanned images relative to a first digital model. The computing device is also configured to adjust the second digital model based on the second input. The computing device is further configured to store the adjusted second digital model in a data repository.

[0124] In some examples, the computing device is configured to receive a second input that identifies the therapeutic target region of an organ. The computing device is also configured to determine the corresponding portion of a second digital model based on the organ's therapeutic target region. Furthermore, the computing device is configured to regenerate the second digital model to identify the corresponding portion. In some examples, regenerating the second digital model includes associating the corresponding portion with an explicit feature for display. In some examples, the computing device is further configured to transmit therapeutic data identifying the organ's therapeutic target region to a radiopharmaceutical system.

[0125] In some examples, the computer is configured to acquire patient test data records, each test data record identifying one of several test types and one of several test target areas for the test performed on the patient. The computer is also configured to determine a first number of each of the several test types performed on the patient based on the test data records. Furthermore, the computer is configured to determine a second number of tests performed on the patient in each of the several test target areas for each of the several test types. The computer is also configured to generate a first map for each of the several test types based on the corresponding first and second numbers. The computer is further configured to store the first maps in a data repository. In some examples, each first map shows the frequency of the corresponding test type in each of the several test target areas. In some examples, the computer generates a second map based on the first and second numbers, the second map shows the probability of treatment for each of the several test target areas, and is further configured to store the second map in a data repository.

[0126] In some examples, a method performed on a computer includes receiving a first input that identifies a patient's organ and receiving a scan image of the organ. The method also includes generating a first digital model of the organ type. Furthermore, the method includes determining the alignment of the scan image with respect to the first digital model. The method also includes generating a second digital model that includes at least a portion of the scan image and the first digital model. The method further includes storing the second digital model in a data repository. In some examples, receiving the first input is done in accordance with the selection of a portion of a displayed target definition map. In some examples, the organ is the heart. In some examples, the method includes providing a second digital model for display.

[0127] In some examples, the method includes receiving a second input that specifies adjustments to the alignment of the scanned image relative to the first digital model. The method also includes adjusting the second digital model based on the second input. The method further includes storing the adjusted second digital model in the data repository.

[0128] In some examples, the method includes receiving a second input that identifies a therapeutic target region of the organ. The method also includes determining a corresponding portion of a second digital model based on the therapeutic target region of the organ. Furthermore, the method includes regenerating the second digital model to identify the corresponding portion. In some examples, regenerating the second digital model includes associating the corresponding portion with explicit features for display. In some examples, the method includes transmitting therapeutic data that identifies the therapeutic target region of the organ to a radiopharmaceutical system.

[0129] In some examples, the method includes obtaining a test data record for the patient, where each test data record identifies one of a plurality of test types and one of a plurality of test target areas for the tests performed on the patient. The method also includes determining a first number of each of the plurality of test types performed on the patient based on the test data record. Furthermore, the method includes determining a second number of tests performed on the patient in each of the plurality of test target areas for each of the plurality of test types. The method further includes generating a first map for each of the plurality of test types based on the corresponding first and second numbers. The method also includes storing the first map in the data repository. In some examples, each first map shows the frequency of the corresponding test type for each of the plurality of test target areas. In some examples, the method includes generating a second map based on the first and second numbers, where the second map shows the probability of treatment for each of the plurality of test target areas, and storing the second map in the data repository.

[0130] In some examples, a non-temporary computer-readable medium stores instructions, which, when executed by at least one processor, cause the at least one processor to perform a process including receiving a first input identifying a patient's organ, and receiving a scan image of the organ. The process also includes generating a first digital model of the organ type. Furthermore, the process includes determining the alignment of the scan image to the first digital model. The process also includes generating a second digital model including at least a portion of the scan image and the first digital model. The process further includes storing the second digital model in a data repository. In some examples, receiving the first input is done in accordance with the selection of a portion of a displayed target definition map. In some examples, the organ is the heart. In some examples, the process includes providing the second digital model for display.

[0131] In some examples, the process includes receiving a second input that identifies adjustments to the alignment of a scanned image relative to a first digital model. The process also includes adjusting the second digital model based on the second input. The process further includes storing the adjusted second digital model in the data repository.

[0132] In some examples, the process includes receiving a second input that identifies the therapeutic target region of the organ. The process also includes determining a corresponding portion of a second digital model based on the therapeutic target region of the organ. Furthermore, the process includes regenerating the second digital model to identify the corresponding portion. In some examples, regenerating the second digital model includes associating the corresponding portion with an explicit feature for display. In some examples, the process includes transmitting therapeutic data that identifies the therapeutic target region of the organ to a radioablation system.

[0133] In some examples, the process includes obtaining a test data record for a patient, where each test data record identifies one of a plurality of test types and one of a plurality of test target areas for a test performed on the patient. The process also includes determining a first number of each of the plurality of test types performed on the patient based on the test data record. Furthermore, the process includes determining a second number of tests performed on the patient in each of the plurality of test target areas for each of the plurality of test types. The process further includes generating a first map for each of the plurality of test types based on the corresponding first and second numbers. The process also includes storing the first map in the data repository. In some examples, each first map shows the frequency of the corresponding test type for each of the plurality of test target areas. In some examples, the process includes generating a second map based on the first and second numbers, where the second map shows the probability of treatment for each of the plurality of test target areas, and storing the second map in the data repository.

[0134] In some examples, a method performed on a computer includes means for receiving a first input that identifies a patient's organ and for receiving a scan image of the organ. The method also includes means for generating a first digital model of the type of organ. Furthermore, the method includes means for determining the alignment of the scan image with respect to the first digital model. The method also includes means for generating a second digital model that includes at least a portion of the scan and the first digital model. The method further includes means for storing the second digital model in a data repository. In some examples, receiving the first input is done in accordance with the selection of a portion of a displayed target definition map. In some examples, the organ is the heart. In some examples, the method includes means for providing the second digital model for display.

[0135] In some examples, the method includes means for receiving a second input that identifies adjustments to the alignment of a scanned image relative to a first digital model. The method also includes means for adjusting the second digital model based on the second input. The method further includes means for storing the adjusted second digital model in the data repository.

[0136] In some examples, the method includes means for receiving a second input that identifies a therapeutic target region of the organ. The method also includes means for determining a corresponding portion of the second digital model based on the therapeutic target region of the organ. Furthermore, the method includes means for regenerating the second digital model to identify the corresponding portion. In some examples, regenerating the second digital model includes associating the corresponding portion with an explicit feature for display. In some embodiments, the method includes means for transmitting therapeutic data identifying the therapeutic target region of the organ to a radioablation therapy system.

[0137] In some examples, the method includes means for obtaining a test data record for the patient, where each test data record identifies one of a plurality of test types and one of a plurality of test target areas for a test performed on the patient. The method also includes means for determining a first number of each of the plurality of test types performed on the patient based on the test data record. Furthermore, the method includes means for determining a second number of tests performed on the patient in each of the plurality of test target areas for each of the plurality of test types. The method further includes means for generating a first map for each of the plurality of test types based on the corresponding first and second numbers. The method also includes means for storing the first map in a data repository. In some examples, each first map shows the frequency of the corresponding test type for each of the plurality of test target areas. In some examples, the method generates a second map based on the first and second numbers, where the second map shows the probability of treatment for each of the plurality of treatment target areas, and includes means for storing the second map in the data repository.

[0138] While the method described above refers to the illustrated flowchart, it will be understood that many other methods can be used to perform the actions related to this method. For example, the order of some processes may be changed, and some of the processes described may be optional.

[0139] Furthermore, the methods and systems described herein can be implemented at least in part in the form of processes implemented on a computer and devices for performing those processes. Alternatively, the disclosed methods may be implemented at least in part in the form of a tangible, non-temporary, machine-readable storage medium encoded in computer program code. For example, the steps of the method may be implemented in hardware, executable instructions executed by a processor (e.g., software), or a combination of both. The medium may include, for example, RAM, ROM, CD-ROM, DVD-ROM, BD-ROM, hard disk drives, flash memory, or any other non-temporary, machine-readable storage medium. When computer program code is loaded into a computer and executed by the computer, the computer becomes a device for performing the method. The method can also be implemented at least in part in the form of a computer on which computer program code is loaded or executed, in which case the computer becomes a special-purpose computer for performing the method. When implemented on a general-purpose processor, the computer program code segments configure the processor to create specific logic circuits. Alternatively, the method can be implemented at least in part on an application-specific integrated circuit for performing the method.

[0140] The foregoing is provided for the purpose of illustrating, describing, and illustrating embodiments of these disclosures. Modifications and adaptations to these embodiments may be obvious to those skilled in the art and may be made without departing from the scope or spirit of these disclosures.

Claims

1. It is a system, Upon receiving the first input to identify the patient's organs, Upon receiving the scan images of the aforementioned organs, A first digital model of the aforementioned organ type is generated, The alignment of the scan image with respect to the first digital model is determined, A second digital model is generated, which includes at least a portion of the scanned image and the first digital model. The second digital model is stored in the data repository. Obtain a record of the examination data for the patient, and for each examination data record, identify one of several examination categories and one of several treatment target areas for the examination performed on the patient. Based on the aforementioned test data records, a first map is generated for each of the plurality of test categories, and each first map shows the number of tests performed on the patient for each of the plurality of treatment target areas. The first map is saved in the data repository. Upon receiving a second input that identifies the therapeutic target region of the aforementioned organ, Based on the therapeutic target region of the organ, the corresponding portion of the second digital model is determined. To identify the corresponding portion, the second digital model is regenerated. A system including a computing device configured in such a way.

2. The system according to claim 1, wherein the computing device is further configured to provide the second digital model for display.

3. The computing device receives a second input that specifies adjustments to the alignment of the scanned image relative to the first digital model, The second digital model is adjusted based on the second input. The adjusted second digital model is stored in the data repository. The system according to claim 1, further configured as follows.

4. The system according to claim 1, wherein regenerating the second digital model includes associating the corresponding portion with an explicit feature for display.

5. The system according to claim 1, wherein the computing device is further configured to transmit treatment data that identifies the treatment target region of the organ to a radiosurgery system.

6. The aforementioned computing device is A second map is generated based on the aforementioned test data record, and the second map shows the number of tests performed on the patient for each of the plurality of treatment target areas, regardless of the test category. The second map is saved to the data repository. The system according to claim 1, further configured as follows.

7. The system according to claim 6, wherein receiving the first input is performed in accordance with the selection of a portion of the displayed target definition map.

8. A method that is performed on a computer, Receiving the first input to identify the patient's organs, Receiving scan images of the aforementioned organs, To generate a first digital model of the aforementioned organ type, To determine the alignment of the scan image with respect to the first digital model, To generate a second digital model that includes at least a portion of the scanned image and the first digital model, To save the aforementioned second digital model to a data repository, A test data record for the aforementioned patient, wherein each test data record obtains a test data record that identifies one of a plurality of test categories and one of a plurality of treatment target areas for the tests performed on the aforementioned patient. Based on the aforementioned test data records, a first map is generated for each of the plurality of test categories, wherein each first map generates a first map showing the number of tests performed on the patient for each of the plurality of treatment target areas. To save the first map in the data repository, Receiving a second input that identifies the therapeutic target region of the aforementioned organ, Determining the corresponding portion of the second digital model based on the therapeutic target region of the organ, To identify the corresponding portion, the second digital model is regenerated. A method that includes this.

9. The computer implementation method according to claim 8, comprising providing the second digital model for display.

10. Receiving a second input that specifies adjustments to the alignment of the scanned image relative to the first digital model, Adjusting the second digital model based on the second input, The adjusted second digital model is stored in the data repository. The computer implementation method according to claim 8, including the method described in claim 8.

11. The computer implementation method according to claim 8, comprising transmitting treatment data that identifies the treatment target region of the organ to a radioresection treatment system.

12. A non-temporary computer-readable medium for storing instructions, wherein, when the instructions are executed by at least one processor, the at least one processor is provided with Receiving the first input to identify the patient's organs, Receiving scan images of the aforementioned organs, To generate a first digital model of the aforementioned organ type, To determine the alignment of the scan image with respect to the first digital model, To generate a second digital model that includes at least a portion of the scanned image and the first digital model, To save the aforementioned second digital model to a data repository, A test data record for the aforementioned patient, wherein each test data record obtains a test data record that identifies one of a plurality of test categories and one of a plurality of treatment target areas for the tests performed on the aforementioned patient. Based on the aforementioned test data records, a first map is generated for each of the plurality of test categories, wherein each first map generates a first map showing the number of tests performed on the patient for each of the plurality of treatment target areas. To save the first map in the data repository, Receiving a second input that identifies the therapeutic target region of the aforementioned organ, Determining the corresponding portion of the second digital model based on the therapeutic target region of the organ, To identify the corresponding portion, the second digital model is regenerated. A non-temporary, computer-readable medium that performs a process including [specific actions].

13. The aforementioned process is, Receiving a second input that specifies adjustments to the alignment of the scanned image relative to the first digital model, Adjusting the second digital model based on the second input, The adjusted second digital model is stored in the data repository. A non-temporary computer-readable medium according to claim 12, further comprising:

Images