System and method for planning cardiac radiotherapy

Abstract

A system (104) and method (400) for predicting the location of a target cardiac region for cardiac ablation, the one or more processors generating a 3D model of a patient's heart based on medical images of the patient (402), and estimating one or more mechanical properties for moving the patient's heart using the 3D model of the patient's heart and the patient's electrophysiological data (404). The one or more processors can use the 3D model and the one or more mechanical properties to generate a simulated motion pattern of the patient's heart through at least a portion of the cardiac cycle (406) and identify a region of interest (ROI) of the patient's heart that is to receive radiation (408). The one or more processors can use the simulated motion pattern of the patient's heart to determine the location of the ROI at a predetermined point in time within the cardiac cycle (410).

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This application claims the benefit of priority of U.S. Patent Application No. 17 / 855,171, filed Jun. 30, 2022, the entire disclosure of which is incorporated herein by reference.

[0002] This application generally relates to systems and methods for planning cardiac radiotherapy. Specifically, this application relates to systems and methods for estimating a patient - specific motion pattern of a heart that pulsates through the cardiac cycle, and the estimated motion pattern is used to estimate the position of an area of interest of the heart through the cardiac cycle.

Background Art

[0003] Cardiac ablation is an invasive medical procedure commonly used to treat various cardiac conditions such as atrial fibrillation (AFib), atrial flutter, atrial tachycardia, ventricular tachycardia (VT), atrioventricular nodal reentrant tachycardia (AVNRT), paroxysmal supraventricular tachycardia (PSVT), Wolff - Parkinson - White syndrome, or cardiac tumors. Standard radiation cardiac procedures involve inserting a catheter into a patient's body to access the patient's heart. Then, heat or extreme cold is applied to destroy abnormal areas of the heart and prevent abnormal electrical signals from passing through the heart. This procedure is risky for at least some patients and typically requires subsequent monitoring of the patient in an intensive care unit. Some of the risks associated with standard radiation ablation include bleeding or infection at the site of catheter insertion, vascular injury, heart valve injury, new or worsening arrhythmias, bradycardia, blood clots, stroke or heart attack, pulmonary vein stenosis, kidney damage from the contrast agent used in the procedure, and / or, in rare cases, death.

[0004] Cardiac radiotherapy ablation (also known as cardiac radioablation) is a non-invasive form of cardiac ablation. Instead of using a catheter, a radiation dose is used to target and destroy abnormal areas of the heart. The use of radiation reduces some of the risks associated with invasive procedures and provides relief for high-risk cardiac patients who may have exhausted other options. However, cardiac radioablation itself has risks and its own challenges. Among them, there is a risk of destroying surrounding healthy tissue, especially in the cardiac region. This risk requires accurate radiation in terms of the radiation area and radiation dose.

[0005] Before a radiotherapy ablation procedure, a radiotherapy treatment plan is developed. The purpose of the treatment plan is to optimize the radiation angles and / or the radiation dose at each angle to ensure that a high radiation dose reaches the target area and a low radiation dose hits the intervening tissue.

Summary of the Invention

[0006] According to a first aspect of the present invention, there is provided a method for predicting the location of a target cardiac region for cardiac ablation according to claim 1.

[0007] According to a second aspect of the present invention, there is provided a system for predicting the location of a target cardiac region for cardiac ablation according to claim 12.

[0008] According to a third aspect of the present invention, there is provided a computer-readable medium according to claim 23.

[0009] Optional features are defined in the dependent claims.

[0010] Aspects described herein relate to improving the prediction of the location of a target cardiac region for cardiac ablation. A simulated motion pattern can be generated that accurately mimics or reproduces the motion of a patient's heart. The simulated motion pattern enables determination of the location of the target cardiac region at various points in the cardiac cycle. The simulated motion pattern or state of the heart can be used by a cardiac radiotherapy planning system to accurately plan the radiation of the target cardiac region while minimizing radiation to surrounding or intervening healthy tissue.

[0011] According to one aspect, a method for predicting the location of a target cardiac region for cardiac ablation can include one or more processors generating a three-dimensional (3D) model of a patient's heart based on medical images of the patient, and estimating one or more mechanical properties for moving the patient's heart using the 3D model of the heart and electrophysiological data of the patient. The method can include one or more processors generating a simulated motion pattern of the patient's heart through at least a portion of the cardiac cycle using the 3D model and the one or more mechanical properties, identifying a region of interest (ROI) of the patient's heart that is to receive radiation, and determining the location of the ROI at a predetermined point in the cardiac cycle using the simulated motion pattern of the patient's heart.

[0012] In some embodiments, the one or more mechanical properties include the contractile and relaxation forces of the patient's heart. In some embodiments, the medical images include a series of image frames acquired over a period of time, and the method can further include one or more processors determining an estimated motion pattern of the patient's heart through the cardiac cycle using the series of image frames. Determining the estimated motion pattern can include tracking the displacement of an individual (separate) set of cardiac landmark points through the series of image frames, or estimating a displacement field using a machine learning model and the series of image frames.

[0013] This method can include determining one or more estimated positions of one or more site points of a patient's heart at a point in the cardiac cycle using an estimated motion pattern of the patient's heart; and determining one or more simulation positions of one or more site points of the patient's heart at the said point in the cardiac cycle using a simulated motion pattern of the patient's heart. The method can include calculating one or more site-point-specific distances between the one or more simulation positions and the one or more estimated positions; updating one or more mechanical characteristics of the patient's heart when it is determined that one or more site-point-specific distances exceed a threshold; and updating the simulated motion pattern of the patient's heart based on the updated one or more mechanical characteristics. The method can include repeating the steps of determining the one or more simulation positions, calculating the one or more site-point-specific distances, updating the one or more mechanical characteristics, and updating the simulated motion pattern of the patient's heart until the one or more site-point-specific distances are below the threshold.

[0014] Determining one or more estimated positions can include one or more processors deforming a 3D model of the patient's heart corresponding to time point t0 according to an estimated motion pattern of the patient's heart to determine an estimated 3D model of the patient's heart corresponding to time point t1, and identifying one or more estimated positions in the estimated 3D model of the patient's heart corresponding to time point t1. The estimated 3D model represents an estimated state of the heart at time point t1. Determining one or more simulated positions can include one or more processors deforming a 3D model of the patient's heart corresponding to time point t0 according to a simulated motion pattern of the patient's heart to determine a simulated 3D model of the patient's heart corresponding to time point t1, and identifying one or more simulated positions in the simulated 3D model of the patient's heart corresponding to time point t1. The simulated 3D model represents a simulated state of the heart at time point t1. The method can include repeating the steps of determining one or more estimated positions and determining one or more simulated positions for a plurality of time point pairs (t0, t1) corresponding to pairs of consecutive image frames in a series of image frames, calculating a plurality of site-specific distances between the simulated positions and the corresponding estimated positions across the plurality of time point pairs (t0, t1), and updating one or more mechanical properties of the patient's heart when it is determined that the plurality of site-specific distances exceed a threshold.

[0015] In some embodiments, updating one or more mechanical characteristics of a patient's heart can include generating a plurality of second simulated motion patterns of the heart corresponding to various changes in the one or more mechanical characteristics and various changes in the electrical characteristics of the heart, determining, for each of the second simulated motion patterns, one or more corresponding simulation positions of one or more site points of the patient's heart at the time point of the cardiac cycle, calculating, for each of the second simulated motion patterns, one or more corresponding distances between the one or more corresponding simulation positions and one or more estimated positions for each site point, selecting a second simulated motion pattern from the plurality of second simulated motion patterns based on the one or more corresponding distances between site points, and updating the one or more mechanical characteristics according to the changes in the one or more mechanical characteristics corresponding to the selected second simulated motion pattern. In some embodiments, the ROI includes one or more segments of a standardized N-segment model (N is an integer). In some embodiments, the method can further include modeling, as boundary conditions incorporated into the simulated motion pattern of the patient's heart, the fixation conditions applied to the patient during a cardiac ablation procedure.

[0016] Another aspect relates to a system for predicting the position of a target cardiac region for cardiac ablation, the system including one or more processors and a memory storing computer code instructions. When executed, the computer code instructions can cause the one or more processors to generate a three-dimensional (3D) model of the patient's heart based on medical images of the patient, estimate one or more mechanical characteristics for moving the patient's heart using the 3D model of the heart and the patient's electrophysiological data, generate a simulated motion pattern of the patient's heart through the cardiac cycle using the 3D model and the one or more mechanical characteristics, identify a region of interest (ROI) of the patient's heart that is irradiated, and determine the position of the ROI at a predetermined time point within the cardiac cycle using the simulated motion pattern of the patient's heart.

[0017] In some embodiments, one or more mechanical characteristics include the contractile and relaxation forces of a patient's heart. In some embodiments, a medical image includes a series of image frames acquired over a period of time, and one or more processors can further determine an estimated motion pattern of the patient's heart through the cardiac cycle using the series of image frames. When determining the estimated motion pattern, the one or more processors can track the displacement of an individual set of cardiac landmark points through the series of image frames, or utilize a machine learning model to estimate the displacement range using the series of image frames.

[0018] One or more processors can use the estimated motion pattern of the patient's heart to determine one or more estimated positions of one or more landmark points of the patient's heart at a point in the cardiac cycle, and use the simulated motion pattern of the patient's heart to determine one or more simulation positions of one or more landmark points of the patient's heart at the said point in the cardiac cycle. The one or more processors can calculate one or more landmark point-specific distances between the one or more simulation positions and the one or more estimated positions, and when it is determined that one or more of the landmark point-specific distances exceed a threshold, update one or more mechanical characteristics of the patient's heart and update the simulated motion pattern of the patient's heart based on the updated one or more mechanical characteristics. The one or more processors can repeat the steps of determining the one or more simulation positions, calculating the one or more landmark point-specific distances, updating the one or more mechanical characteristics, and updating the simulated motion pattern of the patient's heart until one or more of the landmark point-specific distances are below the threshold.

[0019] When determining one or more estimated positions, one or more processors can deform a 3D model of the patient's heart corresponding to time point t0 according to an estimated motion pattern of the patient's heart to determine an estimated 3D model of the heart corresponding to time point t1, and identify one or more estimated positions in the estimated 3D model of the heart corresponding to time point t1. The estimated 3D model indicates the estimated state of the heart at time point t1. When determining one or more simulated positions, one or more processors can deform a 3D model of the patient's heart corresponding to time point t0 according to a simulated motion pattern of the patient's heart to determine a simulated 3D model of the heart corresponding to time point t1, and identify one or more simulated positions in the simulated 3D model of the heart corresponding to time point t1. The simulated 3D model indicates the simulated state of the heart at time point t1. One or more processors perform the steps of determining one or more estimated positions and determining one or more simulated positions for a plurality of time point pairs (t0, t1) corresponding to pairs of consecutive image frames in a series of image frames, calculating a plurality of site-by-site distances between the simulated positions and the corresponding estimated positions across the plurality of time point pairs (t0, t1), and updating one or more mechanical properties of the patient's heart when it is determined that the plurality of site-by-site distances exceed a threshold, and can repeat these steps.

[0020] In some embodiments, when updating one or more mechanical characteristics of a patient's heart, one or more processors generate a plurality of second simulated motion patterns of the heart corresponding to various changes in the one or more mechanical characteristics and various changes in the electrical characteristics of the heart, and for each of the second simulated motion patterns, determine one or more corresponding simulation positions of one or more site points of the patient's heart at the time point of the cardiac cycle, calculate one or more corresponding distances by site point between the one or more corresponding simulation positions and one or more estimated positions for each of the second simulated motion patterns, select a second simulated motion pattern from the plurality of second simulated motion patterns based on the one or more corresponding distances by site point, and update the one or more mechanical characteristics according to the changes in the one or more mechanical characteristics corresponding to the selected second simulated motion pattern. In some embodiments, the ROI includes one or more segments of a standardized N-segment model (N is an integer). In some embodiments, the one or more processors can further model the fixation conditions applied to the patient during a cardiac ablation procedure as boundary conditions incorporated into the simulated motion pattern of the patient's heart.

[0021] A further aspect of the computer-readable medium can include stored computer code instructions. When executed, the computer code instructions cause one or more processors to generate a three-dimensional (3D) model of a patient's heart based on a medical image of the patient, use the 3D model of the heart and the electrophysiological data of the patient to estimate one or more mechanical characteristics for moving the patient's heart, use the 3D model and the one or more mechanical characteristics to generate a simulated motion pattern of the patient's heart through the cardiac cycle, identify a region of interest (ROI) of the patient's heart that receives radiation, and use the simulated motion pattern of the patient's heart to determine the position of the ROI at a predetermined time point within the cardiac cycle.

Brief Description of the Drawings

[0022]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

[0023] Some or all of the figures are schematic representations for illustrative purposes. The above information and the following detailed description include examples that illustrate various aspects and embodiments, and provide an overview or gist for understanding the nature and features of the aspects and embodiments according to the claims. The figures provide further understanding as illustrations of various aspects and embodiments, are incorporated herein, and constitute a part thereof.

Embodiments for Carrying Out the Invention

[0024] Various concepts and embodiments related to methods, devices, and systems for predicting the position of a heart region in the planning of cardiac radiation therapy ablation are described in more detail below. The various concepts described above and in more detail below can be implemented in any of several ways, and the concepts described are not limited to any particular implementation manner. Specific embodiments and application examples are provided primarily for illustrative purposes.

[0025] Cardiac radiation ablation potentially holds the promise of being a safe and effective ablation strategy compared to catheter-based ablation, mainly from the perspectives of its non-invasive nature and the potential ability to target the entire myocardial layer. However, to realize this potential, various challenges need to be overcome. These challenges mainly stem from the stringent requirements regarding radiation accuracy. The heart consists of multiple structures at risk, including coronary arteries and valves. These structures should be shielded from radiation (or receive relatively low radiation) to avoid permanent and significant damage to the heart. On the other hand, the treatment aims to apply a sufficiently high radiation dose to the abnormal region of the heart to destroy or at least alter the characteristics (e.g., electrophysiological properties) of the abnormal region. This balance makes radiation therapy, especially in the case of the heart, a particularly laborious and complex task.

[0026] During radiation treatment planning, various parameters of the external radiation beam are determined to achieve the required radiation dose distribution. These parameters include, for example, the angle and intensity of the radiation beam. This external beam parameter depends on the size, shape, and position of the target region during radiation exposure, the geometric shape and properties of the surrounding or intervening tissues, and the prescribed dose. However, the heart is a continuously moving organ, and radiation is applied while the heart is in motion. Moreover, the motion of various regions of the heart, including the target region, is much more complex than the motion of other organs, such as the brain and spine within it, for which radiation therapy has been shown to be an effective option. In addition, radiation therapy has the potential to cause toxicity to healthy heart tissue. The target region representing the abnormal region to be irradiated is also referred to here as the region of interest (ROI).

[0027] The technical problems associated with cardiac radiation ablation relate to the difficulty of accurately targeting the region of interest and the challenge of determining the optimal radiation level to maximize the success of ablation while minimizing toxicity. In the present disclosure, targeting the region of interest is addressed by the systems, methods, and devices described herein for accurately predicting the position of the target region through at least a portion of the cardiac cycle. The determined position of the ROI can be used during radiation treatment planning to ensure accurate targeting of the ROI. In the case of existing techniques, the motion of the heart is not accurately estimated. As a result, an overestimated target volume has been used exclusively to account for the uncertainty in the position of the target volume (or ROI) at a given point in the cardiac cycle.

[0028] FIG. 1 according to an embodiment shows a computer environment 100 as an example for planning cardiac radiation therapy. Briefly, the computer environment 100 can include a cardiac radiation treatment planning system 102, a region of interest (ROI) positioning system 104, a database 106, and / or a communication network 108. The cardiac radiation treatment planning system 102 can include an imaging device 110, an electrophysiology system 114, and / or one or more computing devices 112. The ROI positioning system 104 can include one or more computing devices such as a computing device 116a and a computing device 116b. These are also referred to herein as computing devices 116, individually or collectively. The computing device 116 is configured to predict the position of the ROI. The cardiac radiation treatment planning system 102, the ROI positioning system 104, and the database 106 are communicatively connected to each other via the communication network 108.

[0029] The communication network 108 can include a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), the Internet, a cellular network, other types of networks, or combinations thereof. Network 108 can include both wired and wireless communications that comply with one or more standards and / or utilize one or more transmission media. Communication through network 108 can be performed according to various communication protocols such as TCP / IP (Transmission Control Protocol and Internet Protocol), UDP (User Datagram Protocol), IEEE communication protocols, etc.

[0030] The cardiac radiotherapy planning system 102 can include one or more imaging devices 110, an electrophysiology system 114, and one or more computing devices 112. The imaging device 110 can include, among others, a Computed Tomography (CT) scanner, a Magnetic Resonance (MR) scanner, a Positron Emission Tomography (PET) scanner, or combinations thereof. The imaging device 110 can acquire medical images of a patient's heart through at least a part of the cardiac cycle. In some embodiments, the imaging device 110 can acquire a series of images representing the motion or deformation of the heart through the cardiac cycle or a part thereof. The acquired medical images can include CT images, Computed Tomography Angiography (CTA) images, MR images, PET images, other types of medical images, or combinations thereof.

[0031] The electrophysiology system 114 is configured to perform an electrophysiological examination of a patient, for example, to evaluate the electrical system of the heart and diagnose abnormal heartbeats or arrhythmias. The electrophysiology system 114 can include one or more catheters, a plurality of wire electrodes, and a computing device connected to the wire electrodes to record electrical signals. A physician inserts a catheter into a vein in the patient's groin and then inserts wire electrodes into the patient's heart through the catheter and the vein. The natural electrical pulses of the heart are transmitted through the wire electrodes and recorded by the computing device of the electrophysiology system 112. In some embodiments, the electrophysiology system 114 can include multiple electrocardiogram (ECG) electrodes arranged on the surface of the patient's body (e.g., the chest) using a multi-electrode vest. The natural electrical pulses of the heart are transmitted through the wire electrodes and recorded by the computing device of the electrophysiology system 114. The computing device of the electrophysiology system 114 can transmit electrical signals through the electrodes to attempt to stimulate the heart tissue to produce an abnormal heart rhythm.

[0032] The computing device 112 can receive medical images from the imaging device 110 and receive electrophysiological examination data from the electrophysiology system 114. The computing device 112 can also acquire other medical data of the patient, such as electrocardiogram (ECG) data, blood pressure data, and / or other patient data. The computing device 112 can be configured to activate or execute a radiation simulation as part of a radiation treatment plan. A radiation treatment planner can use the computing device 112 to simulate one or more sets of radiation treatment parameters and determine which set of parameters will result in the required radiation dose distribution. The computing device 112 can also send the acquired patient data, such as medical images and electrophysiological examination data, to the database 106.

[0033] The ROI positioning system 104 (or each computing device 116) is configured to use the acquired medical images and electrophysiological examination data of the patient to estimate the real movement pattern of the heart or ROI that will reflect the dynamic position of the ROI through at least a part of the cardiac cycle. In estimating the movement pattern of the heart or ROI, the ROI positioning system 104 estimates and uses mechanical characteristics such as the contractile / pressure and relaxation / pressure of the heart that move the heart during the cardiac cycle or a part thereof. The ROI positioning system 104 (or each computing device 116) can generate a simulation model that mimics the movement pattern of the heart and ROI through at least a part of the cardiac cycle. The functional characteristics of the ROI positioning system 104 (or each computing device 116) will be detailed below in relation to FIGS. 3 to 6B.

[0034] In some embodiments, one or more computing devices 116 are configured to execute computer instructions to perform any of the methods described herein or each operation of the method. One or more computing devices 116 can generate and display an electronic platform for displaying information indicative of or related to the movement pattern of the heart and / or ROI. The electronic platform can include a graphical user interface (GUI) through which input data is received and / or the predicted movement pattern and / or position of the heart or ROI is displayed. Examples of electronic platforms generated and managed by one or more computing devices 106 can be web-based applications or websites configured to be displayed on various electronic devices such as mobile devices, tablets, personal computers, and the like.

[0035] FIG. 1 shows a network-based example, but it should be noted that the methods described herein can also be implemented by a single computing device that receives a patient's medical images and electrophysiological data and predicts the movement pattern and / or dynamic position of the ROI according to the methods described herein. The computer environment 100 is not necessarily limited to the components described herein, and may include additional or alternative components not shown for the sake of brevity, and such components should also be considered within the scope of the embodiments described herein. By way of example, the computer environment 100 may include additional or alternative databases, for example, within a heart radiotherapy planning system 102 or within an ROI positioning system 104. Also, the number of computing devices included in the heart radiotherapy planning system 102 or the ROI positioning system 104 may vary according to various embodiments.

[0036] Referring to FIG. 2 according to an example, a block diagram showing an example of the system architecture of a computing system 200 that can be used to execute the methods described herein is illustrated. The computing system 200 can include a computing device 202. The computing device 202 can exemplify any example of the device 112 and / or the device 116 in FIG. 1. By way of illustration and not limitation, the computing device 202 can include a computed tomography (CT) scanner, a medical linear accelerator, a desktop, a laptop, a hardware computer server, a workstation, a personal digital assistant, a mobile computing device, a smartphone, a tablet, or other types of computing devices. The computing device 202 can include one or more processors 204 that execute computer code instructions, a memory 206, and a bus 208 that communicatively connects the processor 204 and the memory 206.

[0037] One or more processors 204 can include a microprocessor, general-purpose processor, multi-core processor, digital signal processor (DSP), or field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), or other types of processors. The one or more processors 204 can be communicatively coupled to a bus 208 for processing information. Memory 206 can include a main memory device 210, such as a random access memory (RAM) or other dynamic storage device, connected to the bus 208 for storing information and instructions to be executed by the processor 204. The main memory device 210 can be used to store temporary variables or other intermediate information during execution of instructions (e.g., related to the methods described herein, such as method 400) by the processor 204. The computing device 202 can include a read-only memory (ROM) 212 or other static storage device connected to the bus 208 for storing static information and instructions for the processor 204. For example, the ROM 212 can store, for example, medical images of a patient received as an input. The ROM 212 can store computer code instructions related to or representative of the methods described herein. A storage device 214, such as a solid-state device, magnetic disk, or optical disk, can be connected to the bus 208 for storing information and / or instructions (or providing them as an input).

[0038] Computing device 202 may be communicatively connected to or include input device 216 and / or output device 218. Computing device 202 may be connected to output device 218 via bus 208. Output device 218 may include a display device such as a liquid crystal display (LCD), thin film transistor LCD (TFT), organic light emitting diode (OLED) display, LED display, electronic paper display, plasma display panel (PDP), or other display for displaying information to a user. Output device 218 may include a communication interface for communicating information to other external devices. Input device 216, such as a keyboard with alphanumeric and other keys, may be connected to bus 208 to communicate information and command selections to processor 204. In another example, input device 216 may be incorporated within a display device such as a touch screen display. Input device 216 may include a cursor controller such as a mouse, trackball, or cursor direction keys to communicate direction information and command selections to processor 204 and control cursor movement on the display device.

[0039] According to various embodiments, the methods or operations (steps) described herein may be implemented as an array of computer code instructions executed by a processor 204 of a computing system 200. The array of computer code instructions can be read from another computer-readable medium, such as a ROM 212 or a storage device 214, into a main memory device 210. Execution of the array of computer code instructions stored in the main memory device 210 can cause the computing system 200 to execute the methods or each operation of the methods described herein. In some embodiments, one or more processors 204 configured as a multiprocessor may be used to execute computer code instructions representing specific examples of the methods or processes described herein. In some other embodiments, a hardwired circuit may be used instead of or in combination with software instructions to implement specific examples of the methods or each operation described herein. Generally, embodiments are not limited to any particular combination of hardware circuitry and software. The functions described herein may be performed by other types of digital electronic circuitry, or by computer software, firmware, hardware, or combinations thereof.

[0040] Referring to FIG. 3 according to the embodiment, a block diagram of an ROI positioning system 104 for predicting the position of a target heart region is shown. The ROI positioning system 104 according to the embodiment is a system for accurately predicting the position of a target heart region. Generally, the ROI positioning system 104 can include a geometry model generator 302, a motion pattern estimator 304, a mechanical property estimator 306, a motion pattern simulator 308, and a motion pattern comparator 310. The ROI positioning system 104 includes or is connected to a database 106. The database 106 can include image data 312, electrophysiological data 314, and / or other patient data 316. The image data 312 can include CT images, CTA images, and / or other medical images of the patient. The electrophysiological data 314 can include electrophysiological examination data of the patient representing the electrical activity of the patient's heart through at least one cardiac cycle or a part thereof. The other patient data 316 can include blood pressure data, ECG data, medical history data, demographic data, or a combination thereof.

[0041] Each of the components 302, 304, 306, 308, and / or 310 can be implemented as a software component, a hardware component, a firmware component, or a combination of software, firmware, and / or hardware. For example, any of these components can be implemented as computer code instructions executed by one or more processors, such as processor 204, to perform respective functional steps or processes. Any of the components 302, 304, 306, 308, and / or 310 can be implemented as a digital circuit. The functional steps or processes associated with each of these components will be detailed below in relation to FIG. 4.

[0042] FIG. 4 according to an embodiment shows a flowchart for explaining an embodiment of a method 400 for predicting the position of a target heart region in cardiac radiation therapy ablation. Briefly, method 400 can include generating a geometric model of a patient's heart based on medical images of the patient (step 402), and estimating one or more mechanical properties of the patient's heart (step 404). Method 400 can include generating a simulated motion pattern of the patient's heart through at least a part of the cardiac cycle (step 406), identifying a region of interest (ROI) of the patient's heart that receives radiation (step 408), and determining the position of the ROI at a predetermined time point within the cardiac cycle (step 410). Method 400 can be executed by one or more computing devices 116 or one or more processors thereof (e.g., processor 204).

[0043] Referring to FIGS. 1-4, method 400 includes one or more computing devices 116 or one or more processors 204 generating a geometric model of a patient's heart based on medical images of the patient (step 402). Before the cardiac ablation procedure, imaging device 110 can acquire image data 312 of the patient. Image data 312 can include cardiac gated CTA images, CT images, MR images, other types of medical images, or combinations thereof. Also, electrophysiology system 114 can record electrophysiological examination data 314 of the patient representing the electrical activity of the patient's heart. Computing device 112 can store image data 312 and electrophysiological data 314 in database 106.

[0044] A physician or other medical professional can mark or outline an ROI on one or more of the acquired medical images of a patient, for example, based on image data 312 and electrophysiological data 314. For example, the physician can manually identify or mark the boundaries of the ROI being irradiated (e.g., on the display of computing device 112). In some embodiments, computing device 112 can process the marked image to refine the boundaries of the ROI using, for example, an image segmentation algorithm, an object identification algorithm, other image processing algorithms, or combinations thereof. Computing device 112 can use the refined (or original marked) ROI boundaries to identify the same ROI in other unmarked images of the patient. In some embodiments, the physician can mark the ROI in all of the acquired medical images.

[0045] In some embodiments, the ROI can include or be one or more segments of a standardized N-segment model (where N is an integer). For example, the standardized N-segment model can include the standardized AHA 17-segment heart model. The standardized N-segment model represents a standard geometric description of the heart. The computing device 112 can identify segments, for example, based on a parametric model of the heart chambers (ventricles and atria) as described in “Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features.”, IEEE Transactions on Medical Imaging 27, no. 11 (November 2008) 1668-81. In some embodiments, other standardized geometric models of the heart can be used. The operator of the computing device 112 can identify the ROI as one or more segments of the standardized N-segment model, for example, by utilizing a user interface presented by the computing device 112.

[0046] The medical image acquired by the imaging device 110 can be a two-dimensional image. The processor 204 or the geometry model generator 302 can generate a patient-specific geometry model of the patient's heart using the medical image data 312. The patient-specific geometry model can include a three-dimensional (3D) model representing the anatomical features of the patient's heart, such as shape, size, and / or various anatomical regions. For example, the processor 204 or the geometry model generator 302 can generate a 3D mesh of the patient's heart using the patient's medical image. The processor 204 or the geometry model generator 302 can add one or more layers on top of the 3D mesh to reflect separate regions or segments of the patient's heart.

[0047] In some embodiments, the geometry model generator 302 can be incorporated within the cardiac radiotherapy planning system 102. For example, the imaging device 110 or the computing device 112 can generate a 3D model of the patient's heart and store the generated 3D model in the database 106. The processor 204 or the ROI positioning system 104 can obtain or access the generated 3D model from the database 106. In some embodiments, the processor 204 or the geometry model generator 302 can register electrophysiological data to the generated 3D model of the patient's heart. In some embodiments, the processor 204 or the geometry model generator 302 can combine electrophysiological data with the generated 3D model of one or more patients' hearts as described in U.S. Patent No. 9,463,072. The content of U.S. Patent No. 9,463,072 is hereby incorporated by reference.

[0048] The processor 204 or the motion pattern estimator 304 can use the image data 312 to determine an estimated motion pattern of a patient's heart over a cardiac cycle or a portion thereof. For example, the processor 204 or the geometry model generator 302 can generate a plurality of 3D models representing various deformed states of the patient's heart over a cardiac cycle or a portion thereof. Given a series of acquired medical images of the patient's heart, the processor 204 or the geometry model generator 302 can generate, for each acquired medical image, a corresponding 3D model representing the deformed state (or simply the state) of the heart at the time point (of the cardiac cycle) at which the medical image was acquired. The plurality of 3D models of the heart corresponding to separate time points of the cardiac cycle can be viewed as a four-dimensional (4D) model of the patient's heart having a fourth dimension representing time. The processor 204 or the motion pattern estimator 304 can track the displacements of individual sets of site points of the heart through the generated series of 3D models (or 4D model) of the patient's heart. The processor 204 or the motion pattern estimator 304 can select a set of site points in one of the generated 3D models of the patient's heart and use motion tracking techniques to track the selected set of site points through the series of 3D models. The processor 204 or the motion pattern estimator 304 can use mesh segmentation to select a set of site points. The processor 204 or the motion pattern estimator 304 can select a set of site points representing landmarks of the heart for motion tracking. In some embodiments, the processor 204 or the motion pattern estimator 304 can select a set of site points in the acquired image (or image frame) and track the selected site points through the acquired series of image frames (e.g., two-dimensional (2D) images). The processor 204 or the motion pattern estimator 304 can map a set of site points to a corresponding set of site points in a series of 3D models of the patient's heart.

[0049] In some embodiments, the processor 204 or the motion pattern estimator 304 can estimate the motion pattern of the patient's heart by estimating a displacement field based on a series of 3D models or the image voxel values of a series of acquired image frames. The processor 204 or the motion pattern estimator 304 can use deep learning techniques to estimate the displacement field, for example, as described in “Learning a Probabilistic Model for Diffeomorphic Registration.” IEEE Transactions on Medical Imaging 38, no. 9 (September 2019): 2165-76. The estimated motion pattern represents the motion of the patient's heart through a cardiac cycle or a portion thereof based on the acquired medical images of the patient.

[0050] Method 400 can include estimating one or more mechanical characteristics of a patient's heart (step 404) and generating a simulated motion pattern of the patient's heart through at least a portion of the cardiac cycle (step 406). The processor 204 or the mechanical characteristic estimator 306 can use the electrophysiological data 314 and the generated geometric (or 3D) model of the patient's heart to estimate the mechanical characteristics of the patient's heart at various points in time during (or during a portion of) the cardiac cycle. The processor 204 or the mechanical characteristic estimator 306 can further use other patient data 316 to estimate the mechanical characteristics of the patient's heart. The processor 204 or the mechanical characteristic estimator 306 can analyze the electrophysiological data 314 (and optionally other patient data 316) to extract measurements of electrical and mechanical activity in the patient's heart. Measurements of electrical activity can include measurements extracted from ECG data such as the total activation time of the left or right ventricle, QRS duration, electrical axis, QT interval duration, site-specific activation times or electrical voltage values as measured by a catheter device as part of an electroanatomical mapping. Measurements of mechanical activity can include one or more of blood pressure obtained invasively or non-invasively (e.g., via an arm cuff), mechanical strain derived from strain imaging, and displacement values derived from imaging. The processor 204 or the mechanical characteristic estimator 306 can simulate the corresponding measurements of electrical and mechanical activity and compare them with the measurements extracted from the data. The processor 204 or the mechanical characteristic estimator 306 can modify the electrical and mechanical characteristics of the patient's heart to minimize the difference between the simulated measurements of electrical and mechanical activity and the measurements based on the data.

[0051] In a second step, the processor 204 or the mechanical property estimator 306 uses the electrical properties modified in the first step to modify the mechanical properties of the patient's heart so as to minimize the difference between the simulated measurements of the mechanical activity and the measurements based on the data. Additional methods for modifying the electrical and mechanical properties of the patient's heart so as to minimize the difference between the simulated measurements of the electrical and mechanical activity and the measurements based on the data are disclosed in U.S. Patent No. 9,129,053, U.S. Patent No. 9,245,091, and U.S. Patent No. 10,733,910. The mechanical properties can include a contractile force or pressure that moves the patient's heart during systole and a relaxation (or elastic) force or pressure that moves the patient's heart during diastole. The contractile force / pressure or relaxation force / pressure at a given point in time during the cardiac cycle correlates with or depends on the electrical activity of the heart at the same point in time. In particular, the electrical activity of the heart triggers or generates the contractile force / pressure or relaxation force / pressure, which in turn moves the heart. As the electrical activity of the heart changes over time, the force / pressure that moves the heart changes.

[0052] Given the estimated force / pressure at a given point in time, the processor 204 or the motion pattern simulator 308 is configured to determine the motion generated by the estimated force / pressure at different site points or regions of the heart. In particular, given the distribution of force / pressure through the patient's heart at that point in time, the processor 204 or the motion pattern simulator 308 can calculate the displacements of various regions or segments of a 3D model of the patient's heart (e.g., the 3D model corresponding to that point in time) according to the local force or pressure. The calculated displacements can represent the movement of various regions or segments of the 3D model over a period such as the period between two consecutive 3D models or between two consecutive image frames.

[0053] Generally speaking, given a generated 3D model of a patient's heart at time point t0, the processor 204 or the motion pattern simulator 308 can calculate the displacements of various regions or fragments of the 3D model between time point t0 and time point t1 (t1 > t0) based on the estimated mechanical properties of the patient's heart at time point t0 or within the period [t0 - t1]. In some embodiments, the processor 204 or the mechanical property estimator 306 can estimate the mechanical properties at individual time points and assume that the mechanical properties are constant within the period between consecutive time points. The processor 204 or the motion pattern simulator 308 can deform the 3D model corresponding to time point t0 according to the calculated displacements and determine the simulated state (or simulated deformed state) of the patient's heart at time point t1.

[0054] In some embodiments, the mechanical property estimator 306 and the motion pattern simulator 308 can operate together in an iterative manner to estimate the mechanical properties of the heart and the simulated motion pattern. For example, the processor 204 or the mechanical property estimator 306 can estimate the mechanical properties of the patient's heart using the generated 3D model and the electrophysiological data 314, and the processor 204 or the motion pattern simulator 308 can generate the motion pattern of the patient's heart using the 3D model and the electrophysiological data 314. The processor 204 may further use other patient data 316 when estimating the mechanical properties of the patient's heart and / or when generating the motion pattern of the patient's heart. The processor 204 or the motion pattern comparator 310 can compare the estimated motion pattern generated by the motion pattern estimator 304 with the simulated motion pattern generated by the motion pattern simulator 308. If the estimated motion pattern and the simulated motion pattern are not sufficiently similar (e.g., based on one or more thresholds), the processor 204 or the mechanical property estimator 306 can adjust the estimated mechanical properties, and a new simulated motion pattern is determined by the processor 204 or the motion pattern simulator 308 based on the adjusted mechanical properties. The motion pattern comparator 310 can compare the estimated motion pattern with the new simulated motion pattern. The processor 204 can repeat these steps (e.g., adjusting the mechanical properties, updating the simulated motion pattern, and comparing the estimated motion pattern with the simulated motion pattern) until both motion patterns are sufficiently close.

[0055] When comparing the estimated motion pattern and the simulated motion pattern, the processor 204 or the motion pattern comparator 310 can select or identify one or more estimated states of the patient's heart (also referred to herein as the ground truth position or the ground truth state) based on the generated 3D model and the estimated motion pattern. Each estimated state represents the deformation and / or position state of the patient's heart determined by applying the estimated motion pattern to the generated 3D model of the patient's heart. For example, the estimated state S i,e represents the deformation and / or position state of the patient's heart determined by applying the estimated motion pattern to the generated 3D model of the patient's heart up to the time point t i (where i is an integer) of the cardiac cycle. The processor 204 or the motion pattern comparator 310 can select or identify one or more simulated states by applying the simulated motion pattern to the generated 3D model of the patient's heart. Each simulated state corresponds to one of the estimated states. For example, the simulated state S i,s and the estimated state S i,e represent the state of the patient's heart at the time point t i . Each of the estimated state and the simulated state represents the deformation of the generated 3D model. The processor 204 or the motion pattern comparator 310 can compare one or more distances between the simulated state S i,s and the estimated state S i,e . The processor 204 or the motion pattern comparator 310 can compare the point-by-point distance, the point-to-curve (also referred to as point-to-surface) distance, or the curve-to-curve (also referred to as surface-to-surface) distance between the simulated state S i,s and the estimated state S i,e with a threshold. If these one or more distances are less than the threshold, the simulated state S i,s and the estimated state S i,eIt is determined that they are sufficiently similar; otherwise, the steps of adjusting the mechanical properties, updating the simulated motion pattern, and comparing the estimated motion pattern and the simulated motion pattern are repeated in another iteration. In this iterative approach, the processor 204 can set an initial estimated value of the mechanical properties based on random guesses, literature data, and / or patient information (e.g., demographic information and / or medical information).

[0056] Referring to FIG. 5 according to the embodiment, a diagram explaining the estimated state and the simulated state of the patient's heart is shown. The 3D shape 502 represents an example of the 3D model (or geometric model) of the patient's heart generated in step 402. The 3D shape 504 represents an example of the estimated state of the patient's heart generated by applying the estimated motion pattern (e.g., up to the time point t of the cardiac cycle) to the 3D model 502. i The 3D shape 506 represents an example of the simulated state of the patient's heart generated by applying the simulated motion pattern (e.g., up to the time point t of the cardiac cycle) to the 3D model 502. The simulated state 506 is expected to converge towards the estimated state 504 after several iterations of adjusting the mechanical properties to update the simulated state. i

[0057] ​Referring to FIGS. 6A and 6B according to the embodiment, a diagram is shown that illustrates the distance between an example of an estimated state of the heart and an example of a simulated state. With respect to FIG. 6A, curve 602 is a 2D representation of the estimated state of the heart, and curve 604 is a 2D representation of the simulated state of the heart. The arrow between curve 602 and curve 604 represents the distance between the two curves. These distances can be point-by-site distances (e.g., the distance between a pair of points where each pair includes a point of the simulated state 604 and a point of the estimated state 602), point-pair surface distances, or surface-to-surface distances. The motion pattern comparator 310 compares the distance between the estimated state 602 and the simulated state 604 with a threshold value, and can determine that the two states are similar if the distance (or its maximum value) is below the threshold value, and otherwise, continue to adjust the estimated mechanical characteristics to update the simulated motion pattern until the two states are sufficiently similar. FIG. 6B shows another example of a 2D representation of the estimated state 606 and the simulated state 608. The arrow between curve 606 and curve 608 represents the distance between both states of the patient's heart.

[0058] When comparing the distance between the estimated state and the simulated state, the processor 204 or the motion pattern comparator 310 can evaluate the distance between the estimated state and the corresponding simulated state at any given point in time throughout the cardiac cycle and compare each of the evaluated distances with a threshold value. In some embodiments, the processor 204 or the motion pattern comparator 310 can average the distances over a plurality of points in time of the cardiac cycle and compare the average distance with the threshold value.

[0059] In some embodiments, the processor 204 can perform a comparison between the estimated heart state and the simulated heart state over individual periods corresponding to the time ranges between successive image frames. For two time points t1, t2 corresponding to two successive image frames F1, F2, the processor 204 or the motion pattern estimator 304 can deform the 3D model of the patient's heart corresponding to time point t1 according to the estimated motion pattern to determine the estimated state of the heart at time point t2. Then, the processor 204 can deform the 3D model of the patient's heart corresponding to time point t1 according to the simulated motion pattern to determine the simulated state of the heart at time point t2. The processor 204 can repeatedly adjust the mechanical properties of the heart and update the simulated motion pattern until the estimated state and the simulated state at time point t2 are sufficiently similar (e.g., the distance is below a threshold). In other words, the mechanical properties of the heart tissue are adjusted to minimize the distance between the estimated state and the simulated state at time point t2. The processor 204 can repeat this process for each pair of time points (t i , F i+1 ) corresponding to each pair of consecutive image frames (F i , t i+1 ). This approach results in a plurality of estimated values of the mechanical properties of the heart tissue over the cardiac cycle (e.g., a set of estimated mechanical properties for each pair of time points (t i , t i+1 ). The processor 204 can define the global optimum value as the average value or the median value.

[0060] In some embodiments, the processor 204 can use a plurality of probabilistic variations of the mechanical and electrical properties of the heart tissue initially estimated from the available measurements. The processor 204 can generate a plurality of simulated motion patterns based on the plurality of probabilistic variations of the mechanical and electrical properties of the heart tissue. The processor 204 can compare each of the plurality of simulated motion patterns with an estimated motion pattern based on the distance between the simulated state and the estimated state associated with each simulated motion pattern. The processor 204 can select a simulated motion pattern that minimizes the distance between the corresponding simulated state and the estimated state.

[0061] In some embodiments, the processor 204 or the motion pattern simulator 308 can use a machine learning model. The machine learning model can use a database of synthetically generated heart motion data generated using a 3D model of the heart, electrophysiological data 314, and other patient data 316. The database of synthetically generated heart motion data can be generated using patient-specific data (e.g., the patient's image data 312 and physiological data 314) or data from a plurality of patients. For example, the database of synthetically generated heart motion data can be generated using a set of values representing the physical (e.g., electrical and mechanical) properties of the heart tissue randomly sampled from a combination of one 3D model of the heart or a plurality of models from a plurality of patients and the data of a plurality of patients. The machine learning model or data-driven motion model can determine the position of each site point of the heart at a given time point t i+1 based on the position of the same site point at the previous time point t i and the physical properties of the heart tissue associated with that site point at time point t i+1configured to represent according to the estimated or measured positions of the same site points in. In a database of cardiac motion generated by synthesis, a plurality of examples of cardiac motion can be generated based on a simulated state of the heart using the addition of random perturbations that simulate the effects of noise. The machine learning model is configured to minimize the distance between the state of the heart generated by the machine learning model and the corresponding simulated state over a number of time points. Looking back at FIG. 3, once trained, the machine learning model can be used by the motion pattern simulator 308 instead of the simulation.

[0062] Returning to FIG. 4, the method 400 can include identifying a region of interest (ROI) of the heart of a patient receiving radiation (step 408) and determining the position of the ROI at a predetermined time point within the cardiac cycle (step 410). The processor 204 can identify the ROI in a plurality of simulated states determined by applying a final simulated motion pattern to the 3D model generated in step 402. The processor 204 can map the ROI identified or marked in the acquired image or image frame to the simulated state. The processor 204 can use an image mask to indicate the position of the ROI in each of the simulated states.

[0063] Processor 204 can provide the simulated motion pattern and / or the plurality of simulated states to the cardiac radiotherapy planning system 102 or each computing device 112. In some embodiments, the identification of the ROI within the simulated state can be performed by the computing device 112. The computing device 112 can use the simulated motion pattern or the corresponding simulated state to determine the position of the ROI at one or more time points of the cardiac cycle. One or more time points of the cardiac cycle can represent the time points at which the radiation beam should be applied to the ROI. Given the position of the ROI, the cardiac radiotherapy planning system 102 or the computing device 112 can accurately target or irradiate the ROI while avoiding the surrounding tissue or intervening tissue as much as possible.

[0064] The final simulated motion pattern (output by the ROI positioning system 104) is optimized to mimic or reproduce the real or actual motion of the patient's heart. The final simulated motion pattern is used by the cardiac radiotherapy planning system 102 or the computing device 112 to estimate the position of the ROI to be treated with radiotherapy under the conditions faced during radiotherapy treatment. In most clinical workflows, the patient is immobilized during radiotherapy treatment by applying rigid or vacuum-based fixation, abdominal compression, and / or a shoulder mask, with or without anesthesia. In some embodiments, one or more computing devices 116 or the computing device 112 can model the fixation conditions as boundary conditions incorporated into the simulated motion pattern. The boundary conditions can act as constraints on the displacement of the heart within the torso. The boundary conditions can be represented, for example, as a predetermined pressure applied to the epicardial surface or as an opposing displacement along a predetermined direction.

[0065] It goes without saying that the embodiments discussed in this specification are provided for illustrative purposes and should not be construed in a limiting sense. For example, other techniques can be used to estimate or adjust the mechanical properties of the heart. Also, other types of distances can be used to compare the simulated state with the corresponding estimated state.

[0066] Each method described in this disclosure, such as method 400 of FIG. 4, can be executed by computer code instructions stored on a computer-readable medium. When the computer code instructions are executed by one or more processors of a computing device, the computing device can be made to execute the method.

[0067] Although the present disclosure has been specifically shown and described with reference to particular embodiments, it should be understood by those of ordinary skill in the art that various changes in form and detail may be made without departing from the spirit and scope of the invention described in this disclosure.

[0068] Although this disclosure includes details of many specific embodiments, these should not be construed as limitations on the scope of any invention or of the claims, but rather as descriptions of features specific to particular embodiments of a particular invention. Certain features described herein in the context of separate embodiments can also be implemented in combination in one embodiment. Conversely, the various features described in the context of one embodiment can also be implemented separately or in any suitable sub-combination in a plurality of embodiments. Further, although features are described above as acting in certain combinations and are initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination can be directed to a sub-combination or variation of a sub-combination.

[0069] Similarly, although operations (acts, steps, procedures) are shown in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order to achieve the desired result, or that all of the illustrated operations be performed. In certain circumstances, multitasking and parallel processing may be advantageous. Further, the separation of various system components in the above-described embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the program components and systems described may generally be integrated into a single software product or packaged into multiple software products.

[0070] With respect to "or", "or" can be interpreted as inclusive such that any term described using "or" can indicate any of the single, two or more, and all of the terms so described.

[0071] The above has described particular embodiments of the subject matter. Other embodiments are within the scope of the claims. In some cases, the functions recited in the claims may be performed in a different order and still achieve the desired result. Additionally, the processes shown in the accompanying drawings do not necessarily require the particular or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.

Claims

1. A method for predicting the position of a target cardiac region in cardiac ablation, comprising: one or more processors generating a three-dimensional (3D) model of the patient's heart based on medical images of the patient; the one or more processors using the 3D model of the heart and electrophysiological data of the patient to estimate one or more mechanical properties for moving the patient's heart; the one or more processors using the 3D model and the one or more mechanical properties to generate a simulated motion pattern of the patient's heart over the cardiac cycle; the one or more processors identifying a region of interest (ROI) of the patient's heart that is to receive radiation; the one or more processors using the simulated motion pattern of the patient's heart to determine the position of the ROI at a predetermined time point within the cardiac cycle. A method comprising the above steps.

2. The method according to claim 1, wherein the one or more mechanical properties include the contractile and relaxation forces of the patient's heart.

3. The medical images include a series of image frames acquired over a period of time, and the one or more processors further determine an estimated motion pattern of the patient's heart over the cardiac cycle using the series of image frames. The method according to claim 1 or 2, further comprising the above steps.

4. Determining the estimated motion pattern includes: tracking the displacement of an individual set of site points of the heart through the series of image frames, or utilizing a machine learning model to estimate a displacement range using the series of image frames. The method according to claim 3, including the above steps.

5. using the estimated motion pattern of the patient's heart to determine one or more estimated positions of one or more site points of the patient's heart at a time point in the cardiac cycle; using the simulated motion pattern of the patient's heart to determine one or more simulation positions of the one or more site points of the patient's heart at the time point in the cardiac cycle; calculating one or more site-point-specific distances between the one or more simulation positions and the one or more estimated positions; updating the one or more mechanical properties of the patient's heart when it is determined that the one or more site-point-specific distances exceed a threshold. Updating the simulated motion pattern of the patient's heart based on the one or more updated mechanical properties The method according to claim 3 or 4, comprising

6. The step of determining the one or more simulation positions, the step of calculating the one or more site-point distances, the step of updating the one or more mechanical properties, and the step of updating the simulated motion pattern of the patient's heart, repeating until the one or more site-point distances are below the threshold The method according to claim 5, comprising

7. Determining the one or more estimated positions According to the estimated motion pattern of the heart of the patient, at time t ０ deform the 3D model of the heart corresponding to time t to determine the estimated 3D model of the heart corresponding to time t １ ​ The estimated 3D model represents the estimated state of the heart at the time t １ and indicates the estimated state of the heart at that time at the time point t １ identifying the one or more estimated positions in the estimated 3D model of the heart corresponding to Determining the one or more simulation positions Deforming the 3D model of the heart corresponding to the time point t according to the simulated motion pattern of the heart of the patient ０ and determining the simulated 3D model of the heart corresponding to the time point t １ ​ The simulated 3D model shows the simulated state of the heart at the time point t １ and indicates the simulated state of the heart at that time point t the time point t １ identifying the one or more simulation positions in the simulated 3D model of the heart corresponding to １ , including The method according to claim 5 or 6

8. For a plurality of time point pairs (t ０ , t １ ) corresponding to pairs of consecutive image frames in the series of image frames, determining the one or more estimated positions and determining the one or more simulation positions; calculating, for the plurality of time point pairs (t ０ , t １ ), a plurality of distances between the simulation positions and the corresponding estimated positions for each of the sites; and repeating the step of updating the one or more mechanical properties of the heart of the patient when it is determined that the plurality of distances for each of the sites exceeds the threshold. The method according to claim 7, comprising

9. Updating the one or more mechanical properties of the patient's heart Generating a plurality of second simulated motion patterns of the heart corresponding to various changes in the one or more mechanical properties and various changes in the electrical properties of the heart For each of the second simulated motion patterns, determining one or more corresponding simulation positions of one or more site points of the patient's heart at the time point of the cardiac cycle For each of the second simulated motion patterns, calculating one or more corresponding site-point distances between the one or more corresponding simulation positions and the one or more estimated positions Selecting a second simulated motion pattern from the plurality of second simulated motion patterns based on the one or more corresponding site-point distances Updating the one or more mechanical properties according to the changes in the one or more mechanical properties corresponding to the selected second simulated motion pattern, including The method according to any one of claims 5 to 8

10. The method according to any one of claims 1 to 9, wherein the ROI includes one or more segments of a standardized N-segment model (N is an integer)

11. Modeling the fixed conditions applied to the patient during cardiac ablation as boundary conditions incorporated into the simulated motion pattern of the patient's heart The method according to any one of claims 1 to 10, further comprising

12. A system for predicting the location of the target heart region of cardiac ablation One or more processors and a memory storing computer code instructions, which, when executed, cause the one or more processors to generate a three-dimensional (3D) model of the patient's heart based on medical images of the patient, estimate one or more mechanical properties for moving the patient's heart using the 3D model of the heart and electrophysiological data of the patient, generate a simulated motion pattern of the patient's heart through the cardiac cycle using the 3D model and the one or more mechanical properties, identify a region of interest (ROI) of the patient's heart that is to receive radiation, determine the position of the ROI at a predetermined time point within the cardiac cycle using the simulated motion pattern of the patient's heart, a system. **Claim 13** The system of claim 12, wherein the one or more mechanical properties include a contractile force and a relaxation force of the patient's heart. **Claim 14** The medical images include a series of image frames acquired over a period of time, and the one or more processors are further configured to determine an estimated motion pattern of the patient's heart through the cardiac cycle using the series of image frames. The system of claim 12 or 13. **Claim 15** When determining the estimated motion pattern, the one or more processors track the displacement of an individual set of site points of the heart through the series of image frames or are configured to utilize a machine learning model to estimate a displacement range using the series of image frames. The system of claim 14. **Claim 16** The one or more processors determine one or more estimated positions of one or more site points of the patient's heart at a time point in the cardiac cycle using the estimated motion pattern of the patient's heart, determine one or more simulation positions of the one or more site points of the patient's heart at the time point in the cardiac cycle using the simulated motion pattern of the patient's heart, calculate one or more site-point-specific distances between the one or more simulation positions and the one or more estimated positions, and update the one or more mechanical properties of the patient's heart when it is determined that the one or more site-point-specific distances exceed a threshold. configured to update the simulated motion pattern of the patient's heart based on the one or more updated mechanical characteristics The system according to claim 14 or 15. **Claim 17** The one or more processors configured to repeat, until the one or more site-by-site distances are below the threshold, determining the one or more simulation positions, calculating the one or more site-by-site distances, updating the one or more mechanical characteristics, and updating the simulated motion pattern of the patient's heart The system according to claim 16. **Claim 18** When determining the one or more estimated positions, the one or more processors According to the estimated motion pattern of the heart of the patient, at time t ０ deform the 3D model of the heart corresponding to time t to determine the estimated 3D model of the heart corresponding to time t １ ​ The estimated 3D model represents the estimated state of the heart at the time point t １ and indicates the estimated state of the heart at that time. the time point t １ configured to identify the one or more estimated positions in the estimated 3D model of the heart corresponding to When determining the one or more simulation positions, the one or more processors According to the simulated motion pattern of the heart of the patient, deform the 3D model of the heart corresponding to the time point t ０ to determine the simulated 3D model of the heart corresponding to the time point t １ ​ The simulated 3D model shows the simulated state of the heart at the time point t １ and indicates the simulated state of the heart at that time point t the time point t １ configured to identify the one or more simulation positions in the simulated 3D model of the heart corresponding to The system according to claim 17. **Claim 19** The one or more processors For a plurality of time point pairs (t ０ , t １ ) corresponding to pairs of consecutive image frames in the series of image frames, repeating the steps of determining the one or more estimated positions and determining the one or more simulation positions, Through the plurality of time point pairs (t ０ , t １ ), calculate the distances between the simulation position and the corresponding estimated position for each of a plurality of site points, configured to update the one or more mechanical characteristics of the patient's heart when it is determined that the plurality of site-by-site distances exceed the threshold The system according to claim 18. **Claim 20** When updating the one or more mechanical characteristics of the patient's heart, the one or more processors generate a plurality of second simulated motion patterns of the heart corresponding to various changes in the one or more mechanical characteristics and various changes in the electrical characteristics of the heart, for each of the second simulated motion patterns, determine one or more corresponding simulation positions of the one or more sites of the patient's heart at the time point of the cardiac cycle, for each of the second simulated motion patterns, calculate one or more corresponding site-by-site distances between the one or more corresponding simulation positions and the one or more estimated positions, select a second simulated motion pattern from the plurality of second simulated motion patterns based on the one or more corresponding site-by-site distances, and update the one or more mechanical characteristics according to the changes in the one or more mechanical characteristics corresponding to the selected second simulated motion pattern The system according to any one of claims 17 to 19. **Claim 21** The ROI includes one or more segments of a standardized N-segment model (N is an integer), the system according to any one of claims 12 to 20. **Claim 22** The one or more processors Further configured to model the fixation conditions applied to the patient during cardiac ablation treatment as boundary conditions incorporated into the simulated motion pattern of the heart of the patient. The system according to any one of claims 12 to 21. **Claim 23** A computer-readable medium comprising stored computer code instructions, which, when executed, cause one or more processors to: generate a three-dimensional (3D) model of the heart of the patient based on a medical image of the patient; estimate one or more mechanical properties for moving the heart of the patient using the 3D model of the heart and electrophysiological data of the patient; generate a simulated motion pattern of the heart of the patient through the cardiac cycle using the 3D model and the one or more mechanical properties; identify a region of interest (ROI) of the heart of the patient that is to receive radiation; determine the position of the ROI at a predetermined point in time within the cardiac cycle using the simulated motion pattern of the heart of the patient; A computer-readable medium.

Images