Digital Twin of the Atrium for Patients with Atrial Fibrillation

A machine learning-based digital twin system generates personalized models of atrial fibrillation patients' hearts, addressing inaccuracies in current simulations by providing precise ablation guidance through real-time electrical activity analysis.

JP2024540875APending Publication Date: 2024-11-06BIOSENSE WEBSTER (ISRAEL) LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2024522303
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-10-10
Filing Date
2022-10-13
Publication Date
2024-11-06

AI Technical Summary

Technical Problem

Current digital simulations for cardiac ablation procedures in atrial fibrillation patients are inaccurate due to their reliance on standard anatomical information and assumptions about electrical conduction, failing to account for patient-specific variations and scar tissue.

Method used

A generation engine utilizing machine learning and artificial intelligence to generate personalized digital twins of the atria based on real-time electrical activity and conduction velocity vectors, providing precise ablation guidance by continuously updating during the procedure.

Benefits of technology

The digital twin offers highly accurate guidance for cardiac physicians, enabling effective ablation procedures by simulating patient-specific electrical activity and suggesting optimal ablation sites, reducing the need for remapping and improving treatment outcomes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024540875000001_ABST
    Figure 2024540875000001_ABST
Patent Text Reader

Abstract

An ablation procedure guidance method is provided herein. The ablation procedure guidance method is implemented by a generation engine running on a processor. The ablation procedure guidance method includes receiving inputs including images and conduction velocity vector estimates, and generating a digital twin of the anatomical structure utilizing the images and the conduction velocity vector estimates. The ablation procedure guidance method also includes presenting, via a user interface of the generation engine, the digital twin to provide precise ablation guidance of the anatomical structure and to provide electrophysiology information of the anatomical structure.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to signal processing, and more particularly to generating a digital twin of the atrium for atrial fibrillation (aFib) patients. [Background technology]

[0002] Cardiac arrhythmias, such as aFib, occur when regions of cardiac tissue do not follow the synchronous beating cycle associated with normal conductive tissue. In general, cardiac arrhythmias can be treated with medication, ablation, or other tissue-destructive means. However, with advanced aFib, knowing the optimal location for ablation becomes very difficult. For example, aFib may vary from patient to patient, and atrial tissue may contain scars and / or triggers, so the optimal ablation location may need to be determined on a case-by-case basis.

[0003] Currently, to aid in determining ablation locations, ablation procedures construct and utilize digital simulations of the heart. These digital simulations are based on standard anatomical information and assume standard electrical conduction. Thus, these simulations have been found to be insufficiently accurate and do not facilitate effective guidance. Summary of the Invention [Problem to be solved by the invention]

[0004] Therefore, there is a need for improved ablation location techniques. [Means for solving the problem]

[0005] According to an exemplary embodiment, an ablation procedure guidance method is provided herein. The ablation procedure guidance method is implemented by a generation engine executing on at least one processor. The ablation procedure guidance method includes receiving, by the generation engine, one or more inputs including one or more images and a conduction velocity vector estimate. The ablation procedure guidance method also includes generating, by the generation engine, a digital twin of the anatomical structure utilizing the one or more images and the conduction velocity vector estimate. The ablation procedure guidance method also includes presenting, via a user interface of the generation engine, the digital twin to provide precise ablation guidance of the anatomical structure and to provide electrophysiology information of the anatomical structure.

[0006] In accordance with one or more embodiments, the above-described ablation procedure guidance method embodiments may be implemented as devices, systems, and / or computer program products. [Brief description of the drawings]

[0007] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, in which like reference numbers indicate similar elements and in which: [Figure 1] 1 illustrates a diagram of an example system in which one or more features of the subject matter of this disclosure can be implemented, in accordance with one or more embodiments. [Diagram 2] FIG. 1 illustrates a block diagram of an exemplary system for generating a digital twin of an atrial chamber of an aFib patient in accordance with one or more embodiments. [Diagram 3] 1 illustrates a method according to one or more embodiments. [Figure 4] 1 illustrates a graphical depiction of an artificial intelligence system, according to one or more embodiments. [Diagram 5] FIG. 1 illustrates a block diagram of an example neural network and a method implemented within the neural network, according to one or more embodiments. [Figure 6]1 illustrates a method according to one or more embodiments. [Figure 7] 1 illustrates an interface in accordance with one or more embodiments. [Figure 8] 1 illustrates an interface in accordance with one or more embodiments. [Figure 9] 1 illustrates an interface in accordance with one or more embodiments. [Figure 10] 1 illustrates an interface in accordance with one or more embodiments. [Figure 11] 1 illustrates an interface in accordance with one or more embodiments. [Figure 12] 1 illustrates a graph in accordance with one or more embodiments. [Figure 13] 1 illustrates an interface in accordance with one or more embodiments. [Figure 14] 1 illustrates a graph in accordance with one or more embodiments. [Figure 15] 1 illustrates an example interface according to one or more embodiments. [Figure 16] 1 illustrates a method according to one or more embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Disclosed herein are signal processing systems, devices, and methods. More particularly, disclosed herein are signal processing operations that generate a digital twin of the atrium for atrial fibrillation (aFib) patients. The signal processing systems, devices, and methods can incorporate machine learning (ML) and / or artificial intelligence (AI) to generate and analyze the digital twin and its associated data to provide improved ablation location techniques.

[0009] In accordance with one or more embodiments, the generation engine may generally correspond to a signal processing system, apparatus, and method, and may include one or more ML / AI algorithms for generating and analyzing a digital twin. In this regard, the generation engine is a processor-executable code or software that is necessarily rooted in the process operations of a medical device equipment and its hardware. For ease of explanation, the generation engine is described herein with respect to mapping the heart (e.g., its atrium). However, any anatomical structure, body part, organ, or portion thereof may be targeted for mapping by the generation engine described herein.

[0010] In general, the generation engine generates / creates a digital twin of the atrium that serves as a guiding tool for ablation of aFib patients. In particular, the digital twin is more robust than current digital simulations that do not have personalized cardiac electrical activity. In other words, the digital simulation assumes normal electrical conduction and assumes that arrhythmias repeat themselves, which is not a symptom of aFib. In this regard, for example, the generation engine measures and utilizes the electrical activity of the aFib patient's heart (e.g., taking into account information about arrhythmia triggers and atrial wall material) to generate and create the digital twin. As a further example, the generation engine utilizes a conduction velocity (CV) vector (e.g., a direct cardiac measurement) as an input to generate and create the digital twin. The CV vector can be based on real-time data, as described herein. The CV vector is based on local signal progression. Thus, the generation engine can utilize a far field reduction algorithm to remove far fields (i.e., signals based on ventricular activation) before calculating the CV vector. Additionally, during the ablation procedure, the generation engine can continuously update the digital twin and suggest optimal ablation and / or additional procedures based on the digital twin.

[0011] As a result of the operation of the generative engine, the digital twin is highly accurate as compared to current digital simulations. Thus, one or more advantages, technical effects, and / or benefits of the generative engine may include using the digital twin to provide effective guidance to cardiac physicians and medical personnel during an ablation procedure. Thus, the generative engine utilizes and modifies, among other things, medical device equipment to enable / implement signal processing operations that are not currently available to or currently not performed by cardiac physicians and medical personnel.

[0012] 1 is a diagram of an example system (e.g., a medical device instrument) in which one or more features of the subject matter herein may be implemented in accordance with one or more embodiments, shown as system 10. All or a portion of system 10 may be used for collecting information (e.g., biometric data and / or training data sets) and / or implementing ML / AI algorithms (e.g., generation engine 101) as described herein. The system 10 includes a recorder 11, a heart 12, a catheter 14, a model or anatomical map 20, an electrogram 21, a spline 22, a patient 23, a physician 24 (or medical professional or clinician), a location pad 25, an electrode 26, a display device 27, a distal tip 28, a sensor 29, a coil 32, a patient interface unit (PIU) 30, an electrode skin patch 38, an ablation energy generator 50, and a workstation 55 (including at least one processor 61 and at least one memory 62 that stores a generation engine 101), as shown. It should be noted that each element and / or item of the system 10 is representative of one or more of that element and / or item. The example system 10 shown in FIG. 1 can be modified to implement the embodiments disclosed herein. The embodiments of the present disclosure can be similarly applied using other system components and configurations. Furthermore, system 10 may include additional components, such as elements for sensing electrical activity, wired or wireless connectors, processing units, and display devices.

[0013] The system 10 includes multiple catheters 14 that are percutaneously inserted by a physician 24 through the vascular system of a patient 23 into a chamber or vasculature of the heart 12. Typically, a delivery sheath catheter (one example of a catheter 14) is inserted into the left or right atrium near a desired location in the heart 12. The multiple catheters 14 can then be inserted into the delivery sheath catheter to reach the desired location. The multiple catheters 14 may include catheters dedicated to sensing Intracardiac Electrogram (IEGM) signals, catheters dedicated to ablation, and / or catheters dedicated to both sensing and ablation. An exemplary catheter 14 configured to sense IEGMs is shown herein. The physician 24 brings a distal tip 28 of the catheter 14 into contact with the heart wall to sense a target site of the heart 12. For ablation, the physician 24 similarly brings a distal end of an ablation catheter to a target site for ablation.

[0014] Catheter 14 is an exemplary catheter that includes one, and preferably multiple, electrodes 26, optionally distributed across multiple splines 22 at distal tip 28, and configured to sense IEGM signals. Catheter 14 may further include a sensor 29 embedded in or near distal tip 28 for tracking the position and orientation of distal tip 28. Optionally and preferably, position sensor 29 is a magnetic-based position sensor including three magnetic coils for sensing three-dimensional (3D) position and orientation.

[0015] The sensor 29 (e.g., a position-based or magnetic-based position sensor) may operate in conjunction with a location pad 25 that includes a plurality of magnetic coils 32 configured to generate a magnetic field within a predetermined working volume. The real-time position of the distal end 28 of the catheter 14 may be tracked based on the magnetic field generated by the location pad 25 and sensed by the sensor 29. Details of magnetic-based position sensing technology are described in U.S. Patent Nos. 5,5391,199; 5,443,489; 5,558,091; 6,172,499; 6,239,724; 6,332,089; 6,484,118; 6,618,612; 6,690,963; 6,788,967; and 6,892,091.

[0016] The system 10 includes one or more electrode patches 38 placed on the patient 23 for skin contact to establish a position reference for the location pads 25 and impedance-based tracking of the electrodes 26. For impedance-based tracking, a current is directed to the electrodes 26 and sensed at the patches 38, so that the location of each electrode can be triangulated via the patches 38. Details of impedance-based location tracking technology are described in U.S. Patent Nos. 7,536,218, 7,756,576, 7,848,787, 7,869,865, and 8,456,182, each of which is incorporated herein by reference.

[0017] Recorder 11 displays electrograms 21 captured by electrodes 18 (e.g., surface electrocardiogram (ECG) electrodes) and IEGMs captured by electrodes 26 of catheter 14. Recorder 11 may include pacing capability for pacing the cardiac rhythm and / or may be electrically connected to a stand-alone pacer.

[0018] The system 10 may include an ablation energy generator 50 adapted to deliver ablation energy to one or more electrodes 26 at the distal tip 28 of the catheter 14 configured for ablation. The energy generated by the ablation energy generator 50 may include, but is not limited to, radio frequency (RF) energy or pulsed field ablation (PFA) energy, including monopolar or bipolar high voltage DC pulses such as may be used to effect irreversible electroporation (IRE), or combinations thereof.

[0019] The patient interface unit (PIU) 30 is an interface configured to establish electrical communication between the catheters, the electrophysiological equipment, a power source, and a workstation 55 that controls the operation of the system 10. The electrophysiological equipment of the system 10 may include, for example, a number of catheters 14, location pads 25, body surface ECG electrodes 18, electrode patches 38, an ablation energy generator 50, and a recorder 11. Optionally and preferably, the PIU 30 additionally includes processing capabilities for implementing real-time calculations of the catheter positions and performing ECG calculations.

[0020] The workstation 55 includes a processor unit 61 having a memory 62, a memory 62 or storage device loaded with suitable operating software, and user interface functionality, as described further herein. The workstation 55 may optionally provide multiple functions, including: (1) modeling the endocardial anatomical structures in three dimensions (3D) and rendering a model or anatomical map 20 for display on the display device 27; (2) displaying activation sequences (or other data) compiled from recorded electrograms 21 with representative visual indicators or images superimposed on the rendered anatomical map 20 on the display device 27; (3) displaying real-time positions and orientations of multiple catheters within the cardiac chambers; and (5) displaying sites of interest, such as locations where ablation energy has been applied, on the display device 27. One commercially available product embodying elements of the system 10 is available as the CARTO™ 3 system, commercially available from Biosense Webster, Inc., 31A Technology Drive, Irvine, Calif., 92618.

[0021] The system 10 can be utilized to detect, diagnose, and / or treat cardiac conditions (e.g., using the generation engine 101). Cardiac diseases, such as cardiac arrhythmias, persist as common and dangerous medical disorders, especially in the geriatric population. For example, the system 10 can be part of a surgical system (e.g., a CARTO® system sold by Biosense Webster) configured to obtain biometric data (e.g., anatomical and electrical measurements of a patient's organs, such as the heart 12, as described herein) and perform cardiac ablation procedures. More specifically, the treatment of cardiac diseases, such as cardiac arrhythmias, often requires obtaining detailed mapping of cardiac tissue, chambers, veins, arteries, and / or electrical pathways. For example, as a prerequisite for successful catheter ablation (as described herein), the source of the cardiac arrhythmia may be precisely localized in the chambers of the heart 12. Such localization may be performed by electrophysiological studies during which spatially resolved electrical potentials are detected by a mapping catheter (e.g., catheter 14) introduced into the chambers of the heart 12. This electrophysiological study, also called electroanatomical mapping, provides 3D mapping data that can be displayed on the display device 27. Often, the mapping and therapy functions (e.g., ablation) are provided by a single catheter or a group of catheters, with the mapping catheter also simultaneously acting as the therapy (e.g., ablation) catheter.

[0022] In a patient (e.g., patient 23) having normal sinus rhythm (NSR), the heart (e.g., heart 12), including the atria, ventricles, and excitable conductive tissue, is electrically excited to beat in a synchronous, patterned manner, which can be detected, such as in intracardiac electrocardiogram (IC ECG) data.

[0023] According to one or more embodiments, in patients (e.g., patient 23) with cardiac arrhythmias (e.g., atrial fibrillation or aFib), the abnormal regions of cardiac tissue do not follow the synchronous beating cycle associated with normal conductive tissue, in contrast to patients with NSR. In contrast, the abnormal regions of cardiac tissue conduct abnormally to adjacent tissue, which disrupts the cardiac cycle and results in an asynchronous cardiac rhythm. It should be noted that this asynchronous cardiac rhythm can also be detected as IC ECG data. Such abnormal conduction has previously been known to occur in various regions of the heart 12, such as, for example, in the region of the sinoatrial (SA) node along the conduction pathway of the atrioventricular (AV) node, or in the myocardial tissue forming the walls of the ventricles and atria. Other conditions, such as atrial flutter, exist in which abnormal conductive tissue patterns lead to reentry pathways, causing the heart chambers to beat in a regular pattern that can be multiples of the sinus rhythm.

[0024] As an example, to assist system 10 in detecting, diagnosing, and / or treating cardiac disease, physician 24 may guide catheter 14 into heart 12 of patient 23 lying in bed. For example, physician 24 may insert a shaft through a sheath while manipulating the distal end of the shaft using a manipulator near the proximal end of catheter 14 and / or a deflection from the sheath. According to one or more embodiments, catheter 14 may be attached to the distal end of the shaft. Catheter 14 may be inserted through the sheath in a collapsed state and then expanded within heart 12.

[0025] In general, electrical activity at a point within the heart 12 can typically be measured by advancing a catheter 14 containing an electrical sensor (e.g., sensor 29) at or near its distal tip (e.g., at least one electrode 26) to the point within the heart 12, contacting tissue with the electrical sensor, and acquiring data at the point. One difficulty with mapping a heart chamber using a catheter type containing only a single distal tip electrode is that a long time may be required to collect data for each point over the necessary number of points required for a detailed map of the heart chamber as a whole. Therefore, multi-electrode catheters (e.g., catheter 14) have been developed to simultaneously measure electrical activity at multiple points within the heart chamber.

[0026] The catheter 14, which may include at least one electrode 26 and a catheter needle coupled on its body, may be configured to obtain biometric data, such as electrical signals, of a body organ (e.g., the heart 12) and / or ablate a tissue region thereof (e.g., a chamber of the heart 12). It is noted that the electrode 26 is representative of any similar element, such as a tracking coil, a piezoelectric transducer, an electrode, or a combination of elements configured to ablate a tissue region or obtain biometric data. According to one or more embodiments, the catheter 14 may include one or more position sensors that are used to determine trajectory information. This trajectory information may be used to infer motion characteristics, such as tissue contractility.

[0027] The biometric data (e.g., patient biometrics, patient data, or patient biometric data) may include one or more of local activation time (LAT), electrical activity, topology, bipolar mapping, baseline activity, ventricular activity, dominant frequency, impedance, and the like. LAT may be a time point of threshold activity corresponding to local activation calculated based on a normalized initial starting point. Electrical activity may be any applicable electrical signal that may be measured based on one or more thresholds and may be sensed and / or enhanced based on signal-to-noise ratio and / or other filters. Topology may correspond to a physical structure of a body part or a portion of a body part, and may correspond to changes in the physical structure for different parts of the body part or for different body parts. Dominant frequency may be a frequency or range of frequencies commonly found in a portion of a body part and may be different in different parts of the same body part. For example, the dominant frequency of the PVs of the heart may be different from the dominant frequency of the right atrium of the same heart. Impedance may be a resistance measurement in a particular region of the body part.

[0028] Examples of biometric data include, but are not limited to, patient identification data, IC ECG data, bipolar intracardiac reference signals, anatomical and electrical measurements, trajectory information, body surface (BS) ECG data, historical data, brain biometric measurements, blood pressure data, ultrasound signals, radio signals, audio signals, two-dimensional or three-dimensional (3D) image data, blood glucose data, and temperature data. The biometric data may generally be used to monitor, diagnose, and treat any number of different diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathies, and coronary artery disease), and autoimmune diseases (e.g., diabetes mellitus type I and type II). It is noted that BS ECG data may include data and signals collected from electrodes on the patient's surface, IC ECG data may include data and signals collected from electrodes inside the patient's body, and ablation data may include data and signals collected from ablated tissue. Additionally, the BS ECG data, IC ECG data, and ablation data may be derived from one or more treatment records along with catheter electrode position data.

[0029] For example, the catheter 14 may use the electrodes 26 to perform intravascular ultrasound and / or MRI catheterization to image the heart 12 (e.g., acquire and process biometric data). The catheter 14 is shown in an enlarged view within a chamber of the heart 12. It will be understood that any shape that includes one or more electrodes 26 may be used to implement the embodiments disclosed herein.

[0030] Examples of catheter 14 include, but are not limited to, a straight catheter with multiple electrodes, a balloon catheter including electrodes distributed on multiple spines forming a balloon, a lasso, a catheter with multiple electrodes in a grid shape or a loop catheter with multiple electrodes, a high density catheter, or any other applicable shape or combination. The straight catheter may be fully or partially elastic so that it can twist, bend, and / or otherwise change its shape based on received signals and / or based on the action of an external force (e.g., cardiac tissue) on the straight catheter. The balloon catheter may be designed to hold its electrodes in intimate contact against the endocardial surface when deployed within the patient's body. As an example, the balloon catheter may be inserted into a lumen such as a pulmonary vein (PV). The balloon catheter may be inserted into the PV in a deflated state, such that the balloon catheter does not occupy its maximum volume while inserted into the PV. The balloon catheter may be expanded while inside the PV, such that the electrodes on the balloon catheter contact the entire circular portion of the PV. Such contact with the entire circular portion of the PV or any other lumen allows for efficient imaging and / or ablation. Other examples of catheter 14 include the PentaRay® catheter and the Constellation catheter.

[0031] According to another example, a body patch and / or body surface electrodes (e.g., one or more electrode patches 38) may be placed on or adjacent to the body of the patient 23. A catheter 14 having one or more electrodes 26 may be placed within the body (e.g., within the heart 12), and the position of the catheter 14 may be determined by the 100 system based on signals transmitted and received between the one or more electrodes 26 of the catheter 14 and the body patch and / or body surface electrodes. Additionally, the electrodes 26 may sense biometric data from within the body of the patient 23, such as within the heart 12 (e.g., the electrodes 26 sense tissue electrical potentials in real time). The biometric data may be correlated with the determined position of the catheter 14, such that a rendering of the patient's body part (e.g., the heart 12) may be displayed showing the biometric data superimposed on the shape of the body part.

[0032] As a further example, the catheter 14 and other items of the system 10 can be connected to a workstation 55. The workstation 55 can include any computing device that employs ML / AI algorithms, which can be included in the generation engine 101. According to an exemplary embodiment, the workstation 55 includes one or more processors 61 (any computing hardware) and memory 62 (any non-transitory tangible medium), where the one or more processors 61 execute computer instructions for the generation engine 101 and the memory 62 stores these instructions for execution by the one or more processors 61. For example, the workstation 55 can be configured to receive and process biometric data to determine whether a particular tissue region conducts electricity. In some embodiments, the workstation 55 can be further programmed by the generation engine 101 (in software) to perform functions of an ablation procedure guidance method. For example, an ablation procedure guidance method can include receiving input (e.g., including one or more images and a conduction velocity vector estimate), utilizing the images and the conduction velocity vector estimate to generate a digital twin of the anatomical structure, and presenting the digital twin to provide precise ablation guidance of the anatomical structure and to provide electrophysiology information of the anatomical structure.

[0033] In accordance with one or more embodiments, the generation engine 101 may be external to the workstation 55, such as located in the catheter 14, in an external device, in a mobile device, in a cloud-based device, or may be a stand-alone processor. In this regard, the generation engine 101 may be transferable / downloadable in electronic form over a network.

[0034] By way of example, the workstation 55 may be any computing device described herein including software (e.g., generation engine 101) and / or hardware (e.g., processor 61 and memory 62), such as a general-purpose computer with appropriate front-end and interface circuitry for transmitting and receiving signals to and from the catheter 14 and controlling other components of the system 10. For example, the front-end and interface circuitry may include an input / output (I / O) communication interface that allows the workstation 55 to receive signals from at least one electrode 26 and / or transmit signals to at least one electrode 111. The workstation 55 may include real-time noise reduction circuitry, typically configured as a field programmable gate array (FPGA). The real-time noise reduction circuitry is followed by an analog-to-digital (A / D) ECG or electrocardiogram / electromyogram (EMG) signal conversion integrated circuit. The workstation 55 may communicate signals from the A / D ECG or EMG circuitry to another processor and / or may be programmed to perform one or more functions disclosed herein.

[0035] A display device 27, which may be any electronic device for visually presenting biometric data, is connected to the workstation 55. According to an exemplary embodiment, during a procedure, the workstation 55 may facilitate the presentation of a rendering of the body part to the physician 24 on the display device 27 and store data representative of the rendering of the body part in the memory 62. For example, a map indicative of motion characteristics may be rendered / constructed based on trajectory information sampled at a sufficient number of points within the heart 12. As an example, the display device 27 may include a touch screen that may be configured to receive input from the medical professional 115 in addition to presenting the rendering of the body part.

[0036] In some embodiments, physician 24 may use one or more input devices, such as a touchpad, mouse, keyboard, gesture recognizer, etc., to manipulate the renderings of elements of system 10 and / or body parts. For example, the input devices may be used to change the position of catheter 14 so that the renderings are updated. Note that display device 27 may be located at the same location or at a remote location, such as another hospital or another healthcare provider network.

[0037] According to one or more embodiments, the system 10 can also obtain biometric data using ultrasound, computed tomography (CT), MRI, or other medical imaging techniques utilizing the catheter 14 or other medical equipment. For example, the system 10 can obtain ECG data and / or anatomical and electrical measurements (e.g., biometric data) of the heart 12 using one or more catheters 14 or other sensors. More specifically, the workstation 55 can be connected by a cable to BS electrodes including adhesive skin patches affixed to the patient 23. The BS electrodes can acquire / generate biometric data in the form of BS ECG data. For example, the processor 61 can determine position coordinates of the catheter 14 within the body part (e.g., the heart 12) of the patient 23. The position coordinates can be based on impedance or electromagnetic fields measured between the body surface electrodes and the electrodes 26 of the catheter 14 or other electromagnetic components. Additionally or alternatively, the location pads generating the magnetic fields used for steering can be located on the surface of the bed (or table) and can be separate from the bed. The biometric data can be transmitted to the workstation 55 and stored in the memory 62. Alternatively, or additionally, the biometric data may be transmitted to a server, which may be local or remote, using a network as described further herein.

[0038] According to one or more embodiments, the catheter 14 may be configured to ablate a tissue region of a chamber of the heart 12. For example, the catheter 14 is shown in an expanded view within a chamber of the heart 12. Additionally, an ablation electrode, such as at least one electrode 26, may be configured to apply energy to a tissue region of an internal organ (e.g., the heart 12). The energy may be thermal energy and may cause damage to the tissue region starting from a surface of the tissue region and extending through a thickness of the tissue region. Biometric data related to the ablation procedure (e.g., ablated tissue, ablation location, etc.) may be considered ablation data.

[0039] According to one example, with respect to acquiring biometric data, a multi-electrode catheter (e.g., catheter 14) can be advanced into a chamber of heart 12. Anterior-posterior (AP) and lateral fluoroscopic pictures can be acquired to establish the position and orientation of each of the electrodes. An ECG can be recorded from each of the electrodes 26 in contact with the cardiac surface relative to a time reference, such as the occurrence of P waves in sinus rhythm from a BS ECG and / or a signal from an electrode 26 of catheter 14 positioned within the coronary sinus. The system further disclosed herein can distinguish between electrodes that record electrical activity and electrodes that do not record electrical activity due to their lack of proximity to the endocardial wall. After an initial ECG is recorded, the catheter can be repositioned and fluoroscopic pictures and ECG can be recorded again. An electrical map (e.g., via cardiac mapping) can then be constructed from an iteration of the above process.

[0040] Cardiac mapping may be performed using one or more techniques. In general, mapping of cardiac regions, such as cardiac regions, tissues, veins, arteries, and / or electrical pathways of the heart 12 may lead to identification of problem areas, such as scar tissue, arrhythmia sources (e.g., electrical rotors), healthy regions, and the like. Cardiac regions may be mapped such that a visual rendering of the mapped cardiac regions is provided using a display, as further disclosed herein. Additionally, cardiac mapping (which is an example of cardiac imaging) may include mapping based on one or more modalities, such as, but not limited to, LAT, regional activation rate, electrical activity, topology, bipolar mapping, dominant frequency, or impedance. Data (e.g., biometric data) corresponding to multiple modalities may be acquired using a catheter (e.g., catheter 14) inserted into the patient's body and may be provided for rendering at the same time or at different times based on corresponding settings and / or physician 24 preferences.

[0041] As an example of the first technique, cardiac mapping may be performed by sensing electrical properties of cardiac tissue, e.g., LAT, as a function of precise location within the heart 12. Corresponding data (e.g., biometric data) may be acquired by one or more catheters (e.g., catheter 14) advanced into the heart 12 and having electrical and position sensors (e.g., electrodes 26) at their distal tips. As a specific example, location and electrical activity may be initially measured at about 10 to about 20 points on the inner surface of the heart 12. These data points may generally be sufficient to generate a preliminary reconstruction or map of the cardiac surface with satisfactory quality. The preliminary map may often be combined with data measured at additional points to generate a more comprehensive map of the cardiac electrical activity. In clinical practice, it is not uncommon to accumulate data from 100 or more sites (e.g., several thousand) to generate a detailed comprehensive map of the electrical activity of the cardiac chambers. The detailed map generated may then be the basis for making decisions about a course of therapeutic action, e.g., tissue ablation as described herein, to alter the propagation of the cardiac electrical activity and restore normal cardiac rhythm.

[0042] Furthermore, cardiac mapping can be generated based on detection of intracardiac potential fields (e.g., one example of IC ECG data and / or bipolar intracardiac reference signals). Non-contact methods can be implemented to simultaneously acquire large amounts of cardiac electrical information. For example, a catheter type having a distal end portion can include a series of sensor electrodes distributed over its surface and connected to insulated conductors for connection to signal sensing and processing means. The size and shape of the end portion can be such that the electrodes are spaced apart from the wall of the cardiac chamber. The intracardiac potential fields can be detected during one cardiac beat. According to one example, the sensor electrodes can be distributed on a series of circumferences located in planes spaced apart from one another. These planes can be perpendicular to the long axis of the end portion of the catheter. At least two further electrodes can be disposed adjacent to both ends of the long axis of the end portion. As a more specific example, the catheter can include four circumferences with eight electrodes equiangularly spaced apart on each circumference. Thus, in this particular implementation, the catheter can include at least 34 electrodes (32 circumferential electrodes and two end electrodes). As another more specific example, the catheter may include other multi-spline catheters such as a turner type with five soft flexible branches, eight radial splines, or parallel splines (e.g., any of which may have a total of 42 electrodes).

[0043] As an example of electrical or cardiac mapping, electrophysiological cardiac mapping systems and techniques based on non-contact and non-expandable multi-electrode catheters (e.g., catheter 14) can be implemented. ECGs may be acquired using one or more catheters 14 with multiple electrodes (e.g., 42-122 electrodes, etc.). This implementation allows knowledge of the relative geometry of the probe and endocardium to be obtained by an independent imaging modality, such as transesophageal echocardiography. After independent imaging, non-contact electrodes can be used to measure cardiac surface potentials and a map can be constructed from the surface potentials (e.g., possibly using a bipolar intracardiac reference signal). This technique can include the following steps (after the independent imaging step): (a) measuring potentials using multiple electrodes placed on a probe placed within the heart 12; (b) determining the geometric relationship of the probe surface to the endocardial surface and / or other fiducials; (c) generating a matrix of coefficients representing the geometric relationship of the probe surface to the endocardial surface; and (d) determining the endocardial potentials based on the electrode potentials and the matrix of coefficients.

[0044] As another example of electrical or cardiac mapping, techniques and devices can be implemented for mapping the electrical potential distribution of a heart chamber. An intracardiac multi-electrode mapping catheter assembly can be inserted into the heart 12. The mapping catheter (e.g., catheter 14) assembly can include a multi-electrode array having one or more integral reference electrodes (e.g., one or more electrodes 26) or a companion reference catheter.

[0045] According to one or more embodiments, the electrodes may be deployed in a generally spherical array that may be spatially referenced to points on the endocardial surface by a reference electrode or by a reference catheter that is brought into contact with the endocardial surface. A preferred electrode array catheter may have a large number of individual electrode sites (e.g., at least 24). In addition, this exemplary technique may be implemented with knowledge of the location of each of the electrode sites on the array and with knowledge of the cardiac geometry. These locations are preferably determined by impedance plethysmography.

[0046] From an electrical or cardiac mapping perspective, and according to another example, the catheter 14 may be a cardiac mapping catheter assembly that may include an electrode array that defines multiple electrode sites. The cardiac mapping catheter assembly also includes a lumen for receiving a reference catheter having a distal tip electrode assembly that may be used to probe the heart wall. The cardiac mapping catheter assembly may include a braid of insulated wires (e.g., having 24-64 wires in the braid), each of which may be used to form an electrode site. The cardiac mapping catheter assembly may be readily positionable within the heart 12 to be used to obtain electrical activity information from a first set of non-contact electrode sites and / or a second set of contact electrode sites.

[0047] Further, according to another example, a catheter 14 capable of performing mapping of electrophysiological activity within the heart can include a distal tip adapted to deliver stimulation pulses for pacing the heart or an ablation electrode for ablating tissue in contact with the tip, and can further include at least a pair of orthogonal electrodes for generating a differential signal indicative of local cardiac electrical activity proximate the orthogonal electrodes.

[0048] As described herein, system 10 may be used to detect, diagnose, and / or treat cardiac conditions. In an exemplary operation, a process may be performed by system 10 for measuring electrophysiological data within a heart chamber. This process may include, in part, placing a set of active and passive electrodes within heart 12, supplying electrical current to the active electrodes thereby generating an electric field within the heart chamber, and measuring the electric field at the passive electrode sites. The passive electrodes are included in an array disposed on an inflatable balloon of a balloon catheter. In a preferred embodiment, the array is said to have 60-64 electrodes.

[0049] As another exemplary operation, cardiac mapping may be performed by the system 10 using one or more ultrasound transducers. The ultrasound transducers may be inserted into the patient's heart 12 and may collect multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) at various locations and orientations within the heart 12. The location and orientation of a particular ultrasound transducer may be known, and the collected ultrasound slices may be stored so that they can be displayed at a later time. One or more ultrasound slices corresponding to the location of a catheter 14 (e.g., a treatment catheter) may be displayed later, and the catheter 14 may be superimposed on the one or more ultrasound slices.

[0050] Considering the system 10, it can be seen that cardiac arrhythmias, including atrial arrhythmias, can be of the multiwavelet-reentrant type, characterized by multiple asynchronous loops of electrical impulses that scatter and often self-propagate around the atria (e.g., another example of IC ECG data). Alternatively or in addition to the multiwavelet-reentrant type, cardiac arrhythmias can also have focal sources of excitation, such as when isolated regions of atrial tissue are excited autonomously in a rapid and repetitive manner (e.g., another example of IC ECG data). Ventricular tachycardia (V-tach or VT) is a tachycardia or fast heart rhythm that originates from one of the ventricles. It is a potentially fatal arrhythmia, as it can lead to ventricular fibrillation and sudden death.

[0051] For example, aFib occurs when the normal electrical impulses generated by the sinoatrial node (e.g., another example of IC ECG data) are overwhelmed by chaotic electrical impulses (e.g., signal interference) originating in the atrial veins and PVs, conducting irregular impulses to the ventricles. The result is an irregular heartbeat that may persist for minutes to weeks or even years. In many cases, aFib is a chronic condition that often carries a small increase in the risk of death from stroke. The treatment approach for aFib is medication to reduce the heart rate or return the heart rhythm to normal. Furthermore, patients with aFib are often given anticoagulants to protect against the risk of stroke. The use of such anticoagulants carries its own risks, internal bleeding. In some patients, medication is not sufficient and the patient's aFib is determined to be drug refractory, i.e., untreatable by standard pharmacological interventions. Synchronized electrical cardioversion can also be used to convert aFib to a normal heart rhythm. Alternatively, patients with aFib may be treated with catheter ablation.

[0052] Catheter ablation-based therapy may include mapping electrical properties of cardiac tissue, particularly the endocardium and cardiac volumes, and selectively ablating cardiac tissue by application of energy. Electrical or cardiac mapping (e.g., performed by any of the electrophysiological cardiac mapping systems and techniques described herein) includes creating an electrical potential map (e.g., voltage map) of wave propagation along cardiac tissue, or a map of arrival times (e.g., LAT map) to points located within various tissues. Electrical or cardiac mapping (e.g., cardiac map) can be used to detect localized cardiac tissue dysfunction. Ablation, such as cardiac mapping-based ablation, can stop or change the propagation of unwanted electrical signals from one portion of the heart 12 to another.

[0053] Ablation techniques disrupt unwanted electrical pathways by creating non-conductive lesions. Various energy delivery modalities have been disclosed to create lesions, including the use of microwave, laser, and more generally radio frequency energy to create a conduction block along the cardiac tissue wall. Another example of an energy delivery technique is irreversible electroporation (IRE), which applies a high electric field that damages cell membranes. In a two-stage procedure (mapping followed by ablation), electrical activity at points within the heart 12 is typically sensed and measured by advancing a catheter 14 containing one or more electrical sensors (e.g., electrodes 26) into the heart 12 and acquiring / capturing data (e.g., generally as biometric data or specifically as ECG data) at multiple points. The ECG data is then used to select a target region of the endocardium where ablation will be performed.

[0054] Cardiac ablation and other cardiac electrophysiology procedures are becoming increasingly complex as physicians treat challenging conditions such as atrial fibrillation and ventricular tachycardia. Treatment of refractory arrhythmias can now rely on the use of 3D mapping systems to reconstruct the anatomical structure of the targeted heart chamber. In this regard, the generation engine 101 employed by the system 10 herein manipulates and evaluates biometric data in general, and ECG data in particular, to generate improved tissue data that allows for more accurate diagnosis, images, scans, and / or maps to treat abnormal heart rhythms or arrhythmias. For example, cardiologists rely on software such as the Complex Fractionated Atrial Electrograms (CFAE) module of the CARTO® 3 3D mapping system manufactured by Biosense Webster, Inc. (Diamond Bar, Calif.) to generate and analyze ECG data. The generation engine 101 of the system 10 enhances this software to generate and analyze improved biometric data, thereby providing further information regarding the electrophysiological properties of the heart 12 (including scar tissue) that represent the cardiac substrate (anatomical and functional) of the aFib.

[0055] Thus, the system 10 can implement a 3D mapping system, such as the CARTO® 3 3D mapping system, to locate potential arrhythmogenic substrates of cardiomyopathies in terms of detection of abnormal ECG. Substrates related to these cardiac diseases have been associated with the presence of delayed ECG and fragmentation of the endocardial and / or epicardial layers of the ventricular chambers (right and left). For example, areas of low or medium voltage may indicate ECG fragmentation and delayed activity. Furthermore, areas of low or medium voltage during sinus rhythm may correspond to critical isthmus identified in sustained coherent ventricular arrhythmias (e.g., in non-permissive ventricular tachycardia, as well as in the atrium). In general, abnormal tissue is characterized by low voltage ECG. However, early clinical experience with endocardial-epicardial mapping has shown that areas of low voltage are not always present as the only arrhythmogenic mechanism in such patients. Indeed, areas of low or medium voltage may show ECG fragmentation and delayed activity during sinus rhythm, which corresponds to the critical isthmus identified during sustained coherent ventricular arrhythmias (e.g., only applicable to non-permissive ventricular tachycardia). Moreover, in many cases, ECG fragmentation and delayed activity are observed in areas showing normal or near-normal voltage amplitudes (>1-1.5 mV). The latter areas can be evaluated according to voltage amplitudes, but are not considered normal according to the intracardiac signal and therefore represent true arrhythmogenic substrates. 3D mapping allows to localize arrhythmogenic substrates on the endocardial and / or epicardial layers of the right / left ventricle, whose distribution may vary depending on the evolution of the primary disease.

[0056] As another exemplary operation, cardiac mapping may also be performed by the system 10 using one or more multi-electrode catheters (e.g., catheter 14). The multi-electrode catheters are used to stimulate and map electrical activity within the heart 12 and to ablate sites of abnormal electrical activity. In use, the multi-electrode catheter is inserted into a major vein or artery, such as the femoral vein, and then guided into a chamber of the heart 12 of interest. A typical ablation procedure involves inserting the catheter 14 having at least one electrode 26 at its distal end into a cardiac chamber. A reference electrode is provided by taping to the patient's skin or by a second catheter placed in or near the heart, or by selecting from one or the other electrodes 26 of the catheter 14. Radio frequency (RF) current is applied to the tip electrode 26 of the ablation catheter 14, and current flows through the medium (i.e., blood and tissue) surrounding the tip electrode toward the reference electrode. The current distribution is determined by the amount of electrode surface in contact with tissue compared to blood, which is more conductive than tissue. Heating of the tissue occurs due to its electrical resistance. When the tissue is heated sufficiently, cell destruction is induced in the cardiac tissue, resulting in the formation of electrically non-conductive lesions in the cardiac tissue. This process also results in heating of the tip electrode 26 by conduction from the heated tissue to the electrode itself. When the temperature of the electrode becomes high enough, possibly exceeding 60° C., a thin, transparent film of dehydrated blood proteins may form on the surface of the electrode 26. As the temperature continues to increase, this dehydrated layer may gradually thicken, causing blood to coagulate on the electrode surface. Because dehydrated biological material has a higher electrical resistance than endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. When the impedance becomes high enough, an impedance rise occurs and the catheter 14 must be removed from the body and the tip electrode 26 must be cleaned.

[0057] 2, shown is a schematic diagram of a system 200 in which one or more features of the presently disclosed subject matter may be implemented, according to one or more embodiments. System 200 may be configured to generate a digital twin of the atrium of an aFib patient.

[0058] The system 200 includes an apparatus 204, a local computing device 206, a remote computing system 208, a first network 210, and a second network 211 for a patient 202 (e.g., an example of the patient 23 of FIG. 1). Additionally, the apparatus 204 may include a biometric sensor 221 (e.g., an example of the catheter 14 of FIG. 1), a processor 222, a user input (UI) sensor 223, a memory 224, and a transceiver 225. It should be noted that for ease of explanation and brevity, the generation engine 101 of FIG. 1 is reused in FIG. 2.

[0059] According to one embodiment, the device 204 may be an example of the system 10 of FIG. 1, where the device 204 may include both patient internal and patient external components. According to another embodiment, the device 204 may be a patient 202 external device that includes an attachable patch (e.g., attached to the patient's skin). According to another embodiment, the device 204 may be internal to the patient's 202 body (e.g., subcutaneously implantable), where the device 204 may be inserted into the patient's 202 body by any applicable method, including oral infusion, surgical insertion via a vein or artery, endoscopic surgery, or laparoscopic surgery. According to one embodiment, although a single device 204 is shown in FIG. 2, an exemplary system may include multiple devices.

[0060] Thus, the apparatus 204, the local computing device 206, and / or the remote computing system 208 may be programmed to execute computer instructions for the generation engine 101. As an example, the memory 223 stores these instructions for the processor 222 to execute such that the apparatus 204 can receive and process biometric data via the biometric sensor 201. In this manner, the processor 222 and the memory 223 are representative of the processor and memory of the local computing device 206 and / or the remote computing system 208.

[0061] The apparatus 204, the local computing device 206, and / or the remote computing system 208 can be any combination of software and / or hardware that individually or collectively stores, executes, and implements the generation engine 101 and its functions. Furthermore, the apparatus 204, the local computing device 206, and / or the remote computing system 208 can be an electronic computer framework that includes and / or uses any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The apparatus 204, the local computing device 206, and / or the remote computing system 208 can be easily scalable, extensible, and modular, capable of being tailored for different services, or capable of reconfiguring some functions independently of others.

[0062] Networks 210 and 211 may be wired networks, wireless networks, or may include one or more wired and wireless networks. According to one embodiment, network 210 is an example of a short-range network (e.g., a local area network (LAN) or a personal area network (PAN)). Information can be transmitted between apparatus 204 and local computing device 206 over short-range network 210 using any one of a variety of short-range wireless communication protocols, such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communication (NFC), Ultraband, Zigbee, or infrared (IR). Further, network 211 is an example of one or more of an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between local computing device 206 and remote computing system 208. Information may be transmitted over network 211 using any one of a variety of long-range wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / New Radio). It is noted that the wired connections of networks 210 and 211 may be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection, and the wireless connections may be implemented using Wi-Fi, WiMAX, and Bluetooth, infrared, cellular networks, satellite communications, or any other wireless connection methodology.

[0063] In operation, the device 204 may continuously or periodically acquire, monitor, store, process, and communicate biometric data associated with the patient 202 via the network 210. Additionally, the device 204, the local computing device 206, and / or the remote computing system 208 communicate via the networks 210 and 211 (e.g., the local computing device 206 may be configured as a gateway between the device 204 and the remote computing system 208). For example, the device 204 may be an example of the system 10 of FIG. 1 configured to communicate with the local computing device 206 via the network 210. The local computing device 206 may be, for example, a fixed / standalone device, a base station, a desktop / laptop computer, a smartphone, a smartwatch, a tablet, or any other device configured to communicate with other devices via the networks 211 and 210. A remote computing system 208, implemented as a physical server on or connected to the network 211 or as a virtual server within a public cloud computing provider of the network 211 (e.g., Amazon Web Services (AWS)®), can be configured to communicate with the local computing device 206 over the network 211. Thus, biometric data related to the patient 202 can be communicated throughout the system 200.

[0064] The elements of the device 204 are now described. The biometric sensor 221 may include, for example, one or more transducers configured to convert one or more environmental conditions into electrical signals such that different types of biometric data may be observed / obtained / obtained. For example, the biometric sensor 221 may include one or more of an electrode (e.g., electrode 26 of FIG. 1), a temperature sensor (e.g., a thermocouple), a blood pressure sensor, a blood glucose sensor, a blood oxygen sensor, a pH sensor, an accelerometer, and a microphone.

[0065] In executing the generation engine 101, the processor 222 can be configured to receive, process, and manage biometric data acquired by the biometric sensor 221, and communicate the biometric data to the memory 224 for storage and / or across the network 210 via the transceiver 225. Biometric data from one or more other devices 204 may also be received by the processor 222 via the transceiver 225. Additionally, as described in more detail below, the processor 222 can be configured to selectively respond to different tapping patterns (e.g., single tap or double tap) received from the UI sensor 223 such that different tasks of the patch (e.g., acquiring, storing, or transmitting data) are initiated based on the detected pattern. In some embodiments, the processor 222 can generate audible feedback regarding detection of the gesture.

[0066] According to one or more embodiments, the generation engine 101, at run time, can receive inputs including images and conduction velocity vector estimates, utilize the images and conduction velocity vector estimates to generate a digital twin of the anatomical structure, and present the digital twin via a user interface to provide precise ablation guidance and electrophysiology information of the anatomical structure.

[0067] According to one or more embodiments, the generation engine 101 can perform a re-estimation of LAT activity based on the digital twin at run-time after performing one or more ablations (note that the ablations can be electroporations). In this case, the digital twin allows the generation engine 101 to generate a LAT map based on the identification of the cardiac source (e.g., the sinoatrial node or the SA node) and to calculate the progression of the signal in the heart 12 based on the CV in each direction. Thus, one or more of the technical effects, advantages, and benefits of the generation engine 101 include being able to provide an actual LAT map (as currently generated in CARTO® 3) and a digital twin LAT map on the same interface. Furthermore, after the ablation, the CV of the ablated location can be updated by the generation engine 101 using an ablation estimation model (such as the CARTO VISITAG™ model). Thus, the digital twin LAT map can also be updated based on the 1250f CV update. Thus, one or more of the technical effects, advantages, and benefits of the generation engine 101 include enabling simulation of a LAT map after ablation without remapping the heart 14. Thus, according to one or more embodiments, the generation engine 101 can generate a digital twin LAT map based on a digital twin model and can update CV vector estimates of ablated cells / tissues in the digital twin model based on the ablation model that affected the digital twin LAT map. The UI sensor 223 includes a piezoelectric or capacitive sensor configured to receive user input, such as, for example, a tap or touch. For example, the UI sensor 223 may be controlled to perform capacitive coupling in response to the patient 202 tapping or touching the surface of the device 204. Gesture recognition may be performed by any one of a variety of capacitive types, such as resistive capacitive, surface capacitive, projected capacitive, surface ultrasonic, piezoelectric, and infrared touch. The capacitive sensor may be positioned over a small area or length of the surface such that a tap or touch on the surface activates the monitoring device.

[0068] The memory 224 may be any non-transitory, tangible medium, such as magnetic, optical, or electronic memory (e.g., any suitable volatile and / or non-volatile memory, such as a random access memory or a hard disk drive). The memory 224 stores computer instructions that are executed by the processor 222.

[0069] The transceiver 225 may include a separate transmitter and a separate receiver, or, alternatively, the transceiver 225 may include a transmitter and receiver integrated into a single device.

[0070] During operation, the device 204 utilizes the generation engine 101 to observe / acquire biometric data of the patient 202 via the biometric sensor 221, store the biometric data in memory, and share this biometric data throughout the system 200 via the transceiver 225. The generation engine 101 can then perform signal processing operations utilizing models, far field reduction algorithms, neural networks, ML, and / or AI to generate a digital twin of the atrium for an atrial fibrillation (aFib) patient.

[0071] Referring now to Figure 3, a method 300 (e.g., performed by generation engine 101 of Figures 1 and / or 2) is shown in accordance with one or more embodiments. Method 300 may be one example of an ablation procedure guidance method for navigating the atria of the heart. Method 300 addresses the need for improved ablation location techniques by providing a multi-stage manipulation of the electrical activity of heart 12 that allows for a better understanding of the electrophysiology more precisely via the digital twin (e.g., taking into account arrhythmia triggers as well as information about atrial wall material).

[0072] The method begins at block 310, where the generation engine 101 receives one or more inputs. The one or more inputs may include biometric data as described herein, and one or more images (e.g., CT, MRI, etc.) of the heart 12. The one or more inputs may be real-time data and patient-specific. More specifically, the one or more inputs may include baseline recordings of IC ECG and / or BS ECG, previous / current CV vector estimates, and / or a lattice Boltzmann model to simulate typical waves propagating along the atrium. According to one or more embodiments, the system 10 may utilize a multi-electrode catheter (e.g., catheter 14) to obtain multiple acquisitions (e.g., baseline recordings) from the cardiac region covered by the electrodes. According to one or more embodiments, the inputs include images, conduction velocity vector estimates, and baseline recordings or lattice Boltzmann models. Additionally, the inputs may be proarrhythmic effects from IC ECG and / or BS ECG.

[0073] In block 320, the generation engine 101 generates a digital twin. For example, the generation engine 101 creates a digital twin of the left atrium of the heart 12 of the aFib patient 23. The digital twin of the heart 12 can be based on images and other inputs. According to one or more embodiments, the generation engine 101 utilizes images and conduction velocity vector estimates to generate the digital twin of the heart 12. The digital twin can also be based on baseline recordings, CV vector estimates, and / or lattice Boltzmann models. Thus, once the generation engine 101 obtains images and other inputs, the generation engine 101 can build an anatomical structure to determine how electricity flows through the anatomical structure. The one or more operations of generating the digital twin in block 320 can include, but are not limited to, performing direction of arrival (DOA) estimation (330), clustering (340), voxelization (350), and dynamic 3D generation (360). In this regard, the generation engine 1010 determines electrical flow through the heart 12 based on performing one or more of DOA estimation, clustering, voxelization, and dynamic 3D generation. The operations of generating a digital twin are described further herein, but each will be briefly described for ease of understanding.

[0074] In blocks 330 and 340, DOA estimation and clustering can be a bottom-up approach that estimates local CV vectors by analyzing atrial activity from unipolar signals segment by segment. Note that DOA estimation automatically identifies pro-arrhythmic CV vectors (e.g., system 10 can utilize DOA estimates to automatically identify CV vector estimates and generate digital twins). That is, once all segments are processed, generation engine 101 clusters to detect DOA clusters (e.g., clustering output can be 1-3 typical conduction velocity vectors). More specifically, the bottom-up stage approach outputs conduction velocity vectors and focal source locations for each point of electrophysiology measurements, and the last stage uses a lattice Boltzmann model to estimate electrical flow simulation patterns based on focal sources.

[0075] In block 350, the generation engine 101 voxelizes (i.e., processes one or more voxels) to find the best CV vector. In this regard, the atrium is voxelized (i.e., the atrium is divided into one or more voxels) into K voxels, and each voxel sees only its six nearest neighbors. Furthermore, the generation engine 101 uses the probability of seeing an excitation wave in close proximity to determine the best CV vector. In block 360, the generation engine 101 performs a dynamic 3D generation that presents the wave (along with the best CV vector). In this regard, a digital twin (e.g., anatomy constructed from images) constructed from one or more inputs is aligned with the dynamic 3D generation.

[0076] In block 370, the generation engine 101 presents the digital twin in a user interface for the physician 24. According to one or more embodiments, the generation engine 101 presents the digital twin to provide precision ablation guidance and to provide electrophysiology information of the anatomy (i.e., the heart 12). For example, the precision ablation guidance in the user interface can include one or more simulations showing how electricity flows through the digital twin based on the conduction velocity vector estimates (e.g., based on the best CV vector) and / or one or more interactions between focal activation with respect to the digital twin and determine foci for ablation based on the one or more interactions. More specifically, the generation engine 101 acts as a guidance tool for the ablation procedure before any ablation is performed. In this manner, the physician 24 can assess the real-time condition of the atria of the heart 12 and interact with the digital twin accordingly.

[0077] In block 380, the generation engine 101 receives one or more additional inputs. The one or more additional inputs can be real-time data and patient-specific. The one or more inputs can include biometric data, catheter motion, CT images, MRI images, real-time ultrasound images, additional IC ECG and / or BS ECG recordings, and / or updated CV vector estimates. According to one or more embodiments, the generation engine 101 receives one or more additional inputs and generates one or more different ablation approach proposals for the ablation procedure and performs a digital twin remapping operation (based on the one or more additional inputs). For example, the physician 24 makes one or more decisions, such as moving the catheter 14 to a new position, after viewing the digital twin presented in block 370. The generation engine 101 utilizes the new position and the updated biometric information associated with the new position (as one or more additional inputs) to generate a simulation. The generation engine 101 simulates different ablation approaches and proposes an approach that reduces arrhythmia with a minimum area of ​​ablation. The generation engine 101 simulates interactions between focal excitations to determine which foci are more important for ablation. Technical effects and advantages of the method 300 include allowing the generation engine 101 to include actual scarring using a bipolar voltage map, or to include simulated scarring based on the assumption that the physician 24 intends to ablate at each location. In accordance with one or more embodiments, the operation of block 380 may be optional.

[0078] At dashed block 380 (optional), ablation is performed. This optional step may be performed by clinician 24 based on the simulations presented in blocks 370 and 380 according to one or more additional inputs. After one or more additional inputs have been received and / or ablation has been performed, generation engine 101 may perform a remapping operation (represented by arrow 395) by returning to block 320.

[0079] All or a portion of the method 300 may be implemented by the ML / AI generation engine 101 as described herein. FIG. 4 illustrates a graphical depiction of an AI system 400, according to one or more embodiments. As illustrated, the AI ​​system 400 includes data 410 (e.g., biometric data), which may be stored on a memory or other storage unit. Additionally, the AI ​​system 400 includes a machine 420 and a model 430, which represent software aspects (e.g., ML / AI algorithms therein) of the generation engine 101 of FIGS. 1-2. The machine 420 and the model 430 together may generate an outcome 440. The AI ​​system 400 may include hardware 450, which may represent the catheter 14 of FIG. 1, the workstation 55 of FIG. 1, and / or the device 204 of FIG. 2. Where appropriate, for ease of understanding, the description of FIGS. 4-5 will be made with reference to FIGS. 1-3. In general, the ML / AI algorithms of the AI ​​system 400 (e.g., implemented by the generative engine 101 of FIGS. 1-2 ) operate on the hardware 450 using data 410 to train a machine 420 to build a model 430 and predict an outcome 440.

[0080] For example, the machine 420 operates as a software controller executing on the hardware 450. The data 410 (e.g., biometric data as described herein) may be ongoing data (i.e., data being continuously collected) or output data associated with the hardware 450. The data 410 may also include currently collected data (e.g., position of the catheter 14), historical data, or other data from the hardware 450, may include measurements during a surgical procedure, may be associated with the outcome of a surgical procedure, and may include a temperature of the heart 12 of FIG. 1 that is collected and correlated with the outcome of a cardiac procedure (or one or more of LA T, electrical activity, topology, bipolar mapping, baseline activity, ventricular activity, dominant frequency, impedance). The data 410 may be associated with the hardware 450. The data 410 may be divided by the machine 420 into one or more subsets.

[0081] Further, the machine 420 is trained, which may include analyzing and correlating the collected data 410. For example, in the cardiac case, the temperature and outcome data 410 may be trained to determine if a correlation or association exists between the temperature of the heart 12 of FIG. 1 during a cardiac procedure and a positive or negative treatment outcome. According to another embodiment, training the machine 420 may include self-training by the generating engine 101 of FIG. 1 with one or more subsets. In this regard, for example, the generating engine 101 of FIG. 1 learns to generate a digital twin and simulate wave propagation.

[0082] The model 430 is constructed on the data 410. Constructing the model 430 may include physical hardware or software modeling, algorithmic modeling, and / or similar modeling intended to represent the collected and trained data 410 (or a subset thereof). In some aspects, constructing the model 430 is part of a self-training operation by the machine 420. The model 430 may be configured to model the operation of the hardware 450 and to model the data 410 collected from the hardware 450 to predict the outcome 440 obtained by the hardware 450. The trained model 430 may be used in predicting the outcome 440 (of the model 430 associated with the hardware 450). For example, and to further the understanding of the present disclosure, in the case of the heart, if temperatures during treatment between 36.5° C. and 37.89° C. (i.e., 97.7° F. and 100.2° F.) result in positive outcomes from cardiac treatments, then the outcome 440 may be predicted for a given treatment using these temperatures. Thus, the predicted outcome 440 can be used to configure the machine 420, model 430, and hardware 450 accordingly.

[0083] Thus, for AI system 400 to operate as described, the ML / AI algorithms therein can include a neural network. Generally, a neural network is a network or circuit of neurons, or in the modern sense, an artificial neural network (ANN) made up of artificial neurons or nodes or cells.

[0084] For example, ANNs include a network of processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between the processing elements and element parameters. These connections in a neuronal network or circuit are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​imply inhibitory connections. The inputs are modified by the weights and summed using a linear combination. An activation function can control the amplitude of the output. For example, the acceptable range of the output is usually 0 to 1, but can also be -1 to 1. ANNs are often adaptive systems that change their structure based on external or internal information flowing through the network.

[0085] In more practical terms, a neural network is a nonlinear statistical data modeling or decision making tool that can be used to model complex relationships between inputs and outputs or to find patterns in data. Thus, ANNs can be used for predictive modeling and adaptive control applications while being trained through a data set. Note that self-learning arising from experience can occur within ANNs, allowing them to draw conclusions from a complex and seemingly unrelated set of information. The usefulness of artificial neural network models lies in the fact that they can be used to estimate and use functions from observations. Unsupervised neural networks can also be used to learn representations of inputs that capture salient features of the input distribution, and more recently, for deep learning algorithms that can implicitly learn distribution functions for observed data. Learning with neural networks is particularly useful in applications where the design of such functions cannot be done manually due to the complexity of the data (e.g., biometric data) or the task (e.g., monitoring, diagnosis, and treatment of any number of different diseases).

[0086] In the AI ​​system 400, the ML / AI algorithms therein may include neural networks that are generally partitioned according to the tasks to which they are applied. These partitions tend to fall within the categories of regression analysis (e.g., function approximation), including time series prediction and modeling, classification, including pattern and sequence recognition, novel detection and making continuous decisions, data processing, including filtering, clustering, blind signal separation, and compression. For example, application areas of ANNs include medical diagnosis and treatment to help create semantic profiles of patient biometric data resulting from medical procedures.

[0087] According to one or more embodiments, the neural network may implement a long-short-term memory neural network architecture, a convolutional neural network (CNN) architecture, or the like. The neural network may be configurable with respect to multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., dropout), and optimization features.

[0088] Long-short-term memory neural network architectures contain feedback connections and can process single data points (e.g., images) along with entire sequences of data (e.g., speech or video). The units of a long-short-term memory neural network architecture can consist of a cell, an input gate, an output gate, and a forget gate, where the cell remembers a value over any time interval, and the gates regulate the flow of information to and from the cell.

[0089] The CNN architecture is a shared weight architecture with translation invariant properties where each neuron in one layer is connected to every neuron in the next layer. The regularization technique of the CNN architecture can exploit hierarchical patterns in the data and organize more complex patterns using smaller and simpler patterns. When a neural network implements a CNN architecture, other configurable aspects of the architecture may include the number of filters at each stage, the kernel size, and the number of kernels per layer.

[0090] 5, a block diagram of an example neural network 500 and a method 501 performed within the neural network 500 is shown in accordance with one or more embodiments. The neural network 500 operates to aid in the implementation of the ML / AI algorithms described herein (e.g., as implemented by the generation engine 101 of FIGS. 1-2). The neural network 500 may be implemented in hardware, such as the machine 420 and / or hardware 450 of FIG. 4. As provided herein, the description of FIGS. 4-5 will be made with reference to FIGS. 1-3, where appropriate, for ease of understanding.

[0091] In an example operation, the generation engine 101 of FIG. 1 includes collecting data 410 from the hardware 450. In the neural network 500, the input layer 510 is represented by a number of inputs (e.g., inputs 512 and 514 of FIG. 5). With respect to block 520 of the method 501, the input layer 510 receives inputs 512 and 514. The inputs 512 and 514 can include biometric data. For example, collecting the data 410 can be aggregating biometric data (e.g., BS ECG data, IC ECG data, and ablation data) from one or more treatment records of the hardware 450 into a dataset (represented by data 410).

[0092] In block 525 of method 501, neural network 500 encodes inputs 512 and 514 with any portion of data 410 (e.g., datasets and predictions generated by AI system 400) to generate a latent representation or data encoding. The latent representation includes one or more intermediate data representations derived from multiple inputs. According to one or more embodiments, the latent representation is generated by an element-wise activation function (e.g., a sigmoid function or a rectified linear function) of generative engine 101 of FIG. 1. As shown in FIG. 5, inputs 512 and 514 are provided to hidden layer 530, which is shown to include nodes 532, 534, 536, and 538. Neural network 500 executes through hidden layer 530 of nodes 532, 534, 536, and 538 to exhibit complex global behavior determined by connections between processing elements and element parameters. Thus, the transition between layer 510 and layer 530 can be viewed as an encoder stage that takes input 512 and input 514 and forwards them to a deep neural network (in layer 530) to learn a smaller representation of a portion of the input (e.g., the resulting latent representation).

[0093] The deep neural network may be a CNN, a long-short-term memory neural network, a fully connected neural network, or a combination thereof. The inputs 512 and 514 may be intracardiac ECG, a body surface ECG, or an intracardiac ECG and a body surface ECG. This encoding results in a dimensionality reduction of the inputs 512 and 514. Dimensionality reduction is the process of reducing the number of random variables (of the inputs 512 and 514) being considered by obtaining a set of key variables. For example, dimensionality reduction may be feature extraction that transforms the data (e.g., the inputs 512 and 514) from a high-dimensional space (e.g., higher than 10 dimensions) to a low-dimensional space (e.g., 2-3 dimensions). Technical effects and advantages of dimensionality reduction include reducing the time and storage space requirements of the data 410, improving the visualization of the data 410, and improving parameter interpretability for ML. This data transformation may be linear or nonlinear. The acts of receiving (block 520) and encoding (block 525) can be considered the data preparation portion of a multi-stage data manipulation by the generation engine 101.

[0094] At block 545 of method 510, neural network 500 decodes the latent representation. The decoding stage receives the encoder output (e.g., the resulting latent representation) and attempts to reconstruct the particular form of input 512 and input 514 using another deep neural network. In this regard, nodes 532, 534, 536, and 538 are combined to generate output 552 in output layer 550, as shown at block 560 of method 510. That is, output layer 590 recovers input 512 and input 514 with reduced dimensionality but without signal interference, signal artifacts, and signal noise. An example of output 552 includes cleaned biometric data (e.g., a clean / denoised version of IC ECG data, etc.). Technical effects and benefits of cleaned biometric data include enabling more accurate monitoring, diagnosis, and treatment of any number of various disorders.

[0095] In accordance with one or more embodiments, the generation engine 101 is described with respect to creating an atrium digital twin (e.g., an atria digital twin or ADT) of the heart 12 for an aFib patient (e.g., patient 120). As described herein, aFib is a major global healthcare challenge. For example, the initiation and maintenance of aFib is not fully understood, which has hindered the development of effective and reliable therapies. Treatment of aFib is often by catheter ablation, where an area of ​​the myocardium determined to be responsible for the initiation or perpetuation of the disorder is targeted and the area is rendered electrically inactive by the local application of radio frequency energy or freezing.

[0096] For example, in the case of paroxysmal aFib, catheter ablation provides relatively good outcomes with success rates ranging from 80% to 90%. However, catheter ablation therapy for patients with persistent aFib is less effective with a success rate of about 50% even with all forms of adjunctive ablation strategies (and about 33% of ablation procedures are performed in patients with persistent or long-term persistent aFib). Pulmonary vein isolation (PVI) may be the first approach, but other ablation strategies are being developed to increase the effectiveness of treatment for this segment of patients.

[0097] There are several driving mechanisms responsible for aFib maintenance: foci, rotors, and epicardial-endocardial dissociation. Recent clinical studies have targeted foci, complex fractionated atrial electrograms (CFAEs), and high dominant frequencies (DFs). However, none of these ablation strategies have been shown to add any value to the PVI approach. One or more reasons why these ablation strategies do not add value may include that they only investigate one modality in persistent aFibs and relate that modality (e.g., simple or complex, focal or non-focal behavior, early or late, segmented or non-segmented) to the success or failure of release from aFib more than one year after the ablation procedure, while ignoring many of the EP and ablation parameters.

[0098] The generation engine 101 overcomes these concerns by generating and providing an ADT for an aFib patient (e.g., patient 120). For example, the ADT models IC ECG data during a baseline recording of an ablation procedure to create an equivalent (e.g., under identical conditions) to all available clinical observations. Based on the ADT, the generation engine 101 can test different ablation approaches for rapid and long-term cessation of aFib and predict the corresponding success. Thus, one or more advantages, technical effects, and / or benefits of the generation engine 101 include a cost-effective, safe, and ethical solution for ablation therapy investigations. That is, the generation engine 101 creates a patient-specific model of the atrium (i.e., the ADT). The patient-specific model can address several challenges related to 3D representation, electrophysiology modeling, and other modeling of the atrium. The generation engine 101 can also apply the same when simulating time-varying contractile conduction flow, simulating hemodynamic flow of the atrium, and creating a digital twin of the ventricle. The generation engine 101 also overcomes these concerns by using IC ECG, 3D imaging of the atria to estimate the CV vector, and a lattice Boltzmann model to simulate N typical electrical flows that best fit the data. For example, the generation engine 101 can utilize and apply deep learning algorithms to estimate the CV vector for each voxel from a set of 12-lead ECG signals. As described herein with respect to FIG. 5, the generation engine 101 can include an ML / AI architecture for CV estimation from the 3D anatomy, the BC ECG, and the 3D positions of the BS electrodes.

[0099] According to one or more embodiments, the generation engine 101 generates a digital twin of the left atrium of an aFib patient (e.g., patient 120) as an ADT. This ADT is generated from baseline recordings of IC-ECG, CV vector estimates, and a Lattice Boltzmann model to simulate typical waves propagating along the left atrium, as described herein (see at least FIG. 3). The ADT can include real scarring using bipolar voltage maps, or simulated scarring based on the assumption that the physician 24 intends to ablate at each location. Thus, the ADT can be used as a guiding tool for the ablation procedure. The ADT can also simulate different ablation approaches (across the ADT) and select the one that reduces arrhythmia with the smallest area of ​​ablation (e.g., the approach with the smallest effective area). The ADT can simulate one or more interactions between focal activations (with respect to the atrial digital twin) to determine which foci are more important for ablation. It is noted that given the nature of aFib, the ADT does not assume that the arrhythmia repeats itself, such as in an anatomically-informed digital simulation, but assumes standard electrical conduction.

[0100] 6, a method 600 is shown according to one or more embodiments. Note that block 605 is shown with a dotted line and indicates an input block. Blocks 610, 615, 620, 625, 630, 635, 640, 645, 650, 675, and 680 are dashed lines and indicate processing blocks, and blocks 655, 665, 670, and 685 are dashed lines and indicate output blocks. Method 600 performs velocity estimation and focus source detection based on DOA estimation (i.e., a process for CV and focus detection based on DOA estimation). Note that DOA can be considered as a method for automatically identifying proarrhythmic CV vectors. Furthermore, method 600 can be a bottom-up approach for estimating local CV vectors, such as using a multi-electrode catheter to obtain multiple acquisitions from the cardiac region covered by the electrodes.

[0101] At block 605, the generation engine 101 receives input records (e.g., multiple acquisitions from the cardiac region covered by the electrodes). At block 610, the generation engine 101 performs atrial detection for each unipolar signal. At decision block 615, the generation engine 101 analyzes atrial activity from the unipolar signal segment by segment.

[0102] In parallel, in block 620, the generation engine 101 further projects the catheter 14 into 2D space. In decision block 625, it is determined whether a valid projection exists, such as the ratio of the sum of the two dominant eigenvalues ​​to the sum of the three eigenvalues ​​is higher than 95%. That is, if the generation engine 101 is not able to project into 2D space, the method proceeds to block 630 (as indicated by the NO arrow). Otherwise, the method 600 proceeds to block 635 (as indicated by the YES arrow). In blocks 630 and 635, a 3D or 2D weighted DOA model estimation is initiated based on the ability to project the catheter into 2D space.

[0103] In decision block 640, the generation engine 101 determines whether the estimation error of the model (e.g., ADT) is large or small. If the estimation error of the model is too large (e.g., larger than 7 ms), the method 600 proceeds to block 645 (as indicated by the NO arrow). In block 645, an iterative mode for DOA estimation is applied. The iterative mode for DOA estimation is illustrated with respect to FIGS. 11-14.

[0104] At decision block 650, the generation engine 101 again determines whether the estimation error of the model (e.g., ADT) is large or small (e.g., greater than 7 ms). If the estimation error of the model is too large (e.g., greater than 7 ms), the method 600 proceeds (as indicated by the NO arrow) to output block 655. At output block 655, the generation engine 101 stores any bad segments for / from the DOA.

[0105] If a valid DOA is detected in blocks 640 and / or 650 (as indicated by the YES arrows), the LAT is corrected in output block 665. One or more DOA points are also stored in memory 62 in output block 670 until all segments have been processed. For example, method 600 may loop to decision block 615, such as to finish all segments.

[0106] In block 675, once all segments have been processed (see arrow 676), k-means clustering is performed for detection of DOA clusters. The k-means clustering can provide / generate a typical CV vector for each position of the catheter 14 (e.g., PentaRay® catheter). In block 680, the generation engine 101 executes the detection stage where the focus source detection starts (i.e., if the origin of one or more of the dominant CV vectors is within 8 mm from the center of the catheter 14, the focus verification mechanism is applied). In output block 685, the generation engine 101 can verify the focus source (e.g., if there are 10 or more earliest S-wave patterns in the electrodes in its vicinity).

[0107] According to one or more embodiments, DOA estimation, lesion detection, and LAT refinement, as well as other aspects of FIG. 6, are further described herein.

[0108] For DOA per segment, a model-based DOA can be applied to each segment of data. For example, the model-based DOA can include a set of at least 10 local atrial activations, t iis the time of local atrial activity of an electrode, = 1,...,m, 10≦m≦N, where N is the number of active electrodes in catheter 14 (e.g., N=20 for the PentaRay® catheter). If generation engine 101 assumes / determines that a single wave originates from any point in 3D space and travels toward catheter 14 with constant CV, then generation engine 101 can define J(θ), the "total cost" of the model, according to Equation 1: where x i ,y i ,z i are the coordinates of the electrode positions, and x0, y0, z0 are the coordinates of the position where the DOA is calculated.

[0109]

number

[0110] That is, the generation engine 101 further

[0111]

number

[0112]

number

[0113] ∇ represents the differential operation and γ is a learning rate factor. Note that γ can be made small to ensure transformation, but not too small to deal with slow transformation or convergence to local minima of J(θ). According to one or more embodiments, a formal description of the gradient descent algorithm can include deriving a differential equation for J(θ) for each parameter of (x0, y0, z0, t0, v), as shown below by Equations 3-7, respectively.

[0114]

number

[0115] 7-11 show interfaces 700, 800, 900, 1000, and 1100, in accordance with one or more embodiments. The interfaces 700, 800, 900, 1000, and 1100 can be generated by the generation engine 101. The interface 700 of FIG. 7 shows an example of DOA estimation based on segments of atrial activity. A first portion 710 of the interface 700 includes a first portion 712 of the interface 700, which includes a first portion 713 of the interface 700, which includes a second portion 714 of the interface 700.i The diagram 720 above the interface 700 shows the estimated focal activations (circles with x's inside). The other circles represent the location of the electrodes in XY space. The diagram 730 below the interface 700 shows the actual location of the catheter 14 on the left atrial anatomy.

[0116] Interface 800 in Figure 8 shows an example isochrone map. Waves are propagating from a circle 810 with an x ​​inside. Each circle represents the arrival time in milliseconds (msec) according to the shaded bar. One or more circles 830 represent the location of the electrodes, with numbers within them representing the estimated error in milliseconds.

[0117] According to one or more embodiments, the generation engine 101 can modify the above model-based DOA with respect to dimensionality reduction, weighted DOA estimation, and / or DOA iterative modes.

[0118] For dimensionality reduction, the catheter 14 can be projected onto a surface. The projection is performed by the generation engine 101 taking the two eigenvectors with the highest eigenvalues. If the energy conserved by the two eigenvalues ​​is greater than 95%, the generation engine 101 assumes / determines that the projection from the 3D space onto the surface is valid for θ=(x0,y0,z0,t0,v) with no z dimension, as shown by equations 8-13.

[0119]

number

[0120] 9, an interface 900 is shown in accordance with one or more embodiments. The interface 900 relates to an example of 2D DOA estimation (where 97.7% of the energy is preserved, and therefore 2D DOA estimation is applied). A first portion 910 of the interface 900 is a iwhere the squares represent the estimated t based on estimates of x0, y0, z0, t0, and v. i In the example shown by interface 900, a single wave travels towards the catheter 14. Diagram 920 above interface 900 shows the estimated focal activation (circle with an x ​​inside). The circle represents the location of the electrode in XY space. Diagram 930 below interface 900 represents the actual location of the catheter 14 on the left atrial anatomy.

[0121] For weighted DOA estimation, the generation engine 101 provides a more reliable and sharper excitation than a shallower excitation, where the sharpness is t i It can be defined based on the time derivative dv / dt of a unipolar signal at each t i can be mapped to a weight between 0 and 1 based on the corresponding time derivative dv / dt. Alternation can be set for 2D according to Equations 14-18.

[0122]

number

[0123] Referring to FIG. 10, an interface 1000 is shown in accordance with one or more embodiments. The interface 1000 is an example of weighted DOA detected as focal activation. The graph of the interface 1100 provides signals to each of the electrodes (e.g., B5, B7, D13, C10, etc.). In the interface 1000, note the earliest S-wave pattern at electrodes E19 and E20. In the chart 1001 of the interface 1000, each circle can represent a gradient weight.

[0124] For the DOA iterative mode, if the average estimation error is above a certain threshold (e.g., 7 ms), the generation engine 101 enters an iterative mode for DOA estimation. At each iteration, the local excitation time with the largest estimation error is removed from the DOA estimation. This process can be repeated as long as there are more than 10 valid local excitation times.

[0125] Referring to FIG. 11, an interface 1100 is shown in accordance with one or more embodiments. This interface is an example of how to display information regarding an estimate of focal activation at the center of the catheter 14. Note that due to the large estimation error of 12.4 ms, the generation engine 101 initiates an iterative mode. The graph of the interface 1100 provides signals representing specific heart beats and activation times (i.e., the time when the signal passed under each pair of electrodes). The 3D image of the interface 1100 represents the location of each electrode within the left atrium. The 2D image of the interface 1100 presented in a graph represents the position of each electrode pair on the surface and the relative activation time.

[0126] Referring to FIG. 12, one or more graphs 1210, 1230, and 1250 are shown according to one or more embodiments. One or more graphs 1210, 1230, and 1250 illustrate a first iteration of a focal source (e.g., at the center of the catheter 14) and second through ninth iterations of focal excitation (e.g., offset near the electrodes). Graph 1210 shows the maximum error per iteration. Graph 1230 shows the conduction velocity per iteration. Both graphs 1210 and 1230 combined show the overall convergence of the model to a "reasonable solution" (the maximum error drops to less than 5 ms after the second iteration, with a CV of 0.5 mm / ms). In graph 1250, dots 1260 represent valid electrodes for DOA estimation, electrodes represent invalid electrodes, and "iteration 9" represents that this electrode was excluded from DOA estimation in iteration 9. Note that the recursive model is used to handle cases with noisy local activation times or cases with more than one wave propagating towards the catheter 14 .

[0127] Referring to FIG. 13, an interface 1300 shows an example of a DOA solution (i.e., the actual result of the model) at iteration 9. A graph 1301 provides a signal representing a particular heartbeat and activation time (i.e., the time when the signal passed under each pair of electrodes). A 3D image 1305 represents the location of each electrode in the left atrium, and a 2D image 1310 presented in the graph represents the position and relative activation time of each electrode pair on the surface. According to one or more embodiments, the graph 1301 shows the unipolar signal after removing the far field activation (to remove the measurement points). According to one or more embodiments, the signal can be acquired by a catheter 14 having one or more splines and one or more electrodes per spline (e.g., an OCTARAY® mapping catheter with 48 electrodes). The estimation error of the model is an important quantity. The estimation error is a measure of the "goodness" of the fit of the model. When the final model results in an overall estimation error above a certain threshold (e.g., 7 ms), the generation engine 101 can assume that the segment is invalid for analysis. The percentage of invalid segments is a good measure of the "complexity" of the aFib in this subject. When using high density catheters and far field reduction algorithms, an "estimation error" can be calculated by the generation engine 101 for each group of electrodes or for each electrode, and a "goodness" can be generated for each electrode.

[0128] With respect to the generation engine 101 moving from segment DOAs to conduction velocity vectors, it is noted that the DOA terms can represent the estimated conduction velocity and (x,y) location of the wave propagating towards the catheter 14. As described herein, the generation engine 101 can provide an estimate of the conduction velocity vector single segment of local atrial activity. Segment durations are typically 100-200 ms. Furthermore, a typical recording has a unipolar signal of 2.5-30 seconds and contains approximately 10-200 segments during an aFib. Thus, all valid DOAs are stored until all segments have been processed, and then k-means clustering is performed. FIG. 14 and graph 1400 show an example of DOA clustering according to one or more embodiments. The generation engine 101 can perform a decision for each recording based on clustering of DOAs. Every circle represents a DOA estimate from a segment of LAT in the recording. There are two clusters of DOAs in this recording that "explain" the data. The first cluster 1410 (circle at (-3.7 mm,-0.2 mm)) contains 80.5% of the DOAs and the second cluster 1420 contains 19.5% of the DOAs in the recording. The output of the clustering are 1 to 3 typical CV vectors.

[0129] A focal source is detected by the generation engine 101 if the dominant cluster falls within an 8 mm radius from the center of the catheter 14. The focal source may also be verified if at least 10 signatures (configurable) of the earliest S-wave pattern are found in electrodes located within an 8 mm radius from the focal source. Note that the verification process is optional since focal detection based DOA may appear at an anatomical location without placing the catheter at the focal activation.

[0130] 15 illustrates user interfaces 1510 and 1540, according to one or more embodiments. Interface 1510 illustrates a lesion map. Interface 1540 illustrates a static map of conduction velocity. The maps in interfaces 1510 and 1540 are based on a DOA algorithm and are presented on the left atrium.

[0131] According to one or more embodiments, a lattice Boltzmann model for electrical flow simulation is described. The bottom-up stage of the DTA algorithm of the generation engine 101 outputs a CV vector and a lesion source location for each electrophysiology measurement point, i.e., for each position of the measurement by the PentaRay® catheter. The final stage of the algorithm of the generation engine 101 uses a lattice Boltzmann model to estimate a pattern of electrical flow simulation based on the conduction velocity vector. The atrium is voxelized into K voxels, and each voxel only sees its six nearest neighbors. The measurements from the previous stage are used to assign a set of possible conduction velocity vectors to each voxel. See Equation 19. φv represents the conduction velocity vector M associated with voxel v. |φ i | is the actual conduction velocity in V / sec, and φ ix ,φ iy are the x and y components of the conduction velocity.

[0132]

number

[0133] For each time sample t, the generation engine 101 estimates for each voxel the probability of activation subject to the conduction velocity, cycle length, and boundary conditions. The generation engine 101 may assume that all voxels with a bipolar voltage value below 0.5 mV are non-conductive and the wave is restricted from activating this voxel. One or more boundary conditions may also be assumed by the generation engine 101 based on the ablation points or lines given as input to the algorithm from a user trying to simulate the best ablation approach. The generation engine 101 starts the operation / algorithm at time 0 when the dominant voxel with focal source indication is "fired". If not present, the focal source is started based on clinical assumptions. For example, the generation engine 101 selects the Buchmann bundle as the focal source location since it is the preferred pathway for electrical activation of the left atrium during normal sinus rhythm.

[0134] The generation engine 101 determines / calculates the probability of seeing an excitation wave in the immediate vicinity of a focus according to Equation 20.

[0135]

number

[0136] e i represents one of the seven nearest neighbors, and dt is 1 ms in the system. f(x+e i , t+dt)=1, the generation engine 101 i Estimate the current CV of voxel x+e in the last 20 ms. i (Several methods can be applied by the generation engine 101, such as collecting information on neighboring waves.) Next, for voxel x+e i θ = [|θ|,θ], denoted as the estimated CV associated with x ,θ y ], the CV criterion can be defined according to Equations 21-23.

[0137]

number

[0138] Note that at the beginning of the estimation, α=1, and α is increased by a factor of 2 every time the lattice Boltzmann model fails to estimate the wave. i If all the above criteria are met, then the CV velocity criterion is met and f(v+e i ,t+dt) is equal to 1 (for example, v+e i (Even if voxels are not scar voxels). The generation engine 101 can then implement a modified Lattice Boltzmann model according to FIG.

[0139] The method 1600 begins at block 620, where the generation engine 101 voxelizes the atrial set φ v on a voxel-by-voxel basis. At block 1640, the generation engine 101 sets an initial voxel of the focus source.

[0140] Then, in block 1660, the generation engine 101 determines, for each t, ​​t←t+dt. Further, in block 1660, for each voxel v, v+e i is the scar voxel f(v+e i If f(v,t)=0, then break. Furthermore, assume that f(v,t)=1, estimate θ, and i If the CV criterion is met at time t+dt, then f(v+e i ,t+dt)=1, and if the CV criterion is not met, then f(v+e i ,t+dt)=0.

[0141] At decision block 1680, the generation engine 101 determines whether a valid wave is present. If a valid wave is present, the method 400 proceeds to block 1690 (as indicated by the arrow at 1681), where the generation engine 101 utilizes the same α for the estimation (e.g., note that at the start of the estimation, α=1). If a valid wave is not present, the method 400 proceeds to block 1695 (as indicated by the NO arrow), where the generation engine 101 increases α and re-estimates, returning a higher α. As mentioned herein, α can be increased by a factor of 2 (e.g., α,(α=α·2)) each time the lattice Boltzmann model fails to estimate a wave.

[0142] Regarding the implementation, the generation engine 101 takes into account the CV to define the overall firing rate of the focal source. Furthermore, once a typical wave is estimated for a single cycle, the matrix φ can be two different matrices. For example, a first matrix can include only elements of φ that met the conducted CV criteria, and a second matrix can include elements that did not meet the CV criteria. The second matrix can be used to create a second simulation of the wave in aFib.

[0143] According to one or more embodiments, the digital twin of the atrium for an aFib patient can be a robust computer-generated replica of the atrium with personalized electrical activity to serve as a guiding tool for ablation. To generate and create the digital twin, the generation engine measures and utilizes the personalized electrical activity and CV vectors of the heart while taking into account information about arrhythmia triggers and atrial wall material. Then, during the ablation procedure, the generation engine continuously updates the digital twin and suggests optimal ablation and / or additional procedures based on the digital twin. As a result, the digital twin generated by the generation engine is highly accurate compared to current digital simulations and can be used for effective guidance during the ablation procedure by cardiac physicians and medical personnel.

[0144] According to one or more advantages and technical benefits, the generation engine 101 and the ADT can simulate different ablation approaches and select an approach that reduces arrhythmia with a minimum ablation area. According to one or more advantages and technical benefits, the generation engine 101 updates the "scar" matrix for each ablation line and creates a simulation based on the new boundaries. According to one or more advantages and technical benefits, the generation engine 101 provides / supports the success of the ablation approach by reducing the duration of the activation period relative to the atrial cycle length. According to one or more advantages and technical benefits, the generation engine 101 and the model simulate interactions between focal activations to determine which foci are more important for ablation.

[0145] According to one or more embodiments, a method is provided that allows for a deep understanding of electrophysiology of a precise anatomical structure via a digital twin. The method is performed by a generation engine executed by one or more processors. The method includes receiving one or more inputs. The one or more inputs include one or more images and a conduction velocity vector estimate. The method includes generating a digital twin of the anatomical structure utilizing the one or more images and the conduction velocity vector estimate. The method includes presenting the digital twin in a user interface that functions as a guiding tool for a medical procedure.

[0146] According to any of the one or more embodiments or method embodiments herein, the one or more inputs can include a baseline recording, a conduction velocity vector estimate, or a lattice Boltzmann model to simulate typical waves propagating along the anatomical structure.

[0147] According to any of the one or more embodiments or method embodiments herein, the digital twin can be based on baseline recordings, conduction velocity vector estimates, or a lattice Boltzmann model.

[0148] According to any of one or more embodiments or method embodiments herein, a digital twin can be generated to determine how electricity flows through the anatomical structures based on performing one or more of direction of arrival estimation, clustering, voxelization, and dynamic 3D generation.

[0149] According to one or more of the embodiments or method embodiments herein, DOA estimation can automatically identify pro-arrhythmic conduction velocity vector estimates from intracardiac or surface electrocardiograms.

[0150] According to any of the one or more embodiments or method embodiments herein, the user interface may provide one or more simulations of the digital twin that show how electricity flows through the anatomical structures based on the best conduction velocity vector.

[0151] According to one or more of the embodiments or any of the method embodiments herein, the medical procedure can include at least an ablation procedure.

[0152] According to one or more of the embodiments or any of the method embodiments herein, the anatomical structure may include an atrium of the heart.

[0153] According to any of the one or more embodiments or method embodiments herein, one or more probes may include patient-specific data.

[0154] According to any of one or more of the embodiments or method embodiments herein, the generation engine may receive one or more additional inputs.

[0155] According to any of one or more of the embodiments or method embodiments herein, the generation engine can generate one or more different ablation approaches and suggestions for a medical procedure.

[0156] According to any of the one or more embodiments or method embodiments herein, the generation engine may perform a remapping operation of the digital twin based on one or more additional inputs.

[0157] According to any of the one or more embodiments or method embodiments herein, the generation engine can generate a digital twin local excitation time map based on the digital twin model.

[0158] According to any of one or more embodiments or method embodiments herein, the generation engine can update the conduction velocity vector estimates of the ablated cells in the digital twin model based on the ablation model that affected the digital twin local activation time map.

[0159] According to one or more of the embodiments or method embodiments herein, a digital twin can be generated for an atrial fibrillation patient.

[0160] According to one or more embodiments, a method is provided that allows for deep understanding of precise anatomical electrophysiology via an atrial digital twin of an atrium of a heart. The method is performed by a generation engine executed by one or more processors. The method includes generating an atrial digital twin utilizing one or more images and a conduction velocity vector estimate, and presenting the atrial digital twin in a user interface that serves as a guiding tool for a medical procedure. The method also includes simulating one or more different ablation approaches over the atrial digital twin, and selecting an approach from the one or more different ablation approaches that reduces arrhythmia with a minimum area of ​​ablation.

[0161] According to one or more embodiments, a method is provided that allows for deep understanding of precise anatomical electrophysiology via an atrial digital twin of an atrium of a heart. The method is performed by a generation engine executed by one or more processors. The method includes generating an atrial digital twin utilizing one or more images and conduction velocity vector estimates, and presenting the atrial digital twin in a user interface that serves as a guiding tool for a medical procedure. The method also includes simulating one or more interactions between focal activations with respect to the atrial digital twin, and determining a lesion based on the one or more interactions that are most important for ablation.

[0162] The flowcharts and block diagrams in the figures illustrate the structure, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions that includes one or more executable instructions for implementing the illustrated logical function. In some alternative implementations, the functions shown in the blocks may occur in an order other than that shown in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, may be implemented by a dedicated hardware-based system that performs the specified function or operation, or may operate or execute a combination of dedicated hardware and computer instructions.

[0163] Although the features and elements have been described above in a particular combination, those skilled in the art will understand that each of the features or elements can be used alone or in combination with other features and elements. In addition, the methods described herein can be implemented in a computer program, software, or firmware that is embodied in a computer-readable medium for execution on a computer or processor. As used herein, a computer-readable medium should not be construed as being a signal that is itself ephemeral, such as an electric wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a wave guide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electric signal transmitted through a flow line.

[0164] Examples of computer readable media include electrical signals (transmitted over wired or wireless connections) and computer readable storage media. Examples of computer readable storage media include, but are not limited to, registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, optical media such as compact disks (CDs) and digital versatile disks (DVDs), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), and memory sticks. The processor may be used with software to implement a radio frequency transceiver for use in a terminal, base station, or any host computer.

[0165] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" are intended to include the plural unless the context clearly indicates otherwise. It is further to be understood that the terms "comprise" and / or "comprising," as used herein, indicate the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or other features, integers, steps, operations, elements, components, and / or groups thereof.

[0166] The description of different embodiments herein is presented for illustrative purposes, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used in this specification are selected to best explain the principles, practical applications, or technical improvements of the embodiments compared to the art found in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0167] [Embodiment] (1) A method of ablation procedure guidance implemented by a generation engine executing on at least one processor, comprising: receiving, by the generation engine, one or more inputs including one or more images and a conduction velocity vector estimate; generating, by the generation engine, a digital twin of an anatomical structure utilizing the one or more images and the conduction velocity vector estimate; presenting the digital twin via a user interface of the generation engine to provide precision ablation guidance of the anatomical structure and to provide electrophysiology information of the anatomical structure; 23. A method for ablation procedure guidance comprising: (2) The ablation procedure guidance method of embodiment 1, wherein the one or more inputs include the one or more images, the conduction velocity vector estimate, and a baseline recording or a lattice Boltzmann model. (3) The ablation procedure guidance method of embodiment 1, wherein the generation engine determines electrical flow through the anatomical structure based on performing one or more of direction of arrival estimation, clustering, voxelizing, and dynamic 3D generation. (4) An ablation procedure guidance method as described in embodiment 1, wherein the one or more inputs include an arrhythmic effect from an intracardiac electrocardiogram or a surface electrocardiogram. (5) The ablation procedure guidance method of embodiment 1, wherein the generation engine utilizes a direction of arrival estimate to automatically identify the conduction velocity vector estimate from the one or more inputs and generate the digital twin.

[0168] (6) The ablation procedure guidance method of embodiment 1, wherein the precise ablation guidance includes simulating how electricity flows through the digital twin based on the conduction velocity vector estimate. (7) the generation engine receives one or more additional inputs; The ablation procedure guidance method of embodiment 1, wherein the generation engine generates one or more different ablation approach proposals for the ablation procedure or performs a remapping operation of the digital twin based on the one or more additional inputs. (8) the generation engine generates a digital twin local excitation time map based on the digital twin model; The ablation procedure guidance method of embodiment 1, wherein the generation engine updates a conduction velocity vector estimate of an ablated cell in the digital twin model based on an ablation model that influenced the digital twin local activation time map. (9) The ablation procedure guidance method of embodiment 1, wherein the precise ablation guidance includes simulating one or more interactions between focal excitations with respect to the digital twin, and determining a lesion for ablation based on the one or more interactions. (10) the anatomical structure includes an atrium of the heart; 2. The ablation procedure guidance method of embodiment 1, wherein the one or more inputs include patient-specific data.

[0169] (11) A system comprising at least one processor executing a generation engine for providing ablation procedure guidance, the generation engine providing the system with: receiving one or more inputs including one or more images and a conduction velocity vector estimate; generating a digital twin of an anatomical structure utilizing the one or more images and the conduction velocity vector estimates; Presenting the digital twin via a user interface of the generation engine to provide precision ablation guidance of the anatomical structure and to provide electrophysiological information of the anatomical structure. The system is configured as follows: (12) The system of embodiment 11, wherein the one or more inputs include the one or more images, the conduction velocity vector estimate, and a baseline recording or a lattice Boltzmann model. (13) The system of embodiment 11, wherein the generation engine determines electrical flow through the anatomical structure based on performing one or more of direction of arrival estimation, clustering, voxelization, and dynamic 3D generation. (14) The system of embodiment 11, wherein the one or more inputs include proarrhythmic effects from an intracardiac electrocardiogram or a surface electrocardiogram. (15) The system of embodiment 11, wherein the generation engine utilizes a direction of arrival estimate to automatically identify the conduction velocity vector estimate from the one or more inputs and generate the digital twin.

[0170] (16) The system of claim 11, wherein the precise ablation guidance includes simulating how electricity flows through the digital twin based on the conduction velocity vector estimate. (17) the generation engine receives one or more additional inputs; The system of embodiment 11, wherein the generation engine generates one or more different ablation approach proposals for an ablation procedure or performs a remapping operation of the digital twin based on the one or more additional inputs. (18) The generation engine generates a digital twin local excitation time map based on the digital twin model; The system of embodiment 11, wherein the generation engine updates a conduction velocity vector estimate of an ablated cell in the digital twin model based on an ablation model that influenced the digital twin local activation time map. (19) The system of embodiment 11, wherein the precise ablation guidance includes simulating one or more interactions between focal excitations with respect to the digital twin and determining a lesion for ablation based on the one or more interactions. (20) The system of embodiment 11, wherein the anatomical structure includes an atrium of the heart and the one or more inputs include patient-specific data.

Claims

1. 1. A system comprising at least one processor executing a generation engine for providing ablation procedure guidance, the generation engine providing the system with: receiving one or more inputs including one or more images and a conduction velocity vector estimate; generating a digital twin of an anatomical structure utilizing the one or more images and the conduction velocity vector estimates; Presenting the digital twin via a user interface of the generation engine to provide precision ablation guidance of the anatomical structure and to provide electrophysiological information of the anatomical structure. The system is configured as follows:

2. The system of claim 1 , wherein the one or more inputs include the one or more images, the conduction velocity vector estimate, and a baseline recording or a lattice Boltzmann model.

3. 10. The system of claim 1, wherein the generation engine determines electrical flow through the anatomical structures based on performing one or more of direction of arrival estimation, clustering, voxelization, and dynamic 3D generation.

4. The system of claim 1 , wherein the one or more inputs include proarrhythmic effects from an intracardiac electrocardiogram or a surface electrocardiogram.

5. 10. The system of claim 1, wherein the generation engine utilizes a direction of arrival estimate to automatically identify the conduction velocity vector estimate from the one or more inputs to generate the digital twin.

6. 2. The system of claim 1, wherein the precise ablation guidance includes simulating how electricity flows through the digital twin based on the conduction velocity vector estimate.

7. the generation engine receives one or more additional inputs; 2. The system of claim 1, wherein the generation engine generates one or more different proposed ablation approaches for an ablation procedure or performs a remapping operation of the digital twin based on the one or more additional inputs.

8. The generation engine generates a digital twin local excitation time map based on the digital twin model; 2. The system of claim 1, wherein the generation engine updates conduction velocity vector estimates of ablated cells in the digital twin model based on an ablation model that influenced the digital twin local activation time map.

9. 2. The system of claim 1, wherein the precise ablation guidance includes simulating one or more interactions between focal excitations with respect to the digital twin and determining a focus for ablation based on the one or more interactions.

10. The system of claim 1 , wherein the anatomical structure includes an atrium of a heart and the one or more inputs include patient-specific data.

11. 1. A method for ablation procedure guidance implemented by a generation engine running on at least one processor, comprising: receiving, by the generation engine, one or more inputs including one or more images and a conduction velocity vector estimate; generating, by the generation engine, a digital twin of an anatomical structure utilizing the one or more images and the conduction velocity vector estimate; presenting the digital twin via a user interface of the generation engine to provide precision ablation guidance of the anatomical structure and to provide electrophysiology information of the anatomical structure; 23. A method for ablation procedure guidance comprising:

12. The method of claim 11 , wherein the one or more inputs include the one or more images, the conduction velocity vector estimate, and a baseline recording or a lattice Boltzmann model.

13. 12. The method of claim 11, wherein the generation engine determines electrical flow through the anatomical structure based on performing one or more of direction of arrival estimation, clustering, voxelization, and dynamic 3D generation.

14. The method of ablation procedure guidance of claim 11 , wherein the one or more inputs include proarrhythmic effects from an intracardiac electrocardiogram or a surface electrocardiogram.

15. 12. The method of claim 11, wherein the generation engine utilizes a direction of arrival estimate to automatically identify the conduction velocity vector estimate from the one or more inputs and generate the digital twin.

16. 12. The method of ablation procedure guidance of claim 11, wherein the precise ablation guidance comprises simulating how electricity flows through the digital twin based on the conduction velocity vector estimate.

17. the generation engine receives one or more additional inputs; 12. The method of ablation procedure guidance of claim 11, wherein the generation engine generates one or more different proposed ablation approaches for an ablation procedure or performs a remapping operation of the digital twin based on the one or more additional inputs.

18. The generation engine generates a digital twin local excitation time map based on the digital twin model; 12. The ablation procedure guidance method of claim 11, wherein the generation engine updates conduction velocity vector estimates of ablated cells in the digital twin model based on an ablation model that influenced the digital twin local activation time map.

19. 12. The method of ablation procedure guidance of claim 11, wherein the precise ablation guidance comprises simulating one or more interactions between focal excitations with respect to the digital twin and determining a focus for ablation based on the one or more interactions.

20. the anatomical structure includes an atrium of the heart; The method of ablation procedure guidance of claim 11 , wherein the one or more inputs include patient-specific data.

Citation Information

Patent Citations

  • Method and system for mapping local conduction velocity

    JP2017532140A

  • Guiding cardiac ablation using machine learning (ML)

    JP2021049341A

  • Calibration of simulated heart rate curves

    JP2021522052A

  • System and method for deep learning based cardiac electrophysiology model personalization

    US20170330075A1

  • Sequential Mapping of Cardiac Arrhythmia without Fiducial Time Reference

    US20210093217A1