Far-field removal from intracardiac signals.

Abstract

To process cardiac signals.SOLUTION: In one embodiment, a method includes: receiving first intracardiac signals including first far-field components captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a cardiac chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode, which is inserted into the cardiac chamber and not in contact with the tissue of the cardiac chamber; training a neural network to remove far-field components from intracardiac signals responsively to the first intracardiac signals and the at least one far-field signal; receiving second intracardiac signals captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; and applying the trained neural network to the second intracardiac signals to remove respective second far-field components from the second intracardiac signals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 070,897, filed August 27, 2020, and U.S. Provisional Patent Application No. 63 / 073,414, filed September 1, 2020, the disclosures of which are incorporated herein by reference.

[0002] FIELD OF THE INVENTION The present invention relates to medical systems, particularly but not exclusively to processing cardiac signals. [Background technology]

[0003] A wide range of medical procedures involve the placement of probes, such as catheters, inside a patient's body. Position sensing systems have been developed to track such probes. Magnetic position sensing is one method known in the art. In magnetic position sensing, magnetic field generators are typically placed at known locations outside the patient's body. A magnetic field sensor in the distal end of the probe generates electrical signals in response to these magnetic fields, and these signals are processed to determine the coordinate position of the distal end of the probe. These methods and systems are described in U.S. Patent Nos. 5,391,199, 6,690,963, 6,484,118, 6,239,724, 6,618,612, and 6,332,089, WO 1996 / 005768, and U.S. Patent Application Publication Nos. 2002 / 0065455, 2003 / 0120150, and 2004 / 0068178. Position may also be tracked using impedance or current-based systems.

[0004] One medical procedure in which these types of probes or catheters have proven extremely useful is in the treatment of cardiac arrhythmias, which, and atrial fibrillation in particular, remain common and dangerous conditions, especially in the aging population.

[0005] Diagnosis and treatment of cardiac arrhythmias involve mapping the electrical properties of cardiac tissue, particularly the endocardium, and selectively ablating the cardiac tissue through the application of energy. Such ablation can stop or modify the propagation of unwanted electrical signals from one part of the heart to another. The ablation process disrupts unwanted electrical pathways by creating non-conductive lesions. Various energy delivery modalities have been previously disclosed for creating lesions, including the use of microwave, laser, and more commonly, radiofrequency energy to create conduction blocks along cardiac tissue walls. In a two-step mapping-then-ablation procedure, a catheter containing one or more electrical sensors is typically advanced into the heart to detect and measure electrical activity at each point within the heart by acquiring data at multiple points. These data are then used to select a target region of the endocardium for this ablation.

[0006] Electrode catheters have been commonly used in medical practice for many years. Electrode catheters are used to stimulate and map electrical activity within the heart and to ablate sites of abnormal electrical activity. In use, an electrode catheter is inserted into a major vein or artery, such as the femoral vein, and then guided into the heart chamber of interest. A typical ablation procedure involves inserting a catheter with one or more electrodes at its distal end into a heart chamber. A reference electrode is typically taped to the patient's skin or may be provided by a second catheter placed in or near the heart. RF (radio frequency) current is applied between the catheter electrode of the ablation catheter and an indifferent electrode (which may be one of the catheter electrodes), and the current is directed to the electrode the medium between , i.e., blood and WeavingThe current flows through the electrode. The distribution of the current may depend on the amount of electrode surface in contact with the tissue compared to blood, which has a higher electrical conductivity than the tissue. Heating of the tissue occurs due to the electrical resistance of the tissue. Sufficient heating of the tissue causes cell destruction in the cardiac tissue, resulting in the formation of lesions in the cardiac tissue, which is electrically non-conductive. In some applications, irreversible electroporation may be performed to ablate the tissue.

[0007] The electrode sensors in the cardiac chambers are far field Electrical activity, i.e., ambient electrical activity occurring away from the sensor, can be detected, which may distort or obscure local electrical activity, i.e., signals occurring at or near the sensor. Commonly assigned U.S. Patent Application Publication No. 2014 / 0005664 to Govari et al. discloses a method for distinguishing a local component in an intracardiac electrode signal due to tissue in contact with the electrode from far-field contributions to the signal, and explains that a therapeutic procedure applied to the tissue can be controlled in response to the distinguished local component. Summary of the Invention [Means for solving the problem]

[0008] According to an embodiment of the present disclosure, a method for analyzing a signal includes receiving a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a heart chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted into the heart chamber but not in contact with tissue of the heart chamber; training an artificial neural network to remove the far-field component from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal; receiving a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a heart chamber of a second living subject; and applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal.

[0009] Further, according to an embodiment of the present disclosure, the method includes calculating a first intracardiac signal in response to at least one far-field signal with a corresponding first far-field component removed, and training includes training an artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed.

[0010] Furthermore, according to an embodiment of the present disclosure, training includes training an autoencoder that includes an encoder and a decoder.

[0011] Additionally, according to an embodiment of the present disclosure, the method includes rendering on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0012] Further, according to an embodiment of the present disclosure, the method includes generating and rendering on a display an electro-anatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0013] Further, in accordance with an embodiment of the present disclosure, the first catheter includes at least one far-field electrode.

[0014] According to yet another embodiment of the present disclosure, a method for detecting cardiac signals includes receiving intracardiac signals captured by at least one sensing electrode of a catheter inserted into a cardiac chamber of a living subject; A method is provided for analyzing the signal, comprising applying the trained artificial neural network to the intracardiac signal to remove corresponding far-field components from the intracardiac signal.

[0015] Further, according to an embodiment of the present disclosure, the method includes rendering on a display a representation of at least one of the intracardiac signals with a corresponding one of the far-field components removed.

[0016] Additionally, according to an embodiment of the present disclosure, the method includes generating and rendering on a display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed.

[0017] According to another embodiment of the present disclosure, there is also provided a software product including a non-transitory computer-readable medium having stored thereon program instructions that, when read by a central processing unit (CPU), cause the CPU to perform the following steps: receive a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, wherein the at least one sensing electrode is in contact with tissue of a heart chamber of a first living subject; and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with tissue of the heart chamber; training an artificial neural network to remove far-field components from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal;

[0018] Further, according to an embodiment of the present disclosure, the instructions, when loaded by the CPU, also cause the CPU to receive a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject, and apply the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal.

[0019] Still further, in accordance with an embodiment of the present disclosure, the instructions, when read by the CPU, also cause the CPU to: calculate a first intracardiac signal in response to the at least one far-field signal, with a corresponding first far-field component removed; and train an artificial neural network in response to the calculated first intracardiac signal, with the corresponding first far-field component removed.

[0020] Additionally, according to an embodiment of the present disclosure, the instructions, when read by the CPU, cause the CPU to render on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0021] Further, according to an embodiment of the present disclosure, the instructions, when read by the CPU, cause the CPU to generate and render on a display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0022] According to yet another embodiment of the present disclosure, there is also provided a software product including a non-transitory computer-readable medium having stored thereon program instructions that, when read by a central processing unit (CPU), cause the CPU to receive intracardiac signals captured by at least one sensing electrode of a catheter inserted into a cardiac chamber of a living subject, and apply a trained artificial neural network to the intracardiac signals to remove corresponding far-field components from the intracardiac signals.

[0023] Further, according to an embodiment of the present disclosure, the instructions, when read by the CPU, cause the CPU to render on a display a representation of at least one of the intracardiac signals with a corresponding one of the far-field components removed.

[0024] Still further, according to an embodiment of the present disclosure, the instructions, when read by the CPU, cause the CPU to generate and render on a display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed.

[0025] According to yet another embodiment of the present disclosure, there is provided a medical system comprising: a first catheter including at least one first sensing electrode configured to be inserted into a cardiac chamber of a first living subject; and a processor configured to receive a first intracardiac signal including a first far-field component captured by the at least one first sensing electrode of the first catheter, wherein the at least one sensing electrode is in contact with tissue of the cardiac chamber of the first living subject, and at least one far-field signal captured from at least one far-field electrode inserted into the cardiac chamber but not in contact with tissue of the cardiac chamber; and train an artificial neural network to remove the far-field component from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal.

[0026] Further, according to an embodiment of the present disclosure, a processor is configured to: calculate a first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; and train an artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed.

[0027] Further, according to an embodiment of the present disclosure, the artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to train the autoencoder to remove far-field components from the intracardiac signal in response to the received first intracardiac signal and at least one far-field signal.

[0028] Further, according to an embodiment of the present disclosure, the system further includes a second catheter including at least one second sensing electrode configured to be inserted into a cardiac chamber of the second living subject, and the processor is also configured to receive a second intracardiac signal captured by the at least one second sensing electrode of the second catheter inserted into the cardiac chamber of the second living subject, and apply the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal.

[0029] Additionally, according to an embodiment of the present disclosure, the trained artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor applies the autoencoder to the second intracardiac signal to derive the corresponding second intracardiac signal from the second intracardiac signal.

[0030] Further, according to an embodiment of the present disclosure, the system includes a display, and the processor is configured to render on the display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0031] Further, in accordance with an embodiment of the present disclosure, there is provided a display, and the processor is configured to generate and render on the display an electro-anatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0032] Further, in accordance with an embodiment of the present disclosure, the first catheter includes at least one far-field electrode.

[0033] Additionally, according to an embodiment of the present disclosure, the first catheter includes an expandable distal end basket assembly, at least one first sensing electrode is disposed on the basket assembly, and at least one far-field electrode is positioned within the basket assembly to prevent the at least one far-field electrode from contacting tissue of a cardiac chamber of the first living subject.

[0034] According to yet another embodiment of the present disclosure, there is provided a medical system comprising: a catheter including at least one sensing electrode configured to be inserted into a cardiac chamber of a living subject; and a processor configured to receive intracardiac signals captured by the at least one sensing electrode inserted into the cardiac chamber and to apply a trained artificial neural network to the intracardiac signals to remove corresponding far-field components from the intracardiac signals.

[0035] Further, according to an embodiment of the present disclosure, the trained artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to apply the autoencoder to the intracardiac signals to remove corresponding far-field components from the intracardiac signals.

[0036] Further, according to an embodiment of the present disclosure, the system includes a display, and the processor is configured to render a representation of at least one of the intracardiac signals on the display with a corresponding one of the far-field components removed.

[0037] Still further, in accordance with an embodiment of the present disclosure, a display is provided, and the processor is configured to generate and render on the display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed. [Brief explanation of the drawings]

[0038] The present invention will be understood from the following detailed description taken in conjunction with the accompanying drawings. [Figure 1]1 is a pictorial illustration of a system for performing catheter procedures on the heart, constructed and operative in accordance with an exemplary embodiment of the present invention; [Figure 2] FIG. 2 is a perspective view of a catheter for use in the system of FIG. 1. [Figure 3] FIG. 2 is a detailed schematic diagram of an electrode assembly for use with the system of FIG. 1. [Figure 4] 4 is a predicted graph of a signal that may be obtained using the electrode assembly of FIG. 3. [Figure 5] FIG. 2 is a schematic diagram of an artificial neural network for use in the system of FIG. 1. [Figure 6] FIG. 6 is a schematic diagram illustrating the training of the artificial neural network of FIG. 5. [Figure 7] FIG. 6 is a flow diagram including steps in a method for training the artificial neural network of FIG. 5. [Figure 8] 2 is a schematic diagram of a catheter for use in the system of FIG. 1 and the signals captured by the catheter. [Figure 9] FIG. 9 is a schematic diagram illustrating the processing of the captured signal of FIG. 8 being processed by a trained artificial neural network. [Figure 10] 9 is a flow diagram including steps in a method for processing the captured signal of FIG. 8 using a trained artificial neural network. [Figure 11] FIG. 1 is a schematic diagram of a displayed intracardiac signal. [Figure 12] FIG. 1 is a schematic diagram of a displayed electroanatomical map. DETAILED DESCRIPTION OF THE INVENTION

[0039] As mentioned previously, electrode sensors within the cardiac chambers far fieldFar-field electrical activity, i.e., ambient electrical activity occurring far from the sensor, can be detected and may distort or obscure local electrical activity, i.e., signals occurring at or near the sensor. Removal of far-field electrical activity from intracardiac signals is not a trivial problem, as the appearance of the far-field depends on many factors, including electrode shape and size, catheter position, anatomical structure, etc. Additionally, the far-field and near-field share common frequencies, and therefore simply using low-pass, high-pass, or band-pass filters does not provide a satisfactory solution.

[0040] Certain catheters but , can be used to provide a signal that can be used to remove far-field components from intracardiac signals. For example, a basket catheter may include a central electrode located in the center of the basket, which remains sufficiently far from cardiac tissue to provide a reasonable estimate of the far-field components. The signal sensed by the central electrode can be used to remove the far-field components from intracardiac signals sensed by the basket electrodes. However, not all catheters have electrodes that measure only the far field. For example, balloon catheters or flat grid catheters do not always include electrodes that are sufficiently far from tissue. For such catheters, the problem of removing the far-field components from sensed intracardiac signals remains.

[0041] Embodiments of the present invention solve the above problems by training an artificial neural network (ANN), such as an autoencoder, to remove far-field components from intracardiac signals based on a set of training signals, which may be provided by a basket catheter that captures intracardiac signals within a heart chamber and simultaneously captures far-field signals using a far-field electrode (such as a central electrode disposed at the center of a basket assembly of the basket catheter).

[0042] The ANN may be trained by inputting the captured intracardiac signal into the ANN. Using an iterative process, the parameters of the ANN are iteratively updated to reduce the difference between the actual output of the ANN and the desired output (e.g., the intracardiac signal with the far-field component removed).

[0043] Once trained, the ANN may be applied to other intracardiac signals captured by another catheter (e.g., a catheter without "far-field electrodes") in the same or a different patient to remove far-field components from the captured intracardiac signals.

[0044] In some embodiments, the weights of the ANN may be transmitted to a cloud server where the ANN can be executed to remove the far-field components from the intracardiac signals transmitted to the server.

[0045] System Description Reference is now made to FIG. 1, which is a diagrammatic illustration of a system 10 for performing catheter procedures on a heart 12, constructed and operative in accordance with an embodiment of the present invention. The medical system 10 may be configured to assess electrical activity and perform ablation procedures on the heart 12 of a living subject. The system includes a catheter 14 that is percutaneously inserted by an operator 16 through the patient's vascular system into a chamber or vasculature of the heart 12. The operator 16, typically a physician, brings the distal end 18 of the catheter into contact with the heart wall, e.g., at an ablation target site. Electrical activity maps may be prepared according to methods disclosed in U.S. Patent Nos. 6,226,542, 6,301,496, and 6,892,091. One commercially available product embodying elements of the system 10 is available as the CARTO® 3 System, commercially available from Biosense Webster, Inc., 3333 Diamond Canyon Road, Diamond Bar, CA 91765. This system can be modified by one skilled in the art to embody the principles of the invention described herein.

[0046] Regions identified as abnormal, for example, by evaluation of electrical activity maps, can be ablated by applying thermal energy, such as by passing radiofrequency current through wires within the catheter to one or more electrodes at the distal end 18 that apply radiofrequency energy to the myocardium. This energy is absorbed within the tissue, heating it to the point where it permanently loses its electrical excitability. If successful, this procedure creates non-conducting lesions in the cardiac tissue that interrupt the abnormal electrical pathways that cause the arrhythmia. The principles of the present invention can be applied to different heart chambers to diagnose and treat a number of different cardiac arrhythmias.

[0047] The catheter 14 typically includes a handle 20 with suitable controls thereon to enable the operator 16 to steer, position, and orient the distal end 18 of the catheter 14 as desired to perform ablation. To assist the operator 16, the distal portion of the catheter 14 contains a position sensor (not shown) that provides signals to a processor 22 located in a console 24. The processor 22 may perform several processing functions, as described below.

[0048] Wire connections 35 may couple console 24 to body surface electrodes 30 and other components of a positioning subsystem for measuring coordinates of the position and orientation of catheter 14. Processor 22 or another processor (not shown) may be an element of the positioning subsystem. As taught in U.S. Pat. No. 7,536,218, catheter electrodes (not shown) and body surface electrodes 30 may be used to measure tissue impedance at the ablation site. A temperature sensor (not shown), typically a thermocouple or thermistor, may be placed on the ablation surface of the distal portion of catheter 14, as described below.

[0049] Console 24 typically houses one or more ablation power generators 25. Catheter 14 may be adapted to deliver ablation energy to the heart using any known ablation technique, such as radiofrequency energy, ultrasound energy, irreversible electroporation, and laser-generated light energy. Such methods are disclosed in U.S. Patent Nos. 6,814,733, 6,997,924, and 7,156,816.

[0050] In one embodiment, the positioning subsystem comprises a magnetic position tracking arrangement that generates magnetic fields within a predetermined working volume using field generating coils 28 and senses these fields at the catheter to determine the position and orientation of the catheter 14. Positioning subsystems are described in U.S. Patent Nos. 7,756,576 and 7,536,218.

[0051] As mentioned above, catheter 14 is coupled to console 24, which allows operator 16 to observe and adjust the functions of catheter 14. Console 24 includes a processor 22, typically a computer with appropriate signal processing circuitry. Processor 22 also includes a display 29. (e.g. monitor) is coupled to drive do. The signal processing circuitry typically receives, amplifies, filters, and digitizes signals from the catheter 14, including signals generated by sensors, such as electrical, temperature, and contact force sensors, as well as a plurality of position sensing electrodes (not shown), located distally within the catheter 14. The digitized signals are received by the console 24 and a positioning system and used to calculate the position and orientation of the catheter 14 and to analyze the electrical signals from the electrodes.

[0052] To generate an electroanatomic map, processor 22 typically includes an electroanatomic map generator, an image registration program, an image or data analysis program, and a graphical user interface configured to present graphical information on display 29.

[0053] System 10 typically includes other elements, not shown for simplicity. For example, system 10 may include an electrocardiogram (ECG) monitor coupled to receive signals from one or more body surface electrodes for providing ECG-synchronized signals to console 24. As noted above, system 10 also typically includes a reference position sensor, either an externally applied reference patch attached to the outside of the patient's body or an internally placed catheter inserted into heart 12 while maintained in a fixed position relative to the heart. Conventional pumps and lines may be provided for circulating fluid through catheter 14 to cool the ablation site. System 10 may receive image data from an external imaging modality, such as an MRI unit, and may include an image processor, which may be incorporated into or invoked by processor 22, for generating and displaying images.

[0054] In practice, some or all of the functionality of processor 22 may be combined into a single physical component or may be embodied using multiple physical components. These physical components may comprise hardwired or programmable devices, or a combination of the two. In some embodiments, at least some of the functionality of processor 22 may be performed by a programmable processor under the control of suitable software. This software may be downloaded to the device in electronic form, for example, over a network. Alternatively, or in addition, this software may be stored in a tangible, non-transitory, computer-readable memory, such as optical, magnetic, or electronic memory. memory It may be stored on a medium.

[0055] Reference is now made to FIG. 2, which is a perspective view of a catheter 14 for use in the system 10 of FIG.

[0056] The catheter 14 comprises an elongate shaft 39 having proximal and distal ends, a control handle 20 at the proximal end of the catheter body, and an expandable distal basket assembly 43 mounted on the distal end of the shaft 39 .

[0057] The shaft 39 comprises an elongated tubular structure having a single axial or central lumen (not shown), although it can optionally have multiple lumens if desired. The shaft 39 is flexible, i.e., bendable, but substantially incompressible along its length. The shaft 39 can be of any suitable construction and made of any suitable material. In some embodiments, the elongated shaft 39 includes an outer wall made of polyurethane or polyether block amide. The outer wall includes an embedded braided mesh, such as stainless steel, to increase the torsional stiffness of the shaft 39, such that when the control handle 20 is rotated, the distal end of the shaft 39 rotates in a corresponding manner.

[0058] The outer diameter of the shaft 39 is not critical and may range from about 2 mm to 5 mm. Similarly, the thickness of the outer wall is not critical and is generally thin enough to allow the central lumen to accommodate any one or more of the puller wires, lead wires, sensor cables, and any other wires, cables, or tubing. Optionally, the inner surface of the outer wall is lined with a stiffening tube (not shown) to improve torsional stability. Examples of catheter body configurations suitable for use in connection with the present invention are described and illustrated in U.S. Patent No. 6,064,905, the entire disclosure of which is incorporated herein by reference.

[0059] Assembly 43 is mounted to the distal end of shaft 39. As shown in FIG. 2, basket assembly 43 includes five splines 45, or arms, mounted generally evenly spaced around a contraction wire 47 that is coupled to the distal tip of assembly 43, causing assembly 43 to contract, retract, and expand when a pulling or pushing force, as the case may be, is applied longitudinally to contraction wire 47. Contraction wire 47 forms the longitudinal axis of symmetry for assembly 43. All splines 45 are attached, directly or indirectly, to contraction wire 47 at their distal ends and to shaft 39 at their proximal ends. When contraction wire 47 is moved longitudinally to expand and contract assembly 43, splines 45 bow outward in the extended position and are generally straight in the contracted position. As will be appreciated by those skilled in the art, the number of splines 45 can vary as needed for a particular application, such that the assembly 43 has at least two splines, typically at least three splines, and as many as ten or more splines. The expandable distal basket assembly 43 is not limited to the configuration depicted in the figures, but can also include other designs, such as spherical or ovoid designs, that include multiple expandable arms directly or indirectly connected at their proximal and distal ends.

[0060] The assembly 43 includes at least one sensing electrode 49 disposed thereon. In some embodiments,Each of the splines 45 may comprise a non-conductively coated flexible wire to which one or more sensing electrodes 49 (e.g., ring spline electrodes) are attached. The electrodes 49 are conveniently referred to as "sensing electrodes," but may also be used to perform ablation. In some embodiments, the flexible wires each comprise a flat nitinol wire, and the non-conductive coatings each comprise a biocompatible plastic tubing, such as polyurethane or polyimide tubing. Alternatively, if a sufficiently rigid non-conductive material is used for the non-conductive coating to allow expansion of the assembly 43, the splines 45 can be designed without an internal flexible wire, as long as the splines have a non-conductive outer surface for attachment of the sensing electrodes 49 over at least a portion of their surface. In some embodiments, the splines may be formed from a flexible polymer strip circuit, with the electrodes 49 disposed on each outer surface of the flexible polymer strip circuit.

[0061] Each of the sensing electrodes 49 on the splines 45 is electrically connected to an appropriate mapping or monitoring system and / or ablation energy source by an electrode lead wire (not shown). The electrode lead wire extends through the control handle 20, through a lumen in the shaft 39, into the non-conductive coating of the corresponding spline 45, and is attached to its corresponding sensing electrode 49 by any suitable method. The catheter 14 includes a far-field electrode 51, e.g., a cylindrical electrode, disposed on the contraction wire 47. The far-field electrode 51 is disposed within the expandable distal basket assembly 43 to prevent the far-field electrode 51 from contacting tissue in the chambers of the heart 12. In some embodiments, the catheter 14 may include more than one far-field electrode 51.

[0062] The function of far-field electrodes 51 is described below. In some embodiments, far-field electrodes 51 may be provided on a different catheter that is inserted into heart 12 simultaneously with catheter 14. Further details of catheter 14 are described in the above-referenced U.S. Patent No. 6,748,255.

[0063] Catheter 14 typically has a plurality of electrodes 49 disposed on a plurality of flexible splines of basket assembly 43. Catheter 14 is configured to be inserted into a chamber of heart 12 (FIG. 1) in a collapsed configuration in which splines 45 are relatively close together. Once inside heart 12, splines 45 can be formed into their expanded basket shape by contraction wires 47 that hold the distal ends of splines 45 and pull the distal ends of splines 45 proximally.

[0064] Reference is now made to Figure 3, which is a detailed schematic diagram of the expandable distal basket assembly 43 of Figure 2. In the expanded configuration of assembly 43, at least a portion of sensing electrode 49 of spline 45 contacts endocardial surface 53 of heart 12, obtaining a signal corresponding to the electrode potential generated at contact with the surface. However, because sensing electrode 49 is within a conductive medium (blood), in addition to the electrode potential from the contact, the obtained signal also includes far-field components from other regions of heart 12.

[0065] The far-field components constitute interfering signals with the endocardial surface electrode potentials. To cancel the interference, embodiments of the present invention position far-field electrodes 51 on the contraction wire 47. In the expanded configuration of assembly 43, the far-field electrodes 51 are positioned on the contraction wire 47 so as to be approximately equidistant from all corresponding sensing electrodes 49, i.e., sensing electrodes 49 that are equidistant from a fixed reference point on the long axis of the catheter, such as reference point 55 at the proximal end of assembly 43, and are shielded from contact with the cardiac surface by spline 45. For example, electrodes 57, 59 may be As shown by dashed lines 61 and 63, equidistant from reference point 55 ,Ma The far-field electrode 51 is also equidistant from the sensing electrode 49. If the far-field electrode 51 is at least 0.5 cm away from the sensing electrode 49 in the expanded configuration of the assembly 43, it will obtain a far-field signal but not a near-field signal from the endocardial surface 53. However, the signal e(t) obtained by the sensing electrode 49 will have both far-field and surface (near-field) components. The far-field component signal x(t) obtained by the far-field electrode 51 is , feelingFrom the signal e(t) obtained by the sensing electrode 49, To counteract the interference these electrodes experience, That is, by signal subtraction: e(t)-x(t). Additionally or alternatively, removal of the far field components may be achieved using any suitable method.

[0066] In some embodiments, the catheter 14 includes a distal position sensor 65 mounted at or near where the distal end of the spine is connected, and a proximal position sensor 67 mounted at or near the proximal end of the assembly 43, so that during use the coordinates of the position sensor 65 relative to the coordinates of the position sensor 67 can be determined and used, together with known information about the curvature of the spline 45, to find the position of each of the sensing electrodes 49.

[0067] Reference is now made to Figure 4, which is a predicted graph of an exemplary signal that may be obtained using assembly 43 of Figure 3. Graph 69 shows the intracardiac signal e(t) obtained from a unipolar or bipolar configuration of sensing electrodes 49. Graph 71 is the signal trace x(t) of the far-field electrode 51, which may be a simultaneous trace. Graph 73 is the signal trace obtained when the far-field component in the electrogram e(t) is removed by subtraction of the signal in graph 71 from the signal in graph 69, or by a modified application of the algorithm described in U.S. Patent Publication No. 2016 / 0175023 or U.S. Patent No. 9,554,718.

[0068] Reference is now made to FIG. 5, which is a schematic diagram of an artificial neural network 75 for use in the system 10 of FIG.

[0069] A neural network is a network or circuit of neurons, or in the modern sense, an artificial neural network, composed of artificial neurons or nodes. The connections of biological neurons 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 linear combinations. An activation function can control the amplitude of the output. For example, the allowed range of the output is usually 0 to 1, but can also be -1 to 1.

[0070] These artificial networks can be used in predictive modeling, adaptive control, and other applications, and can be trained through datasets. Self-learning resulting from experience can occur within the network, allowing it to draw conclusions from complex and seemingly unrelated sets of information.

[0071] For completeness, a biological neural network consists of a group of chemically connected or functionally associated neurons. One neuron may be connected to many other neurons, and the total number of neurons and connections in the network may vary widely. Connections, called synapses, are usually formed from axons to dendrites, although dendritic synapses and other connections are also possible. Apart from electrical signaling, other forms of signaling result from the diffusion of neurotransmitters.

[0072] Artificial intelligence, cognitive modeling, and neural networks are information processing paradigms inspired by the way biological nervous systems process data. Artificial intelligence and cognitive modeling attempt to simulate some of the properties of biological neural networks. In the field of artificial intelligence, artificial neural networks have been successfully applied to speech recognition, image analysis, and adaptive control, and to build software agents or autonomous robots (in computer and video games).

[0073] A neural network (NN) is an interconnected group of natural or artificial neurons that uses a mathematical or computational model based on a connectionist approach to computation for information processing, in the case of artificial neurons, called an artificial neural network (ANN) or simulated neural network (SNN). In most cases, ANNs are adaptive systems that change their structure based on external or internal information flowing through the network. More practically, neural networks are nonlinear statistical data modeling or decision-making tools. They can be used to model complex relationships between inputs and outputs and to find patterns in data.

[0074] In some embodiments, the artificial neural network 75 may include an autoencoder 77 including an encoder 79 and a decoder 81, as shown in Figure 5. In other embodiments, the artificial neural network 75 may include any suitable ANN. The artificial neural network 75 may be implemented in software and / or hardware.

[0075] The encoder 79 includes an input layer 83 where an input is received. The encoder then includes one or more hidden layers 85 that progressively compress the input into a code 87. The decoder 81 includes one or more hidden layers 89 that progressively decompress the code 87 up to an output layer 91 where the output of the autoencoder 77 is provided. The autoencoder 77 includes weights between its layers. The autoencoder 77 manipulates the data received at the input layer 83 according to the values ​​of the various weights between its layers.

[0076] The weights of the autoencoder 77 are updated during the training of the autoencoder 77 so that the autoencoder 77 performs the data manipulation task that it is trained to perform. In the example of Figure 5, the autoencoder 77 is trained to remove far-field components from intracardiac signals, as will be described in more detail with reference to Figures 6 and 7.

[0077] The number of layers and layer width within the autoencoder 77 may be configurable. As the number of layers and layer width increase, the accuracy with which the autoencoder 77 can manipulate data according to the task at hand increases. However, more layers and wider layers generally require more training data, more training time, and training may not converge. As an example, the input layer 83 may include 400 neurons (e.g., to compress a batch of 400 samples). The encoder 79 may include five layers (e.g., 400, 200, 100, 50, and 25) that compress by a factor of two. The decoder may include five layers (e.g., 25, 50, 100, 200, and 400) that restore by a factor of two.

[0078] Reference is now made to Figures 6 and 7. Figure 6 is a schematic diagram of the training of the artificial neural network 75 of Figure 5. Figure 7 is a flow diagram 100 including steps in a method for training the artificial neural network 75 of Figure 5.

[0079] The artificial neural network 75 is trained based on data captured from a catheter, such as the catheter 14 of FIGS. 1-3. An electrode 49 (FIG. 3) of the catheter 14 is in contact with tissue (e.g., the endocardial surface 53 (FIG. 3)) of a chamber (FIG. 1) of the heart 12. The electrode 49 provides an intracardiac signal 93 that includes a far-field component. To provide high-quality training data, the operator 16 typically captures the intracardiac signal 93. 3 Provides 49 electrodes and the organization Ensure that there is good quality contact between the far-field electrodes 51 (FIG. 3) of the catheter 14 provide at least one far-field signal.

[0080] The processor 22 (FIG. 1) is configured to receive intracardiac signals 93 (block 102) including far-field components captured by one or more of the electrodes 49 in contact with tissue of a heart chamber of a living subject. The catheter 14 may provide signals 93 from different electrodes 49 while in a given position within the heart chamber and / or from one or more electrodes 49 while the catheter 14 is moved to different positions within the heart chamber. The intracardiac signals 93 may be provided from different heart chambers and even from different living subjects.

[0081] Processor 22 (FIG. 1) is also configured to receive (block 102) the far-field signals captured by far-field electrodes 51 simultaneously with intracardiac signals 93 captured by electrodes 49 of catheter 14, regardless of the position of catheter 14 (inserted within the heart chamber and not in contact with tissue of the heart chamber) during the capture of intracardiac signals 93. Thus, each intracardiac signal 93 has a corresponding far-field signal captured over the same time interval during which intracardiac signal 93 was captured. Multiple intracardiac signals 93 may have the same corresponding far-field signal captured simultaneously with the multiple intracardiac signals 93.

[0082] In some embodiments, processor 22 (FIG. 1) is configured to calculate intracardiac signal 93 in response to the far-field signal, with the corresponding far-field components removed, to obtain cleaned intracardiac signal 95 (block 104). Cleaned intracardiac signal 95 may be calculated using one of the methods described above with reference to FIG. 3, or any suitable method for removing far-field components from an intracardiac signal.

[0083] The processor 22 is configured to train (block 106) an artificial neural network 75 (e.g., autoencoder 77) to remove far-field components from the intracardiac signal 93 in response to the received intracardiac signal 93 and the far-field signal captured by the far-field electrodes 51 (block 106). In some embodiments, the processor 22 is configured to train the artificial neural network 75 in response to the intracardiac signal 93 and the calculated cleaned intracardiac signal 95 (i.e., the intracardiac signal 93 with the corresponding far-field components removed).

[0084] Training the artificial neural network 75 is generally an iterative process. One method for training the artificial neural network 75 is described below.

[0085] The processor 22 is configured to input the received intracardiac signals 93 to the artificial neural network 75 (block 108, arrow 97). For example, the intracardiac signals 93 are input to the input layer 83 of the encoder 79. The processor 22 is configured to compare the outputs of the artificial neural network 75 (e.g., the outputs of the decoder 81 of the autoencoder 77) with the desired outputs, i.e., the corresponding cleaned intracardiac signals 95 (block 110, arrow 99). For example, given a set of intracardiac signals A, B, and C output by the artificial neural network 75 and a set of corresponding cleaned intracardiac signals A', B', and C', the processor 22 would compare A with A', B with B', C with C', etc. The comparisons are typically performed using a suitable loss function that calculates the overall difference between all outputs of the artificial neural network 75 and all outputs of all desired outputs (e.g., all corresponding cleaned intracardiac signals 95).

[0086] At decision block 112, the processor 22 is configured to determine whether the difference between the output of the artificial neural network 75 and the desired output is sufficiently small. If the difference between the output of the artificial neural network 75 and the desired output is sufficiently small (branch 118), the processor 22 is configured to save the parameters (e.g., weights) of the artificial neural network 75 (e.g., autoencoder 77) (block 120) and / or transmit the parameters (e.g., weights) to a cloud processing server (not shown).

[0087] The difference is small enough Not bad If (branch 114), the processor 22 of The parameters (e.g., weights) (e.g., of the autoencoder 77) are then adjusted (block 116) to reduce the difference between the output of the artificial neural network 75 and the desired output of the artificial neural network 75. The minimized difference is the overall difference between all outputs of the artificial neural network 75 and all desired outputs (e.g., all corresponding cleaned intracardiac signals 95). The processor 22 is configured to adjust the parameters using any suitable optimization algorithm, e.g., a gradient descent algorithm such as Adam optimization. The steps of blocks 108, 110, and 112 are then repeated.

[0088] Reference is now made to Figure 8, which is a schematic illustration of a catheter 200 for use in the system 10 of Figure 1 and an intracardiac signal 202 captured by the catheter 200. The catheter 200 is a flat grid catheter including a plurality of splines 204 (only some of which are labeled for simplicity) with electrodes 206 on each spline 204. The catheter 200 is configured to be inserted into a cardiac chamber of a living subject. The living subject may be the same living subject into which the catheter 14 was inserted and the artificial neural network 75 was trained, or it may be a different living subject.

[0089] The catheter 200 is generally in contact with cardiac tissue. Does not contain electrodes , and therefore capturing a signal representative of only the far field is very difficult to achieve with the catheter 200. The medical system 10 is configured to remove the far-field component from the intracardiac signal 202 using a trained artificial neural network 75 (FIG. 6), as will be described in more detail with reference to FIGS. 9 and 10.

[0090] Catheter 200 is one example of a catheter that provides an intracardiac signal that includes a removed far-field component. Any suitable catheter (e.g., a balloon catheter), or even one that includes far-field electrodes (e.g., a suitable basket catheter), may then be processed using trained artificial neural network 75 to provide an intracardiac signal that removes the far-field component from the provided intracardiac signal.

[0091] Reference is now made to Figures 9 and 10. Figure 9 is a schematic diagram illustrating the processing of the acquired signal 202 of Figure 8 being processed by a trained artificial neural network 75. Figure 10 is a flow diagram 250 including steps in a method for processing the acquired signal 202 of Figure 8 using a trained artificial neural network 75. Reference is also made to Figure 8.

[0092] Processor 22 (FIG. 1) is configured to receive (block 252) an intracardiac signal 202 captured by sensing electrodes 206 of a catheter 200 inserted into a cardiac chamber of a living subject. Processor 22 is configured to apply a trained artificial neural network 75 to intracardiac signal 202 (block 254, arrow 208) to remove corresponding far-field components from intracardiac signal 202 to generate a corresponding cleaned intracardiac signal 210 (arrow 212).

[0093] In some embodiments, the trained artificial neural network includes a trained autoencoder 77. In these embodiments, the processor 22 (FIG. 1) is configured to apply the autoencoder 77 to the intracardiac signal 202 to remove corresponding far-field components from the intracardiac signal 202.

[0094] Reference is now made to Figure 11, which is a schematic illustration of a representation 214 of an intracardiac signal. Reference is also made to Figure 10. The processor 22 (Figure 1) is optionally configured to render (block 256) on the display 29 a representation 214 of the cleaned intracardiac signal 210 (Figure 9) (i.e., the intracardiac signal 202 with the corresponding far-field components removed).

[0095] Reference is now made to Figure 12, which is a schematic illustration of a displayed electroanatomical map 216. Reference is also made to Figure 10. Processor 22 (Figure 1) is optionally configured to generate and render on display 29 (block 258) electroanatomical map 216 in response to the cleaned intracardiac signal 210 (i.e., the intracardiac signal 202 with the corresponding far-field components removed).

[0096] The term "about" or "approximately" used herein in connection with any numerical value or range of values ​​indicates a suitable dimensional tolerance that enables a portion of a component or a collection of components to function in accordance with its intended purpose as described herein. More specifically, "about" or "approximately" may refer to a range of values ​​of ±20% of the recited value, for example, "about 90%" may refer to a range of values ​​of 72% to 108%.

[0097] Various features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination.

[0098] The above-described embodiments are cited by way of example, and the present invention is not limited to what has been particularly shown and described in the foregoing specification. Rather, the scope of the present invention includes both combinations and subcombinations of the various features described above, as well as variations and modifications thereof not disclosed in the prior art that will occur to those skilled in the art upon reading the foregoing description.

[0099] [Embodiment] (1) A method for analyzing a signal, comprising: receiving a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a heart chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with the tissue of the heart chamber; training an artificial neural network to remove far-field components from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal; receiving a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal. (2) The method of embodiment 1, further comprising: calculating the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; and wherein the training comprises training the artificial neural network in response to the first intracardiac signal calculated with the corresponding first far-field component removed. (3) The method of embodiment 1, wherein the training includes training an autoencoder comprising an encoder and a decoder. (4) The method of embodiment 1, further comprising: rendering on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far field components removed. (5) The method of embodiment 1, further comprising generating and rendering on a display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

[0100] (6) The method of embodiment 1, wherein the first catheter includes the at least one far-field electrode. (7) A method for analyzing a signal, comprising: receiving intracardiac signals captured by at least one sensing electrode of a catheter inserted into a cardiac chamber of a living subject; applying the trained artificial neural network to the intracardiac signals to remove corresponding far-field components from the intracardiac signals. (8) The method of embodiment 7, further comprising rendering on a display a representation of at least one of the intracardiac signals with a corresponding one of the far field components removed. (9) The method of embodiment 7, further comprising generating and rendering on a display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed. (10) A software product including a non-transitory computer-readable medium having stored thereon program instructions, the instructions, when read by a central processing unit (CPU), causing the CPU to: receiving a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a heart chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with the tissue of the heart chamber; and training an artificial neural network to remove far-field components from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal.

[0101] (11) When the instruction is read by the CPU, the CPU: receiving a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; 11. The software product of claim 10, further comprising applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal. (12) When the instruction is read by the CPU, the CPU: calculating the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; 11. The software product of claim 10, further comprising: training the artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed. (13) The software product of embodiment 10, wherein the instructions, when read by the CPU, also cause the CPU to render on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed. (14) The software product of embodiment 10, wherein the instructions, when read by the CPU, also cause the CPU to generate and render on a display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed. (15) A software product including a non-transitory computer-readable medium having stored thereon program instructions, the instructions, when read by a central processing unit (CPU), causing the CPU to: receiving intracardiac signals captured by at least one sensing electrode of a catheter inserted into a cardiac chamber of a living subject; applying the trained artificial neural network to the intracardiac signals to remove corresponding far-field components from the intracardiac signals.

[0102] (16) The software product of embodiment 15, wherein the instructions, when read by the CPU, also cause the CPU to render a representation of at least one of the intracardiac signals on a display with a corresponding one of the far field components removed. (17) The software product of embodiment 15, wherein the instructions, when read by the CPU, also cause the CPU to generate and render on a display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed. (18) A health care system, a first catheter including at least one first sensing electrode configured to be inserted into a cardiac chamber of a first living subject; 1. A processor, comprising: receiving a first intracardiac signal including a first far-field component captured by the at least one first sensing electrode of the first catheter, the at least one sensing electrode being in contact with tissue of the heart chamber of the first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with the tissue of the heart chamber; and a processor configured to train an artificial neural network to remove far-field components from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal. (19) The processor: calculating the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; and training the artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed. (20) The system of embodiment 18, wherein the artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to train the autoencoder in response to the received first intracardiac signal and the at least one far-field signal to remove the far-field component from the intracardiac signal.

[0103] (21) The method further comprises: a second catheter including at least one second sensing electrode configured to be inserted into a cardiac chamber of a second living subject; and the processor: receiving a second intracardiac signal captured by the at least one second sensing electrode of the second catheter inserted into the cardiac chamber of the second living subject; 19. The system of embodiment 18, configured to apply the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal. (22) The system of embodiment 21, wherein the trained artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to apply the autoencoder to the second intracardiac signal to remove the corresponding second far-field component from the second intracardiac signal. (23) The system of embodiment 21, further comprising a display, wherein the processor is configured to render a representation of at least one of the second intracardiac signals on the display with a corresponding one of the second far-field components removed. (24) The system of embodiment 21, further comprising a display, wherein the processor is configured to generate and render on the display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed. (25) The system described in embodiment 18, wherein the first catheter includes the at least one far-field electrode.

[0104] (26) The system described in embodiment 25, wherein the first catheter comprises an expandable distal end basket assembly, the at least one first sensing electrode is disposed on the basket assembly, and the at least one far-field electrode is positioned within the basket assembly to prevent the at least one far-field electrode from contacting the tissue of the cardiac chamber of the first biological subject. (27) A health care system, a catheter including at least one sensing electrode configured to be inserted into a cardiac chamber of a living subject; 1. A processor, comprising: receiving an intracardiac signal captured by the at least one sensing electrode inserted into the heart chamber; a processor configured to apply a trained artificial neural network to the intracardiac signals to remove corresponding far-field components from the intracardiac signals. (28) The system of embodiment 27, wherein the trained artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to apply the autoencoder to the intracardiac signal to remove corresponding far-field components from the intracardiac signal. (29) The system of embodiment 27, further comprising a display, wherein the processor is configured to render a representation of at least one of the intracardiac signals on the display with a corresponding one of the far field components removed. (30) The system of embodiment 27, further comprising a display, wherein the processor is configured to generate and render on the display an electroanatomical map in response to at least one of the intracardiac signals with a corresponding one of the far-field components removed.

Claims

1. 1. A software product including a non-transitory computer-readable medium having stored thereon program instructions, the program instructions, when read by a central processing unit (CPU), causing the CPU to: receiving a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, the at least one first sensing electrode being in contact with tissue of a heart chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with the tissue of the heart chamber; removing a far-field component from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal; training an artificial neural network to output a corresponding far-field-removed signal from the received intracardiac signal in response to the first intracardiac signal and the far-field-removed intracardiac signal; receiving a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal; The software product, wherein the first biological subject and the second biological subject are the same biological subject or different biological subjects.

2. The program instructions, when read by the CPU, cause the CPU to: calculating the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; 2. The software product of claim 1, further comprising: training the artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed.

3. 2. The software product of claim 1, wherein the program instructions, when read by the CPU, also cause the CPU to render on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

4. 2. The software product of claim 1, wherein the program instructions, when read by the CPU, also cause the CPU to generate and render on a display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

5. 1. A health care system comprising: a first catheter including at least one first sensing electrode configured to be inserted into a cardiac chamber of a first living subject; a second catheter including at least one second sensing electrode configured to be inserted into a cardiac chamber of a second living subject; 1. A processor, comprising: receiving a first intracardiac signal including a first far-field component captured by the at least one first sensing electrode of the first catheter, the at least one first sensing electrode being in contact with tissue of the heart chamber of the first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber of the first living subject and not in contact with the tissue of the heart chamber of the first living subject; removing a far-field component from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal; training an artificial neural network to output a corresponding far-field-removed signal from the received intracardiac signal in response to the first intracardiac signal and the far-field-removed intracardiac signal; receiving a second intracardiac signal captured by the at least one second sensing electrode of the second catheter inserted into the cardiac chamber of the second living subject; and applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal; The medical system, wherein the first living subject and the second living subject are the same living subject or different living subjects.

6. the processor: calculating the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed; and training the artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed.

7. 6. The medical system of claim 5, wherein the artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to train the autoencoder in response to the received first intracardiac signal and the at least one far-field signal to remove the far-field component from the intracardiac signal.

8. 6. The medical system of claim 5, wherein the trained artificial neural network comprises an autoencoder including an encoder and a decoder, and the processor is configured to apply the autoencoder to the second intracardiac signal to remove the corresponding second far-field component from the second intracardiac signal.

9. 6. The medical system of claim 5, further comprising a display, wherein the processor is configured to render on the display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

10. 6. The medical system of claim 5, further comprising a display, wherein the processor is configured to generate and render on the display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

11. The medical system of claim 5 , wherein the first catheter includes the at least one far-field electrode.

12. 12. The medical system of claim 11, wherein the first catheter comprises an expandable distal basket assembly, the at least one first sensing electrode is disposed on the distal basket assembly, and the at least one far-field electrode is positioned within the distal basket assembly to prevent the at least one far-field electrode from contacting the tissue of the heart chamber of the first living subject.

13. 1. A computer program for analyzing a signal, comprising: On the computer, receiving a first intracardiac signal including a first far-field component captured by at least one first sensing electrode of a first catheter, the at least one first sensing electrode being in contact with tissue of a heart chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted within the heart chamber and not in contact with the tissue of the heart chamber; removing a far-field component from the intracardiac signal in response to the received first intracardiac signal and the at least one far-field signal; training an artificial neural network to output a corresponding far-field-removed signal from the received intracardiac signal in response to the first intracardiac signal and the far-field-removed intracardiac signal; receiving a second intracardiac signal captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; applying the trained artificial neural network to the second intracardiac signal to remove a corresponding second far-field component from the second intracardiac signal; The computer program, wherein the first biological subject and the second biological subject are the same biological subject or different biological subjects.

14. The computer program of claim 13, further comprising causing the computer to calculate the first intracardiac signal in response to the at least one far-field signal with a corresponding first far-field component removed, and wherein the training comprises training the artificial neural network in response to the calculated first intracardiac signal with the corresponding first far-field component removed.

15. The computer program product of claim 13 , wherein the training comprises training an autoencoder comprising an encoder and a decoder.

16. The computer program of claim 13, further comprising causing the computer to render on a display a representation of at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

17. The computer program of claim 13, further comprising causing the computer to generate and render on a display an electroanatomical map in response to at least one of the second intracardiac signals with a corresponding one of the second far-field components removed.

18. The computer program of claim 13 , wherein the first catheter includes the at least one far-field electrode.

Images