Automatic detection of cardiac structures in cardiac mapping

Abstract

The present invention, entitled "Automatic Detection of Cardiac Structures in Cardiac Mapping," discloses a system and method for training a neural network to automatically detect cardiac structures of interest. The system includes a processor comprising a neural network training model that receives training data. The training data includes a first input and a second input. The first input includes first electrophysiological data about a first cardiac structure received by electrodes from a first catheter located within the heart. The second input includes second data related to the first cardiac structure. Based on the training data, the neural network training model generates, as output, a determination of whether the first cardiac structure is a cardiac structure of interest.

Description

Technical Field

[0001] This disclosure relates to artificial intelligence and machine learning associated with the automatic detection of the location of specific structures within the heart, and more preferably with the automatic detection of the location of the His bundle in the heart. Background Technology

[0002] It is well known that ablation catheters are used to induce tissue necrosis in the heart to correct arrhythmias (including but not limited to atrial fibrillation, atrial flutter, atrial tachycardia, and ventricular tachycardia). Arrhythmias can cause a variety of dangerous conditions, including irregular heart rates, loss of atrioventricular synchrony, and blood flow stagnation, which can lead to various illnesses and even death. It is believed that the primary cause of many arrhythmias is stray electrical signals in one or more heart chambers.

[0003] During cardiac ablation, an ablation focus is created in the patient's cardiac tissue. To create the ablation focus, a catheter is inserted into the heart so that it contacts the tissue, and electromagnetic radiofrequency (RF) energy is injected into the tissue from the catheter electrodes, resulting in ablation and the creation of the ablation focus.

[0004] The His bundle (also known as the atrioventricular bundle) is a part of the myocardium that originates near the opening of the coronary sinus (CS). The His bundle is a key part of the heart's electrical conduction system because it plays a role in transmitting electrical impulses from the atrioventricular (AV) node, located between the atria and ventricles, to the ventricles of the heart.

[0005] The His bundle is located in a vulnerable area of ​​the heart, and if it is ablated incorrectly, it can have harmful and undesirable effects on the heart's electrical conduction system. During a routine ablation procedure, physicians typically manually mark the His bundle to identify its location within the heart, allowing it to be avoided during the ablation process. This manual marking of the His bundle is both tedious and time-consuming. Furthermore, manual marking can lead to false positive readings, where the electrocardiogram (ECG) signal appears to be a His bundle pulse when it is not.

[0006] There is a need for automated and reliable systems and methods that utilize artificial intelligence and / or machine learning to accurately detect His bundles. Summary of the Invention

[0007] This article describes methods, devices, systems, and models for automatically detecting the location of specific structures within the heart.

[0008] According to one aspect, the subject matter disclosed herein relates to a system for automatically detecting cardiac structures. The system preferably includes: a first catheter located within the heart to receive electrophysiological data regarding a first cardiac structure; a second catheter located at a predetermined position within the heart; and a processor including a neural network. The neural network receives electrophysiological data from the first catheter, receives distance data regarding the distance between the first and second catheters, determines whether the electrophysiological data regarding the first cardiac structure is consistent with predetermined electrophysiological data regarding a cardiac structure of interest, determines whether the distance between the first and second catheters is less than a predetermined threshold, and determines whether the first cardiac structure is a cardiac structure of interest based on the electrophysiological data and the distance data.

[0009] According to another aspect, the subject matter disclosed herein relates to a system for training a neural network to automatically detect cardiac structures. The system includes a processor comprising a neural network training model that receives training data. The training data includes the location of a previously mapped cardiac structure of interest, electrophysiological data about the first cardiac structure received by a first catheter located within the heart, predetermined electrophysiological data about the cardiac structure of interest, distance data about the distance between the first and second catheters, and predetermined thresholds about the distance between points on the first and second catheters. The neural network training model is trained to determine whether the electrophysiological data matches the predetermined electrophysiological data about the cardiac structure of interest, whether the distance data is less than a predetermined value, and to determine whether the first cardiac structure is the cardiac structure of interest based on the training data.

[0010] According to another aspect, the subject matter disclosed herein relates to a method for training a neural network model to automatically detect cardiac structures. The method includes receiving training data by a processor comprising the neural network model. The training data includes the location of a previously mapped cardiac structure of interest, electrophysiological data about the first cardiac structure received by a first catheter located within the heart, predetermined electrophysiological data about the cardiac structure of interest, distance data about the distance between the first and second catheters, and predetermined thresholds about the distance between points on the first and second catheters. The method also includes training the neural network model with the training data. This training includes determining whether the electrophysiological data is consistent with the predetermined electrophysiological data about the cardiac structure of interest, determining whether the distance data is less than a predetermined value, and determining whether the first cardiac structure is the cardiac structure of interest based on the training data.

[0011] On the other hand, the cardiac structure of interest is the His bundle.

[0012] According to another aspect, the first catheter includes the His bundle mapping catheter.

[0013] According to another aspect, the electrophysiological data on the first cardiac structure received by the first catheter includes electrograms, and more specifically, His bundle electrograms.

[0014] According to another aspect, the second catheter includes a coronary sinus catheter, and more specifically, a position sensor.

[0015] According to another aspect, the training data also includes electrocardiogram data generated by surface body electrodes.

[0016] On the other hand, neural networks are trained to determine whether electrocardiogram data are consistent with predetermined electrophysiological data of the cardiac structures of interest.

[0017] According to another aspect, the neural network is trained to determine that the first cardiac structure is the cardiac structure of interest when the electrophysiological data of the first cardiac structure is consistent with the predetermined electrophysiological data of the cardiac structure of interest and the distance data is less than the predetermined value.

[0018] According to another aspect, the neural network is trained to determine that the first cardiac structure is not the cardiac structure of interest when the electrophysiological data of the first cardiac structure is inconsistent with the predetermined electrophysiological data of the cardiac structure of interest or when the distance data is greater than the predetermined value.

[0019] According to another aspect, the predetermined electrophysiological data of the cardiac structures of interest are stored in a database that communicates with a neural network.

[0020] According to another perspective, neural networks are either convolutional neural networks or long short-term memory neural networks.

[0021] In another aspect, the neural network training model determines that the first cardiac structure is the cardiac structure of interest, and compares this determination with a database of known cardiac structure locations to verify its accuracy. When the accuracy of the determination exceeds a predetermined accuracy threshold, the neural network training model is validated as the standard for the cardiac mapping system.

[0022] According to another aspect, the subject matter disclosed herein relates to a system for training a neural network to automatically detect cardiac structures of interest. The system includes a processor comprising a neural network training model that receives training data. The training data includes a first input and a second input. The first input includes first electrophysiological data about a first cardiac structure received by electrodes of a first catheter located within the heart. The second input includes second data related to the first cardiac structure. Based on the training data, the neural network training model generates, as output, a determination of whether the first cardiac structure is a cardiac structure of interest. Attached Figure Description

[0023] A more detailed understanding can be obtained through the following specific embodiments provided by way of example and in conjunction with the accompanying drawings, wherein similar reference numerals in the drawings indicate similar elements, and wherein:

[0024] Figure 1 This is a block diagram of an exemplary system for remotely monitoring and transmitting patient biometrics according to the subject matter of this application.

[0025] Figure 2 This is a system diagram of an example computing environment for network communication based on the subject matter of this application.

[0026] Figure 3 This is a block diagram of an exemplary apparatus that can implement one or more features of this disclosure according to the subject matter of this application.

[0027] Figure 4 The combination shown is based on the subject matter of this application. Figure 3 A graphical depiction of an exemplary device's artificial intelligence system.

[0028] Figure 5 The subject matter of this application is shown in Figure 4 The methods executed in artificial intelligence systems.

[0029] Figure 6 An example of a probability calculated using Naive Bayes according to the subject matter of this application is shown.

[0030] Figure 7 An exemplary decision tree based on the subject matter of this application is shown.

[0031] Figure 8 An exemplary random forest classifier according to the subject matter of this application is shown.

[0032] Figure 9 An exemplary logistic regression based on the subject matter of this application is shown.

[0033] Figure 10 An exemplary support vector machine according to the subject matter of this application is shown.

[0034] Figure 11 An exemplary linear regression model based on the subject matter of this application is shown.

[0035] Figure 12 An exemplary K-means clustering method based on the subject matter of this application is shown.

[0036] Figure 13 An exemplary ensemble learning algorithm based on the subject matter of this application is shown.

[0037] Figure 14 An exemplary neural network according to the subject matter of this application is shown.

[0038] Figure 15 A hardware-based neural network according to the subject matter of this application is shown.

[0039] Figure 16 An electrocardiogram (ECG) signal generated by the contraction (depolarization) and relaxation (repolarization) of the atrial and ventricular myocardium of the heart, according to the subject matter of this application, is shown.

[0040] Figure 17 An exemplary cardiac ablation system according to the subject matter of this application is shown, wherein one or more features of the disclosed subject matter may be implemented.

[0041] Figure 18A Neural networks are shown, such as Figure 17 A neural network that receives input data to train the network and automatically identifies cardiac structures of interest, such as the His bundle, is more efficient and reliable than manual identification by physicians during procedures such as ablation.

[0042] Figure 18B This is a flowchart illustrating an implementation of a module for training a neural network according to the subject matter of this application.

[0043] Figure 19A Images of the heart obtained by fluorescence microscopy according to the subject matter of this application are shown, illustrating various catheters located within the heart during a cardiac ablation procedure.

[0044] Figure 19B Exemplary first and second catheters located within the heart are shown in accordance with the subject matter of this application.

[0045] Figure 20 Exemplary ECG and His-beam electrophoresis (HBE) signals are shown that can be used in accordance with the systems and methods disclosed herein, based on the subject matter of this application.

[0046] Figure 21 An exemplary convolutional neural network (CNN) according to the subject matter of this application is shown.

[0047] Figure 22 An exemplary recurrent neural network (RNN) according to the subject matter of this application is shown.

[0048] Figure 23 A specific implementation of the described system is shown.

[0049] Figure 24 A specific implementation of the described system is shown.

[0050] Figure 25 A specific implementation of the described system is shown. Detailed Implementation

[0051] The present invention provides methods, systems, and programs for automatically detecting the location of specific structures within the heart, and more preferably, for automatically detecting the location of the His bundle within the heart, and for training a neural network to automatically detect the location of such specific structures within the heart.

[0052] Figure 1 This is a block diagram of an exemplary system 100 for remotely monitoring and transmitting patient biometrics (i.e., patient data). Figure 1 In the example shown, system 100 includes a patient biometric monitoring and processing device 102 associated with patient 104, a local computing device 106, a remote computing system 108, a first network 110, and a second network 120.

[0053] According to an exemplary embodiment, the monitoring and processing device 102 may be a device located inside the patient's body (e.g., subcutaneously implantable). The monitoring and processing device 102 may be inserted into the patient's body via any applicable means, including oral injection, surgical insertion via vein or artery, endoscopic procedure, or laparoscopic procedure.

[0054] According to an exemplary embodiment, the monitoring and processing device 102 may be an external device to the patient. For example, as described in more detail below, the monitoring and processing device 102 may include an attachable patch (e.g., which is attached to the patient's skin). The monitoring and processing device 102 may also include a catheter, probe, blood pressure cuff, scale, bracelet or smartwatch biometric tracker, glucose monitor, continuous positive airway pressure (CPAP) machine, or virtually any device that can provide input related to the patient's health or biometrics, having one or more electrodes.

[0055] According to an exemplary embodiment, the monitoring and processing device 102 may include components inside the patient and components outside the patient.

[0056] exist Figure 1 A single monitoring and processing device 102 is shown. However, an exemplary system may include multiple patient biometric monitoring and processing devices. These devices may communicate with one or more other patient biometric monitoring and processing devices. Additionally or alternatively, these devices may communicate with a network 110.

[0057] One or more monitoring and processing devices 102 may acquire patient biometric data (e.g., electrical signals, blood pressure, temperature, blood glucose levels, or other biometric data) and receive from one or more other monitoring and processing devices 102 at least a portion of the acquired patient biometric data representing the acquired patient biometrics and additional information associated with the acquired patient biometrics. The additional information may be, for example, diagnostic information and / or additional information obtained from an additional device such as a wearable device. Each monitoring and processing device 102 may process data, including patient biometrics acquired by itself and data received from one or more other monitoring and processing devices 102.

[0058] exist Figure 1 In this context, network 110 is an example of a near-field network (e.g., a local area network (LAN) or a personal area network (PAN)). Information can be transmitted between monitoring and processing device 102 and local computing device 106 via near-field network 110 using any of a variety of near-field wireless communication protocols such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, Near Field Communication (NFC), Ultraband, Zigbee, or Infrared (IR)).

[0059] In an exemplary embodiment, network 120 may be a wired network, a wireless network, or include one or more wired and wireless networks. For example, network 120 may be a remote network (e.g., a wide area network (WAN), the Internet, or a cellular network). Information may be transmitted via network 120 using any of a variety of remote wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / New Radio).

[0060] In an exemplary embodiment, patient monitoring and processing device 102 may include a patient biometric sensor 112, a processor 114, a user input (UI) sensor 116, a memory 118, and a transmitter-receiver (i.e., transceiver) 122. Patient monitoring and processing device 102 may continuously or periodically monitor, store, process, and transmit any number of various patient biometrics via network 110. Examples of patient biometrics include electrical signals (e.g., ECG signals and brain biometrics), blood pressure data, blood glucose data, and temperature data. Patient biometrics may be monitored and transmitted for the treatment of any number of various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathy, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes).

[0061] In one embodiment, the patient biometric sensor 112 may include, for example, one or more sensors configured to sense a type of biometric patient biometric. For example, the patient biometric sensor 112 may include electrodes, temperature sensors, blood pressure sensors, blood glucose sensors, blood oxygen sensors, pH sensors, accelerometers, and microphones configured to acquire electrical signals (e.g., cardiac signals, brain signals, or other bioelectrical signals).

[0062] In an exemplary embodiment, as described in more detail below, the patient biometric monitoring and processing device 102 may be an ECG monitor for monitoring ECG signals of the heart. The patient biometric sensor 112 of the ECG monitor may include one or more electrodes for acquiring ECG signals. ECG signals can be used to treat various cardiovascular diseases.

[0063] In an exemplary embodiment, transceiver 122 may include a separate transmitter and receiver. Alternatively, transceiver 122 may include a transmitter and receiver integrated into a single device.

[0064] In an exemplary embodiment, processor 114 may be configured to store patient data, such as patient biometric data acquired by patient biometric sensor 112, in memory 118, and transmit patient data across network 110 via transmitter of transceiver 122. Data from one or more other monitoring and processing devices 102 may also be received by receiver of transceiver 122, as described in more detail below.

[0065] According to an exemplary embodiment, the monitoring and processing device 102 includes a UI sensor 116, which may be a piezoelectric sensor or a capacitive sensor configured to receive user input, such as a tap or touch. For example, in response to a patient 104 tapping or touching a surface of the monitoring and processing device 102, the UI sensor 116 can be controlled to achieve capacitive coupling. Gesture recognition can be achieved via any of a variety of capacitance types, such as resistive capacitance, surface capacitance, projected capacitance, surface acoustic waves, piezoelectric, and infrared touch. The capacitive sensor may be positioned over a small area or along the length of a surface, such that a tap or touch on the surface activates the monitoring device.

[0066] As described in more detail below, processor 114 can be configured to selectively respond to different tap patterns (e.g., single or double taps) of a capacitive sensor (which may be UI sensor 116), enabling different tasks of the patch (e.g., data acquisition, storage, or transmission) to be activated based on the detected pattern. In some embodiments, audible feedback can be given to the user from processing device 102 when a gesture is detected.

[0067] In an exemplary embodiment, a local computing device 106 of system 100 communicates with patient biometric monitoring and processing device 102 and may be configured to act as a gateway to remote computing system 108 via a second network 120. For example, local computing device 106 may be a smartphone, smartwatch, tablet, or other portable smart device configured to communicate with other devices via network 120. Alternatively, local computing device 106 may be a fixed or standalone device, such as a fixed base station including, for example, modem and / or router capabilities, a desktop or laptop computer using an executable program to transmit information between processing device 102 and remote computing system 108 via a PC's radio module, or a USB dongle. Patient biometrics may be transmitted between local computing device 106 and patient biometric monitoring and processing device 102 via a near-field wireless network 110, such as a local area network (LAN) (e.g., a personal area network (PAN)), using near-field wireless technology standards (e.g., Bluetooth, Wi-Fi, ZigBee, Z-wave, and other near-field wireless standards). In some implementations, the local computing device 106 may also be configured to display the acquired patient electrical signals and information associated with the acquired patient electrical signals, as described in more detail below.

[0068] In some exemplary embodiments, the remote computing system 108 may be configured to receive at least one of monitored patient biometrics and patient-associated information via a network 120, which is a remote network. For example, if the local computing device 106 is a mobile phone, the network 120 may be a wireless cellular network, and information may be transmitted between the local computing device 106 and the remote computing system 108 via wireless technology standards such as any of the wireless technologies described above. As described in more detail below, the remote computing system 108 may be configured to provide (e.g., visually displayed and / or audibly provided) at least one of patient biometrics and related information to healthcare professionals (e.g., physicians).

[0069] Figure 2 This is a system diagram of an example computing environment 200 communicating with network 120. In some cases, computing environment 200 is integrated into a public cloud computing platform (such as Amazon Web Services or Microsoft Azure), a hybrid cloud computing platform (such as HP Enterprise OneSphere), or a private cloud computing platform.

[0070] like Figure 2 As shown, the computing environment 200 preferably includes a remote computing system 108 (hereinafter referred to as a computer system), which is an example of a computing system on which the embodiments described herein can be implemented.

[0071] The telecomputing system 108 can perform various functions via a processor 220, which may include one or more processors. For example, functions may include analyzing monitored patient biometrics and related information, and providing (e.g., via display 266) alerts, additional information, or instructions based on physician-determined or algorithm-driven thresholds and parameters. As described in more detail below, the telecomputing system 108 can be used to provide a patient information dashboard (e.g., via display 266) to healthcare professionals (e.g., physicians), enabling them to identify and prioritize patients with more critical needs than others.

[0072] like Figure 2 As shown, computer system 210 may include a communication mechanism (such as bus 221) or other communication mechanisms for transmitting information within computer system 210. Computer system 210 also includes one or more processors 220 coupled to bus 221 for processing information. Processor 220 may include one or more CPUs, GPUs, or any other processor known in the art.

[0073] Computer system 210 may also include system memory 230 coupled to bus 221 for storing information and instructions to be executed by processor 220. System memory 230 may include computer-readable storage media in the form of volatile and / or non-volatile memory, such as read-only system memory (ROM) 231 and / or random access memory (RAM) 232. System memory RAM 232 may include other dynamic storage devices (e.g., dynamic RAM, static RAM, and synchronous DRAM). System memory ROM 231 may include other static storage devices (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). Furthermore, system memory 230 may be used to store temporary variables or other intermediate information during processor 220 instruction execution. Basic input / output system 233 (BIOS) may be included among elements within computer system 210, such as routines for transferring information during startup, which may be stored in system memory ROM 231. RAM 232 may contain data and / or program modules that are immediately accessible and / or currently operated by processor 220. The system memory 230 may additionally include, for example, an operating system 234, application programs 235, other program modules 236, and program data 237.

[0074] In an exemplary embodiment, computer system 210 also includes a disk controller 240 coupled to bus 221 to control one or more storage devices, such as hard disks 241 and removable media drives 242 (e.g., floppy disk drives, optical disk drives, tape drives, and / or solid-state drives), for storing information and instructions. Storage devices can be added to computer system 210 using appropriate device interfaces, such as Small Computer System Interface (SCSI), Integrated Device Electronics (IDE), Universal Serial Bus (USB), or FireWire.

[0075] Computer system 210 may also include a display controller 265 coupled to bus 221 to control a monitor or display 266, such as a cathode ray tube (CRT) or liquid crystal display (LCD), to display information to a computer user. The illustrated computer system 210 includes a user input interface 260 and one or more input devices, such as a keyboard 262 and a pointing device 261, for interacting with the computer user and providing information to processor 220. Pointing device 261 may be, for example, a mouse, trackball, or pointer, for transmitting directional information and command selections to processor 220 and for controlling cursor movement on display 266. Display 266 may provide a touchscreen interface that allows input to supplement or replace the communication of directional information and command selections by pointing device 261 and / or keyboard 262.

[0076] In response to processor 220 executing one or more sequences of instructions contained in memory such as system memory 230, computer system 210 may perform some or every one of the functions and methods described herein. Such instructions may be read into system memory 230 from another computer-readable medium such as hard disk 241 or removable media drive 242. Hard disk 241 may contain one or more data repositories and data files used by the embodiments described herein. The contents of the data repositories and data files may be encrypted to enhance security. Processor 220 may also be employed in a multiprocessing arrangement to execute one or more sequences of instructions contained in system memory 230. In alternative embodiments, hardwired circuitry may be used in place of or in combination with software instructions. Therefore, the embodiments are not limited to any particular combination of hardware circuitry and software.

[0077] As described above, computer system 210 may include at least one computer-readable medium or memory for storing instructions programmed according to the embodiments described herein and for containing the data structures, tables, records, or other data described herein. As used herein, the term computer-readable medium refers to any non-transitory tangible medium that participates in providing instructions to processor 220 for execution. Computer-readable media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-limiting examples of non-volatile media include optical discs, solid-state drives, magnetic disks, and magneto-optical disks, such as hard disk 241 or removable media drive 242. Non-limiting examples of volatile media include dynamic memory, such as system memory 230. Non-limiting examples of transmission media include coaxial cables, copper wires, and optical fibers, including conductors constituting bus 221. Transmission media may also take the form of acoustic or optical waves, such as acoustic or optical waves generated during radio wave and infrared data communication.

[0078] The computing environment 200 may also include a computer system 210 that operates in a networked environment using logical connections to the local computing device 106 and one or more other devices, such as personal computers (laptop or desktop computers), mobile devices (e.g., patient mobile devices), servers, routers, network PCs, peer-to-peer devices, or other public network nodes, and typically includes many or all of the elements described above with respect to computer system 210. When used in a networked environment, computer system 210 may include a modem 272 for establishing communications on network 120, such as the Internet. Modem 272 may be connected to system bus 221 via network interface 270 or via another suitable mechanism.

[0079] like Figure 1 and Figure 2 As shown, network 120 can be any network or system known in the art, including the Internet, intranet, local area network (LAN), wide area network (WAN), metropolitan area network (MAN), direct connection or a series of connections, cellular telephone network, or any other network or medium that can facilitate communication between computer system 610 and other computers (e.g., local computing device 106).

[0080] Figure 3This is a block diagram of an exemplary device 300 that may implement one or more features of this disclosure. For example, device 300 may be a local computing device 106. Device 300 may include, for example, a computer, gaming device, handheld device, set-top box, television, mobile phone, or tablet computer. Device 300 includes a processor 302, a memory 304, a storage device 306, one or more input devices 308, and one or more output devices 310. Device 300 may also optionally include an input driver 312 and an output driver 314. It should be understood that device 300 may include... Figure 3 Additional components not shown include an artificial intelligence accelerator.

[0081] In various alternatives, processor 302 includes a central processing unit (CPU), a graphics processing unit (GPU), a CPU and GPU located on the same die, or one or more processor cores, wherein each processor core can be a CPU or a GPU. In various alternatives, memory 304 is located on the same die as processor 302 or is located separately from processor 302. Memory 304 includes volatile or non-volatile memory, such as random access memory (RAM), dynamic RAM, or cache.

[0082] Storage device 306 includes fixed or removable storage devices, such as hard disk drives, solid-state drives, optical disks, or flash drives. Input device 308 includes, but is not limited to, keyboards, keypads, touchscreens, touchpads, detectors, microphones, accelerometers, gyroscopes, biometric scanners, or network connectors (e.g., wireless LAN cards for transmitting and / or receiving wireless IEEE 802 signals). Output device 310 includes, but is not limited to, displays, speakers, printers, haptic feedback devices, one or more lights, antennas, or network connections (e.g., wireless LAN cards for transmitting and / or receiving wireless IEEE 802 signals).

[0083] Input driver 312 communicates with processor 302 and input device 308, and allows processor 302 to receive input from input device 308. Output driver 314 communicates with processor 302 and output device 310, and allows processor 302 to send output to output device 310. It should be noted that input driver 312 and output driver 314 are optional components, and device 300 will operate in the same manner if input driver 312 and output driver 314 are not present. Output driver 314 may include an accelerated processing unit (“APD”) 316 coupled to display device 318. APD receives computation commands and graphics rendering commands from processor 302, processes those computation and graphics rendering commands, and provides pixel output to display device 318 for display. As described further in detail below, APD 316 includes one or more parallel processing units to perform computations according to the Single Instruction Multiple Data (“SIMD”) paradigm. Therefore, although various functions are described herein as being performed by or in conjunction with APD 316, in various alternatives, the functions described as being performed by APD 316 may additionally or alternatively be performed by other computing devices with similar capabilities, which are not driven by a host processor (e.g., processor 302) and provide graphics output to display device 318. For example, any processing system that performs processing tasks according to the SIMD paradigm is expected to perform the functions described herein. Alternatively, computing systems that do not perform processing tasks according to the SIMD paradigm are expected to perform the functions described herein.

[0084] Figure 4 The combination is shown Figure 3 A functional graphical depiction of an exemplary device for an artificial intelligence system 400 is provided. System 400 includes data 410, a machine 420, a model 430, multiple predictions 440, and underlying hardware 450. System 400 operates in such a way that it uses data 410 to train machine 420 while simultaneously building model 430 to enable prediction of multiple outcomes 440. System 400 may operate relative to hardware 450. In such a configuration, data 410 may be associated with hardware 450 and may originate from, for example, monitoring and processing device 102. For example, data 410 may be data being generated or output data associated with hardware 450. Machine 420 may function as or be associated with controller or data collection associated with hardware 450. Model 430 may be configured to model the operation of hardware 450 and the data 410 collected from hardware 450 in order to predict the outcomes achieved by hardware 450. Using the predicted outcomes 440, hardware 450 may be configured to provide a desired outcome 440 from hardware 450.

[0085] Figure 5 It shows in Figure 4A general method 500 is executed in an artificial intelligence system. Method 500 includes collecting data from hardware at step 510. This data may include data currently collected from the hardware, historical data from the hardware, or other data, or various combinations thereof. For example, the data may include measurements taken during a surgical procedure and may be correlated with the outcome of the procedure. For example, the temperature of the heart may be collected and correlated with the outcome of a cardiac procedure.

[0086] At step 520, method 500 includes training the machine on hardware. This training may include analysis and correlation of the data collected in step 510. For example, in the case of the heart, the data on temperature and outcomes may be trained to determine whether there is a correlation or relationship between the heart's temperature and the outcome during the procedure.

[0087] At step 530, method 500 includes building a model on data associated with the hardware. Building the model may include physical hardware or software modeling, algorithmic modeling, etc., as will be described below. This modeling may attempt to represent the collected and trained data.

[0088] At step 540, method 500 includes predicting the outcome of a model associated with the hardware. Such a prediction of the outcome may be based on a trained model. For example, in the case of the heart, if a temperature between 97.7 and 100.2 during the procedure produces a positive outcome, the outcome can be predicted based on the heart's temperature during the procedure in a given procedure. While the model is basic, it is provided for illustrative purposes and to enhance understanding of this disclosure.

[0089] The systems and methods of this invention are used to train machines, build models, and predict outcomes using algorithms. These algorithms can be used to solve trained models and predict hardware-related results. These algorithms can generally be categorized into classification, regression, and clustering algorithms.

[0090] For example, classification algorithms are used to categorize a dependent variable (which is the variable being predicted) into multiple classes and predict the class (dependent variable) given an input. Therefore, classification algorithms are used to predict outcomes from a fixed set of predefined results. Classification algorithms can include Naive Bayes, decision trees, random forest classifiers, logistic regression, support vector machines, and k nearest neighbors.

[0091] Generally speaking, the Naive Bayes algorithm follows Bayes' theorem and employs a probabilistic approach. It should be understood that other probability-based algorithms can also be used, and these algorithms typically operate using similar probabilistic principles to those described below for the exemplary Naive Bayes algorithm.

[0092] Figure 6An example of probabilities computed by Naive Bayes is shown. The probabilistic approach of Bayes' theorem essentially means that the algorithm has a set of prior probabilities for each class of the target, rather than jumping directly into the data. After inputting the data, the Naive Bayes algorithm updates the prior probabilities to form the posterior probabilities. This is given by the following formula:

[0093]

[0094] Naive Bayes and Bayesian algorithms are often useful when it's necessary to predict whether an input belongs to one of n categories in a given list. Probabilistic methods can be used because the probabilities for all n categories will be quite low.

[0095] For example, such as Figure 6 As shown, a person plays golf, depending on factors including, but not limited to, the external weather shown in the first dataset 610. The first dataset 610 shows the weather in the first column and the golf playing results associated with that weather in the second column. In frequency table 620, the frequency of certain events occurring is generated. In frequency table 620, the frequency with which a person plays or does not play golf under each weather condition is determined. Thus, a likelihood table is compiled to generate initial probabilities. For example, the probability of cloudy weather is 0.29, while the probability of playing golf in general is 0.64.

[0096] Posterior probabilities can be generated from likelihood table 630. These posterior probabilities can be configured to answer questions about weather conditions and whether to play golf under those conditions. For example, the probability of playing golf in sunny weather can be expressed using Bayes' theorem:

[0097] P(Yes|Sunny) = P(Sunny|Yes) * P(Yes) / P(Sunny)

[0098] According to likelihood table 630:

[0099] P(Sunny|Yes) = 3 / 9 = 0.33

[0100] P(sunny) = 5 / 14 = 0.36

[0101] P(is) = 9 / 14 = 0.64.

[0102] Therefore, P(is|sunny) = 0.33 * 0.64 / 0.36 or approximately 0.60 (60%).

[0103] Generally, a decision tree is a tree structure similar to a flowchart, where each outer node represents a test on an attribute and each branch represents the result of that test. Leaf nodes contain the actual predicted labels. A decision tree starts at the root, where attribute values ​​are compared until a leaf node is reached. Decision trees can be used as classifiers when dealing with high-dimensional data and when little time has been spent on data preparation. Decision trees can take the form of simple decision trees, linear decision trees, algebraic decision trees, deterministic decision trees, stochastic decision trees, nondeterministic decision trees, and quantum decision trees. The following sections... Figure 7 An example decision tree is provided in the document.

[0104] Figure 7 A decision tree for deciding whether to play golf is shown, following the same structure as the Bayesian example above. In the decision tree, the first node 710 checks the weather, thus considering sunny 712, cloudy 714, and rainy 716 as choices to proceed down the decision tree. If the weather is sunny, the tree's leg follows to a second node 720 that checks the temperature. In this example, the temperature at node 720 can be high 722 or normal 724. If the temperature at node 720 is high 722, the prediction is "No" (don't play) 723 for golf. If the temperature at node 720 is normal 724, the prediction is "Yes" (play) 725 for golf.

[0105] Furthermore, starting from the first node 710, if the result is cloudy 714, then it is "yes" (hitting) 715 golf ball.

[0106] Starting with the first node (weather 710), the result of rainy day 716 leads to a third node (730) checking the temperature. If the temperature at the third node 730 is normal 732, then "yes" (play) 733. If the temperature at the third node 730 is low 734, then "no" (don't play) 735.

[0107] According to the decision tree, a golfer will play golf if the weather is cloudy (715), sunny at normal temperature (725), or rainy at normal temperature (733). However, a golfer will not play golf if the weather is sunny and hot (723) or rainy and cold (735).

[0108] A random forest classifier is a committee of decision trees, where each decision tree is fed a subset of attributes from the data and makes predictions based on that subset. The mode of the actual predictions of the decision trees is considered to provide the final random forest answer. Random forest classifiers typically mitigate the overfitting present in independent decision trees, resulting in a more robust and accurate classifier.

[0109] Figure 8An exemplary random forest classifier for classifying the colors of clothing is shown. Figure 8 As shown, the random forest classifier comprises five decision trees 8101, 8102, 8103, 8104, and 8105 (collectively or generally referred to as decision tree 810). Each tree is designed to classify the color of clothing. No discussion of each tree and the decisions made is provided, as each individual tree is typically used as... Figure 7 The decision trees are used for operation. In this example, three of the five trees (8101, 8102, 8104) determine that the clothing is blue, one tree determines that the clothing is green (8103), and the remaining tree determines that the clothing is red (8105). The random forest takes these actual predictions from the five trees and calculates the mode of these actual predictions to provide the random forest answer that the clothing is blue.

[0110] Logistic regression is another algorithm used for binary classification tasks. Logistic regression is based on the logistic function (also known as the sigmoid function). This sigmoid curve can take any real-valued number and maps it between 0 and 1, asymptotically approaching those limits. Logistic models can be used to model the probability of a given category or event, such as pass / fail, win / lose, live / die, or healthy / sick. This can be extended to modeling several classes of events, such as determining whether an image contains a cat, dog, lion, etc. Each object detected in the image is assigned a probability between 0 and 1, with the sum of probabilities being 1.

[0111] In a logistic model, the logarithmic odds (logarithm of the odds) of a value labeled "1" is a linear combination of one or more independent variables ("predictors"); these variables can each be binary variables (two categories, encoded by indicator variables) or continuous variables (any real value). The corresponding probability of a value labeled "1" can vary between 0 (definitely the value "0") and 1 (definitely the value "1"), hence the label; the function that converts the logarithmic odds to probabilities is a logistic function, hence this name. The unit of measurement for the logarithmic odds scale is called the sublogarithm, derived from the logistic unit, hence this alternative name. Similar models with different sigmoid functions instead of logistic functions, such as probabilistic models, can also be used; the defining characteristic of a logistic model is that the odds of a given outcome are scaled multiplicatively at a constant rate by adding one of the independent variables, where each independent variable has its own parameter; for a binary dependent variable, this summarizes the odds ratio.

[0112] In a binary logistic regression model, the dependent variable has two levels (categorically). Multinomial logistic regression models outputs with more than two values, and if these multiple categories are ordered, it models them using ordinal logistic regression (e.g., proportional dominance ordinal logistic models). The logistic regression model itself simply models the probability of the output against the input and does not perform statistical classification (it is not a classifier), but it can be used as a classifier, for example, by selecting a cutoff value and classifying inputs with probabilities greater than the cutoff value into one category and inputs with probabilities less than the cutoff value into another; this is a common way to create binary classifiers.

[0113] Figure 9 An exemplary logistic regression is illustrated. This exemplary logistic regression enables the prediction of outcomes based on a set of variables. For example, based on an individual's GPA, acceptance by a school can be predicted. The past history of GPA and its relationship to acceptance make the prediction possible. Figure 9 Logistic regression allows analysis of the GPA variable (920) to predict outcomes (910) limited to 0 to 1. At the lower end of the S-curve (930), the GPA (920) predicts an unacceptable outcome (910). At the upper end of the S-curve (940), the GPA (920) predicts an acceptable outcome (910). Logistic regression can be used to predict home values, customer life expectancy in the insurance industry, and more.

[0114] Support Vector Machines (SVMs) can be used to classify data with the margin between two classes that are as far apart as possible. This is called the maximum margin. SVMs take support vectors into account when drawing the hyperplane, unlike linear regression, which uses the entire dataset for that purpose.

[0115] Figure 10 An exemplary Support Vector Machine (SVM) is illustrated. In the exemplary SVM 1000, data can be classified into two distinct categories, represented as squares 1010 and triangles 1020. The SVM 1000 operates by drawing a random hyperplane 1030. The hyperplane 1030 is monitored by comparing the distances (shown as lines 1040) between the hyperplane 1030 and the nearest data points 1050 from each category. The nearest data points 1050 to the hyperplane 1030 are called support vectors. The hyperplane 1030 is drawn based on these support vectors 1050, and the optimal hyperplane has the maximum distance to each of these support vectors 1050. The distance between the hyperplane 1030 and the support vectors 1050 is called the margin.

[0116] SVM 1000 can be used to classify data by using a hyperplane 1030 such that the distance between the hyperplane 1030 and the support vectors 1050 is maximized. For example, this type of SVM 1000 can be used to predict heart disease.

[0117] K Nearest Neighbors (KNN) is a set of algorithms that typically make no assumptions about the distribution of the underlying data and perform a relatively short training phase. Generally, KNN uses a large number of data points divided into several classes to predict the classification of a newly sampled point. Operationally, KNN specifies an integer N with a new sample. It selects the N entries in the system's model that are closest to the new sample. It then determines the most common classification of these entries and assigns that classification to the new sample. KNN typically requires more storage space as the training set grows. This also means that the estimation time increases proportionally with the number of training points.

[0118] In regression algorithms, the output is a continuous quantity, so regression algorithms can be used when the target variable is a continuous variable. Linear regression is a general example of a regression algorithm. Linear regression can be used to estimate true quality (housing costs, number of bids, all buyout transactions, etc.) based on one or more consistent variables. A connection between the variables and the outcome is created by fitting a best-fit line (i.e., fitting a linear regression). This best-fit line is called the regression line and is expressed by the direct condition Y = a*X + b. Linear regression is best used in methods involving low dimensionality.

[0119] Figure 11 An exemplary linear regression model is illustrated. In this model, the predictor variable 1110 is modeled relative to the measured variable 1120. Clusters of instances of the predictor variable 1110 and the measured variable 1120 are plotted as data points 1130. The data points 1130 are then fitted with a best-fit line 1140. Then, given the measured variable 1120, the best-fit line 1140 is used for subsequent predictions, which predict the predictor variable 1110 for that instance. Linear regression can be used to model and predict outcomes of surgical procedures, performance of financial portfolios, income forecasts, real estate, and traffic at estimated arrival times.

[0120] Clustering algorithms can also be used to model and train datasets. In clustering, inputs are assigned to two or more clusters based on feature similarity. Clustering algorithms typically learn patterns and useful insights from data without any guidance. For example, unsupervised learning algorithms such as K-means clustering can be used to cluster viewers into similar groups based on their interests, age, geography, etc.

[0121] K-means clustering is generally considered a simple unsupervised learning method. In K-means clustering, similar data points are grouped together and bound as clusters. One way to bind data points together is by calculating the centroid of the group. In determining valid clusters, in K-means clustering, the distance between each point and the centroid of the cluster is evaluated. Data points are assigned to the nearest cluster based on their distance to the centroid. The goal of clustering is to determine intrinsic groupings within a set of unlabeled data. The "K" in K-means represents the number of clusters formed. The number of clusters (basically the number of categories that can classify new data instances) can be determined by the user. For example, this determination can be performed during training using feedback and by looking at the size of the clusters.

[0122] K-means is used when the dataset contains points with different and well-spaced intervals; otherwise, if the clusters are not spaced, modeling may lead to inaccurate clustering. Additionally, K-means can be avoided when the dataset contains a large number of outliers or is non-linear.

[0123] Figure 12 This illustrates K-means clustering. In K-means clustering, data points are plotted and assigned K values. For example, for... Figure 12 With K=2, data points are plotted as shown in Figure 1210. These points are then assigned to similar centers in step 1220. Cluster centroids are identified as shown in Figure 1230. Once centroids are identified, these points are reassigned to clusters to provide the minimum distance between data points and their respective cluster centroids, as shown in Figure 1240. New centroids for the clusters can then be determined as shown in Figure 1250. During the reassignment of data points to clusters, new cluster centroids may be formed, iterated, or a series of iterations may occur to minimize the cluster size and determine the centroids of the optimal centroids. Then, when new data points are measured, they can be compared with the centroids and clusters to identify them together with that cluster.

[0124] Ensemble learning algorithms can be used. These algorithms use multiple learning algorithms to achieve better predictive performance compared to the performance that can be obtained from any of the constituent learning algorithms alone. Ensemble learning algorithms perform the task of searching through a hypothesis space to find suitable hypotheses that will make good predictions for a particular problem. Even if the hypothesis space contains hypotheses that are very well-suited to a particular problem, finding good hypotheses can be very difficult. Ensemble algorithms combine multiple hypotheses to form better hypotheses. The term ensemble is generally reserved for methods that use the same base learner to generate multiple hypotheses. The broader terminology of multiple classifier systems also encompasses the mixing of hypotheses that are not induced by the same base learner.

[0125] Evaluating the predictions of an ensemble typically requires more computation than evaluating the predictions of a single model; therefore, ensembles can be seen as a way to compensate for poor learning algorithms by performing a significant amount of additional computation. Fast algorithms such as decision trees are often used in ensemble methods, such as random forests, although slower algorithms can also benefit from ensemble techniques.

[0126] Ensembles are supervised learning algorithms because they can be trained and then used for prediction. Therefore, a trained ensemble represents a single hypothesis. However, this hypothesis is not necessarily contained within the hypothesis space of the model that constructs it. Thus, ensembles can be shown to have greater flexibility in the functions they can represent. Theoretically, this flexibility allows these ensembles to be better fitted to the training data than a single model, but in practice, some ensemble techniques (especially bagging) tend to reduce the problems associated with overfitting to the training data.

[0127] Empirically, ensemble algorithms tend to produce better results when there is significant diversity among the models. Therefore, many ensemble methods attempt to promote diversity among the models they combine. While not intuitive, more stochastic algorithms (such as stochastic decision trees) can produce stronger ensembles than highly deliberate algorithms (such as entropy-reducing decision trees). However, using multiple brute-force learning algorithms has shown to be more effective than techniques that attempt to discard models to promote diversity.

[0128] The number of component classifiers in an ensemble has a significant impact on prediction accuracy. Predetermining the ensemble size, volume, and speed of a large data stream makes this even more critical for online ensemble classifiers. Theoretical frameworks suggest that there exists an ideal number of component classifiers for ensembles, such that having more or fewer classifiers will decrease accuracy. Theoretical frameworks also indicate that using the same number of independent component classifiers as the class labels yields the highest accuracy.

[0129] Some common types of ensembles include Bayesian optimal classifier, bootstrapping aggregation (bagging), boosting, Bayesian model averaging, Bayesian model combination, model storage, and stacking. Figure 13 An exemplary ensemble learning algorithm is shown, in which bagging is performed in parallel 1310 and boosting is performed sequentially 1320.

[0130] 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 ​​represent inhibitory connections. The input is modified by the weights and summed using a linear combination. Activation functions control the amplitude of the output. For example, an acceptable output range is typically between 0 and 1, or the range can be between -1 and 1.

[0131] These artificial networks can be used for predictive modeling, adaptive control, and applications, and can be trained on datasets. Experience-based self-learning can occur within the network, drawing conclusions from complex and seemingly unrelated groups of information.

[0132] For completeness, a biological neural network consists of one or more groups of chemically connected or functionally related neurons. A single neuron can connect to many other neurons, and the total number of neurons and connections in a network can be extensive. Connections (called synapses) typically form from an axon to a dendrite, but dendritic synapses and other connections are also possible. In addition to electrical signals, other forms of signaling, caused by the diffusion of neurotransmitters, exist.

[0133] Artificial intelligence, cognitive modeling, and neural networks are information processing paradigms inspired by how biological nervous systems process data. Artificial intelligence and cognitive modeling attempt to simulate some characteristics 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 to build software agents or autonomous robots (in computers and video games).

[0134] In terms of artificial neurons, often referred to as artificial neural networks (ANNs) or simulated neural networks (SNNs), a neural network (NN) is a set of interconnected natural or artificial neurons that process information using mathematical or computational models based on computational connection methods. In most cases, an ANN is an adaptive system that changes its structure based on information flowing through the network's external or internal systems. More practically, neural networks are tools for modeling nonlinear statistical data or making decisions. These terms can be used to model complex relationships between inputs and outputs or to find patterns in data.

[0135] Artificial neural networks involve networks of simple processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between the processing elements and their parameters.

[0136] A classic type of artificial neural network is the recurrent Hopfield network. The practicality of artificial neural network models lies in their ability to infer functions from observations and also to utilize those functions. Unsupervised neural networks can also be used to learn representations of inputs that capture salient features of the input distribution, and recent deep learning algorithms can implicitly learn the distribution function of observed data. Learning in neural networks is particularly useful in applications where the complexity of the data or task makes manually designing such functions impractical.

[0137] Neural networks can be used in various fields. The tasks applied to artificial neural networks often fall into the following broad categories: function approximation or regression analysis, including time series forecasting and modeling; classification, including pattern and sequence recognition, novelty detection, and order decision-making; and data processing, including filtering, clustering, blind signal separation, and compression.

[0138] Applications of ANNs include nonlinear system recognition and control (vehicle control, process control), game playing and decision making (backgammon, chat, competitions), pattern recognition (radar systems, facial recognition, object recognition), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications, data mining (or knowledge discovery in databases, "KDD"), visualization, and email spam filtering. For example, semantic feature maps of user interests can be created from images trained for object recognition.

[0139] Figure 14 An exemplary neural network is illustrated. In this neural network, there exists an input layer represented by multiple inputs such as 14101 and 14102. Inputs 14101 and 14102 are provided to a hidden layer depicted as including nodes 14201, 14202, 14203, and 14204. These nodes 14201, 14202, 14203, and 14204 are combined to produce output 1430 in the output layer. The neural network performs simple processing via the hidden layer (nodes 14201, 14202, 14203, and 14204) of simple processing elements, and can exhibit complex global behavior determined by the connections between the processing elements and their parameters.

[0140] Figure 14 Neural networks can be implemented in hardware. For example... Figure 15 As shown, a hardware-based neural network is illustrated.

[0141] Cardiac arrhythmias, and more specifically atrial fibrillation (AF), have long been a common and dangerous medical condition, especially in the elderly. In patients with a normal sinus rhythm, the heart, composed of the atria, ventricles, and conduction tissues, beats synchronously and in a patterned manner under electrical stimulation. In patients with arrhythmias, abnormal areas of cardiac tissue do not follow the synchronous beating cycle associated with normal conduction tissues as in patients with a normal sinus rhythm. Instead, the abnormal areas of cardiac tissue conduct abnormally to adjacent tissues, thus disrupting the cardiac cycle into an asynchronous rhythm. This abnormal conduction is known to occur in various regions of the heart, such as the sinoatrial (SA) node region, along the conduction pathways of the atrioventricular (AV) node and His bundle, or in the myocardial tissue that forms the walls of the ventricles and atria.

[0142] Catheter-based ablation therapy can include mapping the electrical properties of cardiac tissue (especially the endocardium and cardiac volume) and selectively ablating cardiac tissue by applying energy. Cardiac mapping, which creates, for example, a mapping of the potential propagating along cardiac tissue (voltage mapping) or a mapping of the time of arrival to various tissue locations (local time activation (LAT) mapping), can be used to detect localized cardiac tissue dysfunction. Ablation, such as cardiac mapping-based ablation, can stop or alter unwanted electrical signals propagating from one part of the heart to another.

[0143] As clinicians treat increasingly challenging conditions such as atrial fibrillation and ventricular tachycardia, cardiac ablation and other cardiac electrophysiological procedures become increasingly complex. Treatment of complex arrhythmias currently relies on the use of three-dimensional (3D) mapping systems to reconstruct the anatomy of the ventricle of interest. For example, cardiologists depend on software such as that produced by Biosense Webster, Inc. (Diamond Bar, Calif.). The Complex Fragmented Atrial Electrogram (CFAE) module of the 33D mapping system analyzes intracardiac EGM signals and identifies ablation points for the treatment of a wide range of cardiac conditions, including atypical atrial flutter and ventricular tachycardia. 3D mapping provides multiple layers of information about the electrophysiological properties of tissues, representing the anatomical and functional matrix of these challenging arrhythmias.

[0144] Electrode catheters have been widely used in medical practice for many years. They are used to stimulate and map electrical activity in the heart, as well as to ablate sites of abnormal electrical activity. In use, the electrode catheter is inserted into a major vein or artery, such as the femoral artery, and then guided to the cardiac chamber of interest. A typical ablation procedure involves inserting a catheter with at least one electrode at its distal end into the cardiac chamber. A reference electrode is provided, usually taped to the patient's skin, or a second catheter positioned in or near the heart may be used to provide the reference electrode. RF (radio frequency) current is applied to the tip electrode of the ablation catheter, and the current flows through the surrounding medium (i.e., blood and tissue) to the reference electrode. The current distribution depends on the amount of contact between the electrode surface and the tissue compared to blood, which has a higher conductivity. Heating of the tissue occurs due to its resistance. The tissue is sufficiently heated to destroy the cells in the cardiac tissue, resulting in the formation of a non-conductive ablation focus within the cardiac tissue. Heating of the electrode also occurs during this process due to conduction from the heated tissue to the electrode itself. If the electrode temperature becomes high enough, perhaps above 60°C, a thin, transparent coating of dehydrated hemoglobin can form on the electrode surface. If the temperature continues to rise, this dehydrated layer can become increasingly thick, causing blood to clot on the electrode surface. Because dehydrated biomaterials have a higher electrical resistance than endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance increases sufficiently, an impedance rise occurs, and the catheter must be removed from the body and the tip electrode cleaned.

[0145] A prerequisite for successful catheter ablation is the accurate localization of the cause of the arrhythmia and the surrounding cardiac region within the cardiac chambers. This localization can be accomplished via an electrophysiological study, during which a mapping catheter introduced into the cardiac chambers is used to spatially resolve electrical potentials. This electrophysiological study (so-called electroanatomical mapping) thus provides 3D mapping data that can be displayed on a monitor. In many cases, mapping and therapeutic functions (e.g., ablation) are provided by a single catheter or a group of catheters, allowing the mapping catheter to simultaneously function as a therapeutic (e.g., ablation) catheter.

[0146] Cardiac mapping can be achieved using one or more techniques. As an example of a first technique, cardiac mapping can be achieved by sensing the electrical properties (e.g., local activation time) of cardiac tissue based on precise locations within the heart. The corresponding data can be acquired via one or more catheters advanced into the heart using catheters with electrical and position sensors at their distal ends. For example, initially, position and electrical activity can be measured at approximately 10 to approximately 20 points on the inner surface of the heart. These data points are often sufficient to generate a preliminary reconstruction or mapping map of the cardiac surface of satisfactory quality. The preliminary map can be combined with data taken from additional points to produce a more comprehensive map of cardiac electrical activity. In clinical settings, it is not uncommon to accumulate data at 100 or more sites to generate a detailed and comprehensive mapping map of cardiac chamber electrical activity. The resulting detailed map can then serve as a basis for determining therapeutic actions, such as tissue ablation, to alter the propagation of cardiac electrical activity and restore normal heart rhythm.

[0147] Catheters containing position sensors can be used to determine the trajectories of points on the surface of the heart. These trajectories can be used to infer kinematic properties, such as tissue contractility. When trajectory information is sampled at a sufficient number of points in the heart, a mapping depicting these kinematic properties can be constructed.

[0148] Typically, a catheter containing an electrical sensor at or near its distal end is advanced to a point in the heart, where the sensor contacts the tissue and acquires data at that point, thereby measuring the electrical activity at that point in the heart. Multi-electrode catheters can be implemented using any suitable shape, such as a linear catheter with multiple electrodes, a balloon catheter including electrodes distributed on multiple ridges that shape the balloon, a lasso or ring catheter with multiple electrodes, or any other suitable shape.

[0149] According to one example, a multi-electrode catheter can be advanced into the chambers of the heart. Anterior and posterior fluorescein (AP) and lateral fluorescein maps are obtained to establish the position and orientation of each electrode. An electrogram relative to a time reference (e.g., starting from the P wave in the sinus rhythm from a surface ECG) can be recorded by each of the electrodes in contact with the cardiac surface. As further disclosed herein, the system can distinguish which electrodes record electrical activity from those that do not, due to their less close proximity to the endocardial wall. After recording the initial electrogram, the catheter can be repositioned, and fluorescein and electrograms can be recorded again. An electromapping can then be constructed iteratively based on the above process.

[0150] According to another example, techniques and devices for mapping the potential distribution of cardiac chambers are available. An intracardiac multi-electrode mapping catheter assembly can be inserted into a patient's heart. The mapping catheter assembly may include a multi-electrode array with an integral reference electrode, or preferably, a mating reference catheter. The electrodes may be deployed in the form of a substantially spherical array. The electrode array may be spatially referenced to points on the endocardial surface via the reference electrode or via a reference catheter in contact with the endocardial surface. A preferred electrode array catheter may carry multiple individual electrode sites (e.g., at least 24). Furthermore, this exemplary technique is achieved by understanding the location of each electrode site in the array and by understanding the cardiac geometry. These locations are preferably determined using techniques of impedance plethysmography.

[0151] According to other examples, body patches and / or surface electrodes may be positioned on or near the patient's body. A catheter having one or more electrodes may be positioned within the patient's body (e.g., within the patient's heart), and the location of this catheter may be determined by the system based on signals transmitted and received between the one or more electrodes of the catheter and the body patch and / or surface electrodes. Additionally, the catheter electrodes may sense biometric data (e.g., LAT values) from within the patient's body (e.g., within the heart). This biometric data may be correlated with the determined location of the catheter, enabling the display of a rendering of the patient's body part (e.g., the heart), and the display of biometric data overlaid on the shape of the body part, as determined by the location of the catheter.

[0152] Electrical signals, such as electrocardiogram (ECG) signals, are typically detected before and / or during cardiac procedures. For example, ECG signals can be used to identify the potential location within the heart from which arrhythmias causing the signal originate. Generally, an ECG is a signal describing the electrical activity of the heart. ECG signals can also be used to map parts of the heart.

[0153] ECG signals are generated by the contraction (depolarization) and relaxation (repolarization) of the atrial and ventricular myocardium. For example... Figure 16 As shown in signal 1602, an ECG signal includes a P wave (due to atrial depolarization), a QRS complex (due to atrial repolarization and ventricular depolarization), and a T wave (due to ventricular repolarization). To record an ECG signal, electrodes can be placed at specific locations on the body or positioned within the body via a catheter. Artifacts (e.g., noise) are unwanted signals that are combined with electronic signals such as ECG signals and can sometimes hinder the diagnosis and / or treatment of heart conditions. Artifacts in electrical signals can include baseline drift, electric field interference, electromyography (EMG) noise, electric field noise, etc.

[0154] Additionally, biometric (e.g., biopotential) patient monitors can use surface electrodes to measure biopotentials, such as ECG or EEG. The fidelity of these measurements is limited by the effectiveness of the electrode connection to the patient. The resistance of the electrode system to the flow of current (called impedance) characterizes the effectiveness of the connection. Generally, the higher the impedance, the lower the fidelity of the measurement. Several mechanisms can contribute to lower fidelity.

[0155] Figure 17 This is an illustration of an exemplary system 1720 that can implement one or more features of the subject matter of this disclosure. All or part of system 1720 can be used to collect information for a training dataset, and / or all or part of system 1720 can be used to implement a trained model. System 1720 may include components, such as catheter 1740, configured to damage tissue regions of organs within the body. Catheter 1740 may also be further configured to obtain biometric data including electronic signals. While catheter 1740 is shown as a pointed catheter, it should be understood that catheters of any shape, including one or more elements (e.g., electrodes), can be used to implement embodiments disclosed herein. System 1720 includes a probe 1721 having an axis navigable by a physician 1730 to a body part of a patient 1728 lying on a table 1729, such as the heart 1726. Multiple probes may be provided according to embodiments; however, for brevity, a single probe 1721 is described in this example, but it should be understood that probe 1721 may represent multiple probes. Figure 17 As shown, physician 1730 can insert shaft 1722 through sheath 1723 while manipulating the distal end of shaft 1722 using a manipulator near the proximal end of catheter 1740 and / or deflecting from sheath 1723. As shown in illustration 1725, catheter 1740 can be fitted to the distal end of shaft 1722. Catheter 1740 can be inserted through sheath 1723 in a collapsed state and can then be deployed within heart 1726. As further described herein, catheter 1740 may include at least one ablation electrode 1747 and catheter needle.

[0156] According to one embodiment, catheter 1740 can be configured to ablate a tissue region of the heart chamber of heart 1726. Illustration 1745 shows catheter 1740 within the heart chamber of heart 1726 in an enlarged view. As shown, catheter 1740 may include at least one ablation electrode 1747 coupled to the body of the catheter. According to other embodiments, multiple elements may be connected via a strip forming the shape of catheter 1740. One or more other elements (not shown) may be provided, which may be any element configured to ablate or obtain biometric data, and may be an electrode, a transducer, or one or more other elements.

[0157] According to the embodiments disclosed herein, an ablation electrode, such as electrode 1747, can be configured to deliver energy to a tissue region of an organ in the body, such as heart 1726. The energy can be thermal and can cause damage to the tissue region by starting from the surface of the tissue region and extending into the thickness of the tissue region.

[0158] According to the embodiments disclosed herein, biometric data may include one or more of the following: local activation time (LAT), electrical activity, topology, bipolar mapping, dominant frequency, impedance, etc. Local activation time can be a time point corresponding to the threshold activity of local activation, calculated based on a normalized initial start point. Electrical activity can be any applicable electrical signal that can be measured based on one or more thresholds and sensed and / or amplified based on signal-to-noise ratio and / or other filters. Topology can correspond to the physical structure of a body part or a portion of a body part, and can correspond to variations in the physical structure relative to different parts of the body part or relative to different body parts. Dominant frequency can be a frequency or frequency range that is prevalent in a part of a body part and can differ in different parts of the same body part. For example, the dominant frequency of the pulmonary veins of the heart can differ from the dominant frequency of the right atrium of the same heart. Impedance can be a resistance measurement at a given region of a body part.

[0159] like Figure 17 As shown, probe 1721 and catheter 1740 can be connected to console 1724. Console 1724 may include processor 1741 (such as a general-purpose computer) having suitable front-end and interface circuitry 1738 for transmitting and receiving signals to and from the catheter, as well as other components for controlling system 1720. In some embodiments, processor 1741 may be further configured to receive biometric data, such as electrical activity, and determine whether a given tissue region is conductive. According to one embodiment, the processor may be located external to console 1724 and may be located, for example, in a catheter, an external device, a mobile device, a cloud-based device, or may be a stand-alone processor.

[0160] As noted above, processor 1741 may include a general-purpose computer that can be software-programmed to perform the functions described herein. The software may be downloaded to the general-purpose computer electronically, for example, via a network, or alternatively or additionally set and / or stored on a non-transitory tangible medium, such as magnetic storage, optical storage, or electronic storage. Figure 17 The exemplary configuration shown can be modified to implement the embodiments disclosed herein. The embodiments disclosed herein can be applied similarly using other system components and setups. Additionally, system 1720 may include additional components such as elements for sensing electrical activity, wired or wireless connectors, processing and display devices, etc.

[0161] According to one embodiment, a display 1727 connected to a processor (e.g., processor 1741) may be located in a remote location such as a separate hospital or within a separate healthcare provider network. Additionally, system 1720 may be part of a surgical system configured to acquire anatomical and electrical measurements of a patient's organ (such as the heart) and perform cardiac ablation procedures. An example of such a surgical system is sold by Biosense Webster. system.

[0162] System 1720 can also, and optionally, use ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), or other medical imaging techniques known in the art to obtain biometric data, such as anatomical measurements of a patient's heart. System 1720 can use catheters, electrocardiograms (EKG), or other sensors that measure the electrical properties of the heart to obtain electrical measurements. Figure 17 As shown, biometric data, including anatomical and electrophysiological measurements, can then be stored in memory 1742 of the mapping system 1720. The biometric data can be transferred from memory 1742 to processor 1741. Alternatively or otherwise, biometric data can be transferred to a server 1760, which may be local or remote, using network 1762.

[0163] Network 1762 can be any network or system known in the art, such as an intranet, local area network (LAN), wide area network (WAN), metropolitan area network (MAN), direct connection or a series of connections, cellular telephone network, or any other network or medium capable of facilitating communication between the measurement system 1720 and the server 1760. Network 1762 can be wired, wireless, or a combination thereof. Wired connections can be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection known in the art. Wireless connections can be implemented using Wi-Fi, WiMAX and Bluetooth, infrared, cellular networks, satellite, or any other wireless connection method known in the art. Additionally, several networks can operate independently or communicate with each other to facilitate communication within network 1762.

[0164] In some cases, server 1760 can be implemented as a physical server. In other cases, server 1762 can be implemented as a public cloud computing provider (e.g., Amazon Web Services). The virtual server.

[0165] According to an exemplary embodiment, server 1760 may be implemented as a processor storing machine learning algorithms (such as neural network 1790) or communicating with such a processor. In another embodiment, neural network 1790 may be implemented in console 1724. For example, but not limited to, neural network 1790 may be on one or more CPU processors, one or more GPU processors, one or more FPGA chips, or on an ASIC dedicated to performing deep learning computations (such as...). Nervana TM The neural network 1790 may be implemented on a neural network processor, but is not limited to, in a medical operating room, a hospital or medical facility, on a server or processor, on a remote server or processor, or in the cloud.

[0166] The console 1724 can be connected to a surface electrode 1743 via a cable 1739, which may include an adhesive skin patch attached to the patient 1730. A processor, in conjunction with a current tracking module, determines the orientation coordinates of the catheter 1740 within a body part of the patient (e.g., the heart 1726). The orientation coordinates may be based on impedance or electromagnetic field measured between the surface electrode 1743 and other electromagnetic components of the electrode 1747 or catheter 1740. Additionally or alternatively, a positioning pad may be located on the surface of the bed 1729 and may be detachable from the bed 1729.

[0167] Processor 1741 may include a real-time noise reduction circuitry system typically configured as a field-programmable gate array (FPGA), followed by an analog-to-digital (A / D) ECG (electrocardiogram) or EMG (electromyography) signal conversion integrated circuit. Processor 1741 may pass 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.

[0168] The console 1724 may also include an input / output (I / O) communication interface that enables the console to transmit signals from and / or to the electrode 1747.

[0169] During the procedure, processor 1741 may facilitate the presentation of a body part rendering 1735 to physician 1730 on display 1727 and store data representing the body part rendering 1735 in memory 1742. Memory 1742 may include any suitable volatile and / or non-volatile memory, such as random access memory or hard disk drive. In some embodiments, medical professional 1730 may be able to manipulate the body part rendering 1735 using one or more input devices, such as a touchpad, mouse, keyboard, gesture recognition device, etc. For example, the input device may be used to change the position of catheter 1740, causing the rendering 1735 to be updated. In an alternative embodiment, display 1727 may include a touchscreen that can be configured to accept input from medical professional 1730 in addition to presenting the body part rendering 1735.

[0170] According to one embodiment, the neural network 1790 can be provided for automatically detecting and identifying the location of specific structures (such as the His bundle) within the heart. The neural network 1790 may have the features described above. Figure 14 and Figure 15 The form of the description.

[0171] The His bundle is a part of the myocardium originating near the orifice of the sclera (CS). It is a crucial part of the heart's electrical conduction system, as it plays a vital role in transmitting electrical impulses from the atrioventricular (AV) node, located between the atria and ventricles, to the ventricles. Located in a vulnerable area of ​​the heart, the His bundle can have harmful and undesirable effects on the heart's electrical conduction system if incorrectly ablated during a catheter ablation procedure. During routine ablation procedures, physicians can manually mark the His bundle to identify its location within the heart, allowing it to be avoided during the procedure. This manual marking of the His bundle is both tedious and time-consuming. Manual marking can also lead to false positives, where the electrocardiogram (ECG) signal appears to be a His bundle pulse, but the pulse's location does not accurately correspond to the His bundle's position. In other routine ablation procedures, physicians may not mark the His bundle, increasing the risk to the patient during the ablation procedure.

[0172] according to Figure 18A Exemplary implementations are provided. Figure 17The neural network 1800, illustrated in the diagram of neural network 1790, receives input data 1810 for training the neural network 1800 and automatically identifies cardiac structures of interest, such as the His bundle 1820, with greater efficiency and reliability than manual identification by a physician during procedures such as ablation procedures. Non-limiting examples of input data 1810 may include intracardiac electrogram (EGM) or ECG signals received by electrodes or bipolar electrode pairs of catheters (such as mapping catheters) 1830, the distance 1840 (typically measured in millimeters) between the electrodes of the first mapping catheter and a point on a second reference catheter, or other inputs 1850. Other inputs 1850 may include discrete Boolean values ​​(i.e., 0 or 1) indicating whether the distance between the electrodes of the first mapping catheter and a point on the second reference catheter is less than a predetermined threshold, such as the force applied by the catheter to the cardiac structure of interest (typically measured in grams) as measured by a force sensor in the catheter, an index indicating the proximity between the electrodes of the catheter and the cardiac structure of interest, the impedance value of the cardiac structure of interest (typically measured in ohms) as measured by the electrodes of the catheter, an electrocardiogram (ECG) signal 1830 received by a surface electrode, manual mapping data of the cardiac structure of interest, and any other electrophysiological data measured by the electrodes of the catheter.

[0173] In one implementation, one or more input data 1810 are fed into a neural network 1800. The input data 1810 may be stored in various locations, including but not limited to hospitals or medical facilities, remote server locations, or the cloud. Training data 1810 may be transmitted to the neural network 1800 in real time, at predetermined intervals, or upon request. Once trained, the neural network 1800 can identify the His bundle 1820 in real time during catheter ablation procedures.

[0174] In one implementation, the output 1820 of the neural network 1800 may include, but is not limited to, discrete Boolean values ​​and continuous values, the discrete Boolean values ​​indicating whether the electrodes of the mapping catheter are sufficiently close to the cardiac structure of interest, such as the His bundle, and the continuous values, such as the matching index, indicating the match between the characteristics of the heart of interest measured by the electrodes of the mapping catheter and the characteristics of the cardiac structure of interest, such as characteristics obtained by manual mapping.

[0175] According to an exemplary embodiment, neural network 1800 may include a convolutional neural network (CNN) or a recurrent neural network (RNN), such as a long short-term memory (LSTM) neural network. A convolutional neural network (CNN) is a deep learning algorithm preferably used in the fields of computer vision and / or image recognition. A CNN assigns importance (learnable weights) to various aspects or features in an input image so that they can be distinguished from each other. An LSTM neural network is a recurrent neural network with feedback connections for deep learning.

[0176] In an exemplary implementation, after each training iteration, the trained model (including its output) can be executed against a standard database (such as a gold standard database) to verify its accuracy. In a non-limiting example, the gold standard database consists of points known to be the cardiac structures under consideration (e.g., the atrioventricular bundle), points known not to be the structures, relevant catheter locations, ECG signals, and other relevant parameters. In an exemplary implementation, if the accuracy of a newly trained model is below a threshold, or alternatively, if the accuracy of a newly trained model is lower than that of a previous model, the model can be discarded. Similarly, if the accuracy of a newly trained model is equal to or higher than a threshold, or alternatively, if the accuracy of a newly trained model is higher than that of a previous model, the model can be released to a field mapping system. In an exemplary implementation, the release of a new model can be performed manually, for example, by an operator downloading a file from a URL and uploading it to the mapping system 1720. Alternatively, the new model can be pushed to the field mapping system 1720 via the Internet.

[0177] Figure 18B This is a flowchart depicting an exemplary embodiment of a module 1860 used to train a neural network 1800 and automatically detect and identify the location of specific structures within the heart. Although Figure 18B Combination Figure 18A A module for automatically identifying the His bundle in the heart is shown, but those skilled in the art will recognize that other cardiac structures or signals can be identified according to module 1860.

[0178] For example, during a cardiac ablation procedure, multiple catheters can be used to obtain various cardiac data recordings. Figure 19A Multiple intracardiac catheters and surface electrodes are shown for obtaining electrophysiological data of heart 1910. According to exemplary embodiments, the catheters may include, for example, an ablation catheter 1920, a CS reference catheter 1930, and a His bundle mapping catheter 1940. Other probes, such as a right ventricular apex (RVA) catheter 1950, may also be used as needed. Ablation catheter 1920 is used to perform the ablation procedure as described above. CS reference catheter 1930 is placed within the coronary sinus 1932 of heart 1910. His bundle mapping catheter 1940 contacts the His bundle and is configured to record His bundle electrograph (HBE), such as... Figure 20 As shown, and as discussed in this article, the 1960 surface electrode was positioned on the body surface to record ECG signals from the heart, as described above and as... Figure 16 and Figure 20 As shown.

[0179] According to an exemplary embodiment, electrophysiological data obtained from catheters 1920, 1930, 1940, 1950 and electrode 1960 can be fed to a processor, such as processor 1741, for analysis and output to a display 1727, and preferably transmitted to a neural network 1790, such as... Figure 17 As shown.

[0180] At step 1865, the neural network 1800 receives first input data from the first catheter. In one embodiment, the first input data 1810 is preferably electrophysiological data, and more preferably an intracardiac electrogrammage (EGM) signal 1840 received by the electrodes or bipolar electrode pair of the first catheter. In one embodiment, the first catheter is a mapping catheter that receives EGM signals from the cardiac structure of interest. In one embodiment, the first catheter is a His bundle mapping catheter 1940, such as... Figures 19A to 19B As shown, the catheter receives His bundle electrophoresis (HBE) signals. The first catheter may include multiple electrodes. Figure 19B A His bundle mapping catheter 1940 with four electrodes 1942a, 1942b, 1942c, and 1942d is shown; however, those skilled in the art will recognize that the His bundle mapping catheter 1940 may include any number of electrodes. The His bundle mapping catheter 1940 may receive EGM signals at any of the electrodes 1942a, 1942b, 1942c, and 1942d.

[0181] At step 1875, the neural network 1800 receives additional input data. In one embodiment, the additional input data may be a second EGM signal received from a second electrode (such as electrode 1942b of the His bundle mapping catheter 1940). Those skilled in the art will recognize that the additional input data may include multiple EGM signals received from different electrodes of the His bundle mapping catheter 1940.

[0182] To help illustrate the various aspects of this disclosure, Figure 20 Exemplary surface ECG and intracardiac HBE recordings 2010 and 2020, respectively, are shown for use according to the methods of this disclosure. As shown in HBE recording 2020, the A wave indicates low right atrial activation, His bundle activity is represented by H, and V deflection indicates ventricular activation. Typically, the time interval between the onset of the A wave and the subsequent onset of V deflection is referred to as the AV interval 2022. When the His bundle mapping catheter 1940 contacts the His bundle, the HBE signal preferably has the pattern shown in HBE recording 2020.

[0183] As is known in the art and discussed above, the surface electrode 1960 serves as a reference electrode and generates a surface ECG record 2010 of the cardiac cycle, which includes the P wave, QRS complex, and T wave as shown in the figure. The P wave represents the polarization phase of the atrial ventricle, the QRS complex represents the repolarization of the ventricle, and the T wave represents the depolarization of the ventricle. Accordingly, the time interval between the onset of the P wave and the onset of the QRS complex is referred to as the PR interval 2012. Line 2030 shows the point where the electrical impulse passes through the His bundle in the surface ECG record 2010.

[0184] In one implementation, the neural network 1800 identifies electrophysiological data, such as HBE signals, corresponding to the location of the His bundle based on input data. For example, the neural network 1800 identifies whether the input data includes electrophysiological data corresponding to the His bundle.

[0185] However, even if the HBE signal exhibits a pattern as shown in HBE Record 2020, the His bundle mapping catheter 1940 may still display false positive readings, for example, when the His bundle mapping catheter 1940 approaches but does not contact the His bundle. Therefore, the neural network can also rely on the distance between the electrodes of the His bundle mapping catheter 1940 and the CS reference electrode 1930, as discussed herein.

[0186] In one implementation, additional input data may also include the distance between the electrodes on the His bundle mapping catheter 1940 and the electrodes on the reference catheter. For example, the reference catheter may be a CS reference catheter 1930 inserted into the coronary sinus of the heart, such as... Figures 19A to 19B As shown. For example, it is well known that the His bundle is anatomically located near the CS. According to an exemplary embodiment, the distance between the electrodes on the His bundle mapping catheter 1940 and the electrodes on the CS reference catheter 1930 is used as proximity data to determine the reliability of the HBE record 2020.

[0187] In one embodiment, the CS reference catheter 1930 may include multiple electrodes. Figure 19B A CS reference catheter 1940 is shown, having ten electrodes 1932a, 1932b, 1932c, 1932d, 1932e, 1932f, 1932g, 1932h, 1932i, and 1932j; however, those skilled in the art will recognize that the CS reference catheter 1940 may include any number of electrodes. In one embodiment, the distance between each electrode 1942a-d of the His bundle mapping catheter 1940 and the nearest point on the CS reference catheter 1930 can be measured. For example, as... Figure 19BAs shown, distance D3 is the distance between electrode 1942c of the His bundle mapping catheter 1940 and the nearest point on the CS reference catheter 1930. Alternatively or additionally, the distance between each electrode 1942a-d of the His bundle mapping catheter 1940 and the nearest electrode 1932a-j of the CS reference catheter 1930 can be measured. Alternatively or additionally, the distance between each electrode 1942a-d of the His bundle mapping catheter 1940 and a selected electrode of the CS reference catheter 1930 can be measured, which can be any of electrodes 1932a-j.

[0188] Those skilled in the art will recognize that the first input data and the additional input data referenced at steps 1865 and 1885 can be any input data discussed herein as well as any other electrophysiological data measured by the electrodes of the catheter.

[0189] At step 1885, the neural network 1800 applies a machine learning algorithm to each received input data point to identify the location of cardiac structures of interest, such as the His bundle. For example, the EGM received by each electrode 1942a-d of the His bundle mapping catheter 1940 and the distance between each electrode 1942a-d and the nearest point of the CS reference catheter 1930 can be used to determine whether any of the electrodes 1942a-d is located on the His bundle, and if so, which one is located on the His bundle. For example, as Figure 19B As shown, the EGM received by electrode 1942c of the His bundle mapping catheter 1940 and the distance D3 between electrode 1942c and CS reference catheter 1930 can be used as inputs to the neural network 1800 to determine whether electrode 1942c of the His bundle mapping catheter 1940 is located on the His bundle. As described in more detail below, determining whether the electrode is located on the His bundle may include viewing the ECG signal, the distance from the CS catheter, and other inputs, including, for example, force and touch state.

[0190] In another example, if the HBE record 2020 at the first selected electrode of the His bundle mapping catheter 1940 has His bundle characteristics, but the spatial location of the first selected electrode is more than a predetermined threshold or range from the CS reference catheter 1930, as in the reference... Figure 19A As shown in distance D2, the neural network 1800 determines that the first selected electrode is not the exact location of the His bundle. On the other hand, if the HBE record 2020 has His bundle characteristics, and the spatial position of the second selected electrode along the His bundle mapping catheter 1940 is less than a predetermined threshold or range from the CS reference catheter 1930, as in the reference... Figure 19A As shown in distance D1, the neural network 1800 determines the exact location of the second selected electrode as the His bundle.

[0191] In one implementation, the neural network learns predetermined thresholds based on the location of the His bundle manually marked by the physician, the distance between the manually marked His bundle and the CS reference catheter 1930, and electrophysiological data (such as HBE record 2020 or ECG record 2010).

[0192] Therefore, the neural network 1800 learns to automatically detect the location of specific structures (such as the His bundle) within the heart based on input data (such as electrophysiological data received from the first catheter, such as EGM data received by the electrodes of the His bundle mapping catheter 2040) and optional supplementary data (such as EGM data received from other electrodes of the first catheter, electrophysiological data received from the second catheter such as the CS reference catheter, manual mapping data, ECG data, EGM data, distance data, force data, proximity index data, impedance data, and any other electrophysiological data measured by the electrodes of the catheter). This supplementary data may be relevant in detecting the His bundle, and although this supplementary data may seem insignificant, the AI ​​algorithm described herein may discover correlations and importance with some of these input data.

[0193] At step 1890, the neural network 1800 generates an output indicating whether the electrodes of the first catheter are positioned on or sufficiently close to a cardiac structure of interest (such as the His bundle). As described above, the output of the neural network may include, but is not limited to, discrete Boolean values ​​and continuous values, wherein the discrete Boolean values ​​indicate whether the electrodes of the catheter are sufficiently close to the cardiac structure of interest, such as the His bundle, and the continuous values, such as the matching index, indicate the match between the characteristics of the cardiac structure of interest measured by the electrodes of the catheter and the characteristics of the cardiac structure of interest (such as characteristics obtained by manual mapping).

[0194] In another embodiment, the neural network 1800 can be used to detect regional aberrant ventricular activation (LAVA) signals within the heart. In such embodiments, LAVA and non-LAVA signals are used as training data in the model, and the neural network learns to distinguish between LAVA and non-LAVA signals to automatically detect LAVA signals in a clinical setting.

[0195] Figure 21 An exemplary implementation of a convolutional neural network (CNN) 2100 for automatically identifying cardiac structures of interest is described. Figure 21As shown, the CNN 2100 preferably receives input data 2110. The input data may include a single input or multiple inputs 2110-1, 2110-2, 2110-3, ..., 2110-n, where "n" is the last of the multiple inputs. By way of example and not limitation, the first input 2110-1 may include a first EGM signal received by a first electrode of the mapping catheter, the second input 2110-2 may include a second EGM signal received by a second electrode of the mapping catheter, the third input 2110-3 may include the distance between the first electrode of the mapping catheter and the nearest electrode of the reference catheter, and the final input (2110-n) may include the distance between the second electrode of the mapping catheter and the nearest electrode of the reference catheter. Input 2110 is provided to a first hidden layer 2120 comprising nodes 2120-1, 2120-2, 2120-3, ..., 2120-n, and optionally to a second or more hidden layers 2130 comprising nodes 2130-1, 2130-2, 2130-3, ..., 2130-n, which are combined to produce an output 2140, such as a Boolean value or a matching index. For example, in a CNN 2100, all EGM inputs 2110 are immediately fed into the neural network to compute the output 2140. The neural network may include a series of convolutional layers that feed one or more pooling layers and flattening layers to provide outputs in the hidden layers, as will be described in more detail below.

[0196] Figure 22 The text describes an exemplary implementation of a recurrent neural network (RNN) 2200, such as a long short-term memory (LSTM) neural network, for automatically identifying cardiac structures of interest. Figure 22 As shown, the RNN 2200 preferably receives input data 2210. Input data 2210 may include a single input or multiple inputs 2210-1, 2210-2, 2210-3, ..., 2210-n, where "n" is the last of the multiple inputs. By way of example and not limitation, the first input 2210-1 may include a first EGM signal received by a first electrode of the mapping catheter, the second input 2210-2 may include the distance between the first electrode of the mapping catheter and the nearest electrode of the reference catheter, the third input 2210-3 may include force data received from the electrodes of the mapping catheter, and the last input 2210-n may include impedance data received from the electrodes of the mapping catheter. Inputs 2210 are provided to the RNN 2200 and combined to produce an output 2240, such as a Boolean value or a matching index. For example, in the RNN 2200, the EGM inputs 2210-1 are fed into the neural network one at a time. As more EGM samples are fed into the RNN 2200, the output 2240 becomes more accurate.

[0197] exist Figure 18BAt step 1895, the output of neural network 1800, such as output 2140 or 2240, is used to train neural network 1800. Specifically, the output of neural network 1800 provides the system output, which is further provided to recursively train neural network 1800 to achieve improved output. For example, as mentioned above, after each training iteration, the training model (including its output) can be executed against a standard database (such as a gold standard database) to verify its accuracy. For example, the output can be a valid output showing where the His bundle is or is not, and the output can be used to further train the algorithm. Furthermore, as referenced... Figure 22 As indicated by arrow 2230, if the accuracy of the newly trained model is equal to or higher than the threshold, or alternatively, if the accuracy of the newly trained model is higher than the accuracy of the previous model, then the model can be used as input to the neural network.

[0198] In one implementation, the training of the neural network 1800 can be supervised at a facility where cardiac procedures are performed (such as a hospital or medical facility) or at a remote location (such as a training center).

[0199] Once the neural network 1800 is trained, it can be used in real time to automatically detect the location of specific structures (such as the His bundle) within the heart.

[0200] Figure 23 A specific implementation 2300 of the described system is shown. Implementation 2300 includes a series of inputs to network 2100, including ECG input 1830, distance from conduit 1840, and other inputs 1850, to produce an output 1820, which includes the probability of His-beam detection (or localization) and the probability of non-His-beam detection (or localization). As described above, ECG input 1830 may include any number of ECG data, including a first ECG 18301, a second ECG 18302, ..., up to a final ECG 1830. N .

[0201] Network 2100 may be a CNN network, such as that described herein. For simplicity, network 2100 may include multiple convolutional layers 2310 interconnected with multiple pooling layers 2320 and further interconnected with multiple flattening layers 2330, said flattening layers may include one or more ResNet and / or fully connected layers. It should be understood that the Softmax layer 2340 may be the last layer in network 2100.

[0202] Convolutional layer 2310 has been referenced at least in this paper. Figure 21The following description is provided. Pooling layer 2320 can be used to reduce the size of the feature map. Pooling layer 2320 can be used to reduce the number of parameters to be learned and the amount of computation performed in network 2100. Pooling layer 2310 summarizes the features present in the regions of the feature map generated by convolutional layer 2310. Flattening layer 2330 transforms the pooled feature map into a single column that is passed to fully connected layer 2100, and adds fully connected layer 2100 to the neural network.

[0203] The Softmax layer 2340 provides a function to transform a vector of K real values ​​into a vector of K real values ​​that sum to 1. Input values ​​can be positive, negative, zero, or greater than one. The Softmax layer 2340 can transform inputs to itself into values ​​between 0 and 1 to allow for interpretation as probabilities. If one input is small or negative, the Softmax layer 2340 transforms it into a low-probability input, and if the input is large, it transforms it into a high-probability input.

[0204] The Softmax layer 2340 can be referred to as the softargmax function or multi-class logistic regression. The Softmax layer 2340 can be a generalization of logistic regression for multi-class classification, and its formula is very similar to the sigmoid function used for logistic regression. The Softmax layer 2340 function can only be used in a classifier when the classes are mutually exclusive.

[0205] The Softmax layer 2340 transforms the score into a normalized probability distribution, which can be displayed to a user or used as input to other systems. The Softmax layer 2340 can be the final layer of the neural network 2100 to produce an output 1820 that includes the probabilities of His bundle and non-His bundle.

[0206] Training may require additional time if the distance 1840 is fed directly into network 2100 as input.

[0207] Figure 24 A specific implementation 2400 of the described system is shown. Implementation 2400 includes a series of inputs to network 2100, including ECG input 1830, to produce output 1820, which includes the probabilities of His-bundle and non-His-bundle patterns. ECG input 1830 may include any number of ECG data, including a first ECG 18301, a second ECG 18302, ..., up to a final ECG 1830. N As mentioned above.

[0208] Network 2100 may be a CNN network, such as that described herein. For simplicity, network 2100 may include multiple convolutional layers 2310 interconnected with multiple pooling layers 2320 and further interconnected with multiple flattening layers 2330, said flattening layers may include one or more ResNet and / or fully connected layers. It should be understood that the Softmax layer 2340 may be the last layer in network 2100.

[0209] ECG input 1830 is available within network 2100 and ends before Softmax layer 2340.

[0210] The distance input to conduit 1840 can be provided as a separate input from ECG input 1830. After multiplication by weights and addition of bias 2420, the distance input 1840 can be provided to activation function 2430. If d is the distance, b is the bias, w is the weight, and f is the activation function, then the output of the activation function is f(wd+b). As understood in the art, activation function 2430 defines the output of the node given a single input or a set of inputs. Activation function 2430 may include functions such as sigmoid, TanH, ELU, and LeakyReLU. The input to softmax layer 2340 can be multiplied by the output of activation function 2430. Softmax layer 2340 converts the score into a normalized probability distribution that can be displayed to a user or used as input to other systems. Softmax layer 2340 can be the final layer of neural network 2100 to produce output 1820, which includes probabilities of His bundle and non-His bundle. Alternatively, instead of a softmax layer 2340 that takes two inputs and produces two outputs, neural network 2330 can generate a single output between -∞ and +∞, and this output can be converted into a probability between 0 and 1 by an activation function such as sigmoid. In this configuration, the input to the final activation function can be multiplied by the output of activation function 2430.

[0211] Figure 25 A specific implementation 2500 of the described system is illustrated. Implementation 2500 includes a series of inputs to network 2100, including ECG input 1830, to produce output 1820, which includes the probabilities of His-bundle and non-His-bundle patterns. ECG input 1830 may include any number of ECG data, including a first ECG 18301, a second ECG 18302, ..., up to a final ECG 1830. N As described above, network 2100 can output the intermediate probability 2520 of the His bundle.

[0212] Network 2100 may be a CNN network, such as that described herein. For simplicity, network 2100 may include a plurality of convolutional layers 2310 interconnected with a plurality of pooling layers 2320 and further interconnected with a plurality of flattening layers 2330, the plurality of flattening layers including one or more ResNet and / or fully connected layers.

[0213] The distance input 1840 and other inputs 1850 can be provided after the convolutional layers 2310, pooling layers 2320, and flattening layers 2330 of the convolutional network. As shown, the distance 1840 and other inputs 1850 can skip all three layers 2310, 2320, and 2330, or only portions of layers 2310, 2320, and 2330, as will be understood. The distance input 1840 and any other input 1850 can be provided to the output of the ECG network 2100, and combined with one or more hidden layers 2500 using a non-convolutional neural network to produce an output 1820, which includes the probabilities of the His bundle and non-His bundle. In this network architecture, because the inputs are scalars, such as distance and applied force, the inputs can be treated as "just another input," resulting in the network taking too long to train and its convergence being challenging. Figure 24 and Figure 25 The configuration described herein resolves this issue.

[0214] Although two networks, 2100 and 2510, are shown, these networks are trained as a single network. Suppose two locations in the heart are explored: one is the desired location (His bundle), and the other is any point in a more distant location within the heart. For example, assume the ECG signals received from these two locations are very similar, and the only way to know which location is the His bundle is to look at the distance. Since distance is not an input, no information about distance is provided to the first neural network. If the first network were trained alone, two very similar signals would need to be fed into the neural network, one as the His bundle and one as a "non-His bundle," causing confusion within the network. The neural network would not converge.

[0215] In this example, to provide better understanding, two very similar signals are included. Even with different signals, the same problem persists because neural networks can learn certain "properties" of a signal to determine the His bundle, and that same property could also exist at another location. While one might understand this difference, a neural network with ECG as a single input can become confused, and its convergence will be challenging. In the best-case scenario, training will take too long; in the worst-case scenario, the network will not converge.

[0216] When training two networks as a single unit, the first network can freely produce "garbage" outputs even when the distance is too large, and still converge. Figure 24 In this context, when the distance is too large, multiplication can reduce the impact of "garbage". Figure 25 In this model, when distance and other parameters indicate a low probability of a His bundle, the second neural network reduces the impact of "garbage." Furthermore, unlike hand-crafted algorithms, the network learns what the relevant distance is. The network learns that when the distance is sufficiently large, the activation function 2430 needs to output a factor that is "close to zero." This "close to zero" factor leads to a low probability of the second network outputting a His bundle, regardless of the output of the first network.

[0217] Generally speaking, cutoff values ​​do not help the results. For example, if ECG signals with a distance <1cm are considered, all other signals are excluded during the training phase. Theoretically, this configuration and cutoff values ​​provide the same "fast convergence" advantage, and this would also solve the problem. The effect of distance should be a continuous function, not a discrete function. Figure 24 and Figure 25 The effect of this architecture is similar to how a neural network learns to construct a function to represent distance. During training, the network gives less and less importance to inputs from distant points. Furthermore, the solution scales to any additional scalar input, such as the applied force, tissue proximity index, etc.

[0218] exist Figure 25 In this system, the first network can output more information to indicate different properties of the signal, and the second network can learn to combine properties with distance. For example, when the distance is short, the second network can learn to give more importance to properties (such as properties A, B, and C). When the distance is long, the second network can learn to give more importance to properties (such as properties D and E).

[0219] The first part of network 2100 may or may not end with a softmax or sigmoid layer. If it ends with a softmax or sigmoid layer, the input to the second part of the network is between 0 and 1. Otherwise, the input to the second part of the network is between -∞ and +∞.

[0220] While this document describes the automated detection of the His bundle as a result of utilizing the neural network described herein, the subject matter of this disclosure is not limited to the automated detection of the His bundle. Automated identification of other cardiac structures and / or signals is within the scope of the disclosed subject matter. For example, the electrocardiographic cycle begins with the sinoatrial (SA) node transmitting electrical impulses through the atrium and via the atrioventricular (AV) node to the His bundle. The His bundle transmits electrical impulses from the AV node to the left and right bundle branches, and then to the Purkinje fibers, which provide electrical signals to the ventricles. In one embodiment, the subject matter disclosed herein can be used for the automated detection of other cardiac structures during the electrocardiographic cycle, including but not limited to the SA node, left and right bundle branches, Purkinje fibers, etc. Furthermore, as another example, the subject matter disclosed herein can be used for the detection of LAVA signals, as previously described. In another embodiment, the subject matter disclosed herein can be used for detecting catheter position and as an alarm system for physicians to detect when a catheter is unintentionally moved from the atrial chamber to the ventricular chamber.

[0221] Although the features and elements have been specifically described above, those skilled in the art will recognize that each feature or element can be used alone or in any combination with other features and elements. Furthermore, while the process steps have been described in a specific order above, these steps can be performed in other desired orders.

[0222] The methods, processes, modules, and systems described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media (such as internal hard disks and removable disks), magneto-optical media, and optical media (such as CD-ROMs and digital versatile discs (DVDs)). The processor associated with the software may be used to implement a radio frequency transceiver used in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0223] Further embodiments of this document may be constituted by supplementing the embodiments with one or more elements from any one or more other embodiments of this document, and / or by replacing one or more elements in one embodiment with one or more elements from one or more other embodiments of this document.

[0224] Therefore, it should be understood that the subject matter disclosed is not limited to the specific embodiments disclosed, but is intended to cover all modifications that conform to the spirit and scope of this disclosure, as defined in the appended claims, detailed description and / or as shown in the drawings.

Claims

1. A system for automatically detecting cardiac structures, the system comprising: Multiple sensing devices located within the heart to receive electrophysiological data about a first cardiac structure, each of the multiple sensing devices providing a one-dimensional signal; The processor includes a neural network, the neural network being: The one-dimensional signal is received from at least one of the plurality of sensing devices; Receive distance data regarding the distance between two of the plurality of sensing devices; The neural network is applied to the received one-dimensional signal to determine the output; Apply weights and biases to the distance; Apply the activation function to the weighted and biased distance; as well as The determined output is multiplied by the output of the activation function to determine whether the first cardiac structure is the cardiac structure of interest based on the electrophysiological data and the distance data.

2. The system of claim 1, wherein the cardiac structure of interest comprises the His bundle.

3. The system of claim 1, wherein the electrophysiological data received by the plurality of sensing devices regarding the first cardiac structure includes ECG signals.

4. The system of claim 1, wherein the plurality of sensing devices comprises a plurality of different electrodes.

5. The system according to claim 1, wherein the distance data is the distance of the calibration electrode.

6. The system according to claim 1, wherein the neural network is a convolutional neural network or a recurrent neural network.

7. The system according to claim 1 further includes training the neural network globally on the one-dimensional signal and the distance data.

8. A method for automatically detecting cardiac structures, the method comprising: Electrophysiological data about the first cardiac structure is received via multiple sensing devices located within the heart, the electrophysiological data including multiple one-dimensional signals; The one-dimensional signal is received from at least one of the plurality of sensing devices via a neural network, and distance data regarding the distance between two of the plurality of sensing devices is also received. The neural network is applied to the received one-dimensional signal to determine the output; Weights and biases are applied to the distance, and an activation function is applied to the weighted and biased distance. as well as The determined output is multiplied by the output of the activation function to determine whether the first cardiac structure is the cardiac structure of interest based on the electrophysiological data and the distance data.

9. The method of claim 8, wherein the cardiac structure of interest comprises the His bundle.

10. The method of claim 8, wherein the electrophysiological data received by the plurality of sensing devices regarding the first cardiac structure includes an ECG signal.

11. The method of claim 8, wherein the plurality of sensing devices comprises a plurality of different electrodes.

12. The method of claim 8, wherein the distance data is the distance of the calibration electrode.

13. The method of claim 8, wherein the neural network is a convolutional neural network or a recurrent neural network.

14. The method of claim 8 further comprises training the neural network globally on the one-dimensional signal and the distance data.

15. A system for automatically detecting cardiac structures, comprising: Multiple sensing devices located within the heart to receive electrophysiological data about a first cardiac structure, each of the multiple sensing devices providing a one-dimensional signal; A processor, the processor including a first neural network, the first neural network receiving the one-dimensional signal from at least one of the plurality of sensing devices and applying the neural network to the received one-dimensional signal to determine an output; The processor includes a second neural network that receives distance data regarding the distance between two of the plurality of sensing devices, applies weights and biases to the distance, and applies an activation function to the weighted and biased distance. as well as The outputs of the first neural network and the second neural network are combined to determine whether the first cardiac structure is a cardiac structure of interest based on the electrophysiological data and the distance data.

16. The system of claim 15, wherein the cardiac structure of interest comprises the His bundle.

17. The system of claim 15, wherein the electrophysiological data received by the plurality of sensing devices regarding the first cardiac structure includes an ECG signal.

18. The system of claim 15, wherein the plurality of sensing devices comprises a plurality of different electrodes.

19. The system of claim 15, wherein the distance data is the distance of the calibration electrode.

20. The system of claim 15 further includes training the first neural network and the second neural network globally on the one-dimensional signal and the distance data.

Images