Systems and methods for determining catheter position - Patents.com

Abstract

To provide systems, devices and techniques for automatically generating CPM matrices.SOLUTION: A system includes a plurality of body surface electrodes configured to sense electric signals, and a processor comprising a neural network. The processor is configured to receive a plurality of historical CPM matrices, patient properties, and corresponding catheter locations, train a learning system based on the plurality of CPM matrices, patient properties, and corresponding catheter locations, generate a model based on the learning system, receive new patient properties at least in part from the plurality of body surface electrodes, and generate new CPM matrices based on new patient properties at least in part from the plurality of body surface electrodes.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 049,191, filed July 8, 2020, which is incorporated by reference as if set forth in its entirety.

[0002] FIELD OF THE INVENTION The present invention relates to artificial intelligence and machine learning related to optimizing cardiac mapping, including systems and methods for determining catheter position. [Background technology]

[0003] Medical conditions such as cardiac arrhythmias (e.g., atrial fibrillation (AF)) are often diagnosed and treated via intracorporeal procedures. For example, electrical pulmonary vein isolation (PVI) from the left atrial (LA) body is performed using ablation to treat AF. PVI, and many other minimally invasive catheterization procedures, require real-time visualization and mapping of intracorporeal surfaces.

[0004] Visualization and mapping of internal body parts can be performed by activation wave mapping propagation, fluoroscopy, computerized tomography (CT), and magnetic resonance imaging (MRI), as well as other techniques that may require more time or resources than are desirable to provide the visualization and mapping. Summary of the Invention [Means for solving the problem]

[0005] Systems, devices, and techniques for automatically generating CPM matrices are disclosed. The system includes a plurality of body surface electrodes configured to sense electrical signals, and a processor including a neural network. The processor is configured to receive a plurality of historical CPM matrices, patient characteristics, and corresponding catheter positions, train a learning system based on the plurality of CPM matrices, the patient characteristics, and the corresponding catheter positions, generate a model based on the learning system, receive new patient characteristics at least in part from the plurality of body surface electrodes, and generate new CPM matrices based at least in part on the new patient characteristics from the plurality of body surface electrodes. [Brief explanation of the drawings]

[0006] A more detailed understanding can be had from the following description, given by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate similar elements and in which: [Figure 1] FIG. 1 is a block diagram of an exemplary system for remote monitoring and communication of patient biometrics. [Figure 2] FIG. 1 is a system diagram of an example computing environment in communication with a network. [Figure 3] FIG. 1 is a block diagram of an example device capable of implementing one or more features of the present disclosure. [Figure 4] 4 shows a graphical depiction of an artificial intelligence system incorporating the exemplary device of FIG. 3. [Figure 5] 5 illustrates a method implemented in the artificial intelligence system of FIG. [Figure 6] 10 shows an example of a naive Bayes calculation probability. [Figure 7] 1 illustrates an exemplary decision tree. [Figure 8] 1 illustrates an exemplary random forest classifier. [Figure 9] 1 shows an exemplary logistic regression. [Figure 10] An exemplary support vector machine is shown. [Figure 11] 1 illustrates an exemplary linear regression model. [Figure 12] 1 illustrates an exemplary K-means clustering. [Figure 13] 1 illustrates an exemplary ensemble learning algorithm. [Figure 14] 1 illustrates an exemplary neural network. [Figure 15] 1 shows a hardware-based neural network. [Figure 16A] 1 shows an embodiment of an intracorporeal catheter. [Figure 16B] 1 shows an embodiment of an intracorporeal catheter. [Figure 16C] 1 shows an embodiment of an intracorporeal catheter. [Figure 17] FIG. 1 is a diagram of an example system in which one or more features of the presently disclosed subject matter may be implemented. [Figure 18] 1 is a flowchart for determining catheter position and generating currents to register multiple position mappings (CPMs). [Figure 19] 1 illustrates an exemplary generation of CPMs using body surface patches. [Figure 20] 1 shows a flowchart for determining historical CPMs. [Figure 21] FIG. 10 is an exemplary logistic regression diagram for predicting CPMs and cardiac position. [Figure 22] 1 shows a system configuration for predicting electrode positions. [Figure 23] The configuration of an NN that can function as an NN is shown below. DETAILED DESCRIPTION OF THE INVENTION

[0007] According to exemplary embodiments of the disclosed subject matter, a new current to position mapping (CPM) matrix may be generated based on correlations between historical CPMs and corresponding known catheter positions. As further disclosed herein, the CPMs are generated based on electrical signals transmitted by catheter electrodes and received at multiple body patches on the surface of the patient's body. The electrical signals are correlated based on the known position of the catheter, which is independently determined using magnetic fields (e.g., received and / or emitted by magnetic catheter sensors, location pads, body patches, etc.).

[0008] New CPM matrices may be generated such that new CPM data for the multiple cardiac locations is generated based on only a subset of known electrical signals corresponding to the multiple cardiac locations. Alternatively, or additionally, new CPM data may be generated such that new CPM data for the multiple cardiac locations is generated without any known catheter locations corresponding to the multiple catheter locations.

[0009] 1 is a block diagram of an exemplary system 100 for remotely monitoring and communicating patient biometrics (i.e., patient data). In the example shown in FIG. 1, the system 100 includes a patient biometric monitoring and processing device 102 associated with a patient 104, a local computing device 106, a remote computing system 108, a first network 110, and a second network 120.

[0010] According to one embodiment, the monitoring and processing device 102 may be a device internal to the patient's body (e.g., subcutaneously implantable). The monitoring and processing device 102 may be inserted into the patient via any applicable method, including oral injection, surgical insertion via a vein or artery, endoscopic procedure, or laparoscopic procedure.

[0011] According to one embodiment, the monitoring and processing device 102 may be a device external to the patient. For example, as described in more detail below, the monitoring and processing device 102 may include an attachable patch (e.g., attached to the patient's skin). The monitoring and processing device 102 may also include a catheter with one or more electrodes, a probe, a blood pressure cuff, a bracelet or smartwatch biometric tracker, a glucose monitor, a continuous positive airway pressure (CPAP) machine, or virtually any device capable of providing input regarding the patient's health or biometrics.

[0012] According to one embodiment, the monitoring and processing device 102 may include both components that are internal to the patient and components that are external to the patient.

[0013] A single monitoring and processing device 102 is shown in Figure 1. However, an exemplary system may include multiple patient biometric monitoring and processing devices. A patient biometric monitoring and processing device may be in communication with one or more other patient biometric monitoring and processing devices. Additionally or alternatively, a patient biometric monitoring and processing device may be in communication with a network 110.

[0014] One or more monitoring and processing devices 102 may acquire patient biometric data (e.g., electrical signals, blood pressure, body temperature, blood glucose levels, or other biometric data) and may receive at least a portion of the patient biometric data representative of the acquired patient biometrics, as well as additional information associated with the acquired patient biometrics from one or more other monitoring and processing devices 102. The additional information may be, for example, diagnostic information and / or additional information obtained from additional devices, such as wearable devices. Each monitoring and processing device 102 may process data including its own acquired patient biometrics as well as data received from one or more other monitoring and processing devices 102.

[0015] 1, network 110 is an example of a short-range network (e.g., a local area network (LAN) or a personal area network (PAN)). Information may be transmitted over short-range network 110 between monitoring and processing device 102 and local computing device 106 using any one of a variety of short-range wireless communication protocols, such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communication (NFC), Ultraband, Zigbee, or infrared (IR).

[0016] Network 120 may be a wired network, a wireless network, or may include one or more wired and wireless networks. For example, network 120 may be a long-range network (e.g., a wide area network (WAN), the Internet, or a cellular network). Information may be transmitted over network 120 using any one of a variety of long-range wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / New Radio).

[0017] The patient monitoring and processing device 102 may include patient biometric sensors 112, a processor 114, user input (UI) sensors 116, memory 118, and a transmitter-receiver (i.e., transceiver) 122. The patient monitoring and processing device 102 may continuously or periodically monitor, store, process, and communicate any number of various patient biometrics over the 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. These patient biometrics may be monitored and communicated for treatment across any number of various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathies, and coronary artery disease) and autoimmune diseases (e.g., type 1 and type 2 diabetes).

[0018] The patient biometric sensors 112 may include, for example, one or more sensors configured to sense a type of biometric patient biometric. For example, the patient biometric sensors 112 may include electrodes configured to acquire electrical signals (e.g., cardiac signals, brain signals, or other bioelectric signals), a temperature sensor, a blood pressure sensor, a blood glucose sensor, a blood oxygen sensor, a pH sensor, an accelerometer, and a microphone.

[0019] As described in more detail below, the patient biometric monitoring and processing device 102 may be an ECG monitor for monitoring cardiac ECG signals. The patient biometric sensor 112 of the ECG monitor may include one or more electrodes for acquiring the ECG signals. The ECG signals may be used in the treatment of various cardiovascular disorders.

[0020] In another example, the patient biometric monitoring and processing device 102 may be a continuous glucose monitor (CGM) for continuously monitoring a patient's blood glucose levels on an ongoing basis to treat various diseases, such as type 1 and type 2 diabetes. The CGM may include subcutaneously placed electrodes that can monitor blood glucose levels from the patient's interstitial fluid. The CGM may be a component of a closed-loop system in which blood glucose data is sent to an insulin pump, for example, for calculated delivery of insulin without user intervention.

[0021] The transceiver 122 may include a separate transmitter and receiver, or alternatively, the transceiver 122 may include a transmitter and receiver integrated into a single device.

[0022] The processor 114 may be configured to store patient data, such as patient biometric data acquired by the patient biometric sensors 112, in the memory 118 and to communicate the patient data over the network 110 via the transmitter of the transceiver 122. Data from one or more other monitoring and processing devices 102 may also be received by the receiver of the transceiver 122, as described in more detail below.

[0023] According to one embodiment, the monitoring and processing device 102 includes a UI sensor 116, which may be a piezoelectric or capacitive sensor configured to receive user input, such as a tap or touch. For example, the UI sensor 116 may be controlled to implement capacitive coupling in response to the patient 104 tapping or touching the surface of the monitoring and processing device 102. Gesture recognition may be implemented via any one of a variety of capacitive types, such as resistive-capacitive, surface-capacitive, projected-capacitive, surface acoustic wave, piezoelectric, and infrared touch. The capacitive sensor may be positioned over a small area or length of the surface such that a tap or touch on the surface activates the monitoring device.

[0024] As described in more detail below, processor 114 may be configured to selectively respond to different tapping patterns (e.g., single tap or double tap) of a capacitive sensor, which may be UI sensor 116, so that different tasks of the patch (e.g., data acquisition, storage, or transmission) may be initiated based on the detected pattern. In some embodiments, audible feedback may be provided to the user from processing unit 102 when a gesture is detected.

[0025] The local computing device 106 of the system 100 may be configured to communicate with the patient biometric monitoring and processing device 102 and act as a gateway to the remote computing system 108 via a second network 120. The local computing device 106 may be, for example, a smartphone, smartwatch, tablet, or other portable smart device configured to communicate with other devices via the network 120. Alternatively, the local computing device 106 may be a fixed or stand-alone device, such as, for example, a desktop or laptop computer using modem and / or router functionality, an executable program to communicate information between the processing device 102 and the remote computing system 108 via a wireless module in a PC, or a fixed base station including a USB dongle. Patient biometrics may be communicated between the local computing device 106 and the patient biometric monitoring and processing device 102 via a short-range wireless network 110, such as a local area network (LAN) (e.g., a personal area network (PAN)), using short-range wireless technology standards (e.g., Bluetooth, Wi-Fi, ZigBee, Z-Wave, and other short-range wireless standards). In some embodiments, the local computing device 106 may also be configured to display the acquired patient electrical signals and information related to the acquired patient electrical signals, as described in more detail below.

[0026] In some embodiments, remote computing system 108 may be configured to receive at least one of the monitored patient's biometrics and information associated with the monitored patient over network 120, which is a long-range network. For example, if local computing device 106 is a mobile phone, network 120 may be a wireless cellular network, and information may be communicated between local computing device 106 and remote computing system 108 via a wireless technology standard, such as any of the wireless technologies described above. As described in more detail below, remote computing system 108 may be configured to provide (e.g., visually display and / or audibly provide) at least one of the patient's biometrics and associated information to a medical professional (e.g., a physician).

[0027] 2 is a system diagram of an example computing environment 200 in communication with network 120. In some embodiments, computing environment 200 is incorporated 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.

[0028] As shown in FIG. 2, computing environment 200 includes a remote computing system 108 (hereinafter computer system), which is an example of a computing system in which embodiments described herein may be implemented.

[0029] The remote computing system 108 can perform various functions via the processor 220, which may include one or more processors. Functions may include analyzing monitored patient biometric and related information and providing alerts, additional information, or instructions (e.g., via the display 266) according to physician-determined or algorithm-driven thresholds and parameters. As described in more detail below, the remote computing system 108 can be used to provide a patient information dashboard (e.g., via the display 266) to a medical professional (e.g., a physician) so that the patient information may enable the medical professional to identify and prioritize patients with more significant needs than others.

[0030] 2, computer system 210 may include a communication mechanism, such as a bus 221, or other communication mechanism for communicating information within computer system 210. Computer system 210 further includes one or more processors 220 coupled with bus 221 for processing information. Processor 220 may include one or more CPUs, GPUs, or any other processors known in the art.

[0031] Computer system 210 also includes a system memory 230 coupled to bus 221 for storing information and instructions executed by processor 220. System memory 230 may include computer-readable storage media in the form of volatile and / or nonvolatile memory, such as read-only system memory (ROM) 231 and / or random access memory (RAM) 232. System memory RAM 232 may also include other dynamic storage device(s) (e.g., dynamic RAM, static RAM, and synchronous DRAM). System memory ROM 231 may also include other static storage device(s) (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). Additionally, system memory 230 may be used to store temporary variables or other intermediate information during execution of instructions by processor 220. A basic input / output system (BIOS) 233 may include routines for transferring information, which may be stored in system memory ROM 231, between elements within computer system 210, such as during start-up. RAM 232 may contain data and / or program modules that are immediately accessible to and / or presently being operated on by processor 220. System memory 230 may also include, for example, an operating system 234, application programs 235, other program modules 236, and program data 237.

[0032] The illustrated computer system 210 also includes a disk controller 240 coupled to bus 221 for controlling one or more storage devices for storing information and instructions, such as a magnetic hard disk 241 and a removable media drive 242 (e.g., a floppy disk drive, a compact disk drive, a tape drive, and / or a solid state drive). Storage devices may be added to computer system 210 using an appropriate device interface (e.g., small computer system interface (SCSI), integrated device electronics (IDE), Universal Serial Bus (USB), or FireWire).

[0033] 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), for displaying 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 a computer user and providing information to processor 220. Pointing device 261 may be, for example, a mouse, trackball, or pointing stick for communicating directional information and command selections to processor 220 and for controlling cursor movement on display 266. Display 266 may provide a touchscreen interface that may enable input that complements or replaces the communication of directional information and command selections by pointing device 261 and / or keyboard 262.

[0034] Computer system 210 may perform some or each of the functions and methods described herein in response to processor 220 executing one or more sequences of one or more instructions contained in a memory, such as system memory 230. 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 include one or more data stores and data files used by the embodiments described herein. Data store contents and data files may be encrypted for improved security. Processor 220 may also be employed in a multi-processing configuration 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. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.

[0035] As mentioned above, computer system 210 may include at least one computer-readable medium or memory for retaining programmed instructions 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 may 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 disks, 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 wire, and fiber optics, including the wires that comprise bus 221. Transmission media can also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0036] The computing environment 200 may further include a computer system 210 operating in a networked environment using logical connections to the local computing device 106 and to one or more other devices, such as a personal computer (laptop or desktop), a mobile device (e.g., a patient mobile device), a server, a router, a network PC, a peer device, or other common network node, and typically includes many or all of the elements described above with respect to the computer system 210. When used in a networked environment, the computer system 210 may include a modem 272 for establishing communications over the network 120, such as the Internet. The modem 272 may be connected to the system bus 221 via a network interface 270 or another appropriate mechanism.

[0037] Network 120 as shown in FIGS. 1 and 2 may be any network or system commonly known in the art, including the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between computer system 610 and other computers (e.g., local computing device 106).

[0038] 3 is a block diagram of an example device 300 capable of implementing one or more features of the present disclosure. Device 300 may be, for example, local computing device 106. Device 300 may include, for example, a computer, a gaming device, a handheld device, a set-top box, a television, a mobile phone, or a tablet computer. Device 300 includes a processor 302, memory 304, storage 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 is understood that device 300 may include additional components not shown in FIG. 3 , including an artificial intelligence accelerator.

[0039] In various alternatives, processor 302 includes a central processing unit (CPU), a graphics processing unit (GPU), a CPU and a GPU located on the same die, or one or more processor cores, each of which may be a CPU or a GPU. In various alternatives, memory 304 is located on the same die as processor 302 or is located separate from processor 302. Memory 304 includes volatile or non-volatile memory, such as random access memory (RAM), dynamic RAM, or a cache.

[0040] The storage devices 306 include fixed or removable storage means, such as a hard disk drive, solid state drive, optical disk, or flash drive. The input devices 308 include, but are not limited to, a keyboard, a keypad, a touch screen, a touch pad, a detector, a microphone, an accelerometer, a gyroscope, a biometric scanner, or a network connection (e.g., a wireless local area network card for transmitting and / or receiving wireless IEEE 802 signals). The output devices 310 include, but are not limited to, a display, a speaker, a printer, a haptic feedback device, one or more lights, an antenna, or a network connection (e.g., a wireless local area network card for transmitting and / or receiving wireless IEEE 802 signals).

[0041] Input driver 312 communicates with processor 302 and input device 308, allowing processor 302 to receive input from input device 308. Output driver 314 communicates with processor 302 and output device 310, allowing processor 302 to send output to output device 310. Note that input driver 312 and output driver 314 are optional components; device 300 operates in the same manner if input driver 312 and output driver 314 are not present. Output driver 316 includes an accelerated processing device ("APD") 316 coupled to display device 318. The APD accepts computational and graphic rendering commands from processor 302, processes those computational and graphic rendering commands, and provides pixel output to display device 318 for display. As described in further detail below, APD 316 includes one or more parallel processing units that perform computations according to the single-instruction-multiple-data ("SIMD") paradigm. Thus, although various functions are described herein as being performed by or in conjunction with the APD 316, in various alternatives, the functions described as being performed by the APD 316 may additionally or alternatively be performed by another computing device having similar capabilities that is not driven by a host processor (e.g., processor 302) and provides graphical output to the display device 318. For example, it is contemplated that any processing system that performs processing tasks according to the SIMD paradigm can perform the functions described herein. Alternatively, computing systems that do not perform processing tasks according to the SIMD paradigm are contemplated to perform the functions described herein.

[0042] FIG. 4 shows a graphical depiction of an artificial intelligence system 200 incorporating the exemplary device of FIG. 3 . The system 400 includes data 410, a machine 420, a model 430, multiple outcomes 440, and underlying hardware 450. The system 400 operates by training the machine 420 using the data 410 while building a model 430 that enables the multiple outcomes 440 to be predicted. The system 400 may operate on the hardware 450. In such a configuration, the data 410 may be associated with the hardware 450 and may originate from the device 102, for example. For example, the data 410 may be ongoing data or output data associated with the hardware 450. The machine 420 may operate as or be associated with a controller or data collection associated with the hardware 450. The model 430 may be configured to model the operation of the hardware 450 as well as model the data 410 collected from the hardware 450 to predict outcomes achieved by the hardware 450. The hardware 450 may be configured to use the predicted outcome 440 to provide a predetermined desired outcome 440 from the hardware 450 .

[0043] Figure 5 illustrates a method 500 implemented in the artificial intelligence system of Figure 4. Method 500 includes collecting data from hardware at step 510. This data may include currently collected historical data or other data from the hardware. For example, this data may include measurements taken during a surgical procedure and may be correlated with the outcome of the procedure. For example, cardiac temperature may be collected and correlated with the outcome of a cardiac procedure.

[0044] At step 520, method 500 includes training the machine on the hardware. Training may include analyzing and correlating the data collected at step 510. For example, in the cardiac case, temperature and outcome data may be trained to determine if a correlation or association exists between cardiac temperature during treatment and outcome.

[0045] Method 500 includes building a model based on the hardware-related data at step 530. Building the model may include physical hardware or software modeling, algorithmic modeling, etc., as described below. The modeling may aim to represent the collected and trained data.

[0046] Method 500 includes predicting an outcome for a hardware-related model at step 540. This outcome prediction may be based on a trained model. For example, for the heart, if a positive outcome from a procedure occurs when the temperature during the procedure is between 97.7 and 100.2°C, then for a given procedure, the outcome may be predicted based on the temperature of the heart during the procedure. This model is rudimentary and is provided for illustrative purposes to facilitate understanding of the present invention.

[0047] The present systems and methods operate to train machines, build models, and predict outcomes using algorithms. These algorithms may be used to solve the trained models and predict outcomes related to the hardware. These algorithms can generally be categorized as classification algorithms, regression algorithms, and clustering algorithms.

[0048] For example, classification algorithms are used in situations where the dependent variable to be predicted is divided into multiple classes and one class, i.e., the dependent variable, is predicted for a given input. Thus, classification algorithms are used to predict outcomes from a number of fixed, predefined outcomes. Classification algorithms may include naive Bayes algorithms, decision trees, random forest classifiers, logistic regression, support vector machines, and k-nearest neighbors.

[0049] In general, the Naive Bayes algorithm follows Bayes' Theorem and follows a probabilistic approach, it being understood that other probability-based algorithms may be used and generally operate using similar principles of probability theory as those described below for the exemplary Naive Bayes algorithm.

[0050] Figure 6 shows an example of a naive Bayes calculation of probability. The probabilistic approach of Bayes' theorem essentially means that instead of jumping directly to the data, the algorithm has a set of prior probabilities for each target class. After the data is input, the naive Bayes algorithm may update the prior probabilities to form posterior probabilities. This is done using the following formula:

[0051]

number

[0052] The Naive Bayes algorithm and the Bayes algorithm in general can be useful when one needs to predict whether an input belongs to a given list of n classes or not. Because the probability of all n classes is very low, a probabilistic approach can be used.

[0053] For example, as shown in FIG. 6, a person's decision to play golf depends on factors including the weather outside, as shown in a first data set 610. The first data set 610 lists the weather in a first column and the playing outcomes associated with that weather in a second column. A frequency table 620 generates the frequency with which a particular event occurs. The frequency table 620 determines how often a person will or will not play golf in each weather condition. From this, a likelihood table is compiled and initial probabilities are generated. For example, the probability that the weather is cloudy is 0.29, but the general probability of playing is 0.64.

[0054] Posterior probabilities may be generated from likelihood table 630. These posterior probabilities may be configured to answer questions about weather conditions and whether golf will be played in those weather conditions. For example, the probability that it is sunny outside and golf will be played can be calculated using the Bayesian formula: P(Yes|Sunny) = P(Sunny|Yes) × P(Yes) / P(Sunny) It may be represented by:

[0055] According to likelihood table 630, P(sunny|yes) = 3 / 9 = 0.33, P(sunny)=5 / 14=0.36, P(yes) = 9 / 14 = 0.64 is.

[0056] Therefore, P(yes|sunny) = .33 × .64 / .36 or approximately 0.60 (60%).

[0057] Generally, a decision tree is a tree structure similar to a flowchart, where each outer node represents a test of an attribute and each branch represents the outcome of that test. The leaf nodes contain the actual predicted labels. A decision tree starts at the root of the tree and 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 is spent on data preparation. Decision trees can take the form of simple decision trees, linear decision trees, algebraic decision trees, deterministic decision trees, randomized decision trees, non-deterministic decision trees, and quantum decision trees. An exemplary decision tree is shown below in Figure 7.

[0058] 7 shows a decision tree that follows the same structure as the Bayesian example above when deciding whether to play golf. In the decision tree, a first node 710 examines whether the weather is sunny 712, cloudy 714, and rainy 716 as options for progressing down the decision tree. If the weather is sunny, the tree branch continues to a second node 720 that examines 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, a predicted outcome of "no" golf 723 occurs. If the temperature at node 720 is normal 724, a predicted outcome of "yes" golf 725 occurs.

[0059] Furthermore, from the first node 710, the outcomes Cloudy 714 and Golf "Yes" 715 are generated.

[0060] From the first node, Weather 710, an outcome of Rain 716 results, and (again) a third node 730 checks the Temperature. If the temperature is normal 732 at the third node 730, the answer is "Yes" 733 to play golf. If the temperature is low 734 at the third node 730, the answer is "No" 735 to not play golf.

[0061] From this decision tree, a golfer will play golf when the weather is cloudy 715, when it is sunny with normal temperatures 725, and when it is raining with normal temperatures 733, but the golfer will not play when it is hot with sunny temperatures 723 or cold with rain 735.

[0062] A random forest classifier is a committee of decision trees, each of which is given a subset of the data's attributes and makes a prediction based on that subset. The mode of the decision trees' actual predictions is taken into account to provide the final random forest answer. Random forest classifiers generally mitigate the overfitting that exists in standalone decision trees, making them more robust and accurate classifiers.

[0063] FIG. 8 illustrates an exemplary random forest classifier for classifying clothing color. As shown in FIG. 8, the random forest classifier includes five decision trees 8101, 8102, 8103, 8104, and 8105 (collectively or generally referred to as decision tree 810). Each of the trees is designed to classify clothing color. Because the individual trees generally operate as the decision trees of FIG. 7, a discussion of each of the trees and the decisions made is not provided. In this illustration, three of the five trees (8101, 8102, 8104) determine that the clothing is blue, one 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 of the five trees and calculates the mode of the actual predictions to provide the random forest's answer that the clothing is blue.

[0064] Logistic regression is another algorithm for binary classification tasks. It is based on the logistic function, also known as the sigmoid function. This S-shaped curve can take any real-valued value and map it between 0 and 1, asymptotically approaching these limits. Logistic models can be used to model the probability of a particular class or event being present, such as pass / fail, win / lose, alive / dead, or healthy / sick. This can be extended to model several classes of events, such as determining whether an image contains a cat, dog, lion, etc. Each object detected in an image is assigned a probability between 0 and 1, and the sum of these probabilities adds up to 1.

[0065] In a logistic model, the log odds (log of the odds) of a value labeled "1" are a linear combination of one or more independent variables ("predictors"), each of which can be binary (two classes coded by indicator variables) or continuous (any real-valued value). The corresponding probability of a value labeled "1" is labeled as such because it can vary between 0 (definitely a value of "0") and 1 (definitely a value of "1"). The logistic function is so named because it converts log odds into probabilities. The unit of measurement for the log odds scale is called a logit, another name for the logistic unit. Similar models, such as the probit model, can also be used, but with a sigmoid function instead of the logistic function. The defining feature of a logistic model is that increasing one of the independent variables multiplicatively scales the odds of a given outcome by a constant ratio, and each independent variable has its own parameters. For binary dependent variables, this generalizes the odds ratio.

[0066] In a binary logistic regression model, the dependent variable has two levels (categories). Outputs with more than two values ​​are modeled by multinomial logistic regression, and if the categories are ordered, they are modeled by ordinal logistic regression (e.g., proportional odds ordinal logistic model). Although a logistic regression model itself simply models the probability of the output with respect to the inputs and does not perform statistical classification (it is not a classifier), it can be used to create a classifier, for example, by selecting a cutoff value and classifying inputs with probabilities greater than the cutoff as one class and inputs with probabilities less than the cutoff as the other class. This is a common way to create a binary classifier.

[0067] FIG. 9 illustrates an exemplary logistic regression. This exemplary logistic regression allows for the prediction of outcomes based on a set of variables. For example, the outcome of being accepted into a school can be predicted based on an individual's grade point average. Predictions can be made based on the relationship between past history of grade point average and acceptance. The logistic regression of FIG. 9 allows analysis of the grade point average variable 920 to predict an outcome 910 defined between 0 and 1. At the lower end of the S-curve 930, the grade point average 920 predicts the outcome 910 of not being accepted. At the upper end of the S-curve 940, the grade point average 920 predicts the outcome 910 of being accepted. Logistic regression can be used to predict home values, customer lifetime value in the insurance sector, etc.

[0068] A support vector machine (SVM) can be used to sort the data by making the margin between the two classes as far apart as possible. This is called margin-maximizing separation. Unlike linear regression, which uses the entire dataset for its purpose, SVM is able to take support vectors into account while plotting the hyperplane.

[0069] FIG. 10 illustrates an exemplary support vector machine. In the exemplary SVM 1000, data can be classified into two distinct classes, represented as squares 1010 and triangles 1020. The SVM 1000 operates by drawing a random hyperplane 1030. This hyperplane 1030 is monitored by comparing the distance (shown by lines 1040) between the hyperplane 1030 and the nearest data points 1050 from each class. The data points 1050 closest to the hyperplane 1030 are known as support vectors. The hyperplane 1030 is drawn based on these support vectors 1050, with the optimal hyperplane having the greatest distance from each support vector 1050. The distance between the hyperplane 1030 and the support vectors 1050 is known as the margin.

[0070] The SVM 1000 may be used for data classification by using the hyperplane 1030 to maximize the distance between the hyperplane 1030 and the support vectors 1050. Such an SVM 1000 may be used, for example, to predict heart disease.

[0071] k Nearest Neighbors (KNN) generally refers to a set of algorithms that make no assumptions about the underlying data distribution and perform reasonably short training phases. Generally, KNN uses a large number of data points divided into classes to predict the classification of a new sample point. Operationally, KNN specifies an integer N with the new sample. The N entries in the model of the system that are closest to the new sample are selected. The most common classification of these entries is determined, and that classification is assigned to the new sample. KNN generally requires increasing storage space as the training set grows. This also means that estimation time increases linearly with the number of training points.

[0072] In regression algorithms, the output is continuous, so regression algorithms can be used when the target variable is a continuous variable. Linear regression is a common example of a regression algorithm. Linear regression can be used to measure true quality (such as housing cost, number of calls, or total transactions) by considering consistent variables. The connection between the variables and the outcome is found by fitting a line of best fit (hence the name linear regression). This line of best fit is known as the regression line and is expressed in direct terms: Y=a×X+b. Linear regression is most often used in low-dimensional approaches.

[0073] 11 shows an exemplary linear regression model, in which predictor variables 1110 are modeled against measurement variables 1120. Clusters of instances of the predictor variables 1110 and measurement variables 1120 are plotted as data points 1130. The data points 1130 are then fitted to a best-fit line 1140. Subsequent predictions then use the best-fit line 1140 to predict the predictor variables 1110 for that instance, given the measurement variables 1120. Linear regression can be used to model and predict financial portfolios, salary forecasts, real estate, and transportation estimated arrival times.

[0074] Clustering algorithms may 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 guidance. For example, unsupervised learning algorithms such as K-means clustering can be used to cluster audiences into similar groups based on interests, age, geography, etc.

[0075] K-means clustering is generally considered a simple unsupervised learning approach. It allows similar data points to be clustered together and bound together in the form of clusters. One way to bind data points together is by calculating the centroid of the data points. To determine effective clusters, K-means clustering evaluates the distance of each point from the cluster centroid. Depending on the distance between the data point and the centroid, the data is assigned to the closest cluster. The goal of clustering is to determine the unique groupings of a set of unlabeled data. The "K" in K-means represents the number of clusters formed. The number of clusters (essentially the number of classes into which new instances of data can be classified) can be determined by the user. This determination can be made, for example, using feedback and looking at the size of the clusters during training.

[0076] K-means is used when the dataset has distinct and well-separated points; otherwise, the modeling may render the clusters inaccurate if they are not separated. Additionally, K-means can be avoided if the dataset contains a large number of outliers or if the dataset is nonlinear.

[0077] FIG. 12 illustrates K-means clustering. In K-means clustering, data points are plotted and assigned a K value. For example, for K=2 in FIG. 12, the data points are plotted as shown in depiction 1210. Next, in step 1220, the points are assigned to similar centers. Cluster centroids are identified as shown in 1230. Once the centroids are identified, the points are reassigned to clusters such that the distance between the data points and the centroid of each cluster is minimized, as shown in 1240. New centroids for the clusters can then be determined as shown in depiction 1250. Once the data points are reassigned to clusters, new centroids for the clusters are formed, and an iteration or series of iterations can occur to minimize the size of the clusters and determine the optimal centroids. Next, new data points can be measured and compared to the centroids and clusters to identify them with their clusters.

[0078] Ensemble learning algorithms may be used. These algorithms use multiple learning algorithms to achieve better predictive performance than would be possible from any of the constituent learning algorithms alone. Ensemble learning algorithms perform the task of searching a hypothesis space to find suitable hypotheses that make good predictions for a particular problem. Even if the hypothesis space contains hypotheses that are highly suitable for a particular problem, finding a suitable hypothesis can be very difficult. Ensemble algorithms combine multiple hypotheses to form a better one. The term ensemble is typically used to refer to methods that generate multiple hypotheses using the same base learner. The broader concept of a multi-classifier system also encompasses the hybridization of hypotheses that are not derived from the same base learner.

[0079] Because evaluating the predictions of an ensemble typically requires more computation than evaluating the predictions of a single model, ensembles can be thought of as a way to compensate for poor learning algorithms by performing a lot of extra computation. Fast algorithms such as decision trees are commonly used in ensemble methods such as random forests, but slower algorithms can also benefit from ensemble methods.

[0080] Ensembles are themselves supervised learning algorithms because they can be used to make predictions after training. A trained ensemble therefore represents a single hypothesis. However, this hypothesis is not necessarily contained within the hypothesis space of the model from which it was constructed. Thus, ensembles can be shown to have more flexibility in the functions they can represent. This flexibility theoretically allows them to overfit the training data more than a single model, but in practice, some ensemble methods (especially bagging) tend to reduce the problems associated with overfitting the training data.

[0081] Empirically, ensemble algorithms tend to perform better when there is a significant degree of diversity among the models. Therefore, many ensemble methods aim to promote diversity among the models they combine. While counterintuitive, more random algorithms (such as random decision trees) can be used to generate more powerful ensembles than highly cautious algorithms (such as entropy-reducing decision trees). However, the use of a variety of powerful learning algorithms has been shown to be more effective than using techniques that attempt to simplify models to promote diversity.

[0082] The number of component classifiers in an ensemble has a significant impact on the accuracy of prediction. This becomes even more important for online ensemble classifiers, where the size of the ensemble and the volume and velocity of the big data stream are determined a priori. Theoretical frameworks suggest that there is an ideal number of component classifiers in an ensemble, and that having more or fewer classifiers than this number will result in a decrease in accuracy. Theoretical frameworks also suggest that using the same number of independent component classifiers as class labels will result in the highest accuracy.

[0083] Some common types of ensembles include Bayesian optimal classifiers, bootstrap aggregation (bagging), boosting, Bayesian model averaging, Bayesian model combination, and model bucketing and stacking. Figure 13 shows an exemplary ensemble learning algorithm in which bagging is performed in parallel (1310) and boosting is performed sequentially (1320).

[0084] 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 inputs are modified by the weights and summed using linear combinations. An activation function can control the amplitude of the output. For example, the allowed range of the output is usually 0 to 1, but can also be -1 to 1.

[0085] These artificial networks can be used in predictive modeling, adaptive control, and applications, and can be trained through datasets. Self-learning arising from experience can occur within the network, allowing it to draw conclusions from complex and seemingly unrelated sets of information.

[0086] For completeness, a biological neural network consists of a group of chemically connected or functionally associated neurons. One neuron may be connected to many other neurons, and the total number of neurons and connections in the network may vary widely. Connections, called synapses, are usually formed from axons to dendrites, although dendritic synapses and other connections are also possible. Apart from electrical signaling, other forms of signaling result from the diffusion of neurotransmitters.

[0087] Artificial intelligence, cognitive modeling, and neural networks are information processing paradigms inspired by the way biological nervous systems process data. Artificial intelligence and cognitive modeling attempt to simulate some of the properties of biological neural networks. In the field of artificial intelligence, artificial neural networks have been successfully applied to speech recognition, image analysis, and adaptive control, and to build software agents or autonomous robots (in computer and video games).

[0088] A neural network (NN) is an interconnected group of natural or artificial neurons that uses a mathematical or computational model based on a connectionist approach to computation for information processing, in the case of artificial neurons, called an artificial neural network (ANN) or simulated neural network (SNN). In most cases, ANNs are adaptive systems that change their structure based on external or internal information flowing through the network. More practically, neural networks are nonlinear statistical data modeling or decision-making tools. They can be used to model complex relationships between inputs and outputs and to find patterns in data.

[0089] Artificial neural networks comprise networks of simple processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between the processing elements and element parameters.

[0090] One classic type of artificial neural network is the recurrent Hopfield network. The utility of artificial neural network models lies in the fact that they can be used to estimate functions from observations and also use them. Unsupervised neural networks can be used to learn representations of inputs that capture salient features of the input distribution, and more recently, in deep learning algorithms that can implicitly learn distribution functions for observed data. Training with neural networks is particularly useful in applications where the complexity of the data or task makes the design of such functions impractical by hand.

[0091] Neural networks can be used in a variety of fields. Tasks to which artificial neural networks are applied tend to fall into the following broad categories: function approximation or regression analysis, including time series prediction and modeling; pattern and sequence recognition; classification, including novelty detection and sequential decision making; data processing, including filtering, clustering, blind signal separation, and compression.

[0092] Areas of application of ANNs include identification and control of nonlinear systems (vehicle control, process control), game playing and decision making (backgammon, chess, racing), pattern recognition (radar systems, face identification, object recognition), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications, data mining (or knowledge discovery in databases, or "KDD"), visualization, and email spam filtering. For example, it is possible to create semantic profiles of user interests resulting from photographs trained for object recognition.

[0093] 14 shows an exemplary neural network. The neural network has an input layer represented by multiple inputs, such as 14101 and 14102. The inputs 14101, 14102 are fed into a hidden layer, shown 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. While neural networks perform simple processing through a hidden layer of simple processing elements, nodes 14201, 14202, 14203, and 14204, these nodes can exhibit complex global behavior determined by the connections between the processing elements and element parameters.

[0094] The neural network of Figure 14 may be implemented in hardware. As shown in Figure 15, a hardware-based neural network is shown.

[0095] Treatment of cardiac disorders, such as cardiac arrhythmias, often requires obtaining detailed mapping of cardiac tissue, chambers, veins, arteries, and / or electrical pathways. For example, a prerequisite for successfully performing catheter ablation is accurately locating the source of the cardiac arrhythmia within a cardiac chamber. Such location can be achieved via electrophysiological studies, during which spatially resolved electrical potentials are detected using a mapping catheter introduced into the cardiac chamber. This electrophysiological study is so-called electroanatomical mapping and thus provides 3D mapping data that can be displayed on a monitor. Often, mapping and therapy functions (e.g., ablation) are provided by a single catheter or group of catheters, such that the mapping catheter also simultaneously operates as a therapy (e.g., ablation) catheter.

[0096] Mapping cardiac regions, such as cardiac regions, tissues, veins, arteries, and / or electrical pathways of the heart, can result in the identification of problem areas, such as scar tissue, arrhythmia sources (e.g., electrical rotors), healthy regions, etc. As further disclosed herein, cardiac regions can be mapped such that a visual representation of the mapped cardiac region is provided using a display. Additionally, cardiac mapping can include mapping based on one or more modalities, such as, but not limited to, local activation time (LAT), electrical activity, topology, bipolar mapping, dominant frequency, or impedance. Data corresponding to multiple modalities can be captured using a catheter inserted into the patient's body and provided for rendering simultaneously or at different times based on corresponding settings and / or medical professional preferences.

[0097] Cardiac mapping can be implemented using one or more techniques. As an example of a first technique, cardiac mapping may be implemented by sensing electrical properties of cardiac tissue, such as regional activation time, as a function of precise location within the heart. The corresponding data can be acquired using one or more catheters advanced into the heart using catheters having electrical and position sensors at their distal tips. As a specific example, position and electrical activity can initially be measured at approximately 10 to approximately 20 locations on the inner surface of the heart. These data points can usually be sufficient to generate a preliminary reconstruction or map of the cardiac surface of satisfactory quality. This preliminary map can be combined with data acquired at additional locations to generate a more comprehensive map of the cardiac electrical activity. In clinical settings, it is not uncommon to accumulate data at 100 or more locations to generate a detailed, comprehensive map of the cardiac chamber's electrical activity. The detailed map can then serve as a basis for making decisions regarding therapeutic actions, such as tissue ablation, to alter the propagation of cardiac electrical activity and restore normal cardiac rhythm.

[0098] A catheter containing a position sensor may be used to determine the trajectory of each point on the heart's surface. These trajectories can be used to infer motion properties, such as the contractile force of the tissue. A map indicative of such motion properties may be constructed when trajectory information is sampled at a sufficient number of points within the heart.

[0099] Electrical activity at a point within the heart can typically be measured by advancing a catheter containing an electrical sensor at or near its distal tip to the point within the heart, contacting tissue with the sensor, and acquiring data at the point. One drawback with mapping a cardiac chamber using a catheter containing only a single distal tip electrode is the long time required to collect data from each point for the necessary number of points required for a detailed map of the cardiac chamber as a whole. Therefore, multi-electrode catheters have been developed to simultaneously measure electrical activity at multiple points within a cardiac chamber.

[0100] A multi-electrode catheter may be implemented using any applicable shape, such as a linear catheter with multiple electrodes, a balloon catheter including electrodes distributed on multiple spines forming a balloon, a lasso or loop catheter with multiple electrodes, or any other applicable shape. Figure 16A shows an example of a linear catheter 1602 including multiple electrodes 1604, 1605, and 1606 that may be used to map a cardiac region. The linear catheter 1602 may be wholly or partially elastic such that it can twist, bend, or change its shape based on received signals and / or based on the application of an external force (e.g., cardiac tissue) to the linear catheter 1602.

[0101] FIG. 16B illustrates one embodiment of a balloon catheter 1612 including multiple splines (e.g., 12 splines in the particular embodiment of FIG. 16B) including splines 1614, 1616, 1617 and multiple electrodes on each spline including electrodes 1621, 1622, 1623, 1624, 1625, and 1626 as shown. The balloon catheter 1612 can be designed so that its electrodes can be held in intimate contact with the endocardial surface when deployed in a patient's body. As an example, the balloon catheter can be inserted into a lumen such as a pulmonary vein (PV). The balloon catheter can be inserted into the PV in a deflated state so that the balloon catheter does not occupy its maximum volume while inserted into the PV. The balloon catheter can be inflated while inside the PV so that the electrodes on the balloon catheter contact the entire circular area of ​​the PV. Such contact with the entire circular portion of the PV, or any other lumen, can enable efficient mapping and / or ablation.

[0102] 16C shows an example of a loop catheter 1630 (also called a lasso catheter) that includes multiple electrodes 1632, 1634, and 1636 that can be used to map a cardiac region. The loop catheter 1630 can be wholly or partially elastic such that it can twist, bend, or change its shape based on received signals and / or based on the application of an external force (e.g., cardiac tissue) to the loop catheter 1630.

[0103] According to one example, a multi-electrode catheter can be advanced into a cardiac chamber. Dorso-anterior (AP) and lateral fluorograms can be acquired to establish the position and orientation of each of the electrodes. Electrograms can be recorded from each electrode in contact with the cardiac surface relative to a temporal reference, such as the onset of the P wave in sinus rhythm obtained from a surface ECG. As further disclosed herein, the system can distinguish between those electrodes that register electrical activity and those that do not due to lack of access to the endocardial wall. After an initial electrogram is recorded, the catheter can be repositioned, and fluorograms and electrograms can be recorded again. An electrical map can then be constructed from a repetition of the above process.

[0104] According to one embodiment, cardiac mapping can be generated based on the detection of intracardiac electrical fields. Non-contact techniques can be implemented to simultaneously acquire a large amount of cardiac electrical information. For example, a catheter having a distal end portion can be provided with a series of sensor electrodes distributed over the surface of the catheter and connected to insulated conductors for connection to signal sensing and processing means. The size and shape of the end portion can be such that the electrodes are substantially spaced from the walls of the heart chamber. The intracardiac electrical fields can be detected during a single heartbeat. According to one embodiment, the sensor electrodes can be distributed on a series of circumferential portions in spaced-apart planes. These planes can be perpendicular to the long axis of the catheter end portion. At least two additional electrodes can be provided adjacent the long axis end portions of the end portion. As a more specific example, the catheter can include four circumferential portions with eight equiangularly spaced electrodes on each circumferential portion. Thus, in this particular implementation, the catheter can include at least 34 electrodes (32 circumferential electrodes and two end electrodes).

[0105] According to another embodiment, an electrophysiological cardiac mapping system and technique based on a non-contact, non-expandable multi-electrode catheter can be implemented. Electrograms can be acquired using a catheter with multiple electrodes (e.g., 42-122 electrodes). According to this implementation, knowledge of the relative geometry of the probe and endocardium can be obtained, for example, through an independent imaging technique such as transesophageal echocardiography. After the independent imaging, non-contact electrodes can be used to measure cardiac surface potentials, from which a map can be constructed. This technique can include the following steps (after the independent imaging step): (a) measuring potentials using multiple electrodes disposed on a probe positioned within the heart; (b) determining the geometric relationship between the probe surface and the endocardium surface; (c) generating a matrix of coefficients representing the geometric relationship between the probe surface and the endocardium surface; and (d) determining the endocardium potentials based on the electrode potentials and the coefficient matrix.

[0106] According to another embodiment, a technique and apparatus for mapping the electrical potential distribution of a cardiac chamber can be implemented. An intracardiac multi-electrode mapping catheter assembly can be inserted into a patient's heart. The mapping catheter assembly can include a multi-electrode array with an integrated reference electrode, or preferably, a companion reference catheter. These electrodes can be arranged in a substantially spherical array. The electrode array can be spatially referenced to a point on the endocardial surface by a reference electrode or reference catheter that comes into contact with the endocardial surface. A preferred electrode array catheter can carry a large number of individual electrode sites (e.g., at least 24). Additionally, the technique of this embodiment can be implemented by knowing the location of each electrode site on the array as well as the cardiac geometry. These locations are preferably determined by the technique of impedance plethysmography.

[0107] According to another embodiment, a cardiac mapping catheter assembly can include an electrode array defining multiple electrode sites. The mapping catheter assembly can also include a lumen for receiving a reference catheter having a distal tip electrode assembly that can be used to probe the heart wall. The mapping catheter can include a braid of insulated wires (e.g., having 24 to 64 wires within the braid), each of which can be used to form an electrode site. The catheter can be easily positionable within the heart to be used to acquire electrical activity information from a first set of non-contact electrode sites and / or a second set of contact electrode sites.

[0108] According to another embodiment, another catheter for mapping electrophysiological activity within the heart can be implemented. The catheter body can include a distal tip adapted to deliver stimulation pulses for pacing the heart, or an ablation electrode for ablating tissue in contact with the tip. The catheter can further include at least a pair of orthogonal electrodes capable of generating a differential signal indicative of local cardiac electrical activity adjacent the orthogonal electrodes.

[0109] According to another example, a process for measuring electrophysiological data within a heart chamber can be implemented. The method can include, in part, positioning a set of active and inactive electrodes in the heart, generating an electric field within the heart chamber by applying an electric current to the active electrodes, and measuring the electric field at the inactive electrode sites. The inactive electrodes are contained within an array positioned on an inflatable balloon of a balloon catheter. In a preferred embodiment, the array is said to have 60-64 electrodes.

[0110] According to another embodiment, cardiac mapping can be implemented using one or more ultrasound transducers that can be inserted into a patient's heart and can acquire multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) at various positions and orientations within the heart. The position and orientation of a given ultrasound transducer can be known, and the acquired ultrasound slices can be stored so that they can be displayed at a later time. One or more ultrasound slices corresponding to the position of a probe (e.g., a treatment catheter) can then be displayed, and the probe can be overlaid on the one or more ultrasound slices.

[0111] According to other embodiments, body patches and / or body surface electrodes may be positioned on or adjacent to a 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 position of the catheter may be determined by the system based on signals transmitted and received between one or more electrodes of the catheter and the body patch and / or body surface electrodes. In addition, the catheter electrodes may sense biometric data (e.g., LAT values) from within the patient's body (e.g., within the heart). The biometric data may be associated with the determined position of the catheter such that a rendering of the patient's body part (e.g., heart) can be displayed and show the biometric data superimposed on the shape of the body part as determined by the position of the catheter.

[0112] FIG. 17 is a diagram of an example system 1720 capable of implementing one or more features of the presently disclosed subject matter. All or a portion of the system 1720 can be used to collect information for a training dataset and / or to implement a trained model. The system 1720 can include components, such as a catheter 1740, configured to acquire biometric data for cardiac mapping and / or to injure a tissue region of an internal organ. Accordingly, it will be understood that the catheter 1740 can be a mapping catheter, a treatment (e.g., ablation) catheter, or both. While the disclosure herein may refer to the catheter 1740 operating as a mapping catheter, a treatment catheter, or both, it will be understood that one or more catheters may be used to implement the subject matter disclosed herein. While the catheter 1740 is shown as being a point catheter, it will be understood that any shape of catheter including one or more elements (e.g., electrodes) can be used to implement the embodiments disclosed herein. The system 1720 includes a probe 1721 having a shaft that a physician 1730 can navigate into a body part, such as a heart 1726, of a patient 1728 lying on a table 1729. According to various embodiments, multiple probes may be provided, and while a single probe 1721 is described herein for simplicity, it will be understood that the probe 1721 may represent multiple probes. As shown in FIG. 17 , the physician 1730 can insert the shaft 1722 through the sheath 1723 while manipulating the distal end of the shaft 1722 using a manipulator 1732 near the proximal end of the catheter 1740 and / or a deflector from the sheath 1723. As shown in inset 1725, the catheter 1740 can be attached at the distal end of the shaft 1722. The catheter 1740 can be inserted through the sheath 1723 in a collapsed state and then expanded within the heart 1726.As further disclosed herein, the catheter 1740 may include at least one ablation electrode 1747 and a catheter needle 1748 .

[0113] According to embodiments, catheter 1740 may be configured to ablate a tissue region in a chamber of heart 1726. Inset 1745 shows a close-up of catheter 1740 inside a chamber of heart 1726. 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 splines that form the shape of catheter 1740. One or more other elements (not shown) may be provided and may be any element configured to perform ablation or acquire biometric data, and may be an electrode, a transducer, or one or more other elements.

[0114] According to embodiments disclosed herein, an ablation electrode, such as electrode 1747, may be configured to deliver energy to a tissue region of a body organ, such as heart 1726. The energy may be thermal energy and may cause damage to the tissue region starting at the surface of the tissue region and extending through the thickness of the tissue region.

[0115] According to embodiments disclosed herein, the biometric data may include one or more of LAT, electrical activity, topology, bipolar mapping, dominant frequency, impedance, etc. The local activation time may be the time point of a threshold activation corresponding to local activation calculated based on a normalized initial onset. The electrical activity may be any applicable electrical signal that can be measured based on one or more thresholds and may be sensed and / or enhanced based on signal-to-noise ratio and / or other filters. The topology may correspond to the physical structure of a body part or portion of a body part, or may correspond to changes in the physical structure for different portions of the body part or for different body parts. The dominant frequency may be a frequency or range of frequencies prevalent in a portion of a body part and may differ in different portions of the same body part. For example, the dominant frequency of the pulmonary veins of a heart may be different from the dominant frequency of the right atrium of the same heart. The impedance may be a resistance measurement in a given region of a body part.

[0116] 17 , the probe 1721 and catheter 1740 can be connected to a console 1724. The console 1724 can include a processor 1741, such as a general-purpose computer with suitable front-end and interface circuitry 1738, for transmitting and receiving signals to and from the catheter, as well as for controlling other components of the system 1720. In some embodiments, the processor 1741 can be further configured to receive biometric data, such as electrical activity, and determine whether a given tissue region conducts electricity. According to one embodiment, the processor can be external to the console 1724, for example, located in the catheter, an external device, a mobile device, a cloud-based device, or can be a stand-alone processor.

[0117] As noted above, processor 1741 may include a general-purpose computer, which may be programmed in software to perform the functions described herein. The software may be downloaded to the general-purpose computer in electronic form, for example, over a network, or alternatively or additionally, may be provided and / or stored on non-transitory tangible media, such as magnetic, optical, or electronic memory. The exemplary configuration shown in FIG. 17 may be modified to implement embodiments disclosed herein. Embodiments of the present disclosure may be similarly applied using other system components and configurations. Furthermore, system 1720 may include additional components, such as elements for sensing electrical activity, wired or wireless connectors, processing and display devices, etc.

[0118] According to one embodiment, a display connected to a processor (e.g., processor 1741) may be located at a remote location, such as a separate hospital or a separate healthcare provider network. Additionally, system 1720 may be part of a surgical system configured to obtain anatomical and electrical measurements of a patient's organs, such as the heart, and to perform cardiac ablation procedures. One example of such a surgical system is the Carto® system sold by Biosense Webster.

[0119] System 1720 can also, and optionally, acquire biometric data, such as anatomical measurements of the patient's heart, using ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), or other medical imaging techniques known in the art. System 1720 can acquire electrical measurements using a catheter, an electrocardiogram (EKG), or other sensors that measure the electrical properties of the heart. The biometric data, including the anatomical and electrical measurements, may then be stored in memory 1742 of mapping system 1720, as shown in FIG. 17 . The biometric data may be transmitted from memory 1742 to processor 1741. Alternatively, or in addition, the biometric data may be transmitted using network 1762 to server 1760, which may be local or remote.

[0120] The network 1762 may be any network or system commonly known in the art, such as an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between the mapping system 1720 and the server 1760. The network 1762 may be wired, wireless, or a combination thereof. Wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection commonly known in the art. Wireless connections may be implemented using Wi-Fi, WiMAX, Bluetooth, infrared, cellular networks, satellite, or any other wireless connection method commonly known in the art. Additionally, several networks may function alone or communicate with each other to facilitate communication within the network 1762.

[0121] In some cases, server 1762 may be implemented as a physical server. In other cases, server 1762 may be implemented as a virtual server, a public cloud computing provider (e.g., Amazon Web Services (AWS)).

[0122] The control console 1724 may be connected by a cable 1739 to body surface electrodes 1743, which may include adhesive skin patches that are affixed to the patient 1730. A processor in conjunction with the current tracking module can determine position coordinates of the catheter 1740 within the patient's body part (e.g., heart 1726). The position coordinates may be based on impedance or electromagnetic fields measured between the body surface electrodes 1743 and electrodes 1748 or other electromagnetic components of the catheter 1740. Additionally or alternatively, location pads may be positioned on the surface of the bed 1729 and may be separate from the bed 1729.

[0123] Processor 1741 may include real-time noise reduction circuitry, typically configured as a field programmable gate array (FPGA), followed by an analog-to-digital (A / D) ECG (electrocardiograph) or EMG (electromyogram) signal conversion integrated circuit. Processor 1741 may communicate signals from the A / D ECG or EMG circuitry to another processor and / or may be programmed to perform one or more functions disclosed herein.

[0124] The control console 1724 may also include an input / output (I / O) communication interface that allows the control console to communicate signals to and / or from the electrodes 1747 .

[0125] During a procedure, processor 1741 facilitates presentation of body part rendering 1735 to physician 1730 on display 1727 and can store data representing body part rendering 1735 in memory 1742. Memory 1742 may comprise any suitable volatile and / or non-volatile memory, such as random access memory or a hard disk drive. In some embodiments, medical professional 1730 may be able to manipulate body part rendering 1735 using one or more input devices, such as a touchpad, mouse, keyboard, gesture recognizer, etc. For example, the input device may be used to change the position of catheter 1740 so that rendering 1735 is updated. In an alternative embodiment, display 1727 may include a touchscreen, which may be configured to receive input from medical professional 1730 in addition to presenting body part rendering 1735.

[0126] According to exemplary embodiments of the disclosed subject matter, new CPM matrices may be generated based on historical CPM matrices with little or no corresponding catheter position information. In particular, the techniques disclosed herein may enable the generation of CPM matrices without the use of an in-body catheter to physically cover the entire heart chamber and determine the ratios for each position.

[0127] A historical CPM matrix may be generated for each given catheter position (e.g., based on the corresponding cluster) based on the current distribution from signals transmitted from an internal catheter electrode and received by multiple body surface (BS) patches on the patient's body. FIG. 18 illustrates a process 1800 for determining a catheter position based on new electrical signals and generating a CPM matrix without new catheter position information corresponding to the new electrical signals. For clarity, many examples of historical CPM matrices with corresponding patient characteristics (e.g., electrical signals, catheter orientation and / or position, cardiac anatomy, etc.) and catheter positions may be used as training data to generate a model according to FIGS. 4-15 provided herein. The model may be trained such that new electrical signals transmitted by the catheter's electrodes may be captured, for example, by the BS patch and fed to the model along with the patient characteristics. Alternatively, or in addition, the model may be trained such that new electrical signals are transmitted by the BS patch and received by the catheter's electrodes and fed to the model along with the patient characteristics. Based on the trained components of the model, the catheter position may be predicted and a CPM matrix may be identified. This implementation would expedite the generation of the CPM matrix, as it reduces the need to capture position information and corresponding ratios for each catheter position.

[0128] As shown in flowchart 1800 of FIG. 18 , in step 1802, historical CPM matrices, certain patient characteristics (e.g., electrical signals, catheter orientation and / or position, cardiac anatomy, etc.), and corresponding catheter positions may be collected. When the electrical signals of the corresponding CPM matrices are generated, the corresponding catheter positions may be identified (e.g., via magnetic mapping electrodes). In step 1804 of process 1800 of FIG. 18 , the historical CPM matrices, patient characteristics, and corresponding positions collected in step 1802 may be used as training data for a learning system. In step 1804, the training data may be used to train the learning system based on a given algorithm. In step 1806 of process 1800, a model may be generated using the trained learning system. The model may be generated given new patient characteristics (e.g., electrical signals, catheter orientation and / or position, cardiac anatomy, etc.), and the model is configured to provide a new CPM matrix with a minimum catheter position or no catheter position as an output.

[0129] 18 , new patient characteristics for the patient (e.g., electrical signals, catheter orientation and / or position, cardiac anatomy, etc.) may be received or provided as input by the model generated in step 1806. In step 1810, the model may output predicted catheter positions and / or generate new CPM matrices based on the input electrical signals.

[0130] FIG. 19 shows an exemplary implementation for collecting electrical signals. As shown, a catheter 1910 may be inserted into a heart chamber (e.g., a cluster) 1900 and may include electrodes configured to emit electrical signals. The electrical signals may be received by one or more BS patches 1920 such that a CPM matrix can be generated based on the received electrical signals emitted by the catheter 1910. According to an alternative implementation, as shown in FIG. 19, a catheter 1910 may be inserted into a heart chamber (e.g., a cluster) 1900 and may include electrodes configured to receive electrical signals. The electrical signals may be transmitted by one or more BS patches 1920 such that a CPM matrix can be generated based on the electrical signals received at the catheter 1910 transmitted by the BS patches 1920.

[0131] 18, a historical CPM matrix and corresponding catheter positions may be received in step 1802. The historical CPM matrix may be generated based on an adaptive CPM estimation process and a CPM application process. The CPM application process may further include a cluster selection module and a CPM application module.

[0132] The adaptive CPM estimation process uses the vector , obtained from a catheter, such as any hybrid catheter having an EM sensor and associated electrodes.

[0133]

number

[0134] The matrices built in the historical CPM estimation process are constructed over time, and therefore there is an initialization period for the Active Current Position (ACL) process during which the processor receives initial data from the decomposition process. For a particular cluster, once the processor has accumulated enough data for that cluster, it can generate the cluster's matrix.

[0135] In historical CPM applications, the generated matrix is ​​used in conjunction with current measurements of the cathode electrodes to calculate the position of each electrode in real time, according to the following equation:

[0136]

number

[0137]

number

[0138]

number

[0139] CPM Vector

[0140]

number

[0141]

number

[0142]

number

[0143] The processor

[0144]

number

[0145]

number

[0146] Once the respiratory indices are accumulated, the processor performs a principal component analysis (PCA) on the indices to find the direction between the components with the largest eigenvalues ​​as follows:

[0147]

number

[0148] The direction given by the above equation is used to calculate the respiration descriptor value as follows:

[0149]

number

[0150] The mean and range of RDi values ​​are calculated as follows:

[0151]

number

[0152] The mean and range are used to calculate a normalized value RDni of RDi, which ranges from 0 to the maximum value ClNo, a number that defines the resolution of the update holder described below, and is typically around 5.

[0153]

number

[0154] The value of RDni is stored in memory.

[0155] 20 is a process 2000 illustrating steps performed by a processor to generate a CPM matrix according to an embodiment of the present invention. The steps of process 2000 are performed in an adaptive CPM estimation process as each measurement is made at the catheter.

[0156] In a first step 2002, measurements are received from any hybrid catheter, as described above, and a processor converts those measurements into CPM vectors

[0157]

number

[0158] In a first update holder step 2004, an update holder index for the measurement is calculated. In a first condition 2006, the processor checks whether the update holder index already exists by checking whether it is stored in memory. If the index already exists, the measurement is discarded and the process ends.

[0159] If the index does not exist, the index and the measurement may be saved in a memory buffer in a save step 2008. The measurement is a vector

[0160]

number

[0161] In a cluster association step 2010, the measurements are associated with their corresponding clusters. This association is performed by calculating a corresponding cluster index from the measurements. The measurements are associated with this cluster index.

[0162] Next, cluster origin

[0163]

number

[0164]

number

[0165] In a second update holder step 2012, an update holder index for the neighboring cluster is calculated using the measurements received in step 2002. If the update index is not already occupied, the measurements are placed in a buffer and the index is saved. If the index is already occupied, no processing occurs.

[0166] In a second condition 2014, the number M of update indices in each cluster Clx is evaluated. If M is greater than a predetermined number, typically on the order of about 40, then in a cluster matrix step 2016, the CPM matrix A of the cluster is calculated using the formula:

[0167]

number

[0168]

number

[0169]

number

[0170] Two CPM matrices A may be calculated for each cluster, one using measurements with the reference catheter and one without reference catheter measurements, and then process 2000 ends.

[0171] If, at condition 2014, M is less than or equal to a predetermined number, the process 2000 ends.

[0172] Typically, the calculations in process 2000 are checked at various stages to ensure that the calculated outcomes are self-consistent. For example, in cluster association step 2010, if the number of existing adjacent clusters is less than a predetermined number, e.g., four, an error is assumed and the measurements of step 2002 are rejected. Other self-consistency checks for the operation of the process will be apparent to those skilled in the art.

[0173] Thus, historical CPM matrices based on corresponding catheter positions may be generated according to process 2000 of FIG. 20. In step 1802 of process 1800 of FIG. 18, historical CPM matrices may be received along with corresponding patient characteristics (e.g., electrical signals, catheter orientation and / or location, cardiac anatomy, etc.) for each given historical CPM matrix. As further disclosed herein, historical CPM matrices may be provided for a large number of patients. A large number of patients may be, for example, more than 100 patients, more than 1000 patients, more than 10,000 patients, etc. The number of patients for which historical CPM data is used may depend on one or more of the quality of the CPM data and the corresponding catheter positions, which may be determined on a case-by-case basis.

[0174] According to one implementation, the CPM matrices provided for the majority of patients may correspond to procedures for which accurate matrices were generated based on patient characteristics (e.g., electrical signals, catheter orientation and / or location, cardiac anatomy, etc.) and corresponding catheter locations. For example, as further disclosed herein, a set of 100 patient sets of CPM data may be available for training a system. Of the 100 available sets of CPM data, only 70 sets may correspond to procedures for which a quality threshold is met. The 70 sets may be used as training data for embodiments disclosed herein. In contrast, the 30 sets that do not meet the quality threshold may not be included as training data.

[0175] In step 1804 of process 1800 of Figure 18, the historical CPM matrices and corresponding catheter positions can be used to train a learning system. Training may be performed using hardware, software, and / or firmware. Training may include analyzing and correlating the CPM matrices, patient characteristics (e.g., electrical signals, catheter orientation and / or position, cardiac anatomy, etc.), and the corresponding catheter positions received in step 1802. In particular, the CPM matrix values ​​at a given catheter position can be used to determine whether a correlation or link exists between a given value or set of values ​​and the corresponding catheter position (e.g., if a given set of matrix values ​​correlates to a given catheter position).

[0176] The CPM matrices, patient characteristics, and catheter position features collected in step 1802 may be extracted and may include patterns, relationships, correlations, electrical signals, catheter orientations and / or positions, cardiac anatomy, etc. A feature matrix may be generated based on the extracted features, and a learning system may be trained in step 1804. According to one implementation, the learning system may be trained based on a machine learning algorithm.

[0177] The learning system may be trained using an algorithm to generate the model in step 1806. The algorithm may be, for example, a classification algorithm, a regression algorithm, a clustering algorithm, or any applicable algorithm capable of generating a model that predicts the location of arrhythmias using ECG data.

[0178] As an example, FIG. 21 shows a logistic regression diagram predicting whether certain patient characteristics (e.g., electrical signal, catheter orientation and / or location, cardiac anatomy, etc.) are likely to correspond to a given catheter location within the heart. This logistic regression then allows for the prediction of a cardiac location and corresponding CPM matrix ratio based on the patient characteristics input into the model. For example, based on multiple patient characteristics, such as a given cardiac anatomy and an electrical signal emitted at a first time, the outcome of the corresponding cardiac location can be provided by the logistic regression model. The past history of the combination of the relationship between given patient characteristics and specific cardiac locations allows for prediction to occur. The logistic regression of FIG. 21 allows for the analysis of a combination of given patient characteristics (e.g., cardiac anatomy and received electrical signal), represented by variables 2120, to be mapped to a cluster within a given cardiac location, e.g., the left atrium, where probability 2110 is defined between 0 and 1. At the low end 2130 of the sigmoid curve, a given combination of patient characteristics 2120 may correspond to the outcome 2110 of not being in the left atrium. At the high end 2140 of the sigmoid curve, the combination 2120 predicts the outcome 2110 of being in the left atrium.

[0179] As described above, various combinations of a large number of such features (e.g., patient characteristics) can be used to generate multiple logistic regression-based outcomes, each predicting the likelihood of a cardiac location and a respective CPM matrix. All such combinations of logistic regression-based outcomes may be used to generate a logistic regression model in step 1906, which is generated based on training the learning system in step 1904.

[0180] Although a logistic regression-based model is provided as an example, it will be appreciated that any applicable algorithm (e.g., classification, regression clustering, etc.) may be used to generate the respective models in step 1906.

[0181] Once sufficient training data (e.g., features) have been used to train the learning system and generate an applicable model, the model may be used with new data. In step 1908, new patient characteristics (e.g., electrical signals, catheter orientation and / or location, cardiac anatomy, etc.) may be applied to the model, and the model may extract features from the new patient characteristics. A feature vector may be generated and input to the model generated in 1906. The model may use the feature vector as input (e.g., as shown in FIG. 15 ) and predict CPM matrices and / or cardiac positions based on the patient characteristics. According to one implementation, a subset of the generated CPM matrices and corresponding known cardiac positions may be provided to the model, such that the model outputs the remainder of the CPM matrices corresponding to unknown cardiac positions.

[0182] A system and method are disclosed for generating a position estimate for each electrode on a catheter based on current measurements by a chest patch. The system and method estimate the location of the catheter electrode given current measurements recorded by a patch (e.g., 6) placed on the patient's chest. The catheter includes electrodes 22 (e.g., two on the main stem and four on each of five arms as shown in FIG. 16B). Each electrode on the catheter emits a current at a different frequency. The current travels through the body until it reaches a sensor on the patch, which generates a current reading. When the electrode is positioned at a specific location, the patch generates one or more vector measurements that describe the current distribution and respiratory indices. This vector is sometimes called a VEC. The system and method can generate an estimate of the electrode's location (in 3D space) by taking the VEC into account.

[0183] One method for estimating the electrode location utilizes an electromagnetic (EM) sensor located on the main stem of the catheter. The location of the EM sensor in 3D space may be known. One of the electrodes on the catheter, called the mapping electrode, is located a given distance on the rigid catheter stem immediately adjacent to the EM sensor, and therefore its location in 3D space may be known with an accuracy that takes into account the location based on the EM sensor.

[0184] As the physician moves the catheter around the heart, the system collects measurements of the known positions of the mapping electrodes (based on the EM sensors) along with the VEC of the mapping electrodes at each point. The system and method can construct a current position mapping (CPM). The CPM includes a mapping from VEC values ​​to voxels where the mapping electrodes access and connect to the VEC values ​​at that location.

[0185] CPM may also include estimation of other nearby voxels not yet accessed by mapping electrodes. The estimate at a particular voxel is currently generated by linear interpolation of VEC values ​​from nearby voxels for which both the VEC value and the location value are known with certainty.

[0186] The system and method can utilize CPM to estimate the 3D location of an electrode: given a VEC value of an electrode, CPM is utilized to identify which voxel contains this VEC value, which indicates the 3D location of the electrode.

[0187] Initially, because the CPM is so small, not all VEC values ​​for the electrodes can be found in the CPM, and therefore the electrode locations cannot be estimated. As the catheter accesses more specific locations within the heart, the CPM can become more comprehensive, and electrode location estimates become available for more locations. The location estimates can become more accurate as more measurements are collected.

[0188] FIG. 22 shows the configuration of a system 2200 for predicting electrode locations. In FIG. 22, "ME" indicates a mapping electrode. The system 2200 includes a neural network (NN) 2260 that can output an estimate of an electrode's location 2280 given this electrode's VEC value 2230.3. The NN 2260 is trained "on the fly" 2200.3 for a new patient 2275 using measurements from the EM sensors and ME 2250.3, and can then be applied to other electrodes' VEC measurements 2230.3 to estimate their locations. For a given patient, the NN is not trained from a "blank slate" because there may not be enough measurements in the given patient's data. Instead, the NN 2260 is initialized offline 2200.1 by training the NN 2260.1 on data collected from a previous patient 2205.1 as well as data collected from a simulation model. Then, in a new patient, transfer learning 2260.2 is utilized to update the NN model 2260 based on measurements from that particular patient 2205.2. Because different cardiac structures vary, training of the NN 2260 cannot be done with raw measurements collected from a previous patient 2205.1. Registration (alignment) is required, i.e., transforming the raw data into the universal coordinate system 2240.1.

[0189] Referring now to Figure 23, there is shown the core configuration of a NN 2300 that may function as NN 2260. Figure 23 is also described with reference to Figure 14. NN 2300, functioning as NN 2260, may include several layers. Input layer 2310 (represented as five nodes, 2310.1, 2310.2, 2310.3, 2310.4, 2310.5) contains vectors representing VEC measurements. Output layer 2340 (represented as three nodes, 2340.1, 2340.2, 2340.3) contains vectors of three values ​​representing positions in 3D space. The number and size of hidden layers 2320, 2330 and their architecture may be varied. As shown in FIG. 23, there is a middle layer 1 2320 (represented as nine nodes 2320.1, 2320.2, 2320.3, 2320.4, 2320.5, 2320.6, 2320.7, 2320.8, 2320.9) and a middle layer 2 2330 (represented as seven nodes 2330.1, 2330.2, 2330.3, 2330.4, 2330.5, 2330.6, 2330.7).

[0190] Various input signals are fed into the left input layer 2310. Further hidden layers are used to represent various features of the inputs, as well as non-linear combinations of the inputs. The output layer 2340 combines the signals into vectors that represent positions in 3D space. Depending on the nature of the data and the required accuracy of the output, more (or fewer) hidden layers 2320, 2330 may be used, as well as hidden layers with different numbers of nodes or different connection topologies.

[0191] This kind of topology can represent any function that maps input to output (Universal Approximation Theorems), but in practice, variations on it or other topologies may be required depending on the nature of the data. For example, we may add another NN component that classifies inputs into specific classes, and this classification value is fed into other layers.

[0192] As will be appreciated, any number of layers and nodes within a layer may be utilized, and the depiction of FIG. 23 is for illustrative purposes and understanding only.

[0193] Data from previous patients 2205.1 are used to train the system 2200.1 and NN 2260.1 to provide vectors representing VEC measurements to the input layer 2310. For each patient, the data includes measurements consisting of pairs of ME location (based on EM sensor location) 2220.1 and the VEC of this electrode 2230.1. Additionally, the data from previous patients 2205.1 may include a Carto 3D model 2210.1 of cardiac tissue.

[0194] This type of data 2205.2 is also required for the online transfer learning stage 2200.2. Data from the current case 2205.2 is used to fine-tune the system 2200.2 and training NN 2260.2 to provide vectors representing VEC measurements to the input layer 2310. For each patient, the data includes paired measurements consisting of the location of the ME (based on the EM sensor location) 2220.2 and the VEC of this electrode 2230.2. Additionally, data from a previous patient 2205.2 may include a Carto 3D model 2210.2 of cardiac tissue.

[0195] Because different cardiac structures vary and the locations where patches are placed on patients also vary, training of the NN 2260 cannot be done with raw measurements collected from a previous patient 2205.1. Registration (alignment) is required, i.e., transforming the raw data into a universal coordinate system (UCS) (2240.1 from the previous patient and 2240.2 from the current patient). Given the carto 3D models 2210.1, 2210.2 of the cardiac tissue, the UCS can be constructed. For example, for each cardiac chamber, the origin of the UCS may be placed exactly at the chamber's center of gravity. The x-axis may be aligned with the specific cardiac structure involved. 3D locations within the available data may be shifted, rotated, and stretched to transform into this UCS.

[0196] The transformed positions 2240.1, 2240.2 are used along with the ME positions in UCS 2250.1, 2250.2 as the desired output values ​​for NNs 2260.1, 2260.2. Thus, raw data 2205.1, 2205.2 are first transformed into UCS 2240.1, 2240.2, 2260.1 to train system 2200, 2260.2 to fine-tune system 2200, and the output of system 2200, including ME positions in UCS 2250.3, can be transformed back to the original coordinate system 2240.3 as needed during the new patient guessing phase 2200.3.

[0197] In the offline stage 2200.1, the NN 2260 is trained (2260.1) on data from the previous example 2205.1. As mentioned above, this data may include pairs of known 3D positions (after conversion to UCS) 2250.1 of mapping electrodes and VEC values ​​2230.1. The ME positions in UCS 2250.1 can be achieved from the Carto 3D model 2210.1 and ME positions 2220.1, which are converted to UCS 2240.1. The VEC values ​​2230.1 serve as input to the NN 2260, and the 3D positions serve as the desired output of the NN 2260.

[0198] The data set of historical data 2205.1 may be divided into a training set, a validation set, and a test set. The first two sets are used during system development, while the test set is used only to evaluate the accuracy of the system. Cross-validation may also be used to improve performance, which incorporates knowledge from past patients 2205.1 into the NN 2260.

[0199] After the system 2200 is deployed, additional data can be accumulated and added to the training dataset to retrain the system 2200 and continually improve its accuracy.

[0200] Historical data 2205.1 may be insufficient to achieve the desired results of training 2260.1 NN 2260. A standard technique in machine learning is to augment real data with artificial data generated by simulation. Systems trained on a combination of real data 2205.1 and simulated data can learn better and be more robust than systems trained only on real data (if the simulation is close enough to reality).

[0201] There are existing systems that produce high-quality simulations of cardiac anatomy, including the electrical currents and how they diffuse and change as they travel through cardiac tissue and fluid. These systems can be used to simulate readings from a catheter as it travels through the heart. The resulting simulated data set can be added to real data 2205.1.

[0202] After training 2260.1, NN 2260, trained NN 2270, may be subjected to online fine-tuning 2200.2. The trained NN 2270 is fine-tuned 2260.2 using data from the current case 2205.2. As mentioned above, this data may include data consisting of known 3D positions (after conversion to UCS) 2250.2 of the mapping electrodes and VEC values ​​2230.2. ME positions in UCS 2250.2 may be achieved from the Carto 3D model 2210.2 and ME positions 2220.2, which are converted to UCS 2240.2. The VEC values ​​2230.2 serve as input to NN 2260, and the 3D positions serve as the desired output of NN 2260.

[0203] The NN 2270 trained on historical data 2205.1 may be used "as is" for online inference on new patients 2205.2. To improve accuracy, fine-tuning 2260.2 can be utilized. Fine-tuning 2260.2, also known as transfer learning, allows knowledge from previously learned tasks to be reused to learn new tasks, thus improving the accuracy of the results. This means that the NN 2260 is continually trained and updated on data collected from new patients 2205.2 as it becomes available while the catheter accesses new locations in the patient's heart. Due to time constraints, all layers 2320, 2330 of the NN 2260 are not retrained, but only the last one or two layers are trained. This provides a "fine-tuning" 2260.2 of the NN 2260 to the cardiac anatomy and measurements of a particular patient. Fine-tuning 2260.2 may be performed after a certain amount of time as needed to generate at least a portion of a Carto model 2210.2 of the current patient's heart, as this model is required to convert the raw inputs to UCS 2240.2. As more measurements are collected to generate Carto model 2210.2, the conversion to UCS 2240.2 becomes more accurate, and thus the NN's 2260 output may improve.

[0204] Once NN 2260 is fine-tuned 2260.2 on patient data 2205.2, the guessing stage 2200.3 can be populated using the trained NN 2275. NN 2260 can provide the VEC values ​​of electrodes 2230.3 to obtain the location of the electrodes in UCS 2250.3. This location then needs to be transformed into the patient specific coordinate system by converting from UCS 2240.3 to obtain the actual location of the predicted electrode location 2280. In parallel, more data continues to be collected for the current patient 2205.2 and used to keep NN 2260 fine-tuned 2260.2.

[0205] Because the various chambers within the heart are separate (left / right atria, left / right ventricles, etc.) and have different structures, a separate NN 2260 may be utilized for each such chamber.

[0206] Each item in the historical data set 2205.1 includes an indication of the chamber in which it was recorded, and during online use, this indication may be provided as a manual instruction from the physician or automatically based on categorization of catheter readings using a separate system.

[0207] The entire process is performed on each chamber separately. However, transfer learning 2260.2 may be performed on data across chambers to improve both the accuracy and performance of the NN 2260. During training 2260.1, 2260.2 of the NN, the lower layers automatically learn to detect basic features that are relevant to all chambers, allowing a multi-chamber approach to be utilized.

[0208] While features and elements are described above in particular combinations, those skilled in the art will understand that each feature or element can be used alone or in combination with other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware embodied in a computer-readable medium for execution on 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-ROM disks and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0209] [Embodiment] (1) A system for automatically generating a CPM matrix, comprising: a plurality of body surface electrodes configured to sense electrical signals; 1. A processor comprising a neural network, receiving a plurality of historical CPM matrices, patient characteristics, and corresponding catheter positions; training a learning system based on the plurality of CPM matrices, the patient characteristics, and the corresponding catheter locations; generating a model based on the learning system; receiving new patient characteristics at least in part from the plurality of body surface electrodes; a processor configured to generate a new CPM matrix from the plurality of body surface electrodes based at least in part on new patient characteristics. (2) The system described in embodiment 1, wherein the received multiple historical CPM matrices are based on the known corresponding catheter positions. (3) The processor: receiving a subset of patient characteristics having known catheter locations; 2. The system of claim 1, further configured to generate a new CPM matrix based also on a subset of patient characteristics having the known catheter positions. (4) The system of embodiment 1, wherein the patient characteristics are selected from one or more of electrical signals, catheter position, catheter orientation, and cardiac anatomical structure. (5) The system of embodiment 4, wherein the patient characteristics include data from a previous patient.

[0210] (6) The system of embodiment 5, wherein the data from the previous patient includes at least one of a Carto 3D model, ME position, and VEC. (7) The system of embodiment 5, wherein the processor further converts the Carto 3D model and the ME position to UCS. (8) The system of embodiment 1, wherein the learning system is trained using at least one of a classification, regression, and clustering algorithm. (9) The system of embodiment 1, wherein the processor is further configured to convert ME positions within the UCS to predicted electrode positions. (10) The system of embodiment 1, wherein the processor is further configured to provide an ME position in UCS based on the training and the VEC of the electrode.

[0211] (11) A method for generating an arrhythmia prediction model, comprising: receiving a plurality of historical CPM matrices, patient characteristics, and corresponding catheter positions; training a learning system based on a first set of historical CPM matrices, patient characteristics, and corresponding catheter positions, wherein the learning system is trained such that combinations of attributes from the historical CPM matrices and the patient characteristics correlate with the first set of corresponding catheter positions; updating the learning system based on a second set of historical CPM matrices, patient characteristics, and corresponding catheter positions, wherein the combination of attributes from the historical CPM matrices and the patient characteristics correlates with the second set of corresponding catheter positions; generating a model based on the first set of corresponding catheter positions and the second set of corresponding catheter positions. (12) The method of embodiment 11, wherein the second set of corresponding catheter positions is improved based on the first set of corresponding arrhythmia sites. (13) The method of embodiment 11, wherein the received multiple historical CPM matrices are based on the known corresponding catheter positions. (14) receiving a subset of patient characteristics having known catheter locations; 12. The method of claim 11, further comprising generating a new CPM matrix based also on a subset of patient characteristics having the known catheter positions. (15) The method of embodiment 11, wherein the patient characteristics are selected from one or more of electrical signals, catheter position, catheter orientation, and cardiac anatomical structure.

[0212] (16) The method of embodiment 15, wherein the patient characteristics include data from a previous patient. (17) The method described in embodiment 16, wherein the data from the previous patient includes at least one of a Carto 3D model, ME position, and VEC. (18) The method of embodiment 17, further comprising converting the Carto 3D model and the ME position to UCS. (19) The method of embodiment 11, wherein the learning system is trained using at least one of a classification, regression, and clustering algorithm. (20) Converting ME locations in UCS to predicted electrode locations; 12. The method of claim 11, further comprising providing an ME position in UCS based on the training and the VEC of the electrode.

Claims

1. 1. A system for automatically generating a CPM matrix, comprising: a plurality of body surface electrodes configured to sense electrical signals; A processor comprising a neural network, receiving a plurality of historical CPM matrices, patient characteristics including electrical signals transmitted by catheter electrodes and received at the body surface electrodes on the surface of the patient's body, or electrical signals transmitted by the body surface electrodes on the surface of the patient's body and received at the catheter electrodes, and corresponding catheter positions; training a learning system based on the plurality of historical CPM matrices, the patient characteristics, and the corresponding catheter positions; generating a model based on the learning system; receiving patient characteristics from the plurality of body surface electrodes or the catheter electrodes; a processor configured to use the model to generate a new CPM matrix based on the received patient characteristics.

2. The system of claim 1 , wherein the received historical CPM matrices are based on known corresponding catheter positions.

3. The processor: receiving a subset of patient characteristics corresponding to known catheter locations; The system of claim 1 , further configured to generate a new CPM matrix based also on the subset of patient characteristics.

4. The system of claim 1 , wherein the patient characteristics further comprise cardiac anatomy.

5. The system of claim 4 , wherein the patient characteristics include data from previous patients.

6. The system of claim 5 , wherein the data from the previous patient includes at least one of a 3D model of cardiac tissue, ME location, and VEC.

7. The system of claim 6 , wherein the processor further converts the 3D model and the ME position to UCS.

8. The system of claim 1 , wherein the learning system is trained using at least one of a classification, regression, and clustering algorithm.

9. The system of claim 1 , wherein the processor is further configured to convert ME locations within the UCS to predicted electrode locations.

10. The system of claim 1 , wherein the processor is further configured to provide an ME location in UCS based on the training and a VEC of the catheter electrode.

11. 1. A method of operating a system for generating a model capable of predicting catheter electrode position, comprising: The processor: receiving a plurality of historical CPM matrices, patient characteristics including electrical signals transmitted by catheter electrodes and received at body surface electrodes on the surface of the patient's body, or electrical signals transmitted by said body surface electrodes on the surface of the patient's body and received by catheter electrodes, and corresponding catheter positions; training a learning system based on a first set of a plurality of historical CPM matrices, patient characteristics, and corresponding catheter positions, wherein the learning system is trained such that combinations of attributes from the historical CPM matrices and the patient characteristics correlate with the first set of corresponding catheter positions; updating the learning system based on a second set of a plurality of historical CPM matrices, patient characteristics, and corresponding catheter positions, wherein the combination of attributes from the historical CPM matrices and the patient characteristics correlates with the second set of corresponding catheter positions; generating a model based on the first set of corresponding catheter positions and the second set of corresponding catheter positions.

12. 12. The method of claim 11, wherein the second set of corresponding catheter locations is refined based on the first set of corresponding arrhythmia locations.

13. The method of claim 11 , wherein the received historical CPM matrices are based on known corresponding catheter positions.

14. the processor: receiving a subset of patient characteristics corresponding to known catheter locations; 12. The method of claim 11, further comprising generating a new CPM matrix based also on the subset of patient characteristics.

15. The method of claim 11 , wherein the patient characteristics further comprise cardiac anatomy.

16. 16. The method of claim 15, wherein the patient characteristics include data from a previous patient.

17. 17. The method of claim 16, wherein the data from the previous patient includes at least one of a 3D model of cardiac tissue, ME location, and VEC.

18. The method of claim 17 further comprising converting the 3D model and the ME position to UCS.

19. The method of claim 11 , wherein the learning system is trained using at least one of a classification, regression, and clustering algorithm.

20. the processor: Transforming ME locations in UCS to predicted electrode locations; 12. The method of claim 11, further comprising: providing an ME location in UCS based on the training and the VEC of the catheter electrode.

Images