Automated tracking of catheter on mapping system display

Abstract

One example includes a medical system with a catheter having a distal portion, a catheter interface unit configured to track the location of the distal portion within an anatomy, an electronic display, and a computing device coupled to both the catheter interface unit and the electronic display. The computing device includes an electronic processor configured to receive a procedure to be performed by a physician using the system, identify an anatomical map, and present it on the electronic display based on a first view. The electronic processor receives the position of the distal portion of the catheter from the catheter interface unit, determines a second view for the anatomical map with a machine learning model based on the anatomical map, the position of the distal portion of the catheter, and the procedure, and controls the display to update the anatomical map from the first view to the second view.

Description

AUTOMATED TRACKING OF CATHETER ON MAPPING SYSTEM DISPLAY

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 709,699, filed October 21, 2024, the entire content of which is incorporated herein by reference.BACKGROUND

[0002] Cardiac arrhythmias disrupt normal heart rhythm and cardiac efficiency.Arrythmias may be caused by, among other things, atrial fibrillation (AFib, or AF) and ventricular tachycardia (VT). These arrhythmias can be treated using multi-electrode catheters that are configured to ablate cardiac tissue via, for example, pulsed field ablation (PF A) or radiofrequency (RF) ablation).SUMMARY

[0003] This disclosure relates to automated tracking of an ablation catheter. In order to enable proper maneuvering of the catheter through the heart during a cardiac ablation procedure, the heart is mapped using electromagnetic sensors on the catheter. Mapping is performed with a catheter interface unit. During cardiac ablation procedures, a physician relies on a human mapper to continuously adjust a visual display of the map to visualize the position of the catheter on a three-dimensional rendering of the anatomy. The mapper may choose between multiple preset views or can present a custom view by rotating the model. This technique requires continuous manual adjustment of the display by the mapper throughout the procedure.

[0004] This manual process can be inefficient and inconsistent. Positioning the map during a procedure is not a trivial process. The human heart has a complex geometry. In addition, catheters have increasingly robust capabilities, resulting in complex electrode structures, including structures that allow different sections of the electrode to move independently. Human mappers have varied skill sets, and not all may be able to map all types of catheters. This may necessitate travel of those mappers that have the required skill sets, increasing the cost and reducing overall availability of mappers. Inconsistency in mapper skill sets can therefore lead to inefficiencies. In addition, techniques and preferences vary between physicians. Where a mapper is available, that mapper may not be able to assist a particular physician in their preferred technique. These limitations, inturn, limit the quantity of procedures that can be performed overall, resulting in inefficient use of equipment and physicians.

[0005] To overcome this challenge, some existing systems can utilize an auto rotate feature, which continuously places the map with the catheter position facing forward (e.g., toward the screen). However, the front facing view may be suboptimal for some tasks. As noted, given the complex geometries of the heart and the catheters, an alternate view may facilitate applying treatment or navigating the catheter into and out of a difficult position. In addition, the physician’s particular technique may be improved by an alternate view position during a procedure. As a consequence, the present automation is insufficient and still requires a highly trained human mapper to attend some procedures for some physicians.

[0006] Accordingly, there is an unmet need to provide systems and methods that can navigate to complex geometries in the heart, in particular, while using catheters with complex electrode structures. Because of these complexities, existing deterministic auto rotation methods are insufficient.

[0007] To address these problems, the present disclosure provides example catheter interface units that use machine learning models to automatically adjust the map view to optimize visualization of the catheter. The machine learning model allows the catheter interface unit to automatically and smoothly rotate the heart map orientation during catheter manipulation, such that an advantageous view of the catheter is presented based on, among other things, physician preference, the type of procedure being performed, and the anatomy under treatment. The embodiments presented herein improve the technology of cardiac ablation systems to provide physicians with enhanced visualizations of heart maps during procedures. Such embodiments reduce the need for manual intervention in the mapping process, thus improving efficiency and accuracy. In addition, more consistent mapping functions may lead to an overall increase in the efficacy and safety of procedures.

[0008] In some aspects, the techniques described herein relate to a medical system including: a catheter system including a catheter, the catheter including a distal portion; a catheter interface unit configured to track a location of the distal portion of the catheter within an anatomy; an electronic display; and an electronic computing device, coupled to the catheter interface unit and the electronic display; wherein the electronic computingdevice includes an electronic processor configured to: receive a procedure to be performed by a physician using the medical system; identify an anatomical map; present the anatomical map on the electronic display based on a first view; receive, from the catheter interface unit, a position of the distal portion of the catheter; determine a second view for the anatomical map with a machine learning model based on the anatomical map, the position of the distal portion of the catheter, and the procedure; and control the electronic display to update the anatomical map from the first view to the second view.

[0009] In some aspects, the techniques described herein relate to a method for automatically rotating an anatomical map during a catheter procedure, the method including: retrieving a procedure to be performed by a physician using a catheter having an electrode structure for delivering ablation energy; generating, with a catheter interface unit configured to track a location of a the electrode structure within an anatomy, an anatomical map; presenting the anatomical map on an electronic display based on a first view; receiving, from the catheter interface unit, a position of the electrode structure; determining, with a machine learning model, a second view for the anatomical map based on the anatomical map, the position of the electrode structure, a configuration for the electrode structure, and the procedure; and controlling the electronic display to rotate the anatomical map from the first view to the second view.

[0010] Example embodiments are herein described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to example embodiments. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a special purpose and unique machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The methods and processes set forth herein need not, in some embodiments, be performed in the exact sequence as shown and likewise various blocks may be performed in parallel rather than in sequence.Accordingly, the elements of methods and processes are referred to herein as “blocks” rather than “steps.”

[0011] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0012] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus that may be on or off-premises, or may be accessed via the cloud in any of a software as a service (SaaS), platform as a service (PaaS), or infrastructure as a service (laaS) architecture so as to cause a series of operational blocks to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide blocks for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. It is contemplated that any part of any aspect or embodiment discussed in this specification can be implemented or combined with any part of any other aspect or embodiment discussed in this specification.

[0013] Further advantages and features consistent with this disclosure will be set forth in the following detailed description, with reference to the figures.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying figures, where like reference numerals refer to identical or functionally similar elements throughout the separate views, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate embodiments, examples, aspects, and features of concepts that include the claimed subject matter and explain various principles and advantages of those implementations, embodiments, examples, aspects, and features.

[0015] FIG. 1 illustrates a system for performing cardiac ablation procedures according to some examples.

[0016] FIG. 2 schematically illustrates an electronic computing device of the system of FIG. 1, according to some examples.

[0017] FIG. 3 illustrates a catheter of the system of FIG. 1, according to some examples.

[0018] FIG. 4A & FIG. 4B illustrate cardiac maps produced by a catheter interface unit included in the system of FIG. 1, according to some examples.

[0019] FIG. 5 is an illustrative example of a cardiac map showing a position of a catheter relative to a cardiac anatomy, produced by a catheter interface unit included in the system of FIG. 1.

[0020] FIG. 6 is an illustrative example of a cardiac map showing a position of a catheter relative to a cardiac anatomy, produced by a catheter interface unit included in the system of FIG. 1.

[0021] FIG. 7 is an illustrative example of a flowchart of a method for automatically presenting a view of a cardiac map using the system of FIG. 1.

[0022] Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help to improve understanding of examples, aspects, and features illustrated.

[0023] For ease of description, some or all of the example systems presented herein are illustrated with a single exemplar of each of its component parts. Some examples may not describe or illustrate all components of the systems. Other example implementations may include more or fewer of each of the illustrated components, may combine some components, or may include additional or alternative components.

[0024] In some instances, the apparatus and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the of various embodiments, examples, aspects, and features so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.DETAILED DESCRIPTION

[0025] FIG. 1 provides an example implementation of a system 100 for performing cardiac ablation procedures. The system includes an ablation system 102, a mapping and navigation console 104, and an electronic computing device 106. The ablation system 102 includes a radiofrequency (RF) generator 108, a pulsed frequency (PF) generator 110, and a catheter interface unit 112. Other embodiments of the ablation system 102 include only one of the RF generator 108 and / or the PF generator 110 (e.g., such that catheter 114 is only configured to provide RF ablation or PF ablation).

[0026] The ablation system 102 further includes a catheter 114. The catheter 114 is a highly flexible treatment device that is suitable for passage through the vasculature. The catheter 114 is adapted for use with the RF generator 108 and / or the PF generator 110 to ablate tissue. In the example illustrated, the catheter 114 has an elongate body 116 having a proximal portion 118 and a distal portion 120. In the illustrated example, the catheter 114 is a lattice catheter. The distal portion 120 includes a treatment element 124. The proximal portion 118 of the catheter 114 is mated to a handle 122 that can include elements such as levers or knobs for manipulating the elongate body 116 and the treatment element 124.

[0027] The elongate body 116 is sized and configured to be passable through a patient’s vasculature and / or positionable proximate to the area of target tissue, and may include one or more lumens (for example, the lumen 128) disposed within the elongate body 116 that provide mechanical, electrical, and / or fluid communication between the proximal portion 118 of the elongate body 116 and the distal portion 120 of the elongate body 116. In some aspects, the elongate body 116 includes a guidewire lumen through which a guidewire or other system component may be located and extended from the distal portion 20 of the catheter 114. The elongate body 116 is configured to facilitate the navigation of the catheter 114 within a patient’s body. In one aspect, the distal portion 120 of the elongate body 116 is flexible and deflectable to allow for more desirable positioning proximate to an area of target tissue (e.g., positioning within the pulmonary veins, the ventricles, the Cavo tricuspid isthmus, and the like). To access an area of target tissue, the catheter 114 may be inserted through one or more blood vessels, such as, for example, one or more femoral veins, or other points of access including arterial access.

[0028] In the illustrated example, the treatment element 124, is an expandable conductive lattice electrode (e.g., comprised of nitinol). During an ablation procedure, the catheter 114 is inserted into a sheath in a collapsed form. Once present in the heart, the lattice can be expanded to a spherical form. In some instances, the lattice can be variably expanded or may be partially flattened to form a disc-like form. The lattice electrode may be energized by either the RF generator 108 (e.g., to deliver radiofrequency ablation (RFA) therapy) or the PF generator 110 (e.g., to deliver pulsed field ablation (PF A) therapy). In some instances, the lattice is a single electrode. In other instances, the lattice is comprised of multiple electrodes (e.g., where the catheter includes numerous treatment elements 124 (not depicted) configured to work together to ablate tissue, such as bipolar PFA between adjacent treatment elements 124 at the distal portion).

[0029] As illustrated, in some instances, the distal portion 120 also includes a central irrigation tip 126, which includes a plurality of irrigation micropores. During a procedure, an irrigation pump 127 may deliver sterile saline or other irrigants through the central irrigation tip 126 during mapping, RFA delivery, and PFA delivery.

[0030] The catheter interface unit 112 performs electroanatomical mapping of the heart during a procedure. As described more particularly with respect to FIG. 3, the distal portion 120 includes location sensors, which are used by the mapping and tracking system 112 to track the catheter’s location and build a three-dimensional map of the heart. The catheter interface unit 112 is coupled to the mapping and navigation console 104. In one example, the mapping and navigation console 104 is a computer including input devices (e.g., a keypad, a keyboard, a mouse, a touchscreen, and the like) and output devices, including a display 130. The display 130 is a suitable display for presenting cardiac maps, as described herein. In some instances, the mapping and navigation console 104 is configured to present the cardiac map on the display 130 and a display 132, which is positioned in the operating environment for use by the physician performing the procedure. Display 130 and display 132 may be similar / identical, such that including both is for purposes of illustration (e.g., demonstrating the ability of aspects of this disclosure to provide the discussed graphical output at numerous devices at numerous locations, such as both within and outside of the sterile operating field).

[0031] The electronic computing device, described more particularly with respect to FIG. 2, is coupled to the catheter system 102, the mapping and navigation console 104, and a database 134. In the illustrated example, these components are communicatively coupled by a communication network 136. The communication network 136 may include, for example, one or more cables, a local area network, a wide area network, a wireless network, such as Wi-Fi™ or Bluetooth™, or combinations of the foregoing. For example, in one implementation, the electronic computing device 106 may communicate with the database 134 via the Internet, and the ablation system 102 via one or more cables. As described herein, in some examples, the electronic computing device 106 operates a machine learning model that controls the catheter interface unit 112 to automatically present views of the cardiac map during mapping and treatment delivery.

[0032] In some implementations, the electronic computing device 106 may be configured to send data to and receive data from the database 134, the catheter system 102, and the mapping and navigation console 104 via the communication network 136 using one or more communication interfaces included in the electronic computing device 106. It should be understood that while the system 100 of FIG. 1 is illustrated as including only a single database 134, a single catheter system 102, a single mapping and navigation console 104, and a single electronic computing device 106, the system 100 may instead include multiples of some or all of those components. For example, the system 100 may include multiple databases and the functionality described herein as being performed by the database 134 may be divided among multiple databases. It should also be understood that, while the ablation system 102 and the electronic computing device 106 are illustrated in FIG. 1 as being separate components in the system 100, the components illustrated as being included in the electronic computing device 106 may instead be included in the catheter system 102, the mapping and navigation console 104, or both.

[0033] In one implementation, the database 134 is configured to store patient data associated with one or more patients. Patient data may include, for example, an age associated with a patient, a computed tomography scan associated with a patient, a gender associated with a patient, a medical history associated with a patient, a combination of the foregoing, or the like. In some implementations, patient data is associated with a patient undergoing a surgical procedure wherein the systems and methods described herein are utilized. In some implementations, the patient data may be stored in the database 134 priorto the surgical procedure. In some implementations, the electronic computing device 106 is configured to send, to the database 134, a query requesting patient data associated with an unique patient identifier and receive, from the database 134, patient data associated with the unique patient identifier. In some implementations, the database 134 is configured to store one or more surgical plans (e.g., relating to cardiac ablation procedures). In one example, the database 134 may receive a surgical plan and a unique plan identifier associated with the surgical plan from an electronic computing device (for example, the electronic computing device 106 or another electronic computing device), via the communication network 136. In some implementations, the electronic computing device 106 is configured to send, to the database 134, a query requesting a surgical plan associated with a unique plan identifier and receive, from the database 134, the surgical plan associated with the unique plan identifier. In some implementations, the database 134 may store medical records relating to previously performed cardiac ablation procedures, physician profiles, and other data as described herein.

[0034] FIG. 2 schematically illustrates an electronic computing device of the system of FIG. 1, according to some examples. The electronic computing device 106 includes an electronic processor 135 (for example, a programmable electronic microprocessor, microcontroller, or similar device), a memory 140 (for example, non-transitory, computer or machine readable memory), an input device 145, and an output device 150. The input device 145 may be, for example, a keypad, a keyboard, a mouse, a touchscreen (for example, as part of the output device 150), a microphone, a camera, a Universal Serial Bus (“USB”) port, or the like. The output device 150 may be, for example, a speaker, a touchscreen, a liquid crystal display (“LCD”), a light-emitting diode (“LED”) display, an organic LED (“OLED”) display, an electroluminescent display (“ELD”), or the like. It should be understood that, while the electronic computing device 106 is illustrated as including a single input device 145 and a single output device 150, the electronic computing device 106 may include multiple input devices and multiple output devices. The electronic processor 135 is communicatively connected to the memory 140, the input device 145, and the output device 150. In some implementations, the electronic processor 135, in coordination with the memory 140, is configured to implement, among other things, the methods described herein. In some implementations, the memory includes a machine learning model 155.

[0035] Machine learning generally refers to the ability of a computer to learn to perform a task without being explicitly programmed to do so. In some embodiments, a computer program (e.g., a machine learning engine) is configured to construct an algorithm based on inputs. Supervised learning involves presenting a computer program with example inputs and their desired outputs. The computer program is configured to learn a general rule that maps the inputs to the outputs from the training data it receives. Example machine learning engines include decision tree learning, association rule learning, artificial neural networks, classifiers, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and genetic algorithms. Using all of these approaches, a computer program can ingest, parse, and understand data and progressively refine algorithms for data analytics.

[0036] The machine learning model 155 is used, as described herein, to generate views used in automatically updating (e.g., rotating, flipping, zooming in, zooming out, including more anatomical information, including less anatomical information, including more annotation, including less annotation) an anatomical map during a catheter procedure. For example, the machine learning model 155 may take as inputs the current position of a catheter within an anatomy, information on a procedure being performed on the anatomy, and a three-dimensional map of the anatomy. Given these inputs, the machine learning model 155 may predict one or more views of the three-dimensional map, which would be helpful to a physician performing the procedure. In some instances, the machine learning model 155 may select one of the views and present it on an electronic display in an operating theater, as described herein.

[0037] In some examples, the machine learning model 155 is trained using training data consisting of recorded procedures performed using a human mapper or single physician. The recorded procedures may include video captures and data logs from the equipment (e.g., sensor readings, control inputs, physician feedback, and the like). Other training data may include the type of procedure being performed, an elapsed time of the procedure (including an elapsed time of particular steps within the procedure, such as the time of a particular navigation step, or the time of an ablation step, or the like), whether or not an elapsed time deviates from a regular time (e.g., where a physician is struggling to complete a step, such that an updated view with new / different / less / more information isprovided), the type of catheter being used in the procedure, patient history data, treatment outcomes, the anatomical and electrical maps created during the procedure, and the like. The training data would be selected to represent a sufficient variety of procedure types, patient types, and physicians. In this way, the machine learning model 155 may learn how certain views of certain magnifications, orientations, and / or with / without certain information that is presented at different times of the procedure may reduce the time and / or increase the efficacy of the ablation procedure in different circumstances, and therein learn to dynamically provide and update the view in real-time during a procedure in response to real-time updates from the system 100 (e.g., updates including information on the catheter position, timing of the procedure, the patient data, physician data, etc.).

[0038] In some examples, the machine learning model 155 is a deep learning model (e.g., a convolutional neural network (CNN), a recurrent neural network (RNN), or a deep reinforcement network). In some instances, initial training of the model is performed using unsupervised learning. In one example, the training would include preprocessing the recordings (e.g., segmenting the videos into frames and extracting features from each frame). In some instances, feature extraction would use techniques such as clustering (e.g., using K-means or hierarchical clustering algorithms) to identify patterns and similarities in the data without needing labels to learn the inherent structure of the training data. In some instances, dimensionality reduction (e.g., Principal Component Analysis (PCA) or t-Distributed Stochastic Neighbor Embedding (t-SNE)) to reduce the dimensionality of the training data to identify the most important features that contribute to the patterns in the data. The clustered and dimensionality-reduced data is analyzed to identify common patterns to the mapping operations. This analysis may reveal that certain clusters correspond to specific phases of the medical procedure where a particular view of the anatomical map should be presented. The identified patterns may be used to train the model. In some instances, the clusters and patterns can serve as pseudo-labels for supervised learning. In some instances, labeled data (e.g., procedures where physicians identify preferable views during a procedure) can be used to fine-tune the model.

[0039] FIG. 3 A illustrates an example catheter of the system of FIG. 1. In particular, FIG. 3A illustrates the distal portion 120. As illustrated in FIG. 3, the treatment element 124 includes a plurality of sensors 302. In some examples, the sensors 302 are temperature sensors that function as electrodes for sensing temperature and / or voltage. In the illustratedexample, nine sensors 302 are distributed substantially uniformly on the surface of the lattice. The distribution of the sensors 302 allows for a six degree of freedom location determination, which enables the catheter interface unit 112 to track the treatment element 124.

[0040] Another example catheter, as shown in FIG. 3B, is an example medical device 320 with an electrode structure 324 with a plurality of moveable sections.The medical device 320 may include numerous arms 326 each with a plurality of electrodes 328. The electrode structure 324 may be moved in numerous ways, such as from a compressed configuration where the arms 326 are parallel with a central shaft 330 to an expanded basket configuration where the arms 326 are deployed out from this central shaft 330. In some examples, electrodes of the electrode structure 324 may be configured to ablate between each other via bipolar PFA techniques as indicated by the bidirectional arrows.

[0041] FIGS. 4A & 4B illustrate cardiac maps produced the catheter interface unit 112. FIG. 4A includes a cardiac map 402, which indicates measured voltages using different colors. FIG. 4B includes a cardiac map 404, which also includes a plurality of discs 406, which indicate positions where the catheter applied ablation therapy (e.g., using RFA or PFA).

[0042] FIG. 5 illustrates example cardiac maps 502, 504, of the type displayed by the mapping and navigation console 104 during an ablation procedure. Each cardiac map 502, 504 includes a representation of the catheter, in particular, the treatment element 124. Cardiac map 502 is displayed using the Left Lateral view option. Cardiac map 504 is displayed using the Left Anterior Oblique view option. In both cardiac maps 504 and 506, the treatment element 124 is well visualized.

[0043] FIG. 6 illustrates example cardiac maps 602, 604, of the type displayed by the mapping and navigation console 104 during an ablation procedure. Cardiac map 602 is displayed using the Right Anterior Oblique view option. Cardiac map 604 is displayed using the Left Anterior Oblique view option. As illustrated in FIGS. 5 and 6, other view options include the Posterior-Anterior, Anterior-Posterior, Right Lateral, Superior, Inferior, Right Posterior Oblique, and Left Posterior Oblique views. Cardiac map 604 shows the treatment element 124 well visualized. In Cardiac map 602, the treatmentelement 124 is not well visualized. Despite this, the view is preferred by the physician because it provides a better understanding of the map shape. This is an example of where current automated rotation technique, which always places the treatment element 124 toward the front, would not be desirable or efficient.

[0044] FIG. 7 is an illustrative example of a flowchart of a method for automatically presenting a view of a cardiac map using the system of FIG. 1.

[0045] As an example, the method 700 is described as being at least partially performed by the electronic computing device 106 and, in particular, the electronic processor 135. However, it should be understood that in some embodiments, portions of the method 700 may be performed by other devices, including for example, the catheter interface unit 112 and / or the mapping and navigation console 104. Additional electronic processors may also be included in the device 106 that perform all or a portion of the method 700.

[0046] At block 702, the electronic processor 135 receives a procedure to be performed by a physician using the medical system. For example, the electronic computing device 106 may retrieve a surgical plan, which contains information on the procedure, from the database 134. In another example, the procedure may be loaded into the system as part of a pre-operative configuration.

[0047] At block 704, the electronic processor 135 identifies, an anatomical map. In some aspects, the anatomical map is generated by the system 100, such as using information received from the catheter 114. For example, as the procedure is performed, the catheter interface unit 112 receives data from sensors on the catheter and uses the data to construct a three-dimensional anatomical map of the anatomy. In one example, the anatomical map is a cardiac map, as described herein. In some examples, the catheter interface unit 112 provides this map to electronic computing device 106 as the map is produced. In some instances, the map data is continuously updated (e.g., streaming data). In some instances, a series of maps is created and sent to the electronic computing device 106 by the catheter interface unit 112. In some embodiments, the catheter interface unit 112 may be adding geometry to the map while utilizing the method 700. For example, there may be no map, upon which to initially base rotation. In some embodiments, once a specific volume of anatomy has been generated, the mapping feature will automatically turn on. In certain embodiments, the anatomical map is generated by another system (e.g.,a system external to system 100), and is then received by system 100 for use as discussed herein.

[0048] At block 706, the electronic processor 135 presents the anatomical map on the electronic display (e.g., the electronic display 130, the electronic display 132, or both) based on a first view. As illustrated in FIG. 7, the method 700 operates iteratively throughout the surgical procedure to rotate the anatomical map during both mapping and therapy delivery. Accordingly, as the method operates, the term “first view” may refer to an initial view of the anatomical map presented at the start of the procedure, or it may refer to the view of the anatomical map currently presented on the electronic display.

[0049] At block 708, the electronic processor 135 receives from the catheter interface unit 112, a position of the distal portion 120 of the catheter 114. The catheter interface unit 112 tracks the location of the catheter 114 (e.g., using electromagnetic sensors) as it moves through the anatomy being mapped (e.g., a heart). In some instances, the catheter interface unit 112 provides location data to the electronic computing device 106 continuously. In other instances, the catheter interface unit 112 provides location data to the electronic computing device 106 in periodic updates.

[0050] At block 710, the electronic processor 135 determines a second view for the anatomical map with a machine learning model based on the anatomical map, the position of the distal portion of the catheter, and the procedure to be performed. For example, the electronic processor 135 may provide the anatomical map, the position of the distal portion of the catheter, and the procedure as inputs to the machine learning model 155. As described herein, the machine learning model 155 is trained to take such inputs and determine the optimal view for the anatomical map for a given time during the procedure. Catheter configurations may vary. Accordingly, in some instances, the electronic processor 135 also provides data about the catheter’s electrode structure as inputs to the machine learning model 155. Such data may include information about the geometry of the electrode structure (e.g., whether the electrode comprises multiple independently movable sections, whether the electrode structure comprises a single or multiple electrodes, and the like).

[0051] Automated view selection and presentation may be performed during mapping, treatment, or both. Accordingly, in some instances, the electronic processor 135 providesas input to the machine learning model 155 an indication of whether the catheter system is applying ablation energy. Some electrode structures comprise multiple electrodes for applying ablation energy. In such cases, the indication that the catheter system is applying ablation energy identifies which of the plurality of electrodes are being energized. In some instances, the electronic processor 135 may receive an input identifying a target area of the anatomy and provide the input to the machine learning model 155. For example, a physician may indicate using a touch screen, voice command, or other method an area of the anatomy that the physician would like to navigate to or avoid.

[0052] In some instances, the electronic processor 135 receives a physician profile for the physician and determines the second view for the anatomical map with the machine learning model based on the physician profile. For example, the electronic processor 135 may retrieve the physician profile from the database 134. In some instances, the electronic processor 135 may use the physician profile to apply weights to parameters of the machine learning model 155. In another example, the machine learning model 155 may be a physician-specific model derived from a general model by using the physician profile as further training data. In some instances, the electronic processor may generate, with the machine learning model, a plurality of candidate views for the anatomical map using the anatomical map, the position of the catheter, and the procedure and then select a second view from the candidate views using the physician profile to weight or score the candidate views.

[0053] In some instances, the electronic processor 135 may determine the second view based on a threshold satisfied at the first view, despite the physician being at the same step in the procedure. For example, the threshold may be a time threshold, such that the physician has spent at least a threshold amount of time at a given step in the procedure without successfully completing this step in the procedure (e.g., where this threshold amount of time is 2X or 3X an average amount of time spent on that particular step). For another example, the threshold may be an “attempt” threshold, where the physician has attempted (and failed) this step a threshold amount of times without success. These thresholds may be relative to variables of the procedure, where a threshold is “higher” for a more complex or delicate procedure. In some examples, the electronic processor 135 may learn to detect successful completion of a given step in the procedure, whereas inother examples successful completion of a given step may be an input that is actively received from a physician, or a combination of the two.

[0054] At block 712, the electronic processor 135 controls the electronic display to update the anatomical map from the first view to the second view. For example, the electronic processor 135 may gradually update the anatomical map in virtual three-dimensional space until it arrives at the second view. Updating the view may include rotating the first view, increasing magnification (zooming in) from the first view, decreasing magnification (zooming out) from the first view, including additional / less / different anatomical and / or annotation information from the first view, or the like. The speed of the update may be determined by the machine learning model based on similar factors as were used to determine the second view.

[0055] In some instances, the electronic processor 135 may determine with the machine learning model 155 a view change interval. The view change interval represents the time between changing of views. The view change interval may be determined by the machine learning model based on similar factors as were used to determine the second view. In some instances, the electronic processor 135 may continue to generate second views but may not update to a new view until after the view change interval has passed. In other instances, the electronic processor 135 may not generate a new second view until after the view change interval has passed.

[0056] In some instances, the physician may prefer an alternative view to the one selected and displayed according to the method 700. In such instances, the system provides a means for the physician to override the view. For example, a user interface may provide a series of selectors corresponding to a series of views. In another example, the physician may be able to issue voice commands to the system to change the view or revert to the prior view. Regardless of the form of the input, the electronic processor 135, responsive to receiving the input overriding the second view for the anatomical map, will generate and display a third view for the anatomical map. The third view may be specified by the physician as part of the input, or it may be determined automatically by the machine learning model 155 (e.g. by choosing the next view in a ranked list of candidate views or generating a new view entirely). In some instances, where physician feedback is received for a view, the feedback is used to retrain (e.g., refine) the machine learning model 155.

[0057] As should be apparent from this detailed description above, the operations and functions of the electronic computing devices presented herein are sufficiently complex as to require their implementation on a computer system, and cannot be performed, as a practical matter, in the human mind. Electronic computing devices such as set forth herein are understood as requiring and providing speed and accuracy and complexity management that are not obtainable by human mental steps, in addition to the inherently digital nature of such operations (e.g., a human mind cannot interface directly with RAM or other digital storage, cannot transmit or receive electronically encoded video, electronically encoded audio, etc., among other features and functions set forth herein).

[0058] In the foregoing specification, specific embodiments have been described.However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings. The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

[0059] Moreover, in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms “comprises,” “comprising,” “has,” “having,” “includes,” “including,” “contains,” “containing,” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises ...a,” “has ... a,” “includes ... a,” or “contains ... a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. Unless the context of their usageunambiguously indicates otherwise, the articles “a,” “an,” and “the” should not be interpreted as meaning “one” or “only one.” Rather these articles should be interpreted as meaning “at least one” or “one or more.” Likewise, when the terms “the” or “said” are used to refer to a noun previously introduced by the indefinite article “a” or “an,” “the” and “said” mean “at least one” or “one or more” unless the usage unambiguously indicates otherwise.

[0060] It should be understood that although certain figures presented herein illustrate hardware and software located within particular devices, these depictions are for illustrative purposes only. The illustrated components, unless explicitly described to the contrary, may be combined or divided into separate software, firmware, and / or hardware. For example, instead of being located within and performed by a single electronic processor, logic and processing described herein may be distributed among multiple electronic processors. Similarly, one or more memory modules and communication channels or networks may be used even if embodiments described or illustrated herein have a single such device or element. Also, regardless of how they are combined or divided, hardware and software components may be located on the same computing device or may be distributed among multiple different devices. Accordingly, in this description and in the claims, if an apparatus, method, or system is claimed, for example, as including a controller, control unit, electronic processor, computing device, logic element, module, memory module, communication channel or network, or other element configured in a certain manner, for example, to perform multiple functions, the claim or claim element should be interpreted as meaning one or more of such elements where any one of the one or more elements is configured as claimed, for example, to make any one or more of the recited multiple functions, such that the one or more elements, as a set, perform the multiple functions collectively.

[0061] It will be appreciated that some embodiments may be comprised of one or more generic or specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain nonprocessor circuits, some, most, or all of the functions of the method and / or apparatus described herein. Alternatively, some or all functions could be implemented by a statemachine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of approaches could be used.

[0062] Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Any suitable computer-usable or computer readable medium may be utilized. Examples of such computer-readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0063] The terms “substantially,” “essentially,” “approximately,” “about,” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “one of,” without a more limiting modifier such as “only one of,” and when applied herein to two or more subsequently defined options such as “one of A and B” should be construed to mean an existence of any one of the options in the list alone (e.g., A alone or B alone) or any combination of two or more of the options in the list (e.g., A and B together).

[0064] A device or structure that is “configured” in a certain way is configured in at least that way but may also be configured in ways that are not listed.

[0065] The terms “coupled,” “coupling,” or “connected” as used herein can have several different meanings depending on the context in which these terms are used. For example, the terms coupled, coupling, or connected can have a mechanical or electrical connotation. For example, as used herein, the terms coupled, coupling, or connected canindicate that two elements or devices are directly connected to one another or connected to one another through intermediate elements or devices via an electrical element, electrical signal or a mechanical element depending on the particular context.

[0066] The following paragraphs provide various clauses reciting examples and alternatives disclosed herein.

[0067] Example 1. A medical system comprising: a catheter system including a catheter, the catheter including a distal portion; a catheter interface unit configured to track a location of the distal portion of the catheter within an anatomy; an electronic display; and an electronic computing device, coupled to the catheter interface unit and the electronic display; wherein the electronic computing device includes an electronic processor configured to: receive a procedure to be performed by a physician using the medical system; identify an anatomical map; present the anatomical map on the electronic display based on a first view; receive, from the catheter interface unit, a position of the distal portion of the catheter; determine a second view for the anatomical map with a machine learning model based on the anatomical map, the position of the distal portion of the catheter, and the procedure; and control the electronic display to update the anatomical map from the first view to the second view.

[0068] Example 2. The medical system of example 1, wherein: the distal portion of the catheter includes an electrode structure for applying ablation energy; and the electronic processor is further configured to determine the second view for the anatomical map with the machine learning model based on the electrode structure.

[0069] Example 3. The medical system of example 2, wherein the electrode structure comprises a plurality of independently movable sections.

[0070] Example 4. The medical system of any of examples 1 to 3, wherein the electronic processor is further configured to: receive from the catheter system an indication that the catheter system is applying ablation energy; determine the second view for the anatomical map with the machine learning model based on the indication that the catheter system is applying ablation energy.

[0071] Example 5. The medical system of example 4, wherein: the distal portion of the catheter includes a plurality of electrodes for applying ablation energy; and the indicationthat the catheter system is applying ablation energy identifies which of the plurality of electrodes are being energized.

[0072] Example 6. The medical system of any of examples 1 to 5, wherein the electronic processor is further configured to: receive an input identifying a target area of the anatomy; and determine the second view for the anatomical map with the machine learning model based on the input identifying the target area of the anatomy.

[0073] Example 7. The medical system of any of examples 1 to 6, wherein the electronic processor is further configured to: receive a physician profile for the physician; and determine the second view for the anatomical map with the machine learning model based on the physician profile.

[0074] Example 8. The medical system of example 7, wherein the electronic processor is further configured to: generate, with the machine learning model, a plurality of candidate views for the anatomical map using the anatomical map, the position of the catheter, and the procedure; and select, with the machine learning model, one of the plurality of candidate views for the anatomical map as the second view for the anatomical map using the physician profile.

[0075] Example 9. The medical system of any of examples 1 to 8, wherein the electronic processor is further configured to: determine with the machine learning model a view change interval; and control the electronic display to update the anatomical map from the first view to the second view based on the view change interval.

[0076] Example 10. The medical system of any of examples 1 to 9, wherein the electronic processor is further configured to: receiving an input overriding the second view for the anatomical map; responsive to receiving the input overriding the second view for the anatomical map, generate a third view for the anatomical map; control the electronic display to rotate the anatomical map from the second view to the third view; and retrain the machine learning model based on the input overriding the second view for the anatomical map.

[0077] Example 11. The medical system of any of examples 1 to 10, wherein the electronic processor is further configured to: generate the anatomical map.

[0078] Example 12. The medical system of example 11, wherein the anatomical map is generated using information received from the catheter.

[0079] Example 13. A method for automatically rotating an anatomical map during a catheter procedure, the method comprising: retrieving a procedure to be performed by a physician using a catheter having an electrode structure for delivering ablation energy; identifying an anatomical map; presenting the anatomical map on an electronic display based on a first view; receiving, from the catheter interface unit, a position of the electrode structure; determining, with a machine learning model, a second view for the anatomical map based on the anatomical map, the position of the electrode structure, a configuration for the electrode structure, and the procedure; and controlling the electronic display to update the anatomical map from the first view to the second view.

[0080] Example 14. The method of example 13, wherein the electrode structure comprises a plurality of independently movable sections.

[0081] Example 15. The method of any of examples 13 and 14, wherein determining the second view for the anatomical map includes determining the second view for the anatomical map based on an indication that the electrode structure is applying ablation energy.

[0082] Example 16. The method of example 15, wherein: the electrode structure includes a plurality of electrodes for applying ablation energy; and the indication that the electrode structure is applying ablation energy identifies which of the plurality of electrodes are being energized.

[0083] Example 17. The method of any of examples 13 to 16, further comprising: retrieving a physician profile for the physician; and determining the second view for the anatomical map with the machine learning model based on the physician profile.

[0084] Example 18. The method of any of examples 13 to 17, further comprising: determining, with the machine learning model, a view change interval; and controlling the electronic display to rotate the anatomical map from the first view to the second view based on the view change interval.

[0085] Example 19. The method of any of examples 13 to 18, further comprising: receiving an input overriding the second view for the anatomical map; responsive toreceiving the input overriding the second view for the anatomical map, generating a third view for the anatomical map; controlling the electronic display to update the anatomical map from the second view to the third view; and retraining the machine learning model based on the input overriding the second view for the anatomical map.

[0086] Example 20. The method of any of examples 1 to 10, further comprising: generating the anatomical map.

[0087] Example 21. The method of example 20, wherein the anatomical map is generated using information received from the catheter.

[0088] Various features and advantages of the embodiments presented herein are set forth in the following claims.

Claims

CLAIMSWhat is claimed is:

1. A medical system (100) comprising:a catheter (114) system (100) including a catheter (114), the catheter (114) including a distal portion (120);a catheter (114) interface unit (112) configured to track a location of the distal portion (120) of the catheter (114) within an anatomy;an electronic display (132) (130); andan electronic computing device (106), coupled to the catheter (114) interface unit (112) and the electronic display (132) (130);wherein the electronic computing device (106) includes an electronic processor (135) configured to:receive a procedure to be performed by a physician using the medical system (100);identify an anatomical map;present the anatomical map on the electronic display (132) (130) based on a first view;receive, from the catheter (114) interface unit (112), a position of the distal portion (120) of the catheter (114);determine a second view for the anatomical map with a machine learning model (155) based on the anatomical map, the position of the distal portion (120) of the catheter (114), and the procedure; andcontrol the electronic display (132) (130) to update the anatomical map from the first view to the second view.

2. The medical system (100) of claim 1, wherein:the distal portion (120) of the catheter (114) includes an electrode structure (324) for applying ablation energy; andthe electronic processor (135) is further configured to determine the second view for the anatomical map with the machine learning model (155) based on the electrode structure (324).

3. The medical system (100) of claim 2, wherein the electrode structure (324) comprises a plurality of independently movable sections.

4. The medical system (100) of any of claims 1 to 3, wherein the electronic processor (135) is further configured to:receive from the catheter (114) system (100) an indication that the catheter (114) system (100) is applying ablation energy;determine the second view for the anatomical map with the machine learning model (155) based on the indication that the catheter (114) system (100) is applying ablation energy.

5. The medical system (100) of claim 4, wherein:the distal portion (120) of the catheter (114) includes a plurality of electrodes (328) for applying ablation energy; andthe indication that the catheter (114) system (100) is applying ablation energy identifies which of the plurality of electrodes (328) are being energized.

6. The medical system (100) of any of claims 1 to 5, wherein the electronic processor (135) is further configured to:receive an input identifying a target area of the anatomy; anddetermine the second view for the anatomical map with the machine learning model (155) based on the input identifying the target area of the anatomy.

7. The medical system (100) of any of claims 1 to 6, wherein the electronic processor (135) is further configured to:receive a physician profile for the physician; anddetermine the second view for the anatomical map with the machine learning model (155) based on the physician profile.

8. The medical system (100) of claim 7, wherein the electronic processor (135) is further configured to:generate, with the machine learning model (155), a plurality of candidate views for the anatomical map using the anatomical map, the position of the catheter (114), and the procedure; andselect, with the machine learning model (155), one of the plurality of candidate views for the anatomical map as the second view for the anatomical map using the physician profile.

9. The medical system (100) of any of claims 1 to 8, wherein the electronic processor (135) is further configured to:determine with the machine learning model (155) a view change interval; and control the electronic display (132) (130) to update the anatomical map from the first view to the second view based on the view change interval.

10. The medical system (100) of any of claims 1 to 9, wherein the electronic processor (135) is further configured to:receiving an input overriding the second view for the anatomical map; responsive to receiving the input overriding the second view for the anatomical map, generate a third view for the anatomical map;control the electronic display (132) (130) to rotate the anatomical map from the second view to the third view; andretrain the machine learning model (155) based on the input overriding the second view for the anatomical map.

11. The medical system (100) of any of claims 1 to 10, wherein the electronic processor (135) is further configured to:generate the anatomical map.

12. The medical system (100) of claim 11, wherein the anatomical map is generated using information received from the catheter (114).

13. A method (700) for automatically rotating an anatomical map during a catheter (114) procedure, the method (700) comprising:retrieving a procedure to be performed by a physician using a catheter (114) having an electrode structure (324) for delivering ablation energy;identifying an anatomical map;presenting the anatomical map on an electronic display (132) (130) based on a first view;receiving, from the catheter (114) interface unit (112), a position of the electrode structure (324);determining, with a machine learning model (155), a second view for the anatomical map based on the anatomical map, the position of the electrode structure (324), a configuration for the electrode structure (324), and the procedure; andcontrolling the electronic display (132) (130) to update the anatomical map from the first view to the second view.

14. The method (700) of claim 13, further comprising:retrieving a physician profile for the physician; anddetermining the second view for the anatomical map with the machine learning model (155) based on the physician profile.

15. The method (700) of any of claims 13 and 14, further comprising:receiving an input overriding the second view for the anatomical map; responsive to receiving the input overriding the second view for the anatomical map, generating a third view for the anatomical map;controlling the electronic display (132) (130) to update the anatomical map from the second view to the third view; andretraining the machine learning model (155) based on the input overriding the second view for the anatomical map.

Images