Ablation visualization system

Abstract

Example systems and techniques are disclosed that may determine at least one treatment strategy for a lesion. An example system may include memory configured to store a plurality of treatment pathways and processing circuitry communicatively coupled to the memory. The processing circuitry may be configured to determine the plurality of treatment pathways. The processing circuitry may be configured to determine, for each respective treatment pathway of the plurality of treatment pathways, one or more respective predicted effectiveness indicators, one or more respective predicted risks, and a respective confidence level associated with at least one of the respective predictions. The processing circuitry may be configured to output for display the plurality of treatment pathways, and the one or more respective predicted effectiveness indicators, the one or more respective predicted risks, and the respective confidence level associated with at least one of the respective predictions for each respective treatment pathway.

Description

ABLATION VISUALIZATION SYSTEM

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 619,904, filed January 11, 2024, the entire content of which is incorporated herein by reference.TECHNICAL FIELD

[0002] This disclosure relates to a system for use with medical ablation procedures.BACKGROUND

[0003] During a medical procedure, a clinician may use one or more imaging systems to visualize internal anatomy of a patient. Such imaging systems may display anatomy, medical instruments, or the like, and may be used to diagnose a patient condition or assist in guiding a clinician in moving a device, such as a medical instrument to an intended location inside the patient. Imaging systems may use sensors to capture video images or still images which may be displayed during the medical procedure. Imaging systems include fluoroscopy systems, angiography systems, ultrasound imaging systems, computed tomography (CT) scan systems, magnetic resonance imaging (MRI) systems, isocentric C-arm fluoroscopic systems, positron emission tomography (PET) systems, intravascular ultrasound (IVUS), optical coherence tomography (OCT), near infrared spectroscopy (NIRS), as well as other imaging systems.

[0004] An ablation procedure is a medical procedure where tissue is ablated in a patient. For example, in a renal denervation (RDN) procedure, nerves within or about the wall of a renal artery are ablated through the use of radiofrequency pulses, ultrasound energy, or the like, to treat drug resistant hypertension.SUMMARY

[0005] In general, this disclosure is directed to various techniques and medical systems for using images captured during (and / or prior to) an ablation procedure, such as an RDN procedure, to facilitate clinician decision making through enhanced imaging and, in some examples, provide clinical guidance for a clinician for use during such a medical procedure. The techniques and systems may also capture information relating to the procedure and prepare medical procedure report(s) based on such information.

[0006] A renal denervation procedure is generally considered to be slower and last longer than desirable. For example, procedure time may be extended by over-ablating locations to ensure ablation coverage is adequate. There may be a sub-optimal spread and uncoordinated positioning of delivery elements, such as electrodes, during an ablation procedure. As such, it may be desirable to provide a system and techniques to decrease the time it takes to perform an ablation procedure, while maintaining or increasing the efficacy of the procedure.

[0007] Currently, frustrations may occur during an ablation procedure without a form of visualized ablation tracking. For example, the anatomy of the patient may move with movement of the patient during the ablation procedure. This may lead to the clinician not knowing where, in the displayed image data, the clinician already performed ablation and / or how far, it at all, the ablation device has moved since performing the previous ablation at a previous ablation location. Such a situation may lead to the clinician desiring to view a cine file taken during the delivery of the previous ablation, which may add to the length of the procedure. Additionally, or alternatively, this situation may lead to the clinician conducting further, and potentially unnecessary ablation, to be sure the location to be ablated has been ablated, and / or the clinician being doubtful about whether the procedure was performed optimally.

[0008] According to the techniques of this disclosure, a system may provide computerized tracking and analysis. Such a system may include machine learning and / or artificial intelligence analysis for procedure optimization. As used herein, a term “machine learning model” may include a machine learning model or an artificial intelligence model. The system may support clinicians before, during, and / or after ablation procedures. The system may recommend ablation locations, and track ablation locations as ablations are completed. In some examples, the system may automatically generate an ablation map of where ablations were completed for documentation of an ablation procedure, such as the RDN procedure.

[0009] The techniques of this disclosure may improve ablation procedure speed. The techniques of this disclosure may guide a clinician to optimize ablation coverage along key areas of a vessel and reduce the likelihood of re-ablations over an area that has already been subject to ablation, which a clinician might otherwise perform additional ablation to ensure coverage when the clinician is uncertain about the location of completed ablations. The techniques of this disclosure may improve procedure consistency and efficacy through accurate targeting of tissue to be ablated.

[0010] The techniques of this disclosure may also provide for accurate, streamlined clinical procedure documentation. Clinicians have expressed a desire to review records indicating the locations of where tissue was ablated to confirm a procedure was successful. Current approaches to satisfying this desire are approximate and may be relatively difficult and / or slow to review and analyze. The techniques of this disclosure may greatly streamline review by presenting information visually and instantaneously, including during the procedure, and / or prepare records of ablation procedures based on information captured during the RDN procedures.

[0011] The techniques of this disclosure may include an analysis and data processing tool which may be used to analyze an ablation procedure, allowing for a streamlined and detailed comparison between ablations versus therapy efficacy. In some examples, such a tool may include, or may pre-process information for, one or more machine learning models for analysis and live guidance.

[0012] In one example, a medical system includes memory configured to store imaging data and renal denervation device data; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the imaging data of a patient; obtain the renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generate a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and output, for display, the plurality of representations.

[0013] In another example, a method includes obtaining imaging data of a patient; obtaining renal denervation device data; determining, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

[0014] In another example, a non-transitory computer readable medium stores instructions, which, when executed, cause processing circuitry to: obtain imaging data of a patient; obtain renal denervation device data; determine, based on the imaging data, one ormore recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

[0015] Further disclosed herein are example systems and techniques that may determine at least one treatment strategy for a lesion, wherein an example system may include memory configured to store a plurality of treatment pathways and processing circuitry communicatively coupled to the memory, wherein the processing circuitry may be configured to determine the plurality of treatment pathways, wherein the processing circuitry may be configured to determine, for each respective treatment pathway of the plurality of treatment pathways, one or more respective predicted effectiveness indicators, one or more respective predicted risks, and a respective confidence level associated with at least one of the respective predictions, and wherein the processing circuitry may be configured to output for display the plurality of treatment pathways, and the one or more respective predicted effectiveness indicators, the one or more respective predicted risks, and the respective confidence level associated with at least one of the respective predictions for each respective treatment pathway.

[0016] These and other aspects of the present disclosure will be apparent from the detailed description below. In no event, however, should the above summaries be construed as limitations on the claimed subject matter, which subject matter is defined solely by the attached claims.

[0017] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the apparatus and methods described in detail within the accompanying drawings and description below. Further details of one or more examples are set forth in the accompanying drawings and the description below.BRIEF DESCRIPTION OF DRAWINGS

[0018] FIG. l is a schematic perspective view of an example of a system for performing an ablation procedure according to one or more aspects of this disclosure.

[0019] FIG. 2 is a block diagram of an example of a computing device in accordance with one or more aspects of this disclosure.

[0020] FIG. 3 is a block diagram of an example energy generation device in accordance with one or more aspects of this disclosure.

[0021] FIG. 4 is a conceptual diagram illustrating example anatomy and medical instruments for an RDN procedure in accordance with one or more aspects of this disclosure.

[0022] FIG. 5 is a conceptual diagram illustrating an example user interface which may be displayed during an RDN procedure in accordance with one or more aspects of this disclosure.

[0023] FIG. 6 is a conceptual diagram illustrating an example of tracked features during an RDN procedure in accordance with one or more aspects of this disclosure.

[0024] FIG. 7 is a conceptual diagram illustrating an example of a local coordinate system and a vessel cross section in accordance with one or more aspects of this disclosure.

[0025] FIG. 8 is a conceptual diagram illustrating an example 3D model according to one or more aspects of this disclosure.

[0026] FIG. 9 is a conceptual diagram illustrating another example 3D model according to one or more aspects of this disclosure.

[0027] FIG. 10 is a block diagram illustrating an example system according to one or more aspects of this disclosure.

[0028] FIG. 11 is a block diagram illustrating another example system according to one or more aspects of this disclosure.

[0029] FIG. 12 is a block diagram illustrating another example system according to one or more aspects of this disclosure.

[0030] FIGS. 13A-13B are flow diagrams illustrating example ablation visualization techniques of this disclosure.

[0031] FIG. 14 is a flow diagram illustrating example ablation visualization techniques of this disclosure.

[0032] FIG. 15 is a flow diagram illustrating example ablation visualization techniques of this disclosure.

[0033] FIG. 16 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of this disclosure.

[0034] FIG. 17 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of this disclosure.DETAILED DESCRIPTION

[0035] Imaging systems may be used to assist a clinician in a medical procedure, such as an ablation procedure. For example, imaging systems may be used to visualize the vasculature of a patient and the location of any medical instrument located within the vasculature of the patient. While described primarily herein with respect to the vasculature of a patient, imaging systems described herein may be used for other medical purposes and are not limited to cardiovascular purposes.

[0036] Imaging systems may generate image and / or video data via sensors. Such image and / or video data is referred to herein as imaging data. This imaging data may be displayed on a display device, with or without additional information overlayed on the imaging data. In some examples, the imaging data may be stored for future reference, such as in an electronic patient record. In some examples, this imaging data may be used to construct a three- dimensional (3D) model of the vasculature of the patient which may be of use to a clinician attempting to view the vasculature in 3D.

[0037] Imaging data may include fluoroscopy imaging data, fluoroscopy with contrast imaging data, CT imaging data, X-ray imaging data, IVUS imaging data, OCT imaging data, NIRS imaging data, MRI imaging data, ultrasound imaging data, angiogram imaging data, or other imaging data.

[0038] This disclosure describes systems and techniques for guiding a clinician through an ablation procedure, such as an RDN procedure. Such a system may obtain imaging data and renal derivation device data. The system may determine, based on imaging data, one or more recommended ablation locations, and determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations. The system may generate a plurality of representations including a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation of each of the one or more completed ablation locations and output the plurality of representations for display.

[0039] FIG. l is a schematic perspective view of an example of a system for performing an ablation procedure according to one or more aspects of this disclosure. Medical system 100 may provide a system for guiding a clinician through the ablation procedure including determining recommended ablation locations, determining completed ablation locations, and generating representations of the recommended ablation locations and the completed ablationlocations. The representations may be overlayed on imaging data and / or represented in a 3D model of vasculature of a patient. Medical system 100 may also provide a system for documenting the ablation procedure. Such a system may reduce the time of an ablation procedure, reducing the amount of contrast a patient may be exposed to, and may improve patient outcomes. Such a system may also reduce an amount of time a clinician spends documenting various ablation procedures.

[0040] System 100 includes a display device 110, a table 120, device tracking system 121, imager 140 (which may be an angiography and / or fluoroscopy imager), additional imager(s) 142, computing device 150, additional equipment 152, server 160, and network 156. System 100 may be an example of a system for use in a catheterization laboratory (Cath lab), surgical ward, or other healthcare environment. For simplicity purposes, the environment in which system 100 is used is hereinafter referred to as a Cath lab. In some examples, system 100 may include other devices. In some examples, system 100 may be used during a diagnostic session to diagnose issues for a patient or to acquire imaging data prior to an interventional procedure. In some examples, system 100 may be used during an interventional procedure, such as an ablation procedure.

[0041] Computing device 150 may be associated with one or more clinicians, who may be located in the Cath lab during the medical procedure. Computing device 150 may include, for example, an off-the-shelf device, such as a laptop computer, desktop computer, tablet computer, smart phone, or other similar device. In other examples, computing device 150 may be a special purpose computing device, such as one specifically designed to be used in a Cath lab. Computing device 150 includes memory and processing circuitry.

[0042] In some examples, computing device 150 may be configured to control an electrosurgical generator, a power supply, or any other accessories and peripheral devices relating to, or forming part of, system 100. In some examples, computing device 150 may perform various control functions with respect to imager 140, additional imager(s) 1042, display device 110, additional equipment 152, and / or the like. Computing device 150 may be communicatively coupled to device tracking system 121, imager 140, additional imager(s) 142, one or more devices of additional equipment 152, display device 110, server 160, and / or network 156.

[0043] While a number of features are described herein as being attributed to computing device 150, in some examples, features attributed to computing device 150 may be performed by processing circuitry of any of computing device 150, imager 140, server 160, network 156(e.g., one or more computing devices forming or connected to network 156), other elements of system 100, or any combinations thereof. In some examples, processing circuitry associated with computing device 150 may be distributed and shared across any combination of computing device 150, imager 140, server 160, network 156, display device 110, and / or other elements of system 100. Additionally, in some examples, processing operations or other operations performed by processing circuitry of computing device 150 may be performed by processing circuitry residing remotely, such as one or more cloud servers or processors. For purposes of ease of discussion herein, such processing circuitry may be considered a part of computing device 150.

[0044] System 100 may include network 156, which is a suitable network such as a local area network (LAN) that includes a wired network or a wireless network, a wide area network (WAN), a wireless mobile network, a Bluetooth network, or the Internet. In some examples, network 156 may be a secure network, such as a hospital network, which may limit access by users. In some examples, network 156 may interconnect various devices of system 100.

[0045] As discussed above, imager 140 may be fluoroscopy imager, and may image portions of a patient’s body during or before a medical procedure to visualize patient anatomy and / or medical instruments, e.g., of additional equipment 152. Additional imager(s) 142 may also be configured to image portions of a patient’s body, such as vasculature of the patient. Additional imager(s) 142 may be devices other than fluoroscopy devices. For example, additional imager(s) may be any other type of imaging device, such as a CT device, an IVUS device, an OCT device, a NIRS device, an MRI device, a PET device, or the like.

[0046] Computing device 150 may be configured to determine, based on imaging data from imager 140 and / or additional imager(s) 142, one or more recommended ablation locations. For example, computing device 150 may execute one or more machine learning models and / or computer vision algorithms to determine recommended ablation locations.

[0047] Computing device 150 may be configured to determine, based on the imaging data and renal denervation device data, one or more completed ablation locations. For example, computing device 150 may obtain data from a renal denervation device (e.g., of additional equipment 152) indicative of an ablation event and time synchronize the data indicative of the ablation event with a location of a delivery element in the imaging data to determine a completed ablation location, as the ablation event occurs at the location of the delivery element at the time of the ablation event.

[0048] Computing device 150 may be configured to generate representations of any recommended ablation locations and any completed ablation locations and be configured to control display device 110 to display such representations, such as in an overlay over the imaging data and / or in a 3D model of the vasculature of the patient.

[0049] In some examples, computing device 150 may be further configured to determine, based on the imaging data and the renal denervation device data, any failed ablation locations, and generate representations of any failed ablation locations for display.

[0050] Additional equipment 152 may include medical instruments configured to be used during a medical procedure, such as an ablation procedure, including, but not limited to, guide catheters, ablation catheters, energy generation devices, and / or other devices.

[0051] Display device 110 may be configured to display captured imaging data, from, for example, imager 140 and / or additional imager(s) 142. In some examples, display device 110 may be configured to display representations of recommended ablation locations and representations of completed ablation locations overlaid on imaging data from imager 140 and / or additional imager(s) 142. In some examples, display device 110 may be configured to display a 3D model of the vasculature of a patient including representations of recommended ablation locations and representations of completed ablation locations, instead of, or in addition to, captured imaging data. In some examples, display device 110 may be configured to display the various user interfaces disclosed herein. Display device 110 may be configured to display any other content discussed as being displayed in this disclosure.

[0052] Table 120 may be, for example, an operating table or other table suitable for use during a medical procedure, such as an ablation procedure. Table 120 may include a device tracking system 121, such as a specially designed pad to be placed under, or integrated into, table 120.

[0053] Device tracking system 121 may include radio frequency identification (RFID), near field communication (NFC), battery powered sensors, triangulation technology, and / or an electromagnetic (EM) field generator which may be used to generate an EM field during the medical procedure. Such technologies may be used to track the positions of one or more devices (e.g., medical instruments) within the body of a patient during a medical procedure. For example, device tracking system may track the location of devices (e.g., devices of additional equipment 152) by tracking sensors attached to or incorporated in such devices. In some examples, device tracking system 121 may serve as a charging pad which may wirelessly charge various sensors which may be placed on or in the patient, such as formonitoring patient parameters, during the medical procedure. Such sensors may wirelessly communicate with computing device 150. In this manner, fewer wires may be present in a Cath lab than otherwise may be, lowering a risk of entanglement with the patient or a clinician moving about the Cath lab. In some examples, wired sensors (e.g., of additional equipment 152) may be utilized which may be, via the wires of the wired sensors, connected to or disconnected from one or more devices of system 100, such as computing device 150.

[0054] Server 160 may be configured to store data obtained by and / or determined or generated by computing device 150. In some examples, server 160 may be configured to perform techniques attributed to computing device 150. Server 160 may be communicatively coupled to computing device 150, for example, by wired, optical, or wireless communications and / or by network 156. Server 160 may be a hospital server which may or may not be located in a Cath lab, such as a cloud-based server, or the like. Server 160 may be configured to store patient data, electronic patient records, or the like.

[0055] FIG. 2 is a block diagram of an example of a computing device in accordance with one or more aspects of this disclosure. Computing device 200 may be an example of computing device 150, a computing device of network 156, and / or server 160 of FIG. 1 and may include a workstation, a desktop computer, a laptop computer, a server, a smart phone, a tablet, a dedicated computing device, or any other computing device capable of performing the techniques of this disclosure.

[0056] In some examples, computing device 200 may be configured to perform processing, control and other functions associated with various devices of FIG. 1, such as display device 110, imager 140, additional imager(s) 142, additional equipment 152, and / or device tracking system 121. Computing device 200 may include, for example, a memory 202, processing circuitry 204, a display 206, a network interface 208, an input device(s) 210, or an output device(s) 212, each of which may represent any of multiple instances of such a device within the computing system, for ease of description.

[0057] While processing circuitry 204 appears in computing device 200 in FIG. 2, in some examples, features attributed to processing circuitry 204 may be performed by processing circuitry of any of computing device 150, imager 140, server 160, computing devices of network 156, or other components of FIG. 1. In some examples, one or more processors associated with processing circuitry 204 in computing device 200 may be distributed and shared across any combination of computing device 150, imager 140, server 160, computing devices of network 156, or other components of FIG. 1. Additionally, in someexamples, processing operations or other operations performed by processing circuitry 204 may be performed by one or more processors residing remotely, such as one or more cloud servers or processors, each of which may be considered a part of computing device 200. Computing device 200 may be used to perform any of the techniques described in this disclosure, and may form all or part of devices or systems configured to perform such techniques, alone or in conjunction with other components, such as components of computing device 150, imager 140, server 160, computing devices of network 156, other components of FIG. 1, or a system including any or all of such devices.

[0058] Memory 202 of computing device 200 includes any non-transitory computer- readable storage media for storing data or software that is executable by processing circuitry 204 and that controls the operation of computing device 150. In one or more examples, memory 202 may include one or more solid-state storage devices such as flash memory chips. In one or more examples, memory 202 may include one or more mass storage devices connected to the processing circuitry 204 through a mass storage controller (not shown) and a communications bus (not shown).

[0059] Although the description of computer-readable media herein refers to a solid-state storage, it should be appreciated by those skilled in the art that computer-readable storage media may be any available media that may be accessed by the processing circuitry 204. That is, computer readable storage media includes non-transitory, volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. For example, computer-readable storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, Blu-Ray or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and that may be accessed by computing device 200. In one or more examples, computer-readable storage media may be stored in the cloud or remote storage and accessed using any suitable technique or techniques through at least one of a wired or wireless connection.

[0060] Memory 202 may store one or more applications 215, which may be executable by processing circuitry 204. Applications 215 may include natural language processing (NLP) model(s) 228, machine learning (ML) models (s) 222, computer vision models (s) 224, and / or user interface(s) 218. In some examples, any of ML model(s) 222, computer vision model(s)224, and / or NLP model(s) 228 may be the same algorithms. In some examples, any of ML model(s) 222, computer vision model(s) 224, and / or NLP model(s) 228 may be the different algorithms.

[0061] User interface(s) 218 may include one or more user interfaces which processing circuitry 204 may output for display by display 206 and / or display device 110. Content of user interface(s) 218 may include that described with respect to FIGS. 4-9 hereinafter, for example, and may include representations of recommended ablation locations and a representations of completed ablation locations in an overlay or a 3D model of vasculature of a patient.

[0062] Memory 202 may store imaging data 214, RDN device data 216, electronic patient record 236, 3D model 232, overlay 240, ablation / coordinates data 234, and / or user profiles 238. Imaging data 214 may be captured by imager 140 and / or additional imager(s) 142 (FIG.1) during a medical procedure of a patient. Processing circuitry 204 may obtain imaging data 214 from imager 140 and / or additional imager(s) 142 and store imaging data 214 in memory 202.

[0063] Processing circuitry 204 may use imaging data 214 to guide a clinician during an ablation procedure. For example, processing circuitry 204 may determine, based on imaging data 214, one or more recommended ablation locations and determine, based on imaging data 214 and RDN device data 216, one or more completed ablation locations. Processing circuitry 204 may generate overlay 240 and / or 3D model 232 which may include representations of the recommended ablation locations and representations of the completed ablation locations. Processing circuitry 204 may control display 206 to display overlay 240 on imaging data 214. Additionally, or alternatively, processing circuitry 204 may control display 206 to display 3D model 232.

[0064] Overlay 240 may include representations (e.g., visual indications) of delivery elements, completed ablation locations, recommended ablation locations, failed ablation locations, and / or the like. Such representations may distinguish, not only what the representation represents, but also a 3D location within a two-dimensional (2D) space, so as to assist the clinician. For example, the representations may differentiate between dorsal and ventral positions. The representations may include different shapes, colors, and / or the like which may help discriminate between the different types of representations. The representations of this disclosure are further described with respect to FIGS. 4-9 hereinafter.

[0065] 3D model 232 may include a 3D model, such as those discussed with respect to FIGS. 8-9 of vasculature of a patient. 3D model 232 may include an identification of locations of an ablation catheter, delivery elements of the ablation catheter, ablated areas, recommended areas for ablations, failed ablation locations, and / or the like.

[0066] RDN device data 216 may include information generated by a device configured to control ablation delivery elements, such as an energy generation device (See FIG. 3). For example, RDN device data 216 may include information relating to the delivery of ablation energy by one or more delivery elements, including when energy was delivered, a length of energy delivery, an amplitude of energy delivery, a map of energy delivery, any error codes generated by the energy generation device and times relating to the generation of the error codes, etc.

[0067] Ablation / coordinates data 234 may include an identification of locations of an ablation catheter, delivery elements of the ablation catheter, ablated areas, recommended areas to be ablated, failed ablations locations. Ablation / coordinates data 234 may include coordinates information of one or more local coordinate systems and a global coordinate system, which may be used for appropriately mapping the locations of the ablation catheter, delivery elements of the ablation catheter, ablated areas, recommended areas to be ablated, failed ablations locations, and / or the like to the appropriate positions within imaging data 214 for producing overlay 240 and / or 3D model 232.

[0068] Electronic patient record 236 may include information relating to the current patient’s medical history, such as electronic forms, imaging data from prior procedures, including diagnostic procedures, or the like. During or after an ablation procedure, processing circuitry 204 may update electronic patient record 236 to include information generated during an ablation procedure, such as to include imaging data 214, RDN device data 216, 3D model 232, and / or ablation / coordinates data 234.

[0069] Processing circuitry 204 may use information obtained during a medical procedure, such as imaging data 214, RDN device data 216, ablation / coordinates data 234, overlay 240, and / or 3D model 232 to automatically update electronic patient record 236 such that a clinician does not need to enter all pertinent information into electronic patient record 236 manually. For example, processing circuitry 204 may, at the end of an ablation procedure (such as when the RDN device is powered off or when a clinician indicates an end of the procedure through an input device, e.g., of input devices 210), automatically generate an ablation map indicative the completed ablation locations of the ablation procedure and storethe ablation map in electronic patient record 236. User profiles 238 may store user settings and / or preferences specific to a given clinician, as discussed later herein with respect to FIG. 13B.

[0070] ML model(s) 222, and / or computer vision model(s) 224, may be trained using data collected from past medical procedures, such as previous imaging data, previous ablation data, and / or previous patient demographic data. Such data may be from a plurality of patients and / or a current patient. The previous ablation data may include a plurality of ablation techniques, a plurality of device types, a plurality of patient types, and outcome data associated with previous ablation procedures. In some examples, at least one of the previous ablation data, or previous patient demographic data is generated by executing a natural language processing model (e.g., of NLP model(s) 228) on content of a plurality of electronic patient records. As such, ML model(s) 222, computer vision model(s)224, may be trained on data from actual procedures, reflecting actual treatments, and actual outcomes from past medical procedures. Such models may be utilized to determine recommended ablation locations.

[0071] Potential machine learning or artificial intelligence techniques that may be used include Naive Bayes, k-means clustering, k-nearest neighbors, random forest, support vector machines, neural networks, linear regression, logistic regression, classification models, anomaly detection, Convolutional neural networks (CNNs), object detection, natural language processing (NLP), facial recognition, Recommender systems, optical character recognition (OCR) to read text & characters from other systems and / or screens, or any other similar techniques. Such models may be train using batch gradient descent, stochastic gradient descent, mini-batch gradient descent, or any other similar techniques. Example machine learning models are further discussed hereinafter with respect to FIGS. 16 and 17.

[0072] Processing circuitry 204 may execute any of user interface(s) 218 so as to cause display 206 (and / or display device 110 of FIG. 1) to present that UI of user interface(s) 218 to one or more clinicians performing the ablation procedure. In some examples, user interface(s) 218 may include overlay 240 and / or 3D model 232.

[0073] Processing circuitry 204 may capture real-time information from equipment, such as imager 140, additional imager(s) 142, and / or additional equipment 152 (e.g., a RDN device). For example, fluoroscopy imaging may be obtained via network interface 208 (e.g., over high-definition multimedia interface (HDMI), serial digital interface (SDI), digital visualinterface (DVI), optical interface, internet protocol video, or the like) by computing device 150 from a live video feed output by imager 140.

[0074] Processing circuitry 204 may track a live position(s) of delivery elements (e.g., electrodes) within the vasculature of the patient, and may enhance visualization on a displayed fluoroscopy image, for example, on display 206 and / or display device 110.

[0075] Processing circuitry 204 may combine imaging data 214 and RDN device data 216 to determine ablation locations. Processing circuitry 204 may use timestamp information from imaging data 214 and RDN device data 216 to synchronize the data to accurately determine a location of an ablation. In some examples, processing circuitry 204 may combine RDN device data 216 with visual signals from a vessel spasm during ablation to synchronize imaging data 214 and RDN device data 216. In some examples, system 100 may execute computer vision model(s) 224 to determine an occurrence of such a vessel spasm. In some examples, processing circuitry 204 may track ablation performance of individual delivery elements (e.g., electrodes).

[0076] Processing circuitry 204 may determine or compute recommended future ablation location(s). Processing circuitry 204 may visually communicate such information to a clinician on a display in real-time during the procedure, for example, through user interface(s) 218. For example, processing circuitry 204 may recommend a next ablation location during an ablation at a present ablation location. Processing circuitry 204 may display a 2D and / or a 3D representation of the anatomy (including any visual ablation indicators) on display 206 and / or display device 110.

[0077] In some examples, processing circuitry 204 may, via user interface(s) 218, visually indicate previous ablation locations, current delivery element locations, recommended future ablation locations, and / or ablation performance, such as successful and / or failed ablations. In some examples, ablation performance may be visualized based on an amount energy delivered to a vessel surface, such as energy within RDN device data 216.

[0078] In some examples, processing circuitry 204 may use a 2D output to display a persistent vessel output (e.g., a representation of a vessel profile even when contrast is not being injected into the patient) on display 206 and / or display device 110. For example, processing circuitry 204 may record vessel diameter along a plurality of sampled points along the vessel segments during contrast injection. The persistent vessel output may include an approximation of the renal anatomy to provide a more complete picture of the ablation map atall times. As such, the techniques of this disclosure may lower the amount of contrast which may be required to be injected into the patient during the RDN procedure.

[0079] In some examples, system 100 may be configured to continue the mapping / tracking process, even when video input (e.g., imaging data 214 from imager 140) is interrupted, by ignoring any irrelevant windows of time (e.g., times during which no video is captured) and pausing the update process of overlay 240, 3D model 232, and / or any of user interface(s) 218, until a later time, such as when the capture of imaging data 214 resumes.

[0080] In some examples, processing circuitry 204 may save anatomy geometry and ablation data (coordinates and signal data) in a digital file for later review or further processing and / or analysis. For example, processing circuitry 204 may store ablation / coordinates data 234 in memory 202. In some examples, ablation / coordinates data 234 may be stored as image(s) and / or video data. Processing circuitry 204 may use ablation / coordinates data 234 to update electronic patient record 236, such as to prepare a report of the RDN procedure. In some examples, processing circuitry 204 may transmit ablation / coordinates data 234 and / or any report of the RDN procedure to network 156 and / or server 160 (both of FIG. 1) for storage and / or other use.

[0081] Peri-procedure, and during the delivery of renal denervation energy, computing device 200 may output visual overlays, such as overlay 240, on a display displaying imaging data 214 to guide the clinician in performing the ablation procedure. Such visual overlays may include highlighting recommended locations for ablations, and may change the color and / or provide a differentiating representation of such locations when the locations have been successfully ablated. In some examples, the visual overlays may include a countdown clock for the recommended length of the ablation, and / or the other such information that may be of assistance to the clinician.

[0082] Post-procedure, computing device 200 may generate 2D images, 3D images, and or 3D models (e.g.., 3D model 232) of the renal artery tree with the completed and / or failed ablation locations shown along with other relevant data, (e.g., ablation duration, energy delivered) to document the ablation procedure. Computing device 200 may store such documentation in electronic patient record 236. In some examples, computing device 200 may collect other data, for example, from imager 140, other imager(s) 142, and / or other equipment 152 which may be used for product enhancements or new product development (including algorithms), ongoing research, insurance claims generation, and / or post market surveillance.

[0083] In some examples, computing device 200 may output a text overview of a recommended or suggested protocol for the clinician, such as via user interface(s) 218 and then overlay overlay 240 on imaging data 214 for viewing by the clinician. In some examples, the recommended ablation locations of overlay 240 and / or 3D model 232 may be represented on the imaging data as x’s or circles in the specific recommended locations. In some examples, the circles may be colored, such as colored white. Such x’s or circles may change to another representation (e.g., a square) and / or turn to another color (e.g., green) as the ablation is completed. In some examples, computing device 200 may obtain energy delivery data, for example, RDN device data 216, from an ablation device, to record how much energy was delivered at each ablation location. In some examples, computing device 200 may execute computer vision model(s) 224 to track delivery elements of an ablation catheter to identify where the ablation occurs. In some examples, computing device 200 may automatically generate a report of the ablation procedure during and / or after the procedure is completed. Computing device 200 may store the report in electronic patient record 236 and / or send report to server 160 via network interface 208.

[0084] Processing circuitry 204 may be implemented by one or more processors, which may include any number of fixed-function circuits, programmable circuits, or a combination thereof. In various examples, control of any function by processing circuitry 204 may be implemented directly or in conjunction with any suitable electronic circuitry appropriate for the specified function. Fixed-function circuits refer to circuits that provide particular functionality and are preset on the operations that may be performed. Programmable circuits refer to circuits that may programmed to perform various tasks and provide flexible functionality in the operations that may be performed. For instance, programmable circuits may execute software or firmware that cause the programmable circuits to operate in the manner defined by instructions of the software or firmware. Fixed-function circuits may execute software instructions (e.g., to receive parameters or output parameters), but the types of operations that the fixed-function circuits perform are generally immutable. In some examples, the one or more of the units may be distinct circuit blocks (fixed-function or programmable), and in some examples, the one or more units may be integrated circuits.

[0085] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), graphics processing units (GPUs) or other equivalent integrated or discrete logic circuitry. Accordingly, the termprocessing circuitry 204 as used herein may refer to one or more processors having any of the foregoing processor or processing structure or any other structure suitable for implementation of the techniques described herein. In addition, in some aspects, the functionality described herein may be provided within dedicated hardware or software modules configured for encoding and decoding, or incorporated in a combined codec. Also, the techniques could be fully implemented in one or more circuits or logic elements.

[0086] Display 206 may be touch sensitive or voice activated, enabling display 206 to serve as both an input and output device. Alternatively, a keyboard (not shown), mouse (not shown), joystick (not shown) or other data input device(s)s (e.g., input device(s) 210) may be employed. In some examples, display 206 may include a virtual reality and / or augmented reality headset. In some examples, display 206 may include a hologram device.

[0087] Network interface 208 may be adapted to connect to a network (e.g., network 156) such as a local area network (LAN) that includes a wired network or a wireless network, a wide area network (WAN), a wireless mobile network, a Bluetooth network, or the internet. In some examples, network interface 208 may include one or more application programming interfaces (APIs) for facilitating communication with other devices. For example, computing device 200 may receive imaging data 214 from imager 140 and / or additional imager(s) 142 during an ablation procedure via network interface 208. Computing device 200 may interact with server 160 via network interface 208. Computing device 200 may receive updates to its software, for example, applications 215, via network interface 208. Computing device 200 may also display notifications on display 206 that a software update is available.

[0088] Input device(s) 210 may include any device that enables a user to interact with computing device 200, such as, for example, a mousejoystick, keyboard, foot pedal, touch screen, augmented-reality input device(s) receiving inputs such as hand gestures or body movements, or voice interface.

[0089] Output device(s) 212 may include any connectivity port or bus, such as, for example, parallel ports, serial ports, universal serial busses (USB), or any other similar connectivity port known to those skilled in the art.

[0090] Applications 215 may include one or more software programs stored in memory 202 and executed by processing circuitry 204 of computing device 200.

[0091] FIG. 3 is a block diagram of an example RDN device in accordance with one or more aspects of this disclosure. RDN device 300 of FIG. 3 may be an example of an ablation device of additional equipment 152 (FIG. 1). RDN device 300 may be an energy generationdevice configured to be used with an ablation catheter that uses electrodes as delivery elements. While RDN device 300 may be configured to be used with an ablation catheter that uses electrodes as delivery elements, the techniques of this disclosure are more broadly applicable to include any RDN device that controls delivery elements to perform an ablation. As shown in FIG. 3, RDN device 300 may include positive terminal (+) 312, negative terminal (-) 314, energy generator 302, processing circuitry 304, user interface 306, storage device 308, and network interface 320.

[0092] Positive terminal 312 may be coupled to energy generator 302 and may be configured to attach to one or more conductors of an ablation catheter (not shown) so as to conduct electricity between energy generator 302 and the one or more conductors. Negative terminal 314 may be coupled to energy generator 302 (or alternatively to ground) and may be configured to attach to one or more conductors of the ablation catheter so as to conduct electricity between the one or more conductors and energy generator 302. Energy generator 302 may be configured to provide radiofrequency electrical pulses to the one or more conductors of the ablation catheter to perform an electroporation procedure or other ablation procedure to tissue within vessels of a patient. While shown in the example of FIG. 3 as a single energy generator, RDN device 300 is not so limited. For instance, RDN device 300 may include multiple energy generators that are each capable of generating ablation signals in parallel. In some examples, RDN device 300 may include energy generators of different types, such as a radiofrequency energy generator (such as an RDN generator), a pulsed field energy generator, and / or a cryogenic or thermal energy generator.

[0093] Processing circuitry 304 may include one or more processors, such as any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), discrete logic circuitry, or any other processing circuitry configured to provide the functions attributed to processing circuitry 304 herein may be embodied as firmware, hardware, software or any combination thereof. Processing circuitry 304 controls energy generator 302 to generate signals according to various settings 310 which may be stored in storage device 308.

[0094] Storage device 308 may be configured to store controller data 316 within RDN device 300, respectively, during operation. Controller data 316 may be an example of controller data 220 and may include an amount of energy delivered during an ablation, an amount of time the energy was delivered, error codes, etc. In some examples, generator data may include timestamps. Storage device 308 may include a computer-readable storagemedium or computer-readable storage device. In some examples, storage device 308 includes one or more of a short-term memory or a long-term memory. Storage device 308 may include, for example, random access memories (RAM), dynamic random access memories (DRAM), static random access memories (SRAM), magnetic discs, optical discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable memories (EEPROM). In some examples, storage device 308 is used to store data indicative of instructions, e.g., for execution by processing circuitry 304, respectively.

[0095] User interface 306 may include a button or keypad, lights, a speaker / microphone for voice commands, and / or a display, such as a liquid crystal (LCD), light-emitting diode (LED), or organic light-emitting diode (OLED). User interface 306 may be configured to receive input from a clinician, such as selecting settings from settings 310 for use during an ablation therapy session. In some examples, the display may be configured to display information regarding an in-progress ablation therapy session, such as patient parameters or other information which may be useful to a clinician.

[0096] FIG. 4 is a conceptual diagram illustrating example anatomy and medical instruments of an example user interface in accordance with one or more aspects of this disclosure. View 420 may be an example of a view which may be displayed on display 206 and / or display device 110 during an RDN procedure. View 420 may include patient anatomy, such as kidney 410 and renal artery 406. View 420 may also include medical instrument(s), such as guide catheter 400 and ablation catheter 402. Ablation catheter 402 may include delivery elements 404, which may include electrodes configured to deliver denervation energy to target tissue within renal artery 406, thermal energy delivery elements configured to deliver thermal energy to target tissue within renal artery 406, and / or alcohol delivery elements configured to deliver alcohol to target tissue within renal artery 406. Target tissue may include tissue to be ablated. Ablation catheter 402 may be configured to be coupled to RDN device. For example, in the example where delivery elements 404 of ablation catheter 402 include electrodes, one or more of the electrodes may be coupled to positive terminal 312 and one or more of the electrodes may be coupled to negative terminal 314.

[0097] FIG. 5 is a conceptual diagram illustrating an example user interface which may be displayed during an RDN procedure in accordance with one or more aspects of this disclosure. In the example of FIG. 5, delivery elements 504 of ablation catheter 502 are described as including electrodes, however, delivery elements 504 may, alternatively or additionally, include thermal delivery elements and / or alcohol delivery elements.

[0098] System 100 may display user interface 550 on display 206 and / or display device 110 during an RDN procedure. User interface 550 may include a view 520, similar to view 420 of FIG. 4. View 520 may include imaging data 214 received from imager 140 with overlay 240 overlayed on imaging data 214. For example, view 520 (via overlay 240) may include visual indications of ventral electrodes 504A and dorsal electrodes 504B (collectively “electrodes 504” to assist a clinician in determining where each electrode is located three dimensionally within the anatomy of the patient.

[0099] View 520 may also include visual indications of completed ventral ablations 516A and dorsal ablations 516A to assist a clinician in determining where ablations have already been performed. View 520 may also include visual indications of recommended ventral locations to be ablated 512A and recommended dorsal locations to be ablated 514B, to assist a clinician in guiding electrodes 504 to an appropriate location to perform further ablations.

[0100] In some examples, view 520 may include a visual indication for any failed ablations, such as failed ablation 518. For example, a failed ablation may include an ablation where the intended ablation energy did not reach target tissue, such as where the ablation energy was not delivered at a sufficient amplitude and / or for a sufficient time. In some examples, system 100 may compare the amplitude and / or length of time ablation energy is delivered (e.g., based on RDN device data 216) to one or more thresholds to determine a failed ablation. In some examples, system 100 may determine a failed ablation based on an error code from RDN device data 216. The visual indication of failed ablation 518 may assist a clinician in determining which ablation sites may require the delivery of further ablation energy.

[0101] The visual indications discussed with respect to view 520 may include different shapes, colors, and / or the like which may help discriminate one type of overlaid depiction from another. User interface 550 may include a key 552 which may display an example representation of each depiction that may be overlaid in view 520 to reduce the mental burden on a clinician during the RDN procedure, e.g., so a clinician need not recall from memory what each depiction represents. User interface 550 may include recommendations 554, which may provide a descriptive and / or visual representation of recommendations of system 100 to the clinician. Recommendations 554 may be updated in real time such that when a clinician maneuvers ablation catheter 502 and / or guide catheter 500, the description may change to reflect the actual position of ablation catheter 502, guide catheter 500, and electrodes 504. Insome examples, the updating of the description may occur in a periodic manner, such as every second or every half second.

[0102] User interface 550 may also include progress 556 which may track progress of the RDN procedure, such as a percentage of completeness of the RDN procedure.

[0103] FIG. 6 is a conceptual diagram illustrating an example of tracked features during an RDN procedure in accordance with one or more aspects of this disclosure. For example, system 100 may identify key trackable features, shown in boxes in FIG. 6. Such features may include anatomical features and / or other features, such as medical instruments, implanted devices, or portions thereof, within the patient. For example, system 100 may execute at machine learning model(s) 222 and / or computer vision model(s) 224 to identify such features. For example, system 100 may identify kidney 610, elongated structure 600 of guide catheter 400 (FIG. 4), vertebrae 612, distal opening 601 of guide catheter 400, portion 602 of ablation catheter 402 (FIG. 4) outside of distal opening 601, bifurcations 614A-614C, bifurcations 616A-616B, and / or the like, for example, by executing one or more of computer vision model(s) 224 on imaging data 214. In some examples, bifurcations 614A-614C may represent an endpoint for any ablations. For example, vessels distal to bifurcations 614A- 614C may be too small to successfully navigate and ablate.

[0104] System 100 may define a corresponding local coordinate system for each vessel section between key or selected features. Example sections are shown as lines between the larger filled circles, like circles 620 A and 620B. As shown, section 630 spans from circle 620 A (which may represent a beginning of branching of a renal artery) to circle 620B (which may represent the distal opening 601. For example, system 100 may define a local coordinate system by length along a section (e.g., proportionally along a vessel centerline), in addition to the polar coordinates of each delivery element (e.g., electrode) present within the section. System 100 may identify delivery element locations on the local coordinate system. System 100 may record delivery element coordinates in the appropriate local coordinate system when an ablation device signal, e.g., from RDN device 300, indicates an ablation event. For example, RDN device 300 may output a signal indicative of an ablation event. System 100 may map ablation locations from each local coordinate system onto a global coordinate system to generate an image with representations of completed ablations (and, in some examples, any failed ablations) marked for display, on display 206 and / or display device 110. For example, system 100 may generate overlay 240 and / or 3D model 232 to include such representations. System 100 may mark near and far side ablations distinctly. For example,near side may include one of dorsal or ventral and far side may include the other of dorsal or ventral. System 100 may mark near and far side ablations with their own respective marking and / or color to indicate whether they are near side ablations or far side ablations. System 100 may repeat this process for each frame of imaging data 214 obtained from imager 140 and / or additional imagers 142.

[0105] FIG. 7 is a conceptual diagram illustrating an example of a local coordinate system and a vessel cross section in accordance with one or more aspects of this disclosure. A cross section 732 of a renal vessel taken at cross section 730 is shown. A diameter 738 of cross section 732 is also shown. In some examples, a value of diameter 738 may be displayed, e.g., as part of user interface(s) 218, overlay 240, and / or 3D model 232. A location of (or a recommended location of) an electrode 734 is displayed within cross section 732. The location of electrode 734 may be displaced from a vertical axis of cross section 732 by an angle 736, such as 45 degrees. Displaying the location of electrode 734 within cross section 732 may assist a clinician in manipulating ablation catheter 402 to position electrode 734 at an appropriate location along the circumference of the vessel represented in cross section 732 for ablation. For example, it may be desirable to ablate nerves along an entire circumference of cross section 732. In some examples, cross section 732 may display ablated areas along the circumference of cross section 732 in a different color and / or with a different representation so as to differentiate areas that have been ablated from areas that have not. Generally, when ablation is delivered, an area of about 25% - 30% (90° - 108°) of the circumference of a cross section of a vessel may experience the ablation. While described as an electrode, electrode 734 may be any type of delivery element.

[0106] FIG. 7 also includes an example representation of local coordinate system values in table 740. Such a local coordinate system may identify, for each electrode of the RDN catheter, a vessel section, such as vessel R3 (Right renal artery - section 3); a distance (e.g., a distance from a distal point of the vessel section to a proximal point of the vessel section), which may be set forth in a system of measure, such as in millimeters, percentages of the length of the vessel segment, or the like; an angle, such as an angle from a vertical axis of the cross section of the vessel, and / or the like.

[0107] An example of table 740 includes:

[0108] System 100 may track the energy delivered by RDN device 300 as a single-value metric or an array of values derived from RDN device data 216 obtained, e.g., from RDN device 300 (e.g., time (e.g., duration), energy readings, etc.). System 100 may distinguish between the right and left renal arteries, for example, based on a relative position of detected anatomical features and / or tracked features (see FIG. 6). For example, the vena cava is located on a right side of a patient leading to a longer renal artery on the right side of the patient than on the left side of the patient. Such anatomical features may be used to distinguish between the right and left renal arteries.

[0109] In some examples, system 100 may determine vessel sections so as to maximize consistency of anatomy between frames. Vessel sections may include curves, splines, straight lines, and / or the like. For example, system 100 may identify a curve in the vasculature of the patient of a certain size in one frame of imaging data 214 and identify a curve in the vasculature of the patient of the same size in a succeeding frame of imaging data 214 and identify the curves of the same size in the two frames as a same vessel section.

[0110] For 2D (on-screen fluoroscopy) visualization, “global coordinates” may simply refer to on-screen pixel coordinates. As such, as patient anatomy moves (e.g., due to patient movement and / or imaging sensor movement) between frames, the global coordinate for each ablation point may need to be recalculated. For example, system 100 may recalculate the global coordinates for each ablation point on a frame-by-frame basis so as to be able to relatively accurately display a representation of a location of an ablation over imaging data 214.[OHl] FIG. 8 is a conceptual diagram illustrating an example 3D model according to one or more aspects of this disclosure. 3D model 800 may be an example of 3D model 232 of FIG. 2. In some examples, system 100 may map the global coordinates onto 3D model 800,allowing a clinician to view the anatomy from any angle. For example, 3D model 800 may be displayed and manipulatable by a clinician via input device(s) 210. System 100 may determine 3D model 232. For example, system 100 may obtain 3D model 800 from an imported 3D DICOM file (e.g., from a CT scan), generate 3D model 800 via epipolar geometry reconstruction techniques and by capturing fluoroscopy angulation data along with the fluoroscopy imaging itself, and / or obtain 3D model 800 from a 3D reconstruction device.

[0112] System 100 may display 3D model 800 on display 206 and / or display device 110. For example, 3D model 800 may include a representation of kidney 810 and renal vessel 806. 3D model 800 may also include a representation of lead 802, ventral electrodes 804A, dorsal electrodes 804B, ventral ablations 816A, dorsal ablations 816B, recommended ventral locations to be ablated 812A, recommended dorsal locations to be ablated 812B, and / or any failed ablations (not shown). In some examples, 3D model 800 may be displayed in lieu of view 520 (FIG. 5). In other examples, 3D model 800 may be displayed along with view 520 either on a same display or a different display. For example, 3D model 800 may be displayed on display 206 while user interface 550 may be displayed on display device 110.

[0113] In some examples, system 100 may perform a live 3D reconstruction process to allow for a continuation of the mapping process if the clinician changes the fluoroscopy angle mid-procedure. For example, system 100 may perform the live 3D reconstruction process within a system internal coordinate system, such as the global coordinate system discussed herein, but may not, in some examples, display a reconstructed 3D model to the clinician. Such a live 3D reconstruction process may include system 100 translating the polar coordinates of points to account for angularity of a detector of imager 140 relative to patient anatomy, and also adjusting vessel segments or possibly re-segmenting vessels in response to angularity changes. For example, a vessel segment might be initially represented as a straight line, but after viewing the vessel from another angle, the vessel segment could be translated to a line that curves when viewed from the new angle. In another example, a vessel segment may split into 2 new segments when viewed from the new angle, in which case, system 100 may re-translate all previous tracked points onto those 2 new lines.

[0114] FIG. 9 is a conceptual diagram illustrating another example 3D model according to one or more aspects of this disclosure. System 100 may highlight ablated locations in 3D model 232 to display on display 206 and / or display device 110, through the use of, for examples, simple markers of particular colors and / or shapes. Alternatively, or additionally, system 100 may visually display the ablation locations with an energy delivery heatmap 910projected onto the vessel surface. For example, energy delivery heatmap 910 may include red for areas where a relatively high amount of energy is delivered during ablation, orange for areas where a relatively moderate amount of energy is delivered during ablation, and yellow for areas where a relatively low amount of energy is delivered during ablation, and / or the like. In some examples, color scales may be defined as relative to other ablations or on a predefined scale. For example, “energy delivered” could be defined as a cumulative energy delivered to a surface, or another metric, such as a maximum temperature measured for greater than a predefined time period, such as 2 seconds. In some examples, system 100 may be configured to permit a clinician or other user to toggle between displaying a heatmap and displaying simple markers. For example, system 100 may display energy delivery heatmap 910 on display 206 and / or display device 110. In some examples, the techniques of FIG. 9 may be applied to a 2D image, if applicable. For example, view 520 of FIG. 5 may include an energy delivery heatmap, similar to energy delivery heatmap 910, but in 2D, in view 550.

[0115] In some examples, rather than display a heatmap of energy delivered, 3D model 900 may include a similar indication of areas which have been ablated. For example, an alternative heatmap may indicate areas successfully ablated in one color, areas not yet ablated in another color, and / or areas unsuccessfully ablated in a third color.

[0116] FIG. 10 is a block diagram illustrating an example system according to one or more aspects of this disclosure. System 1000 may be similar to or an example of, system 100 (FIG. 1). In the example of FIG. 10, system 1000 may include a fluoroscopy imaging system 1002, RDN energy generator 1010, and computing system 1020. Fluoroscopy imaging system may include a live RDN angiography image feed device 1004, such as imager 140 (FIG. 1), and may include a display, such as display device 110, onto which system 1000 may display live angiography images. Such displayed live angiography images may have information overlaid thereon, as described herein.

[0117] RDN energy generator 1010 may determine electrode signal information 1012, such as how much energy was delivered to a given electrode during an ablation, a time stamp associated with the start and / or end of the delivery of energy, and / or the like.

[0118] Computing system 1020, which may be an example of computing device 200 (FIG. 2), may include one or more RDN visualization program(s) 1022. Processing circuitry of computing system 1020 may execute the RDN visualization program(s) 1022 to determine overlay information to overlay on the live image feed based on live RDN angiography image feed 1004 and electrode signal information 1012. Computing system 1020 may generate anoutput video feed 1024 which includes the angiography image feed with overlaid information which may be used to guide an RDN procedure. For example, output video feed 1024 may include information such as that described with respect to any of, or any combination of, FIGS. 4-9 of this disclosure overlaid on live RDN angiography image feed 1004. Computing system 1020 may output output video feed 1024 to display 1006 for display in the Cath lab.

[0119] FIG. 11 is a block diagram illustrating another example system according to one or more aspects of this disclosure. System 1100 may be similar to or an example of, system 100 (FIG. 1). In the example of FIG. 11, system 1100 may include a fluoroscopy imaging system 1102, RDN energy generator 1110, computing system 1120, and additional display / computing system 1140. Fluoroscopy imaging system may include a live RDN angiography image feed device 1104, such as imager 140 (FIG. 1). Additional display / computing system 1140 may include display 1142, such as display 206 and / or display device 110, onto which system 1100 may display live angiography images. Such displayed live angiography images may have overlaid information thereon.

[0120] RDN energy generator 1110 may determine electrode signal information 1112, such as how much energy was delivered to a given electrode during an ablation, a time stamp associated with the start and / or end of the delivery of energy, and / or the like.

[0121] Computing system 1120, which may be an example of computing device 200 (FIG. 2), may include one or more RDN visualization program(s) 1122. Processing circuitry of computing system 1120 may execute the RDN visualization program(s) 1122 to determine overlay information to overlay on the live image feed based on live RDN angiography image feed 1104 and electrode signal information 1112. Computing system 1120 may generate an output video feed 1124 which includes the angiography image feed with overlaid information which may be used to guide an RDN procedure. For example, output video feed 1124 may include information such as that described with respect to any of, or any combination of, FIGS. 4-9 of this disclosure overlaid on live RDN angiography image feed 1104. Computing system 1020 may output output video feed 1124 to display 1142 for display in the Cath lab.

[0122] FIG. 12 is a block diagram illustrating another example system according to one or more aspects of this disclosure. System 1200 may be similar to or an example of, system 100 (FIG. 1). In the example of FIG. 12, system 1200 may include a fluoroscopy imaging system 1102 and RDN console 1210. Fluoroscopy imaging system may include a live RDN angiography image feed device 1104, such as imager 140 (FIG. 1).

[0123] RDN console 1210 may determine electrode signal information 1212, such as how much energy was delivered to a given electrode during an ablation, a time stamp associated with the start and / or end of the delivery of energy, and / or the like. RDN console 1210 may also include one or more RDN visualization program(s) 1214. Processing circuitry of RDN console 1210 may execute the RDN visualization program(s) 1214 to determine overlay information to overlay on the live image feed based on live RDN angiography image feed 1204 and electrode signal information 1212. RDN console 1210 may generate an output video feed 1216 which includes the angiography image feed with overlaid information which may be used to guide an RDN procedure. For example, output video feed 1216 may include information such as that described with respect to any of, or any combination of, FIGS. 4-9 of this disclosure overlaid on live RDN angiography image feed 1204. RDN console 1210 may display output output video feed 1216 on display 1218 for display in the Cath lab.

[0124] FIGS. 13A-13B are flow diagrams illustrating example ablation visualization techniques of this disclosure. The techniques of FIGS. 13A-13B are described with respect to system 100 of FIG. 1, but may be practiced by any of systems 1000 (FIG. 10), 1100 (FIG. 11, 1200 (FIG. 12), or any other system capable of performing such techniques.

[0125] System 100 may obtain live angio image feed 1302, from, for example, imager 140. For example, live angio image feed 1302 may include fluoroscopy data, such as imaging data 214. In some examples, system 100 may also obtain recorded angio video file 1304. Recorded angio video file 1304 may include imaging data from a previous medical procedure and may be included in imaging data 214 and / or electronic patient record 236. System 100 may apply recorded angio video file 1304 to video decoder 1312 to produce angio frame 1310. Alternatively, or additionally, system 100 may obtain angio frame 1310 from live angio image feed 1302. For example, angio frame 1310 may represent a single frame of angio imaging data. System 100 may also obtain live and / or recorded electrode data 1306. For example, system 100 may obtain live and / or recorded electrode data 1306 from additional equipment 152 (e.g., RDN device 300 (FIG. 3)), RDN device data 216 (FIG. 2), and / or electronic patient record 236 (FIG. 2). Live and / or recorded electrode data 1306 may be synchronized with live angio image feed 1302 and / or recorded angio video file 1304. For example, system 100 may synchronize live and / or recorded electrode data 1306 with live angio image feed 1302 and / or recorded angio video file 1304 through the use of timestamps, muscle twitches, or the like.

[0126] System 100 may perform anatomy tracking 1320 of information in angio frame 1310, such as is discussed above with respect to FIG. 6. In some examples, system 100 may use computer vision model(s) 224 to perform feature extraction to track anatomy. System 100 may perform vessel identification 1322 to identify vessels and / or vessel segments in angio frame 1310. For example, system 100 may utilize pixel thresholding and masking, perform edge detection, and / or edge selection to identify a primary vessel. System 100 may also perform electrode identification 1324 to identify delivery elements 404 of ablation catheter 402 (both of FIG. 4) in angio frame 1310. For example, system 100 may use pixel thresholding and masking, perform edge detection, and / or edge selection to identify particular electrodes of delivery elements 404. System 100 may perform electrode 3D spatial interpretation 1330 on the identified electrodes in angio frame 1310. For example, system 100 may calculate a length and radial expansion to determine a 3D position of electrodes. System 100 may map an identified vessel and current electrode positions to a local coordinate system 1340. In some examples, system 100 may add a signal map, such as a heatmap like heatmap 910 of FIG. 9, or other mapping of energy signals associated with an active delivery element (e.g., electrode) based on RDN device data 216. System 100 may map all points of the vessel(s) and electrodes (and, optionally, other anatomy, guide catheter 400 and / or ablation catheter 402), based on the anatomy tracking 1320, to a global coordinate system. For example, system 100 may map points from each vessel section back, including anything located within such vessel section(s), onto a full image and / or model. System 100 may proceed to FIG. 13B.

[0127] In the example of FIG. 13B, system 100 may store the signal map in signal map memory 1342 (e.g., of memory 202, for example, in ablation / coordinates data 234). System 100 may use signal maps in signal map memory 1342 to map previous points (such as locations of completed and / or failed ablations) to local coordinate system 1346. System 100 may store user settings / preferences 1344. For example, user settings / preferences 1344 may be stored in memory 202. User settings / preferences 1344 may include information selectable or enterable by a user, such as a clinician, regarding how much ablation energy the user would like delivered, how close together the user likes ablations to be, how conservative or how liberal the clinician would like to be regarding RDN procedure(s), turn procedure suggestions on or off, modify visualization settings (such as colors, markers, or the like), hide or show specific types of visual overlays and / or indicators, and / or the like. Based on the mapping of the previous points to the local coordinate system and user settings / preferences, system 100may suggest device position 1354 for one or more next ablation(s). In some examples, system 100 determine the suggested device position using a rule-based algorithm or from an analysis of previous outcomes (e.g., using machine learning model(s) 222). System 100 may map suggested points to local coordinate system 1352. System 100 may then map the suggested points to the global coordinate system 1350.

[0128] System 100 may, from the points mapped to the global coordinate system, generate a composite overlay 1360. Composite overlay 1360 may be an example of overlay 240 and may include remapped features and / or representations of completed, recommended, and / or failed ablations which may be overlaid onto imaging data 214 to be displayed and / or overlaid or incorporated into 3D model 232 for display. Such remapped features and / or representations may include any of the information discussed throughout this disclosure, including with respect to FIGS. 4-9 of this disclosure. System 100 may encode video and signal data 1362, for example, for procedure documentation, review, debugging, etc. System 100 may save file(s) 1370. For example, system 100 may save the encoded information in memory 202, such as in electronic patient record 236. System 100 may output video feed 1372. For example, system 100 may output the composite video including any overlay information to display 1374 (e.g., display 206 and / or display device 110).

[0129] FIG. 14 is a flow diagram illustrating example ablation visualization techniques of this disclosure. System 100 may obtain historical case data 1402 as input. Historical case data 1402 may include fluoroscopy, ablation, and / or patient demographic information and outcome data for a plurality of patients. System 100 may also obtain fluoroscopy data 1412, which may include imaging data 214 from imager 140. System 100 may also obtain generator data 1422, may include RDN device data 216 from RDN device 300.

[0130] System 100 may perform processing 1404. As part of processing 1404, system 100 may execute computer vision model(s) 224, machine learning model(s) 222, and / or NLP model(s) 228 to process historical case data 1402.

[0131] System 100 may also perform processing 1414. As part of processing 1414, system 100 may execute computer vision model(s) 224 and / or machine learning model(s) 222 to process fluoroscopy data 1412.

[0132] System 100 may perform a segmentation of techniques across device types with outcome data and differences in patient type 1406. Such a segmentation may include a segmentation of different procedural techniques observed in real world practice across device types (e.g., different medical instruments) with respective outcome data and any meaningfuldifferences in patient types (e.g., patient A does well with technique / device X vs. patient B does better with technique / device Y). Patient type may include anatomical features and / or medical history.

[0133] System 100 may generate a map 1416 which may include a 2D and / or 3D map of renal arteries including branches with diameters, the presence and location of any calcium which may take the form of a discrete yes / no calcium is present and / or an overlay on the fluoroscopic image showing the location and / or severity of any calcium deposit. For example, map 1416 include any of the information discussed with respect to FIGS. 4-9.

[0134] System 100 may determine recommended ablation locations 1408, which may be output peri-procedure prior to RDN, and may include recommended ablation locations based on successful past cases, protocol of the manufacturer of ablation catheter 402, size of artery, presence of calcification, and / or the like.

[0135] System 100 may determine ablation and / or error data 1426. Ablation and / or error data 1426 may include RDN device data 216, such as high density data detailing how much energy and / or alcohol was delivered during ablation over what increment of time, indexed to a time stamp and / or any error codes generated by RDN device 300, indexed to the time stamp. Ablation and / or error data 1426 may be an example of RDN device data 216 of FIG. 2.

[0136] System 100 may associate data 1417, such as map 1416 and ablation and / or error data 1426 using the time stamps. System 100 may produce visual overlays 1418, for example, peri-procedure, during RDN. Visual overlays 1418 may include visual overlays on a fluoroscopy screen to guide a clinician as discussed with respect to FIGS. 3-9. Visual overlays 1418 may include examples of overlay 240 and / or user interface(s) 218 both of FIG.2. Visual overlays 1418 may include highlighting and / or marking locations for suggested ablations, and changing the color and / or marking when those locations have been successfully ablated. In some examples, visual overlays 1418 may include a countdown clock for the recommended length of time of a given ablation. Such a countdown clock may run while ablation is being performed.

[0137] System 100 may also generate documentation 1428, for example, post-procedure. Documentation 1428 may include 2D images, 3D images and / or 3D model(s) of the renal artery tree with the ablation locations shown along with relevant data, such as ablation duration and / or energy delivered, to document the RDN procedure.

[0138] FIG. 15 is a flow diagram illustrating example ablation visualization techniques of this disclosure. The techniques of FIG. 15 are described with respect to computing device200, but may be practiced by any device or combination of devices described in this disclosure or any other device or system capable of performing such techniques.

[0139] Computing device 200 may obtain imaging data of a patient (1500). For example, computing device 200 may receive or retrieve imaging data from imager 140 and / or additional imagers 142 or load imaging data 214 from memory 202. Computing device 200 may obtain renal denervation device data (1502). For example, computing device 200 may receive or retrieve renal denervation device data from additional equipment 152 and / or RDN device 300 or RDN device data 216 from memory 202.

[0140] Computing device 200 may determine, based on the imaging data, one or more recommended ablation locations (1504). For example, computing device 200 may execute one or more of ML model(s) 222 and / or computer vision model(s) 224 to determine the one or more recommended ablation locations.

[0141] Computing device 200 may determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations (1506). For example, computing device 200 may synchronize imaging data 214 and RDN device data 216 and, based on a location of one or more delivery elements during an ablation event as indicated by RDN device data 216, determine the one or more completed ablation locations.

[0142] Computing device 200 may generate a plurality of representations including a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations (1508). For example, computing device 200 may generate overlay 240 and / or 3D model 232 which may include such representations.

[0143] Computing device 200 may output, for display, the plurality of representations (1510). For example, computing device 200 may control display 206 and / or display device 110 to overlay overlay 240 on imaging data 214 and / or display 3D model 232.

[0144] In some examples, system 100 may include RDN device 300, wherein RDN device data 216 includes data from a data output of RDN device 300. In some examples, computing device 200 may determine, based on imaging data 214 and RDN device data 216, one or more failed ablation locations. In such examples, generating the output further includes generating corresponding representations of the one or more failed ablation locations.

[0145] In some examples, the output includes overlay 240 configured to be overlaid on imaging data 214. In some examples, system 100 comprises the display (e.g., display 206and / or display device 110), the display configured to display overlay 240 on imaging data 214.

[0146] In some examples, the output includes a three-dimensional model (e.g., 3D model 232). In some examples, the output includes at least one heatmap indicative of an amount of energy delivery to one or more respective locations.

[0147] In some examples, computing device 200 may automatically generate, based on imaging data 214 and RDN device data 216, an ablation map indicative of one or more completed ablation locations and store the ablation map in electronic patient record 236.

[0148] In some examples, computing device 200 may identify one or more features in imaging data 214. In some examples, computing device 200 may define, based on the identified one or more features, a plurality of vessel sections. In some examples, computing device 200 may determine, for each of the plurality of vessel sections, a corresponding local coordinate system. In some examples, computing device 200 may determine a location of at least one electrode in one of the plurality of vessel sections using the corresponding local coordinate system when renal denervation device output indicates an ablation event. In some examples, computing device 200 may map the corresponding local coordinate system to a global coordinate system. In some examples, computing device 200 may determine a location of one of the one or more completed ablations based on the mapping.

[0149] In some examples, computing device 200 may, as part of determining the one or more recommended ablation locations, execute one or more ML model(s) 222. The medical system of claim 10, wherein the one or more ML model(s) 222 are trained based on at least one of previous imaging data, previous ablation data, or previous patient demographic data. In some examples, the previous ablation data includes a plurality of ablation techniques, a plurality of device types, a plurality of patient types, and outcome data associated with previous ablation procedures. In some examples, at least one of the previous ablation data, or previous patient demographic data is generated by executing a natural language processing application on content of a plurality of electronic patient records. In some examples, each of the plurality of patient types is defined by at least one of an anatomical feature or medical history.

[0150] In some examples, computing device 200 may execute at least one of a computer vision model (e.g., of computer vision model(s) 224) or a machine learning model (e.g., of ML model(s) 222) to map, based on imaging data 214, vessels of the patient including at least one branch and at least one diameter of a vessel, wherein the output further comprises the atleast one diameter. In some examples, he medical system of claim 1, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to determine, based on the imaging data, one or more calcification locations, wherein the output further comprises corresponding representations of each of the one or more calcification locations.

[0151] In some examples, determining the one or more recommended ablation locations is further based on processed patient data, computing device 200 may obtain electronic patient record 236 and execute a natural language processing application on content of electronic patient record 236 to generate the processed patient data. In some examples, the one or more recommended ablation locations are further based on at least one of learned successful past ablation procedures, myofascial release protocol, a diameter of an artery, or a presence of calcification.

[0152] FIG. 16 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of this disclosure. Machine learning model 1600 may be an example of ML model(s) 222, computer vision model(s) 224, and / or NLP model(s) 228. Machine learning model 1600 may be an example of a deep learning model, or deep learning algorithm, trained to determine recommended ablation locations. One or more of computing device 150, server 160, and / or other device may train, store, and / or utilize machine learning model 1600, but other devices of system 100 may apply inputs to machine learning model 1600 in some examples. In some examples, other types of machine learning and deep learning models or algorithms may be utilized in other examples. For example, a convolutional neural network model of ResNet-18 may be used. Some non-limiting examples of models that may be used for transfer learning include AlexNet, VGGNet, GoogleNet, ResNet50, or DenseNet, etc. Some non-limiting examples of machine learning techniques include Support Vector Machines, K-Nearest Neighbor algorithm, and Multi-layer Perceptron.

[0153] As shown in the example of FIG. 16, machine learning model 1600 may include three types of layers. These three types of layers include input layer 1602, hidden layers 1604, and output layer 1606. Output layer 1606 comprises the output from the transfer function 1605 of output layer 1606. Input layer 1602 represents each of the input values XI through X4 provided to machine learning model 1600. In some examples, the input values may include any of the values input into the machine learning model, as described above. For example, the input values may include imaging data 214, as described above. In addition, insome examples input values of machine learning model 1600 may include additional data, such as other data that may be collected by or stored in system 100, such as data from electronic patient record 236, which may be processed by NLP model(s) 228.

[0154] Each of the input values for each node in the input layer 1602 is provided to each node of a first layer of hidden layers 1604. In the example of FIG. 16, hidden layers 1604 include two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater number of nodes may be used in other examples. Each input from input layer 1602 is multiplied by a weight and then summed at each node of hidden layers 1604. During training of machine learning model 1600, the weights for each input are adjusted to establish a relationship between imaging data 214 and appropriate locations represented in imaging data 214 for future ablations. In some examples, one hidden layer may be incorporated into machine learning model 1600, or three or more hidden layers may be incorporated into machine learning model 1600, where each layer includes the same or different number of nodes.

[0155] The result of each node within hidden layers 1604 is applied to the transfer function of output layer 1606. The transfer function may be linear or non-linear, depending on the number of layers within machine learning model 1600. Example non-linear transfer functions may be a sigmoid function or a rectifier function. The output 1607 of the transfer function may be a classification that any particular spot within the vasculature of the patient depicted in imaging data 214 is (or is not) appropriate (or more or less appropriate) for a future ablation.

[0156] As shown in the example above, by applying machine learning model 1600 to input data such as imaging data 214, processing circuitry 204 is able to determine features in imaging data 214 and / or one or more recommended ablation locations. Processing circuitry 204 may utilize such features to determine a local coordinate system, to map the local coordinate system to a global coordinate system, and / or to generate representations of the one or more recommended ablation locations. Processing circuitry 204 may control display 206 to display such representations. As such, processing circuitry 204 may guide a clinician during an ablation procedure.

[0157] FIG. 17 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of this disclosure. Process 1770 may be used to train ML model(s) 222 or machine learning model 1600. A machine learning model 1774 (which may be an example of machine learning model 1600) may beimplemented using any number of models for supervised and / or reinforcement learning, such as but not limited to, an artificial neural network, a decision tree, naive Bayes network, support vector machine, or k-nearest neighbor model, CNN, RNN, LSTM, ensemble network, to name only a few examples.

[0158] In some examples, one or more of computing device 150, server 160, and / or another device initially trains machine learning model 1774 based on a corpus of training data 1772. Training data 1772 may include, for example, previous imaging data of the current patient, previous imaging data of other patients, previous ablation data, previous patient demographic data, and / or the like. Previous ablation data, for example, may include a plurality of ablation techniques, a plurality of ablation device types, a plurality of patient types, and / or outcome data associated with previous ablation procedures using such ablation techniques and device types on such patient types. In some examples, the previous ablation data and / or previous patient demographic data may be generated by executing a natural language processing application on content of a plurality of electronic patient records to automatically extract relevant nor desired training data.

[0159] For example, by using an NLP model, computing device 200 may capture potentially cofounding, non-anatomical conditions or factors, which may be useful in determining a recommended ablation location. For example, a medical chart of a patient may include details of such conditions or factors that are indicative of a generalized high level of sympathetic overactivity (e.g., increased heart rate, increased blood pressure, increased respiration, etc.) which may indicate more robust ablations are required than would be suggested by anatomy alone. Computing device 200 may use the NLP model to capture such details. In such an example, the machine learning model may analyze underlying characteristics associated with the patient, rather than just anatomical factors, when determining recommended ablation locations.

[0160] In some examples, training data 1772 may include annotations identifying features and / or recommended ablation locations in imaging data of training data 1772. Training data 1772 may include data from past medical procedures performed on a plurality of patients having different patient conditions, different prior medical procedures, annotations or tags, other training data mentioned herein, and / or the like.

[0161] While training machine learning model 1774, processing circuitry of system 100 may compare 1776 a prediction or classification with a target output 1778. Processing circuitry 204 may utilize an error signal from the comparison to train (learning / training 880)machine learning model 1774. Processing circuitry 204 may generate machine learning model weights or other modifications which processing circuitry 204 may use to modify machine learning model 1774. For examples, processing circuitry 204 may modify the weights of machine learning model 1774 based on the learning / training 1780. For example, one or more of computing device 150, server 160, and / or another device, may, for each training instance in training data 1772, modify, based on training data 1772, the manner in which features and / or recommended ablation locations are determined.

[0162] The techniques discussed herein may be used in any combination or alone.

[0163] While many of the techniques described herein are attributed to processing circuitry 204, in some examples, such techniques may be performed by server 160, imager 140, additional imager(s) 142, additional equipment 152, other computing devices not shown in FIG. 1, or any combination thereof. Furthermore, while many of the techniques described herein are attributed to display 206, such techniques may be performed by display device 110, other display devices not shown in FIGS. 1 or 2, or any combination thereof.

[0164] The techniques described in this disclosure may be implemented, at least in part, in hardware, software, firmware or any combination thereof. For example, various aspects of the described techniques may be implemented within one or more processors or processing circuitry, including one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuitry, as well as any combinations of such components. The terms “controller”, “processor”, or “processing circuitry” may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent circuitry. A control unit comprising hardware may also perform one or more of the techniques of this disclosure. Such hardware, software, and firmware may be implemented within the same device or within separate devices to support the various operations and functions described in this disclosure. In addition, any of the described units, circuits or components may be implemented together or separately as discrete but interoperable logic devices. Depiction of different features as circuits or units is intended to highlight different functional aspects and does not necessarily imply that such circuits or units must be realized by separate hardware or software components. Rather, functionality associated with one or more circuits or units may be performed by separate hardware or software components or integrated within common or separate hardware or software components.

[0165] The techniques described in this disclosure may also be embodied or encoded in a computer-readable medium, such as a computer-readable storage medium, containing instructions. Instructions embedded or encoded in a computer-readable storage medium may cause a programmable processor, or other processor, to perform the method, e.g., when the instructions are executed. Computer readable storage media may include random access memory (RAM), read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), or electronically erasable programmable read only memory (EEPROM), or other computer readable media.

[0166] This disclosure includes the following non-limiting examples.

[0167] Example 1 A. A medical system comprising: memory configured to store imaging data and renal denervation device data; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the imaging data of a patient; obtain the renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generate a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and output, for display, the plurality of representations.

[0168] Example 2A. The medical system of example 1 A, further comprising the renal denervation device, wherein the renal denervation device data comprises data from a data output of the renal denervation device.

[0169] Example 3A. The medical system of example 1 A or example 2A, wherein the processing circuitry is further configured to: determine, based on the imaging data and the renal denervation device data, one or more failed ablation locations, wherein generating the output further comprises generating corresponding representations of the one or more failed ablation locations.

[0170] Example 4A. The medical system of any of examples 1 A-3A, wherein the output comprises an overlay configured to be overlaid on the imaging data.

[0171] Example 5A. The medical system of example 4A, further comprising the display, the display configured to display the overlay on the imaging data.

[0172] Example 6A. The medical system of any of examples 1 A-5A, wherein the output comprises a three-dimensional model.

[0173] Example 7A. The medical system of any of examples 1 A-6A, wherein the output comprises at least one heatmap indicative of an amount of energy delivery to one or more respective locations.

[0174] Example 8A. The medical system of any of examples 1 A-7A, wherein the processing circuitry is further configured to: automatically generate, based on the imaging data and the renal denervation device data, an ablation map indicative of one or more completed ablation locations; and store the ablation map in an electronic patient record.

[0175] Example 9A. The medical system of any of examples 1 A-8A, wherein the processing circuitry is further configured to: identify one or more features in the imaging data; define, based on the identified one or more features, a plurality of vessel sections; determine, for each of the plurality of vessel sections, a corresponding local coordinate system; determine a location of at least one electrode in one of the plurality of vessel sections using the corresponding local coordinate system when renal denervation device output indicates an ablation event; map the corresponding local coordinate system to a global coordinate system; and determine a location of one of the one or more completed ablations based on the mapping.

[0176] Example 10A. The medical system of any of examples 1A-9A, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is configured to execute one or more machine learning models.

[0177] Example 11 A. The medical system of example 10 A, wherein the one or more machine learning models are trained based on at least one of previous imaging data, previous ablation data, or previous patient demographic data.

[0178] Example 12A. The medical system of example 11 A, wherein the previous ablation data comprises a plurality of ablation techniques, a plurality of device types, a plurality of patient types, and outcome data associated with previous ablation procedures.

[0179] Example 13A. The medical system of any of examples 10A-12A, wherein at least one of the previous ablation data, or previous patient demographic data is generated by executing a natural language processing application on content of a plurality of electronic patient records.

[0180] Example 14A. The medical system of example 13A, wherein each of the plurality of patient types is defined by at least one of an anatomical feature or medical history.

[0181] Example 15A. The medical system of any of examples 1A-14A, wherein the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to map, based on the imaging data, vessels of the patientincluding at least one branch and at least one diameter of a vessel, wherein the output further comprises the at least one diameter.

[0182] Example 16A. The medical system of any of examples 1A-15A, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to determine, based on the imaging data, one or more calcification locations, wherein the output further comprises corresponding representations of each of the one or more calcification locations.

[0183] Example 17A. The medical system of examples 1A-16A, wherein determining the one or more recommended ablation locations is further based on processed patient data, and wherein the processing circuitry is further configured to: obtain an electronic patient record; and execute a natural language processing application on content of the electronic patient record to generate the processed patient data.

[0184] Example 18A. The medical system of any of examples 1A-17A, wherein the one or more recommended ablation locations are further based on at least one of learned successful past ablation procedures, myofascial release protocol, a diameter of an artery, or a presence of calcification.

[0185] Example 19A. A method comprising: obtaining imaging data of a patient; obtaining renal denervation device data; determining, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

[0186] Example 20A. A non-transitory computer-readable storage medium storing instructions, which, when executed, cause processing circuitry to: obtain imaging data of a patient; obtain renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one ormore completed ablation locations; and outputting, for display, the plurality of representations.

[0187] Various examples have been described. These and other examples are within the scope of the following claims. Further disclosed herein is the subject-matter of the following clause:1. A medical system comprising: memory configured to store imaging data and renal denervation device data; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the imaging data of a patient; obtain the renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generate a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and output, for display, the plurality of representations.2. The medical system of clause 1, wherein the processing circuitry is further configured to: determine, based on the imaging data and the renal denervation device data, one or more failed ablation locations, wherein generating the output further comprises generating corresponding representations of the one or more failed ablation locations.3. The medical system of clause 1 or clause 2, wherein the output comprises at least one of an overlay configured to be overlaid on the imaging data, a three-dimensional model, or at least one heatmap indicative of an amount of energy delivery to one or more respective locations.4. The medical system of any of clauses 1-3, wherein the processing circuitry is further configured to: automatically generate, based on the imaging data and the renal denervation device data, an ablation map indicative of one or more completed ablation locations; and store the ablation map in an electronic patient record.5. The medical system of any of clauses 1-4, wherein the processing circuitry is further configured to: identify one or more features in the imaging data; define, based on the identified one or more features, a plurality of vessel sections; determine, for each of the plurality of vessel sections, a corresponding local coordinate system; determine a location of at least one electrode in one of the plurality of vessel sections using the corresponding local coordinate system when renal denervation device output indicates an ablation event; map the corresponding local coordinate system to a global coordinate system; and determine a location of one of the one or more completed ablations based on the mapping.6. The medical system of any of clauses 1-5, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is configured to execute one or more machine learning models.7. The medical system of clause 6, wherein the one or more machine learning models are trained based on at least one of previous imaging data, previous ablation data, or previous patient demographic data.8. The medical system of clause 7, wherein the previous ablation data comprises a plurality of ablation techniques, a plurality of device types, a plurality of patient types, and outcome data associated with previous ablation procedures, wherein each of the plurality of patient types is defined by at least one of an anatomical feature or medical history.9. The medical system of clause 7, wherein at least one of the previous ablation data, or previous patient demographic data is generated by executing a natural language processing application on content of a plurality of electronic patient records.10. The medical system of any of clauses 1-9, wherein the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to map, based on the imaging data, vessels of the patient including at least one branch and at least one diameter of a vessel, wherein the output further comprises the at least one diameter.11. The medical system of any of clauses 1-10, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to determine, based on the imaging data, one or more calcification locations, wherein the output further comprises corresponding representations of each of the one or more calcification locations.12. The medical system of any of clauses 1-11, wherein determining the one or more recommended ablation locations is further based on processed patient data, and wherein the processing circuitry is further configured to: obtain an electronic patient record; and execute a natural language processing application on content of the electronic patient record to generate the processed patient data.13. The medical system of any of clauses 1-12, wherein the one or more recommended ablation locations are further based on at least one of learned successful past ablation procedures, myofascial release protocol, a diameter of an artery, or a presence of calcification.14. A method comprising: obtaining imaging data of a patient; obtaining renal denervation device data; determining, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations;generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.15. A non-transitory computer-readable storage medium storing instructions, which, when executed, cause processing circuitry to: obtain imaging data of a patient; obtain renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

Claims

CLAIMS1. A medical system comprising: memory configured to store imaging data and renal denervation device data; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the imaging data of a patient; obtain the renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determine, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generate a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and output, for display, the plurality of representations.

2. The medical system of claim 1, wherein the processing circuitry is further configured to: determine, based on the imaging data and the renal denervation device data, one or more failed ablation locations, wherein generating the output further comprises generating corresponding representations of the one or more failed ablation locations.

3. The medical system of claim 1 or claim 2, wherein the output comprises at least one of an overlay configured to be overlaid on the imaging data, a three-dimensional model, or at least one heatmap indicative of an amount of energy delivery to one or more respective locations.

4. The medical system of any of claims 1-3, wherein the processing circuitry is further configured to:automatically generate, based on the imaging data and the renal denervation device data, an ablation map indicative of one or more completed ablation locations; and store the ablation map in an electronic patient record.

5. The medical system of any of claims 1-4, wherein the processing circuitry is further configured to: identify one or more features in the imaging data; define, based on the identified one or more features, a plurality of vessel sections; determine, for each of the plurality of vessel sections, a corresponding local coordinate system; determine a location of at least one electrode in one of the plurality of vessel sections using the corresponding local coordinate system when renal denervation device output indicates an ablation event; map the corresponding local coordinate system to a global coordinate system; and determine a location of one of the one or more completed ablations based on the mapping.

6. The medical system of any of claims 1-5, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is configured to execute one or more machine learning models.

7. The medical system of claim 6, wherein the one or more machine learning models are trained based on at least one of previous imaging data, previous ablation data, or previous patient demographic data.

8. The medical system of claim 7, wherein the previous ablation data comprises a plurality of ablation techniques, a plurality of device types, a plurality of patient types, and outcome data associated with previous ablation procedures, wherein each of the plurality of patient types is defined by at least one of an anatomical feature or medical history.

9. The medical system of claim 7, wherein at least one of the previous ablation data, or previous patient demographic data is generated by executing a natural language processing application on content of a plurality of electronic patient records.

10. The medical system of any of claims 1-9, wherein the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to map, based on the imaging data, vessels of the patient including at least one branch and at least one diameter of a vessel, wherein the output further comprises the at least one diameter.

11. The medical system of any of claims 1-10, wherein as part of determining the one or more recommended ablation locations, the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to determine, based on the imaging data, one or more calcification locations, wherein the output further comprises corresponding representations of each of the one or more calcification locations.

12. The medical system of any of claims 1-11, wherein determining the one or more recommended ablation locations is further based on processed patient data, and wherein the processing circuitry is further configured to: obtain an electronic patient record; and execute a natural language processing application on content of the electronic patient record to generate the processed patient data.

13. The medical system of any of claims 1-12, wherein the one or more recommended ablation locations are further based on at least one of learned successful past ablation procedures, myofascial release protocol, a diameter of an artery, or a presence of calcification.

14. A method comprising: obtaining imaging data of a patient; obtaining renal denervation device data; determining, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

15. A non-transitory computer-readable storage medium storing instructions, which, when executed, cause processing circuitry to: obtain imaging data of a patient; obtain renal denervation device data; determine, based on the imaging data, one or more recommended ablation locations; determining, based on the imaging data and the renal denervation device data, one or more completed ablation locations; generating a plurality of representations comprising a corresponding representation of each of the one or more recommended ablation locations and a corresponding representation for each of the one or more completed ablation locations; and outputting, for display, the plurality of representations.

Images