Ablation visualization system

Abstract

Example systems and techniques that can determine at least one treatment strategy for a lesion are disclosed. An example system can include a memory configured to store a plurality of treatment paths and a processing circuit communicatively coupled to the memory. The processing circuit can be configured to determine the plurality of treatment paths. The processing circuit can be configured to determine, for each respective treatment path of the plurality of treatment paths, 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 circuit can be configured to output the plurality of treatment paths and, for each respective treatment path, 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 display.

Description

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

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

[0003] During medical procedures, clinicians may use one or more imaging systems to visualize a patient's internal anatomy. These systems can display anatomical structures, medical devices, and more, and can be used to diagnose patient conditions or guide clinicians in moving devices such as medical instruments to their intended locations within the patient's body. Imaging systems can use sensors to capture video or still images that can be displayed during medical procedures. These systems include fluoroscopy systems, angiography systems, ultrasound imaging systems, computed tomography (CT) systems, magnetic resonance imaging (MRI) systems, isocentric C-arm fluoroscopy systems, positron emission tomography (PET) systems, intravascular ultrasound (IVUS), optical coherence tomography (OCT), near-infrared spectroscopy (NIRS), and other imaging systems.

[0004] Ablation procedures are medical procedures that ablate tissues within a patient's body. For example, in the renal denervation (RDN) procedure, nerves within or surrounding the renal artery are ablated using techniques such as radiofrequency pulses or ultrasound energy to treat drug-resistant hypertension. Summary of the Invention

[0005] Generally, this disclosure relates to various technologies and medical systems for facilitating decision-making by clinicians through enhanced imaging using images captured during (and / or prior to) ablation procedures, such as RDN procedures, and, in some examples, providing clinical guidance to clinicians for use during such medical procedures. The technologies and systems can also capture procedure-related information and prepare medical procedure reports based on such information.

[0006] Renal denervation procedures are generally considered to be slower and longer than desired. For example, procedure time can be prolonged by over-ablation sites to ensure adequate ablation coverage. Suboptimal deployment and uncoordinated positioning of delivery elements (such as electrodes) may occur during the ablation procedure. Therefore, it may be desirable to provide systems and techniques for reducing the time spent performing ablation procedures while maintaining or increasing their effectiveness.

[0007] Currently, the lack of some form of visual ablation tracking can lead to frustration during ablation procedures. For example, a patient's anatomy can shift as the patient moves during the procedure. This can result in clinicians being unaware of the location where ablation has been performed and / or how far the ablation device has moved (if it has) since a previous ablation was performed at the previous location, as shown in the displayed image data. This can cause clinicians to expect to review images taken during the delivery of previous ablations, potentially increasing the procedure's duration. Additionally or alternatively, this situation may lead clinicians to perform further, and potentially unnecessary, ablations to ensure the site has been ablated, and / or to question whether the procedure was performed optimally.

[0008] According to the technology disclosed herein, the system can provide computerized tracking and analysis. Such a system may include machine learning and / or artificial intelligence analysis for protocol optimization. As used herein, the term "machine learning model" may include a machine learning model or an artificial intelligence model. The system can support clinicians before, during, and / or after an ablation protocol. The system can recommend ablation sites and track the ablation sites upon completion of ablation. In some examples, the system can automatically generate an ablation map of the completed ablation site for documentation of ablation protocols, such as RDN protocols.

[0009] The technology disclosed herein can improve the speed of ablation procedures. It can guide clinicians to optimize ablation coverage along key areas of blood vessels and reduce the likelihood of re-ablation in already ablated areas, where clinicians might otherwise perform additional ablation to ensure coverage when unsure of the ablation location. The technology disclosed herein can improve procedural consistency and efficacy by accurately targeting the tissue to be ablated.

[0010] The techniques disclosed herein can also provide accurate and concise documentation of clinical procedures. Clinicians have expressed an expectation for review of documentation indicating the location of tissue ablation to confirm the success of the procedure. Current methods for meeting this expectation are approximate, and review and analysis can be relatively difficult and / or slow. The techniques disclosed herein can greatly simplify review by presenting information visually and instantaneously (including during the procedure), and / or by preparing ablation procedure documentation based on information captured during the RDN procedure.

[0011] The techniques disclosed herein may include analytical and data processing tools that can be used to analyze ablation protocols, thereby allowing for simplified and detailed comparisons between ablation and treatment efficacy. In some examples, such tools may include one or more machine learning models for analysis and real-time guidance, or may preprocess information for one or more machine learning models used for analysis and real-time guidance.

[0012] In one example, a medical system includes: a 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: acquire imaging data of a patient; acquire renal denervation device data; determine one or more recommended ablation sites based on the imaging data; determine one or more completed ablation sites based on the imaging data and the renal denervation device data; generate a plurality of representations including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and output the plurality of representations for display.

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

[0014] In another example, a non-transitory computer-readable medium stores instructions that, when executed, cause processing circuitry to: acquire imaging data of a patient; acquire renal denervation device data; determine one or more recommended ablation sites based on the imaging data; determine one or more completed ablation sites based on the imaging data and the renal denervation device data; generate a plurality of representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and output the plurality of representations for display.

[0015] This document further discloses an example system and technique for determining at least one treatment strategy for a lesion, wherein the example system may include a 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 corresponding treatment pathway, one or more validity indicators of a corresponding prediction, one or more risks of a corresponding prediction, and a corresponding confidence level associated with at least one of the corresponding predictions, and wherein the processing circuitry may be configured to output the plurality of treatment pathways and the validity indicators of one or more corresponding predictions for each corresponding treatment pathway, the risks of one or more corresponding predictions, and the corresponding confidence level associated with at least one of the corresponding predictions for display.

[0016] These and other aspects of this disclosure will become apparent from the following detailed description. However, in no event should the foregoing summary be construed as a limitation on the claimed subject matter, which is defined solely by the appended claims.

[0017] The present invention is intended to provide an overview of the subject matter described herein. It is not intended to provide an exclusive or exhaustive interpretation of the devices and methods described in detail in the following drawings and description. Further details of one or more examples are set forth in the following drawings and description. Attached Figure Description

[0018] Figure 1 This is a schematic perspective view of an example system for performing ablation procedures according to one or more aspects of this disclosure.

[0019] Figure 2 This is a block diagram illustrating an example of a computing device according to one or more aspects of this disclosure.

[0020] Figure 3 This is a block diagram of an example energy generation apparatus according to one or more aspects of this disclosure.

[0021] Figure 4 These are conceptual diagrams illustrating example anatomy and medical devices for RDN protocols according to one or more aspects of this disclosure.

[0022] Figure 5 This is a conceptual diagram illustrating an example user interface that may be displayed during RDN procedures according to one or more aspects of this disclosure.

[0023] Figure 6 This is a conceptual diagram illustrating an example of the characteristics of tracking during RDN procedures according to one or more aspects of this disclosure.

[0024] Figure 7 This is a conceptual diagram illustrating an example of a local coordinate system and a cross-section of a blood vessel according to one or more aspects of this disclosure.

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

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

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

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

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

[0030] Figures 13A to 13B This is a flowchart illustrating an example ablation visualization technique of this disclosure.

[0031] Figure 14 This is a flowchart illustrating an example ablation visualization technique of this disclosure.

[0032] Figure 15 This is a flowchart illustrating an example ablation visualization technique of this disclosure.

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

[0034] Figure 17 This is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of this disclosure. Detailed Implementation

[0035] Imaging systems can be used to assist clinicians in medical procedures such as ablation procedures. For example, imaging systems can be used to visualize a patient's vascular system and the location of any medical devices located within the patient's vascular system. While this article primarily describes a patient's vascular system, the imaging systems described herein can be used for other medical purposes and are not limited to cardiovascular purposes.

[0036] Imaging systems can 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 superimposed on it. In some examples, imaging data may be stored for future reference, such as in an electronic patient record. In some examples, the imaging data can be used to construct a three-dimensional (3D) model of the patient's vascular system, which may be useful for clinicians attempting to view the vascular system in 3D.

[0037] Imaging data may include fluorescence fluoroscopy imaging data, fluorescence fluoroscopy imaging data using contrast agents, CT imaging data, X-ray imaging data, IVUS imaging data, OCT imaging data, NIRS imaging data, MRI imaging data, ultrasound imaging data, angiography imaging data, or other imaging data.

[0038] This disclosure describes a system and techniques for guiding clinicians through ablation procedures, such as RDN procedures. This system can acquire imaging data and renal denervation device data. The system can determine one or more recommended ablation sites based on the imaging data, and one or more completed ablation sites based on the imaging data and renal denervation device data. The system can generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites, and output multiple representations for display.

[0039] Figure 1 This is a schematic perspective view of an example 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 an ablation procedure, including determining a recommended ablation site, determining the completed ablation site, and generating representations of the recommended and completed ablation sites. The representation may be overlaid on imaging data and / or represented in a 3D model of the patient's vascular system. Medical system 100 may also provide a system for recording the ablation procedure. Such a system can reduce the time of the ablation procedure, thereby reducing the amount of contrast agent the patient may be exposed to, and can improve patient outcomes. Such a system can also reduce the amount of time clinicians spend recording various ablation procedures.

[0040] System 100 includes a display device 110, a workbench 120, a device tracking system 121, an imager 140 (which may be an angiography and / or fluoroscopy imager), an additional imager 142, a computing device 150, additional equipment 152, a server 160, and a network 156. System 100 may be an example of a system for use in a catheterization lab, surgical ward, or other healthcare setting. For simplicity, the environment in which system 100 is used is referred to hereinafter as a Cathlab. In some examples, system 100 may include other devices. In some examples, system 100 may be used during a diagnostic session to diagnose a patient's problem 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 a Cath lab during medical procedures. Computing device 150 may include, for example, off-the-shelf devices such as laptops, desktop computers, tablets, smartphones, or other similar devices. In other examples, computing device 150 may be a dedicated computing device, such as a computing device specifically designed for use 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, power supply, or any other accessories and peripheral devices associated with or forming part of system 100. In some examples, computing device 150 may perform various control functions concerning imager 140, additional imager 1042, display device 110, additional equipment 152, etc. Computing device 150 may be communicatively coupled to device tracking system 121, one or more of imager 140, additional imager 142, additional equipment 152, display device 110, server 160, and / or network 156.

[0043] While this document describes multiple features as belonging to computing device 150, in some examples, features belonging to computing device 150 may be performed by processing circuitry of any of the 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 combination thereof. In some examples, the 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 the processing circuitry of computing device 150 may be performed by remotely residing processing circuitry (such as one or more cloud servers or processors). For the purposes of this discussion, such processing circuitry may be considered part of computing device 150.

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

[0045] As discussed above, imager 140 may be a fluoroscopy imager and may image portions of a patient's body during or before medical procedures to visualize the patient's anatomy and / or medical devices such as add-on device 152. Add-on imager 142 may also be configured to image portions of the patient's body, such as the patient's vascular system. Add-on imager 142 may be a device other than a fluoroscopy apparatus. For example, the add-on imager may be any other type of imaging device, such as a CT apparatus, IVUS apparatus, OCT apparatus, NIRS apparatus, MRI apparatus, PET apparatus, etc.

[0046] The computing device 150 can be configured to determine one or more recommended ablation sites based on imaging data from the imager 140 and / or the additional imager 142. For example, the computing device 150 can execute one or more machine learning models and / or computer vision algorithms to determine the recommended ablation sites.

[0047] The computing device 150 can be configured to determine one or more completed ablation sites based on imaging data and renal denervation device data. For example, the computing device 150 can obtain data indicating an ablation event from the renal denervation device (e.g., attached to accessory 152) and time-synchronize the data indicating the ablation event with the location of the delivery element in the imaging data to determine the completed ablation site, since the ablation event occurs at the location of the delivery element when the ablation event occurs.

[0048] The computing device 150 can be configured to generate representations of any recommended ablation sites and any completed ablation sites, and is configured to control the display device 110 to display such representations, such as in a stack over imaging data and / or in a 3D model of the patient’s vascular system.

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

[0050] Additional equipment 152 may include medical devices configured for use during medical procedures, such as ablation procedures, including but not limited to guiding 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 142. In some examples, display device 110 may be configured to display representations of recommended ablation sites and completed ablation sites superimposed on the imaging data from imager 140 and / or additional imager 142. In some examples, display device 110 may be configured to display a 3D model of the patient's vascular system, including representations of recommended ablation sites and completed ablation sites, as an alternative to or supplement to the captured imaging data. In some examples, display device 110 may be configured to display various user interfaces disclosed herein. Display device 110 may be configured to display any other content discussed in this disclosure as being displayed.

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

[0053] Device tracking system 121 may include radio frequency identification (RFID), near field communication (NFC), battery-powered sensors, triangulation technology, and / or an EM field generator that can be used to generate an electromagnetic (EM) field during medical procedures. Such technologies can be used to track the location of one or more devices (e.g., medical devices) within a patient's body during medical procedures. For example, the device tracking system can track the location of devices by tracking sensors attached to or incorporated into those devices (e.g., devices attached to attachment 152). In some examples, device tracking system 121 can function as a charging pad that wirelessly charges various sensors that can be placed on or inside the patient, such as for monitoring patient parameters during medical procedures. Such sensors can communicate wirelessly with computing device 150. In this way, fewer wires may be present in the Cath lab than would otherwise be, reducing the risk of entanglement with the patient or clinicians moving around within the Cath lab. In some examples, a wired sensor (e.g., attachment 152) may be used, which can be connected to or disconnected from one or more devices of system 100 (such as computing device 150) via wires from the wired sensor.

[0054] Server 160 may be configured to store data obtained and / or determined or generated by computing device 150. In some examples, server 160 may be configured to perform technologies belonging to computing device 150. Server 160 may be communicatively coupled to computing device 150, for example, via wired, optical, or wireless communication and / or via 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. Server 160 may be configured to store patient data, electronic patient records, etc.

[0055] Figure 2 This is a block diagram illustrating an example of a computing device according to one or more aspects of this disclosure. The computing device 200 may be... Figure 1 Examples of computing devices 150, network 156, and / or server 160 may include workstations, desktop computers, laptop computers, servers, smartphones, tablets, dedicated computing devices, or any other computing devices capable of performing the techniques of this disclosure.

[0056] In some examples, computing device 200 can be configured to perform operations related to... Figure 1 The computing device 200 may include, for example, a memory 202, processing circuitry 204, a display 206, a network interface 208, an input device 210, or an output device 212, each of which may represent any of a plurality of instances of such a device within the computing system for ease of description.

[0057] Although processing circuit 204 appears Figure 2 In the computing device 200, however, in some examples, the features belonging to the processing circuit 204 may be from the computing device 150, the imager 140, the server 160, the network 156, or other computing devices. Figure 1 The processing circuitry of any of the other components may execute this. In some examples, one or more processors associated with the processing circuitry 204 in computing device 200 may span computing device 150, imager 140, server 160, network 156, or other computing devices. Figure 1 Any combination of other components distributed and shared. Additionally, in some examples, processing operations or other operations performed by processing circuitry 204 may be performed by one or more remotely residing processors (such as one or more cloud servers or processors), each of which may be considered part of computing device 200. Computing device 200 can be used to perform any of the techniques described in this disclosure and can be used alone or in combination with other components (such as computing device 150, imager 140, server 160, network 156, etc.). Figure 1 Other components, or components of a system that includes any or all of such devices, form all or part of a device or system configured to perform such technology.

[0058] The memory 202 of computing device 200 includes any non-transitory computer-readable storage medium for storing data or software that can be executed by processing circuitry 204 and control 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 processing circuitry 204 via a mass storage controller (not shown) and a communication bus (not shown).

[0059] While the description of computer-readable media herein refers to solid-state storage devices, those skilled in the art will understand that computer-readable storage media can be any available medium accessible by 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 storing information such as computer-readable instructions, data structures, program modules, or other data. For example, computer-readable storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state memory technologies, CD-ROM, DVD, Blu-ray or other optical storage devices, magnetic tape cassettes, magnetic tape, disk storage devices or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by computing device 200. In one or more examples, computer-readable storage media may be stored in the cloud or remote storage and accessed via at least one wired or wireless connection using any suitable one or more technologies.

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

[0061] User interface 218 may include one or more user interfaces, and processing circuitry 204 may output the one or more user interfaces for display by display 206 and / or display device 110. The content of user interface 218 may include, for example, the following information. Figures 4 to 9 The description may include a representation of the recommended ablation site and the completed ablation site in a stacked or 3D model of the patient's vascular system.

[0062] The memory 202 can store imaging data 214, RDN device data 216, electronic patient records 236, 3D models 232, overlays 240, ablation / coordinate data 234, and / or user profiles 238. Imaging data 214 can be stored during the patient's medical procedures by the imager 140 and / or the additional imager 142. Figure 1 The processing circuit 204 can acquire imaging data 214 from the imager 140 and / or the additional imager 142, and store the imaging data 214 in the memory 202.

[0063] Processing circuitry 204 can guide clinicians during ablation procedures using imaging data 214. For example, processing circuitry 204 can determine one or more recommended ablation sites based on imaging data 214, and determine one or more completed ablation sites based on imaging data 214 and RDN device data 216. Processing circuitry 204 can generate a stack 240 and / or a 3D model 232, which includes representations of recommended ablation sites and representations of completed ablation sites. Processing circuitry 204 can control display 206 to display stack 240 on the imaging data 214. Additionally or alternatively, processing circuitry 204 can control display 206 to display 3D model 232.

[0064] Stack 240 may include representations (e.g., visual indicators) of delivery elements, completed ablation sites, recommended ablation sites, failed ablation sites, etc. Such representations can distinguish not only what the representation indicates, but also 3D locations within two-dimensional (2D) space to assist clinicians. For example, the representation can distinguish between dorsal and ventral localization. The representation may include different shapes, colors, etc., which can help identify different types of representations. The following section discusses… Figures 4 to 9 Further description of the representation in this disclosure.

[0065] 3D model 232 may include 3D models, such as those of a patient's vascular system. Figures 8 to 9 The 3D models discussed. 3D model 232 may include identification of the location of the ablation catheter, the delivery elements of the ablation catheter, the ablation area, the recommended area for ablation, the location of failed ablation, etc.

[0066] RDN device data 216 may include devices configured to control ablation delivery elements (such as energy generation devices (see...) Figure 3 The information generated. For example, RDN device data 216 may include information related to the delivery of ablation energy by one or more delivery elements, including when the energy was delivered, the duration of the energy delivery, the magnitude of the energy delivery, the energy delivery graph, any error codes generated by the energy generation device, and the time associated with the generation of the error codes, etc.

[0067] The ablation / coordinate data 234 may include identification of the location of the ablation catheter, the delivery element of the ablation catheter, the ablation area, the recommended area to be ablated, and the failed ablation location. The ablation / coordinate data 234 may include coordinate information of a global coordinate system and one or more local coordinate systems, which can be used to appropriately map the location of the ablation catheter, the delivery element of the ablation catheter, the ablation area, the recommended area to be ablated, the failed ablation location, etc., to appropriate localization within the imaging data 214 for generating the overlay 240 and / or the 3D model 232.

[0068] The electronic patient record 236 may include information related to the current patient's medical history, such as spreadsheets, imaging data from previous procedures (including diagnostic procedures), etc. During or after the ablation procedure, the processing circuitry 204 may update the electronic patient record 236 to include information generated during the ablation procedure, such as imaging data 214, RDN device data 216, 3D model 232, and / or ablation / coordinate data 234.

[0069] Processing circuitry 204 can use information acquired during a medical procedure, such as imaging data 214, RDN device data 216, ablation / coordinate data 234, overlay 240, and / or 3D model 232, to automatically update the electronic patient record 236, eliminating the need for clinicians to manually input all relevant information into the electronic patient record 236. For example, processing circuitry 204 can automatically generate an ablation map indicating the completion of the ablation procedure at the end of the procedure (such as when the RDN device is powered off or when the clinician indicates the end of the procedure via an input device, such as in input device 210), and store the ablation map in the electronic patient record 236. User profile 238 can store user settings and / or preferences specific to a given clinician, as described later herein. Figure 13B Discussed.

[0070] The ML model 222 and / or computer vision model 224 can be trained using data collected from past medical procedures, such as previous imaging data, previous ablation data, and / or previous patient demographics. This data can come from multiple patients and / or the current patient. Previous ablation data can include various ablation techniques, device types, patient types, and outcome data associated with previous ablation procedures. In some examples, at least one of the previous ablation data or previous patient demographics is generated by performing a natural language processing model (e.g., in NLP model 228) on the contents of multiple electronic patient records. Therefore, the ML model 222 and computer vision model 224 can be trained on data from actual procedures to reflect actual treatment and actual outcomes from past medical procedures. Such models can be used to determine recommended ablation sites.

[0071] Potential machine learning or artificial intelligence techniques that can be used include Naive Bayes, k-means clustering, k-nearest neighbors, random forests, support vector machines, neural networks, linear regression, logistic regression, classification models, anomaly detection, convolutional neural networks (CNNs), object detection, natural language processing (NLP), face recognition, recommender systems, optical character recognition (OCR) for reading text and characters from other systems and / or screens, or any other similar techniques. Such models can be trained using batch gradient descent, stochastic gradient descent, mini-batch gradient descent, or any other similar techniques. The following section discusses... Figure 16 and Figure 17 Further discussion of example machine learning models.

[0072] Processing circuitry 204 can execute any user interface in user interface 218 to enable display 206 (and / or Figure 1 The display device 110 presents the UI in user interface 218 to one or more clinicians performing the ablation procedure. In some examples, user interface 218 may include overlay 240 and / or 3D model 232.

[0073] Processing circuitry 204 can capture real-time information from equipment such as imager 140, additional imager 142, and / or additional equipment 152 (e.g., RDN device). For example, computing device 150 can obtain fluoroscopic imaging from the real-time video feed output by imager 140 via network interface 208 (e.g., via High Definition Multimedia Interface (HDMI), Serial Digital Interface (SDI), Digital Vision Interface (DVI), optical interface, Internet Protocol Video, etc.).

[0074] The processing circuit 204 can track the real-time positioning of the delivery element (e.g., an electrode) within the patient's vascular system and can enhance visualization on fluorescence fluoroscopy images, such as those displayed on the display 206 and / or the display device 110.

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

[0076] Processing circuitry 204 can determine or calculate recommended future ablation sites. Processing circuitry 204 can visually communicate this information to clinicians in real time during the procedure, for example, via user interface 218 on a display. For instance, processing circuitry 204 can recommend the next ablation site during ablation at the current ablation site. Processing circuitry 204 can display 2D and / or 3D representations of anatomical structures (including any visual ablation indicators) on display 206 and / or display device 110.

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

[0078] In some examples, processing circuitry 204 can use 2D output to display persistent vascular output on display 206 and / or display device 110 (e.g., a representation of the vessel contour even when contrast agent has not been injected into the patient). For example, processing circuitry 204 can record the vessel diameter at multiple sampling points along the vessel segment during contrast agent injection. Continuous vascular output may include an approximate representation of the renal anatomy to always provide a more complete picture of the ablation map. Therefore, the techniques of this disclosure can reduce the amount of contrast agent that may need to be injected into the patient during RDN procedures.

[0079] In some examples, system 100 can 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 time windows (e.g., times during which no video is captured) and pausing the update process of any user interface in overlay 240, 3D model 232, and / or user interface 218, until a later time, such as when the capture of imaging data 214 resumes.

[0080] In some examples, processing circuitry 204 can save anatomical geometry and ablation data (coordinate and signal data) in a digital file for later review or further processing and / or analysis. For example, processing circuitry 204 can store ablation / coordinate data 234 in memory 202. In some examples, ablation / coordinate data 234 can be stored as image and / or video data. Processing circuitry 204 can use ablation / coordinate data 234 to update electronic patient record 236 to prepare an RDN protocol report. In some examples, processing circuitry 204 can transmit ablation / coordinate data 234 and / or any RDN protocol report to network 156 and / or server 160 (both in [location missing]). Figure 1 (in Chinese) for storage and / or other purposes.

[0081] During the peri-procedure period, and during the delivery of renal denervation energy, computing device 200 can output visual overlays (such as overlay 240) on a display showing imaging data 214 to guide clinicians in performing ablation procedures. Such visual overlays may include highlighting recommended sites for ablation, and may change color and / or provide a distinct representation of such sites when they have been successfully ablated. In some examples, the visual overlay may include a countdown clock for the recommended duration of ablation, and / or other such information that may be helpful to clinicians.

[0082] Following the procedure, computing device 200 can generate 2D images, 3D images, and / or 3D models of the renal artery tree (e.g., 3D model 232) showing completed and / or failed ablation sites, along with other relevant data (e.g., ablation duration, delivered energy) to document the ablation procedure. Computing device 200 can store such documentation in an electronic patient record 236. In some examples, computing device 200 can collect additional data, for example, from imager 140, other imagers 142, and / or other equipment 152, which can be used for product enhancement or new product development (including algorithms), ongoing research, insurance claim 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 a clinician, such as via user interface 218, and then overlay 240 onto imaging data 214 for the clinician to view. In some examples, the recommended ablation sites of overlay 240 and / or 3D model 232 may be represented on the imaging data as x-shapes or circles at specific recommended sites. In some examples, the circles may be colored, such as white. When ablation is complete, such x-shapes or circles may be changed to another representation (e.g., a square) and / or changed to another color (e.g., green). In some examples, computing device 200 may obtain energy delivery data from the ablation device, such as RDN device data 216, to record how much energy was delivered at each ablation site. In some examples, computing device 200 may execute computer vision model 224 to track the delivery elements of the ablation catheter to identify the location where ablation occurs. In some examples, computing device 200 may automatically generate a report of the ablation protocol during and / or after protocol completion. The computing device 200 can store the report in the electronic patient record 236 and / or send the report to the server 160 via the 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 combinations 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 circuitry refers to circuitry that provides specific functionality and is pre-configured for executable operations. Programmable circuitry refers to circuitry that can be programmed to perform various tasks and provide flexible functionality in executable operations. For example, programmable circuitry may execute software or firmware that causes the programmable circuitry to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuitry may execute software instructions (e.g., receive or output parameters), but the type of operation performed by fixed-function circuitry is generally immutable. In some examples, one or more units within the unit may be different 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 circuits. Therefore, the term "processing circuit 204" as used herein may refer to one or more processors having any of the foregoing processors or processing structures, or any other structure suitable for implementing the techniques described herein. Furthermore, in some aspects, the functionality described herein may be provided within dedicated hardware or software modules configured for encoding and decoding, or incorporated into combined codecs. Additionally, these techniques may be fully implemented in one or more circuit or logic elements.

[0086] Display 206 may be touch-sensitive or voice-activated, enabling it to function as both an input and output device. Alternatively, a keyboard (not shown), mouse (not shown), joystick (not shown), or other data input devices (e.g., input device 210) may be used. In some examples, display 206 may include a virtual reality and / or augmented reality head-mounted device. In some examples, display 206 may include a holographic device.

[0087] Network interface 208 may be adapted to connect to a network (e.g., network 156), such as a local area network (LAN), wide area network (WAN), wireless mobile network, Bluetooth network, or the Internet, including wired or wireless networks. 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 142 via network interface 208 during an ablation procedure. Computing device 200 may interact with server 160 via network interface 208. Computing device 200 may receive updates to its software (e.g., application 215) via network interface 208. Computing device 200 may also display a notification on display 206 that a software update is available.

[0088] Input device 210 may include any device that enables a user to interact with computing device 200, such as, for example, a mouse, joystick, keyboard, foot pedal, touch screen, augmented reality input device that receives input such as hand gestures or body movements, or voice interface.

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

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

[0091] Figure 3 This is a block diagram of an example RDN device according to one or more aspects of this disclosure. Figure 3 The RDN device 300 can be an add-on device 152 ( Figure 1 Examples of ablation devices. RDN device 300 can be an energy-generating device configured for use with an ablation catheter using electrodes as delivery elements. While RDN device 300 can be configured for use with an ablation catheter using electrodes as delivery elements, the technology disclosed herein is more broadly applicable to any RDN device that includes controlling the delivery element to perform ablation. Figure 3 As shown, the RDN device 300 may include a positive terminal (+) 312, a negative terminal (-) 314, an energy generator 302, a processing circuit 304, a user interface 306, a storage device 308, and a network interface 320.

[0092] The positive terminal 312 may be coupled to the energy generator 302 and may be configured to be attached to one or more conductors of the ablation catheter (not shown) to conduct electricity between the energy generator 302 and one or more conductors. The negative terminal 314 may be coupled to the energy generator 302 (or alternatively grounded) and may be configured to be attached to one or more conductors of the ablation catheter to conduct electricity between one or more conductors and the energy generator 302. The energy generator 302 may be configured to provide radiofrequency electrical pulses to one or more conductors of the ablation catheter to perform electroporation or other ablation procedures on tissue within a patient's blood vessels. Although in Figure 3 The example shown is a single energy generator, but the RDN device 300 is not limited to this. For example, the RDN device 300 may include multiple energy generators, each capable of generating ablation signals in parallel. In some examples, the RDN device 300 may include different types of energy generators, such as radio frequency energy generators (such as RDN generators), pulsed field energy generators, and / or cryogenic energy generators or thermal energy generators.

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

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

[0095] User interface 306 may include buttons or a 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 show information about the ongoing ablation therapy session, such as patient parameters or other information that may be useful to the clinician.

[0096] Figure 4 This is a conceptual diagram illustrating an example anatomical structure and medical device of an example user interface according to one or more aspects of this disclosure. View 420 may be an example of a view that can be displayed on display 206 and / or display device 110 during RDN procedures. View 420 may include patient anatomy, such as kidney 410 and renal artery 406. View 420 may also include medical devices, such as guiding catheter 400 and ablation catheter 402. Ablation catheter 402 may include delivery elements 404, which may include electrodes configured to deliver denervated energy to target tissue within renal artery 406, thermal 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 an RDN device. For example, in an example where the delivery element 404 of the ablation catheter 402 includes electrodes, one or more of these electrodes may be coupled to the positive terminal 312, and one or more of these electrodes may be coupled to the negative terminal 314.

[0097] Figure 5 This is a conceptual diagram illustrating an example user interface that can be displayed during RDN procedures, according to one or more aspects of this disclosure. Figure 5 In the example, the delivery element 504 of the ablation catheter 502 is described as including an electrode; however, the delivery element 504 may alternatively or additionally include a thermal delivery element and / or an alcohol delivery element.

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

[0099] View 520 may also include visual indications of completed ventral ablation 516A and dorsal ablation 516A to assist clinicians in identifying the locations where ablation has been performed. View 520 may also include visual indications of recommended ventral locations 512A and recommended dorsal locations 514B for ablation to assist clinicians in guiding electrode 504 to appropriate locations for further ablation.

[0100] In some examples, view 520 may include a visual indication of any failed ablation (such as failed ablation 518). For example, failed ablation may include ablation where the expected ablation energy did not reach the target tissue, such as when the ablation energy was not delivered with sufficient amplitude and / or for sufficient duration. In some examples, system 100 may compare the amplitude and / or duration of ablation energy delivery (e.g., based on RDN device data 216) to one or more thresholds to determine failed ablation. In some examples, system 100 may determine failed ablation based on error codes from RDN device data 216. The visual indication of failed ablation 518 can assist clinicians in determining which ablation sites may require additional ablation energy delivery.

[0101] The visual cues discussed in view 520 may include different shapes, colors, etc., which can help distinguish one type of overlaid depiction from another. User interface 550 may include a legend 552 that displays an example representation of each depiction, which can be overlaid in view 520 to reduce the mental burden on clinicians during RDN procedures, for example, so that clinicians do not need to recall what each depiction represents from memory. User interface 550 may include recommendations 554 that can provide clinicians with descriptive and / or visual representations of the recommendations of system 100. Recommendations 554 may be updated in real time so that the description can change to reflect the actual positioning of ablation catheter 502, guide catheter 500, and electrode 504 as clinicians manipulate ablation catheter 502 and / or guide catheter 500. In some examples, updates to the description may occur periodically, such as every second or every half second.

[0102] The user interface 550 may also include a progress 556, which can track the progress of the RDN procedure, such as the percentage of completion of the RDN procedure.

[0103] Figure 6 This is a conceptual diagram illustrating examples of traceable features during RDN procedures according to one or more aspects of this disclosure. For example, system 100 may identify key traceable features, such as... Figure 6 As shown in the box. Such features may include anatomical features and / or other features within the patient's body, such as medical devices, implanted devices, or parts thereof. For example, system 100 may perform this process at machine learning model 222 and / or computer vision model 224 to identify such features. For example, system 100 may identify the kidney 610, guiding catheter 400, etc., for example by performing one or more computer vision models from computer vision model 224 on imaging data 214. Figure 4 The slender structure 600, vertebra 612, distal opening 601 of guiding catheter 400, and ablation catheter 402 outside distal opening 601 ( Figure 4 Part 602, bifurcations 614A to 614C, bifurcations 616A to 616B, etc. In some examples, bifurcations 614A to 614C can represent endpoints used for any ablation. For example, vessels distal to bifurcations 614A to 614C may be too small to be successfully navigated and ablated.

[0104] System 100 can define a corresponding local coordinate system for each vascular segment between key features or selected features. Example segments are shown as lines between larger solid circles (such as circles 620A and 620B). As shown, segment 630 spans from circle 620A (which may represent the beginning of a branch of the renal artery) to circle 620B (which may represent the distal opening 601). For example, in addition to the polar coordinates of each delivery element (e.g., an electrode) present within the segment, system 100 can also define a local coordinate system by extending along the length of the segment (e.g., proportionally along the vessel centerline). System 100 can identify the delivery element locations on the local coordinate system. When an ablation device signal (e.g., from RDN device 300) indicates an ablation event, system 100 can record the delivery element coordinates in the appropriate local coordinate system. For example, RDN device 300 can output a signal indicating an ablation event. System 100 can map ablation sites from each local coordinate system to a global coordinate system to generate an image with representations labeled for display on display 206 and / or display device 110 of completed ablation (and, in some examples, any failed ablation). For example, system 100 can generate a stack 240 and / or a 3D model 232 to include such representations. System 100 can distinguish between proximal and distal ablation. For example, proximal can include either dorsal or ventral, and distal can include the other. System 100 can use its own corresponding markers and / or colors to label proximal and distal ablation to indicate whether they are proximal or distal ablation. System 100 can repeat this process for each frame of imaging data 214 obtained from imager 140 and / or additional imager 142.

[0105] Figure 7This is a conceptual diagram illustrating an example of a local coordinate system and a cross-section of a blood vessel according to one or more aspects of this disclosure. A cross-section 732 of a renal vessel, taken at section 730, is shown. A diameter 738 of section 732 is also shown. In some examples, the value of diameter 738 may be displayed as, for example, part of a user interface 218, overlay 240, and / or 3D model 232. The position (or recommended position) of electrode 734 is shown within section 732. The position of electrode 734 can be shifted by an angle 736, such as 45 degrees, from the vertical axis of section 732. Displaying the position of electrode 734 within section 732 can assist clinicians in manipulating ablation catheter 402 to position electrode 734 appropriately along the circumference of the blood vessel represented in section 732 for ablation. For example, it may be desirable to ablate a nerve along the entire circumference of section 732. In some examples, section 732 may be displayed in different colors and / or using different representations to show the ablated area along the circumference of section 732 in order to distinguish the ablated area from the unablated area. Generally, when delivering ablation, approximately 25% to 30% (90° to 108°) of the circumference of the vessel section may undergo ablation. Although described as an electrode, electrode 734 can be any type of delivery element.

[0106] Figure 7 It also includes example representations of local coordinate system values ​​in Table 740. This local coordinate system can identify vascular segments for each electrode of the RDN catheter, such as vessel R3 (right renal artery - segment 3); distances (e.g., the distance from the distal point of the vascular segment to the proximal point of the vascular segment), which can be expressed in a measurement system (e.g., in millimeters, as a percentage of the length of the vascular segment); angles, such as the angle with respect to the vertical axis of the vascular cross-section, etc.

[0107] Examples in Table 740 include:

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

[0109] In some examples, system 100 can identify vascular segments to maximize the consistency of anatomical structures between frames. Vascular segments can include curves, splines, straight lines, etc. For example, system 100 can identify a curve of a specific size in the patient's vascular system in one frame of imaging data 214, and identify curves of the same size in the patient's vascular system in consecutive frames of imaging data 214, and identify curves of the same size in the two frames as the same vascular segment.

[0110] For 2D (on-screen fluoroscopy) visualization, "global coordinates" can simply refer to pixel coordinates on the screen. Therefore, as patient anatomy moves between frames (e.g., due to patient movement and / or imaging sensor movement), it may be necessary to recalculate the global coordinates for each ablation point. For example, system 100 may recalculate the global coordinates for each ablation point frame-by-frame to enable a relatively accurate representation of the ablation location above imaging data 214.

[0111] Figure 8 This is a concept diagram illustrating an example 3D model according to one or more aspects of this disclosure. The 3D model 800 may be... Figure 2 Examples of 3D model 232. In some examples, system 100 can map global coordinates onto 3D model 800, allowing clinicians to view anatomical structures from any angle. For example, 3D model 800 can be displayed and manipulated by a clinician via input device 210. System 100 can determine 3D model 232. For example, system 100 can 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 angular data and 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 representations of kidney 810 and renal vessels 806. 3D model 800 may also include representations of lead 802, ventral electrode 804A, dorsal electrode 804B, ventral ablation 816A, dorsal ablation 816B, recommended ventral ablation site 812A, recommended dorsal ablation site 812B, and / or any failed ablation (not shown). In some examples, 3D model 800 may be displayed instead of view 520. Figure 5 In other examples, the 3D model 800 may be displayed on the same or different displays along with the view 520. For example, the 3D model 800 may be displayed on display 206, while the user interface 550 may be displayed on display device 110.

[0113] In some examples, if a clinician changes the angle of the fluoroscopy examination during the procedure, system 100 can perform a real-time 3D reconstruction process to allow the mapping process to continue. For example, system 100 can perform the real-time 3D reconstruction process within an internal coordinate system (such as the global coordinate system discussed herein), but in some examples, the reconstructed 3D model may not be displayed to the clinician. This real-time 3D reconstruction process may include system 100 transforming the polar coordinates of points to account for the angular offset of the imager 140's detector relative to the patient's anatomy, and also adjusting or possibly resegmenting vessel segments in response to changes in angular offset. For example, a vessel segment may initially be represented as a straight line, but after viewing the vessel from another angle, the segment may be transformed into a curved line when viewed from the new angle. In another example, when viewed from a new angle, the vessel segment may be divided into two new segments, in which case system 100 can retransform all previously tracked points to these two new lines.

[0114] Figure 9 This is a conceptual diagram illustrating another example 3D model according to one or more aspects of this disclosure. System 100 can highlight the ablation location in 3D model 232 for display on display 206 and / or display device 110 by using simple markers, such as specific colors and / or shapes. Alternatively or additionally, system 100 can visually display the ablation location, wherein an energy delivery thermogram 910 is projected onto the surface of the blood vessel. For example, energy delivery thermogram 910 may include red for areas where a relatively large 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 small amount of energy is delivered during ablation, etc. In some examples, the color scale may be defined relative to other ablations or on a predefined scale. For example, “delivered energy” may be defined as the cumulative energy delivered to the surface, or another measure, such as the maximum temperature measured over a period of time greater than a predefined time period, such as 2 seconds. In some examples, system 100 may be configured to allow clinicians or other users to switch between displaying a thermogram and displaying simple markers. For example, system 100 may display an energy delivery heatmap 910 on display 206 and / or display device 110. In some examples, if applicable, Figure 9 This technology can be applied to 2D images. For example, Figure 5 View 520 may include an energy delivery heatmap, similar to energy delivery heatmap 910, but in 2D in view 550.

[0115] In some examples, the 3D model 900 may include similar indications of areas that have been ablated, rather than displaying a heatmap of the delivered energy. For example, alternative heatmaps may use one color to indicate areas that have been successfully ablated, another color to indicate areas that have not yet been ablated, and / or a third color to indicate areas that have not been successfully ablated.

[0116] Figure 10 This is a block diagram illustrating an example system according to one or more aspects of this disclosure. System 1000 may be similar to system 100 ( Figure 1 (Or, an example of this system.) Figure 10 In this example, system 1000 may include a fluorescence fluoroscopy imaging system 1002, an RDN energy generator 1010, and a computing system 1020. The fluorescence fluoroscopy imaging system may include a real-time RDN angiography image feed device 1004, such as an imager 140. Figure 1 The system 1000 may include a display, such as display device 110, on which it can display real-time angiographic images. Such displayed real-time angiographic images may have information superimposed thereon, as described herein.

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

[0118] It can be a computing device 200 ( Figure 2 The example computing system 1020 may include one or more RDN visualization programs 1022. The processing circuitry of the computing system 1020 may execute the RDN visualization program 1022 to determine overlay information to be superimposed on the real-time image feed based on the real-time RDN angiography image feed 1004 and electrode signal information 1012. The computing system 1020 may generate an output video feed 1024 that includes an angiography image feed with overlay information that can be used to guide RDN procedures. For example, the output video feed 1024 may include information superimposed on the real-time RDN angiography image feed 1004, such as information regarding this disclosure. Figures 4 to 9 The information described by any one or any combination thereof. The computing system 1020 can output the video feed 1024 to the display 1006 for display in the Cath lab.

[0119] Figure 11 This is a block diagram illustrating another example system according to one or more aspects of this disclosure. System 1100 may be similar to system 100 ( Figure 1 (Or, an example of this system.) Figure 11In this example, system 1100 may include a fluorescence fluoroscopy imaging system 1102, an RDN energy generator 1110, a computing system 1120, and an additional display / computing system 1140. The fluorescence fluoroscopy imaging system may include a real-time RDN angiography image feed device 1104, such as an imager 140 (…). Figure 1 The additional display / computing system 1140 may include a display 1142, such as display 206 and / or display device 110, on which system 1100 can display real-time angiographic images. Such displayed real-time angiographic images may have overlaid information thereon.

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

[0121] It can be a computing device 200 ( Figure 2 The example computing system 1120 may include one or more RDN visualization programs 1122. The processing circuitry of the computing system 1120 may execute the RDN visualization program 1122 to determine overlay information to be superimposed on the real-time image feed based on the real-time RDN angiography image feed 1104 and electrode signal information 1112. The computing system 1120 may generate an output video feed 1124 that includes an angiography image feed with overlay information that can be used to guide RDN procedures. For example, the output video feed 1124 may include information superimposed on the real-time RDN angiography image feed 1104, such as information regarding this disclosure. Figures 4 to 9 The information described by any one or any combination of these. The computing system 1020 can output the video feed 1124 to the display 1142 for display in the Cath lab.

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

[0123] RDN console 1210 can determine electrode signal information 1212, such as how much energy was delivered to a given electrode during ablation, timestamps associated with the start and / or end of energy delivery, etc. RDN console 1210 may also include one or more RDN visualization programs 1214. The processing circuitry of RDN console 1210 can execute the RDN visualization program 1214 to determine overlay information to be superimposed on the real-time image feed based on the real-time RDN angiography image feed 1204 and the electrode signal information 1212. RDN console 1210 can generate an output video feed 1216 that includes an angiography image feed with overlay information that can be used to guide RDN procedures. For example, output video feed 1216 may include information superimposed on the real-time RDN angiography image feed 1204, such as information regarding this disclosure. Figures 4 to 9 The information described by any one or any combination of the following. The RDN console 1210 can display the output video feed 1216 on the monitor 1218 for display in the Cath lab.

[0124] Figures 13A to 13B This is a flowchart illustrating an example ablation visualization technique of this disclosure. Figures 13A to 13B The technology is about Figure 1 System 100 describes it, but it can be described by system 1000 ( Figure 10 System 1100 Figure 11 System 1200 Figure 12 (or any other system capable of performing such techniques) to practice.

[0125] System 100 can obtain real-time angiography image feed 1302 from, for example, imager 140. For example, real-time angiography image feed 1302 may include fluoroscopic examination data, such as imaging data 214. In some examples, system 100 may also obtain recorded angiography video files 1304. Recorded angiography video files 1304 may include imaging data from previous medical procedures and may be included in imaging data 214 and / or electronic patient record 236. System 100 may apply the recorded angiography video file 1304 to video decoder 1312 to generate angiography frames 1310. Alternatively or additionally, system 100 may obtain angiography frames 1310 from real-time angiography image feed 1302. For example, angiography frame 1310 may represent a single frame of angiography imaging data. System 100 may also obtain real-time and / or recorded electrode data 1306. For example, system 100 may obtain electrode data 1306 from additional equipment 152 (e.g., RDN device 300). Figure 3 ), RDN device data 216 ( Figure 2 ) and / or electronic patient records 236 ( Figure 2 The system 100 acquires real-time and / or recorded electrode data 1306. The real-time and / or recorded electrode data 1306 can be synchronized with real-time angiography image feed 1302 and / or recorded angiography video file 1304. For example, the system 100 can synchronize the real-time and / or recorded electrode data 1306 with real-time angiography image feed 1302 and / or recorded angiography video file 1304 using timestamps, muscle twitches, etc.

[0126] System 100 can perform anatomical structure tracking 1320 of the information in the angiography frame 1310, such as the above-mentioned... Figure 6 Discussed. In some examples, system 100 may use computer vision model 224 to perform feature extraction to track anatomical structures. System 100 may perform vessel identification 1322 to identify vessels and / or vessel segments in angiography frame 1310. For example, system 100 may utilize pixel thresholding and masking, perform edge detection and / or edge selection to identify main vessels. System 100 may also perform electrode identification 1324 to identify delivery elements 404 of ablation catheter 402 in angiography frame 1310 (both are in...). Figure 4 (In the middle). For example, system 100 can use pixel thresholding and masking, perform edge detection and / or edge selection to identify specific electrodes of delivery element 404. System 100 can perform electrode 3D spatial interpretation 1330 on the identified electrodes in angiography frame 1310. For example, system 100 can calculate length and radial dilatation to determine the 3D positioning of the electrodes. System 100 can map the identified blood vessels and current electrode positioning to a local coordinate system 1340. In some examples, system 100 can add signal maps based on RDN device data 216, such as Figure 9 The system 100 can generate a heat map 910, or another mapping of energy signals associated with an active delivery element (e.g., an electrode). The system 100 can map all points of the blood vessel and electrode (and optionally, other anatomical structures, guiding catheter 400, and / or ablation catheter 402) to a global coordinate system based on anatomical structure tracking 1320. For example, the system 100 can map points from each vascular segment (including anything located within such vascular segments) back onto the complete image and / or model. The system 100 can proceed to... Figure 13B .

[0127] exist Figure 13BIn the example, system 100 may store signal maps in signal map memory 1342 (e.g., the signal map memory of memory 202, for example, stored in ablation / coordinate data 234). System 100 may use the signal maps in signal map memory 1342 to map previous points (such as the location of completed ablation and / or failed ablation) 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 that can be selected or entered by a user (such as a clinician) regarding how much ablation energy the user wishes to deliver, how close the ablation points are to each other, how conservative or flexible the clinician prefers regarding RDN protocols, turning protocol recommendations on or off, modifying visualization settings (such as colors, markers, etc.), hiding or showing specific types of visual overlays and / or indicators, etc. Based on the mapping of previous points to local coordinate system and user settings / preferences, system 100 may suggest device positioning 1354 for one or more next ablations. In some examples, system 100 uses rule-based algorithms or analysis of previous results (e.g., using machine learning model 222) to determine the proposed device location. System 100 can map the proposed points to a local coordinate system 1352. System 100 can then map the proposed points to a global coordinate system 1350.

[0128] System 100 can generate a composite overlay 1360 from points mapped to a global coordinate system. The composite overlay 1360 can be an example of overlay 240 and can include remapped features and / or representations of completed ablation, recommended ablation, and / or failed ablation, which can 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 can be included throughout this disclosure (including those relating to this disclosure). Figures 4 to 9 Any information discussed. System 100 can encode video and signal data 1362, for example, for procedural documentation, review, debugging, etc. System 100 can save files 1370. For example, system 100 can save the encoded information in memory 202, such as in electronic patient record 236. System 100 can output video feeds 1372. For example, system 100 can output composite video including any overlay information to display 1374 (e.g., display 206 and / or display device 110).

[0129] Figure 14This is a flowchart illustrating an example ablation visualization technique of the present 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 multiple 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, which may include RDN device data 216 from RDN device 300.

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

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

[0132] System 100 can perform segmentation 1406 of techniques across device types that have differences in outcome data and patient types. This segmentation may include segmentation of different procedural techniques across device types (e.g., different medical devices) observed in real-world practice, with any meaningful differences in the corresponding outcome data and patient types (e.g., patient A responds well to technique / device X, while patient B responds better to technique / device Y). Patient types may include anatomical features and / or medical history.

[0133] System 100 can generate Figure 1416, which may include a 2D and / or 3D map of a renal artery including branches with diameters, the presence and location of any calcium, which may take the form of discrete "yes" or "no" calcium presence, and / or a stack of images on a fluoroscopic examination showing the location and / or severity of any calcium deposits. For example, Figure 1416 includes information about... Figures 4 to 9 Any information in the discussion.

[0134] System 100 can determine recommended ablation sites 1408, which can be output peri-procedurally prior to RDN and can include recommended ablation sites based on successful past cases, the manufacturer's protocol for the ablation catheter 402, the size of the artery, the presence of calcification, etc.

[0135] System 100 can determine ablation and / or error data 1426. Ablation and / or error data 1426 may include RDN device data 216, such as high-density data indexed to timestamps detailing how much energy and / or alcohol was delivered within what time increments during ablation, and / or any error codes indexed to timestamps generated by RDN device 300. Ablation and / or error data 1426 may be… Figure 2 Example of RDN device data 216.

[0136] System 100 can use timestamps to correlate data 1417, such as Figure 1416, and ablation and / or error data 1426. System 100 can generate visual overlays 1418 during RDN, for example, peri-procedure. Visual overlays 1418 may include visual overlays on a fluoroscopic examination screen to guide clinicians, such as regarding... Figures 3 to 9 The visual overlay 1418 may include [discussion]. Figure 2 Examples of both overlay 240 and / or user interface 218. Visual overlay 1418 may include highlighting and / or marking locations for suggested ablation, and changing color and / or marking when those locations have been successfully ablated. In some examples, visual overlay 1418 may include a countdown clock for a recommended duration for a given ablation. Such a countdown clock may run while ablation is being performed.

[0137] System 100 may also generate a document record 1428, for example, after the procedure. Document record 1428 may include 2D images, 3D images, and / or 3D models of the renal artery tree, wherein the ablation site is shown along with relevant data such as ablation duration and / or delivered energy, to record the RDN procedure.

[0138] Figure 15 This is a flowchart illustrating an example ablation visualization technique of this disclosure. Figure 15 The technology described is related to computing device 200, 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 technology.

[0139] The computing device 200 can acquire patient imaging data (1500). For example, the computing device 200 can receive or retrieve imaging data from the imager 140 and / or the additional imager 142, or load imaging data 214 from the memory 202. The computing device 200 can acquire renal denervation device data (1502). For example, the computing device 200 can receive or retrieve renal denervation device data from the additional equipment 152 and / or the RDN device 300, or receive or retrieve RDN device data 216 from the memory 202.

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

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

[0142] The computing device 200 can generate multiple representations, including a corresponding representation for each of one or more recommended ablation sites and a corresponding representation for each of one or more completed ablation sites (1508). For example, the computing device 200 can generate a stack 240 and / or a 3D model 232 that may include such representations.

[0143] The computing device 200 can output multiple representations for display (1510). For example, the computing device 200 can control the display 206 and / or the display device 110 to overlay the overlay 240 onto the imaging data 214 and / or display it on the 3D model 232.

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

[0145] In some examples, the output includes a stack 240 configured to be overlaid on the imaging data 214. In some examples, system 100 includes a display (e.g., display 206 and / or display device 110) configured to display the stack 240 on the 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 indicating the amount of energy delivered to one or more corresponding locations.

[0147] In some examples, computing device 200 may automatically generate an ablation map indicating one or more completed ablation sites based on imaging data 214 and RDN device data 216, 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 multiple vascular segments based on the identified one or more features. In some examples, computing device 200 may determine a corresponding local coordinate system for each of the multiple vascular segments. In some examples, when the renal denervation device outputs an indication of an ablation event, computing device 200 may use the corresponding local coordinate system to determine the position of at least one electrode in one of the multiple vascular segments. 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 the location of one of one or more completed ablations based on the mapping.

[0149] In some examples, as part of determining one or more recommended ablation sites, computing device 200 may execute one or more ML models 222. According to the medical system of claim 10, the one or more ML models 222 are trained based on at least one of previous imaging data, previous ablation data, or previous patient demographic data. In some examples, previous ablation data includes multiple ablation techniques, multiple device types, multiple 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 performing a natural language processing application on the contents of multiple electronic patient records. In some examples, each of the multiple patient types is defined by at least one of anatomical features or medical history.

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

[0151] In some examples, determining one or more recommended ablation sites is also based on processed patient data, and the computing device 200 may acquire an electronic patient record 236 and perform natural language processing on the contents of the electronic patient record 236 to generate processed patient data. In some examples, one or more recommended ablation sites are also based on at least one of the following: learned previously successful ablation procedures; myofascial release protocols; the diameter of the artery; or the presence of calcification.

[0152] Figure 16 This 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 222, computer vision model 224, and / or NLP model 228. Machine learning model 1600 may be an example of a deep learning model or deep learning algorithm trained to determine recommended ablation sites. One or more of computing device 150, server 160, and / or other devices may train, store, and / or utilize machine learning model 1600, but in some examples, other devices of system 100 may apply input to machine learning model 1600. In some examples, and in others, other types of machine learning and deep learning models or algorithms may be utilized. For example, a convolutional neural network model of ResNet-18 may be used. Some non-limiting examples of models that can be used for transfer learning include AlexNet, VGGNet, GoogleNet, ResNet50, or DenseNet. Some non-limiting examples of machine learning techniques include support vector machines, K-nearest neighbor algorithms, and multilayer perceptrons.

[0153] like Figure 16 As shown in the example, the machine learning model 1600 may include three types of layers. These three types of layers include an input layer 1602, a hidden layer 1604, and an output layer 1606. The output layer 1606 includes the output of the transfer function 1605 from the output layer 1606. The input layer 1602 represents each of the input values ​​X1 to X4 provided to the machine learning model 1600. In some examples, as described above, the input values ​​may include any of the values ​​input into the machine learning model. For example, the input values ​​may include imaging data 214, as described above. Furthermore, in some examples, the input values ​​of the machine learning model 1600 may include additional data, such as other data that may be collected by or stored in the system 100, such as data from the electronic patient record 236, which may be processed by the NLP model 228.

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

[0155] The results for each node within hidden layer 1604 are applied to the transfer function of output layer 1606. The transfer function can be linear or nonlinear, depending on the number of layers within the machine learning model 1600. Example nonlinear transfer functions could be sigmoid functions or rectified functions. The output 1607 of the transfer function can be any specific point within the patient's vascular system depicted in imaging data 214 that is (or is not) a suitable (or more or less suitable) classification for future ablation.

[0156] As shown in the example above, by applying the machine learning model 1600 to input data such as imaging data 214, the processing circuit 204 is able to determine features in the imaging data 214 and / or one or more recommended ablation sites. The processing circuit 204 can utilize these features to determine a local coordinate system, map the local coordinate system to a global coordinate system, and / or generate a representation of one or more recommended ablation sites. The processing circuit 204 can control the display 206 to show such a representation. Therefore, the processing circuit 204 can guide clinicians during the ablation procedure.

[0157] Figure 17 This 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 can be used to train ML model 222 or machine learning model 1600. Machine learning model 1774 (which can be an example of machine learning model 1600) can be implemented using any number of models for supervised and / or reinforcement learning, such as, but not limited to, artificial neural networks, decision trees, Naive Bayes networks, support vector machines or k-nearest neighbor models, CNNs, RNNs, LSTMs, ensemble networks, to name a few.

[0158] In some examples, one or more of the computing device 150, server 160, and / or another device initially train the 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 demographics, etc. Previous ablation data may, for example, include multiple ablation techniques, multiple ablation device types, multiple 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, previous ablation data and / or previous patient demographics may be generated automatically by performing natural language processing applications on the contents of multiple electronic patient records to extract relevant or desired training data.

[0159] For example, by using an NLP model, the computing device 200 can capture potential confounding non-anatomical conditions or factors, which can be useful in determining the recommended ablation site. For instance, a patient's medical record may include details of such conditions or factors indicating generally high levels of sympathetic hyperactivity (e.g., increased heart rate, elevated blood pressure, increased respiration, etc.), which may indicate the need for a more potent ablation than suggested by anatomical structures alone. The computing device 200 can use an NLP model to capture such details. In such examples, when determining the recommended ablation site, the machine learning model can analyze underlying characteristics associated with the patient, not just anatomical factors.

[0160] In some examples, training data 1772 may include annotations identifying features in the imaging data of training data 1772 and / or recommended ablation sites. Training data 1772 may include data from past medical procedures performed on multiple patients with different patient conditions and different prior medical procedures, annotations or labels, other training data mentioned herein, etc.

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

[0162] The techniques discussed in this article can be used in any combination or individually.

[0163] While many of the techniques described herein belong to the processing circuit 204, in some examples such techniques may be provided by the server 160, imager 140, additional imager 142, additional equipment 152, etc. Figure 1 Other computing devices not shown, or any combination thereof, may perform this. Furthermore, while many of the techniques described herein pertain to display 206, such techniques can be performed by display device 110, Figure 1 Or other display devices not shown in 2, or any combination thereof.

[0164] The techniques described in this disclosure can be implemented, at least in part, in hardware, software, firmware, or any combination thereof. For example, various aspects of the described techniques can be implemented within one or more processors or processing circuits, 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 circuits, and any combination of such components. The terms “controller,” “processor,” or “processing circuit” generally refer to any of the aforementioned logic circuits individually or in combination with other logic circuits, or any circuit in any other equivalent circuit. A control unit including hardware can also perform one or more of the techniques disclosed herein. Such hardware, software, and firmware can be implemented within the same device or in separate devices to support the various operations and functions described in this disclosure. Furthermore, any of the described units, circuits, or components can be implemented together or independently as discrete but interoperable logic devices. Describing 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 implemented by separate hardware or software components. Conversely, the functionality associated with one or more circuits or units may be performed by independent hardware or software components, or integrated within common or independent hardware or software components.

[0165] The techniques described in this disclosure can also be embedded 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 can cause a programmable processor or other processor to perform the method, for example, when executing those instructions. The computer-readable storage medium may include random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), or electrically erasable programmable read-only memory (EEPROM) or other computer-readable media.

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

[0167] Example 1A. A medical system comprising: a 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: acquire the imaging data of a patient; acquire the renal denervation device data; determine one or more recommended ablation sites based on the imaging data; determine one or more completed ablation sites based on the imaging data and the renal denervation device data; generate a plurality of representations including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and output the plurality of representations for display.

[0168] Example 2A. The medical system according to Example 1A, the medical system further includes a renal denervation device, wherein the renal denervation device data includes data output from the renal denervation device.

[0169] Example 3A. The medical system according to Example 1A or Example 2A, wherein the processing circuit is further configured to: determine one or more failed ablation sites based on the imaging data and the renal denervation device data, wherein generating the output further includes generating a corresponding representation of the one or more failed ablation sites.

[0170] Example 4A. A medical system according to any one of Examples 1A to 3A, wherein the output includes a stack configured to be superimposed on the imaging data.

[0171] Example 5A. The medical system according to Example 4A, the medical system further includes a display configured to display the overlay on the imaging data.

[0172] Example 6A. A medical system according to any one of Examples 1A to 5A, wherein the output includes a three-dimensional model.

[0173] Example 7A. A medical system according to any one of Examples 1A to 6A, wherein the output includes at least one heat map indicating the amount of energy delivered to one or more corresponding locations.

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

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

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

[0177] Example 11A. The medical system according to Example 10A, 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 according to Example 11A, wherein the prior ablation data includes multiple ablation techniques, multiple device types, multiple patient types, and outcome data associated with prior ablation procedures.

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

[0180] Example 14A. The medical system according to Example 13A, wherein each of the multiple patient types is defined by at least one of anatomical features or medical history.

[0181] Example 15A. A medical system according to any one of Examples 1A to 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 the patient’s blood vessels based on the imaging data, the blood vessels including at least one branch and at least one diameter, wherein the output further includes the at least one diameter.

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

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

[0184] Example 18A. A medical system according to any one of Examples 1A to 17A, wherein the one or more recommended ablation sites are further based on at least one of the following: learned previously successful ablation procedures; myofascial release protocols; the diameter of the artery; or the presence of calcification.

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

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

[0187] Various embodiments have been described. These and other embodiments are within the scope of the appended claims. The subject matter of the following provisions is also disclosed herein: 1. A medical system, the medical system comprising: A memory configured to store imaging data and renal denervation device data; and Processing circuitry, communicatively coupled to the memory, is configured to: Obtain the patient's imaging data; Obtain the data of the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and Output the multiple representations for display.

[0188] 2. The medical system according to Clause 1, wherein the processing circuitry is further configured to: Based on the imaging data and the renal denervation device data, one or more failed ablation sites are determined. Generating the output also includes generating a corresponding representation of the one or more failed ablation sites.

[0189] 3. The medical system according to Clause 1 or Clause 2, wherein the output includes at least one of the following: a stack configured to be superimposed on the imaging data; a three-dimensional model; or at least one heat map indicating the amount of energy delivered to one or more corresponding locations.

[0190] 4. The medical system according to any one of clauses 1 to 3, wherein the processing circuit is further configured to: Based on the imaging data and the renal denervation device data, automatically generate an ablation map indicating one or more completed ablation sites; and The ablation map is stored in the electronic patient record.

[0191] 5. The medical system according to any one of clauses 1 to 4, wherein the processing circuit is further configured to: Identify one or more features in the imaging data; Multiple vascular segments are defined based on one or more identified features; For each of the plurality of vascular segments, a corresponding local coordinate system is determined; When the renal denervation device outputs an indication ablation event, the corresponding local coordinate system is used to determine the position of at least one electrode in one of the plurality of vascular segments; Map the corresponding local coordinate system to the global coordinate system; and The location of one completed ablation is determined based on the mapping.

[0192] 6. The medical system according to any one of clauses 1 to 5, wherein, as part of determining the one or more recommended ablation sites, the processing circuitry is configured to execute one or more machine learning models.

[0193] 7. The medical system according to 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.

[0194] 8. The medical system according to Clause 7, wherein the prior ablation data includes multiple ablation techniques, multiple device types, multiple patient types and outcome data associated with prior ablation procedures, wherein each of the multiple patient types is defined by at least one of anatomical features or medical history.

[0195] 9. The medical system according to Clause 7, wherein at least one of the previous ablation data or previous patient demographic data is generated by performing a natural language processing application on the contents of multiple electronic patient records.

[0196] 10. The medical system according to any one of clauses 1 to 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 the patient's blood vessels based on the imaging data, the blood vessels including at least one branch and at least one diameter, wherein the output further includes the at least one diameter.

[0197] 11. The medical system according to any one of clauses 1 to 10, wherein, as part of determining the one or more recommended ablation sites, the processing circuitry is further configured to execute at least one of a computer vision model or a machine learning model to determine the one or more calcification sites based on the imaging data, wherein the output further includes a corresponding representation of each of the one or more calcification sites.

[0198] 12. The medical system according to any one of clauses 1 to 11, wherein determining the one or more recommended ablation sites is further based on processed patient data, and wherein the processing circuitry is further configured to: Obtain electronic patient records; and Natural language processing is applied to the contents of the electronic patient record to generate the processed patient data.

[0199] 13. The medical system according to any one of Clauses 1 to 12, wherein the one or more recommended ablation sites are also based on at least one of the following: a previously successful ablation protocol; a myofascial release protocol; the diameter of the artery; or the presence of calcification.

[0200] 14. A method comprising: Obtain the patient's imaging data; Obtain data on the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and Output the multiple representations for display.

[0201] 15. A non-transitory computer-readable storage medium storing instructions, which, when executed, cause processing circuitry to: Obtain the patient's imaging data; Obtain data on the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; and Output the multiple representations for display.

Claims

1. A medical system, the medical system comprising: A memory configured to store imaging data and renal denervation device data; and Processing circuitry, communicatively coupled to the memory, is configured to: Obtain the patient's imaging data; Obtain the data of the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; as well as Output the multiple representations for display.

2. The medical system according to claim 1, wherein the processing circuit is further configured to: Based on the imaging data and the renal denervation device data, one or more failed ablation sites are determined. Generating the output also includes generating a corresponding representation of the one or more failed ablation sites.

3. The medical system of claim 1 or claim 2, wherein the output comprises at least one of the following: a stack configured to be superimposed on the imaging data; a three-dimensional model; or at least one heat map indicating the amount of energy delivered to one or more corresponding locations.

4. The medical system according to any one of claims 1 to 3, wherein the processing circuit is further configured to: Based on the imaging data and the renal denervation device data, automatically generate an ablation map indicating one or more completed ablation sites; and The ablation map is stored in the electronic patient record.

5. The medical system according to any one of claims 1 to 4, wherein the processing circuit is further configured to: Identify one or more features in the imaging data; Multiple vascular segments are defined based on one or more identified features; For each of the plurality of vascular segments, a corresponding local coordinate system is determined; When the renal denervation device outputs an indication ablation event, the corresponding local coordinate system is used to determine the position of at least one electrode in one of the plurality of vascular segments; Map the corresponding local coordinate system to the global coordinate system; and The location of one completed ablation is determined based on the mapping.

6. The medical system according to any one of claims 1 to 5, wherein, as part of determining the one or more recommended ablation sites, 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 prior ablation data includes multiple ablation techniques, multiple device types, multiple patient types, and outcome data associated with prior ablation procedures, wherein each of the multiple patient types is defined by at least one of anatomical features 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 performing a natural language processing application on the contents of a plurality of electronic patient records.

10. The medical system according to any one of claims 1 to 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 the patient's blood vessels based on the imaging data, the blood vessels including at least one branch and at least one diameter, wherein the output further includes the at least one diameter.

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

12. The medical system according to any one of claims 1 to 11, wherein determining the one or more recommended ablation sites is further based on processed patient data, and wherein the processing circuitry is further configured to: Obtain electronic patient records; and Natural language processing is applied to the contents of the electronic patient record to generate the processed patient data.

13. The medical system according to any one of claims 1 to 12, wherein the one or more recommended ablation sites are further based on at least one of: learned previously successful ablation procedures; myofascial release protocols; the diameter of the artery; or the presence of calcification.

14. A method, the method comprising: Obtain the patient's imaging data; Obtain data on the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; as well as Output the multiple representations for display.

15. A non-transitory computer-readable storage medium storing instructions, which, when executed, cause processing circuitry to: Obtain the patient's imaging data; Obtain data on the renal denervation device; Based on the imaging data, one or more recommended ablation sites can be determined; One or more ablation sites are determined based on the imaging data and the renal denervation device data; Generate multiple representations, including a corresponding representation for each of the one or more recommended ablation sites and a corresponding representation for each of the one or more completed ablation sites; as well as Output the multiple representations for display.

Images