Co-registration of renal nerve bundles with x-ray images for renal denervation procedure guidance

Abstract

An apparatus includes a processor configured for communication with an intravascular imaging catheter. The processor is configured to control the intravascular imaging catheter to obtain a plurality of intravascular images during movement of the catheter along a length of a renal artery, wherein the plurality of intravascular images depict one or more nerve bundles for targeting during a renal denervation procedure. The processor performs a co-registration between a plurality of nerve bundle data points and a first X-ray image of the renal artery, the plurality of nerve bundle data points representing the nerve bundles and being associated with treatment locations along the length of the renal artery for the renal denervation procedure, the first X-ray image obtained with contrast agent inside the renal artery. The processor outputs a screen display to a display based on the co-registration and is configured to guide a user with respect to the renal denervation procedure.

Description

Technical Field

[0001] This article describes systems, devices, and methods for co-registering renal angiography with renal nerve bundle data from intravascular imaging to guide renal denervation (RDN) surgery. This RDN nerve data co-registration system has specific, but not exclusive, utility in improving the speed and outcome of renal denervation surgery. Background Technology

[0002] Renal denervation (RDN) is a potentially promising surgical procedure for treating hypertension that cannot be adequately managed with antihypertensive medications. Studies have demonstrated its high effectiveness, with response rates showing a reduction in systolic blood pressure of 5 mmHg or higher in approximately two-thirds of patients. However, studies have also shown varying levels of efficacy, with a subset (currently estimated at approximately 30%) exhibiting no response or a negative response to the procedure. This non-responder demographic may exist due to a combination of factors, possibly stemming from physiological factors and / or inadequate treatment administration.

[0003] Currently, renal denervation surgery is performed intravascularly under fluorescence microscopy guidance. There is almost no information available about the correct location for performing the RDN procedure or the characteristics and morphology of the tissues adjacent to the artery. Using fluorescence microscopy, the user can only identify the boundaries of the artery in a 2D projection.

[0004] Information included in the background section of this specification (including any references cited herein and any descriptions or discussions thereof) is incorporated herein for technical reference purposes only and should not be considered as subject matter defining the scope of this disclosure. Summary of the Invention

[0005] A co-registration system for renal denervation (RDN) nerve data is disclosed, enabling clinicians to predict which treatment sites are likely to show a favorable response to RDN treatment and / or to determine the success or completion of an ongoing RDN treatment. This disclosure relates to projecting co-registration data regarding the size and location of renal nerves at different locations onto fluorescence microscopic images of the renal artery during RDN surgery. Currently, renal denervation (RDN) surgery is performed intravascularly under fluorescence microscopic guidance, with little available information regarding the correct location for performing the RDN procedure or the tissue adjacent to the artery. Intravascular imaging or preoperative CT imaging can better assess and identify tissue adjacent to the artery, particularly the size and location of the renal nerve bundle targeted by the RDN procedure. The presence of certain features (e.g., nerve bundles located close to the renal artery) and the absence of other features (e.g., calcifications or other features preventing access to the nerve bundle) can affect the efficacy of RDN surgery, thus helping to guide the user and inform them where they should or should not use one or more RDN treatment devices. The RDN neural data co-registration system disclosed in this paper has specific but non-exclusive utility for determining the site suitability and / or completion / success of renal denervation surgery.

[0006] This summary is provided to present, in a simplified form, the selection of concepts further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. A broader presentation of the features, details, utility, and advantages of an RDN neural data co-registration system (as defined in the claims) is provided and illustrated in the following written description of various aspects of this disclosure. Attached Figure Description

[0007] The illustrative aspects of this disclosure will be described with reference to the accompanying drawings, in which:

[0008] Figure 1 This is a schematic diagram of an intraluminal imaging system based on various aspects of this disclosure.

[0009] Figure 2 This is a schematic diagram of the processor circuitry according to various aspects of this disclosure.

[0010] Figure 3 This is a schematic diagram of an intraluminal imaging catheter that is pulled back through the left renal artery of the left kidney, according to various aspects of this disclosure.

[0011] Figure 4 It is a schematic diagram of X-ray images of the renal artery tree with contrast agent according to various aspects of this disclosure.

[0012] Figure 5 It is a representation of a lateral cross-sectional IVUS image of the renal artery at a first location, according to various aspects of this disclosure.

[0013] Figure 6 It is a representation of a lateral cross-sectional IVUS image of the renal artery at a second location, different from the first location, according to various aspects of this disclosure.

[0014] Figure 7A It is a schematic diagram representing the joint registration of renal nerve data points and angiographic route images of the renal artery tree based on various aspects of this disclosure.

[0015] Figure 7B It is a schematic diagram representing the co-registration of intravascular image frames and angiographic route images of the renal artery tree according to various aspects of this disclosure.

[0016] Figure 8 This is a common registration screen display of an example RDN neural data common registration system based on various aspects of this disclosure.

[0017] Figure 9 The image is a roadmap screen display of an example RDN neural data co-registration system based on various aspects of this disclosure.

[0018] Figure 10 The image is a roadmap screen display of an example RDN neural data co-registration system based on various aspects of this disclosure.

[0019] Figure 11 The image is a roadmap screen display of an example RDN neural data co-registration system based on various aspects of this disclosure.

[0020] Figure 12 It is a schematic diagram in the form of a flowchart illustrating an example RDN neural data co-registration method based on various aspects of this disclosure.

[0021] Figure 13 It is a schematic diagram in the form of a block diagram representing an example machine learning model training process for identifying RDN disposal locations based on various aspects of this disclosure.

[0022] Figure 14 This is a schematic diagram in the form of a block diagram of an example machine learning model training system for RDN disposal location computation based on various aspects of this disclosure.

[0023] Figure 15 It is a schematic diagram in the form of a block diagram representing an example machine learning model inference pattern for RDN processing location computation based on various aspects of this disclosure.

[0024] Figure 16 It is a schematic diagram in the form of a flowchart illustrating various aspects of the RDN disposal assessment process based on the present disclosure.

[0025] Figure 17 This is a schematic diagram of the renal vascular system of a patient according to various aspects of this disclosure, wherein the renal denervation treatment device is located in the left renal artery of the left kidney. Detailed Implementation

[0026] According to at least one aspect of this disclosure, a co-registration system for RDN neural data is provided, which enables clinicians to predict which treatment sites are likely to show a favorable response to RDN treatment and / or to determine the success or completion of an ongoing RDN treatment.

[0027] This disclosure relates to projecting co-registered data onto fluorescence microscopic images of the renal nerve during RDN surgery (e.g., overlaying data onto the location of captured data). Currently, renal denervation (RDN) surgery is performed intravascularly under fluorescence microscopic guidance. Little information is available regarding the correct location for performing RDN surgery or the characteristics and morphology of tissues adjacent to the artery. Using fluorescence microscopy, the user can only identify the boundaries of the artery in a 2D projection. Intravascular imaging or preoperative CT imaging can better assess and identify tissues adjacent to the artery (e.g., renal nerve, renal vein, arterial wall thickening, fat deposits adjacent to the artery, or calcification). The presence or absence of these features affects the efficacy of RDN surgery and can therefore help guide clinicians to know where they should or should not use one or more RDN treatment devices.

[0028] This disclosure brings advanced imaging information to the fluorescence microscope or angiographic view that the physician is using to guide RDN procedures. The position of the renal nerve relative to the renal artery can help clinicians performing RDN better position their treatment devices for successful nerve ablation.

[0029] The RDN neural data co-registration system includes a fluorescence microscopic view or angiographic view of the renal artery tree taken during surgery. Adjacent to this image is high-level imaging, such as optical coherence tomography (OCT) or intravascular ultrasound (IVUS) imaging taken from a catheter within the renal artery, or computed tomography (CT) imaging taken prior to surgery. These images can contain more detailed information about the tissue surrounding the renal artery tree.

[0030] In one aspect, users will be able to scroll along the renal artery in angiography to show a corresponding cross-sectional view of advanced imaging.

[0031] In one aspect, this advanced imaging is generated using intravascular ultrasound (IVUS) or intravascular optical coherence tomography (OCT).

[0032] On the other hand, computer vision systems are trained to recognize structures within high-level imaging to further guide the user to the morphology of the tissue surrounding the renal artery. Some such features include (one or more) renal nerves, the arterial wall, renal veins, adipose tissue, scar tissue, calcification, thickening of the arterial wall, and arterial spasm.

[0033] Another aspect will indicate the RDN treatment location corresponding to the optimal chance of a successful surgery. This location can be derived by training an algorithm on previously performed RDN surgeries and correlating treatment and neural locations with the clinical efficacy of the technique.

[0034] On the other hand, advanced imaging such as IVUS is performed after RDN treatment to identify whether neural tissue has been properly ablated. IVUS imaging, which can show both healthy and ablated neural tissue, can be co-registered with renal artery angiography.

[0035] This disclosure significantly facilitates the execution of interventional procedures (e.g., renal denervation) by enhancing clinicians' understanding of where interventions will be most effective. The RDN neural data co-registration system disclosed herein is implemented on a processor communicating with one or more sensors. This system actually detects and measures the patient's renal nerves, the proximity of the renal nerves to the renal arteries, and the renal nerves' likely response to RDN interventions. This enhanced situational awareness transforms blind medical procedures with a 70% success rate into procedures where success can be accurately predicted and even measured in real time to determine if further intervention is needed, without the usual waiting and observation of whether the patient's hypertension decreases over a period of days or weeks. This unconventional approach improves the functional operation of the renal denervation system by increasing the success rate of RDN interventions and by providing the necessary information for surgery only where the renal nerve bundles may be affected.

[0036] The RDN neural data co-registration system can be implemented at least partially as a process viewable on a display and operated by a control process executed on a processor that accepts user input from a keyboard, mouse, or touchscreen interface and communicates with one or more sensors. At this point, the control process performs certain specific operations in response to different inputs or selections made at different times. Some outputs of the RDN neural data co-registration system can be printed, displayed on a display, indicated by light or hue, or otherwise communicated to a human operator. Certain structures, functions, and operations of the processor, display, sensors, and user input system are known in the art, while other structures, functions, and operations are described herein to specifically implement novel features or aspects of this disclosure.

[0037] This disclosure relates to U.S. Provisional Application US63 / 565843, filed March 15, 2024, entitled "Catheter-Based ProceduresWith Procedure Room Detection Of Biomarkers In Patient Blood And Associated Devices, Systems, And Methods"; U.S. Provisional Application US63 / 565640, filed March 15, 2024, entitled "Multi-Factor Renal Denervation Index For Patient Suitability and / or Expected Responsiveness To Renal Denervation Treatment"; U.S. Provisional Application US63 / 565612, filed March 15, 2024, entitled "Renal Denervation Treatment Guidance Using Hemodynamic Co-Registration and Associated Systems, Devices, and Methods"; and U.S. Provisional Application US63 / 565612, filed March 15, 2024, entitled "Renal Denervation Treatment Assessment Using Ambulatory Blood Pressure". The U.S. provisional application US63 / 565589 concerning “Monitor”, each of which is incorporated herein by reference as fully set forth herein.

[0038] These descriptions are provided for illustrative purposes only and should not be construed as limiting the scope of the RDN neural data co-registration system. Certain features may be added, removed, or modified without departing from the spirit of the claimed subject matter.

[0039] For the purpose of facilitating an understanding of the principles of this disclosure, reference will now be made to the aspects illustrated in the accompanying drawings, and these aspects will be described using specific language. Nevertheless, it should be understood that this is not intended to limit the scope of this disclosure. Any changes and further modifications to the devices, systems, and methods described in this disclosure, as well as any further application of the principles of this disclosure, are fully contemplated and included within this disclosure, as would normally occur to those skilled in the art to which this disclosure pertains. In particular, it is fully contemplated that features, components, and / or steps described with respect to one aspect can be combined with features, components, and / or steps described with respect to other aspects of this disclosure. However, for the sake of brevity, numerous iterations of these combinations will not be described separately.

[0040] Figure 1 This is a schematic diagram illustrating an intraluminal imaging system according to various aspects of this disclosure. In some aspects, the intraluminal imaging system 100 may be an intravascular ultrasound (IVUS) imaging system. The intraluminal imaging system 100 may include an intraluminal device 102, a patient interface module (PIM) 104, a console or processing system 106, a monitor 108, and an external imaging system 132, which may include angiography, ultrasound, X-ray, computed tomography (CT), magnetic resonance imaging (MRI), or other imaging techniques, instruments, and methods. The size and shape of the intraluminal device 102 are configured and / or otherwise structurally arranged to be positioned within the lumen of a patient's body. For example, in various aspects, the intraluminal device 102 may be a catheter, guidewire, guiding catheter, pressure wire, and / or flow wire. In some cases, the system 100 may include additional components and / or may be available without them. Figure 1 The system is implemented with one or more of the components shown. For example, system 100 may omit the external imaging system 132.

[0041] The intraluminal imaging system 100 (or intravascular imaging system) can be any type of imaging system suitable for the patient's lumen or vascular system. In some aspects, the intraluminal imaging system 100 is an intravascular ultrasound (IVUS) imaging system. In other aspects, the intraluminal imaging system 100 may include a system configured for forward-looking intravascular ultrasound (FL-IVUS) imaging, intravascular photoacoustic (IVPA) imaging, intracardiac echocardiography (ICE), transesophageal echocardiography (TEE), and / or other suitable imaging modalities.

[0042] It should be understood that system 100 and / or device 102 can be configured to acquire any suitable intraluminal imaging data. In some aspects, device 102 may include imaging components of any suitable imaging modality (e.g., optical imaging, optical coherence tomography (OCT), etc.). In some aspects, device 102 may include any suitable non-imaging components (including pressure sensors, flow sensors, temperature sensors, optical fibers, reflectors, mirrors, prisms, ablation elements, radio frequency (RF) electrodes, conductors, or combinations thereof). Generally, device 102 may include imaging elements to acquire intraluminal imaging data associated with lumen 120. The size and shape of device 102 may be set (and / or configured) for insertion into a patient's blood vessel or lumen 120.

[0043] System 100 can be deployed in a catheterization laboratory with a control room. Processing system 106 can be located in the control room. Alternatively, processing system 106 can be located elsewhere (e.g., within the catheterization laboratory itself). The catheterization laboratory may include sterile areas, while its associated control room may or may not be sterile, depending on the procedure and / or healthcare facility to be performed. The catheterization laboratory and control room can be used to perform any number of medical imaging procedures (e.g., angiography, fluorescein microscopy, CT, IVUS, virtual histology (VH), forward-looking IVUS (FL-IVUS), intraluminal photoacoustic (IVPA) imaging, fractional flow reserve (FFR) measurement, coronary flow reserve (CFR) measurement, optical coherence tomography (OCT), computed tomography, intracardiac echocardiography (ICE), forward-looking ICE (FLICE), endovascular palpation, transesophageal echocardiography, and other medical imaging modalities, or combinations thereof). In some respects, device 102 can be controlled from a remote location (e.g., a control room), eliminating the need for an operator to be physically present with the patient.

[0044] Intraluminal device 102, PIM 104, monitor 108, and external imaging system 132 can be directly or indirectly communicatively coupled to processing system 106. These components can be communicatively coupled to medical processing system 106 via wired connections (e.g., standard copper or fiber optic links) and / or via wireless connections using IEEE 802.11 Wi-Fi, Ultra-Wideband (UWB), FireWire, Wireless USB, or another high-speed wireless network standard. Processing system 106 can be communicatively coupled to one or more data networks (e.g., a TCP / IP-based local area network (LAN)). In other respects, different protocols can be utilized (e.g., Synchronous Optical Network (SONET)). In some cases, processing system 106 can be communicatively coupled to wide area network (WAN). Processing system 106 can utilize network connectivity to access various resources. For example, processing system 106 can communicate via network connectivity with a Medical Digital Imaging and Communication (DICOM) system, a Picture Archiving and Communication (PACS) system, and / or a Hospital Information System (HIS).

[0045] From a macroscopic perspective, the intraluminal ultrasound imaging device 102 emits ultrasonic energy from a transducer array 124 included in a scanner assembly 110 mounted near the distal end of the intraluminal device 102. The ultrasonic energy is reflected by tissue structures in the medium surrounding the scanner assembly 110 (e.g., the lumen 120), and the ultrasonic echo signals are received by the transducer array 124. The scanner assembly 110 generates one or more electrical signals representing the ultrasonic echoes. The scanner assembly 110 may include one or more individual ultrasonic transducers and / or the transducer array 124 in any suitable configuration (e.g., planar array, curved array, circular array, annular array, etc.). For example, in some instances, the scanner assembly 110 may be a one-dimensional or two-dimensional array. In some instances, the scanner assembly 110 may be a rotating ultrasound device. The effective area of ​​the scanner assembly 110 may include one or more segments (e.g., one or more rows, one or more columns, and / or one or more orientations) of one or more transducer materials and / or ultrasonic elements that can be uniformly or independently controlled and activated. The effective area of ​​the scanner assembly 110 can be patterned or structured in various basic or complex geometries. The scanner assembly 110 can be positioned in a lateral orientation (e.g., emitting ultrasonic energy perpendicular to and / or orthogonal to the longitudinal axis of the intraluminal device 102) and / or a forward orientation (e.g., emitting ultrasonic energy parallel to and / or along the longitudinal axis). In some instances, the scanner assembly 110 is structurally arranged to emit and / or receive ultrasonic energy at an angle relative to the longitudinal axis in the proximal or distal direction. In some aspects, the ultrasonic energy emission can be electronically redirected by selectively triggering one or more transducer elements of the scanner assembly 110.

[0046] The ultrasonic transducers(s) of the scanner assembly 110 may be piezoelectric micromechanical ultrasonic transducers (PMUTs), capacitive micromechanical ultrasonic transducers (CMUTs), single crystals, lead zirconate titanate (PZT), PZT composites, other suitable transducer types, and / or combinations thereof. In one aspect, the ultrasonic transducer array 124 may include any suitable number of individual transducer elements or acoustic elements between 1 and 1000 acoustic elements (including, for example, 2, 4, 36, 64, 128, 500, 812, and / or other larger and smaller values ​​of acoustic elements).

[0047] The received echo signal is transmitted from PIM 104 to processing system 106, where the ultrasound image (including flow information) is reconstructed and displayed on monitor 108. The console or processing system 106 may include a processor and memory. Processing system 106 is capable of operating features that facilitate the intraluminal imaging system 100 described herein. For example, the processor may execute computer-readable instructions stored on a non-transient tangible computer-readable medium.

[0048] PIM 104 facilitates signal communication between processing system 106 and scanner assembly 110 included in in-lumen device 102. This communication may include: providing commands to one or more integrated circuit controller chips within in-lumen device 102 to select one or more specific elements on transducer array 124 for transmission and reception; providing a transmission trigger signal to one or more integrated circuit controller chips to activate transmitter circuitry to generate electrical pulses to excite the selected transducer array elements; and / or receiving amplified echo signals received from the selected transducer array elements via amplifiers included on one or more integrated circuit controller chips. In some aspects, PIM 104 performs preliminary processing of the echo data before relaying the data to processing system 106. In examples of such aspects, PIM 104 performs amplification, filtering, and / or aggregation of the data. In one aspect, PIM 104 also provides high-voltage and low-voltage DC power to support the operation of in-lumen device 102, including circuitry within scanner assembly 110.

[0049] Processing system 106 receives echo data from scanner assembly 110 via PIM 104 and processes the data to reconstruct an image of tissue structures in the medium surrounding scanner assembly 110. Generally, device 102 can be used within any suitable anatomical structure and / or body lumen of a patient. Processing system 106 outputs image data such that an image of a blood vessel or lumen 120 (e.g., a cross-sectional IVUS image of lumen 120) is displayed on monitor 108. Lumen 120 can represent a fluid-filled or fluid-surrounded structure (including natural and artificial structures). Lumen 120 can be within a patient's body. Lumen 120 can be a blood vessel (e.g., an artery or vein in the patient's vascular system, including the cardiac vascular system, peripheral vascular system, neurovascular system, renal vascular system, and / or any other suitable lumen within the body). For example, device 102 can be used to examine any number of anatomical locations and tissue types (including, but not limited to, organs including the liver, heart, kidneys, gallbladder, pancreas, lungs; ducts; intestines), nervous system structures (including the brain, dural sac, spinal cord, and peripheral nerves), urethra, and valves within the blood, ventricles, or other parts of the heart and / or other systems of the body). In addition to natural structures, device 102 can also be used to examine artificial structures (e.g., but not limited to, heart valves, stents, shunts, filters, and other devices).

[0050] The controller or processing system 106 may include processing circuitry having one or more processors that communicate with memory and / or other suitable tangible computer-readable storage media. The controller or processing system 106 may be configured to perform one or more aspects of this disclosure. In some aspects, the processing system 106 and the monitor 108 are separate components. In other aspects, the processing system 106 and the monitor 108 are integrated into a single component. For example, system 100 may include a touchscreen device (including a housing having a touchscreen display and a processor). System 100 may include any suitable input device (e.g., a touchpad or touchscreen display, keyboard / mouse, joystick, buttons, etc.) for a user to select options shown on monitor 108. The processing system 106, monitor 108, input devices, and / or combinations thereof may be referred to as the controller of system 100. The controller may communicate with device 102, PIM 104, processing system 106, monitor 108, input devices, and / or other components of system 100.

[0051] In some aspects, the intraluminal device 102 includes features similar to those of conventional solid-state IVUS catheters, such as those disclosed in U.S. Patent US7,846,101, which is incorporated herein by reference in its entirety. For example, the intraluminal device 102 may include a scanner assembly 110 near the distal end of the intraluminal device 102 and a transmission harness 112 extending along the longitudinal body of the intraluminal device 102. The cable or transmission harness 112 may include multiple conductors (including one, two, three, four, five, six, seven or more conductors).

[0052] The transmission harness 112 terminates in a PIM connector 114 at the proximal end of the intraluminal device 102. The PIM connector 114 electrically couples the transmission harness 112 to the PIM 104 and physically couples the intraluminal device 102 to the PIM 104. In one aspect, the intraluminal device 102 also includes a guidewire exit port 116. Accordingly, in some instances, the intraluminal device 102 is a quick-change catheter. The guidewire exit port 116 allows distal insertion of a guidewire 118 to guide the intraluminal device 102 through the lumen 120.

[0053] Monitor 108 may be a display device (e.g., a computer monitor or other type of screen). Monitor 108 may be used to display optional prompts, instructions, and visualizations of imaging data to the user. In some aspects, monitor 108 may be used to provide the user with a process-specific workflow for completing an intraluminal imaging procedure. This workflow may include: performing pre-stent planning to determine the status of the lumen and the feasibility of stenting, and performing post-stent checks to determine the status of the stent that has been positioned in the lumen.

[0054] External imaging system 132 can be configured to acquire X-ray images, radiographic images, angiographic / venographic images (e.g. with contrast agent), and / or fluorescence microscopy images (e.g. without contrast agent) of a patient's body (including blood vessels 120). External imaging system 132 can also be configured to acquire computed tomographic images of the patient's body (including blood vessels 120). External imaging system 132 may include an external ultrasound probe configured to acquire ultrasound images of the patient's body (including blood vessels 120) when positioned externally to the body. In some aspects, system 100 includes other imaging modalities (e.g., MRI) to acquire images of the patient's body (including blood vessels 120). Processing system 106 can combine intraluminal images acquired by intraluminal device 102 to utilize images of the patient's body.

[0055] Figure 2This is a schematic diagram of processor circuitry 250 according to various aspects of this disclosure. Processor circuitry 250 can be implemented as needed in the intraluminal imaging system 100 or other devices or workstations (e.g., third-party workstations, network routers, etc.) or on a cloud processor or other remote processing unit to implement the method. As shown, processor circuitry 250 may include processor 260, memory 264, and communication module 268. These components can communicate directly with each other or indirectly, for example, via one or more buses.

[0056] Processor 260 may include a central processing unit (CPU), a digital signal processor (DSP), an ASIC, a controller, or any combination of the following: a general-purpose computing device, a reduced instruction set computing (RISC) device, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other related logic devices (including mechanical computers and quantum computers). Processor 260 may also include another hardware device, firmware device, or any combination thereof configured to perform the operations described herein. Processor 260 may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a DSP core, or any other such configuration.

[0057] Memory 264 may include cache memory (e.g., the cache memory of processor 260), random access memory (RAM), magnetoresistive RAM (MRAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, solid-state memory devices, hard disk drives, other forms of volatile and non-volatile memory, or combinations of different types of memory. In one aspect, memory 264 includes a non-transitory computer-readable medium. Memory 264 may store instructions 266. Instructions 266 may include instructions that, when executed by processor 260, cause processor 260 to perform the operations described herein. Instructions 266 may also be referred to as code. The terms “instruction” and “code” should be interpreted broadly to include any type of computer-readable statement(s). For example, the terms “instruction” and “code” may refer to one or more programs, routines, subroutines, functions, procedures, etc., and “instruction” and “code” may include a single computer-readable statement or a number of computer-readable statements.

[0058] Communication module 268 may include any electronic circuitry and / or logic circuitry to facilitate direct or indirect data communication between processor circuitry 250 and other processors or devices. In this respect, communication module 268 may be an input / output (I / O) device. In some instances, communication module 268 facilitates direct or indirect communication between processor circuitry 250 and / or various components of the intraluminal imaging system 100. Communication module 268 can communicate within processor circuitry 250 via various methods or protocols. Serial communication protocols may include, but are not limited to, US Serial Protocol Interface (US SPI), I2C bus (I... 2 C) Recommended standards RS-232, RS-485, Controller Area Network (CAN), Ethernet, ARINC 429, MODBUS, MIL-STD-1553, or any other suitable method or protocol. Parallel protocols include, but are not limited to, Industry Standard Architecture (ISA), Advanced Technology Attachment (ATA), Small Computer System Interface (SCSI), Peripheral Component Interconnect (PCI), IEEE 488, IEEE 1284, and other suitable protocols. Where appropriate, serial and parallel communication can be bridged by a Universal Asynchronous Receiver Transmitter (UART), a Universal Synchronous Receiver Transmitter (USART), or other suitable subsystems.

[0059] External communication (including but not limited to software updates, firmware updates, preset sharing between the processor and the central server, or readouts from the circular ultrasound imaging array) can be accomplished using any suitable wireless or wired communication technology (e.g., cable interfaces such as Universal Serial Bus (USB), Micro USB, Lightning or FireWire, Bluetooth, Wi-Fi, ZigBee, Li-Fi) or cellular data connections (e.g., 2G / GSM (Global System for Mobile Communications), 3G / UMTS (Universal Mobile Telecommunications System), 4G, LTE, WiMax, or 5G)). For example, Bluetooth Low Energy (BLE) radios can be used to establish connections to cloud services, for data transfer, and for receiving software patches. The controller can be configured to communicate with remote servers or local devices (e.g., laptops, tablets, or handheld devices) or may include a display capable of showing status variables and other information. Information can also be transferred on physical media such as USB flash drives or memory sticks.

[0060] It should also be understood that one or more steps of the above method can be performed by one or more components of the ultrasound imaging system (e.g., a processing system, multiplexer, beamformer, signal processing unit, image processing unit, or any other suitable component of the system). For example, activating the scan sequence can be performed by a processor communicating with a multiplexer configured to select or activate one or more elements of the ultrasound transducer array. In some aspects, generating an ultrasound image may include beamforming an incoming signal from the ultrasound imaging device and processing the beamformed signal by an image processor. The system's processing components may be integrated within the ultrasound imaging device, contained in an external console, or may be separate components.

[0061] Figure 3 This is a schematic diagram of an endoluminal imaging catheter 102 retracted through the left renal artery 310 of the left kidney 320, according to various aspects of this disclosure. The imaging component 370 of the endoluminal imaging catheter 102 (e.g., an OCT imaging element or an ultrasound transducer array) can collect image data of structures outside the renal artery 310, thereby providing information about the location of the renal nerve at various points along the length of the renal artery 310, as well as information about other structures (e.g., lesions, fat deposits, calcifications, etc.) that may obstruct or otherwise interfere with the delivery of treatment energy to the renal nerve.

[0062] You can also see the abdominal aorta at 330°, the left renal vein at 340°, the right renal vein at 350°, and the right kidney at 360°.

[0063] Figure 4 This is a schematic diagram of an X-ray image 400 with contrast agent of the renal artery tree 405 according to various aspects of this disclosure. The abdominal aorta 330, left renal artery 310, left renal artery branch 410, right renal artery 350, and right renal artery branch 450 are visible. For example, X-ray images with contrast agent can be taken prior to RDN surgery to provide a route map of the renal artery tree 405 to help guide the surgery. Superimposed on the renal artery tree 405 is... Figure 3 The pull-back path 402 of the intravascular imaging device 102. For example, Figure 4 This could be a screen display that shows the renal artery tree as a roadmap image.

[0064] In some respects, instead of being based on angiography images, roadmap images can be 3D models of the renal artery tree or portions thereof constructed from CT image data.

[0065] Figure 5This is a representation of a lateral cross-sectional IVUS image 500 of the renal artery at a first location, according to various aspects of this disclosure. The imaging catheter 102, arterial lumen 510, arterial wall 520, surrounding tissue 530, renal nerve bundle 540, and calcifications or other obstructions 550 are visible. A first arrow DN indicates the distance from the arterial wall 520 to the distal nerve bundle 540. A second arrow DP indicates the depth of penetration of the renal denervation treatment (e.g., a radius of 5 mm from the center of the lumen). A third arrow DF indicates the depth of field of the IVUS imaging device 102 (e.g., a radius of 10 mm from the radial center of the imaging device 102).

[0066] exist Figure 5 In the example shown, one nerve bundle 540 is located outside the treatment penetration depth DP and is also blocked by calcification or other obstacles 550, so it is unlikely to be affected by RDN treatment. However, two nerve bundles 540 are located within the treatment penetration depth DP and are not blocked by obstacles, so they may be affected by RDN treatment. Based on this information, clinicians can determine whether the location is suitable for RDN treatment.

[0067] For example, U.S. Patent 9,615,878, filed December 20, 2013, describes the identification of the degree of ablation of nerve bundles in intravascular images, which is incorporated herein by reference as if the patent were fully set forth herein.

[0068] Figure 6 This is a representation of a lateral cross-sectional IVUS image 600 of the renal artery at a second location, different from the first location, according to various aspects of this disclosure. The imaging catheter 102, arterial lumen 510, arterial wall 520, surrounding tissue 530, and renal nerve bundle 540 are visible. Figure 6 In the example shown, one nerve bundle 540 is located outside the treatment penetration depth DP and is therefore unlikely to be affected by RDN treatment. However, another nerve bundle 540 is located within the treatment penetration depth DP and is not obstructed by any obstacles, and therefore may be affected by RDN treatment. Based on this information, clinicians can determine whether the location is suitable for RDN treatment.

[0069] In some examples, but not by limitation, clinicians may seek treatment locations where all nerve bundles are within the treatment penetration depth. In other examples, clinicians may seek treatment locations where at least one nerve bundle is within the treatment penetration depth. In still other examples, clinicians may select treatment locations where most nerve bundles are within the treatment penetration depth. Therefore, the RDN neural data co-registration system can compute data points with metrics for each image frame or location. Metrics may be, for example, or include, the average depth of nerve bundles, the minimum depth of nerve bundles, the maximum depth of nerve bundles, the number of nerve bundles visible in the frame, the size of one or more nerve bundles in the image frame, the number of nerve bundles within the treatment penetration depth, the number of nerve bundles weighted by their proximity to the renal artery wall, the distance between the renal artery boundary and one or more nerve bundles, the total area of ​​nerve bundles within the treatment penetration depth, the average size of nerve bundles, the density of nerve bundles within the frame, the density of nerve bundles within the treatment penetration depth, the volume of neural tissue over the imaging pullback length, or other metrics that a person skilled in the art would consider. One or more of these metrics can be used to help clinicians assess RDN treatability for each location associated with an intravascular image frame. Such a metric can also be derived from a 3D model based on CT image data rather than intravascular (e.g., IVUS or OCT) image data, and associated with a specific location along the renal artery where the metric was calculated. In either case, the metric represents the structure of one or more nerve bundles and represents the geometry, structural relationship, spatial relationship, or geometric relationship between the nerve bundle and the renal artery wall.

[0070] Figure 7A This is a schematic diagram 700 showing the co-registration of renal nerve data points 710 and angiographic route image 400 of the renal artery tree based on various aspects of this disclosure. Figure 7A In the example shown, the position of the imaging element 370 or the RDN treatment device 740 can be seen in frame 730 of a live fluorescence microscopy X-ray display taken during an RDN procedure. Each such position is associated with a renal nerve data point 710 derived from the intravascular image frame 720 along the pullback path 402, making it possible to add the renal nerve data point 710, along with the current position of the imaging array 370 or the RDN treatment device 740 (e.g., as a visual annotation), to the position of the intravascular image frame 720 on the pullback path 402 of the route map.

[0071] As indicated by arrow 764, because the pullback path 402 is associated with the fluorescence microscopy image 730, each position 741 along the path 402 can be associated with one or more fluorescence microscopy images 730. Furthermore, because a correspondence is also established between the fluorescence microscopy image 730 and the intravascular renal nerve data point 710, the data point 710 can also be associated with a position 741 along the path 402, as indicated by arrow 766. Just as different fluorescence microscopy images 730 and intravascular renal nerve data points 710 are associated with various positions along the pullback path 402, fluorescence microscopy images 730 and intravascular renal nerve data points 710 can be associated with the same positions along the route map image 400, as indicated by arrows 768 and 769.

[0072] Multiple neural bundle data points differ from multiple intravascular images. Figure 7B The image shows the common registration of the intravascular images themselves, rather than the common registration of the neural bundle data points.

[0073] Figure 7B This is a schematic diagram 700 showing the co-registration of an intravascular image frame 720 and an angiographic route map image 400 of the renal artery tree according to various aspects of this disclosure. Figure 7B In the example shown, the position of the imaging element 370 or the RDN treatment device 740 can be seen in frame 730 of a live fluorescence microscopy X-ray display taken during an RDN procedure. Each such position is associated with an intravascular image frame 720 along the pullback path 402, making it possible to show the intravascular image frame 720 together with the current position of the imaging array 370 or the RDN treatment device 740 (e.g., as a visual annotation) at the position of the intravascular image frame 720 on the pullback path 402 of the route map image 400.

[0074] As indicated by arrow 764, because the pullback path 402 is associated with the fluorescence microscopy image 730, each position 741 along the path 402 can be associated with one or more fluorescence microscopy images 730. Furthermore, because a correspondence is also established between the fluorescence microscopy image 730 and the intravascular image frame 720, the image frame 720 can also be associated with a position 741 along the path 402, as indicated by arrow 766. Just as different fluorescence microscopy images 730 and intravascular image frames 720 are associated with various positions along the pullback path 402, fluorescence microscopy images 730 and intravascular image frames 720 can be associated with the same positions along the route map image 400, as indicated by arrows 768 and 769.

[0075] In cases where the renal nerve images are derived from CT image data rather than intravascular data, the RDN neural data co-registration system will determine the mapping between the corresponding locations of the first three-dimensional (3D) model of the renal artery tree obtained from computed tomography (CT) imaging data and the second 3D model of the blood vessel obtained from X-ray angiography data.

[0076] For example, aspects of co-registration are described in U.S. Patent US7930014 entitled “Vascular Image co-registration” and U.S. Publication US2012 / 0004537 entitled “Co-use of endoluminal data and extraluminal imaging”. These documents are incorporated herein by reference as if their descriptions were fully contained herein.

[0077] Figure 8 This is an example of a co-registration screen display 800 for RDN neural data co-registration systems according to various aspects of this disclosure. The co-registration screen display 800 includes a route map image 400 of the renal artery tree 405, an image longitudinal display (ILD) 810, location markers 820 in both the ILD 810 and the route map image 400, and a tomographic intravascular image 720 associated with the location of the location markers 820. Figure 8 In the example shown, location marker 820 indicates the location of the nerve bundle 540 closest to the arterial wall 520. Text annotations 830 describing one or more locational characteristics can also be seen. This could, for example, include information about the renal nerve bundle adjacent to the wall 520 of the right renal artery 350. In some respects, the RDN neural data co-registration system can automatically identify and display the locations of anatomical structures most favorable for RDN treatment.

[0078] In other respects, the RDN neural data co-registration system can automatically identify and display multiple locations or ranges of locations for anatomical structures favorable for RDN treatment. Based on this information, clinicians can then apply human judgment to decide whether to perform RDN treatment at the identified location(s). In some respects, clinicians can drag location markers 820 along the renal artery 350 to view intravascular images 720 and text annotations 830 associated with each location along the renal artery. In such respects, the text annotations may be or include the renal nerve data points 710 of Figure 7.

[0079] Figure 9 This is a roadmap image screen display 900 for an example RDN neural data co-registration system based on various aspects of this disclosure. Figure 9In the example shown, location marker 820 has been used to mark two automatically identified locations along the left renal artery 310. These could be, for example, two locations where three nerve bundles fall within the RDN treatment depth. In the example, one location marker in location marker 820 marks locations where two nerve bundles are very close to the arterial wall (e.g., less than 1 mm from the arterial wall), while the other location marker in location marker 820 marks locations where one nerve bundle is very close to the arterial wall (e.g., less than 1 mm). Since either of these locations could potentially benefit from RDN treatment, the RDN neural data co-registration system has marked both of them on the screen display 900. The clinician can then decide whether to apply RDN treatment at either of the identified locations, at both locations, or at neither location.

[0080] Note that, depending on the implementation, angiographic images of the left and right renal arteries can be captured simultaneously; alternatively, angiographic images of the left and right renal arteries can be captured at different times and then combined into a single route map screen display 900.

[0081] Figure 10 The image shown on the screen is a roadmap image for an example RDN neural data co-registration system, based on various aspects of this disclosure. (Image 1000) Figure 10 In the example shown, multiple locations along the left renal artery 310 have been annotated with numerical displays 1010, which show the renal nerve measurement or data point for each location. The measurement or data point can be, for example, the distance from the artery wall to the nerve bundle (e.g., mean distance, median distance, minimum distance, maximum distance, or weighted average distance). These numerical displays can be, for example, dots 1020, where each dot represents a distance of one millimeter. This provides clinicians with a visual cue regarding whether treatment at a location with one or two dots 1020 may be more advantageous than treatment at a location with multiple dots 1020. In some respects, a location with zero dots may indicate one or more nerve bundles in direct contact with the artery wall, and a location marked with an "X" may indicate that no nerve bundle was identified at that location. In other respects, the numerical indicators can be bars of varying lengths, Arabic numerals, or other symbols. Clinicians can use this information to determine at which locations(s) along the length of artery 310 to apply RDN treatment.

[0082] Figure 11 The image on screen 1100 is a roadmap diagram of an example RDN neural data co-registration system based on various aspects of this disclosure. Figure 11In the example shown, the locations along the left renal artery 310 have been annotated with a color-coded display 1110, which shows a metric or data point at each location along the renal artery 310. The metric or data point can be, for example, the distance from the artery wall to the nerve bundle (e.g., mean distance, median distance, minimum distance, maximum distance, or weighted average distance). For example, a darker color can indicate areas where the nerve bundle is closer to the artery 310 (areas with more or more nerve clusters within the treatment penetration depth, etc.), while a lighter color can indicate areas where the nerve bundle is farther from the artery, areas where no nerve bundle was detected, etc. (or areas with fewer or zero nerve bundles within the treatment penetration depth). In other respects, these quantities can be indicated by red and green coloring, respectively, or by other combinations of hues, brightness, shading, etc., that effectively convey distance, nerve count, nerve density information, etc., to the clinician. The clinician can then use this information to determine at which (or which) locations along the length of the artery 310 (if any) to apply RDN treatment.

[0083] Figure 12 This is a schematic diagram in the form of a flowchart illustrating an example RDN neural data co-registration method 1200 based on various aspects of this disclosure. It should be understood that it can be used in conjunction with... Figure 12 The steps of method 1200 may be executed in different sequences as shown, with additional steps provided before, during, and after these steps, and / or some steps in the described steps may be replaced or eliminated in other embodiments. One or more steps of method 1200 may be executed by one or more devices and / or systems described herein (e.g., components of system 100 and / or processor circuitry 1050).

[0084] In step 1205, method 1200 includes receiving a first X-ray image of the renal artery for use as a route map image, in the presence of contrast agent fluid within the renal artery. The method then proceeds to step 1210.

[0085] In step 1210, method 1200 includes receiving a series of second X-ray images of the renal artery during the movement of an intravascular imaging catheter through the renal artery in the absence of contrast agent fluid inside the renal artery, and then the method proceeds to step 1215.

[0086] In step 1215, method 1200 includes: controlling an intravascular imaging catheter to obtain an intravascular image of the renal artery during catheter movement through the renal artery, the image depicting the nerve bundles adjacent to the renal artery. The method then proceeds to step 1220.

[0087] In step 1220, method 1200 includes: identifying neural bundles (if any) in an intravascular image. The method then proceeds to step 1225.

[0088] In step 1225, method 1200 includes: determining neural bundle data points, as described above. Figure 6 , Figure 7A and Figures 8 to 11 As described in the text. Then, the method proceeds to step 1230 and / or step 1240.

[0089] In step 1230, method 1200 includes: performing co-registration between nerve bundle data points and a first X-ray image (e.g., a roadmap image) of the renal artery, as described above. Figure 7A As described in the document. Then, the method proceeds to step 1240 and / or step 1245.

[0090] In step 1235, method 1200 optionally includes receiving one or more predicted RDN treatment locations from a trained machine learning model. In step 1240, method 1200 further includes determining the location of an indicator on the first X-ray image (e.g., a roadmap image) to guide the user to perform RDN treatment. Note that co-registration and machine learning algorithms can be used independently or together. One example includes displaying co-registered IVUS metrics adjacent to an angiographic image, while also displaying the predicted RDN treatment location from the machine learning algorithm. In some cases, the combination of co-registration and one or more machine learning indicators can guide the user to an optimal location or treatment area.

[0091] Then, the method proceeds to step 1245.

[0092] In step 1245, method 1200 includes: generating one or more screen displays to provide user guidance on where to perform RDN treatment on the renal artery, such as, for example, in Figure 8-11 As shown in the diagram. Then, the method proceeds to step 1250.

[0093] In step 1250, method 1200 includes: outputting a screen display to a video display (e.g., Figure 1 (Monitor 108). Then, the method optionally proceeds to step 1255.

[0094] In step 1255, method 1200 includes: for the clinician, performing RDN treatment based on user guidance provided in a screen display. Method 1200 is now complete.

[0095] This document provides flowcharts for illustrative purposes; those skilled in the art will recognize numerous variations that still fall within the scope of this disclosure. For example, any step described herein may optionally include outputting information related to that step to the user, thus representing an improvement in the user interface relative to the prior art by providing information that would otherwise not be available.

[0096] Similarly, the logic of a flowchart can be shown as sequential. However, similar logic can be parallel, massively parallel, object-oriented, real-time, event-driven, cellular automata, or otherwise, while simultaneously implementing the same or similar functionality. To execute the methods described herein, a processor can divide each step in the steps described herein into multiple machine instructions, and these instructions can be executed at rates of hundreds, thousands, millions, or billions per second, either on a single processor or across multiple processors. This rapid execution may be necessary to execute the method in real-time or near real-time, as described herein. For example, the identification of neural tracts, the computation of neural tract data points, and the co-registration of neural tract data points on a roadmap image can occur in real-time or near real-time.

[0097] Figure 13 This is a schematic diagram in the form of a block diagram representing an example machine learning model training process 1300 for identifying RDN treatment locations according to various aspects of this disclosure. The training process 1300 begins with a set of training data 1310, which includes data from a population of patients 1320. The data may include, for example, RDN treatment locations 1330, nerve bundle data points 1340, and post-RDN outcomes 1350 for each patient 1320 (e.g., reduction in systolic blood pressure at 3 or 6 months post-procedure). In other aspects, the data may include contrast-enhanced X-ray images (e.g., roadmap images) 1360 annotated with RDN treatment locations 1330, and intravascular images 1370 depicting nerve bundles and associated nerve bundle data points 1340.

[0098] These values ​​1330, 1340, 1350 (and possible images 1360, 1370) are used to train an untrained machine learning model 1380 with parameter A to produce a trained machine learning model 1390 with parameter B, which can be used in inference mode to compute the treatment location for a new patient. In one aspect, the machine learning model is a supervised learning model based on a multivariate regression model. In another aspect, the machine learning model is based on trained object detection techniques in computer vision; convolutional neural networks (e.g., AlexNet, Fast R-CNN, and Faster R-CNN) or one-step architectures (e.g., YOLO, SSD, and RetinaNet).

[0099] Figure 14 This is a schematic diagram in block form of an example machine learning model training system 1400 for calculating RDN treatment locations according to various aspects of this disclosure. The training system 1400 begins with a set of training data 1310, which includes data from a population of patients 1320. The data may include, for example, RDN treatment locations 1330, nerve bundle data points 1340, and post-RDN results 1350 (e.g., reduction in systolic blood pressure at 3 or 6 months post-procedure) for each patient 1320. In other aspects, the data may include contrast-enhanced X-ray images (e.g., roadmap images) 1360 annotated with RDN treatment locations 1330, and intravascular images 1370 depicting nerve bundles and associated nerve bundle data points 1340.

[0100] These values ​​1330, 1340, 1350 (and possibly images 1360, 1370) are used to train a predictive machine learning network or model 1410, which generates a predicted RDN treatment location 1320 for each patient 1320. These locations 1420 are then evaluated against a model objective or function 1430 (e.g., the difference between the RDN treatment location 1330 and the predicted RDN treatment location 1420, the difference between the RDN post-outcome 1350 and the expected RDN post-outcome associated with the predicted RDN treatment location 1420) to determine training success, and if the predicted RDN location 1420 falls below a threshold for the desired accuracy (e.g., used to predict the RDN post-outcome 1350), the parameters undergo repeated updates 1440 until the desired accuracy is achieved. In some instances, the updates 1440 may be performed using the gradient of the objective function and backpropagation to update the parameters of the predictive network 1410. In some embodiments, newly introduced patient data (e.g., within the context of a clinical trial) may be retrained and / or fine-tuned.

[0101] Figure 15This is a schematic diagram in the form of a block diagram of an example machine learning model inference pattern 1500 for calculating RDN treatment locations according to various aspects of this disclosure. A trained machine learning model 1410 receives data from a new patient 1510, which may include, for example, a first X-ray image 1520 of the new patient 1510 with contrast agent (e.g., a roadmap image), an intravascular image 1530 depicting nerve bundles, and / or calculated nerve bundle data points 1540. Based on this input data, the trained machine learning model 1410 generates one or more RDN treatment locations 1550, which the machine learning model 1410 determines are likely to produce a favorable treatment outcome (e.g., a reduction in systolic blood pressure of 5 mmHg or greater). This can, for example, provide clinicians with information to determine whether RDN surgery is necessary for the patient, and if so, information about which location(s) in the renal artery to perform the treatment.

[0102] Figure 16 It is a schematic diagram in the form of a flowchart of an example RDN disposal assessment process 1600 based on various aspects of this disclosure.

[0103] In step 1610, method 1600 includes performing co-registration between nerve bundle data points and X-ray images (e.g., roadmap images) of the renal artery with contrast agent prior to RDN treatment; and in step 1620, method 1600 includes generating / displaying a pre-RDN treatment screen display.

[0104] In step 1630, method 1600 includes: a clinician performing RDN treatment.

[0105] In step 1640, method 1600 includes performing co-registration between post-treatment neural bundle data points and X-ray images (e.g., roadmap images) of the renal artery with contrast agent.

[0106] In some respects, post-treatment nerve bundle data points are calculated in the same manner as pre-treatment nerve bundle data points. The ablation effect alters the material properties of the tissue, allowing computer vision systems to detect the presence of ablated and healthy nerves in the same frame, or to compare the presence of ablated and healthy nerves between pre-treatment and post-treatment images. In this context, clinicians can, for example, examine whether any healthy nerve fiber bundles are no longer present at any location along the renal artery within the RDN treatment depth, and if no healthy nerve fiber bundles are present at any location along the renal artery within the RDN treatment depth, the clinician can consider the treatment successful.

[0107] In other respects, post-treatment nerve bundle data points may, for example, be or include the level of nerve fiber ablation. In this case, clinicians may, for example, perform an examination to see if all selected treatment sites show 50% or greater ablation of the nerve fiber bundle within the RDN treatment depth, and if so, the treatment can be considered successful.

[0108] Other success metrics may be used alternatively or additionally, including but not limited to ablation area and / or ablation volume in posttreatment imaging data, percentage of thermal ablation within treatment penetration depth, ratio of thermal ablation volume or area to theoretical treatment volume or area, volume or area of ​​ablated nerve bundles, percentage of ablated nerve bundles, or percentage of ablation per nerve bundle.

[0109] In step 1640, method 1600 further includes: generating and displaying the processed screen display 1650.

[0110] Figure 17 This is a schematic diagram of a patient's renal vascular system 1700 according to various aspects of this disclosure, wherein a renal denervation treatment device 1710 is located in the left renal artery 1720 of the left kidney 1740. In one example, the renal denervation treatment device 1710 may include a catheter 1750 having a renal denervation tool (e.g., electrodes, balloon, etc.) that delivers energy to damage the renal nerve in order to lower the patient's blood pressure. Depending on the implementation, the delivered energy may be electrical, chemical, thermal, cold, etc. The renal denervation treatment device 1710 may, for example, enter the renal artery 1720 via the abdominal aorta 1760. The renal vein 1730 may also be visible.

[0111] A system of one or more computers can be configured to perform specific operations or actions by installing software, firmware, hardware, or combinations thereof on the system, which, in operation, causes the system to perform those actions. One or more computer programs can be configured to perform specific operations or actions by including instructions that, when executed by a data processing device, cause that device to perform those actions. One general aspect includes an apparatus comprising processor circuitry configured to communicate with an intravascular imaging catheter, wherein the processor circuitry is configured to: control the intravascular imaging catheter to acquire multiple intravascular images during movement of the catheter along the length of a renal artery, wherein the multiple intravascular images depict one or more nerve bundles for targeting during a renal denervation procedure; perform a common registration between: multiple nerve bundle data points representing the one or more nerve bundles and associated with a treatment location along the length of the renal artery for the renal denervation procedure; and a first X-ray image of the renal artery, obtained with contrast agent present within the renal artery; and output a screen display configured to guide a user regarding the renal denervation procedure, wherein the screen display is based on the common registration. Other embodiments of this aspect include corresponding computer systems, apparatuses, and computer programs recorded on one or more computer storage devices, all configured to perform the actions of the method.

[0112] Implementations may include one or more of the following features. In some aspects, the screen display may include a first X-ray image superimposed with multiple representations of the plurality of nerve bundle data points, wherein each of the plurality of representations is located at the same position as one of the plurality of nerve bundle data points. In some aspects, each representation may include a plurality of dots proportional to the value of a corresponding data point among the plurality of nerve bundle data points. In some aspects, the processor circuitry is configured to perform the co-registration between the plurality of intravascular images and the first X-ray image separately from the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery. In some aspects, each representation may include a color or shading corresponding to the value of a corresponding data point among the plurality of nerve bundle data points. In some aspects, the screen display may further include location markers indicating the location along the renal artery. In some aspects, the screen display may further include a tomographic image of the renal artery at the location indicated by the location markers. In some aspects, the tomographic image may include a nerve bundle corresponding to the nerve bundle data point at the location indicated by the location markers. In some aspects, the location indicated by the location marker is a treatment location selected by a trained machine learning model. In some aspects, the screen display further includes a longitudinal image display, wherein the location marker appears on both the longitudinal image display and the first X-ray image. In some aspects, after performing the co-registration between the plurality of nerve bundle data points and the first X-ray image, the plurality of nerve bundle data points are each associated with a plurality of locations along the length of the renal artery. In some aspects, the plurality of nerve bundle data points may include at least one of the following: the distance between the boundary of the renal artery and the one or more nerve bundles; the number of the one or more nerve bundles; the size of the one or more nerve bundles; or the number of the one or more nerve bundles located within the penetration depth of the renal denervation treatment device used to perform the renal denervation treatment. In some aspects, the plurality of nerve bundle data points differ from the plurality of intravascular images. In some aspects, in order to perform the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery, the processor circuitry is configured to: receive the first X-ray image of the renal artery; receive multiple second X-ray images of the renal artery during movement of the intravascular imaging catheter, wherein the multiple second X-ray images are obtained without contrast agent within the renal artery and depict multiple locations of the intravascular imaging catheter during the movement; and use the multiple second X-ray images to perform the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery.Implementations of the described technology may include hardware, methods or processes, or computer software on a computer-accessible medium.

[0113] One general aspect includes a method. The method includes: controlling an intravascular imaging catheter in communication with the processor circuitry to acquire multiple intravascular images during movement of the intravascular imaging catheter along the length of a renal artery, wherein the multiple intravascular images depict one or more nerve bundles for targeting during a renal denervation procedure; utilizing the processor circuitry to perform a common registration between: multiple nerve bundle data points representing the one or more nerve bundles and associated with a treatment location along the length of the renal artery for the renal denervation procedure; and an X-ray image of the renal artery obtained with contrast agent present within the renal artery; and outputting a screen display to a display in communication with the processor circuitry, the screen display being configured to guide a user regarding the renal denervation procedure, wherein the screen display is based on the common registration. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, all configured to perform the actions of the method.

[0114] Therefore, it can be seen that the RDN neural data co-registration system advantageously provides a means for determining the most favorable location for RDN treatment within the left or right renal artery in real time during surgery. The RDN neural data co-registration system also provides a means of determining whether the RDN procedure is complete (e.g., whether the renal nerve bundle has been adequately ablated at the desired location). Clinicians can use the screen display 1650 to determine whether RDN treatment is complete or whether further treatment is needed to adequately ablate the renal nerve fiber bundle at the desired location.

[0115] Numerous variations are possible in the examples and aspects described above. For instance, variables other than those listed herein can be used, and different sensors or sensor types can be employed. The techniques described herein can be used not only before and during medical interventions but also at other times to provide measures that can indicate a patient's health or disease status.

[0116] Therefore, the logical operations constituting the various aspects of the technology described herein are referred to differently as operations, steps, objects, elements, components, or modules. Furthermore, it should be understood that these logical operations can occur, be performed, or be arranged in any order unless otherwise expressly stated or the language of the claims inherently requires a specific order.

[0117] All directional references (e.g., up, down, inside, outside, upward, downward, left, right, lateral, front, back, top, bottom, above, below, vertical, horizontal, clockwise, counterclockwise, proximal, and distal) are used for illustrative purposes only to aid the reader in understanding the claimed subject matter and (particularly with respect to the location, orientation, or use of RDN neural data co-registration systems) do not impose limitations. Connectivity references (e.g., attachment, coupling, connection, joining, or “connected to”) should be interpreted broadly and, unless otherwise stated, can include intermediate components between sets of elements and relative movement between elements. Therefore, a connectivity reference does not necessarily mean that two elements are directly connected and fixed to each other. The term “or” should be interpreted as “and / or” rather than “exclusive or”. The word “comprising” does not exclude other elements or steps, and the quantifiers “a” or “an” do not exclude a plurality. Unless otherwise indicated in the claims, the stated values ​​should be interpreted as illustrative only and not as limiting.

[0118] The foregoing descriptions, examples, and data provide a complete description of the structure and use of exemplary aspects of the RDN neural data co-registration system as defined in claims. While various aspects of the claimed subject matter have been described above with a degree of specificity or by reference to one or more individual aspects, those skilled in the art can make numerous changes to the disclosed aspects without departing from the spirit or scope of the claimed subject matter.

[0119] Other aspects are also anticipated. All that is contained in the above description and shown in the accompanying drawings is intended to be illustrative of specific aspects and not limiting. Changes in detail or structure may be made without departing from the essential elements of the subject matter as defined in the following claims.

[0120] Another embodiment.

[0121] Example 1: An apparatus comprising:

[0122] A processor circuit configured to communicate with an intravascular imaging catheter, wherein the processor circuit is configured to:

[0123] The intravascular imaging catheter is controlled to acquire multiple intravascular images during its movement along the length of the renal artery, wherein the multiple intravascular images depict one or more nerve bundles for targeting during renal denervation treatment.

[0124] Perform a common registration between the following two:

[0125] Multiple nerve bundle data points, representing one or more nerve bundles, and associated with treatment locations along the length of the renal artery for the renal denervation treatment; and

[0126] The first X-ray image of the renal artery was obtained with contrast agent present inside the renal artery; and

[0127] A screen display is output to a monitor, the screen display being configured to guide the user regarding the renal denervation procedure, wherein the screen display is based on the co-registration.

[0128] Example 2: The apparatus according to Example 1, wherein the screen displays a first X-ray image including a plurality of representations superimposed with the plurality of neural bundle data points, wherein each of the plurality of representations is located at the same position as one of the plurality of neural bundle data points.

[0129] Example 3: The apparatus according to Example 2, wherein each represents a plurality of points that are proportional to the values ​​of corresponding data points in the plurality of neural bundle data points.

[0130] Example 4: The apparatus according to Example 2, wherein each representation includes a color or shading corresponding to the value of the corresponding data point among the plurality of nerve bundle data points.

[0131] Example 5: The apparatus according to Example 2, wherein the screen display further includes a location marker indicating the location along the renal artery.

[0132] Example 6: The apparatus according to Example 5, wherein the screen display further includes a tomographic image of the renal artery at the location indicated by the location marker.

[0133] Example 7: The apparatus according to Example 6, wherein the tomographic image includes a nerve bundle corresponding to a nerve bundle data point at the location indicated by the location marker.

[0134] Example 8: The apparatus according to Example 5, wherein the location indicated by the location marker is a disposal location selected by a trained machine learning model.

[0135] Example 9: The apparatus according to Example 5, wherein the screen display further includes a portrait image display, and wherein the position mark appears on both the portrait image display and the first X-ray image.

[0136] Example 10: The apparatus according to Example 1, wherein, after performing the co-registration between the plurality of nerve bundle data points and the first X-ray image, the plurality of nerve bundle data points are respectively associated with a plurality of locations along the length of the renal artery.

[0137] Example 11: The apparatus according to Example 1, wherein the plurality of neural bundle data points includes at least one of the following:

[0138] The distance between the boundary of the renal artery and the one or more nerve bundles;

[0139] The number of one or more nerve bundles;

[0140] The size of the one or more nerve bundles; or

[0141] The number of one or more nerve bundles located within the penetration depth of the renal denervation device used to perform the renal denervation procedure.

[0142] Example 12: The device according to Example 1, wherein the plurality of nerve bundle data points are different from the plurality of intravascular images.

[0143] Example 13: The apparatus according to Example 3, wherein the processor circuitry is configured to perform the co-registration between the plurality of intravascular images and the first X-ray image separately from the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery.

[0144] Example 14. The apparatus according to Example 1, wherein, in order to perform the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery, the processor circuit is configured to:

[0145] Receive the first X-ray image of the renal artery;

[0146] Multiple second X-ray images of the renal artery are received during the movement of the intravascular imaging catheter, wherein the multiple second X-ray images are obtained without contrast agent within the renal artery, and depict multiple locations of the intravascular imaging catheter during the movement; and

[0147] The multiple second X-ray images are used to perform the co-registration between the multiple nerve bundle data points and the first X-ray image of the renal artery.

[0148] Example 15: A method comprising:

[0149] The intravascular imaging catheter, which communicates with the processor circuitry, is controlled by a processor circuitry to acquire multiple intravascular images as the catheter moves along the length of the renal artery. These multiple intravascular images depict one or more nerve bundles for targeting during renal denervation treatment.

[0150] The processor circuitry is used to perform a common registration between the following two items:

[0151] Multiple nerve bundle data points, representing one or more nerve bundles, and associated with treatment locations along the length of the renal artery for the renal denervation treatment; and

[0152] The X-ray image of the renal artery, obtained with contrast agent present inside the renal artery; and

[0153] A screen display is output to a display that communicates with the processor circuitry, the screen display being configured to guide the user regarding the renal denervation procedure, wherein the screen display is based on the co-registration.

[0154] Example 16: A method comprising:

[0155] The processor circuitry is used to perform the following common registration:

[0156] Multiple nerve bundle data points, representing one or more nerve bundles targeted during renal denervation procedures, and associated with a treatment location along the length of the renal artery for the renal denervation procedure, the one or more nerve bundles being depicted within multiple intravascular images obtained by moving the intravascular imaging catheter along the said length of the renal artery; and

[0157] The X-ray image of the renal artery, obtained with contrast agent present inside the renal artery; and

[0158] Output a screen display to a display communicating with the processor circuitry, the screen display being configured to guide the user regarding the renal denervation procedure, wherein the screen display is based on the co-registration; and

[0159] Optionally, the display is controlled to output the screen display to the user.

[0160] Example 17, the method of claim 16, further includes using a processor circuit to perform the following operations: using the processor circuit to control an intravascular imaging catheter communicating with the processor circuit to acquire multiple intravascular images during movement of the intravascular imaging catheter along the length of the renal artery, wherein the multiple intravascular images depict one or more nerve bundles for targeting during renal denervation treatment.

[0161] Example 18: A computer program including instructions that, when executed, cause the implementation of the method according to Example 16 or 17.

[0162] Example 19: A computer program including instructions that, when executed, cause the computer program according to Example 18 to be executed.

[0163] Example 20: The computer program according to Example 19, when executed, causes: the display to output the screen display to the user; and optionally causes the screen display to be output to the display.

Claims

1. A processor circuit configured for communication with an intravascular imaging catheter, wherein, The processor circuit is configured as follows: Perform a common registration between the following two: Multiple nerve bundle data points, representing one or more nerve bundles targeted during renal denervation procedures, and associated with the procedure location for the renal denervation procedure along the length of the renal artery, wherein the one or more nerve bundles are depicted within multiple intravascular images obtained by moving the intravascular imaging catheter along the said length of the renal artery; and The first X-ray image of the renal artery was obtained with contrast agent present inside the renal artery. as well as A screen display is output to a monitor, the screen display being configured to guide the user regarding the renal denervation procedure, wherein the screen display is based on the co-registration.

2. The processor circuit according to claim 1, wherein, The screen displays a first X-ray image comprising multiple representations of the plurality of nerve bundle data points superimposed on it, wherein each of the plurality of representations is located at the same position as one of the plurality of nerve bundle data points.

3. The processor circuit according to claim 2, wherein, Each of the plurality of representations includes a plurality of dots that are proportional to the value of the corresponding data point in the plurality of neural bundle data points; or Each of the plurality of representations includes a color or shading corresponding to the value of a corresponding data point in the plurality of neural bundle data points.

4. The processor circuit according to any one of the preceding claims, wherein, The screen display also includes location markers indicating the position along the renal artery.

5. The processor circuit according to claim 4, wherein, The screen display also includes a tomographic image of the renal artery at the location indicated by the location marker, wherein the tomographic image includes a nerve bundle corresponding to a nerve bundle data point at the location indicated by the location marker.

6. The processor circuit according to claim 4, wherein, The location indicated by the location marker is a disposal location selected by a trained machine learning model.

7. The processor circuit according to claim 4, wherein, The screen display also includes a portrait image display, wherein the position marker appears on both the portrait image display and the first X-ray image.

8. The processor circuit according to any one of the preceding claims, wherein, After performing the co-registration between the plurality of nerve bundle data points and the first X-ray image, the plurality of nerve bundle data points are associated with a plurality of locations along the length of the renal artery.

9. The processor circuit according to any one of the preceding claims, wherein, The plurality of nerve bundle data points includes at least one of the following: The distance between the boundary of the renal artery and the one or more nerve bundles; The number of one or more nerve bundles; The size of the one or more nerve bundles; or The number of one or more nerve bundles located within the penetration depth of the renal denervation device used to perform the renal denervation procedure.

10. The processor circuit according to any one of the preceding claims, wherein, The multiple nerve bundle data points are different from the multiple intravascular images.

11. The processor circuit according to claim 3, wherein, The processor circuitry is configured to perform the co-registration between the multiple intravascular images and the first X-ray image separately from the co-registration between the multiple nerve bundle data points and the first X-ray image of the renal artery.

12. The processor circuit according to any one of the preceding claims, wherein, In order to perform the co-registration between the plurality of nerve bundle data points and the first X-ray image of the renal artery, the processor circuitry is configured to: Receive the first X-ray image of the renal artery; Multiple second X-ray images of the renal artery are received during the movement of the intravascular imaging catheter, wherein the multiple second X-ray images are obtained without contrast agent within the renal artery, and depict multiple locations of the intravascular imaging catheter during the movement; and The multiple second X-ray images are used to perform the co-registration between the multiple nerve bundle data points and the first X-ray image of the renal artery.

13. An apparatus comprising a processor circuit according to any one of claims 1-12, the apparatus comprising at least one of the following: a display device for communicating with the processor circuit, or the intravascular imaging catheter.

14. A method comprising: The processor circuitry is used to perform the following common registration: Multiple nerve bundle data points, representing one or more nerve bundles targeted during renal denervation procedures, and associated with a treatment location along the length of the renal artery for the renal denervation procedure, the one or more nerve bundles being depicted within multiple intravascular images obtained by moving the intravascular imaging catheter along the said length of the renal artery; and The X-ray image of the renal artery, obtained with contrast agent present inside the renal artery; and Output a screen display to a display communicating with the processor circuitry, the screen display being configured to guide the user regarding the renal denervation procedure, wherein the screen display is based on the co-registration; and Optionally, the display is controlled to output the screen display to the user.

15. A computer program comprising instructions that, when executed, cause the computer program comprising the following instructions: the instructions, when executed, cause the implementation of the method according to claim 14.

Images