Delivery of therapeutic neuromodulation

Abstract

The embodiments disclosed in this application relate to techniques for neuromodulation delivery. Based on image data acquired from a subject, control parameters for the energy application of neuromodulation energy can be dynamically varied during delivery to maintain the desired characteristics of the neuromodulation energy. For example, the neuromodulation energy bundle can be dynamically adjusted to address organ movement during respiration. In another embodiment, a desired region of interest is identified within the subject based on a trained neural network and acquired image data.

Description

Background Technology

[0001] The subject matter disclosed herein relates to identifying, targeting, and / or administering medication to regions of interest (regions of concern) within a subject via the application of neuromodulatory energy to elicit targeted physiological outcomes. Specifically, the disclosed techniques may be part of a personalized treatment protocol.

[0002] Neuromodulation has been used to treat a variety of clinical conditions. For example, electrical stimulation along different sites of the spinal cord has been used to treat chronic back pain. However, positioning electrodes at or near target nerves is challenging. For instance, such techniques may involve the surgical placement of electrodes that deliver energy. Furthermore, tissue-specific targeting via neuromodulation is challenging. Electrodes located at or near certain target nerves mediate neuromodulation by triggering action potentials in nerve fibers, which in turn leads to the release of neurotransmitters at the synapses and synaptic communication with the next nerve. This delivery can result in relatively larger or more diffuse physiological effects than desired, as the current implementation of implanted electrodes stimulates many nerves or axons at once. Due to the complexity and interconnectedness of neural pathways, more selective and targeted (targeted) modulation may be more clinically useful. However, the effectiveness of selectively targeting specific nerves may depend on the accurate positioning of the energy application device. The accurate focusing of neuromodulation energy can vary depending on individual patient anatomy. For example, some patients may have variations in organ size or location relative to others based on height, weight, age, sex, clinical condition, etc. In addition, patients may exhibit anatomical changes over time, or this may complicate the accuracy of energy delivery. Summary of the Invention

[0003] The disclosed embodiments are not intended to limit the scope of the claimed subject matter, but are merely intended to provide a brief overview of possible implementations. In fact, this disclosure may cover a variety of forms that may be similar to or different from the embodiments set forth below.

[0004] In one embodiment, a neuromodulation delivery system is provided. The system includes an energy application device configured to deliver neuromodulation energy to a region of interest within a subject. The system also includes a controller configured to receive image data of the subject's internal tissue; identify the region of interest within the image data; control the application of neuromodulation energy via the energy application device to the identified region of interest to deliver a dose of neuromodulation energy (a specific dose of neuromodulation energy); receive updated image data of the subject's internal tissue before dose delivery is complete; identify positional changes of the region of interest relative to the energy application device based on the updated image data; and adjust the application of neuromodulation energy via the energy application device based on the changed position of the region of interest to continue delivering the dose of neuromodulation energy to treat the subject.

[0005] In another embodiment, a method for delivering neuromodulation energy is provided. The method includes the steps of: delivering energy to a region of interest (ROI) of a subject using control parameters, wherein the energy is a portion of the total energy of an individual dose (single dose) to be applied to the RIO, and wherein the energy is applied using an energy application device; acquiring image data from the subject concurrently with energy delivery and prior to the application of the total individual dose, the image data representing (characterizing) the internal tissue including the RIO; identifying positional changes of the RIO relative to the energy application device based on the image data; adjusting one or more control parameters in the set of control parameters based on the positional changes of the RIO; and delivering additional energy to the RIO using the adjusted control parameters to deliver another portion of the total individual dose of energy using the energy application device.

[0006] In another embodiment, a neuromodulation delivery system is provided. The system includes an energy application device configured to deliver neuromodulation energy to a region of interest within a subject. The system also includes a controller configured to control the energy application device to acquire image data representing the subject's internal tissue; to identify regions of interest based on the image data using a neural network trained on image data of respective internal tissues of a group of subjects, wherein the respective internal tissues are of the same type as the subject's internal tissues; to control the application of neuromodulation energy via the energy application device to the identified regions of interest to treat the subject by delivering a dose of neuromodulation energy; to acquire updated image data simultaneously with the dose delivery; and to dynamically change one or more control parameters controlling the application of the neuromodulation energy based on the updated image data. Attached Figure Description

[0007] These and other features, aspects, and advantages of the invention will be better understood when the following detailed description is read with reference to the accompanying drawings, wherein the same characters denote the same parts throughout the drawings, wherein:

[0008] Figure 1 This is a schematic diagram of an autonomic nervous system modulation and delivery system according to an embodiment of the present disclosure;

[0009] Figure 2 This is a block diagram of an autonomic nervous system modulation and delivery system according to an embodiment of the present disclosure;

[0010] Figure 3 This is a schematic diagram of an autonomic neural modulation delivery system according to an embodiment of the present disclosure, which applies neural modulation energy to a region of interest within a tissue including anatomical structures.

[0011] Figure 4 This is a schematic diagram of an autonomic neural modulation delivery system for tracking moving regions of interest according to an embodiment of the present disclosure;

[0012] Figure 5 Based on Figure 4 A schematic diagram of the applied energy for the movement identified in the diagram;

[0013] Figure 6 This is a flowchart of an autonomic neural modulation and delivery technology according to an embodiment of the present disclosure;

[0014] Figure 7 This is a schematic diagram of the input to a neural network according to an embodiment of the present disclosure;

[0015] Figure 8 This is a flowchart of an autonomic neural modulation and delivery technology according to an embodiment of the present disclosure;

[0016] Figure 9 This is a block diagram of an example of an autonomic neural modulation delivery system including dual imaging and therapeutic probes according to embodiments of the present disclosure;

[0017] Figure 10 yes Figure 9 Images from dual imaging and treatment probes;

[0018] Figure 11 This is an example graphical user interface of an autonomic neural modulation and delivery system according to embodiments of the present disclosure;

[0019] Figure 12 This is an example graphical user interface of an autonomic neural modulation delivery system during alignment with a region of interest, according to an embodiment of this disclosure;

[0020] Figure 13This is an example graphical user interface of an autonomic neural modulation delivery system during the delivery of neural modulation energy to a region of interest according to embodiments of the present disclosure;

[0021] Figure 14 This is an example graphical user interface of an autonomic neural modulation delivery system according to embodiments of the present disclosure, after completing the delivery of neural modulation energy to the region of interest; and

[0022] Figure 15 An example of organ identification using an autonomic neural modulation delivery system according to an embodiment of the present disclosure is shown. Detailed Implementation

[0023] One or more specific implementations will be described below. To provide a concise description of these implementations, not all features of the actual implementation are described in this specification. It should be understood that, as in any engineering or design project, many implementation-specific decisions must be made to achieve the developer's specific goals, such as complying with system-related and business-related constraints, which may vary from implementation to implementation. Furthermore, it should be understood that such development work may be complex and time-consuming, but remains routine work for design, production, and manufacturing for those skilled in the art who benefit from this disclosure.

[0024] Any examples or descriptions given herein should not be construed in any way as limiting, defining, or explicitly defining any one or more terms used with them. Rather, these examples or descriptions should be considered as descriptions of various specific implementations and are merely illustrative. Those skilled in the art will understand that any one or more terms used with these examples or descriptions will cover other implementations that may or may not be given with them or elsewhere in the specification, and all such implementations are intended to be included within the scope of such one or more terms. The language used to designate such non-limiting examples and descriptions includes, but is not limited to, “for example,” “e.g.,” “such as,” “for instance,” “including,” “in some implementations,” “in some implementations,” and “in one implementation.”

[0025] This article provides a region-of-interest (ROI) targeting neuromodulation technique as part of a treatment protocol, which allows for the reproducible and reliable application of energy to one or more specific ROIs during the treatment protocol. The disclosed technique provides autonomous delivery of neuromodulated energy that induces and dynamically modulates one or more parameters of delivery based on changes in the position of the desired energy target (e.g., ROI) during delivery, so that delivery does not require interruption. For example, while a patient may be instructed to remain still during neuromodulated energy delivery, minute changes in patient position or even breathing can cause movement of internal organs, potentially altering the position of the target relative to an external or extracorporeal energy application device (e.g., an ultrasound therapy probe). Because neuromodulated energy can be focused on a tissue volume including a specific axonal terminus or a group of axonal termins within the tissue (and conversely, excluding other axonal termins present in the tissue), slight tissue movement can cause the focal area of ​​the energy application device to shift from the ROI to an adjacent area of ​​tissue excluding the desired axonal terminus, thus potentially failing to achieve the physiological outcomes associated with neuromodulation of the desired axonal terminus. Even movement of the region of interest within millimeters or centimeters can lead to inaccurate application of neuromodulation energy, which may prevent the desired therapeutic goal from being achieved.

[0026] To address tissue movement within a time frame (time frame) of one or more doses of neuromodulated energy, the delivery area can be expanded beyond the region of interest (ROI) to address minute movements. However, depending on the specific ROI, this approach may reduce the desired treatment specificity by exposing other axonal terminals to neuromodulated energy, potentially causing confounding physiological effects that could undermine or interfere with the intended therapeutic target. Furthermore, this approach may limit the total dose delivery during a single treatment by exposing a larger volume of tissue to energy, potentially reaching per-dose energy limits more quickly before delivering the desired dose to the ROI.

[0027] This technology allows for the accurate delivery of neuromodulated energy. It is user-friendly and eliminates or reduces the anatomical guidance input required by trained clinicians, thus allowing less experienced caregivers to manage (treatment, therapy) at home or in an outpatient setting, thereby expanding treatment options. Furthermore, while trained clinicians can identify anatomical landmarks to accurately guide energy delivery, each clinician may introduce their own preference biases during treatment, which can interfere with accurate dosing over time, especially when multiple clinicians are involved in the care. This technology provides less experienced caregivers with a tool to deliver neuromodulated energy as part of a treatment protocol.

[0028] In one implementation, the disclosed technique combines imaging data acquired before and / or during the processing period to track movement over time in a region of interest, enabling real-time refocusing or redirection of energy to maintain energy delivery on or within the region of interest. Imaging data can be acquired using a multifunctional device configured to acquire image data and deliver neurally modulated energy. In one example, a neural network is used to identify organs comprising regions, regions of interest, anatomical structures, or combinations thereof. Once identified, movement can be tracked based on ongoing or updated image data.

[0029] Neural networks can be trained on images from a population of subjects to rapidly identify organs or other tissues including regions of interest (ROIs), in some implementations without operator intervention. The neural network architecture can involve layers that allow for the identification of structures based on morphology, pattern matching, edge recognition, etc. The neural network can also be configured to identify ROIs within organs or tissues. For example, if the ROI corresponds to the hilum region of the liver, the neural network can be trained on a ground truth image of the population to identify ROIs that may contain or overlap with the hilum region of a specific subject.

[0030] Therefore, the disclosed neuromodulation delivery technology can be used in conjunction with a neuromodulation system configured to deliver neuromodulation energy as part of a processing scheme. Figure 1 This is a schematic diagram of a system 10 for neuromodulation to achieve neuromodulatory effects in response to energy application, such as neurotransmitter release and / or activation of synaptic components (e.g., presynaptic and postsynaptic cells). The depicted system includes a pulse generator 14 coupled to an energy application device 12 (e.g., an ultrasound transducer). The energy application device 12 is configured to receive energy pulses, for example, via a lead or wireless connection, which, in use, are directed to a region of interest within the subject's internal tissues or organs, thereby leading to targeted physiological outcomes.

[0031] In some embodiments, the energy application device 12 and / or pulse generator 14 may, for example, communicate wirelessly with a controller 16, which in turn may provide instructions to the pulse generator 14. In other embodiments, the energy application device 12 may be an external device, for example operable to apply energy percutaneously or non-invasively from a site outside the subject, and in some embodiments, may be integrated with the pulse generator 14 and / or controller 16. In embodiments where the energy application device 12 is external, the energy application device 12 may be operated by a caregiver and positioned at a site on or above the subject's skin, such that energy pulses are delivered transdermally to the desired internal tissue. Once positioned to apply energy pulses to the desired site, the system 10 may initiate neuromodulation of one or more neural pathways to achieve targeted physiological outcomes or clinical effects. In other embodiments, the pulse generator 14 and / or energy application device 12 may be implanted in a biocompatible site (e.g., the abdomen) and may be internally coupled, for example, via one or more leads. In some embodiments, the system 10 may be implemented such that some or all of the components can communicate with each other in a wired or wireless manner.

[0032] In some embodiments, system 10 may include an evaluation device 20 coupled to controller 16 and evaluating features indicating whether a targeted physiological outcome of modulation has been achieved. In one embodiment, the targeted physiological outcome may be localized. For example, modulation of one or more neural pathways may result in local tissue or functional changes, such as changes in tissue structure, localized changes in the concentration of certain molecules, tissue displacement, increased fluid movement, etc. The targeted physiological outcome may be the goal of the treatment protocol.

[0033] Modulating one or more neural pathways to achieve a targeted physiological outcome may result in systemic or non-local changes, and the targeted physiological outcome may be related to changes in circulating molecular concentrations or changes in tissue properties (excluding the region of interest to which energy is directly applied). In one example, displacement may be an alternative measure (representative metric) of the desired modulation, and displacement measurements below the desired displacement value may lead to modifications of the modulation parameters until the desired displacement value is induced. Therefore, in some embodiments, the assessment device 20 may be configured to assess concentration changes. In some embodiments, the assessment device 20 may be an imaging device configured to assess changes in organ size, location, and / or tissue characteristics. In another embodiment, the assessment device 20 may be a circulating glucose monitor. Although the depicted elements of system 10 are shown individually, it should be understood that some or all of the elements may be combined with each other. In another embodiment, the assessment device may assess a local temperature rise in tissue, which may be detected using a separate temperature sensor or ultrasound imaging data from the energy application device 12 when configured for ultrasound energy application. The assessment of differences in sound velocity can be detected using different imaging techniques before / during / after treatment.

[0034] Based on this assessment, the adjustment parameters of controller 16 can be changed to deliver an effective amount of energy. For example, if adjustment is desired to be associated with changes in concentration (circulating or tissue concentration of one or more molecules) within a defined time window (e.g., 5 minutes or 30 minutes after the start of the energy application program) or relative to a baseline at the start of the program, changes in adjustment parameters (such as pulse frequency or other parameters) may be desired. This can then be provided to controller 16 by the operator or via an automated feedback loop to define or adjust the energy application parameters or adjustment parameters of pulse generator 14 until the adjustment parameters produce an effective amount of applied energy. As provided herein, data from assessment device 20 can be provided as part of a feedback loop to train each individual's neural network as part of a treatment protocol and / or redirect or refocus energy to address movement of the region of interest during treatment. In one embodiment, the initially defined region of interest can be refined based on feedback from the assessment device regarding the effectiveness of the neuromodulation energy during the treatment protocol to produce an updated region of interest. Feedback can be, for example, changes in the concentration of the molecule of interest due to the application of neuromodulation energy. These refinements or updates to regions of interest can be used as part of a patient-specific network, where the network is updated to identify specific regions of interest that have the greatest impact on the physiological parameters of interest for a particular individual, based on expected clinical outcomes.

[0035] The system 10 provided herein can provide energy pulses as part of a treatment protocol to apply an effective amount of energy, based on various modulating parameters. For example, modulating parameters can include various stimulation time patterns ranging from continuous to intermittent. For intermittent stimulation, energy is delivered at a certain frequency for a period of time during the signal-on period. Following the signal-on period is a period of time without energy delivery, referred to as the signal-off period. Modulating parameters can also include the frequency and duration of stimulation application. The application frequency can be continuous or delivered at different time intervals, such as within a day or week. Furthermore, the treatment protocol can specify the time of day for energy application or relative to the time of eating or other activities. The duration of treatment that elicits targeted physiological outcomes can last for different time periods, including but not limited to minutes to hours. In some embodiments, the duration of treatment with a specific stimulation pattern can last for one hour, repeated at intervals such as 72 hours. In some embodiments, energy can be delivered at a higher frequency, such as once every three hours, for a shorter duration, such as 30 minutes. Depending on the modulating parameters, such as treatment duration, frequency, and amplitude, the application of energy can be adjusted to obtain the desired outcome.

[0036] Figure 2 This is a block diagram of some components of system 10. As provided herein, system 10 for neuromodulation may include a pulse generator 14 adapted to generate multiple energy pulses for application to tissues of a subject. Pulse generator 14 may be standalone or may be integrated into an external device, such as controller 16. Controller 16 includes a processor 30 for controlling the device. Software code or instructions are stored in memory 32 of controller 16 and executed by processor 30 to control various components of the device. Controller 16 and / or pulse generator 14 may be connected to energy application device 12 via one or more leads 33 or wirelessly. Processor 30 may be configured to access software from memory 32 to operate a neural network previously trained on images of other subjects (e.g., not necessarily the subject being treated). Furthermore, processor may be configured to allow updating of the neural network based on image data of the subject of interest.

[0037] The controller 16 may include a user interface with input / output circuitry 34 and a display 36 adapted to allow clinicians to provide selection inputs or adjustment parameters to the treatment procedure. However, some implementations of the system 10 may also include implementations without a display 36 providing feedback using sound or light. For example, a relatively simple home system 10 may or may not have a display 36 and is configured not to provide inexperienced users with information unhelpful in achieving the treatment objectives. The processor 30 may be configured to operate a neural network and identify regions of interest using a relatively simple interface, while providing guidance for moving the energy application device 12 to the correct treatment site.

[0038] The system may include a beam controller 37, which can control the focal position of the energy beam of the energy application device 12 by controlling one or both of the steer and / or focusing of the energy application device 12. The beam controller 37 may also control one or more articulating portions of the energy application device 12 to reposition the transducer. The beam controller may receive instructions from the processor 30 to cause changes in the focusing and / or steer of the energy beam. The system 10 may respond to one or more position sensors 38 and / or one or more contact sensors 39 that provide feedback to the energy application device 12. The beam controller 37 may include a motor to facilitate the steer of one or more articulating portions of the energy application device 12. In one embodiment, the motor is located inside the probe housing, and the fixed surface (lens of the ultrasonic probe) contacts the body. The motor can move internally with 1 to 6 degrees of freedom, while the probe remains stationary on the body. In other or alternative implementations, the probe is shaped more like a conventional imaging probe, held by a motorized clamp, and moves along the skin in up to six degrees of freedom, similar to a freehand scan. Changing the angle corresponds to three degrees of freedom, and to turning (manipulating) the beam in 3D space. Changing the position corresponds to the other three degrees of freedom, including XY movement that slides along the body surface, or Z movement that corresponds to adjusting the depth of focus or contact force.

[0039] It is conceivable that system 10 includes features that allow for positioning, steering, and / or focus adjustment in order to facilitate the techniques disclosed herein.

[0040] Each modulation program stored in memory 32 may include one or more sets of modulation parameters, including pulse amplitude, pulse duration, pulse frequency, pulse repetition rate, etc. Pulse generator 14 modifies its internal parameters in response to a control signal from controller device 16 to alter the stimulation characteristics of the energy pulse applied to the subject by the energy application device 12, transmitted via lead 33. Any suitable type of pulse generation circuit may be employed, including but not limited to constant current, constant voltage, multiple independent current or voltage sources, etc. The applied energy is a function of current amplitude and pulse duration. Controller 16 allows adjustable control of the energy by changing modulation parameters and / or initiating energy application at a specific time or canceling / inhibiting energy application at a specific time. In one embodiment, the adjustable control of the energy application device is based on information about the concentration of one or more molecules (e.g., circulating molecules) in the subject. If the information comes from assessment device 20, a feedback loop may drive the adjustable control. For example, a diagnosis may be made based on circulating glucose concentration measured by assessment device 20 in response to neural modulation. When the concentration exceeds a predetermined threshold or range, controller 16 can initiate a treatment protocol that applies energy to a region of interest (e.g., the liver) and has regulatory parameters associated with a decrease in circulating glucose. The treatment protocol may use different regulatory parameters than those used in the diagnostic protocol (e.g., higher energy levels, more frequent application).

[0041] In one implementation, memory 32 stores different operating modes selectable by the operator. For example, the stored operating modes may include individual models or neural networks for identifying specific regions of interest (ROIs) and executing a set of modulatory parameters associated with a specific treatment site (such as a ROI in the liver, pancreas, gastrointestinal tract, or spleen). Each organ or site may be associated with a different model. Furthermore, different sites may have different associated modulatory parameters based on the depth of the relevant organ, the size of the ROI, the desired physiological outcome, etc. Controller 16 can be configured to execute appropriate instructions based on the selection of a specific organ, rather than requiring the operator to manually input a mode. In another implementation, memory 32 stores operating modes for different types of procedures. For example, activation may be associated with different ranges of stimulation pressure or frequency relative to those associated with inhibiting or blocking tissue function.

[0042] In a specific example, when the energy application device is an ultrasonic transducer, the effective amount of energy can involve a predetermined time-averaged intensity applied to the region of interest. For example, the effective amount of energy can include time-averaged power (time-averaged intensity) and at 1 mW / cm². 2 -30,000mW / cm 2(Time-averaged intensity) and peak positive pressure ranging from 0.1 MPa to 7 MPa (peak pressure). In one example, the time-averaged intensity in the region of interest is less than 35 mW / cm². 2 Less than 500mW / cm 2 or less than 720mW / cm 2 In one example, the time-averaged intensity is associated with levels below those associated with thermal damage and ablation / cavitation. In another specific example, when the energy application device is a mechanical actuator, the vibration amplitude is in the range of 0.1 to 10 mm. The selected frequency can depend on the mode of energy application, such as ultrasound or a mechanical actuator. The controller 16 is capable of operating in a verification mode to obtain a predetermined treatment position, and the predetermined treatment position can be implemented as part of a treatment operation mode configured to execute a treatment scheme when the energy application device 12 is positioned at the predetermined treatment position.

[0043] The system may also include an imaging device that facilitates focusing the energy application device 12. In one embodiment, the imaging device may be integrated with or be the same device as the energy application device 12, thereby applying different ultrasound parameters (frequency, aperture, or energy) to select (e.g., spatially select) a region of interest and focus energy onto the selected region of interest for targeting and subsequent neuromodulation. In another embodiment, memory 32 stores one or more targeting or focusing patterns for spatially selecting regions of interest within an organ or tissue structure. Spatial selection may include selecting subregions of an organ to identify organ volumes corresponding to the regions of interest. Spatial selection may rely on image data provided herein. Based on spatial selection, the energy application device 12 may focus (e.g., using beam controller 37) onto a focus position on a selected volume corresponding to the region of interest. It should be understood that the image data used to guide the focus position may be volumetric or planar. For example, the energy application device 12 may be configured to first operate in a verification mode to acquire predetermined processing positions by capturing image data used to identify predetermined processing positions associated with capturing regions of interest. The verification mode energy is not applied at a level suitable for neuromodulation processing and / or not with modulation parameters suitable for neuromodulation processing. However, once the region of interest is identified, the controller 16 can then operate in the processing mode according to the adjustment parameters associated with achieving the targeted physiological outcome.

[0044] The controller 16 can also be configured to receive inputs related to the targeted physiological outcome as inputs for selecting modulating parameters. For example, when using an imaging modality to assess tissue characteristics, the controller 16 can be configured to receive calculated characteristic indices or parameters. Based on whether the index or parameter is above or below a predetermined threshold, a diagnosis can be made, and an indication of the diagnosis can be provided (e.g., via a display). In one embodiment, the parameter can be a measure of tissue displacement of the affected tissue or a measure of the depth of the affected tissue. Other parameters can include assessing the concentration of one or more molecules of interest (e.g., assessing one or more of the concentration change, rate of change, or determination of whether the concentration is within a desired range relative to a threshold or baseline / control). Furthermore, the energy application device 12 (e.g., an ultrasound transducer) can operate under the control of the controller 16 to perform the following actions: a) acquiring image data of tissue that can be used for spatial selection of a region of interest within a target tissue; b) applying modulating energy to the region of interest; and c) acquiring image data to determine that a targeted physiological outcome has occurred (e.g., via displacement measurement). In this embodiment, the imaging device, the assessment device 20, and the energy application device 12 can be the same device.

[0045] Figure 3 The diagram illustrates energy delivery to a region of interest 44 using the provided energy application device 12. The energy application device 12 includes an ultrasound transducer 42 (e.g., a transducer array) capable of applying energy to a target organ or tissue 43, such as the liver, spleen, or pancreas. The energy application device 12 may include control circuitry for controlling the ultrasound transducer 42. The control circuitry of the processor 30 (…) Figure 2 The energy application device 12 can be integrated with the energy application device 12 (e.g., via an integrated controller 16) or it can be a separate component. The energy application device 12 can also be configured to acquire image data to help spatially select a desired or targeted region of interest 44 and focus the applied energy on the region of interest of the target tissue or structure.

[0046] Regions of interest 44 and / or target tissues 43 may include various anatomical features or structures for automatic identification, for example, via neural networks, as provided herein. For example, organs may have characteristic edges 50 of a specific shape, may have capillaries or smaller vessels 52, and internal neural structures 54 entering tissue 43. Tissue 43 may be within a predictable range of size or volume based on subject size (size), weight, age, and / or clinical condition, or may have a size range 56, for example, on the x, y, or z axis. Tissue 43 may be localized relative to other internal structures, such as other organs 60 or larger vessels 62. These and other features can be provided as inputs for identifying regions of interest 44 and / or target tissues 43. Furthermore, these features can be obtained from a patient population to identify predictable features that tend to stabilize within the patient population (e.g., the location of larger vessels, organs, or glands) and more variable features that change over time between and within subjects, based on clinical condition, metabolic state, patient weight, etc. For example, the size of certain organs may change after meals. Other identifying features can be vascular bifurcation, entry / exit points of arteries and veins into organs (“hepatic hilum”, “hilus”, “hilum”, “fissure”, “indentation”, “duct”, etc.). Based on the variability of these factors, networks with different weights or filters can be used. As these factors change, appropriate models can be employed, specifically trained for other subjects with similar factors. An example might be patient aging. Networks using different models might be used for individuals of different ages. As the patient's age changes, the model best suited to the patient at a given time point can be selected. Therefore, a different set of networks can be accessed. Such networks can include more general or generic models, models for specific demographics, and fully personalized models.

[0047] The desired target tissue 43 can be internal tissue or an organ comprising axon terminals and synapses of non-neuronal cells. Synapses can be stimulated by applying energy directly to the axon terminals within the focal field or focal region 48 of an ultrasound transducer 42 focused on a region of interest 44 of the target tissue 43, to induce action potentials and / or release molecules into the synaptic space, such as neurotransmitter release and / or changes in ion channel activity, thereby causing downstream effects. The region of interest 44 can be selected to include a certain type of axon terminal, such as an axon terminal of a specific neuronal type and / or an axon terminal forming a synapse with a certain type of non-neuronal cell. Thus, the region of interest 44 can be selected as a portion of the target tissue 43 corresponding to the desired axon terminal (and associated non-neuronal cell). Energy application can be selected to preferentially trigger the release of one or more molecules, such as neurotransmitters, from the synapse or to directly activate the non-neuronal cell itself via direct energy transduction (i.e., mechanotransduction or voltage-activating proteins within the non-neuronal cell), or to induce activation within both neurons and non-neuronal cells, from which the desired physiological effect is induced. The region of interest 44 can be selected as a site of neural entry into the organ. In one embodiment, liver stimulation or modulation may refer to modulation of the region of interest 44 at or near the porta hepatis. Identification of a predetermined treatment location 46 on the patient's skin (or clothing) may include the selection of the region of interest 44, whereby the location of the region of interest 44 on the patient's body within the focal area 48 of the energy application device 12 is the predetermined treatment location 46 during operation.

[0048] Energy can be focused or substantially concentrated on the region of interest 44 and only concentrated on a portion of the internal tissue 43, for example, less than about 50%, 25%, 10%, or 5% of the total volume of tissue 43. That is, the region of interest 44 can be a subregion of the internal tissue 43. In one embodiment, energy can be applied to two or more regions of interest 44 in the target tissue 43, and the total volume of the two or more regions of interest 44 can be less than about 90%, 50%, 25%, 10%, or 5% of the total volume of tissue 43. In one embodiment, energy is applied only to about 1%-50% of the total volume of tissue 43, only to about 1%-25% of the total volume of tissue 43, only to about 1%-10% of the total volume of tissue 43, or only to about 1%-5% of the total volume of tissue 43. In some embodiments, only the axonal terminals in the regions of interest 44 of the target tissue 43 will directly receive the applied energy and release neurotransmitters, while unstimulated axonal terminals outside the regions of interest 44 do not receive a large amount of energy and are therefore not activated / stimulated in the same way. In some embodiments, axonal terminals in the tissue portion directly receiving energy will induce altered neurotransmitter release. In this way, tissue subregions can be targeted for neuromodulation in a granular manner; for example, one or more subregions can be selected. In some embodiments, energy application parameters can be selected to induce preferential activation of neural or non-neural components within the tissue directly receiving energy, to induce desired combined physiological effects. In some embodiments, energy can be focused or concentrated in an area less than about 25 mm. 3 Within a certain volume. In some implementations, the energy can be focused or concentrated to approximately 0.5 mm. 3 -50 mm 3 Within the volume. The focusing volume and focusing depth used to focus or concentrate energy within the region of interest 44 may be affected by the size / configuration of the energy application device 12. The focusing volume of energy application may be defined by the focal field or focusing region of the energy application device 12.

[0049] Energy can be applied essentially only to one or more regions of interest 44 to preferentially activate synapses in a targeted manner, thereby achieving targeted physiological outcomes. Thus, in some embodiments, only a subset of multiple different types of axonal terminals in tissue 43 are exposed to direct energy application.

[0050] As presented herein, the identification of the correct processing location 46 on the subject may not be sufficient to target and deliver energy from the energy application device 12 to the region of interest 44. Figure 4As shown, during treatment, when the patient breathes or moves, the region of interest 44 can move out of the focal region 48 (shown as the initial focal region 48a). System 10 can be configured to acquire updated or ongoing image data of tissue 43 using the imaging transducer 68 within the energy application device 12 (which can be acquired via timing or gating control via controller 16, alternating with or during the dark or off periods of the processing energy delivery). The energy used to acquire the image data has different parameters than the processing energy and, in one embodiment, may not induce targeted physiological outcomes. Movement away from transducer 42 triggers adjustments (adjustments) to conditioning parameters, such as adjusting to higher power and / or longer application time to achieve the desired exposure, and redirecting / focusing the ultrasound beam to a new location in the region of interest 44b, 44c, as... Figure 5 As shown. Tracking movement toward the skin may result in adjusting the tuning parameters to lower power and / or shorter application time, as well as redirecting and / or focusing the ultrasound beam to a new location.

[0051] Adjustments can be made dynamically to accommodate real-time movement of the region of interest 44, thereby achieving the desired exposure. Furthermore, system 10 takes into account variations in overall adjustment parameters when calculating the applied energy dose. That is, adjustments can be made without moving the energy application device 12 from the processing position 46. In other words, the processing position 46 allows energy delivery to the region of interest 44 within the potential processing area 70, based on the typical operating parameters and geometry of the transducer 42 and the energy application device 12. If the region of interest 44 remains within the potential processing area 70, the energy application device 12 automatically steers or adjusts to allow uninterrupted dose delivery, or physically moves away from the processing position 46, even when moving within the potential processing area 70. That is, the energy application device 12 is approximately positioned in the correct location (i.e., processing position 46), and fine-tuning / focusing is performed in real-time. If the region of interest 44 moves outside the potential processing area 70, energy delivery is paused via controller 16. Alarms or notifications may be provided. System 10 can be configured to wait to determine (based on image data acquired from imaging transducer 68) whether the region of interest 44 has returned to its position within the potential processing area 70 before recovery. If it is determined after a predetermined time period that the region of interest is no longer within the potential processing area 70, an instruction can be provided to move the energy application device 12 to a new processing position 46. In this way, the energy application device moves only when it is determined that the region of interest 44 is no longer within the potential processing area 70, which reduces the operator's workload and the possibility of incorrect positioning and repositioning of the energy application device 12. Furthermore, even slightly incorrect positioning of the energy application device 12 can be corrected using neural networks or other techniques for identifying the region of interest 44 within the potential processing area 70.

[0052] Figure 6 This is a flowchart of a technique 100 for neurally modulated energy delivery. Certain reference figures discussed in conjunction with technique 100 may be as follows: Figure 1-5 The technique 100 can be performed during the initiation or establishment of the treatment protocol, or as part of the verification of the treatment protocol. In some embodiments, the image data can also be part of the patient verification procedure. In step 102, image data is acquired, for example, using the energy application device 12 in imaging mode. The image data is provided as input to identify a region of interest 44 within the image data in step 104. Once identified, in step 106, neuromodulation energy is delivered to the region of interest, for example, by delivering energy from the energy application device through the patient's skin and to the region of interest 44.

[0053] System 10 can acquire updated image data in step 108, showing the movement of tissue 43 from its initial position and at various positions (see...). Figure 4The transitions between tissues 43a, 43b, and 43c are associated with the movement of regions of interest 44b and 44c. In step 110, the movement or change in position is identified, and in step 112, the adjustment parameters of the energy application device 23 are adjusted. In one embodiment, the system 10 can use the movement of tissue 43 as a characterization or estimate of the movement of region of interest 43.

[0054] In one example, updated image data can be evaluated as a characteristic of a specific type of movement. For example, rhythmic or periodic movement of tissue 43 and / or the region of interest toward and then away from transducer 68 over a period of time (e.g., 1-5 seconds) can be a characteristic of respiration. The system can predict future respirations and create a model of the predicted movement of the region of interest 44 over time, aligning energy delivery at a specific time with one or more predicted locations of the region of interest 44 during respiration. In another or alternative implementation, system 10 can identify apnea or cessation of respiration within the acquired image data and align energy delivery with the time period during which the region of interest is relatively still when the subject pauses (intervals) between breaths.

[0055] In one implementation, system 10 can use image data and the determined position of region of interest 44 relative to focus region 48 to determine dose delivery over time. For example, in one implementation, energy application device 12 can minimally adjust the steering and / or focusing of energy delivery during movement of region of interest, while adjusting other parameters. Based on the movement of region of interest 44 identified outside focus region 48, system 10 can calculate total dose delivery. Thus, movement can allow system 10 to extend the dose delivery period, such that the total dose delivered directly to region of interest 44 is within desired parameters, taking into account the time period during energy delivery when region of interest 44 is outside focus region 48. Furthermore, system 10 can also determine total delivery to areas outside region of interest 44 and adjust steering and / or focusing when the energy applied outside region of interest 44 reaches a threshold. It should be understood that steering can change the angle of the ultrasound beam, while focusing changes the depth of focus and / or the overall beam size.

[0056] In some implementations, system 10 uses a neural network to identify the location of region of interest 44 and / or target tissue 43 within the acquired image data. In one implementation, the identification can be performed in a typically autonomous manner with minimal operator intervention. Figure 7This is a schematic diagram of an implementation of constructing a neural network to identify the location of a region of interest 44 and / or target tissue 43 within acquired image data. The neural network 122 may be based on image data 120 (i.e., received dose) acquired from corresponding imaging probes 68 (e.g., 68a, 68b, 68c) of each subject 118 (including subjects 118a, 118b, 118c who are not subjects of interest 118). The neural network 122 receives group image data and is trained on the group image data based on specific baseline truth parameters. The neural network 122 may be dedicated to a specific tissue or organ, and in a particular embodiment, may be dedicated to a specific dosing regimen. As shown, the neural network 122 may be part of a controller 16. In other embodiments, the neural network 122 may communicate with the controller 16, but is not necessarily part of the controller 16. A treatment probe of the energy application device 12 may be configured to respond to the controller 16 and the neural network output. In step 124, the imaging probe 68 acquires image data from the subject 118 and provides the image data as input to the neural network 122, such as... Figure 8 As discussed in the article.

[0057] Figure 8 It can be combined Figure 1-7 The flowchart illustrates certain elements used to perform technique 130. This technique includes a step 132 where population image data is provided to train a neural network. In step 134, technique 130 also receives image data of a subject of interest. The subject of interest may or may not be included in the population image data. In step 136, the trained neural network is used to identify regions of interest in the image data. In one embodiment, technique 130 may include acquiring images from the subject, annotating these images (for supervised learning), and then feeding back the annotated images to update the network. The updated network is then applied to all subsequent images acquired from that patient.

[0058] Furthermore, technique 130 may include selecting a subset of all images acquired from the patient for annotation and use in network updates, as data annotation can be a laborious process. The subset of images to be used for network updates can be selected based on several factors, one of which is how well an existing population-based network model performs on that image. For example, if a population-based model already performs well on a given image, updating the model using that image may not be beneficial. However, for images where the network provides poor results, perhaps manually detected or with other automatically detected criteria (such as low probability scores), expert annotations can be obtained for such images and then provided to the network.

[0059] As discussed herein, neural network 122 may include one or more layers that allow for the identification of organs and / or structures. Certain layers of neural network 122 may be suspended or frozen, while other layers of the network are trained using data from subjects of interest to adapt the model to the specific individual. While large deep networks are powerful, such networks require processing large amounts of data. In cases with limited data (such as individual subjects), certain layers in a population-based model may be frozen to reduce the number of parameters the network must learn. Since the population-based model has also been trained on the same type of images and / or for the same type of task, the weights and filters it learns in layers closer to the input layer are often low-level enough (i.e., edges, rows, etc.) that the benefits provided by relearning are limited. The neural network may be supervised or unsupervised. Neural network 122 may be updated to accommodate patient-specific variations among the subjects. Furthermore, neural network 122 may include a validation step to assess the confidence in identifying regions of interest (see [link to relevant documentation]). Figure 15 In one implementation, the patient-specific model can be validated on an independent dataset from the patient to ensure that the overall accuracy of the model has been improved for the patient in question before being deployed to their treatment device.

[0060] Figure 9 This is an example system 150 that can be used in conjunction with or as part of system 10. System 150 includes various features that allow for image acquisition, such as a dual-function probe 152 (see [link to system 10]). Figure 10 The system 150 includes: an imaging transducer 156, shown as a GE 3S Sector Array Probe (General Electric), and a treatment probe 154, shown as a HIFU probe, and an image probe controller 155 that controls image acquisition via the imaging transducer 156. The system 150 also includes a frame capturer (frame grabber) 157 for manipulating the acquired image data. It should be understood that while some embodiments operate on a rendered image from the acquired image data, the system 10 may also use raw or unrendered image data as input. The treatment probe 154 can be operated under the control of a treatment probe controller 162 (which controls a pulse generator circuit 160 and an RF power amplifier 158).

[0061] Figure 11An example of a graphical user interface (GUI) that can be used in conjunction with system 10 and illustrates images acquired using system 150 is shown. The GUI displays a neuromodulation prescription, which may specify a treatment protocol (including treatment date or time information for the individual subject) and / or target tissue, and in some implementations may include the total energy of the individual dose and observable parameters of correlation associated with the treatment. For example, the prescription may set a target for the change in the concentration of the molecule of interest relative to a baseline before treatment. The GUI may indicate the treatment status and acquired ultrasound images, such as image data of the acquired subject, and descriptions provided by a neural network indicating anatomical structures detected in the images. The neural network identifies the anatomical structures of the kidney. However, the associated treatment protocol is the delivery of autonomic neuromodulation energy to the liver.

[0062] Therefore, as Figure 12 As shown in the example graphical user interface, at the start of the dose, the system waits for the target anatomy (in this case, the liver) to appear in the field of view before delivering the treatment. If the identified probe placement is unsuitable for treatment delivery, the status indicator "Aligned" appears. Figure 13 During the process, once the anatomical structure of interest is aligned with the anatomical structure in the field of view identified by the neural network, a dose of therapeutic or neuromodulated energy is delivered. This status indicates "delivery in progress," and the therapeutic beam is visualized in the ultrasound image. Figure 14 Even when focused on the target organ (i.e., the liver), the system stops delivering treatment, and the total energy of the individual dose is completed, as shown in the box.

[0063] Figure 15 Results from a neural network trained for organ detection, used to identify and locate the spleen, kidney, and liver on ultrasound images, are shown. The captured images include probability indicators of the identification (e.g., 99%, 97%). In one implementation, the identification of an organ or a region of interest within an organ can be based on the neural network output reaching a probability threshold for identification. In one example, the threshold could be at least 95%, at least 97%, or at least 99%.

[0064] The disclosed technique allows for the delivery of neuromodulated energy that takes into account movement of the desired region of interest. This movement can be movement during treatment, such as a result of respiration or blood flow. It can also be a repositioning or alteration of organ size between interval doses. For example, patient weight loss or clinical condition may change the size or depth of an organ. These changes, in turn, can be assessed to provide more accurate neuromodulated energy delivery.

[0065] This written specification uses examples to disclose the invention, including the best mode, and also enables any person skilled in the art to practice the invention, including making and using any device or system and performing any combination of methods. The patent scope of the invention is defined by the claims, but may include other examples that would occur to a person skilled in the art. Such other examples are intended to fall within the scope of the claims if they have structural elements that are not indistinguishable from the literal language of the claims, or if they include equivalent structural elements that are not substantially different from the literal language of the claims.

Claims

1. A neural modulation delivery system, comprising: An energy application device is configured to deliver neuromodulatory energy to a region of interest within a subject; and The controller is configured as follows: Receive image data of the subject's internal tissues; Identify the region of interest within the image data; Controlling the application of the neuromodulation energy to the identified region of interest via the energy application device to deliver the dose of neuromodulation energy thereto; Updated image data of the subject's internal tissues are received prior to the completion of dose delivery; Based on the updated image data, the positional change of the region of interest relative to the energy application device is identified; as well as In response to determining, based on the updated image data, that the region of interest has moved outside the potential processing area of ​​the energy application device, the application of the neural modulation energy via the energy application device is suspended; Wait to determine whether the region of interest has returned to its position within the potential processing area, and if it is determined that the region of interest is no longer within the potential processing area after a predetermined time period has elapsed, provide an instruction to move the energy application device to a new processing location.

2. The system according to claim 1, wherein, The energy application device includes an ultrasonic transducer, and the controller is configured to control the energy application device to deflect and / or focus the ultrasonic beam formed by the ultrasonic transducer onto an identified region of interest.

3. The system according to claim 1, wherein, The energy application device includes a motor configured to change the position or angle of the energy application device and / or the transducer of the energy application device relative to the subject in response to an instruction from the controller, so as to align the neuromodulation energy beam with the region of interest.

4. The system according to claim 1, wherein, The image data corresponds to the field of view of the energy application device.

5. The system of claim 1, comprising an imaging transducer configured to acquire the image data and the updated image data.

6. The system according to claim 5, wherein, The imaging transducer is part of the energy application device, such that the imaging transducer comes into contact with the subject during the application of the neuromodulation energy.

7. The system according to claim 1, wherein, The controller is configured to use a neural network to identify the region of interest, the positional change, or both, in order to process the image data or the updated image data.

8. The system according to claim 7, wherein, The neural network is adjusted based on previously acquired image data of the subject's anatomical structures.

9. The system according to claim 7, wherein, The neural network was trained on image data of anatomical structures from a group of subjects.

10. The system according to claim 7, wherein, The neural network is trained on image data of anatomical structures from a group of subjects, wherein the region of interest is defined by the presence of a specific structure in the subjects.

11. The system according to claim 10, wherein, The anatomical structures include one or more of organs, nerves, nerve plexuses, and blood vessels, and the neural network is trained to recognize the anatomical structures in or near the region of interest.

12. The system according to claim 10, wherein, The anatomical structures are located within the liver or spleen.

13. The system of claim 7, wherein the neural network comprises one or more layers configured to recognize anatomical structures.

14. The system according to claim 7, wherein, The neural network is updated based on the image data and the updated image data.

15. The system according to claim 7, wherein, The controller is configured to receive input that selects the internal organization and to select the neural network based on the selected internal organization.

16. The system according to claim 7, wherein, The controller is configured to train the neural network for the subject using only a subset of its layers.

17. A neural modulation delivery system, comprising: An energy application device is configured to deliver neuromodulatory energy to a region of interest within a subject; and The controller is configured as follows: The energy application device is controlled to acquire image data, which represents the internal tissue of the subject. A neural network trained on image data of the internal tissues of the subject population identifies the region of interest based on the image data, wherein the internal tissues are of the same type as the internal tissues of the subject. The subject is treated by controlling the application of the neuromodulation energy to the identified region of interest via the energy application device to deliver a dose of the neuromodulation energy; Acquire updated image data while delivering the dose; as well as In response to determining, based on the updated image data, that the region of interest has moved outside the potential processing area of ​​the energy application device, the application of the neural modulation energy via the energy application device is suspended; Wait to determine whether the region of interest has returned to its position within the potential processing area, and if it is determined that the region of interest is no longer within the potential processing area after a predetermined time period has elapsed, provide an instruction to move the energy application device to a new processing location.

18. The system according to claim 17, wherein, The controller is configured to use the neural network and based on the updated image data to predict the movement path of the region of interest, and to dynamically change one or more control parameters based on the predicted movement path.

Images