Delivery of therapeutic neuromodulation

Abstract

To provide techniques for neuromodulation delivery.SOLUTION: Based on image data acquired from a patient, control parameters for controlling energy application of neuromodulating energy may be dynamically changed during the course of the delivery in order to maintain desired characteristics of the neuromodulating energy. For example, the beam of the neuromodulating energy may be dynamically adjusted considering movement of an organ during breathing. In another embodiment, a desired region of interest is identified within the patient based on a trained neural network and the acquired image data.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The subject matter disclosed herein relates to the identification, targeting, and / or administration to a patient's region of interest by the application of energy for neuromodulation, with the aim of causing a targeted physiological outcome. In particular, the disclosed techniques may be part of a personalized treatment protocol for an individual.

Background Art

[0002] Neuromodulation has been used in the treatment of various clinical conditions. For example, in the treatment of chronic low back pain, methods of applying electrical stimulation at various positions along the spinal cord have been employed. However, it is difficult to place electrodes at the target nerve or in its vicinity. For example, such techniques may involve surgical procedures for the placement of electrodes for delivering energy. Furthermore, it is difficult to target specific tissues with neuromodulation. Neuromodulation is mediated by inducing action potentials in nerve fibers by electrodes placed at a specific target nerve or in its vicinity, resulting in the release of neurotransmitters from nerve synapses and causing synaptic transmission to the next nerve. Current implantable electrode implementations stimulate multiple nerves or axons at once, and such propagation may cause the physiological effect to be relatively enlarged or diffused more than desired. Since nerve pathways are complex and interconnected, it would be clinically more useful if the target of the regulatory effect could be determined more selectively. However, the effectiveness of selectively targeting a specific nerve depends on how accurately the energy application device can be placed. The degree to which the focus of neuromodulation energy can be accurately aligned may vary depending on the anatomical structure of an individual patient. For example, the size and position of organs may change compared to other patients depending on a specific patient's height, weight, age, gender, clinical condition, etc. Furthermore, a patient may undergo anatomical changes over time or that can complicate the accuracy of energy delivery.

Prior Art Documents

Patent Documents

[0003] [Patent Document 1] U.S. Patent Application Publication No. 2014 / 316269 [Overview of the project]

[0004] The disclosed embodiments are not intended to limit the scope of the claimed subject matter, but rather are intended solely to provide a brief overview of possible embodiments. In fact, this disclosure may include various forms, which may be similar to or different from the embodiments described below.

[0005] In one embodiment, a neuromodulation delivery system is provided. The system includes an energy delivery device configured to deliver neuromodulation energy to a patient's region of interest. The system also includes a controller configured to receive image data of the patient's internal tissue; identify the region of interest from the image data; control the application of the neuromodulation energy to the identified region of interest via the energy delivery device to deliver a dose of the neuromodulation energy to the identified region of interest; receive updated image data of the patient's internal tissue before the delivery of the dose is complete; identify changes in the position of the region of interest relative to the energy delivery device based on the updated image data; and adjust the application of the neuromodulation energy via the energy delivery device based on the changed position of the region of interest to continue the delivery of the dose of the neuromodulation energy to treat the patient.

[0006] Another embodiment provides a method for delivering energy for neuromodulation. This method includes: delivering energy to a patient's region of interest using control parameters, wherein the energy is a portion of the total energy amount of individual doses applied to the region of interest, and delivering the energy using an energy delivery device; acquiring image data from the patient representing the internal tissue including the region of interest while delivering the energy and before the total energy amount of the individual doses is applied; identifying changes in the position of the region of interest relative to the energy delivery device based on the image data; adjusting one or more control parameters belonging to a group of control parameters based on the changes in the position of the region of interest; and delivering additional energy to the region of interest using the adjusted control parameters and delivering another portion of the total energy amount of the individual doses using the energy delivery device.

[0007] In another embodiment, a neuromodulation delivery system is provided. This system includes an energy delivery device configured to deliver neuromodulation energy to a patient's region of interest. The system also includes controlling the energy delivery device to acquire image data representing the patient's internal tissue; identifying the region of interest based on the image data using a neural network trained on image data of each patient belonging to a population, which is the same type of tissue as the patient's internal tissue; controlling the application of the neuromodulation energy by the energy delivery device to the identified region of interest to treat the patient, thereby delivering a dose of the neuromodulation energy; acquiring updated image data while delivering a previous dose; and a controller configured to dynamically change one or more control parameters for controlling the application of the neuromodulation energy based on the updated image data. [Brief explanation of the drawing]

[0008] These and other features, aspects, and advantages of the present invention will be better understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals throughout the drawings indicate the same parts. [Figure 1] This is a schematic diagram of an autonomous neuromodulation delivery system according to an embodiment of the present disclosure. [Figure 2] This is a block diagram of an autonomous neuromodulation delivery system according to an embodiment of the disclosure. [Figure 3] An embodiment of the present disclosure is a schematic diagram of an autonomous neuromodulation delivery system that applies neuromodulation energy to a region of interest within a tissue, including an anatomical structure. [Figure 4] This is a schematic diagram of an autonomous neuromodulation delivery system for tracking a moving region of interest according to an embodiment of the present disclosure. [Figure 5] This is a schematic diagram of the energy application adjusted based on the motion identified in Figure 4. [Figure 6] This is a flowchart of the autonomous neuromodulation delivery technology according to the embodiments of this disclosure. [Figure 7] This is a schematic diagram of the input to the neural network according to the embodiments of this disclosure. [Figure 8] This is a flowchart of the autonomous neuromodulation delivery technology according to the embodiments of this disclosure. [Figure 9] This is a block diagram of an example of an autonomous neuromodulation delivery system including a dual imaging and therapeutic probe according to an embodiment of the present disclosure. [Figure 10] Figure 9 shows images of the dual imaging and therapeutic probes. [Figure 11] This is an exemplary graphical user interface for an autonomous neuromodulation delivery system according to an embodiment of the present disclosure. [Figure 12] This is an exemplary graphical user interface for an autonomous neuromodulation delivery system during region of interest alignment processing according to an embodiment of the present disclosure. [Figure 13] This is an exemplary graphical user interface for an autonomous neuromodulation delivery system during neuromodulation energy delivery to a region of interest, according to embodiments of the present disclosure. [Figure 14] This is an exemplary graphical user interface for an autonomous neuromodulation delivery system after the delivery of neuromodulation energy to the region of interest is complete, according to embodiments of the present disclosure. [Figure 15] This figure shows an example of organ identification using an autonomous neuromodulation delivery system according to an embodiment of the present disclosure. [Modes for carrying out the invention]

[0009] One or more specific embodiments are described below. For the sake of brevity in describing these embodiments, this specification does not describe all features of the actual embodiments. It should be understood that in actual implementation development, such as in engineering or design projects, many implementation-specific decisions must be made to achieve the developer's specific objectives, such as addressing system-related and business-related constraints, which may differ from implementation to implementation. Furthermore, it should be understood that while such development work can be complex and time-consuming, it is nevertheless a routine task related to design, fabrication, and manufacturing for those skilled in the art who are interested in this disclosure.

[0010] Any examples or illustrations described herein shall not be deemed to limit, restrict, or define any terms used in such examples or illustrations. Rather, such examples or illustrations are described in relation to different specific embodiments and should be considered merely illustrative. Any one or more terms used in such examples or illustrations shall encompass other embodiments in which such examples or illustrations are used or not used, or which are not described elsewhere in this specification, and it will be understood by those skilled in the art that such embodiments are intended to be within the scope of that one or more terms. Words that express such non-limiting examples and illustrations include, but are not limited to, “for example,” “for instance,” “etc.,” “to give an example,” “including,” “in a particular embodiment,” “in some embodiments,” and “in one embodiment.”

[0011] This specification discloses a technique for neuromodulation to a targeted region of interest, which enables the reproducible and highly reliable application of energy to one or more specific regions of interest as part of a treatment protocol during the course of said treatment protocol. The disclosed technique provides an autonomous energy delivery method for neuromodulation, which dynamically adjusts one or more delivery parameters based on changes in the location of the desired energy target (e.g., region of interest) during energy delivery, so as not to interrupt energy delivery. For example, while a patient can be instructed to remain still while neuromodulation energy is being delivered, even slight changes in the patient's position or even their breathing can cause internal organs to move, potentially altering the relative position of the target to an external or extracorporeal energy application device (e.g., an ultrasound probe). Because neuromodulation energy can be focused on a volume of tissue containing a specific axon terminal or group of axon terminals (or conversely, a volume of tissue that does not contain other axon terminals), even slight tissue movement can cause the energy application device's focus to move out of the region of interest and to an adjacent region of tissue that does not contain the desired axon terminal. As a result, the physiological outcome resulting from neuromodulation of the desired axon terminal may not be achieved. If the region of interest moves, even by millimeters or centimeters, the location to which neuromodulation energy is applied may become inaccurate, potentially preventing the achievement of the desired therapeutic goal.

[0012] To account for the tissue movements that may occur during the time it takes to apply one or more doses of neuromodulation energy, it is conceivable to define a larger delivery area outside the volume of the region of interest, taking into account minute movements. However, in such a method, depending on the specific region of interest, other axonal terminals may be exposed to the neuromodulation energy, reducing the desired specificity of the treatment and potentially leading to physiological confounding effects that may slow down or hinder the achievement of the desired therapeutic goal. Furthermore, such an approach increases the overall volume of tissue exposed to energy, limiting the total dose that can be delivered in a single treatment session, and potentially reaching the limit of energy per dose in a short time, and in some cases before the desired dose can be delivered to the region of interest.

[0013] The present technology enables the accurate delivery of energy for neuromodulation in a user-friendly manner that eliminates or reduces the need for manual work with anatomical guidance by trained clinicians, thereby enabling less experienced caregivers to perform treatments at home or in an outpatient setting and increasing the available treatment options. Further, while trained clinicians can identify anatomical landmarks for accurately delivering energy, individual clinicians may have their own treatment preference biases, which can, over time, particularly when multiple clinicians are involved in a patient's care, potentially interfere with the delivery of accurate dosages. The present technology provides a tool for less experienced caregivers to deliver energy for neuromodulation as part of a treatment protocol.

[0014] In one embodiment, the disclosed technology incorporates imaging data acquired before and / or during a treatment session to track the movement of an area of interest over time and enables the real-time adjustment of the focus and direction of the energy such that delivery of the energy is maintained over or within the area of interest. Acquisition of the imaging data can be performed using a multifunctional device configured to perform both acquisition of image data and delivery of energy for neuromodulation. In one example, a neural network is used to identify an organ, including an area, area of interest, anatomical structure, or a combination thereof. Once identified, movement can be tracked based on the ongoing or updated acquired image data.

[0015] In some embodiments, the neural network can be trained with images obtained from a patient population so as to quickly identify an organ or other tissue containing the region of interest without the involvement of an operator. The neural network architecture may use various layers that enable the identification of structures, based on morphology, pattern matching, edge detection, etc. Further, the neural network may be configured to identify the region of interest from within an organ or tissue. For example, when the region of interest is the porta hepatis region of the liver, the neural network can be trained based on the correct images of the patient population so as to identify the region of interest that highly likely contains or overlaps with the porta hepatis region of a specific patient.

[0016] For that purpose, the disclosed neuromodulation delivery technique may be used in combination with a neuromodulation system configured for use in delivering neuromodulation energy as part of a treatment protocol. FIG. 1 is a schematic diagram of a neuromodulation system 10 for obtaining a neuromodulation effect, such as releasing neurotransmitters and / or activating synaptic elements (e.g., presynaptic cells, postsynaptic cells) by applying energy. The illustrated system includes a pulse generator 14 coupled to an energy application device 12 (e.g., an ultrasonic transducer). The energy application device 12 is configured to receive an energy pulse, for example, via a lead wire or a wireless connection, and direct this pulse to a region of interest of the patient's internal tissue or organ during use, thereby bringing about a targeted physiological outcome.

[0017] In certain embodiments, the energy application device 12 and / or pulse generator 14 may communicate with the controller 16, for example, wirelessly, and the controller 16 may send commands to the pulse generator 14. In other embodiments, the energy application device 12 may be an external device and may operate to apply energy transcutaneously or non-invasively from a location outside the patient's body, and in certain embodiments may be integrated with the pulse generator 14 and / or controller 16. In embodiments where the energy application device 12 is an external device, the energy application device 12 is operated by a caregiver, and energy pulses are sent to the desired internal location. The system may be positioned on or above the patient's skin so that it is delivered percutaneously to the tissue. Once positioned so that the energy pulse is applied to the desired site, the system 10 can initiate neuromodulation of one or more neural pathways to achieve the target physiological outcome or clinical effect. In other embodiments, the pulse generator 14 and / or energy delivery device 12 may be implanted in a biocompatible site (e.g., the abdomen) and connected within the body, for example, via one or more lead wires. In some embodiments, the system 10 may be implemented so that some or all of its components can communicate with each other wired or wirelessly.

[0018] In certain embodiments, the system 10 may include an evaluation device 20 coupled to the controller 16, which evaluates characteristics indicating whether the target physiological outcome of the modulation has been achieved. In one embodiment, the target physiological outcome may be local. For example, modulation of one or more nerve pathways may cause local changes in tissue or function, such as altering tissue structure, causing local changes in specific molecular concentrations, displacing tissue, or increasing fluid motility. The target physiological outcome may also be the objective of a treatment protocol.

[0019] Modulation of one or more neural pathways to achieve a target physiological outcome may result in systemic or non-local changes, and the target physiological outcome may relate to changes in circulating molecular concentrations or changes in tissue properties that do not involve the region of interest to which energy is directly applied. In one example, displacement may be measured as an alternative to the desired modulation, and if the measured displacement is below the expected displacement value, the modulation parameter may be modified until the expected displacement value is induced. Thus, in some embodiments, the evaluation device 20 may be configured to evaluate concentration changes. In some embodiments, the evaluation device 20 may be an imaging device configured to evaluate changes in organ size, location and / or tissue properties. In another embodiment, the evaluation device 20 may be a circulating glucose monitor. The components of system 10 are shown separately in the figure, but it should be understood that some or all of the components may be combined with each other. In another embodiment, the evaluation device may evaluate localized tissue temperature increases, which can be detected using a separate temperature sensor or, if the energy application device 12 is configured to apply ultrasonic energy, using ultrasonic imaging data. The difference in sound velocity can be detected using differential imaging techniques before, during, and after treatment.

[0020] Based on the evaluation, the modulation parameters of the controller 16 may be modified to ensure that an effective amount of energy is delivered. For example, if the desired modulation is related to a change in concentration (circulating or tissue concentration of one or more molecules) relative to a reference value within a defined time frame (e.g., 5 minutes, 30 minutes after the start of the energy application treatment) or at the start of the treatment, it may be desirable to modify the modulation parameters, such as pulse frequency or other parameters. In such cases, the operator or an automated feedback loop may make changes to define or adjust the energy application parameters or modulation parameters of the pulse generator 14 until an effective amount of energy is delivered by those parameters or modulation parameters. As described herein, data from the evaluation device 20 may be provided as part of a feedback loop to train individual neural networks as part of the treatment protocol and / or to re-engage and refocus energy in consideration of movement in the region of interest during treatment. In one embodiment, an updated region of interest may be obtained by adjusting the initially defined region of interest based on feedback from the evaluation device regarding the effectiveness of the neuromodulation energy during the course of the treatment protocol. Here, feedback may be, for example, a change in the concentration of the molecule of interest as a result of applying neuromodulation energy. Such adjustments or updates to the region of interest may be used as part of a specific patient-specific network, where the network updates are performed to recognize specific regions of interest that have the greatest impact on the physiological parameters of interest for that particular individual, based on the desired clinical outcome.

[0021] The system 10 provided herein may deliver energy pulses according to various modulation parameters, which are part of a treatment protocol, in order to apply an effective amount of energy. For example, the modulation parameters may include various patterns of stimulation time, ranging from continuous to intermittent patterns. When stimulation is intermittent, energy is delivered at a constant frequency for a certain period of time while the signal is on. After the signal on time, there is a period of no energy supply, called a signal off time. The modulation parameters may further include the frequency and duration of stimulation application. The application frequency may be continuous or may be delivery over various periods, for example, a daily or weekly cycle. Furthermore, the treatment protocol may specify the time of energy application, or specify the time relative to meals or other activities. The treatment time to achieve the target physiological outcome may vary in duration, ranging from several minutes to several hours. In certain embodiments, the duration of treatment using a specified stimulation pattern may be 1 hour, and repeated, for example, at 72-hour intervals. In certain embodiments, energy delivery may be performed for a shorter duration, e.g., 30 minutes, or more frequently, e.g., every 3 hours. The application of energy can be controlled to be adjustable according to modulation parameters such as treatment duration, frequency, and amplitude, so that the desired results are achieved.

[0022] Figure 2 is a block diagram of a specific component of system 10. As described herein, the neuromodulation system 10 may include a pulse generator 14 adapted to generate multiple energy pulses to be applied to the patient's tissue. The pulse generator 14 may be separate from or integrated with external devices such as a controller 16. The controller 16 includes a processor 30 for controlling the device. To control various components of the device, the memory 32 of the controller 16 stores software code or instructions to be executed by the processor 30. The controller 16 and / or the pulse generator 14 may be connected to the energy application device 12 via one or more lead wires 33 or wirelessly. The processor 30 may be configured to access from the memory 32 software for operating a neural network pre-trained on images of other patients (e.g., not necessarily including the patient under treatment). Furthermore, the processor may be configured to update the neural network based on image data of the patient of interest.

[0023] The controller 16 may include a user interface having input / output circuits 34 and a display 36 adapted to allow a clinician to input selections for the modulation program and set modulation parameters. However, certain embodiments of the system 10 may include implementations that do not have a display 36 that provides feedback using sound or light. For example, a relatively simple home system 10 may have a configuration with or without a display 36 so that inexperienced users are not shown information that is not useful in achieving treatment goals. The processor 30 can be configured to operate a neural network using a relatively simple interface to identify regions of interest while providing guidance to move the energy application device 12 to the correct treatment position.

[0024] The system may include a beam controller 37 capable of controlling the focal position of the energy beam of the energy application device 12 by controlling either or both the steering and / or focusing of the energy application device 12. The beam controller 37 may further control one or more joints of the energy application device 12 to change the position of the transducer. The beam controller may receive commands from the processor 30 to change the focusing and / or steering of the energy beam. The system 10 may be configured to respond to one or more position sensors 38 and / or contact sensors 39 that provide feedback about the energy application device 12. The beam controller 37 may include a motor that enables steering of one or more joints of the energy application device 12. In one embodiment, the motor is located inside the probe housing and its fixed surface (the lens of the ultrasound probe) is in contact with the body. The motor can move internally with 1 to 6 degrees of freedom while the probe is stationary on the body. In additional or other embodiments, the probe is shaped like a conventional imaging probe, held in an electrically operated fixture, and moved along the skin with up to 6 degrees of freedom, similar to a freehand scan. Angle changes correspond to three degrees of freedom and correspond to the steering of the beam in three-dimensional space. Position changes correspond to the other three degrees of freedom and consist of XY motion for sliding along the surface of the body, or Z motion for adjusting the depth of focus or contact force. System 10 may include features that enable adjustment of position, steering, and / or focus in order to enable the technology disclosed herein.

[0025] Each modulation program stored in memory 32 may include one or more modulation parameters, including pulse amplitude, pulse duration, pulse frequency, and pulse repetition rate. Receiving a control signal from controller 16, pulse generator 14 modifies its internal parameters, thereby altering the stimulating characteristics of the energy pulses transmitted via lead wires 33 to the patient to whom the energy application device 12 is applied. Any suitable type of pulse generation circuit can be used, including but not limited to constant current, constant voltage, or multiple independent current or voltage sources. The applied energy is a function of the current amplitude and pulse duration. Controller 16 can tune the energy by changing the modulation parameters and / or by initiating energy application at a specific time or canceling / suppressing energy application at a specific time. In one embodiment, the tuned control of the energy application device is based on information regarding the concentration of one or more molecules (e.g., circulating molecules) in the patient. If this information is obtained from evaluation device 20, a feedback loop can drive the tuned control. For example, a diagnosis can be made based on the circulating glucose concentration measured by evaluation device 20 in response to neuromodulation. If the concentration exceeds a predetermined threshold or range, the controller 16 can initiate a therapeutic protocol involving energy delivery to the region of interest (e.g., the liver) using modulation parameters related to the reduction of circulating glucose. The therapeutic protocol may use different modulation parameters than those used in the diagnostic protocol (e.g., parameters with higher energy levels and delivery frequencies).

[0026] In one embodiment, different operating modes selectable by the operator are stored in memory 32. The stored operating modes may include, for example, separate models or neural networks for identifying a specific region of interest and executing a set of modulation parameters associated with a specific treatment site, such as the liver, pancreas, gastrointestinal tract, or spleen. Each organ or site may be associated with a different model. Furthermore, different modulation parameters may be associated with different sites based on the depth of the relevant organ, the size of the region of interest, the desired physiological outcome, etc. Instead of requiring the operator to manually input a mode, the controller 16 may be configured to execute an appropriate command when a specific organ is selected. In another embodiment, operating modes for different types of treatments are stored in memory 32. For example, a different stimulation pressure or frequency range may be associated with activation than one that suppresses or blocks tissue function.

[0027] In certain examples, when the energy application device is an ultrasonic transducer, the effective amount of energy may include a predetermined time-averaged intensity applied to the region of interest. For example, the effective amount of energy may include time-averaged output (time-averaged intensity) and peak positive pressure in the ranges of 1 mW / cm² to 30,000 mW / cm² (time-averaged intensity) and 0.1 MPa to 7 MPa (peak pressure), respectively. In one example, the time-averaged intensity in the region of interest is less than 35 mW / cm², less than 500 mW / cm², or less than 720 mW / cm². In one example, the time-averaged intensity is associated with a level lower than the level associated with thermal damage and cauterization / cavitation phenomena. 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 may depend on the energy application mode, such as ultrasonic or mechanical actuator. The controller 16 may be configured to operate in verification mode to acquire a predetermined treatment position, which may be implemented as part of a treatment operation mode configured to execute a treatment protocol when the energy application device 12 is positioned at the predetermined treatment position.

[0028] The system may also include an imaging device to facilitate focusing of the energy application device 12. In one embodiment, the imaging device may be integrated with the energy application device 12, or they may be the same device, so that different ultrasound parameters (frequency, aperture, or energy) are applied when selecting a region of interest (e.g., spatially selecting) and when focusing energy on the selected region of interest for targeting and subsequent neuromodulation. In another embodiment, one or more targeting or focusing modes used for spatially selecting a region of interest within an organ or tissue structure are stored in memory 32. Spatial selection may include selecting a sub-region of an organ to identify the organ volume corresponding to the region of interest. Spatial selection may be performed using image data provided herein. Based on the spatial selection, the energy application device 12 may focus (e.g., using a beam controller 37) on the selected volume corresponding to the region of interest. It should be understood that the image data used to guide the focal position may be either three-dimensional or two-dimensional data. For example, the energy application device 12 may be initially operated in verification mode to acquire a predetermined treatment location by capturing image data used to identify a predetermined treatment location associated with capturing the region of interest. The energy in verification mode is not at a level of modulation parameters suitable for neuromodulation therapy, and / or no such parameters are applied. However, once the region of interest is identified, the controller 16 can be operated in treatment mode according to modulation parameters relevant to achieving the target physiological outcome.

[0029] The controller 16 may also be configured to accept inputs related to the target physiological outcome as inputs for selecting modulation parameters. For example, when using an imaging modality for tissue characterization, the controller 16 may be configured to accept an index calculated for that characteristic or a parameter for that characteristic. A diagnosis can be made based on whether the index or parameter is above or below a predetermined threshold, and the diagnosis can be displayed (e.g., on a display). In one embodiment, the parameter may be a measured value of tissue displacement of the affected tissue or a measured value of the affected tissue depth. Other parameters may include an evaluation of the concentration of one or more molecules of interest (e.g., one or more evaluations of concentration change relative to a threshold or reference value / control, rate of change, or determination of whether the concentration is within a desired range). Furthermore, the energy application device 12 (e.g., an ultrasound transducer) may operate under the control of the controller 16 to perform the following operations: a) acquiring tissue image data that can be used to spatially select a region of interest in the target tissue; b) applying modulation energy to the region of interest; c) acquiring image data for determining (e.g., by displacement measurement) whether the target physiological outcome has occurred. In such embodiments, the imaging device, evaluation device 20, and energy application device 12 may be the same device.

[0030] Figure 3 shows energy delivery to a region of interest 44 using the energy delivery device 12 described above. The energy delivery device 12 includes an ultrasonic 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 delivery device 12 may also include a control circuit for controlling the ultrasonic transducer 42. The control circuit of the processor 30 (Figure 2) may be part of the energy delivery device 12 (e.g., through an integrated controller 16) or a separate component. The energy delivery device 12 may also be configured to select a desired or targeted region of interest 44 in space and acquire image data to assist in focusing the applied energy onto the region of interest of the target tissue or structure.

[0031] The region of interest 44 and / or target tissue 43 may include anatomical features or structures to facilitate automated recognition, for example, using a neural network, as described herein. For example, an organ may have a characteristic edge 50 with a specific shape, or it may have capillaries or thinner vessels 52 in addition to internal neural structures 54 extending into the tissue 43. The tissue 43 may also be within a predictable size or volume range based on the patient's physique, weight, age, and / or clinical symptoms, or it may feature a dimensional range 56 along the x, y, or z axis, for example. The tissue 43 may also be within a range of other organs 60 or more The blood vessels 62 may be positioned relative to other internal structures. The above and other features may be provided as input when recognizing the region of interest 44 and / or target tissue 43. Furthermore, in addition to variable features that vary over time between or within patients depending on clinical symptoms, metabolic status, patient weight, etc., predictable features that tend to appear stably across the patient population (e.g., location of larger blood vessels, organs or glands) may be obtained from the patient population to identify these features. For example, the size of a particular organ may change after a meal. Other recognition features may include entry / exit points for blood vessels, arteries, and veins ("porta", "hilus", "hilum", "fissure", "indendation", "duct", etc.). Networks with varying weights and filters may be used based on the variability of these factors. If these factors change, an appropriate model specially trained on other patients with similar factors may be used. One example may be patient aging. For individuals of different ages, different networks of models can be used. If a patient's age changes, the model best suited to that patient at a given point in time can be selected. Therefore, multiple different sets of networks may be accessed. Such networks may include more general or generic models, models tailored to specific demographic features, and fully individualized models.

[0032] The desired target tissue 43 may be an internal tissue or organ containing axon terminals and synapses of non-neuronal cells. Synapses may also be stimulated by directly applying energy to axon terminals within the focal region or focal zone 48 of an ultrasonic transducer 42 focused on the region of interest 44 of the target tissue 43, resulting in action potentials and / or release of molecules into the synaptic cleft, such as the release of neurotransmitters and / or changes in ion channel activity that have downstream effects. The region of interest 44 can be selected to include specific types of axon terminals, such as axon terminals of a particular type of neuron and / or axon terminals that form synapses with a particular type of non-neuronal cell. Thus, the region of interest 44 can be selected to correspond to a portion of the target tissue 43 that contains the desired axon terminals (and associated non-neuronal cells). Regarding the application of energy, one can choose to preferentially induce the release of one or more molecules, such as neurotransmitters from nerves within synapses; directly activate non-neuronal cells themselves via direct energy conversion (i.e., mechanotransduction or potential-activating proteins within non-neuronal cells); or activate both neuronal and non-neuronal cells to induce the desired physiological effect. The region of interest 44 may be selected as the site where nerves enter an organ. In one embodiment, liver stimulation or modulation may refer to the modulation of the hepatic hilum or a region of interest 44 adjacent to the hepatic hilum. When identifying a predetermined treatment location 46 from the patient's skin (or clothing), a region of interest 44 may be selected so that the predetermined treatment location 46 is a position on the patient's body where the region of interest 44 is within the focal zone 48 when the energy application device 12 is operating.

[0033] The energy may be focused on only a portion of the region of interest 44 and the internal tissue 43, for example, less than 50%, 25%, 10%, or 5% of the total volume of the tissue 43, or substantially focused on it. That is, the region of interest 44 may be a portion of the internal tissue 43. In one embodiment, energy can be applied to two or more regions of interest 44 within the target tissue 43, and the combined volume of the two or more regions of interest 44 may be less than 90%, 50%, 25%, 10%, or 5% of the total volume of the tissue 43. In one embodiment, the energy is applied to only about 1% to 50% of the total volume of the tissue 43, only about 1% to 25% of the total volume of the tissue 43, only about 1% to 10% of the total volume of the tissue 43, or only about 1% to 5% of the total volume of the tissue 43. In certain embodiments, only axon terminals in the region of interest 44 of the target tissue 43 directly receive the applied energy and release neurotransmitters, while unstimulated axon terminals outside the region of interest 44 receive virtually no energy and are therefore not activated / stimulated in the same way. In some embodiments, axon terminals in the tissue portion that directly receives energy release neurotransmitters in a modified manner. In this way, by selecting, for example, one or more subregions, subregions of tissue can be targeted for neuromodulation at a finer granularity. In some embodiments, the parameters at the time of energy application can be selected to preferentially activate either neural or non-neuronal elements within the tissue that directly receive the energy in order to induce a desired combination of physiological effects. In certain embodiments, the energy may be focused or concentrated within a volume of less than approximately 25 mm³. In certain embodiments, the energy may be focused or concentrated within a volume of approximately 0.5 mm³ to 50 mm³. The focal volume and depth of focus within the region of interest 44, which are used to focus or concentrate energy, may depend on the size / configuration of the energy application device 12. The focal volume of the energy application may also be defined by the focal point or focal band of the energy application device 12.

[0034] To achieve the desired physiological outcome, the energy may be targeted to preferentially activate synapses and applied substantially to only one or more regions of interest 44. Thus, in certain embodiments, only a portion of several different types of axonal terminals within the tissue 43 are exposed to the directly applied energy.

[0035] As described herein, simply identifying the correct treatment location 46 on the patient may be insufficient for delivering energy from the energy delivery device 12 to target the region of interest 44. As shown in Figure 4, if the patient breathes or moves during treatment, the region of interest 44 may move out of the focal band 48 (shown as the initial focal band 48a). The system 10 may be configured to use the imaging transducer 68 in the energy delivery device 12 to acquire updated or continuous image data of the tissue 43 (such image data can be acquired at intervals alternating with the dark or quiescent phases of therapeutic energy delivery, or via gating control via the controller 16, or during the dark or quiescent phases). The energy parameters used to acquire the image data differ from the therapeutic energy parameters, and in one embodiment, the target physiological outcome may not be achieved. If movement occurs away from transducer 42, the modulation parameters are adjusted, for example, to increase the output and / or extend the application time to achieve the desired exposure, as shown in Figure 5, to initiate steering / focusing of the ultrasound beam to the position of the region of interest 44b, 44c after the movement. If movement towards the skin is tracked, the modulation parameters may be adjusted to decrease the output and / or shorten the application time to steering and / or focus the ultrasound beam to the position after the movement.

[0036] Such adjustments may be made dynamically, taking into account the real-time movement of the region of interest 44 to achieve the desired exposure. Furthermore, in system 10, when calculating the energy dose to be applied, the overall change in the modulation parameters is taken into account. Such adjustments can be made even if the energy delivery device 12 does not move from the treatment position 46, as shown in the figure. That is, the treatment position 46 allows energy to be delivered to the region of interest 44 that is located within the treatable area 70. The treatable area 70 is based on general operating parameters and the geometric shape of the transducer 42 and the energy delivery device 12. As long as the region of interest 44 remains within the treatable area 70, even if it moves within the treatable area 70, the energy delivery device 12 will be automatically directed or adjusted to enable dose delivery without operator intervention, without pausing the energy delivery device 12 or moving it physically away from the treatment position 46. That is, if the energy delivery device 12 is positioned in the approximately correct position (i.e., the treatment position 46), more precise directing / focusing can be performed in real time. If the region of interest 44 moves outside the treatable area 70, energy delivery is interrupted via the controller 16. An alarm or notification may be issued. The system 10 may be configured to wait for it to be determined (based on image data acquired from the imaging transducer 68) whether the region of interest 44 has returned to a position within the treatable area 70 before resuming. If it is determined that the region of interest is not within the treatable area 70 after a predetermined time has elapsed, the system may instruct the energy delivery device 12 to move to another treatment position 46. In this way, the energy delivery device is only moved when it is determined that the region of interest 44 is not within the treatable area 70, thus reducing the burden on the operator and minimizing the possibility of inaccurate positioning or repositioning of the energy delivery device 12. Furthermore, if the position of the energy delivery device 12 is even slightly inaccurate, its position can be corrected using a neural network or other technique to identify the region of interest 44 within the treatable area 70.

[0037] Figure 6 is a flowchart of technique 100 for neuromodulation energy delivery. In the description relating to technique 100, certain reference numerals described in Figures 1 to 5 may be referenced. Technique 100 can be performed at the initiation or planning of a treatment protocol, or as part of treatment protocol validation. In certain embodiments, image data may be part of a patient validation procedure. In step 102, image data is acquired using, for example, the energy delivery device 12 in imaging mode. In step 104, image data is provided as input for identifying the region of interest 44 from the image data. Once identified, in step 106, neuromodulation energy is delivered to the region of interest by, for example, delivering energy from the energy delivery device to reach the region of interest 44 through the patient's skin.

[0038] In step 108, the system 10 may acquire updated image data showing the movement of tissue 43 from its initial position, leading to movement of regions of interest 44b, 44c, and transitions between various positions (see Figure 4, tissues 43a, 43b, 43c). In step 110, the movement or change in position is identified, and in step 112, the modulation parameters of the energy application device 23 are adjusted. In one embodiment, the system 10 may use the movement of tissue 43 as a substitute or estimate for the movement of the region of interest 43.

[0039] In one example, updated image data may be evaluated to characterize a particular type of movement. For instance, rhythmic or periodic movement of tissue 43 and / or region of interest, occurring over a period of time (e.g., 1–5 seconds), moving towards and away from transducer 68, may be characteristic of respiration. The system can create a model that predicts the movement of the region of interest 44 over time in order to predict future respiration and, at a given time, deliver energy aligned with one or more predicted positions of the region of interest 44 during respiration. In an additional or alternative embodiment, the system 10 may identify pauses or the end of respiration from the acquired image data in order to deliver energy aligned with periods when the patient is suspending respiration and the region of interest is relatively still.

[0040] In one embodiment, the system 10 can use image data and the position of the region of interest 44 determined relative to the focal band 48 to calculate the delivery dose over time. For example, in one embodiment, the energy delivery device 12 can adjust the steering and / or focusing of energy delivery within a minimal range while adjusting other parameters as the region of interest moves. Based on the movement of the region of interest 44 identified outside the focal band 48, the system 10 can calculate the total delivery dose. Therefore, if movement occurs, the system 10 can extend the delivery time or account for the period during energy delivery when the region of interest 44 extends outside the focal band 48 so that the total dose delivered directly to the region of interest 44 falls within a desired parameter range. Furthermore, the system 10 can also consider the total delivery to areas outside the region of interest 44 and adjust the steering and / or focusing when the energy applied outside the region of interest 44 reaches a threshold. It should be understood that steering changes the angle of the ultrasonic beam, while focusing changes the depth of focus and / or overall size of the beam.

[0041] In certain embodiments, the system 10 uses a neural network to locate the region of interest 44 and / or target tissue 43 in the acquired image data. In one embodiment, the locateging may be in a largely autonomous manner with minimal operator intervention. Figure 7 is a schematic diagram of an embodiment in which a neural network is constructed to locate the region of interest 44 and / or target tissue 43 from the acquired image data. The neural network 122 may be based on image data 120 acquired from each imaging probe 68 (e.g., 68a, 68b, 68c) of various patients 118, including patients 118a, 118b, 118c, who are not the patient of interest (i.e., the patient receiving the administration). The neural network 122 receives its population image data and is trained with its population image data based on specific ground truth parameters. The neural network 122 may be specialized for a specific tissue or organ, or, in certain embodiments, for a specific administration plan. The neural network 122 may be part of the controller 16 as shown in the figure. In other embodiments, the neural network 122 may communicate with the controller 16, but it does not necessarily have to be part of the controller 16. The therapeutic probe, which can be configured as an energy application device 12, responds to the outputs from the controller 16 and the neural network. As illustrated in Figure 8, in step 124, the imaging probe 68 acquires image data from the patient 118, and this image data is provided as input to the neural network 122.

[0042] Figure 8 is a flowchart of Method 130, which can be performed in association with the specific elements shown in Figures 1 to 7. This method includes a step in step 132 where population image data is provided and a neural network is trained. Method 130 also receives image data of a patient of interest in step 134. The patient of interest may or may not be included in the population image data. In step 136, the trained neural network is used to identify a region of interest from the image data. In one embodiment, Method 130 may include collecting images from the patient, annotating those images (annotations for supervised learning), and then updating the network by feeding back the annotated images. The updated network is then applied to all images subsequently collected from that patient.

[0043] Since data annotation can be a complex process, method 130 may further include selecting and annotating a subset of all images collected from patients and using them to update the network. The subset of images used for network updating can be selected based on various factors, one of which may be how well an existing population-based network model performs on those images. For example, if a population-based model already performs well on a given image, there may be little benefit in updating the model using that image. However, images for which the network results are insufficient can be detected manually or automatically using another criterion (e.g., a low probability score), and such images can be annotated by experts and input into the network.

[0044] As described herein, the neural network 122 may include one or more layers that enable the identification of organs and / or structures. Certain layers of the neural network 122 may be held back or frozen to train the model to a specific individual, while other layers of the network are trained with data obtained from the patient of interest. Large and deep networks are powerful, but such networks operate with large amounts of data. As may be the case with individual patients, when only a limited amount of data is available, freezing certain layers in a population-based model can reduce the number of parameters that the network must learn. Population-based models are also trained with similar images and / or similar tasks, so weights and filters learned in layers closer to the input layer are usually at sufficiently low levels (i.e., edges, lines, etc.) where the benefit of retraining is limited. The neural network may be a supervised or unsupervised neural network. The neural network 122 may be updated to accommodate patient-specific changes in the patient. Furthermore, the neural network 122 may include a validation step to assess the reliability of its recognition of the region of interest (see Figure 15). In one embodiment, if a patient-specific model is used, validation may be performed using an independent dataset from that patient to confirm that the overall accuracy of the model has improved for that patient before it is deployed to a treatment device.

[0045] Figure 9 shows an exemplary system 150 that can be used with or as part of system 10. System 150 includes various functions that enable image acquisition, such as a dual-function probe 152 (see Figure 10), which includes, for example, an imaging transducer 156, indicated as a GE 3S sector array probe (General Electric), and a therapeutic probe 154, indicated as a HIFU probe, as well as an image probe controller 155 that controls image acquisition via the imaging transducer 156. System 150 further includes a frame grabber 157 that operates with the acquired image data. It should be understood that, in certain embodiments, system 10 operates with images rendered from the acquired image data, but it is also possible to use raw image data or unrendered image data as input. The therapeutic probe 154 may be operated under the control of the therapeutic probe controller 162, which controls a pulse generation circuit 160 and an RF power amplifier 158.

[0046] Figure 11 shows an example of a graphical user interface that can be used with system 10 and displays images acquired using system 150. The graphical user interface displays the neuromodulation prescription. The neuromodulation prescription is a term that represents the treatment protocol (including treatment date or timing information for individual patients) and / or target tissue, and in certain embodiments, may include the total energy amount of each dose and observable parameters related to the treatment. For example, the prescription may include a target concentration change relative to a baseline value before the start of treatment for the molecule of interest. The user interface may also display the status of the procedure and acquired ultrasound images, such as acquired patient image data, as well as captions provided by the neural network showing anatomical structures detected from the images. The neural network identified the anatomical structure of the kidney. However, the relevant treatment protocol is for energy delivery for autonomous neuromodulation to the liver.

[0047] Therefore, as shown in the illustrative graphical user interface of Figure 12, when initiating administration, the system waits until the target anatomical structure (in this case, the liver) appears in the field of view before performing the treatment. The status is displayed as "Adjusting" because the identified probe placement is not suitable for performing the treatment. In Figure 13, when the neural network determines that the location of the anatomical structure in the field of view matches that of the anatomical structure of interest, the therapeutic energy or the dose of neuromodulation energy is delivered. The status changes to "Delivering," and the therapeutic beam is visually displayed in the ultrasound image. In Figure 14, the system is focused on the target organ (i.e., the liver), but has stopped delivering the treatment, and has reached the total energy amount for individual doses, as shown in this frame.

[0048] Figure 15 shows the results from a neural network trained for organ detection to identify and locate the spleen, kidneys, and liver on ultrasound images. The acquired images include specific probability representations (e.g., 99%, 97%). In one embodiment, an organ or region of interest within an organ may be identified when a probabilistic threshold is reached based on the output of the neural network. In one example, the threshold may be at least 95%, at least 97%, or at least 99%.

[0049] The technology of this disclosure enables the delivery of neuromodulation energy that takes into account the movement of a desired region of interest. The movement may be movement during therapy, for example, movement resulting from respiration or blood flow. The movement may also be a change in position or organ size when doses are administered at intervals. For example, the size or depth of an organ may change due to a decrease in the patient's weight or clinical symptoms. In response, such changes can be evaluated to deliver neuromodulation energy more accurately.

[0050] This specification uses examples to disclose the present invention in best mode and to enable those skilled in the art to carry out the invention, including the manufacture and use of any apparatus or system, and the execution of any incorporated method. The patentable scope of the present invention is defined by the claims and may include other embodiments that a person skilled in the art could conceive. If such other examples have structural elements that are not different from the language of the claims, or include equivalent structural elements that are substantially different from the language of the claims, such examples are intended to be within the scope of the claims. [Explanation of Symbols]

[0051] 10 Systems 12 Energy application device 14. Pulse Generator 16 Controllers 20 Evaluation device 30 processors 32 memory 33 Lead wires 34 Input / Output Circuits 36 displays 37 Beam Controller 38 Position Sensor 39 Contact Sensor 42 transducers 43, 43a, 43b, 43c organization 44, 44a, 44b, 44c Areas of Interest 46 Treatment position Focal bands 48, 48a, and 48b 50 Edge 52 Blood vessels 54 Internal Neural Structure 56 Dimensional range 60 organs 62 Blood vessels 68 Imaging probes 70 Treatable area 100 methods 118 patients 122 Neural Networks 130 Method 150 Systems 152 Dual-Function Probe 154 Therapeutic probes 155 Image probe controller 156 Imaging Transducer 157 Frame Grabber 158 RF Power Amplifier 160 pulse generation circuit 162 Therapeutic probe controller

Claims

1. It is a neuromodulation system, pulse generator, Controller and Includes, The aforementioned controller, Receive image data representing the internal tissue of the subject, The received image data provides a determination that it matches a region of interest in the internal tissue of the subject. It is configured in such a way, The aforementioned determination is, A step of generating a probabilistic representation of the identification, The steps include comparing the probabilistic representation of the identification with the probabilistic threshold for identification, Includes, The aforementioned controller, If it is determined that the probabilistic representation of the identification is equal to or greater than the probabilistic threshold for the identification, a signal indicating identification and position matching is returned. The pulse generator is configured to generate energy pulses based on the fact that the returned signal indicates identification and positional matching. The controller associates changes in the location of the region of interest characteristic of the subject's respiratory pattern based on the updated image data, and adjusts the control of the pulse generator to generate the energy pulse during the period predicted to be between breaths of the subject. Neuromodulation system.

2. The aforementioned controller, Receive updated image data, Based on the updated image data, the change in the position of the region of interest is identified. Based on the determination that the updated image data does not match the region of interest, the generation of the energy pulse is temporarily suspended in response to the absence of a signal. The system according to claim 1, configured as described above.

3. The system according to claim 1, wherein the controller is configured to predict the movement path of the region of interest and to dynamically change one or more control parameters of the pulse generator based on the predicted movement path.

4. The system according to claim 1, wherein the energy pulse is applied to the region of interest so that the neuromodulation energy dose is not applied to a region outside the region of interest.

5. The system according to claim 1, wherein the controller is configured to track the movement of the region of interest and to automatically operate the ultrasonic energy application device based on the tracked movement, and the ultrasonic energy application device receives the energy pulse from the pulse generator.

6. The system according to claim 5, wherein the controller is configured to change the focal position of the ultrasonic beam of the energy application device via control based on a change in the position of the region of interest, and the energy application device receives the energy pulse from the pulse generator.

7. The system according to claim 5, wherein the ultrasonic energy application device comprises a motor configured to change the position or angle of the ultrasonic energy application device and / or the transducer of the ultrasonic energy application device relative to the subject in response to instructions from the controller for aligning the ultrasonic beam of the energy application device to the region of interest.

8. The system according to claim 1, comprising an imaging transducer configured to acquire the aforementioned image data.

9. The system according to claim 8, wherein the imaging transducer is part of an ultrasonic energy application device, and while receiving the energy pulse, the imaging transducer is in contact with the subject.

10. A method for delivering neuromodulation energy, The steps include receiving image data of the subject, The steps include generating a display that probabilistically indicates the identification of a region of interest based on the aforementioned image data, The steps include comparing the probabilistic representation of the identification with the probabilistic threshold for identification, The steps include: returning a signal indicating a match between identification and location when it is determined that the probabilistic representation of identification is greater than or equal to the probabilistic threshold for identification; The steps include controlling a pulse generator to generate an energy pulse in response to a return signal indicating identification and positional matching, The steps include obtaining updated image data from the subject, The steps include relating the changes in the location of the region of interest characteristic of the subject's respiratory pattern to the updated image data, The steps include adjusting the control of the pulse generator to generate the energy pulse during the period predicted to be between breaths of the subject, Includes, A method for showing the internal structure of the region of interest using updated image data.

11. The method according to claim 10, further comprising the step of acquiring the image data using an energy application device.

12. The method according to claim 11, wherein the energy application device is an ultrasonic transducer.

13. A step of identifying changes in the position of the region of interest based on the updated image data, Based on the determination that the updated image data does not match the region of interest, the generation of the energy pulse is temporarily suspended in response to the signal not being returned. The method according to claim 10, including the method described in claim 10.

14. The method according to claim 13, comprising the step of adjusting the energy pulse based on the region of interest approaching the energy application device or based on the region of interest moving away from the energy application device.

15. The method according to claim 13, comprising changing the focal position of the ultrasonic beam of the energy application device via control based on a change in the position of the region of interest, wherein the energy application device receives an energy pulse from a pulse generator.

16. The method according to claim 15, further comprising the step of focusing to supply additional energy based on a change in the location of the region of interest.

17. A method for delivering neuromodulation energy from a therapeutic probe, The controller receives the image data of the subject, The controller receives an annotation that identifies a region of interest based on the aforementioned image data, The steps include: updating the neural network with the controller based on the aforementioned annotation; The controller receives subsequent image data of the subject, The controller provides a step of operating the updated neural network to determine whether the subsequent image data matches the region of interest, The controller generates a probabilistic representation of the identification based on the output from the neural network, The steps include: comparing the probabilistic representation of the identification with the probabilistic threshold for identification and the controller; The steps include the controller providing the determination, The controller returns a signal indicating identification and position matching when it determines that the probabilistic representation of the identification is equal to or greater than the probabilistic threshold for the identification. The steps include: the therapeutic probe generating an energy pulse in response to a return signal indicating the identification and positional agreement; The steps include: the controller acquiring updated image data from the subject; The steps include: the controller associating changes in the location of regions of interest characteristic of the subject's respiratory pattern based on the updated image data; The steps include: the controller adjusting the control of the pulse generator to generate the energy pulse during the period predicted to be between breaths of the subject; Methods that include...

18. The controller uses the neural network to identify changes in the location of the region of interest based on the updated image data, The method according to claim 17, comprising the steps of the therapeutic probe interrupting the generation of an energy pulse in response to no signal being returned from the neural network, based on the controller providing a determination that the updated image data does not match the region of interest,

19. The method according to claim 18, wherein the neural network is trained with images from a group of subjects.

Images