The disclosure relates to electrosurgical procedures and, more particularly, to systems and methods for controlling an ultrasonic surgical system.
Surgical instruments are utilized to perform various functions on tissue structures. An example of such a surgical instrument is an ultrasonic surgical instrument that utilizes ultrasonic energy, i.e., ultrasonic vibrations, to treat tissue. More specifically, a typical ultrasonic surgical instrument utilizes mechanical vibration energy transmitted at ultrasonic frequencies to coagulate, cauterize, fuse, seal, cut, desiccate, fulgurate, or otherwise treat tissue.
As used herein, the term “distal” refers to the portion that is being described which is further from a user, while the term “proximal” refers to the portion that is being described which is closer to a user. Further, to the extent consistent, any of the aspects described herein may be used in conjunction with any or all of the other aspects described herein.
In accordance with aspects of the disclosure, a computer-implemented method for controlling a surgical system is provided. The computer-implemented method includes activating an ultrasonic surgical system including an ultrasonic generator, an ultrasonic transducer, and an ultrasonic blade. The method further includes collecting data from the ultrasonic surgical system, including an electrical parameter associated with the activated ultrasonic surgical system. The method additionally includes communicating the data to a machine learning algorithm, determining the vessel size based on the data using the machine learning algorithm, communicating the determined vessel size to a computing device associated with the ultrasonic generator, and controlling the activated ultrasonic surgical system in accordance with the vessel size. When the ultrasonic surgical system is activated, the ultrasonic generator produces a drive signal to drive the ultrasonic transducer which, in turn, produces ultrasonic energy that is transmitted to the ultrasonic blade for treating a vessel in contact with the ultrasonic blade.
In an aspect of the present disclosure, controlling the activated ultrasonic surgical system includes determining when to stop generating, by the ultrasonic generator, the drive signal, wherein the drive signal is for sealing the vessel. A second drive signal is generated, by the ultrasonic generator, for cutting the vessel, based on the determining.
In another aspect of the present disclosure, the data from the ultrasonic surgical system may include a voltage, a current, a frequency, a velocity, a TransV, a TransVPhase, MFB, Z_ph, or df/dt.
In an aspect of the present disclosure, a machine learning algorithm may include a neural network.
In yet another aspect of the present disclosure, the neural network may include a temporal convolutional network or a feed-forward network.
In a further aspect of the present disclosure, the computer-implemented method may further include training the neural network by accessing ultrasonic surgical system data or identifying patterns in data.
In an aspect of the present disclosure, the computer-implemented method may further include training the neural network to use training data, which may include: a voltage, a current, a frequency, a velocity, a TransV, a TransVPhase, MFB, Z_ph, or df/dt.
In a further aspect of the present disclosure, training the neural network may include supervised training, unsupervised training, or reinforcement learning.
In accordance with aspects of the disclosure, a system for controlling an ultrasonic surgical procedure is presented. The system includes an ultrasonic generator, an ultrasonic transducer, an ultrasonic blade, a processor, and a memory coupled to the processor. When the ultrasonic surgical system is activated, the ultrasonic generator produces a drive signal to drive the ultrasonic transducer which, in turn, produces ultrasonic energy that is transmitted to the ultrasonic blade for treating a vessel in contact with the ultrasonic blade. The memory coupled to the processor includes instructions, which when executed by the processor, cause the system to: collect data from the ultrasonic surgical system, communicate the data to a machine learning algorithm, determine by the machine learning algorithm the vessel size based on the data, communicate the determined vessel size to a computing device, and control the activated ultrasonic surgical system in accordance with the vessel size. The data includes an electrical parameter associated with the activated ultrasonic surgical system. The computing device is associated with the ultrasonic generator.
In a further aspect of the present disclosure, controlling the activate ultrasonic surgical system may include: determining when to stop generating, by the ultrasonic generator, a first drive signal for sealing the vessel, and generating, by the ultrasonic generator, a second drive signal for a cutting the vessel, based on the determining.
In yet a further aspect of the present disclosure, collecting the data from the ultrasonic surgical system may include measuring a voltage, a current, a frequency, a velocity, a TransV, a TransVPhase, MFB, Z_ph, or df/dt.
In yet another aspect of the present disclosure, a machine learning program may include a neural network.
In a further aspect of the present disclosure, the neural network may include a temporal convolutional network or a feed-forward network.
In yet a further aspect of the present disclosure, the instructions, when executed by the processor, may further cause the system to train the neural network by accessing ultrasonic surgical system data or identifying patterns in data.
In yet another aspect of the present disclosure, the instructions, when executed by the processor, may further cause the system to train the neural network to use training data which may include: a voltage, a current, a frequency, a velocity, a TransV, a TransVPhase, MFB, Z_ph, or df/dt.
In a further aspect of the present disclosure, the training of the neural network may include a supervised, unsupervised training, or reinforcement learning.
In accordance with aspects of the disclosure, a non-transitory storage medium that stores a program, causing a computer to execute a method is presented. The method includes activating an ultrasonic surgical system. The ultrasonic surgical system includes an ultrasonic generator, an ultrasonic transducer, and an ultrasonic blade. The method further includes collecting data from the ultrasonic surgical system, communicating the data to a machine learning algorithm, determining the vessel size based on the data, using the machine learning algorithm, communicating the determined vessel size to a computing device associated with the ultrasonic generator, and controlling the activated ultrasonic surgical system in accordance with the vessel size. When the ultrasonic surgical system is activated, the ultrasonic generator produces a drive signal to drive the ultrasonic transducer which, in turn, produces ultrasonic energy that is transmitted to the ultrasonic blade for treating a vessel in contact with the ultrasonic blade. The data includes an electrical parameter associated with the activated ultrasonic surgical system.
In an aspect of the present disclosure, controlling the activated ultrasonic surgical system includes determining when to stop generating, by the ultrasonic generator, the drive signal, wherein the drive signal is for sealing the vessel. A second drive signal is generated, by the ultrasonic generator, for cutting the vessel, based on the determining.
In another aspect of the present disclosure, the data from the ultrasonic surgical system may include a voltage, a current, a frequency, a velocity, a TransV, a TransVPhase, MFB, Z_ph, or df/dt.
In an aspect of the present disclosure, a machine learning algorithm may include a neural network.
In yet another aspect of the present disclosure, the neural network may include a temporal convolutional network or a feed-forward network.
Various aspects and features of the disclosure are described herein with reference to the drawings wherein:
Tissue sealing involves heating tissue to liquefy the collagen and elastin in the tissue so that it reforms into a fused mass with significantly-reduced demarcation between the opposing tissue structures. To achieve a tissue seal without causing unwanted damage to tissue at the surgical site or collateral damage to adjacent tissue, it is necessary to control the application of energy to tissue, thereby controlling the temperature of tissue during the sealing process.
With respect to utilizing vessel size information in real-time in order to control the application of energy to tissue to achieve a tissue seal, it would be desirable to determine vessel size during the initial stages of the tissue sealing process to improve seal quality based on measurement data. As detailed below, this may be accomplished by utilizing data available from the surgical system and running a machine learning algorithm to estimate vessel size based upon that data. The estimated vessel size may then be fed back to a controller for use in controlling the application of energy to tissue in accordance therewith. The vessel size may include, but is not limited to vessel diameter, vessel mass, tissue surface area, and/or tissue mass.
The systems and methods herein are not limited to estimating vessel diameter. In various embodiments, the systems and methods may estimate vessel mass (or tissue mass) and then utilize vessel mass (or tissue mass) to detect and adjust for tissue types. For example, the tissue types may include both vascular and non-vascular, arteries vs. veins, etc. In various embodiments, the system may adjust for thin and thick tissue, small and large vessels (veins, arteries), pulmonary vasculature, etc.
The systems and methods of the disclosure detailed below may be incorporated into any type of surgical system for treating tissue such as, for example, the ultrasonic surgical systems detailed hereinbelow. For purposes of illustration and in no way limiting the scope of the appended claims, the systems and methods for estimating vessel diameter for use in controlling the application of energy to tissue are described in the disclosure in the context of ultrasonic surgical systems.
The terms “artificial intelligence,” “data models,” or “machine learning” may include, but are not limited to, neural networks, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), Bayesian Regression, Naive Bayes, nearest neighbors, least squares, means, and support vector regression, among other data science and artificial science techniques.
The term “application” may include a computer program designed to perform particular functions, tasks, or activities for the benefit of a user. Application may refer to, for example, software running locally or remotely, as a standalone program or in a web browser, or other software which would be understood by one skilled in the art to be an application. An application may run on a controller, e.g., controller 500 (
Referring now to
With continued reference to
The actuator tube of outer shaft assembly 415 is configured to move relative to the support tube of outer shaft assembly 415 to enable pivoting of clamp member 458 between an open position, wherein clamp member 458 is spaced from blade 432, and a closed position, wherein clamp member 458 is approximated relative to blade 432. Clamp member 458 is moved between the open and closed positions in response to actuation of clamp trigger 426.
Continuing with reference to
TAG 420, as noted above, includes generator 470 and ultrasonic transducer 480. Generator 470 includes an outer housing 460 that houses a TAG microcontroller 500 having a memory. TAG 420 supports the ultrasonic transducer 480 thereon. The ultrasonic transducer 480 may include a piezoelectric stack and defines a forwardly extending horn configured to engage the proximal end of the waveguide. A series of contacts (not explicitly shown) associated with TAG 420 enable communication of power and/or control signals between TAG 420, battery assembly 418, and the two-mode switch assembly, although contactless communication therebetween is also contemplated.
In general, in use, when battery assembly 418 and TAG 420 are attached to handle assembly 412 and the waveguide, respectively, and ultrasonic surgical instrument 410 is activated, battery assembly 418 provide power to generator 470 of TAG 420 which, in turn, uses this power to apply an AC signal to the ultrasonic transducer 480 of TAG 420. The ultrasonic transducer 480, in turn, converts the AC signal into high-frequency mechanical motion. This high-frequency mechanical motion produced by the ultrasonic transducer 480 is transmitted along the waveguide to the blade 432 for application of such ultrasonic energy to tissue adjacent to or clamped between blade 432 and clamp member 458 to treat tissue.
Referring now to
The AC current and voltage sensors of the sensor module 444 sense and provide the sensed AC voltage and current signals, respectively, to the controller 500 of generator 470, which then may adjust output of battery assembly 418 and/or the AC output stage 440 in response to the sensed AC voltage and current signals. Controller 500 is described in greater detail hereinbelow (see
The sensed voltage and current from sensor module 444 are fed to analog-to-digital converters (ADCs) 442. The ADCs 442 sample the sensed voltage and current to obtain digital samples of the voltage and current of the AC output stage 440. The digital samples are processed by the controller 500 and used to generate a control signal to control the DC/AC inverter of the AC output stage 440. The ADCs 442 communicate the digital samples to the controller 500 for further processing.
In various embodiments, the controller 500 may collect data relating to the generator 470 during use, including voltage, current, power, frequency, velocity, or any parameters derived from these signals such as AC voltage applied to the transducer (TransV), AC current applied to the transducer (Transl), phase angle between TransV and the phase reference signal (TransVPhase), Motional feedback bridge (MFB), impedance phase (Z_ph), or df/dt. For example, with respect to the ultrasonic surgical system of
During such tissue treatment, the sensor circuitry, e.g., sensor module 444, of the generator 470 may sense parameters of the tissue, system, and/or energy (ultrasonic energy) such as, for example, voltage, current, frequency, velocity, TransV, TransVPhase, MFB, Z_ph, and/or df/dt. This may occur as a snapshot or over a time interval and may be determined at the beginning of tissue treatment, e.g., at or within 250 ms of initiation of tissue treatment. The sensed data may include, for example, time that the power is applied to ultrasonic transducer 480. The sensor module 444 may measure data from the system, for example, the voltage and/or a current of the drive signal delivered to the ultrasonic transducer 480. This sensed data obtained by the sensor circuitry is relayed to the controller 500 (via the ADC's 442, in embodiments) for further processing, as detailed below.
In various embodiments, the controller 500 uses the stored settings and the parameters as training data for a machine learning algorithm. In various embodiments, training the machine learning algorithm may be performed by a computing device outside of the generator 470, and the resulting algorithm may be communicated to the controller 500 of generator 470. In various embodiments, the controller 500 communicates the determined vessel diameter that was output from the machine learning algorithm to a computing device, e.g., of controller 500, for use in formulating, e.g., switching, confirming, modifying, generating, etc., a tissue sealing algorithm. In various embodiments, the controller 500 adjusts, on the generator 470, an algorithm that controls a sealing cycle (by adjusting the drive signal from generator 470 to ultrasonic transducer 480), based on the output of the machine learning algorithm. In various embodiments, the machine learning algorithm network may use supervised learning, unsupervised learning, or reinforcement learning. In various embodiments, the neural network may include a temporal convolutional network, with one or more fully connected layers, or a feed forward network. In various embodiments, the training may happen on a separate system. In various embodiments, the controller 500 may use the stored settings and the sensed parameters for a machine learning algorithm to infer the vessel diameter.
Referring to
In various embodiments, the memory 530 can be random access memory, read-only memory, magnetic disk memory, solid state memory, optical disc memory, and/or another type of memory. In various embodiments, the memory 530 can be separate from the controller 500 and can communicate with the processor 520 through communication buses of a circuit board and/or through communication cables such as serial ATA cables or other types of cables. The memory 530 includes computer-readable instructions that are executable by the processor 520 to operate the controller 500. In various embodiments, the controller 500 may include a network interface 540 to communicate with other computers or a server. In embodiments, a storage device 510 may be used for storing data. In various embodiments, the controller 500 may include one or more FPGAs 550. The FPGA 550 may be used for executing various machine learning algorithms such as those provided in accordance with the disclosure, as detailed below.
The memory 530 stores suitable instructions, to be executed by the processor 520, for receiving the sensed data, e.g., sensed data from sensor module 444 via ADCs 442 (see
Storage device 510 of controller 500 stores one or more machine learning algorithms and/or models, configured to estimate one or more tissue parameters, e.g., vessel diameter, vessel mass, and/or tissue mass, based upon the sensed data received from sensory circuitry, e.g., from sensor module 444 via ADCs 442 (see
Referring generally to
Once the vessel diameter is determined by the controller 500, depending upon the vessel diameter, settings, user input, etc., controller 500 may for example, output an alert and/or warning to user interface, implement, switch, or modify a particular tissue sealing algorithm based upon which the battery cells of battery assembly 418 and AC output stage 440 provide energy to the ultrasonic transducer 480, modify the energy provided to the ultrasonic transducer 480, and/or inhibit further energy delivery to the ultrasonic transducer 480.
With reference to
In various embodiments, the generator control parameters 904 that correlate with particular sensor measurements 902 of are used as inputs to the machine learning algorithm during training. In various embodiments, the generator control parameters 904 may include, for example, time, slope, or other generator 470 parameters. In various embodiments, the controller 500 may communicate to a remote server, for example, the stored adjusted control parameters, text data, and/or the output of the machine learning algorithm.
In various embodiments, the outputs of the neural network may be used as training data for supervised learning, unsupervised learning, or reinforcement learning. It is contemplated that the training may be performed on a separate system, for example, GPU workstations, High Performing Computer Clusters, etc., and the trained network would then be deployed in the ultrasonic surgical system. In various embodiments, the controller 500 outputs, from the machine learning algorithm, a prediction of the vessel diameter (vessel mass and/or tissue mass) based on the inputs.
Referring now to
Referring now to Instrument 2 of
Referring now to
Initially, at step 802, the controller 500 may activate an ultrasonic surgical system. The ultrasonic surgical system includes an ultrasonic generator 470, an ultrasonic transducer 480, and an ultrasonic blade 432. When the ultrasonic surgical system is activated, the ultrasonic generator 470 produces a drive signal to drive the ultrasonic transducer 480 which, in turn, produces ultrasonic energy that is transmitted to the ultrasonic blade 432 for treating a vessel in contact with the ultrasonic blade 432. The vessel defines a vessel diameter.
At step 804, the controller 500 may collect data from the ultrasonic surgical system. In various embodiments, the data includes electrical parameters associated with the activated ultrasonic surgical system. In various embodiments, the controller 500 may collect data relating to the generator 470, for example, voltage, current, frequency, velocity, TransV, TransVPhase, MFB, Z_ph, or df/dt. The data may be collected during an initial stage of activation, e.g., within the first 5 seconds of activation. At step 806, controller 500 may communicate the data to the machine learning algorithm 908 (e.g., a neural network). In various embodiments, the neural network may include a temporal convolutional network or a feed-forward network. In various embodiments, the machine learning algorithm 908 may be trained using data relating to the generator 470, for example, voltage, current, frequency, velocity, TransV, TransVPhase, MFB, Z_ph, or df/dt. In various embodiments, the training may include supervised training, unsupervised training, or reinforcement learning. In various embodiments, the reinforcement learning may include a reward or a punishment.
At step 808, the controller 500 may determine, using the machine learning algorithm 908, the vessel size based upon the data. The vessel size may include, for example, a vessel diameter, a vessel mass, a tissue surface area, and/or a tissue mass. For example, based on the output for the machine learning algorithm 908, the controller 500, may determine that the vessel diameter is approximately 6 mm. At step 810 the controller 500 may communicate the determined vessel diameter to a computing device associated with the ultrasonic generator 470.
At step 812, the controller 500 may control the activated ultrasonic surgical system in accordance with the vessel size. In various embodiments, the controller 500 may determine when to stop generating, by the ultrasonic generator 470, a first drive signal (e.g., a “seal” drive signal) for driving the ultrasonic transducer 480 to seal the vessel. In various embodiments, the controller 500 may generate, by the ultrasonic generator 470, a second drive signal (e.g., a “cut” drive signal) for driving the ultrasonic transducer to cut the vessel, based on the determining. For example, the controller 500 may determine at approximately 13 seconds to stop generating a “seal” drive signal and may then generate a “cut” drive signal.
Referring now to
From the foregoing and with reference to the various figure drawings, those skilled in the art will appreciate that certain modifications can also be made to the disclosure without departing from the scope of the same. While several embodiments of the disclosure have been shown in the drawings, it is not intended that the disclosure be limited thereto, as it is intended that the disclosure be as broad in scope as the art will allow and that the specification be read likewise. Therefore, the above description should not be construed as limiting, but merely as exemplifications of particular embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the claims appended hereto.
The present application is a U.S. National Stage Application filed under 35 U.S.C. § 371(a) claiming the benefit of and priority to International Patent Application No. PCT/US2021/012062, filed Jan. 4, 2021, which claims the benefit of and priority to U.S. Provisional Patent Application Ser. No. 62/961,818, filed Jan. 16, 2020, the entire disclosures of each of which being incorporated by reference herein.
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/US2021/012062 | 1/4/2021 | WO |
Number | Date | Country | |
---|---|---|---|
62961818 | Jan 2020 | US |