WO2023029495A1 - 基于智能温度感知的超声刀血管自适应剪切方法及系统 - Google Patents

基于智能温度感知的超声刀血管自适应剪切方法及系统 Download PDF

Info

Publication number
WO2023029495A1
WO2023029495A1 PCT/CN2022/087010 CN2022087010W WO2023029495A1 WO 2023029495 A1 WO2023029495 A1 WO 2023029495A1 CN 2022087010 W CN2022087010 W CN 2022087010W WO 2023029495 A1 WO2023029495 A1 WO 2023029495A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
ultrasonic
real
ultrasonic knife
time
Prior art date
Application number
PCT/CN2022/087010
Other languages
English (en)
French (fr)
Inventor
姚龙洋
王福源
刘振中
丁飞
骆威
Original Assignee
以诺康医疗科技（苏州）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 以诺康医疗科技（苏州）有限公司 filed Critical 以诺康医疗科技（苏州）有限公司
Publication of WO2023029495A1 publication Critical patent/WO2023029495A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods, e.g. tourniquets
    • A61B17/32—Surgical cutting instruments
    • A61B17/320068—Surgical cutting instruments using mechanical vibrations, e.g. ultrasonic
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
    • A61B90/03—Automatic limiting or abutting means, e.g. for safety
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
    • A61B90/08—Accessories or related features not otherwise provided for
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods, e.g. tourniquets
    • A61B2017/00017—Electrical control of surgical instruments
    • A61B2017/00022—Sensing or detecting at the treatment site
    • A61B2017/00084—Temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods, e.g. tourniquets
    • A61B17/32—Surgical cutting instruments
    • A61B17/320068—Surgical cutting instruments using mechanical vibrations, e.g. ultrasonic
    • A61B2017/320082—Surgical cutting instruments using mechanical vibrations, e.g. ultrasonic for incising tissue
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
    • A61B90/08—Accessories or related features not otherwise provided for
    • A61B2090/0807—Indication means
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
    • Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working

Definitions

  • the present invention relates to the field of medical devices, in particular to a method and system for controlling an ultrasonic scalpel, in particular to a method and system for adaptively cutting blood vessels by an ultrasonic scalpel based on intelligent temperature sensing, and a generator and an ultrasonic scalpel equipped with the system. Knife surgical instrument.
  • Ultrasonic cutting and hemostasis surgery system for soft tissue refers to the ultrasonic vibration obtained through the piezoelectric converter (the electrical energy is transmitted to the piezoelectric converter through the energy generator, and the electrical energy is converted into mechanical energy by the piezoelectric converter). It is further amplified, and the amplified ultrasonic vibration is used for cutting and coagulating the soft tissue by the ultrasonic knife rod. Clinical use of this device enables lesion resection at lower temperatures and less bleeding, and ensures minimal lateral thermal damage to tissue. With the popularity of minimally invasive surgery, ultrasonic scalpel has become a routine surgical instrument.
  • the ultrasonic knife system is mainly composed of a generator, a transducer and an ultrasonic knife bar. As shown in FIG.
  • the ultrasonic knife bar 14 at the farthest end is coupled with the transducer 11 inside the cannula 13 , and the transducer 11 is connected with a generator (not shown) through a cable 15 .
  • the current of ultrasonic frequency in the generator is transmitted to the transducer, and the transducer converts the electrical energy into mechanical energy that vibrates back and forth.
  • the end of the ultrasonic cutter rod moves at a certain frequency (such as 55.6kHz) vibration, the heat generated by friction causes the water in the tissue cells in contact with the knife tip to vaporize, the protein hydrogen bond breaks, the cells disintegrate and re-merge, and the tissue is cut after solidification.
  • a certain frequency such as 55.6kHz
  • controlling the appropriate temperature range can divide the blood vessel cutting process into two stages: vascular sealing and incision.
  • control the relatively low output power level to keep the blood vessels in a suitable temperature range to ensure that the blood vessels can be well fused without being damaged.
  • the output power level is increased to control the blood vessel at a high temperature above 200°C to achieve rapid drying, coagulation and incision of the blood vessel.
  • it is necessary to design an adaptive shearing method that can intelligently control the temperature of the ultrasonic blade and the power level of the transducer.
  • the present invention provides a method and system for self-adaptive shearing of blood vessels by an ultrasonic knife based on intelligent temperature sensing, a generator equipped with the system, and an ultrasonic knife surgical instrument.
  • a method for self-adaptive shearing of blood vessels by an ultrasonic knife based on intelligent temperature perception comprising the following steps,
  • the temperature distribution function model is a neural network algorithm model, including one or more algorithm model combinations of feedforward neural network, memory neural network, and attention neural network, and the model training method is supervised learning, semi-supervised learning, One or more combinations of unsupervised learning and reinforcement learning.
  • the model training method is specifically to extract input features from the training set, input them into the neural network algorithm model to calculate the intermediate value and gradient value of each neuron, and the loss function of the model can be mean square error MSE or average Absolute error MAE, and use the gradient descent method to update the weight, repeat the above process until the model reaches the predetermined stop condition, stop training and save the model after reaching the stop condition.
  • the loss function of the model can be mean square error MSE or average Absolute error MAE, and use the gradient descent method to update the weight, repeat the above process until the model reaches the predetermined stop condition, stop training and save the model after reaching the stop condition.
  • the temperature distribution function model is composed of layers and corresponding neurons and weights, weight parameters and application programs are stored in the generator memory, the memory is Flash, EEPROM or other non-volatile storage devices, and the application program is stored in the processor
  • the processor is either an ARM, DSP, FPGA, CPU, GPU or ASIC chip existing in the generator, or a remote server connected through a network.
  • step S1 "estimating the real-time temperature of the ultrasonic cutter bar according to the temperature distribution function model” specifically includes inputting characteristic parameters to the temperature distribution function model, and the characteristic parameters include work feedback parameters, physical structure characteristic parameters , one or more combinations of environmental parameters.
  • the work feedback parameters include one or several parameters of real-time voltage U, real-time current I, power P, impedance R, real-time resonance frequency f, real-time voltage and current phase difference ⁇ ;
  • the physical structure characteristic parameters include ultrasonic One or more parameters of the material of the cutter bar and the length of the tool bar;
  • the environmental parameters include one or more parameters of the ambient temperature and the ambient humidity.
  • step S2 "judging the temperature range of the real-time temperature” specifically includes,
  • Three preset temperature thresholds from low to high, are the first temperature threshold T 1 , the second temperature threshold T 2 , and the third temperature threshold T 3 ;
  • Preset temperature range below the first temperature threshold T1 is the first temperature range, between the first temperature threshold T1 and the second temperature threshold T2 is the second temperature range, the second temperature threshold Between T2 and the third temperature threshold T3 is a third temperature range;
  • the power level of the ultrasonic knife transducer is adaptively adjusted within the first current value output range so that the ultrasonic knife bar is at Reach the second temperature threshold T 2 on the basis of maintaining the first temperature change rate; when it is judged that the real-time temperature T est is in the second temperature range, adaptively adjust the ultrasonic knife transducer within the second current value output range
  • the power level makes the ultrasonic knife rod reach the third temperature threshold T 3 on the basis of maintaining the second temperature change rate; when it is judged that the real-time temperature T est is in the third temperature range, within the third current value output range Adaptively adjust the power level of the transducer of the ultrasonic knife to maintain the third temperature change rate of the ultrasonic knife for a duration of t1.
  • the first current value, the second current value, and the third current value are a constant value or a value range; the first current output value is greater than the second current output value, and the second current output value value greater than the third current output value.
  • the first temperature change rate, the second temperature change rate, and the third temperature change rate are all within 0-50° C./s, and the first temperature change rate is the largest.
  • the temperature rise of the ultrasonic knife rod does not exceed 200° C. on the basis of maintaining the third temperature change rate, and the third temperature range corresponds to the optimum closing temperature range of blood vessels.
  • the power level applied to the ultrasonic knife transducer is adjusted to control the current output value of the ultrasonic knife, so that the ultrasonic knife bar maintains the third temperature change rate.
  • the four-rate-of-temperature base ramps up and remains within a fourth temperature range.
  • the fourth temperature range does not exceed 300°C, preferably 200°C-300°C, and the fourth temperature range corresponds to the blood vessel drying and cutting temperature range.
  • the present invention also discloses an ultrasonic knife blood vessel self-adaptive shearing system based on intelligent temperature perception, including:
  • a real-time temperature estimation unit is used to estimate the real-time temperature T est of the ultrasonic cutter bar according to the temperature distribution function model;
  • a processing unit configured to determine the temperature range of the real-time temperature T est ;
  • the adjustment unit is used to adjust the power level applied to the transducer of the ultrasonic knife according to the judgment result, so as to control the current output of the ultrasonic knife, and then control the rate of temperature change.
  • the present invention also discloses a generator for self-adaptive shearing control of ultrasonic scalpel blood vessels based on intelligent temperature perception, including:
  • control circuit coupled to the memory, the control circuit configured to:
  • the power level applied to the transducer of the ultrasonic knife is adjusted to control the current output of the ultrasonic knife, thereby controlling the temperature change rate.
  • the present invention also discloses an ultrasonic scalpel surgical instrument based on intelligent temperature sensing and adaptive cutting control of ultrasonic scalpel blood vessels, including:
  • an ultrasonic electromechanical system comprising an ultrasonic transducer coupled to the ultrasonic blade via an ultrasonic guide;
  • a generator configured to supply power to the ultrasound transducer, wherein the generator includes a control circuit configured to:
  • the power level applied to the transducer of the ultrasonic knife is adjusted to control the current output of the ultrasonic knife, thereby controlling the temperature change rate.
  • the beneficial effect of the present invention is mainly reflected in that the actual temperature of the cutter rod is distributed along the one-dimensional space of the cutter rod when the ultrasonic cutter rod is working, and the temperature distribution on it is determined by the real-time working feedback parameters of the ultrasonic cutter rod, the physical structure characteristic parameters and the surrounding environment parameters Set decision, each temperature distribution corresponds to a solution of the temperature distribution function, which can be approximated by machine learning algorithm; when the ultrasonic tool holder is working, according to its real-time resonance frequency, voltage, current, impedance, power, shape and environment and other characteristic parameters , input the machine learning algorithm model to estimate the real-time temperature distribution of the ultrasonic knife blade, and then perform power control according to the estimated temperature, which is accurate and effective.
  • Inputting the real-time feature parameter set into at least one machine learning algorithm model can estimate the temperature of the ultrasonic knife blade including the tip of the knife; adjust the output power level according to the first energy control algorithm to keep the target temperature within the first temperature range, and complete the blood vessel sealing process ; Adjust the output power level according to the second energy control algorithm to keep the target temperature within the second temperature range, thereby completing the blood vessel drying, coagulation and incision process.
  • Fig. 1 is a schematic diagram of the structural configuration of the ultrasonic knife in the prior art
  • Fig. 2 is a flow chart of the present invention to estimate the real-time temperature of the ultrasonic cutter bar based on the temperature distribution function model;
  • Fig. 3 is a schematic flow chart of the ultrasonic knife blood vessel self-adaptive cutting method based on intelligent temperature sensing in the present invention
  • Fig. 4 is a flow chart of the first adaptive energy control algorithm of the ultrasonic knife based on intelligent temperature perception in the present invention
  • Fig. 5 is a flow chart of the second adaptive energy control algorithm of the ultrasonic knife based on intelligent temperature perception in the present invention
  • Fig. 6 is a graph of an embodiment of the estimated target temperature change in the adaptive cutting of blood vessels by the ultrasonic knife based on intelligent temperature sensing according to the present invention.
  • the phase-locking algorithm is used to change the working frequency of the transducer so that the transducer works at the state of maximum working efficiency, that is, the resonance state.
  • the sound wave propagating on the ultrasonic knife bar must meet the standing wave condition. Assuming that the length of the ultrasonic knife bar is L, the sound wave wavelength is ⁇ , the sound velocity is v, and the resonance frequency is f, then the following conditions must be met in the resonant state Working conditions:
  • n is a positive integer
  • the heat spreads along the setting direction of the ultrasonic knife bar so the temperature may be different at different positions of the ultrasonic knife bar.
  • the temperature t at different positions is expressed as:
  • T(l) is a position temperature distribution function on the tool holder, l ranges from 0 to L, and the position of the apex on the tip side of the ultrasonic cutter holder is the coordinate origin.
  • Temperature can affect the Young's modulus of the tool holder, and ultimately affect the sound wave velocity.
  • the sound velocity v at different positions on the tool holder can be expressed as a function of temperature:
  • Formula (1) can be expressed as:
  • Formula (6) can be expressed as:
  • Formula (7) is an integral equation.
  • f is a certain resonant frequency
  • the temperature T(l) is affected by parameters such as voltage, current, power, impedance, shape of the tool holder, and environmental parameters.
  • the temperature distribution function T(l) of the integral equation may have infinitely many solutions, and there will be more different temperature distributions for different tool holders.
  • an artificial neural network algorithm model is a mathematical model inspired by the human brain nervous system, similar to biological neurons, composed of multiple Nodes (artificial neurons) are interconnected and can be used to model complex relationships between data.
  • the connections between different nodes are given different weights, and each weight represents the influence of one node on another node.
  • Each node represents a specific function, information from other nodes is comprehensively calculated by its corresponding weight, input into an activation function and a new activity value is obtained.
  • the activation function is used to introduce nonlinear elements and increase the expressive ability of the neural network. Commonly used activation functions include Sigmoid, Tanh, ReLU, etc.
  • artificial neurons are adaptive nonlinear dynamic systems composed of a large number of neurons through extremely rich and perfect connections.
  • the most commonly used neural network learning algorithm is the backpropagation algorithm, and the optimization method is the gradient descent algorithm.
  • the backpropagation algorithm is the optimization method.
  • the gradient descent algorithm is the gradient descent algorithm. Theoretically, a two-layer neural network can approximate any function, and increasing the number of network layers can make the neural network have stronger representation ability under the same number of neurons.
  • the commonly used neural network models include feedforward neural network model, memory neural network model and attention neural network model, etc.: multilayer perceptron (Multilayer Perceptron, MLP) and convolutional neural network (Convolutional Neural Network, CNN) are the first Feed neural network model; Recurrent Neural Network (RNN) is a memory neural network model, and commonly used RNN models include Gate Recurrent Unit (GRU) and Long Short-Term Memory Neural Network (Long Short-Term Memory, LSTM); Attention neural network models include Transformer, etc.
  • MLP Multilayer Perceptron
  • CNN convolutional neural network
  • RNN Recurrent Neural Network
  • GRU Gate Recurrent Unit
  • Long Short-Term Memory Neural Network Long Short-Term Memory
  • Attention neural network models include Transformer, etc.
  • the memory neural network model adds memory capability on the basis of the feedforward neural network, and is often used to process time series data.
  • Commonly used memory neural networks include RNN, GRU, LSTM, etc.
  • GRU and LSTM have long-term memory capabilities and are able to process long-term sequences.
  • the temperature distribution function model of the present invention may be based on a machine learning algorithm model including one or more combination of algorithm models in a neural network algorithm model.
  • the input characteristics include one or more combinations of work feedback parameters, physical structure characteristic parameters, and environmental parameters.
  • the work feedback parameters include but not limited to real-time voltage U, real-time current I, power P, impedance R, real-time resonance frequency f;
  • the physical structure characteristic parameters include but not limited to ultrasonic cutter bar material, length;
  • the environmental parameters include But not limited to ambient temperature and ambient humidity.
  • the voltage U and the current I are sampled in real time by the generator, and the real-time power P and impedance R can be calculated by the following formula:
  • the real-time frequency f is calculated by the following formula:
  • k is determined by a functional relationship between real-time voltage U and current I:
  • ⁇ is the real-time voltage and current phase difference, the calculation formula is:
  • Voltage phase ⁇ U and current phase ⁇ I are sampled by the generator in real time, and ⁇ 0 is a constant.
  • the sampling frequency of the voltage and current sensor can be 64 times or 128 times the actual signal frequency, etc.
  • the output voltage U, output current I, resonance frequency f, frequency first derivative df, impedance R, phase ⁇ , power P and other parameters are passed through the sampling value FFT and other mathematical operations can be obtained.
  • Physical structural characteristic parameters such as material and length of the ultrasonic knife bar can be stored in the memory chip of the ultrasonic knife or the generator, and the generator can directly read the corresponding memory chip to obtain these characteristic parameters, and the environmental parameters can be obtained by real-time measurement through the sensor.
  • the model training method of the present invention can be supervised learning, semi-supervised learning, unsupervised learning and reinforcement learning.
  • Supervised learning needs to collect all the input feature information and training labels of the model, which can be collected at a certain time interval, the time interval can be 1ms or 10ms, and the real-time temperature is measured as the supervised training label.
  • the real-time shear temperature point can be embedded or external A temperature sensor or an infrared thermometer is used to measure it, and a large amount of labeled data is collected as a training data set S.
  • a neural network model training process implemented by model supervised learning can be: take the input features from the training data set S, and input the neural network model to calculate the intermediate value and gradient value of each neuron, and the loss function of the model can be the mean square Error MSE or mean absolute error MAE, and use the gradient descent method to update the weight, repeat the above process until the model reaches the predetermined stop condition, such as the prediction accuracy reaches the target value or the loss is no longer reduced, stop training and save the model after reaching the stop condition , this model can represent the function of the temperature distribution on the blade including the blade tip when all the target ultrasonic blades are working.
  • the trained model is composed of each layer and corresponding neurons and weights.
  • the weight parameters and application algorithm programs are stored in the generator memory.
  • the memory can be Flash, EEPROM or other non-volatile storage devices, and the application program is in the processor.
  • the processor can be an ARM, DSP, FPGA, CPU, GPU or ASIC chip existing in the generator, or a remote server connected through a network.
  • the temperature distribution function model estimation method of the present invention is as shown in Figure 2, input the real-time ultrasonic knife feature parameter set X into the model, the model can find the most likely knife rod temperature distribution according to the input feature set, and the temperature T est can be determined by Obtained from the temperature distribution, T est is the estimated real-time temperature of the ultrasonic tool holder.
  • the present invention discloses a method for self-adaptive cutting of blood vessels by an ultrasonic knife based on intelligent temperature perception, which includes the following steps:
  • the present invention can control the output power level of the ultrasonic knife transducer based on the estimated real-time temperature to realize the sealing and cutting process of blood vessels.
  • the generator controls the temperature of the vascular surgery site to be in the first temperature range according to the first energy control algorithm to complete the blood vessel sealing process.
  • the first temperature range can be a suitable temperature range within 0°C to 200°C.
  • the first energy control algorithm One implementation is shown in Fig. 4 , the real-time temperature value is estimated by the temperature estimation model, and the output energy is controlled according to the temperature value.
  • the power level of the ultrasonic knife transducer is adaptively adjusted within the first current value output range so that the ultrasonic knife bar maintains the first temperature
  • the second temperature threshold T 2 is reached on the basis of the rate of change, and the first current range can correspond to a larger current value to achieve a larger power level output to achieve the purpose of quickly removing water on the surface of blood vessels and rapidly heating up.
  • the ultrasonic scalpel can be adaptively adjusted within the second current value output range
  • the power level of the transducer makes the ultrasonic knife rod reach the third temperature threshold T 3 on the basis of maintaining the second temperature change rate, so as to gradually increase the blood vessel temperature value and gradually denature the collagen in the blood vessel tissue.
  • the ultrasonic scalpel can be adaptively adjusted within the third current value output range
  • the power level of the transducer keeps the ultrasonic scalpel at the third rate of temperature change for a duration of t1, thereby achieving complete fusion of the vessel walls on both sides.
  • the above temperature range may be a suitable temperature range within 0-200° C.
  • the temperature change rate may be a suitable rate within 0-50° C./s
  • the first temperature change rate is the largest.
  • the temperature rise of the ultrasonic knife rod does not exceed 200° C. on the basis of maintaining the third temperature change rate
  • the third temperature range corresponds to the optimum closing temperature range of blood vessels.
  • the first current value, the second current value, and the third current value are a fixed value or a numerical range; the first current output value is greater than the second current output value, and the second current output value is greater than the set value the third current output value.
  • the second energy control algorithm is used to realize the incision process.
  • a control process is shown in FIG. 5 .
  • the estimated target temperature reaches the sealing end temperature threshold or exceeds the predetermined time threshold, it may be determined that the blood vessel sealing is completed.
  • the power level applied to the ultrasonic knife transducer is adjusted to control the current output value of the ultrasonic knife, and the current The value is adjusted to a larger fourth current range, so as to ensure a larger power level, so that the ultrasonic blade can be heated up on the basis of maintaining the fourth temperature change rate and kept in the fourth temperature range, so as to realize blood vessel Quickly dry and set and cut.
  • the fourth temperature range does not exceed 300°C, and may be 200°C to 300°C, and the fourth temperature range corresponds to the blood vessel drying and cutting temperature range.
  • control process is only a specific implementation of the blood vessel shearing process according to the temperature distribution function model, and the control process can also be combined into one or divided into multiple control processes, all within the scope of the present invention.
  • a temperature change curve of blood vessel shearing according to the above process is shown in Figure 6, and the temperature is the maximum temperature estimated by the neural network model at a specific region of the knife tip.
  • the purpose is to adjust the power level up and down in real time according to the real-time temperature change rate in the three temperature ranges to maintain the target temperature change rate. Time to increase the current level.
  • the temperature rises rapidly, and reach the temperature threshold T1 at time t1; then adjust the output power level with the second current range, and reach the temperature threshold T2 at time t2; then adjust the output power with the third current range At the time t3, the temperature threshold T3 is reached, and the blood vessel sealing process is completed at this time; finally, the output power level is adjusted at the fourth current level to complete the blood vessel drying, coagulation and incision process.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Heart & Thoracic Surgery (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Veterinary Medicine (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Dentistry (AREA)
  • Mechanical Engineering (AREA)
  • Surgical Instruments (AREA)

Abstract

一种基于智能温度感知进行血管密闭及切开的超声软组织切割止血手术方法和系统。该系统包括发生器、换能器（11）和超声刀头，发生器在工作时实时收集手术器械的反馈参数，然后通过温度分布函数模型根据这些反馈参数和器械特征参数预估手术部位的实时温度，发生器根据第一自适应能量控制算法来控制血管手术部位的温度位于第一温度范围来完成血管密闭过程，然后根据第二自适应能量控制算法来控制血管的温度位于第二温度范围来完成血管干燥凝固和切开过程，精准可靠。

Description

基于智能温度感知的超声刀血管自适应剪切方法及系统 技术领域
本发明涉及医疗器械领域，尤其涉及一种超声手术刀的控制方法及系统，特别为一种基于智能温度感知的超声刀血管自适应剪切方法及系统、及设置有该系统的发生器、超声刀外科器械。
背景技术
软组织超声切割止血手术系统(简称超声刀系统)，是指将通过压电转换器(通过能量发生器将电能传递至压电转换器，由压电转换器将电能转换为机械能)获得的超声振动进一步放大，并由超声刀杆将放大后的超声振动用于对软组织的切割和凝闭的器械。临床用这种器械可在较低温度和较少出血的情况下实现病灶切除，并能确保最小的组织侧向热损伤。随着微创外科手术的普及，超声手术刀已经成为一种常规手术器械。
超声刀系统主要由发生器、换能器和超声刀杆组成，如图1所示，超声刀的换能器11和超声刀外壳12配接在一起，套管13位于超声刀外壳12的远端，位于最远端的超声刀杆14在套管13内部与换能器11耦接在一起，换能器11通过线缆15与发生器(未示出)连接。发生器中超声频率的电流传导至换能器，换能器将电能转化为前后振动的机械能，通过超声刀杆的传递和放大使超声刀杆末端(又称超声刀头)以一定频率(例如55.6kHz)振动，摩擦产生的热量导致与刀尖接触的组织细胞内水汽化，蛋白质氢键断裂，细胞崩解重新融合，组织凝固后被切开。
在闭合血管时，刀尖与组织蛋白接触，通过机械振动产生热量，导致组织内胶原蛋白变性，在刀尖钳口压力作用下上下两侧血管壁融合在一起，并在高温下干燥凝固形成一个坚固的闭合区域达到止血目的。一 般来讲，控制合适的温度范围可以将血管切割过程分为血管密闭和切开两个阶段，先控制输出相对较低功率水平让血管处于合适的温度范围保证血管能够较好的融合而不被切开，研究表明当血管温度处于110℃～180℃时可以完成最佳的熔合效果，继而提高输出功率水平控制血管处于200℃以上的高温来实现血管的快速干燥凝固和切开过程。鉴于此，有必要设计一种能智能控制超声刀杆温度及换能器功率水平的自适应剪切方法。
发明内容
本发明为了解决上述技术问题，提供了一种基于智能温度感知的超声刀血管自适应剪切方法及系统、及设置有该系统的发生器、超声刀外科器械。
为解决以上技术问题，本发明的技术方案为：
一种基于智能温度感知的超声刀血管自适应剪切方法，包括如下步骤，
S1、根据温度分布函数模型预估超声刀杆实时温度T est；
S2、判断所述实时温度T est所处温度范围；
S3、根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
优选的，所述温度分布函数模型为神经网络算法模型，包括前馈神经网络、记忆神经网络、注意力神经网络的一种或多种算法模型组合，模型训练方法为监督学习、半监督学习、无监督学习和强化学习的一种或多种组合。
优选的，所述模型训练方法具体为从训练集中提取输入特征，输入至所述神经网络算法模型中计算每个神经元的中间值和梯度值，模型的 损失函数可以为均方误差MSE或者平均绝对误差MAE，并利用梯度下降法进行权重更新，重复以上过程直到模型达到预定的停止条件，达到停止条件后停止训练并保存模型。
优选的，所述温度分布函数模型由层和相应的神经元及权重构成，权重参数和应用程序保存在发生器内存中，内存为Flash、EEPROM或者其他非易失存储设备，应用程序在处理器中运行，所述处理器或为存在于所述发生器中的ARM、DSP、FPGA、CPU、GPU或者ASIC芯片，或为通过网络连接的远程服务器。
优选的，所述步骤S1中，“根据温度分布函数模型预估超声刀杆实时温度”具体包括，向所述温度分布函数模型输入特征参数，所述特征参数包括工作反馈参数，物理结构特征参数，环境参数的一种或多种组合。
优选的，所述工作反馈参数包括实时电压U、实时电流I、功率P、阻抗R、实时谐振频率f、实时电压电流相位差θ的一种或几种参数；所述物理结构特征参数包括超声刀刀杆材料、刀杆长度的一种或几种参数；所述环境参数包括环境温度、环境湿度的一种或几种参数。
优选的，所述步骤S2中，“判断实时温度所处温度范围”具体包括，
预设三个温度阈值，从低到高分别为第一温度阈值T 1、第二温度阈值T 2、第三温度阈值T 3；
预设温度范围，低于所述第一温度阈值T 1为第一温度范围，所述第一温度阈值T 1和第二温度阈值T 2之间为第二温度范围，所述第二温度阈值T 2和第三温度阈值T 3之间为第三温度范围；
确定实时温度T est所处温度范围。
优选的，所述步骤S3中，当判断得到所述实时温度T est所处第一温 度范围时，在第一电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第一温度变化速率的基础上达到第二温度阈值T 2；当判断得到所述实时温度T est所处第二温度范围时，在第二电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第二温度变化速率的基础上达到第三温度阈值T 3；当判断得到所述实时温度T est所处第三温度范围时，在第三电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀保持第三温度变化速率，持续时间t1。
优选的，所述第一电流值、第二电流值、第三电流值为一个定值或一个数值范围；所述第一电流输出值大于所述第二电流输出值，所述第二电流输出值大于所述第三电流输出值。
优选的，所述第一温度变化速率、第二温度变化速率、第三温度变化速率均为0～50℃/s之内，且所述第一温度变化速率最大。
优选的，所述超声刀杆在保持第三温度变化速率的基础上升温不超过200℃，所述第三温度范围对应血管的最适宜闭合温度范围。
优选的，当超声刀杆在保持第三温度变化速率的基础上升温一段时间t1后，调节施加到超声刀换能器的功率水平以控制超声刀的电流输出值，使超声刀杆在保持第四温度变化速率的基础上升温并保持在第四温度范围内。
优选的，所述第四温度范围不超过300℃，优选为200℃～300℃，所述第四温度范围对应于血管干燥和切割温度范围。
本发明还揭示了一种基于智能温度感知的超声刀血管自适应剪切系统，包括：
实时温度预估单元，用于根据温度分布函数模型预估超声刀杆实时温度T est；
处理单元，用于判断所述实时温度T est所处温度范围；
调节单元，用于根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
本发明还揭示了一种基于智能温度感知的超声刀血管自适应剪切控制的发生器，包括：
控制电路，所述控制电路耦接到存储器，所述控制电路被配置为能够：
根据温度分布函数模型预估超声刀杆实时温度T est；
判断所述实时温度T est所处温度范围；
根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
本发明还揭示了一种基于智能温度感知的超声刀血管自适应剪切控制的超声刀外科器械，包括：
超声机电系统，所述超声机电系统包括经由超声波导联接到超声刀的超声换能器；以及
发生器，所述发生器被配置为向所述超声换能器供应功率，其中所述发生器包括控制电路，所述控制电路被配置为能够：
根据温度分布函数模型预估超声刀杆实时温度T est；
判断所述实时温度T est所处温度范围；
根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
本发明的有益效果主要体现在：超声刀杆工作时刀杆实际温度为沿着刀杆的一维空间分布，其上温度分布由超声刀杆实时工作反馈参数、物理结构特征参数以及周围环境参数集合决定，每个温度分布对应于温 度分布函数的一个解，利用机器学习算法可以逼近该函数；超声刀杆工作时根据其实时谐振频率、电压、电流、阻抗、功率及外形和环境等特征参数，输入机器学习算法模型就可以估计出超声刀刀杆的实时温度分布，进而根据估计的温度进行功率控制，准确有效。将实时特征参数集输入至少一种机器学习算法模型可以进行超声刀刀杆包括刀尖温度估计；根据第一能量控制算法调整输出功率水平保持目标温度控制在第一温度范围内，完成血管密闭过程；根据第二能量控制算法调整输出功率水平保持目标温度控制在第二温度范围内，从而完成血管干燥凝固和切开过程。
附图说明
图1是现有技术中超声刀的结构配置示意图；
图2是本发明基于温度分布函数模型预估超声刀杆实时温度的流程图；
图3是本发明基于智能温度感知的超声刀血管自适应剪切方法的流程示意图；
图4是本发明基于智能温度感知的超声刀的第一自适应能量控制算法的流程图；
图5是本发明基于智能温度感知的超声刀的第二自适应能量控制算法的流程图；
图6是本发明基于智能温度感知的超声刀血管自适应剪切中预估目标温度变化的一种实施例的曲线图。
具体实施方式
以下将结合附图所示的具体实施方式对本发明进行详细描述。但这些实施方式并不限于本发明，本领域的普通技术人员根据这些实施方式 所做出的结构、方法、或功能上的变换均包含在本发明的保护范围内。
超声刀系统在工作过程中利用锁相算法改变换能器的工作频率使换能器工作在最大工作效率状态，也就是谐振状态。在谐振状态下，声波在超声刀刀杆上传播必须满足驻波条件，假设超声刀刀杆长度为L，声波波长为λ，声速为v，谐振频率为f，则在谐振状态下必须满足以下工作条件：
Figure PCTCN2022087010-appb-000001
其中n为正整数。
假设声波周期为τ，则满足以下公式：
Figure PCTCN2022087010-appb-000002
可以得到：
Figure PCTCN2022087010-appb-000003
实际工作中热量沿着超声刀刀杆的设置方向扩散，因此在超声刀刀杆不同位置温度可能不同，不同位置温度t表示为：
t＝T(l)(4)
T(l)为刀杆上的一个位置温度分布函数，l的范围为0～L，超声刀杆刀尖一侧顶点位置为坐标原点。
温度可以影响刀杆的杨氏模量，最终影响声波速度，刀杆上不同位置的声速v可以表示为温度的函数：
v(l)＝V(T(l))(5)
公式(1)可以表示为：
Figure PCTCN2022087010-appb-000004
公式(6)可以表示为：
Figure PCTCN2022087010-appb-000005
公式(7)为一个积分方程，对于确定时间点，f为确定的谐振频率，温度T(l)受电压、电流、功率、阻抗、刀杆形状、环境参数等参数影响。在n、f和L确定的情况下积分方程的温度分布函数T(l)可能有无穷多个解，对于不同的刀杆，会有更多种不同的温度分布。
鉴于此，本发明揭示了一种机器学习算法模型，具体为神经网络算法模型，人工神经网络算法模型是一种受人脑神经系统启发而构造的数学模型，与生物神经元类似，由多个节点(人工神经元)互相连接而成，可以用来对数据之间的复杂关系进行建模。不同节点之间的连接被赋予不同的权重，每个权重代表一个节点对另外一个节点的影响大小。每个节点代表一种特定函数，来自其他节点的信息经过其相应的权重综合计算，输入到一个激活函数中并得到一个新的活性值。激活函数用来引入非线性元素，增加神经网络的表达能力，常用的激活函数有Sigmoid，Tanh，ReLU等。
从系统观点来看，人工神经元是由大量神经元通过极其丰富和完善的连接而构成的自适应非线性动态系统。目前最常用的神经网络学习算法为反向传播算法，优化方法为梯度下降算法。理论上，一个两层的神经网络就可以逼近任意的函数，增加网络层数可以让神经网络在相同的神经元数量下具有更强的表示能力。目前比较常用的神经网络模型有前馈神经网络模型、记忆神经网络模型及注意力神经网络模型等：多层感知机(Multilayer Perceptron，MLP)和卷积神经网络(Convolutional Neural Network,CNN)为前馈神经网络模型；循环神经网络(Recurrent Neural Network，RNN)为记忆神经网络模型，常用的RNN模型包括门控神经单元(Gate Recurrent Unit，GRU)和长短期记忆神经网络(Long  Short-Term Memory,LSTM)；注意力神经网络模型包括Transformer等。
记忆神经网络模型在前馈神经网络基础上增加了记忆能力，常用来处理时序数据，常用的记忆神经网络包括RNN、GRU、LSTM等。GRU和LSTM具有长期的记忆能力，能够处理长时间序列。
本发明温度分布函数模型可以基于机器学习算法模型包括神经网络算法模型中的一种或者多种算法模型组合。输入特征包括工作反馈参数，物理结构特征参数，环境参数的一种或多种组合。所述工作反馈参数包括但不限于实时电压U、实时电流I、功率P、阻抗R、实时谐振频率f；所述物理结构特征参数包括但不限于超声刀杆材料、长度；所述环境参数包括但不限于环境温度、环境湿度。
输入特征越完备，神经网络模型的逼近能力越强。本发明模型中，电压U和电流I由发生器实时采样得到，实时功率P和阻抗R可以由以下公式计算得到：
P＝U×I(15)
Figure PCTCN2022087010-appb-000006
实时频率f由以下公式计算得到：
f＝k×(θ-θ 0)(17)
其中，k由实时电压U和电流I的一个函数关系确定：
k＝K(U,I)(18)
θ为实时电压电流相位差，计算公式为：
θ＝θ U-θ I(19)
电压相位θ U和电流相位θ I由发生器实时采样得到，θ 0为一个常数。
电压电流传感器采样频率可以为实际信号频率的64倍或者128倍等， 输出电压U、输出电流I，谐振频率f、频率一阶导数df、阻抗R和相位θ、功率P等参数由采样值经过FFT等数学运算得到。超声刀刀杆材料、长度等物理结构特征参数可以保存在超声刀或者发生器的存储芯片中，发生器直接读取相应的存储芯片可以得到这些特征参数，环境参数可以通过传感器进行实时测量得到。
本发明模型训练方法可以为监督学习、半监督学习、无监督学习和强化学习等方式。监督学习需要采集模型的所有输入特征信息以及训练标签，可以以一定的时间间隔采集，时间间隔可以为1ms或者10ms，并测量实时温度作为监督训练标签，实时剪切温度点可以采用嵌入或者外部的温度传感器或者红外测温仪来测量得到，采集大量标记数据得到作为训练数据集S。
模型监督学习实现的一种神经网络模型训练过程可以为：从训练数据集S中取输入特征，并输入神经网络模型计算每个神经元的中间值和梯度值，模型的损失函数可以为均方误差MSE或者平均绝对误差MAE，并利用梯度下降法进行权重更新，重复以上过程直到模型达到预定的停止条件，比如预测精度达到目标值或者损失不再减小，达到停止条件后停止训练并保存模型，这个模型即可以表示所有目标超声刀工作时刀杆包括刀尖上的温度分布的函数。
训练好的模型由各个层和相应的神经元及权重构成，权重参数和应用算法程序保存在发生器内存中，内存可以为Flash、EEPROM或者其他非易失存储设备中，应用程序在处理器中运行，处理器可以为存在于发生器中的ARM、DSP、FPGA、CPU、GPU或者ASIC芯片，也可以为通过网络连接的远程服务器。
本发明温度分布函数模型预估温度方法如图2所示，将实时超声刀 特征参数集X输入模型，模型根据输入的特征集合可以找到最可能的刀杆温度分布，温度T est可以由在该温度分布中得到，T est即为预估的超声刀杆实时温度。
如图3所示，本发明揭示了一种基于智能温度感知的超声刀血管自适应剪切方法，包括如下步骤：
S1、根据温度分布函数模型预估超声刀杆实时温度T est；
S2、判断所述实时温度T est所处温度范围；
S3、根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
结合图4和图5揭示的一种实施例，本发明能基于预估的实时温度控制超声刀换能器的输出功率水平来实现血管的密闭和切开过程。
首先发生器根据第一能量控制算法来控制血管手术部位的温度位于第一温度范围来完成血管密闭过程，第一温度范围可以为0℃～200℃内的一个合适温度范围，第一能量控制算法一种实现方式如图4所示，通过温度估计模型预估实时温度值，根据该温度值控制输出能量。
具体来讲，首先当判断得到所述实时温度T est所处第一温度范围时，在第一电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第一温度变化速率的基础上达到第二温度阈值T 2，第一电流范围可以对应于较大电流值，实现较大功率水平输出，用来达到快速去除血管表层水分，并快速升温的目的。
当判断得到所述实时温度T est所处第二温度范围时，即达到第一温度阈值T 1且低于第二温度阈值T 2时，可以在第二电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第二温度变化速率的基础上达到第三温度阈值T 3，从而逐步提高血管温度值，使血管组织内 胶原蛋白逐步变性。
当判断得到所述实时温度T est所处第三温度范围时，即达到第二温度阈值T 2且低于第三温度阈值T 3时，可以在第三电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀保持第三温度变化速率，持续时间t1，从而实现两侧血管壁完全熔合。
以上温度范围可以为0～200℃内的合适温度范围，温度变化速率可以为0～50℃/s内的合适速率，且所述第一温度变化速率最大。所述超声刀杆在保持第三温度变化速率的基础上升温不超过200℃，所述第三温度范围对应血管的最适宜闭合温度范围。所述第一电流值、第二电流值、第三电流值为一个定值或一个数值范围；所述第一电流输出值大于所述第二电流输出值，所述第二电流输出值大于所述第三电流输出值。
血管密闭完成后采用第二能量控制算法实现切开过程，一种控制过程如图5所示。当估计目标温度达到密闭结束温度阈值或者超出预定时间阈值后可以判断血管密闭完成。在确认血管密闭完成后，即当超声刀杆在保持第三温度变化速率的基础上升温一段时间t1后，调节施加到超声刀换能器的功率水平以控制超声刀的电流输出值，将电流值调整到一个较大的第四电流范围，从而保证达到一个较大的功率水平，使超声刀杆在保持第四温度变化速率的基础上升温并保持在第四温度范围内，从而实现血管的快速干燥凝固并切开。所述第四温度范围不超过300℃，可以为200℃～300℃，所述第四温度范围对应于血管干燥和切割温度范围。
以上控制过程只是根据温度分布函数模型实现血管剪切过程的一种具体实施方式，也可以将控制过程合为一个或者分成多个控制过程，均在本发明范围内。
根据上述过程进行血管剪切的一条温度变化曲线如图6所示，该温度为神经网络模型估计的位于刀尖特定区域的最大温度。简单来说目的在于在三个温度范围内均需要根据实时温度变化速率实时自适应上下调整功率水平，来维持目标温度变化速率，温升速率过大的时候降低电流大小，温升速率过小的时候提升电流大小。首先以较大功率水平开始密闭过程，温度快速上升，在时间t1达到温度阈值T1；然后以第二电流范围调整输出功率水平，在时间t2达到温度阈值T2；然后以第三电流范围调整输出功率水平，在时间t3达到温度阈值T3，此时完成血管密闭过程；最后以第四电流水平调整输出功率水平，完成血管干燥凝固和切开过程。
以上仅是本发明的优选实施方式，应当指出的是，上述优选实施方式不应视为对本发明的限制，本发明的保护范围应当以权利要求所限定的范围为准。对于本技术领域的普通技术人员来说，在不脱离本发明的精神和范围内，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (16)

  1. 一种基于智能温度感知的超声刀血管自适应剪切方法，其特征在于，包括如下步骤，
    S1、根据温度分布函数模型预估超声刀杆实时温度T est；
    S2、判断所述实时温度T est所处温度范围；
    S3、根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
  2. 根据权利要求1所述的方法，其特征在于，所述温度分布函数模型为神经网络算法模型，包括前馈神经网络、记忆神经网络、注意力神经网络的一种或多种算法模型组合，模型训练方法为监督学习、半监督学习、无监督学习和强化学习的一种或多种组合。
  3. 根据权利要求2所述的方法，其特征在于，所述模型训练方法具体为从训练集中提取输入特征，输入至所述神经网络算法模型中计算每个神经元的中间值和梯度值，模型的损失函数可以为均方误差MSE或者平均绝对误差MAE，并利用梯度下降法进行权重更新，重复以上过程直到模型达到预定的停止条件，达到停止条件后停止训练并保存模型。
  4. 根据权利要求3所述的方法，其特征在于，所述温度分布函数模型由层和相应的神经元及权重构成，权重参数和应用程序保存在发生器内存中，内存为Flash、EEPROM或者其他非易失存储设备，应用程序在处理器中运行，所述处理器或为存在于所述发生器中的ARM、DSP、FPGA、CPU、GPU或者ASIC芯片，或为通过网络连接的远程服务器。
  5. 根据权利要求1所述的方法，其特征在于，所述步骤S1中，“根据温度分布函数模型预估超声刀杆实时温度”具体包括，向所述温度分布函数模型输入特征参数，所述特征参数包括工作反馈参数，物理结构特征参数，环境参数的一种或多种组合。
  6. 根据权利要求5所述的方法，其特征在于，所述工作反馈参数包括实时电压U、实时电流I、功率P、阻抗R、实时谐振频率f、实时电压电流相位差θ的一种或几种参数；所述物理结构特征参数包括超声刀刀杆材料、刀杆长度的一种或几种参数；所述环境参数包括环境温度、环境湿度的一种或几种参数。
  7. 根据权利要求1所述的方法，其特征在于，所述步骤S2中，“判断实时温度所处温度范围”具体包括，
    预设三个温度阈值，从低到高分别为第一温度阈值T 1、第二温度阈值T 2、第三温度阈值T 3；
    预设温度范围，低于所述第一温度阈值T 1为第一温度范围，所述第一温度阈值T 1和第二温度阈值T 2之间为第二温度范围，所述第二温度阈值T 2和第三温度阈值T 3之间为第三温度范围；
    确定实时温度T est所处温度范围。
  8. 根据权利要求7所述的方法，其特征在于，所述步骤S3中，当判断得到所述实时温度T est所处第一温度范围时，在第一电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第一温度变化速率的基础上达到第二温度阈值T 2；当判断得到所述实时温度T est所处第二温度范围时，在第二电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀杆在保持第二温度变化速率的基础上达到第三温度阈值T 3；当判断得到所述实时温度T est所处第三温度范围时，在第三电流值输出范围内自适应调整超声刀换能器的功率水平使超声刀保持第三温度变化速率，持续时间t1。
  9. 根据权利要求8所述的方法，其特征在于，所述第一电流值、第二电流值、第三电流值为一个定值或一个数值范围；所述第一电流输出 值大于所述第二电流输出值，所述第二电流输出值大于所述第三电流输出值。
  10. 根据权利要求9所述的方法，其特征在于，所述第一、第二、第三温度变化速率均为0～50℃/s之内，且所述第一温度变化速率最大。
  11. 根据权利要求10所述的方法，其特征在于，所述超声刀杆在保持第三温度变化速率的基础上升温不超过200℃，所述第三温度范围对应血管的最适宜闭合温度范围。
  12. 根据权利要求11所述的方法，其特征在于，当超声刀杆在保持第三温度变化速率的基础上升温一段时间t1后，调节施加到超声刀换能器的功率水平以控制超声刀的电流输出值，使超声刀杆在保持第四温度变化速率的基础上升温并保持在第四温度范围内。
  13. 根据权利要求12所述的方法，其特征在于，所述第四温度范围不超过300℃，所述第四温度范围对应于血管干燥和切割温度范围。
  14. 一种基于智能温度感知的超声刀血管自适应剪切系统，其特征在于，包括
    实时温度预估单元，用于根据温度分布函数模型预估超声刀杆实时温度T est；
    处理单元，用于判断所述实时温度T est所处温度范围；
    调节单元，用于根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
  15. 一种基于智能温度感知的超声刀血管自适应剪切控制的发生器，其特征在于，包括
    控制电路，所述控制电路耦接到存储器，所述控制电路被配置为能够：
    根据温度分布函数模型预估超声刀杆实时温度T est；
    判断所述实时温度T est所处温度范围；
    根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
  16. 一种基于智能温度感知的超声刀血管自适应剪切控制的超声刀外科器械，其特征在于，包括
    超声机电系统，所述超声机电系统包括经由超声波导联接到超声刀的超声换能器；以及
    发生器，所述发生器被配置为向所述超声换能器供应功率，其中所述发生器包括控制电路，所述控制电路被配置为能够：
    根据温度分布函数模型预估超声刀杆实时温度T est；
    判断所述实时温度T est所处温度范围；
    根据判断结果，调节施加到超声刀换能器的功率水平以控制超声刀电流输出，进而控制温度变化速率。
PCT/CN2022/087010 2021-08-30 2022-04-15 基于智能温度感知的超声刀血管自适应剪切方法及系统 WO2023029495A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111004180.7A CN113729864B (zh) 2021-08-30 2021-08-30 基于智能温度感知的超声刀血管自适应剪切方法及系统
CN202111004180.7 2021-08-30

Publications (1)

Publication Number Publication Date
WO2023029495A1 true WO2023029495A1 (zh) 2023-03-09

Family

ID=78733831

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/087010 WO2023029495A1 (zh) 2021-08-30 2022-04-15 基于智能温度感知的超声刀血管自适应剪切方法及系统

Country Status (2)

Country Link
CN (1) CN113729864B (zh)
WO (1) WO2023029495A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113729864B (zh) * 2021-08-30 2023-08-29 以诺康医疗科技（苏州）有限公司 基于智能温度感知的超声刀血管自适应剪切方法及系统
CN113712630B (zh) * 2021-08-30 2023-10-17 以诺康医疗科技（苏州）有限公司 一种基于剪切结束判断模型的控制方法和系统
CN113722994B (zh) * 2021-08-30 2023-11-07 以诺康医疗科技（苏州）有限公司 基于温度分布函数模型的超声刀杆温度控制方法及系统
CN115670591B (zh) * 2023-01-03 2023-06-09 上海逸思医疗科技股份有限公司 超声刀系统的能量输出控制方法、装置和设备、介质
CN116585627B (zh) * 2023-07-14 2023-10-10 以诺康医疗科技（苏州）有限公司 超声刀杆温度控制方法、系统、发生器及超声医疗器械

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4832022A (en) * 1986-05-26 1989-05-23 Tomsky Gosudarstvenny Universitet Im. Kuibysheva Cryogenic ultrasonic scalpel
CN107847262A (zh) * 2015-06-30 2018-03-27 伊西康有限责任公司 利用基于组织参数采用同时能量模态的用户自适应技术的外科系统
CN108697461A (zh) * 2016-01-15 2018-10-23 伊西康有限责任公司 基于按钮位移、强度或局部组织表征选择性施加能量的模块化电池供电手持式外科器械
US20190201042A1 (en) * 2017-12-28 2019-07-04 Ethicon Llc Determining the state of an ultrasonic electromechanical system according to frequency shift
CN113722994A (zh) * 2021-08-30 2021-11-30 以诺康医疗科技（苏州）有限公司 基于温度分布函数模型的超声刀杆温度控制方法及系统
CN113743007A (zh) * 2021-08-30 2021-12-03 以诺康医疗科技（苏州）有限公司 基于智能温度感知的超声刀垫片保护方法及系统
CN113729864A (zh) * 2021-08-30 2021-12-03 以诺康医疗科技（苏州）有限公司 基于智能温度感知的超声刀血管自适应剪切方法及系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7137980B2 (en) * 1998-10-23 2006-11-21 Sherwood Services Ag Method and system for controlling output of RF medical generator
US7901400B2 (en) * 1998-10-23 2011-03-08 Covidien Ag Method and system for controlling output of RF medical generator
US9498277B2 (en) * 2007-02-01 2016-11-22 Conmed Corporation Apparatus and method for rapid reliable electrothermal tissue fusion and simultaneous cutting
CN107106232B (zh) * 2015-07-24 2019-10-08 奥林巴斯株式会社 能量处置系统、能量控制装置以及能量处置器具
WO2018025374A1 (ja) * 2016-08-04 2018-02-08 オリンパス株式会社 制御装置
WO2019003346A1 (ja) * 2017-06-28 2019-01-03 オリンパス株式会社 手術システムのハンドピースの製造方法、手術システムのハンドピースの特性の設定方法、手術システムのハンドピース及び手術システム
US11707293B2 (en) * 2018-03-08 2023-07-25 Cilag Gmbh International Ultrasonic sealing algorithm with temperature control
EP3536254B1 (en) * 2018-03-08 2024-01-10 Ethicon LLC Ultrasonic sealing algorithm with temperature control
US20230015369A1 (en) * 2020-01-16 2023-01-19 Covidien Lp System and method for controlling an ultrasonic surgical system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4832022A (en) * 1986-05-26 1989-05-23 Tomsky Gosudarstvenny Universitet Im. Kuibysheva Cryogenic ultrasonic scalpel
CN107847262A (zh) * 2015-06-30 2018-03-27 伊西康有限责任公司 利用基于组织参数采用同时能量模态的用户自适应技术的外科系统
CN108697461A (zh) * 2016-01-15 2018-10-23 伊西康有限责任公司 基于按钮位移、强度或局部组织表征选择性施加能量的模块化电池供电手持式外科器械
US20190201042A1 (en) * 2017-12-28 2019-07-04 Ethicon Llc Determining the state of an ultrasonic electromechanical system according to frequency shift
CN113722994A (zh) * 2021-08-30 2021-11-30 以诺康医疗科技（苏州）有限公司 基于温度分布函数模型的超声刀杆温度控制方法及系统
CN113743007A (zh) * 2021-08-30 2021-12-03 以诺康医疗科技（苏州）有限公司 基于智能温度感知的超声刀垫片保护方法及系统
CN113729864A (zh) * 2021-08-30 2021-12-03 以诺康医疗科技（苏州）有限公司 基于智能温度感知的超声刀血管自适应剪切方法及系统

Also Published As

Publication number Publication date
CN113729864B (zh) 2023-08-29
CN113729864A (zh) 2021-12-03

Similar Documents

Publication Publication Date Title
WO2023029495A1 (zh) 基于智能温度感知的超声刀血管自适应剪切方法及系统
WO2023029496A1 (zh) 基于智能温度感知的超声刀垫片保护方法及系统
WO2023029494A1 (zh) 基于温度分布函数模型的超声刀杆温度控制方法及系统
WO2023029497A1 (zh) 一种基于剪切结束判断模型的超声刀控制方法和系统
US7250048B2 (en) Ablation system and method of use
JP7318006B2 (ja) 電気外科システムのエネルギー評価
KR102123783B1 (ko) 초음파 수술 기구용 스위치 배열체
KR102138543B1 (ko) 초음파 수술 기구용 회전 가능 전기 접속
CA2869890A1 (en) Devices and techniques for cutting and coagulating tissue
CA2869953A1 (en) Techniques for cutting and coagulating tissue for ultrasonic surgical instruments
BR112014025798B1 (pt) Aparelho
US20210100606A1 (en) Systems and methods for controlling delivery of electrosurgical energy
CN108685612A (zh) 向凝集仪器供能的发生器及其控制方法
US20230015369A1 (en) System and method for controlling an ultrasonic surgical system
US11399859B2 (en) Energy control device and treatment system
JP6214831B1 (ja) 処置システム及び制御装置
US20220265303A1 (en) Medical device and method for controlling the same including discriminating end-of-cut conditions based on temperature
US20220273332A1 (en) End-point detection method and medical device controller and treatment system with end-point detection, particularly for electrosurgery
Yao et al. Predicting damage characteristics of RF ablation targets based on SVR algorithm
CN118034397A (zh) 腔镜手术钳头用温度反馈控制方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22862641

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE