CN113768611B - Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning - Google Patents
Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning Download PDFInfo
- Publication number
- CN113768611B CN113768611B CN202111084117.9A CN202111084117A CN113768611B CN 113768611 B CN113768611 B CN 113768611B CN 202111084117 A CN202111084117 A CN 202111084117A CN 113768611 B CN113768611 B CN 113768611B
- Authority
- CN
- China
- Prior art keywords
- temperature
- tissue
- radio frequency
- ultrasonic
- signals
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
- A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/006—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using measurement of the effect of a material on microwaves or longer electromagnetic waves, e.g. measuring temperature via microwaves emitted by the object
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/22—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using measurement of acoustic effects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
- A61B2018/00571—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body for achieving a particular surgical effect
- A61B2018/00577—Ablation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
- A61B2018/00636—Sensing and controlling the application of energy
- A61B2018/00773—Sensed parameters
- A61B2018/00791—Temperature
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Electromagnetism (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Acoustics & Sound (AREA)
- Otolaryngology (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Plasma & Fusion (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a method for measuring temperature of tissues by combining ultrasonic radio frequency signals with machine learning, which adopts a computer three-dimensional simulation technology to accurately select a region of interest, reduces the influence of ultrasonic echo signals, acoustic shielding effect and thermo-acoustic transmission effect in a mode of measuring the temperature of a plurality of regions of interest in real time, and ensures the accuracy of data by adopting a real-time temperature measuring method. And the temperature measurement model is made by combining the results of in-vitro and in-vivo experiments, so that a basis is provided for real-time temperature measurement on a human body in the future, and meanwhile, a temperature image is built by combining machine learning with an image radio frequency signal to perform the temperature measurement model, so that more image visual information is provided. And the multi-map layer is overlapped and displayed and the display mode of the key temperature point isotherm identification is convenient for doctors to observe and monitor the lesion suppression or the temperature condition of the region of interest in real time during ablation.
Description
Technical Field
The invention relates to medical ultrasonic radio frequency signal processing and extraction of human body temperature information expressed in medical ultrasonic radio frequency signals, in particular to a method for extracting tissue temperature from medical ultrasonic radio frequency signals by using a machine learning algorithm.
Background
Focal thermal ablation under ultrasound device guidance is a minimally invasive or non-invasive physical therapy technique for localized tumors. The common treatment means at present mainly comprise radio frequency ablation, microwave ablation, high-intensity focused ultrasound, laser ablation and the like. And monitoring the temperature of the target tissue and its surrounding tissue during ablation is important. At present, accurate ablation of a cancer area is required, not only is accurate needle insertion position required, but also a skilled doctor needs to judge whether to completely ablate a tumor area or excessively ablate healthy tissues around the lesion through a gasification area of the ablation area during ablation, so that temperature control in the treatment process is critical.
At present, the domestic common tissue temperature measurement mainly takes intervention type, and the human body is monitored by entering the temperature measuring optical fiber or the temperature measuring needle, so that the problem is that the temperature of the single point position of the tissue area can be measured, and the temperature of the whole human body target tissue area can not be monitored. The non-invasive ultrasonic nondestructive temperature measurement method comprises an ultrasonic echo frequency shift nondestructive temperature measurement method, an ultrasonic echo time shift method and an ultrasonic scattering echo power spectrum, and the algorithms used in the method are all traditional signal processing methods and are linear correlations with temperature through analysis. And the temperature of the focus area is increased during thermal ablation to generate a thermoacoustic lens effect and an acoustic shielding phenomenon, so that an ultrasonic echo signal behind a treatment area is changed.
Disclosure of Invention
Aiming at the defects and shortcomings in the prior art, the invention aims to provide a method for measuring the temperature of tissues by combining ultrasonic radio frequency signals with machine learning. The invention adopts a machine learning mode to analyze the ultrasonic radio frequency signal content; constructing an interested region by combining a three-dimensional simulation technology to accurately distribute needles, acquiring ultrasonic radio frequency signals in real time according to needle distribution conditions, acquiring accurate temperature information, and reducing the influence of ultrasonic echo signals, sound shielding effect, thermoacoustic lens effect and the like; and extracting the characteristics of the temperature difference and the ultrasonic radio frequency data, analyzing the temperature characteristics in different areas, constructing a machine learning model, and simultaneously using an in-vitro experiment to further optimize the model and establishing the correlation between the image and the temperature.
The technical scheme of the invention is as follows:
the method for measuring the temperature of the tissue by combining ultrasonic radio frequency signals with machine learning is characterized by comprising the following steps:
(1) The three-dimensional concept of an ablation area is obtained through multi-section scanning, and a three-dimensional model of the ablation area is built according to different mathematical algorithm models to arrange an ablation needle;
(2) Setting multi-path temperature measuring needles on the isolated tissue at different distances or different angles relative to the position of the ablation needle;
(3) Obtaining temperature T of non-ablated ex-vivo tissue 0 And at this time the radio frequency signal RF 0 The acquisition frequency is N frames/second; the in-vitro tissue is ablated for T seconds, and the temperature is obtained to be T j Radio frequency signal RF j At this time, the temperature of the isolated tissue changes (T j -T 0 ) The radio frequency signal at each frame is reflectedIn (a) and (b);
(4) Simulating according to the data of the temperature measuring needle of each passage and the Pennes approximate biological heat equation to obtain tissue simulation temperatures in different areas at different times; according to the sampling format of the radio frequency signals, each frame of radio frequency signal data can be converted into a radio frequency signal matrix of p x q, wherein p is the number of scanning lines, and q is the number of sampling points;
(5) Obtaining the tissue temperature of each frame in different areas according to the simulation in the step (4), namely, the tissue simulation temperature of different areas in different time, dividing the tissue simulation temperature into a plurality of sections according to the temperature range, finding out radio frequency signal matrixes of the corresponding sections in the corresponding frames, and requiring the size of each matrix to be consistent;
(6) Inputting the data of the radio frequency signal matrix in the step (5) and the corresponding temperature interval into a machine learning model for training;
(7) And (3) acquiring radio frequency signals of the tissue to be detected, inputting the radio frequency signals into the model trained in the step (6), and finally obtaining temperature information of the tissue to be detected.
Further, the step (7) is to make a temperature map layer according to different temperature information, and display the temperature map layer on the whole area in a superposition way; and marking different temperature areas with different colors, and marking an isotherm area of a key temperature point for temperature prompt.
Further, the Pennes approximation biological heat equation:
wherein ρ is the density (kg/m) 3 ) C is the specific heat capacity (W/m 3 K), K is the thermal conductivity (W/mK), T (x, y, z, T) is the tissue temperature, Q blood For heat transfer generated during blood perfusion, Q met For heat generated by metabolism, Q e For energy change caused by water evaporation, Q absorb Absorbing power of laser, microwave or radio frequency for tissue.
Further, in the step (4), the arrangement of the radio frequency signal matrix conforms to the arrangement of the pixels of the ultrasonic imaging.
Further, the machine learning model includes a supervised model, an unsupervised model, or a probabilistic model.
An ultrasound device employing the method of using ultrasound radio frequency signals in combination with machine learning to temperature measure tissue as described in any of the above.
Further, the apparatus comprises: the ultrasonic device comprises an ultrasonic probe, an ultrasonic beam former, a pre-amplifier and filter, an A/D conversion module and a GPU.
Further, the ultrasonic probe transmits ultrasonic waves to the tissue to be detected and receives ultrasonic signals reflected by the tissue; the ultrasonic beam forming device comprises a transmitting part and a receiving part, and generates high-voltage pulse signals and echo signals required by exciting the ultrasonic probe; the received echo signals are sent to a pre-amplifier and a filter; the amplified and filtered signals are converted into digital signals by an A/D conversion module; and directly entering the GPU after being converted into the digital signal, and outputting the digital signal as a temperature value of the tissue to be detected. The invention has the following points:
key point one: and in the early stage, three-dimensional calculation is carried out to simulate a model of the interested part, and the arrangement of the needle arrangement strategy is carried out to realize accurate array arrangement.
Key point two: and the temperature model is trained by combining radio frequency data and Pennes biological heat equation with a machine learning method, so that the influence of ultrasonic echo signals and sound shielding effects is reduced.
Key points three: meanwhile, an in-vitro tissue is adopted for establishing and predicting a temperature model.
Key point four: the temperature map layer mode is used for carrying out overall image display and is provided with a key temperature point mark of an isotherm.
Compared with the prior art, the invention has the following advantages:
the invention adopts the computer three-dimensional simulation technology to accurately select the region of interest, and the influence of ultrasonic echo signals, sound shielding effect and thermo-acoustic transmission effect is reduced in a mode of measuring the temperature of a plurality of regions of interest (in multiple directions) in real time. The real-time temperature measurement method based on the in-vitro tissue is relatively accurate in constructing a temperature measurement model by combining machine learning with an image radio frequency signal. And the multi-image layer is overlapped and displayed and the display mode of the key temperature point isotherm mark provides more image visual information, so that a doctor can observe and monitor the temperature condition of a focus inhibition or region of interest in real time during ablation.
Drawings
FIG. 1 is a frame diagram of an ablation region using a regular prism calculation;
FIG. 2 shows the arrangement of the temperature probe for the in-vitro experiment in the second step;
FIG. 3 is a graph showing the temperature distribution profile and the thermal damage fraction obtained in the fourth step;
FIG. 4 is a flowchart of the machine learning model training steps.
Detailed Description
The invention is further described below with reference to the drawings and examples.
The method for measuring the temperature of the tissue by combining the ultrasonic radio frequency signals with the machine learning in the embodiment comprises the following steps:
step one: the three-dimensional concept of an ablation area is obtained by multi-section scanning, and a three-dimensional model of a target area is built according to different mathematical algorithm models according to actual conditions to perform needle arrangement (needle arrangement refers to the arrangement of ablation needles). This step is to select an ablation zone to deploy the ablation needle.
Such as regular prism calculations, regular polyhedron calculations, etc. Taking a regular prism calculation method as an example, a mathematical calculation model of a regular prism is taken as an example to describe and explain a computer three-dimensional needle distribution process, and the process shows that the area selection is relatively accurate when the model is built.
The formula can be used(wherein 2R is the range of an ablation area, 2R is the diameter of an ablation needle umbrella, n is the number of needle placement times), and the number of needle placement times can be reasonably selected according to the range of needle placement.
The needle arrangement mode is shown in fig. 1, and specifically comprises the following steps: 1) Scanning the maximum diameter of the ablation area; 2) Setting the shape of a regular prism according to the ablation range and solving n; 3) Dividing the maximum diameter into n-2 sectors, and respectively ablating each sector to complete the ablation of the prismatic surface; 4) Finding the maximum section perpendicular to the section, and supplementing one needle at the head and the tail of the regular prism treatment area to complete the whole ablation.
Step two: placing a plurality of access temperature measuring needles on an isolated tissue (such as isolated pig liver or beef liver) at different distances or different angles relative to the setting position of the ablation needle in the step (1). The situation is shown in fig. 2, wherein x1, x2, x3 and x4 are temperature measuring needles with different distances or different angles, and 01, 02, 03 and 04 are channels for real-time temperature measurement of the temperature measuring needles.
Step three: obtaining the temperature T of the in-vitro tissue under the condition of not ablating at room temperature 0 And at this time the radio frequency signal RF 0 The acquisition frequency is N frames/second;
the in-vitro tissue is ablated for T seconds, and the temperature is obtained to be T j Radio frequency signal RF j At this time, the temperature of the isolated tissue changes (T j -T 0 ) The radio frequency signal at each frame is reflectedIs a kind of medium.
Step four: and simulating heat transfer in the biological material according to a Pennes approximate biological heat equation (shown below) and the data of the temperature measuring needle of each passage, so as to obtain tissue simulation temperatures (simulation of temperature change) at different areas at different times.
Wherein ρ is the density (kg/m 3 ) C is the specific heat capacity (W/m 3 K), K is the thermal conductivity (W/mK), T (x, y, z, T) is the tissue temperature, Q blood For heat transfer generated during blood perfusion, Q met For heat generated by metabolism, Q e For energy change caused by water evaporation, Q absorb Absorbing power of laser, microwave or radio frequency for tissue. The calculation result is shown in fig. 3.
In addition, according to the sampling format of the radio frequency signals, the data of each frame of radio frequency signals can be converted into a matrix of p x q, wherein p is the number of scanning lines, q is the number of sampling points, and meanwhile, the arrangement of the matrix of the radio frequency signals also accords with the arrangement of the pixels of ultrasonic imaging.
Step five: according to the calculation in the fourth step, the tissue temperature under different regions of each frame (namely, the tissue simulation temperature under different regions of different time) can be obtained, the tissue temperature is divided into a plurality of sections according to the temperature range, and the radio frequency signal matrix of the corresponding section under the corresponding frame is found, wherein the size of each matrix is required to be consistent.
For example, all temperatures are divided into a plurality of intervals, such as interval 1 (20-40 degrees celsius), interval 2 (40-60 degrees celsius), interval 3 (60-90 degrees celsius), and interval 4 (90-150 degrees celsius); corresponding temperature intervals are corresponding to the radio frequency signal matrixes.
Step six: inputting the data of the radio frequency signal matrix in the fifth step and the corresponding temperature interval into a machine learning model for training, wherein the process is shown in fig. 4.
Wherein the machine learning model may be trained using a supervised model, an unsupervised model, and a probabilistic model. For example, training is performed using a variety of algorithms such as artificial neural networks, support vector machines, hierarchical clustering, EM algorithms, K-Means, and the like.
Step seven: and (3) acquiring radio frequency signals of the living tissue to be detected, inputting the radio frequency signals into the model trained in the step (six), and finally obtaining temperature information of the tissue to be detected.
Preferably, a temperature map layer is made according to different temperature information, the temperature map layer is displayed on the whole area in a superimposed mode, different temperature areas are marked with different colors, and an isotherm area marked with key temperature points is used for temperature prompt.
Fig. 5 shows a specific structure diagram of the temperature interval classification model in the ultrasonic equipment.
The 001 ultrasonic probe emits ultrasonic waves to the human body and receives ultrasonic signals reflected by human body tissues. The 002 ultrasound beamformer includes transmit and receive portions. Generating the high voltage pulse signal and the echo signal required for exciting the probe. The received echo signals are sent to a pre-signal amplifier and filter 003, the order of which is determined by the relative magnitudes of the signal and noise. When the out-of-band noise of the received signal is a major contradiction, the noise amplitude is far greater than the signal amplitude, and then the signal needs to enter the filter and then enter the pre-amplifier. When the received signal and noise amplitude are small, the signal should pass through the pre-amplifier and then the filter. The amplified and filtered signal is converted from an analog signal to a digital signal by the a/D conversion module 004. After being converted into the digital signal, the digital signal directly enters the GPU 005 provided with the temperature interval classification model. The output is a temperature value within the zone.
The foregoing is merely a preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the claims of the present invention.
Claims (5)
1. An ultrasound apparatus for use with a method of thermometry of tissue using ultrasound radio frequency signals in combination with machine learning, the apparatus comprising: the ultrasonic device comprises an ultrasonic probe, an ultrasonic beam former, a preamplifier and filter, an A/D conversion module and a GPU; the ultrasonic probe transmits ultrasonic waves to the tissue to be detected and receives ultrasonic signals reflected by the tissue; the ultrasonic beam former comprises a transmitting part and a receiving part, wherein the transmitting part generates high-voltage pulse signals required by exciting the ultrasonic probe, and the receiving part receives echo signals reflected from the ultrasonic probe; the received echo signals are sent to a pre-amplifier and a filter; the amplified and filtered signals are converted into digital signals by an A/D conversion module; directly entering the GPU after being converted into the digital signal, and outputting the digital signal as a temperature value of the tissue to be detected;
the method for measuring the temperature of the tissue by combining ultrasonic radio frequency signals with machine learning comprises the following steps:
(1) The three-dimensional concept of an ablation area is obtained through multi-section scanning, and a three-dimensional model of the ablation area is built according to different mathematical algorithm models to arrange an ablation needle;
(2) Setting multi-path temperature measuring needles on the isolated tissue at different distances or different angles relative to the position of the ablation needle;
(3) Obtaining temperature T of non-ablated ex-vivo tissue 0 And at this time the radio frequency signal RF 0 The acquisition frequency is N frames/second; the in-vitro tissue is ablated for T seconds, and the temperature is obtained to be T j Radio frequency signal RF j At this time, the temperature of the isolated tissue changes (T j -T 0 ) The radio frequency signal at each frame is reflectedIn (a) and (b);
(4) Simulating according to the data of the temperature measuring needles of each passage and the Pennes approximate biological heat equation to obtain tissue simulation temperatures in different areas at different times; according to the sampling format of the radio frequency signals, each frame of radio frequency signal data can be converted into a radio frequency signal matrix of p x q, wherein p is the number of scanning lines, and q is the number of sampling points;
(5) Obtaining the tissue temperature of each frame in different areas according to the simulation in the step (4), namely, the tissue simulation temperature of different areas in different time, dividing the tissue simulation temperature into a plurality of sections according to the temperature range, finding out radio frequency signal matrixes of the corresponding sections in the corresponding frames, and requiring the size of each matrix to be consistent;
(6) Inputting the data of the radio frequency signal matrix in the step (5) and the corresponding temperature interval into a machine learning model for training;
(7) And (3) acquiring radio frequency signals of the tissue to be detected, inputting the radio frequency signals into the model trained in the step (6), and finally obtaining temperature information of the tissue to be detected.
2. The ultrasonic apparatus according to claim 1, wherein the step (7) is to make a temperature map layer based on different temperature information, superimposed and displayed on the whole area; and marking different temperature areas with different colors, and marking an isotherm area of a key temperature point for temperature prompt.
3. The ultrasound device of claim 1 or 2, wherein the Pennes approximates the biological heat equation:
wherein ρ is the density (kg/m) 3 ) C is the specific heat capacity (W/m 3 K), K is the thermal conductivity (W/mK), T (x, y, z, T) is the tissue temperature, Q blood For heat transfer generated during blood perfusion, Q met For heat generated by metabolism, Q e For energy change caused by water evaporation, Q absorb Absorbing power of laser, microwave or radio frequency for tissue.
4. The ultrasound apparatus according to claim 1 or 2, wherein in the step (4), the arrangement of the radio frequency signal matrix conforms to the arrangement of pixels of ultrasound imaging.
5. The ultrasound device of claim 1 or 2, wherein the machine learning model comprises a supervised model, an unsupervised model, or a probabilistic model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111084117.9A CN113768611B (en) | 2021-09-15 | 2021-09-15 | Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111084117.9A CN113768611B (en) | 2021-09-15 | 2021-09-15 | Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113768611A CN113768611A (en) | 2021-12-10 |
| CN113768611B true CN113768611B (en) | 2023-09-29 |
Family
ID=78844414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111084117.9A Active CN113768611B (en) | 2021-09-15 | 2021-09-15 | Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113768611B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116798638B (en) * | 2023-08-26 | 2023-11-03 | 南京诺源医疗器械有限公司 | Three-dimensional temperature field simulation method for microwave ablation of liver tumor |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103381097A (en) * | 2012-05-02 | 2013-11-06 | 美国西门子医疗解决公司 | Ultrasound for therapy control or monitoring |
| CN105877779A (en) * | 2014-04-01 | 2016-08-24 | 美国西门子医疗解决公司 | Thermal Therapy Ablation Detection With Ultrasound |
| CN109171998A (en) * | 2018-10-22 | 2019-01-11 | 西安交通大学 | Heating ablation region recognition monitoring imaging method and system based on ultrasonic deep learning |
| CN110325137A (en) * | 2017-02-23 | 2019-10-11 | 尹诺伯拉狄夫设计公司 | System and method for melting Stateful Inspection and custom ablated forming |
| CN111050679A (en) * | 2017-08-31 | 2020-04-21 | 柯惠有限合伙公司 | System and method for sensing temperature at different locations of a microwave antenna using multiple fiber optic sensors |
| CN112146761A (en) * | 2020-08-14 | 2020-12-29 | 上海数川数据科技有限公司 | Human body temperature measurement compensation method based on machine learning |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7771418B2 (en) * | 2005-03-09 | 2010-08-10 | Sunnybrook Health Sciences Centre | Treatment of diseased tissue using controlled ultrasonic heating |
| US9675821B2 (en) * | 2006-03-14 | 2017-06-13 | Boston Scientific Scimed, Inc. | Device for thermal treatment of tissue and for temperature measurement of tissue providing feedback |
| US7871406B2 (en) * | 2006-08-04 | 2011-01-18 | INTIO, Inc. | Methods for planning and performing thermal ablation |
| US20130123885A1 (en) * | 2010-04-16 | 2013-05-16 | New York University | Apparatus, systems, computer-accessible medium and methods for facilitating radio frequency hyperthermia and thermal contrast in a magnetic resonance imaging system |
| US20200265309A1 (en) * | 2019-02-14 | 2020-08-20 | Covidien Lp | Systems and methods for estimating tissue parameters using surgical devices |
-
2021
- 2021-09-15 CN CN202111084117.9A patent/CN113768611B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103381097A (en) * | 2012-05-02 | 2013-11-06 | 美国西门子医疗解决公司 | Ultrasound for therapy control or monitoring |
| CN105877779A (en) * | 2014-04-01 | 2016-08-24 | 美国西门子医疗解决公司 | Thermal Therapy Ablation Detection With Ultrasound |
| CN110325137A (en) * | 2017-02-23 | 2019-10-11 | 尹诺伯拉狄夫设计公司 | System and method for melting Stateful Inspection and custom ablated forming |
| CN111050679A (en) * | 2017-08-31 | 2020-04-21 | 柯惠有限合伙公司 | System and method for sensing temperature at different locations of a microwave antenna using multiple fiber optic sensors |
| CN109171998A (en) * | 2018-10-22 | 2019-01-11 | 西安交通大学 | Heating ablation region recognition monitoring imaging method and system based on ultrasonic deep learning |
| CN112146761A (en) * | 2020-08-14 | 2020-12-29 | 上海数川数据科技有限公司 | Human body temperature measurement compensation method based on machine learning |
Non-Patent Citations (5)
| Title |
|---|
| 基于回波平移序列的快速三维磁共振温度成像方法;蒋芮 等;《波谱学杂志》;第36卷(第3期);253-260 * |
| 微波热疗组织超声衰减系数的温度相关性研究;吴薇薇;任稆平;吴水才;;《中国医疗设备》(第04期);21-23 * |
| 甲状腺超声诊断与微创介入治疗的现状与展望;徐栋;《中华医学超声杂志(电子版)》;20200131;第17卷(第1期);1-5 * |
| 超声成像与治疗技术进展与趋势;郑海荣 等;《中国科学:生命科学》;第50卷(第11期);1256-1267 * |
| 金属植入物对离体猪肝射频消融的热影响;林振文等;《中国介入影像与治疗学》;20130710;第10卷(第7期);422-425 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113768611A (en) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113749754B (en) | Ultrasonic equipment using method for extracting temperature information in ultrasonic radio frequency signals based on convolutional neural network | |
| CN103153174B (en) | For determining the character determining device of Properties of Objects | |
| CN102858252B (en) | Property determining apparatus for determining a property of an object | |
| RU2577760C2 (en) | Mapping system and method for medical procedures | |
| US11109840B2 (en) | Calibration of ultrasonic elasticity-based lesion-border mapping | |
| CN101090670B (en) | Ultrasonic image-guided tissue-damaging system and method | |
| US20180132722A1 (en) | Method, apparatus and system for complete examination of tissue with hand-held imaging devices | |
| US11382599B2 (en) | Ultrasound imaging system reconstructing an intravascular image using angular positions of a transducer array | |
| US20160100821A1 (en) | Hand-held imaging devices with position and/or orientation sensors for complete examination of tissue | |
| CN101919728B (en) | Warm and hot therapeutic device | |
| KR20050074925A (en) | Prediction and assessment ablation of cardiac tissue | |
| US20120271165A1 (en) | Multi-channel hemispherical ultrasonic wave transmit and receiving detection | |
| US11439308B2 (en) | Methods and systems for thermal monitoring of tissue with an ultrasound imaging system | |
| CN113768611B (en) | Method for measuring temperature of tissue by combining ultrasonic radio frequency signals with machine learning | |
| CN104853805A (en) | Image-guided therapeutic apparatus and method of preparation of an image-guided therapeutic apparatus for treatment of tissue | |
| US9649127B2 (en) | Real time three-dimensional heat-induced echo-strain imaging for monitoring high-intensity acoustic ablation produced by conformal interstitial and external directional ultrasound therapy applicators | |
| Mitri et al. | Prostate cryotherapy monitoring using vibroacoustography: preliminary results of an ex vivo study and technical feasibility | |
| JP2024038018A (en) | Percutaneous catheter system and method for rapid diagnosis of lung disease | |
| Allman et al. | Deep neural networks to remove photoacoustic reflection artifacts in ex vivo and in vivo tissue | |
| CN104822326A (en) | Ultrasonic volume flow measurement for ablation therapy | |
| JP2017164559A (en) | Ultrasonic device | |
| CN110075430A (en) | A kind of ultrasonic cavitation method of real-time and system based on comentropy | |
| Rangraz et al. | Real-time monitoring of high-intensity focused ultrasound thermal therapy using the manifold learning method | |
| CN113855229A (en) | One-stop type vertebral tumor microwave ablation operation simulation method and device | |
| Moradi et al. | A photoacoustic image reconstruction method for point source recovery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |