CN115399909A - Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine - Google Patents
Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine Download PDFInfo
- Publication number
- CN115399909A CN115399909A CN202211054871.2A CN202211054871A CN115399909A CN 115399909 A CN115399909 A CN 115399909A CN 202211054871 A CN202211054871 A CN 202211054871A CN 115399909 A CN115399909 A CN 115399909A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- parameters
- drug delivery
- transdermal drug
- parameter
- 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.)
- Granted
Links
- 238000013271 transdermal drug delivery Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000002474 experimental method Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 27
- 239000013598 vector Substances 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 238000002604 ultrasonography Methods 0.000 claims description 28
- 230000035515 penetration Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 13
- 238000011160 research Methods 0.000 abstract description 6
- 238000012827 research and development Methods 0.000 abstract description 3
- 238000012706 support-vector machine Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 229940079593 drug Drugs 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 230000001225 therapeutic effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012377 drug delivery Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000037317 transdermal delivery Effects 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010579 first pass effect Methods 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- CGIGDMFJXJATDK-UHFFFAOYSA-N indomethacin Chemical compound CC1=C(CC(O)=O)C2=CC(OC)=CC=C2N1C(=O)C1=CC=C(Cl)C=C1 CGIGDMFJXJATDK-UHFFFAOYSA-N 0.000 description 1
- 229960000905 indomethacin Drugs 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000008591 skin barrier function Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001839 systemic circulation Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61D—VETERINARY INSTRUMENTS, IMPLEMENTS, TOOLS, OR METHODS
- A61D7/00—Devices or methods for introducing solid, liquid, or gaseous remedies or other materials into or onto the bodies of animals
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
- G16H40/63—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 for local operation
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Veterinary Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Animal Behavior & Ethology (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Medicinal Preparation (AREA)
Abstract
The invention discloses a method for establishing an ultrasonic parameter model for an ultrasonic transdermal drug delivery machine, and belongs to the technical field of ultrasonic parameter research. Firstly, a plurality of groups of ultrasonic parameters are set according to the existing conditions as input feature vectors of a training set, the result obtained by an experiment is used as an output label of the training set, and the result and the output label are trained through an SVM classifier to obtain a prediction model of the optimal ultrasonic parameters. The invention effectively solves the experimental difficulty under the condition of lacking practical cases, uses the SVM classifier to predict the transdermal effect under different parameters by fewer experiments, greatly saves the early-stage test cost, can more comprehensively analyze the factors influencing the ultrasonic transdermal drug delivery effect by bringing all the parameters into the input characteristic parameters, obtains the parameter prediction model with qualified accuracy rate, and provides guidance for the subsequent research and development of the ultrasonic transdermal drug delivery machine with more reasonable parameters.
Description
Technical Field
The invention relates to the technical field of ultrasonic parameter research, in particular to a method for establishing an ultrasonic parameter model for an ultrasonic transdermal drug delivery machine.
Background
Transdermal administration refers to a method of administering a drug to the surface of the skin such that the drug passes through the skin at a constant rate (or near constant rate) and enters the systemic circulation to produce a systemic or local therapeutic effect. Transdermal administration has many advantages: the drug absorption is not influenced by factors such as pH, food, transport time and the like in the digestive tract; the first pass effect of the liver is avoided; adverse reactions caused by overhigh blood concentration due to too fast absorption are overcome; the drug delivery speed can be continuously controlled, the drug delivery is flexible, and the like. However, the skin has a specific barrier function, which effectively limits the exchange of substances with the external environment and the penetration of foreign compounds. While protecting the human body, the skin barrier also blocks the passage of macromolecular drugs into the human body.
The ultrasonic penetration promotion is a new non-invasive means for effectively enhancing transdermal drug delivery, and has the advantages of no damage to human bodies, simple operation and wide clinical application. However, the sonophoresis has not been uniformly concluded in the action mechanism, and the main stream suggests that factors such as thermal effect, mechanical effect and cavitation effect act together. This makes the parameters affecting the penetration-promoting effect have a mutual and complex relationship, and it is difficult to simply describe the effect of each parameter on the result. For example, tezel et al found that low frequency ultrasound had a better penetration enhancing effect than high frequency ultrasound, asona et al found that the duty cycle was 1:2, the ultrasonic wave has the best effect on promoting the infiltration of the indometacin.
The existing ultrasonic transdermal drug delivery scientific research design usually only aims at qualitative research on several ultrasonic parameters, such as ultrasonic frequency, duty ratio, action time and the like, but the effect under the combined action of more parameters cannot be evaluated. Enterprises or research units engaged in the production of ultrasound-enhanced transdermal drug delivery machines cannot simultaneously have ultrasound equipment with gradually-adjustable functions and containing various parameters, and cannot determine appropriate parameter ranges by customizing a large number of different ultrasound equipment for experiments. Therefore, in order to further improve the ultrasonic transdermal drug delivery efficiency and save the research cost, a strategy optimization method for obtaining a proper parameter prediction model through a proper amount of preliminary experiments under the condition of only having certain experimental parameters is urgently needed.
Disclosure of Invention
The invention aims to provide a method for establishing an ultrasonic parameter model for an ultrasonic transdermal drug delivery machine.
In order to realize the purpose, the invention adopts the following technical scheme: a method of establishing an ultrasound parametric model for an ultrasound transdermal delivery machine, comprising: firstly, a plurality of groups of ultrasonic parameters are set according to the existing conditions as input feature vectors of a training set, the result obtained by an experiment is used as an output label of the training set, and the result and the output label are trained through an SVM classifier to obtain a prediction model of the optimal ultrasonic parameters.
Further, the method for establishing the ultrasonic parameter model for the ultrasonic transdermal drug delivery machine comprises the following steps:
step one, setting experiment parameters: selecting at least M ultrasonic parameters according to the existing actual conditions, setting at least N grades under each selected parameter, and combining the grades into at least N grades M Grouping parameters;
step two, collecting an experimental result: grouping rat experiments of ultrasonic transdermal drug delivery according to the parameters in the step one, recording transdermal results of all depths obtained by the experiments, and randomly dividing experimental groups into a training set and a testing set;
step three, training an SVM classifier: taking the parameters selected in the step one as input feature vectors of a training set, taking the results in the step two as output labels of the training set, and training through an SVM classifier to obtain a parameter prediction model under each depth;
step four, verifying the accuracy of the prediction model: and verifying the accuracy of each prediction model by using a test set: if the accuracy is higher than 85%, the model is the optimal ultrasonic parameter model for transdermal drug delivery at the corresponding depth; and if the accuracy is lower than 85%, judging that the model is invalid.
Further, in the method for establishing the ultrasound parameter model for the ultrasound transdermal drug delivery machine, in the first step, the number M of the ultrasound parameters and the parameter step N are positive integers and the following conditions are satisfied: m is more than or equal to 3, N is more than or equal to 2; the units of the selected parameters need to be uniformly converted into international standard units.
Further, the method for establishing the ultrasonic parameter model for the ultrasonic transdermal drug delivery machine comprises the following specific steps: and (4) carrying out ultrasonic transdermal drug delivery rat experiments with consistent operation according to the parameter groups in the step one, repeating each group of parameters for three times, and recording the picture of the deepest fluorescence permeation area of the skin cross section of the rat irradiated by the ultrasonic through a fluorescence microscope and a camera. For the analysis of the picture, from the position of the picture showing the skin surface downward (i.e., in the depth direction), the total E of the fluorescence intensity per 0.1mm deep rectangle (5 mm in width) was recorded in order i (i =1,2, \ 8230;, n) while recording the sum E of the fluorescence intensities in equally sized rectangles at a distance of 3mm under the skin 0 As background, a tag vector is obtained by the following equation:
E i ≥5×E 0 ;
if the formula is met, recording the ith element of the label vector as 1, and indicating that the transdermal depth can reach i multiplied by 0.1mm under the parameters of the group; if the skin penetration depth does not meet the parameters of the group, the skin penetration depth is marked as 0, which indicates that the skin penetration depth does not reach i multiplied by 0.1mm under the parameters of the group; this results in a column of label vectors of length n.
Further, in the method for establishing the ultrasonic parameter model for the ultrasonic transdermal drug delivery machine, in the third step, the feature vectors input into each group take n elements in the label vectors as label results in turn to participate in n times of training, and finally n prediction models corresponding to different depths are obtained.
Further, in the method for establishing an ultrasound parameter model for an ultrasound transdermal drug delivery machine, in the fourth step, the elements in the test set are not less than 20% of the training set.
The invention has the advantages that: the experimental difficulty under the condition of lacking actual cases is effectively solved, the transdermal effects under different parameters are predicted by using an SVM classifier through fewer experiments, the early-stage testing cost is greatly saved, the factors influencing the ultrasonic transdermal administration effect can be more comprehensively analyzed by bringing all parameters into input characteristic parameters, a parameter prediction model with qualified accuracy is obtained, and reliable guidance is provided for the ultrasonic transdermal administration equipment with more reasonable parameters in subsequent research and development.
Drawings
FIG. 1 is a schematic flow chart of a method for establishing an ultrasound parameter model for an ultrasound transdermal drug delivery machine according to the present invention.
FIG. 2 is a photograph of fluorescence permeation of skin cross section of the area irradiated by ultrasound in a rat.
Description of reference numerals: a rat skin surface 1, a collected fluorescence intensity calculation region 2 and a background fluorescence intensity calculation region 3.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments.
The invention is described in detail below with reference to the figures and specific embodiments.
Example 1: the invention relates to a method for establishing an ultrasonic parameter model for an ultrasonic transdermal drug delivery machine, which selects an ultrasonic transdermal drug delivery prototype in the initial development stage of a certain enterprise, and the adjustable parameters provided by the ultrasonic transdermal drug delivery machine comprise the following three parameters: ultrasonic frequency, effective pulse width, duty cycle, all have several gears (at least 2 gears) that can supply to adjust under each parameter. If different combinations of all gears under all parameters are tested, the experiment cost is overlarge, the period is overlong, and therefore a parameter prediction model about the transdermal effect needs to be obtained through a small amount of early experiments, and a more reasonable parameter range is determined from the model for subsequent research and development.
As shown in fig. 1, the method comprises the following steps: step one, setting experiment parameters. Firstly, according to the existing conditions, with reference to table 1, 3 ultrasound parameters of ultrasound frequency, effective pulse width and duty ratio are used as input feature vectors of a training set, and 2 steps are set under each parameter, so that 8 parameter groups are formed by permutation and combination.
The units of the selected parameters need to be uniformly converted into international standard units so as to ensure the uniformity of the input parameters. In the present embodiment, the ultrasonic frequency (MHz), the effective pulse width (us), and the duty ratio (%).
And step two, collecting an experimental result. The ultrasonic transdermal drug delivery rat experiments with consistent operation were carried out according to the parameter groups in table 1, and each group of parameters was repeated three times for 24 groups of experiments. And recording the picture of the deepest fluorescence penetration of the skin cross section of the rat in the ultrasonic irradiation area by a fluorescence microscope and a camera. Referring to FIG. 2, the images were analyzed, from the image showing the skin surface 1 of the rat downward (i.e., in the depth direction), and the total E of the fluorescence intensities in the collected fluorescence intensity calculation region 2 (5 mm in width) per 0.1mm deep rectangular frame was recorded in order i (i =1,2, \8230;, 10), a fluorescent transdermal effect within 1mm from the skin surface. The sum E of the fluorescence intensities in the same size rectangular frame 3 at a distance of 3mm below the skin is recorded simultaneously 0 As a background, i.e., a background fluorescence intensity calculation region 3, a label vector is obtained by the following formula: e i ≥5×E 0 ;
If the formula is met, recording the ith element of the label vector as 1, and indicating that the transdermal depth can reach i multiplied by 0.1mm under the parameters of the group; failure to meet this criteria is noted as 0, indicating failure of the skin penetration depth to reach i × 0.1mm under this set of parameters. This results in a column of label vectors of length n. The results of the transdermal experiments under each parameter group are reported in table 1 (only one data set out of three repeated experiments is shown for purposes of example).
Table 1:
in combination with Table 2, E 1 ~E 10 The sum of fluorescence intensities corresponding to 10 depth rectangular boxes under the conditions of the 1 st parameter set, E 0 The sum of the background fluorescence intensity corresponding to a rectangular frame 3mm away from the skin. The label vector calculated by the above formula is: 1100000000, it means the transdermal depth of the group reaches0.2mm is used.
Table 2:
recording symbols | Sum of fluorescence | Recording symbol | Sum of fluorescence |
E 0 | 4.31 | E 6 | 7.54 |
E 1 | 54.85 | E 7 | 4.50 |
E 2 | 29.62 | E 8 | 4.32 |
E 3 | 20.04 | E 9 | 4.35 |
E 4 | 18.22 | E 10 | 4.31 |
E 5 | 12.01 |
。
Randomly extracting 5 groups of experiment parameter conditions and results in 24 groups of experiments as a test set, and using the rest 19 groups of experiment parameter conditions and results as a training set.
And step three, training an SVM classifier. And (4) taking the parameters selected in the step one as input feature vectors of a training set, taking the results in the step two as output labels of the training set, and training by an SVM (support vector machine) classifier to obtain a parameter prediction model under each depth. In practical implementation, the present embodiment uses multiple kernel functions and finally obtains different prediction models, and here, only the case where a linear kernel is used as a kernel function is shown as an example.
Each group of input feature vectors takes 10 elements in the label vector as a label result to participate in 10 times of training, and finally 10 prediction models corresponding to different depths are obtained.
And step four, verifying the accuracy of the prediction model. And verifying the accuracy of each prediction model by using a test set: if the accuracy is higher than 85%, the model is the optimal ultrasonic parameter model for transdermal drug delivery at the corresponding depth; and if the accuracy is lower than 85%, judging that the model is invalid. In this embodiment, the accuracy of the 10 prediction models is greater than 90%, so that the 10 models can be used as the prediction model of the transdermal drug delivery optimal ultrasound parameter.
After obtaining the model, the researchers of the ultrasonic transdermal drug delivery machine may input different gear positions of each parameter into the prediction model, and at this time, a parameter combination without previous experiments may be included, for example: the ultrasonic frequency is 2MHz, the effective pulse width is 60us, and the duty cycle is 30%. After input, the feedback results output by the 10 prediction models are respectively as follows: 1111111000, the transdermal depth of which is predicted to be 0.7mm. This result is superior to the previous result, so that the combination of parameters and their vicinity should be fully referenced in the subsequent prototype development process.
Example 2: the same ultrasonic transdermal delivery machine as in example 1 was used, the ultrasonic frequencies being chosen: 1MHz, 1.5MHz, effective pulse width is 20us, 25us, duty cycle is: 50% and 60% are arranged and combined together to form 8 parameter combinations, and the parameter model establishing process consistent with that in the embodiment 1 is carried out.
After 10 prediction models with corresponding depths are obtained, verification of a test set shows that the accuracy of the 3 rd prediction model is 80%, the accuracy of the 7 th prediction model is 75% and is lower than 85%, so that the prediction model is judged to be invalid, and parameters and gears thereof need to be selected again and experiments need to be carried out again.
The units used in the above examples are shown in Table 3.
Table 3:
frequency of ultrasonic emission | MHz |
Ultrasonic pulse repetition frequency | Hz |
Pulse width | ms |
Duration of treatment | s |
Ultrasonic sound intensity | W/cm 2 |
Ultrasonic sound pressure | MPa |
Length of therapeutic frame | mm |
Width of therapeutic frame | mm |
Longitudinal moving speed of treatment frame | mm/s |
Transverse moving speed of treatment frame | mm/s |
Focus position of therapeutic frame | mm |
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the scope of the present invention in any way, and all technical solutions obtained by using equivalent substitution methods fall within the scope of the present invention.
Claims (6)
1. A method for establishing an ultrasonic parameter model for an ultrasonic transdermal drug delivery machine is characterized by comprising the following steps: firstly, a plurality of groups of ultrasonic parameters are set according to the existing conditions as input feature vectors of a training set, the result obtained by an experiment is used as an output label of the training set, and the result and the output label are trained through an SVM classifier to obtain a prediction model of the optimal ultrasonic parameters.
2. The method of establishing an ultrasound parametric model for an ultrasound transdermal drug delivery machine according to claim 1, wherein: the method comprises the following steps:
step one, setting experiment parameters: selecting at least M ultrasonic parameters according to the existing actual conditions, setting at least N grades under each selected parameter, and combining the selected parameters into at least N grades M Grouping parameters;
step two, collecting an experimental result: grouping rat experiments of ultrasonic transdermal drug delivery according to the parameters in the step one, recording transdermal results of various depths obtained by the experiments, and randomly dividing the experimental groups into a training set and a testing set;
step three, training an SVM classifier: taking the parameters selected in the step one as input feature vectors of a training set, taking the results in the step two as output labels of the training set, and training through an SVM classifier to obtain a parameter prediction model under each depth;
step four, verifying the accuracy of the prediction model: and verifying the accuracy of each prediction model by using a test set: if the accuracy is higher than 85%, the model is the optimal ultrasonic parameter model for transdermal drug delivery at the corresponding depth; and if the accuracy rate is lower than 85%, judging that the model is invalid.
3. The method of establishing an ultrasound parametric model for an ultrasound transdermal drug delivery machine according to claim 2, wherein: in the first step, the number M of ultrasonic parameters and the parameter grading N are positive integers and need to satisfy the following conditions: m is more than or equal to 3, N is more than or equal to 2; the units of the selected parameters need to be uniformly converted into international standard units.
4. The method of establishing an ultrasound parametric model for an ultrasound transdermal drug delivery machine according to claim 2, wherein: the second step comprises the following specific steps: performing ultrasonic transdermal drug delivery rat experiments with consistent operation according to the parameter groups in the step one, repeating each group of parameters for three times, and recording the picture of the deepest fluorescence permeation area of the skin cross section of the rat irradiated by ultrasonic through a fluorescence microscope and a camera; for the analysis of the picture, from the position of the picture showing the skin surface downward (i.e., in the depth direction), the total E of the fluorescence intensity per 0.1mm deep rectangle (5 mm in width) was recorded in order i (i =1,2, \ 8230;, n) while recording the total fluorescence intensity in a equally sized rectangle at a distance of 3mm below the skinAnd E 0 As background, a tag vector is obtained by the following equation:
E i ≥5×E 0 ;
if the formula is met, recording the ith element of the label vector as 1, and indicating that the transdermal depth can reach i multiplied by 0.1mm under the parameters of the group; if the skin penetration depth is not met, the skin penetration depth is marked as 0, and the skin penetration depth under the parameters of the group cannot reach i multiplied by 0.1mm; this results in a column of label vectors of length n.
5. The method of establishing an ultrasound parametric model for an ultrasound transdermal drug delivery machine according to claim 2, wherein: and in the third step, each group of input feature vectors take n elements in the label vectors as label results to participate in n times of training, and finally, n prediction models corresponding to different depths are obtained.
6. A method of establishing an ultrasound parametric model for an ultrasound transdermal drug delivery machine according to claim 2 or 4, wherein: and in the fourth step, the elements in the test set are not less than 20% of the training set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211054871.2A CN115399909B (en) | 2022-08-31 | 2022-08-31 | Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211054871.2A CN115399909B (en) | 2022-08-31 | 2022-08-31 | Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115399909A true CN115399909A (en) | 2022-11-29 |
CN115399909B CN115399909B (en) | 2024-07-23 |
Family
ID=84163958
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211054871.2A Active CN115399909B (en) | 2022-08-31 | 2022-08-31 | Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115399909B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102279906A (en) * | 2010-06-29 | 2011-12-14 | 上海聚类生物科技有限公司 | Method for improving accuracy rate of SVM modeling |
WO2016183348A1 (en) * | 2015-05-12 | 2016-11-17 | The Johns Hopkins University | Methods, systems and devices comprising support vector machine for regulatory sequence features |
WO2019105105A1 (en) * | 2017-11-28 | 2019-06-06 | 深圳市岩尚科技有限公司 | Classification prediction data processing method for photoplethysmography-based blood pressure measurement device |
CN111462116A (en) * | 2020-05-13 | 2020-07-28 | 吉林大学第一医院 | Multimodal parameter model optimization fusion method based on imagery omics characteristics |
CN112668382A (en) * | 2020-07-21 | 2021-04-16 | 北京工业大学 | Support vector machine-based ultrasonic signal identification method for defects in steel ingot |
CN112971708A (en) * | 2019-12-12 | 2021-06-18 | 上海交通大学 | Bilirubin noninvasive detection device based on skin fluorescence spectrum analysis |
-
2022
- 2022-08-31 CN CN202211054871.2A patent/CN115399909B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102279906A (en) * | 2010-06-29 | 2011-12-14 | 上海聚类生物科技有限公司 | Method for improving accuracy rate of SVM modeling |
WO2016183348A1 (en) * | 2015-05-12 | 2016-11-17 | The Johns Hopkins University | Methods, systems and devices comprising support vector machine for regulatory sequence features |
WO2019105105A1 (en) * | 2017-11-28 | 2019-06-06 | 深圳市岩尚科技有限公司 | Classification prediction data processing method for photoplethysmography-based blood pressure measurement device |
CN112971708A (en) * | 2019-12-12 | 2021-06-18 | 上海交通大学 | Bilirubin noninvasive detection device based on skin fluorescence spectrum analysis |
CN111462116A (en) * | 2020-05-13 | 2020-07-28 | 吉林大学第一医院 | Multimodal parameter model optimization fusion method based on imagery omics characteristics |
CN112668382A (en) * | 2020-07-21 | 2021-04-16 | 北京工业大学 | Support vector machine-based ultrasonic signal identification method for defects in steel ingot |
Also Published As
Publication number | Publication date |
---|---|
CN115399909B (en) | 2024-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10772646B2 (en) | Method for controlling histotripsy using confocal fundamental and harmonic superposition combined with hundred-microsecond ultrasound pulses | |
WO2021036897A1 (en) | Photoacoustic imaging system and method | |
Bimbard et al. | Multi-scale mapping along the auditory hierarchy using high-resolution functional UltraSound in the awake ferret | |
US20130090579A1 (en) | Pulsed Cavitational Therapeutic Ultrasound With Dithering | |
DE102018218751A1 (en) | MACHINE-BASED WORKFLOW IN ULTRASONIC IMAGING | |
Vlaisavljevich et al. | Effects of f-number on the histotripsy intrinsic threshold and cavitation bubble cloud behavior | |
US11049238B2 (en) | Systems and methods for prediction of tumor response to chemotherapy using pre-treatment quantitative ultrasound parameters | |
CN107753062A (en) | TCD,transcranial Doppler cerebral angiography super-resolution imaging method based on Markov chain Monte-Carlo multi-target tracking | |
RU2013108800A (en) | IMPROVING FILTER FOR A SPECIFIC AUTHORITY FOR RELIABLE SEGMENTATION OF MEDICAL IMAGES | |
US20070167755A1 (en) | Methods of monitoring cellular death using low frequency ultrasound | |
Somwanshi et al. | An efficient brain tumor detection from MRI images using entropy measures | |
CN1891162A (en) | Ultrasonic diagnostic equipment | |
CN115399909A (en) | Method for establishing ultrasonic parameter model for ultrasonic transdermal drug delivery machine | |
CN101036596A (en) | Phantom model sport platform and method for sport simulating | |
US11497476B2 (en) | Systems and methods for prediction of tumor treatment response to using texture derivatives computed from quantitative ultrasound parameters | |
Soni et al. | Kidney stone recognition and extraction using directional emboss & SVM from computed tomography images | |
CN101051384A (en) | Self adaptive reinforced digital image reducing blood vessle image | |
KR101221824B1 (en) | Apparatus for Treatment and Driving Method Thereof | |
DE10100441A1 (en) | Monitoring brain activity in a patient by application of a stimulus and monitoring of the resultant activity using magnetic resonance imaging so that brain activity can be highly resolved | |
Jordan et al. | Focused ultrasound stimulation of an ex-vivo Aplysia abdominal ganglion preparation | |
DE60304619T2 (en) | Device and method for bioanalysis by means of probe arrays | |
US20080247625A1 (en) | Method and System for Leading Macromolecule Substances into Living Target Cells | |
He et al. | Longitudinal neural and vascular recovery following ultraflexible neural electrode implantation in aged mice | |
Jacobson et al. | A mechanistic study identifying improved technology critical metal delamination from printed circuit boards at lower power sonications in a deep eutectic solvent | |
Liu et al. | Artifact suppression for passive cavitation imaging using U-Net CNNs with uncertainty quantification |
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 |